From 8b810918d59781116794a6679999afdc76b857ef Mon Sep 17 00:00:00 2001 From: darindf Date: Mon, 30 Apr 2018 22:43:27 -0700 Subject: [PATCH 01/40] Add `dtype` argument for `chunkize_serial`, fix `LdaModel` (#2027) * Changed to datatype int for distributed * Updated * Use dask instead of pyro * Revert "Use dask instead of pyro" This reverts commit cb4900f092e9d4eb29e8b51aa8403bcdf2529fcc. * Removed space after paren --- gensim/models/ldamodel.py | 3 ++- gensim/utils.py | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py index 6d37ac0f7d..25698edb50 100755 --- a/gensim/models/ldamodel.py +++ b/gensim/models/ldamodel.py @@ -698,7 +698,8 @@ def rho(): dirty = False reallen = 0 - for chunk_no, chunk in enumerate(utils.grouper(corpus, chunksize, as_numpy=chunks_as_numpy)): + chunks = utils.grouper(corpus, chunksize, as_numpy=chunks_as_numpy, dtype=self.dtype) + for chunk_no, chunk in enumerate(chunks): reallen += len(chunk) # keep track of how many documents we've processed so far if eval_every and ((reallen == lencorpus) or ((chunk_no + 1) % (eval_every * self.numworkers) == 0)): diff --git a/gensim/utils.py b/gensim/utils.py index f6e5c4fdf3..6d2823c652 100644 --- a/gensim/utils.py +++ b/gensim/utils.py @@ -1119,7 +1119,7 @@ def substitute_entity(match): return RE_HTML_ENTITY.sub(substitute_entity, text) -def chunkize_serial(iterable, chunksize, as_numpy=False): +def chunkize_serial(iterable, chunksize, as_numpy=False, dtype=np.float32): """Give elements from the iterable in `chunksize`-ed lists. The last returned element may be smaller (if length of collection is not divisible by `chunksize`). @@ -1148,7 +1148,7 @@ def chunkize_serial(iterable, chunksize, as_numpy=False): if as_numpy: # convert each document to a 2d numpy array (~6x faster when transmitting # chunk data over the wire, in Pyro) - wrapped_chunk = [[np.array(doc) for doc in itertools.islice(it, int(chunksize))]] + wrapped_chunk = [[np.array(doc, dtype=dtype) for doc in itertools.islice(it, int(chunksize))]] else: wrapped_chunk = [list(itertools.islice(it, int(chunksize)))] if not wrapped_chunk[0]: From 0f42adb7fe66e1a7193ea14374ed11175e746b3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Wed, 30 May 2018 10:34:59 +0200 Subject: [PATCH 02/40] fix logging formatting in downloader --- gensim/downloader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/downloader.py b/gensim/downloader.py index 8a787207f2..f3672ead01 100644 --- a/gensim/downloader.py +++ b/gensim/downloader.py @@ -420,7 +420,7 @@ def load(name, return_path=False): if __name__ == '__main__': logging.basicConfig( - format='%(asctime)s :%(name)s :%(levelname)s :%(message)s', stream=sys.stdout, level=logging.INFO + format='%(asctime)s : %(name)s : %(levelname)s : %(message)s', stream=sys.stdout, level=logging.INFO ) parser = argparse.ArgumentParser( description="Gensim console API", From 500f99c2b44f48bd58a08b29b2e2bf1121edc9f7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Wed, 30 May 2018 10:58:53 +0200 Subject: [PATCH 03/40] fixes to HashDictionary --- gensim/corpora/hashdictionary.py | 95 ++++++++++++++++---------------- 1 file changed, 47 insertions(+), 48 deletions(-) diff --git a/gensim/corpora/hashdictionary.py b/gensim/corpora/hashdictionary.py index 79065e5ead..7c05063a77 100644 --- a/gensim/corpora/hashdictionary.py +++ b/gensim/corpora/hashdictionary.py @@ -5,13 +5,15 @@ # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""This module implements the "hashing trick" [1]_ -- a mapping between words and their integer ids -using a fixed and static mapping. +""" +This module implements the "hashing trick" [1]_ -- a mapping between words and their integer ids +using a fixed, static mapping (hash function). Notes ----- + The static mapping has a constant memory footprint, regardless of the number of word-types (features) in your corpus, -so it's suitable for processing extremely large corpora. The ids are computed as `hash(word) % id_range`, +so it's suitable for processing extremely large corpora. The ids are computed as `hash(word) %% id_range`, where `hash` is a user-configurable function (`zlib.adler32` by default). Advantages: @@ -19,13 +21,11 @@ * New words can be represented immediately, without an extra pass through the corpus to collect all the ids first. * Can be used with non-repeatable (once-only) streams of documents. -* All tokens will be used (not only that you see in documents), typical problem - for :class:`~gensim.corpora.dictionary.Dictionary`. - +* Able to represent all tokens (not only those present in training documents) Disadvantages: -* Words may map to the same id, causing hash collisions. The word <-> id mapping is no longer a bijection. +* Multiple words may map to the same id, causing hash collisions. The word <-> id mapping is no longer a bijection. References @@ -48,21 +48,23 @@ class HashDictionary(utils.SaveLoad, dict): - """Encapsulates the mapping between normalized words and their integer ids. + """ + Mapping between words and their integer ids, using a hashing function. Notes ----- Unlike :class:`~gensim.corpora.dictionary.Dictionary`, building a :class:`~gensim.corpora.hashdictionary.HashDictionary` before using it **isn't a necessary step**. - The documents can be computed immediately, from an uninitialized - :class:`~gensim.corpora.hashdictionary.HashDictionary` without seeing the rest of the corpus first. + + You can start converting words to ids immediately, without training on a corpus. Examples -------- >>> from gensim.corpora import HashDictionary >>> + >>> dct = HashDictionary(debug=False) # needs no training corpus! + >>> >>> texts = [['human', 'interface', 'computer']] - >>> dct = HashDictionary(texts) >>> dct.doc2bow(texts[0]) [(10608, 1), (12466, 1), (31002, 1)] @@ -73,14 +75,14 @@ def __init__(self, documents=None, id_range=32000, myhash=zlib.adler32, debug=Tr Parameters ---------- documents : iterable of iterable of str - Iterable of documents, if given - use them to initialization. + Iterable of documents. If given, used to collect additional corpus statistics. HashDictionary can work without these statistics (optional parameter). id_range : int, optional - Number of hash-values in table, used as `id = myhash(key) % id_range`. + Number of hash-values in table, used as `id = myhash(key) %% id_range`. myhash : function - Hash function, should support interface myhash(str) -> int, used `zlib.adler32` by default. + Hash function, should support interface `myhash(str) -> int`, uses `zlib.adler32` by default. debug : bool - If True - store raw tokens mapping (as str <-> id). - If you find yourself running out of memory (or not sure that you really need raw tokens), set `debug=False`. + If True - store which tokens have mapped to a given id. **Will use a lot of RAM**. + If you find yourself running out of memory (or not sure that you really need raw tokens), keep `debug=False`. """ self.myhash = myhash # hash fnc: string->integer @@ -104,9 +106,7 @@ def __init__(self, documents=None, id_range=32000, myhash=zlib.adler32, debug=Tr def __getitem__(self, tokenid): """Get all words that have mapped to the given id so far, as a set. - Warnings - -------- - Works only if `debug=True`. + Works only if you initialized your `HashDictionary` object with `debug=True`. Parameters ---------- @@ -116,14 +116,14 @@ def __getitem__(self, tokenid): Return ------ set of str - Set of all corresponding words. + Set of all words that have mapped to this id. """ return self.id2token.get(tokenid, set()) def restricted_hash(self, token): """Calculate id of the given token. - Also keep track of what words were mapped to what ids, for debugging reasons. + Also keep track of what words were mapped to what ids, if `debug=True` was set in the constructor. Parameters ---------- @@ -158,7 +158,8 @@ def from_documents(*args, **kwargs): return HashDictionary(*args, **kwargs) def add_documents(self, documents): - """Build dictionary from a collection of documents. + """Collect corpus statistics from a corpus. Useful only if `debug=True`, to build + the reverse `id=>set(words)` mapping. Notes ----- @@ -173,11 +174,12 @@ def add_documents(self, documents): -------- >>> from gensim.corpora import HashDictionary >>> + >>> dct = HashDictionary(debug=True) # needs no training corpus! + >>> >>> corpus = [["máma", "mele", "maso"], ["ema", "má", "máma"]] - >>> dct = HashDictionary(corpus) >>> "sparta" in dct.token2id False - >>> dct.add_documents([["this","is","sparta"],["just","joking"]]) # add more documents in dictionary + >>> dct.add_documents([["this", "is", "sparta"], ["just", "joking"]]) >>> "sparta" in dct.token2id True @@ -192,43 +194,39 @@ def add_documents(self, documents): ) def doc2bow(self, document, allow_update=False, return_missing=False): - """Convert `document` into the bag-of-words format, like [(1, 4), (150, 1), (2005, 2)]. + """Convert a sequence of words `document` into the bag-of-words format of + `[(word_id, word_count)]` (e.g. `[(1, 4), (150, 1), (2005, 2)]`). Notes ----- - Each word is assumed to be a **tokenized and normalized** utf-8 encoded string. No further preprocessing - is done on the words in `document` (apply tokenization, stemming etc) before calling this method. + Each word is assumed to be a **tokenized and normalized** string. No further preprocessing + is done on the words in `document`: you have to apply tokenization, stemming etc before calling this method. - If `allow_update` or `self.allow_update` is set, then also update dictionary in the process: update overall + If `allow_update` or `self.allow_update` is set, then also update the dictionary in the process: update overall corpus statistics and document frequencies. For each id appearing in this document, increase its document frequency (`self.dfs`) by one. Parameters ---------- - document : list of str - Is a list of tokens = **tokenized and normalized** strings (either utf8 or unicode). + document : sequence of str + A sequence of word tokens = **tokenized and normalized** strings. allow_update : bool, optional - If True - update dictionary in the process. - return_missing : bool, optional - Show token_count for missing words. HAVE NO SENSE FOR THIS CLASS, BECAUSE WE USING HASHING-TRICK. + If True - update corpus statistics and if `debug=True`, also the reverse id=>word mapping. + return_missing : bool + Not used. Only here for compatibility with the Dictionary class. Return ------ list of (int, int) Document in Bag-of-words (BoW) format. - list of (int, int), dict - If `return_missing=True`, return document in Bag-of-words (BoW) format + empty dictionary. Examples -------- >>> from gensim.corpora import HashDictionary >>> - >>> corpus = [["máma", "mele", "maso"], ["ema", "má", "máma"]] - >>> dct = HashDictionary(corpus) - >>> dct.doc2bow(["this","is","máma"]) + >>> dct = HashDictionary() + >>> dct.doc2bow(["this", "is", "máma"]) [(1721, 1), (5280, 1), (22493, 1)] - >>> dct.doc2bow(["this","is","máma"], return_missing=True) - ([(1721, 1), (5280, 1), (22493, 1)], {}) """ result = {} @@ -260,7 +258,11 @@ def doc2bow(self, document, allow_update=False, return_missing=False): return result def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): - """Filter tokens in dictionary by frequency. + """Filter tokens in the debug dictionary by their frequency. Only makes sense when `debug=True`. + + Since :class:`~gensim.corpora.hashdictionary.HashDictionary` id range is fixed and doesn't depend on the number + of tokens seen, this doesn't really "remove" anything. + It only clears some supplementary statistics, for easier debugging and a smaller RAM footprint. Parameters ---------- @@ -280,16 +282,13 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): #. More than `no_above` documents (fraction of total corpus size, **not absolute number**). #. After (1) and (2), keep only the first `keep_n` most frequent tokens (or keep all if `None`). - Since :class:`~gensim.corpora.hashdictionary.HashDictionary` id range is fixed and doesn't depend on the number - of tokens seen, this doesn't really "remove" anything. - It only clears some supplementary statistics, for easier debugging and a smaller RAM footprint. - Examples -------- >>> from gensim.corpora import HashDictionary >>> + >>> dct = HashDictionary(debug=True) + >>> >>> corpus = [["máma", "mele", "maso"], ["ema", "má", "máma"]] - >>> dct = HashDictionary(corpus) >>> dct.filter_extremes(no_below=1, no_above=0.5, keep_n=1) >>> print dct.token2id {'maso': 15025} @@ -314,7 +313,7 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): ) def save_as_text(self, fname): - """Save this HashDictionary to a text file. + """Save the debug token=>id mapping to a text file. Only makes sense when `debug=True`, for debugging. Parameters ---------- @@ -337,7 +336,7 @@ def save_as_text(self, fname): >>> data.save_as_text(get_tmpfile("dictionary_in_text_format")) """ - logger.info("saving HashDictionary mapping to %s" % fname) + logger.info("saving %s mapping to %s" % (self, fname)) with utils.smart_open(fname, 'wb') as fout: for tokenid in self.keys(): words = sorted(self[tokenid]) From ba6146155692fe0adde21c79eba64c40fc25577c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Wed, 30 May 2018 11:47:08 +0200 Subject: [PATCH 04/40] more fixes to broken formatting --- gensim/corpora/hashdictionary.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/gensim/corpora/hashdictionary.py b/gensim/corpora/hashdictionary.py index 7c05063a77..4f57b83071 100644 --- a/gensim/corpora/hashdictionary.py +++ b/gensim/corpora/hashdictionary.py @@ -30,6 +30,7 @@ References ---------- + .. [1] http://en.wikipedia.org/wiki/Hashing-Trick """ @@ -53,6 +54,7 @@ class HashDictionary(utils.SaveLoad, dict): Notes ----- + Unlike :class:`~gensim.corpora.dictionary.Dictionary`, building a :class:`~gensim.corpora.hashdictionary.HashDictionary` before using it **isn't a necessary step**. @@ -60,6 +62,7 @@ class HashDictionary(utils.SaveLoad, dict): Examples -------- + >>> from gensim.corpora import HashDictionary >>> >>> dct = HashDictionary(debug=False) # needs no training corpus! @@ -74,6 +77,7 @@ def __init__(self, documents=None, id_range=32000, myhash=zlib.adler32, debug=Tr Parameters ---------- + documents : iterable of iterable of str Iterable of documents. If given, used to collect additional corpus statistics. HashDictionary can work without these statistics (optional parameter). id_range : int, optional @@ -110,11 +114,13 @@ def __getitem__(self, tokenid): Parameters ---------- + tokenid : int Token identifier (result of hashing). Return ------ + set of str Set of all words that have mapped to this id. @@ -127,11 +133,13 @@ def restricted_hash(self, token): Parameters ---------- + token : str Input token. Return ------ + int Hash value of `token`. @@ -163,15 +171,18 @@ def add_documents(self, documents): Notes ----- + This is only a convenience wrapper for calling `doc2bow` on each document with `allow_update=True`. Parameters ---------- + documents : iterable of list of str Collection of documents. Examples -------- + >>> from gensim.corpora import HashDictionary >>> >>> dct = HashDictionary(debug=True) # needs no training corpus! @@ -266,6 +277,7 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): Parameters ---------- + no_below : int, optional Keep tokens which are contained in at least `no_below` documents. no_above : float, optional @@ -276,6 +288,7 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): Notes ----- + For tokens that appear in: #. Less than `no_below` documents (absolute number) or \n @@ -284,6 +297,7 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): Examples -------- + >>> from gensim.corpora import HashDictionary >>> >>> dct = HashDictionary(debug=True) @@ -317,17 +331,20 @@ def save_as_text(self, fname): Parameters ---------- + fname : str Path to output file. Notes ----- + The format is: `id[TAB]document frequency of this id[TAB]tab-separated set of words in UTF8 that map to this id[NEWLINE]`. Examples -------- + >>> from gensim.corpora import HashDictionary >>> from gensim.test.utils import get_tmpfile >>> From 7a38bcd469a9705be76c6089410d04e9e9b5a266 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Thu, 31 May 2018 11:37:51 +0200 Subject: [PATCH 05/40] minor wording change --- gensim/corpora/hashdictionary.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/corpora/hashdictionary.py b/gensim/corpora/hashdictionary.py index 4f57b83071..386b3ee9b3 100644 --- a/gensim/corpora/hashdictionary.py +++ b/gensim/corpora/hashdictionary.py @@ -21,7 +21,7 @@ * New words can be represented immediately, without an extra pass through the corpus to collect all the ids first. * Can be used with non-repeatable (once-only) streams of documents. -* Able to represent all tokens (not only those present in training documents) +* Able to represent any token (not only those present in training documents) Disadvantages: From 700a1be6eec406335d99b3c6fdb3f750e5cf2371 Mon Sep 17 00:00:00 2001 From: Ivan Menshikh Date: Fri, 1 Jun 2018 07:45:58 +0500 Subject: [PATCH 06/40] Fix PEP8 in `HashDictionary` --- gensim/corpora/hashdictionary.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/gensim/corpora/hashdictionary.py b/gensim/corpora/hashdictionary.py index 386b3ee9b3..a478c5e79f 100644 --- a/gensim/corpora/hashdictionary.py +++ b/gensim/corpora/hashdictionary.py @@ -79,14 +79,17 @@ def __init__(self, documents=None, id_range=32000, myhash=zlib.adler32, debug=Tr ---------- documents : iterable of iterable of str - Iterable of documents. If given, used to collect additional corpus statistics. HashDictionary can work without these statistics (optional parameter). + Iterable of documents. If given, used to collect additional corpus statistics. + :class:`~gensim.corpora.hashdictionary.HashDictionary` can work + without these statistics (optional parameter). id_range : int, optional Number of hash-values in table, used as `id = myhash(key) %% id_range`. myhash : function Hash function, should support interface `myhash(str) -> int`, uses `zlib.adler32` by default. debug : bool If True - store which tokens have mapped to a given id. **Will use a lot of RAM**. - If you find yourself running out of memory (or not sure that you really need raw tokens), keep `debug=False`. + If you find yourself running out of memory (or not sure that you really need raw tokens), + keep `debug=False`. """ self.myhash = myhash # hash fnc: string->integer From e50a0574e70b4c8808b16b50f140f21c4bb6352e Mon Sep 17 00:00:00 2001 From: Jonathan Hourany Date: Sun, 10 Jun 2018 01:31:14 -0700 Subject: [PATCH 07/40] Fixed Typo and increased performance in analyze_sentence (#2070) * Type Type on line 147. Sentence is "...happy ending has it won't..." where "has" should be "as" * Swapped + operator for append when adding to list As @piskvorky pointed out, using `s + [None]`on line 149 creates a new list, an expensive operation considering the goal is just to append `None` to an already existing list. Using `append` increases performance by 5 micro seconds per function call on my system --- gensim/models/phrases.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py index 6dc4112a15..5ff4e99051 100644 --- a/gensim/models/phrases.py +++ b/gensim/models/phrases.py @@ -141,11 +141,12 @@ def analyze_sentence(self, sentence, threshold, common_terms, scorer): """ s = [utils.any2utf8(w) for w in sentence] + # adding None is a trick that helps getting an automatic happy ending + # as it won't be a common_word, nor score + s.append(None) last_uncommon = None in_between = [] - # adding None is a trick that helps getting an automatic happy ending - # has it won't be a common_word, nor score - for word in s + [None]: + for word in s: is_common = word in common_terms if not is_common and last_uncommon: chain = [last_uncommon] + in_between + [word] From 8715c00c714216f8f946583d633df5a381b8ca1f Mon Sep 17 00:00:00 2001 From: Umang Varma Date: Wed, 20 Jun 2018 00:15:54 -0400 Subject: [PATCH 08/40] Fix linear decay for learning rate in `Doc2Vec.infer_vector`. Fix #2061 (#2063) * Linear decay for learning rate in infer_vector * remove whitespace --- gensim/models/doc2vec.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py index f57694273d..f79f0153a5 100644 --- a/gensim/models/doc2vec.py +++ b/gensim/models/doc2vec.py @@ -546,6 +546,8 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): if not self.sg: neu1 = matutils.zeros_aligned(self.trainables.layer1_size, dtype=REAL) + alpha_delta = (alpha - min_alpha) / (steps - 1) + for i in range(steps): if self.sg: train_document_dbow( @@ -562,7 +564,7 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): self, doc_words, doctag_indexes, alpha, work, neu1, learn_words=False, learn_hidden=False, doctag_vectors=doctag_vectors, doctag_locks=doctag_locks ) - alpha = ((alpha - min_alpha) / (steps - i)) + min_alpha + alpha -= alpha_delta return doctag_vectors[0] From 90c22fdbeeef11cb4cd2929053eee0ca0c409ba1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Wed, 20 Jun 2018 08:23:01 +0200 Subject: [PATCH 09/40] Fix documentation for `*2vec` models (#2087) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Remove useless methods * started working on docstrings * more work done * Finished documentation for the `BaseWordEmbeddingsModel * PEP-8 * Revert "Remove useless methods" This reverts commit feb3c321aa12561125918a2fc3b86142f973d87e. * added documentation for the class and all its helper methods * remove duplicated type info * Added documentation for `Doc2vec` model and all its helper methods * Fixed paper references and added documentation for –Doc2VecVocab * Fixed paper references * minor referencing fixes * sphinx identation * Added docstrings for the private methods in `BaseAny2Vec` * Applied all code review corrections, example fix still pending * Added missing docstrings * Fixed `int {1, 0}` -> `{1, 0}` * Fixed examples and code review corrections * Fixed examples and applied code review corrections (optional arguments, correct types, blank lines at end of docstrings * Applied code review corrections and added top level usage examples * Added high level explanation of the class hierarchy, fixed code review corrections * Final identation fixes * Documentation fixes * Fixed all examples * delete redundant reference to module * Added explanation for all important class attributes. These include some intuitive information taken from the papers but also references to usage examples for users that do not wish to understand the underlying theory. * documented public cython functions * documented public cython functions in doc2vec * Applied code review corrections * added documentation for public cython methods in `fasttext` * added documentation for C functions in the word2vec * fix build issues * add missing rst * fix base_any2vec * fix doc2vec[1] * fix doc2vec[2] * fix doc2vec[3ъ * fix doc2vec[4] * fix doc2vec_inner + remove unused imports * fix fasttext[1] * reformat example sections * word2vec doc fixes * more doc fixes * merging in changes from #1944 * review docs for doc2vec, base_any2vec * review fasttext docs * review poincare docs * minor typo fixes * simplify word2vec.train() docs * update alpha & epoch docs for *2vec models * add *_inner docs * fixing KeyedVectors docs * disable sphinx latex and errors (temporary, revert later) * hyperlink fixes * Fix build warnings * fix flake8 * enable strict doc building * embedsignature for w2v & ft * yes/no -> ✅/❌ * cleanup base_any2vec * clenup cython files * cleanup doc2vec * improve d2v example * cleanup fasttext * clenup utils_any2vec * clenup poincare * clenup keyedvectors * cleanup word2vec * add newline around module docstrings + re-generate *.c files (for correct doc building) --- docs/src/Makefile | 2 +- docs/src/apiref.rst | 4 + docs/src/models/base_any2vec.rst | 10 + docs/src/models/doc2vec_inner.rst | 9 + docs/src/models/fasttext_inner.rst | 9 + docs/src/models/word2vec_inner.rst | 9 + gensim/models/_utils_any2vec.c | 459 ++- gensim/models/base_any2vec.py | 694 ++++- gensim/models/doc2vec.py | 857 ++++-- gensim/models/doc2vec_inner.c | 4283 +++++++++++++++------------- gensim/models/doc2vec_inner.pyx | 152 +- gensim/models/fasttext.py | 453 ++- gensim/models/fasttext_inner.c | 3362 ++++++++++++---------- gensim/models/fasttext_inner.pyx | 75 +- gensim/models/keyedvectors.py | 965 ++++--- gensim/models/poincare.py | 577 ++-- gensim/models/utils_any2vec.py | 46 +- gensim/models/word2vec.py | 859 ++++-- gensim/models/word2vec_inner.c | 4242 ++++++++++++++------------- gensim/models/word2vec_inner.pyx | 284 +- 20 files changed, 10144 insertions(+), 7207 deletions(-) create mode 100644 docs/src/models/base_any2vec.rst create mode 100644 docs/src/models/doc2vec_inner.rst create mode 100644 docs/src/models/fasttext_inner.rst create mode 100644 docs/src/models/word2vec_inner.rst diff --git a/docs/src/Makefile b/docs/src/Makefile index be62859ff7..30cbe5a869 100644 --- a/docs/src/Makefile +++ b/docs/src/Makefile @@ -40,7 +40,7 @@ html: @echo @echo "Build finished. The HTML pages are in ../" -upload: +upload: scp -r _build/html/* rr:public_html/gensim/ dirhtml: diff --git a/docs/src/apiref.rst b/docs/src/apiref.rst index 66fe192b07..29f91d9f47 100644 --- a/docs/src/apiref.rst +++ b/docs/src/apiref.rst @@ -53,6 +53,9 @@ Modules: models/callbacks models/utils_any2vec models/_utils_any2vec + models/word2vec_inner + models/doc2vec_inner + models/fasttext_inner models/wrappers/ldamallet models/wrappers/dtmmodel models/wrappers/ldavowpalwabbit.rst @@ -64,6 +67,7 @@ Modules: models/deprecated/word2vec models/deprecated/keyedvectors models/deprecated/fasttext_wrapper + models/base_any2vec similarities/docsim similarities/index sklearn_api/atmodel diff --git a/docs/src/models/base_any2vec.rst b/docs/src/models/base_any2vec.rst new file mode 100644 index 0000000000..e6685cda66 --- /dev/null +++ b/docs/src/models/base_any2vec.rst @@ -0,0 +1,10 @@ +:mod:`models.base_any2vec` -- Base classes for any2vec models +============================================================= + +.. automodule:: gensim.models.base_any2vec + :synopsis: Base classes for any2vec models + :members: + :inherited-members: + :special-members: __getitem__ + :undoc-members: + :show-inheritance: diff --git a/docs/src/models/doc2vec_inner.rst b/docs/src/models/doc2vec_inner.rst new file mode 100644 index 0000000000..92e7cf8628 --- /dev/null +++ b/docs/src/models/doc2vec_inner.rst @@ -0,0 +1,9 @@ +:mod:`models.doc2vec_inner` -- Cython routines for training Doc2Vec models +========================================================================== + +.. automodule:: gensim.models.doc2vec_inner + :synopsis: Optimized Cython routines for training Doc2Vec models + :members: + :inherited-members: + :undoc-members: + :show-inheritance: diff --git a/docs/src/models/fasttext_inner.rst b/docs/src/models/fasttext_inner.rst new file mode 100644 index 0000000000..4c5a1b1f65 --- /dev/null +++ b/docs/src/models/fasttext_inner.rst @@ -0,0 +1,9 @@ +:mod:`models.fasttext_inner` -- Cython routines for training FastText models +============================================================================ + +.. automodule:: gensim.models.fasttext_inner + :synopsis: Optimized Cython routines for training FastText models + :members: + :inherited-members: + :undoc-members: + :show-inheritance: diff --git a/docs/src/models/word2vec_inner.rst b/docs/src/models/word2vec_inner.rst new file mode 100644 index 0000000000..857b9fc1dd --- /dev/null +++ b/docs/src/models/word2vec_inner.rst @@ -0,0 +1,9 @@ +:mod:`models.word2vec_inner` -- Cython routines for training Word2Vec models +============================================================================ + +.. automodule:: gensim.models.word2vec_inner + :synopsis: Optimized Cython routines for training Word2Vec models + :members: + :inherited-members: + :undoc-members: + :show-inheritance: diff --git a/gensim/models/_utils_any2vec.c b/gensim/models/_utils_any2vec.c index 24fed7ffcf..2fd18bbbc7 100644 --- a/gensim/models/_utils_any2vec.c +++ b/gensim/models/_utils_any2vec.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.27.3 */ +/* Generated by Cython 0.28.3 */ #define PY_SSIZE_T_CLEAN #include "Python.h" @@ -7,7 +7,7 @@ #elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.6+ or Python 3.3+. #else -#define CYTHON_ABI "0_27_3" +#define CYTHON_ABI "0_28_3" #define CYTHON_FUTURE_DIVISION 0 #include #ifndef offsetof @@ -183,6 +183,103 @@ #undef BASE #undef MASK #endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) #define Py_OptimizeFlag 0 #endif @@ -211,12 +308,12 @@ #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif -#if PY_VERSION_HEX < 0x030700A0 || !defined(METH_FASTCALL) +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif - typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject **args, Py_ssize_t nargs); - typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject **args, + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast @@ -228,6 +325,18 @@ #else #define __Pyx_PyFastCFunction_Check(func) 0 #endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif #if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x03060000 @@ -237,6 +346,36 @@ #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; // PyThread_create_key reports success always +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif // TSS (Thread Specific Storage) API #if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else @@ -249,6 +388,11 @@ #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif #if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ @@ -293,18 +437,6 @@ #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif -#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) - #define PyObject_Malloc(s) PyMem_Malloc(s) - #define PyObject_Free(p) PyMem_Free(p) - #define PyObject_Realloc(p) PyMem_Realloc(p) -#endif -#if CYTHON_COMPILING_IN_PYSTON - #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) -#else - #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) -#endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 @@ -321,6 +453,7 @@ #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact + #define PyObject_Unicode PyObject_Str #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) @@ -332,7 +465,11 @@ #ifndef PySet_CheckExact #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) #endif -#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type @@ -367,16 +504,10 @@ #define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t #endif #if PY_MAJOR_VERSION >= 3 - #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func)) + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : (Py_INCREF(func), func)) #else #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) #endif -#ifndef __has_attribute - #define __has_attribute(x) 0 -#endif -#ifndef __has_cpp_attribute - #define __has_cpp_attribute(x) 0 -#endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods @@ -394,96 +525,6 @@ unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif -#ifndef CYTHON_RESTRICT - #if defined(__GNUC__) - #define CYTHON_RESTRICT __restrict__ - #elif defined(_MSC_VER) && _MSC_VER >= 1400 - #define CYTHON_RESTRICT __restrict - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_RESTRICT restrict - #else - #define CYTHON_RESTRICT - #endif -#endif -#ifndef CYTHON_UNUSED -# if defined(__GNUC__) -# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -#endif -#ifndef CYTHON_MAYBE_UNUSED_VAR -# if defined(__cplusplus) - template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } -# else -# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) -# endif -#endif -#ifndef CYTHON_NCP_UNUSED -# if CYTHON_COMPILING_IN_CPYTHON -# define CYTHON_NCP_UNUSED -# else -# define CYTHON_NCP_UNUSED CYTHON_UNUSED -# endif -#endif -#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) -#ifdef _MSC_VER - #ifndef _MSC_STDINT_H_ - #if _MSC_VER < 1300 - typedef unsigned char uint8_t; - typedef unsigned int uint32_t; - #else - typedef unsigned __int8 uint8_t; - typedef unsigned __int32 uint32_t; - #endif - #endif -#else - #include -#endif -#ifndef CYTHON_FALLTHROUGH - #if defined(__cplusplus) && __cplusplus >= 201103L - #if __has_cpp_attribute(fallthrough) - #define CYTHON_FALLTHROUGH [[fallthrough]] - #elif __has_cpp_attribute(clang::fallthrough) - #define CYTHON_FALLTHROUGH [[clang::fallthrough]] - #elif __has_cpp_attribute(gnu::fallthrough) - #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] - #endif - #endif - #ifndef CYTHON_FALLTHROUGH - #if __has_attribute(fallthrough) - #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) - #else - #define CYTHON_FALLTHROUGH - #endif - #endif - #if defined(__clang__ ) && defined(__apple_build_version__) - #if __apple_build_version__ < 7000000 - #undef CYTHON_FALLTHROUGH - #define CYTHON_FALLTHROUGH - #endif - #endif -#endif - -#ifndef CYTHON_INLINE - #if defined(__clang__) - #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) - #elif defined(__GNUC__) - #define CYTHON_INLINE __inline__ - #elif defined(_MSC_VER) - #define CYTHON_INLINE __inline - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_INLINE inline - #else - #define CYTHON_INLINE - #endif -#endif #if defined(WIN32) || defined(MS_WINDOWS) #define _USE_MATH_DEFINES @@ -520,6 +561,7 @@ static CYTHON_INLINE float __PYX_NAN() { #define __PYX_HAVE__gensim__models___utils_any2vec #define __PYX_HAVE_API__gensim__models___utils_any2vec +/* Early includes */ #ifdef _OPENMP #include #endif /* _OPENMP */ @@ -604,7 +646,7 @@ static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) -#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False)) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ @@ -712,7 +754,7 @@ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } static PyObject *__pyx_m = NULL; static PyObject *__pyx_d; static PyObject *__pyx_b; -static PyObject *__pyx_cython_runtime; +static PyObject *__pyx_cython_runtime = NULL; static PyObject *__pyx_empty_tuple; static PyObject *__pyx_empty_bytes; static PyObject *__pyx_empty_unicode; @@ -794,16 +836,7 @@ static const char *__pyx_f[] = { /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_getattro)) - return tp->tp_getattro(obj, attr_name); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_getattr)) - return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); -#endif - return PyObject_GetAttr(obj, attr_name); -} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif @@ -998,6 +1031,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) #define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) #endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) /* CheckBinaryVersion.proto */ static int __Pyx_check_binary_version(void); @@ -1038,6 +1072,7 @@ static PyObject *__pyx_pf_6gensim_6models_14_utils_any2vec_ft_hash(CYTHON_UNUSED static PyObject *__pyx_pf_6gensim_6models_14_utils_any2vec_2compute_ngrams(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_word, unsigned int __pyx_v_min_n, unsigned int __pyx_v_max_n); /* proto */ static PyObject *__pyx_int_0; static PyObject *__pyx_int_1; +/* Late includes */ /* "gensim/models/_utils_any2vec.pyx":10 * """General functions used for any2vec models.""" @@ -1508,17 +1543,17 @@ static PyObject *__pyx_pw_6gensim_6models_14_utils_any2vec_3compute_ngrams(PyObj kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_min_n)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_min_n)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("compute_ngrams", 1, 3, 3, 1); __PYX_ERR(0, 33, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_max_n)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_max_n)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("compute_ngrams", 1, 3, 3, 2); __PYX_ERR(0, 33, __pyx_L3_error) } @@ -1648,12 +1683,101 @@ static int __Pyx_InitGlobals(void) { return -1; } +static int __Pyx_modinit_global_init_code(void); /*proto*/ +static int __Pyx_modinit_variable_export_code(void); /*proto*/ +static int __Pyx_modinit_function_export_code(void); /*proto*/ +static int __Pyx_modinit_type_init_code(void); /*proto*/ +static int __Pyx_modinit_type_import_code(void); /*proto*/ +static int __Pyx_modinit_variable_import_code(void); /*proto*/ +static int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + + #if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC init_utils_any2vec(void); /*proto*/ -PyMODINIT_FUNC init_utils_any2vec(void) +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC void #else -PyMODINIT_FUNC PyInit__utils_any2vec(void); /*proto*/ -PyMODINIT_FUNC PyInit__utils_any2vec(void) +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#else +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyObject * +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (!(defined(__cplusplus)) || (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ > 4))) + #define CYTHON_SMALL_CODE __attribute__((optimize("Os"))) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + + +#if PY_MAJOR_VERSION < 3 +__Pyx_PyMODINIT_FUNC init_utils_any2vec(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC init_utils_any2vec(void) +#else +__Pyx_PyMODINIT_FUNC PyInit__utils_any2vec(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit__utils_any2vec(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); @@ -1701,17 +1825,19 @@ static int __pyx_pymod_exec__utils_any2vec(PyObject *__pyx_pyinit_module) __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m && __pyx_m == __pyx_pyinit_module) return 0; + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif #if CYTHON_REFNANNY - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); - if (!__Pyx_RefNanny) { - PyErr_Clear(); - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); - if (!__Pyx_RefNanny) - Py_FatalError("failed to import 'refnanny' module"); - } - #endif - __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit__utils_any2vec(void)", 0); +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit__utils_any2vec(void)", 0); if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) @@ -1781,13 +1907,14 @@ static int __pyx_pymod_exec__utils_any2vec(PyObject *__pyx_pyinit_module) if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) /*--- Constants init code ---*/ if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Global init code ---*/ - /*--- Variable export code ---*/ - /*--- Function export code ---*/ - /*--- Type init code ---*/ - /*--- Type import code ---*/ - /*--- Variable import code ---*/ - /*--- Function import code ---*/ + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + (void)__Pyx_modinit_variable_export_code(); + (void)__Pyx_modinit_function_export_code(); + (void)__Pyx_modinit_type_init_code(); + (void)__Pyx_modinit_type_import_code(); + (void)__Pyx_modinit_variable_import_code(); + (void)__Pyx_modinit_function_import_code(); /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) @@ -1845,6 +1972,20 @@ static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { } #endif +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); @@ -1991,7 +2132,7 @@ static PyObject* __Pyx_PyUnicode_Join(PyObject* value_tuple, Py_ssize_t value_co ukind = __Pyx_PyUnicode_KIND(uval); udata = __Pyx_PyUnicode_DATA(uval); if (!CYTHON_PEP393_ENABLED || ukind == result_ukind) { - memcpy((char *)result_udata + char_pos * result_ukind, udata, ulength * result_ukind); + memcpy((char *)result_udata + char_pos * result_ukind, udata, (size_t) (ulength * result_ukind)); } else { #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030300F0 || defined(_PyUnicode_FastCopyCharacters) _PyUnicode_FastCopyCharacters(result_uval, char_pos, uval, 0, ulength); @@ -2077,6 +2218,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -2087,6 +2229,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -2097,6 +2240,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -2107,6 +2251,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -2117,6 +2262,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -2127,6 +2273,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; default: return PyLong_Type.tp_as_number->nb_add(op1, op2); } } @@ -2354,11 +2501,14 @@ static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_li #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { - use_cline = PyDict_GetItem(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); + use_cline = __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); } else #endif { @@ -3314,7 +3464,7 @@ static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) - PyErr_Clear(); + return -1; ++t; } return 0; @@ -3528,6 +3678,9 @@ static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_DECREF(x); return ival; } +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } diff --git a/gensim/models/base_any2vec.py b/gensim/models/base_any2vec.py index e6a31263ec..3b6dabf95e 100644 --- a/gensim/models/base_any2vec.py +++ b/gensim/models/base_any2vec.py @@ -5,7 +5,33 @@ # Copyright (C) 2018 RaRe Technologies s.r.o. # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""Contains base classes required for implementing any2vec algorithms.""" +"""This module contains base classes required for implementing \*2vec algorithms. + +The class hierarchy is designed to facilitate adding more concrete implementations for creating embeddings. +In the most general case, the purpose of this class is to transform an arbitrary representation to a numerical vector +(embedding). This is represented by the base :class:`~gensim.models.base_any2vec.BaseAny2VecModel`. The input space in +most cases (in the NLP field at least) is plain text. For this reason, we enrich the class hierarchy with the abstract +:class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` to be used as a base for models where the input +space is text. + +Notes +----- +Even though this is the usual case, not all embeddings transform text, such as the +:class:`~gensim.models.poincare.PoincareModel` that embeds graphs. + +See Also +-------- +:class:`~gensim.models.word2vec.Word2Vec`. + Word2Vec model - embeddings for words. +:class:`~gensim.models.fasttext.FastText`. + FastText model - embeddings for words (ngram-based). +:class:`~gensim.models.doc2vec.Doc2Vec`. + Doc2Vec model - embeddings for documents. +:class:`~gensim.models.poincare.PoincareModel` + Poincare model - embeddings for graphs. + +""" + from gensim import utils import logging from timeit import default_timer @@ -27,18 +53,40 @@ class BaseAny2VecModel(utils.SaveLoad): - """Base class for training, using and evaluating any2vec model. - Contains implementation for multi-threaded training. + """Base class for training, using and evaluating \*2vec model. - """ + Contains implementation for multi-threaded training. The purpose of this class is to provide a + reference interface for concrete embedding implementations, whether the input space is a corpus + of words, documents or anything else. At the same time, functionality that we expect to be common + for those implementations is provided here to avoid code duplication. + + In the special but usual case where the input space consists of words, a more specialized layer + is provided, consider inheriting from :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + Notes + ----- + A subclass should initialize the following attributes: + + * self.kv - keyed vectors in model (see :class:`~gensim.models.keyedvectors.Word2VecKeyedVectors` as example) + * self.vocabulary - vocabulary (see :class:`~gensim.models.word2vec.Word2VecVocab` as example) + * self.trainables - internal matrices (see :class:`~gensim.models.word2vec.Word2VecTrainables` as example) + + """ def __init__(self, workers=3, vector_size=100, epochs=5, callbacks=(), batch_words=10000): - """Initialize model parameters. + """ - A subclass should initialize the following attributes: - - self.kv (instance of concrete implementation of `BaseKeyedVectors` interface) - - self.vocabulary (instance of concrete implementation of `BaseVocabBuilder` abstract class) - - self.trainables (instance of concrete implementation of `BaseTrainables` abstract class) + Parameters + ---------- + workers : int, optional + Number of working threads, used for multithreading. + vector_size : int, optional + Dimensionality of the feature vectors. + epochs : int, optional + Number of iterations (epochs) of training through the corpus. + callbacks : list of :class:`~gensim.models.callbacks.CallbackAny2Vec`, optional + List of callbacks that need to be executed/run at specific stages during training. + batch_words : int, optional + Number of words to be processed by a single job. """ self.vector_size = int(vector_size) @@ -55,7 +103,7 @@ def _get_job_params(self, cur_epoch): raise NotImplementedError() def _set_train_params(self, **kwargs): - """Set model parameters required for training""" + """Set model parameters required for training.""" raise NotImplementedError() def _update_job_params(self, job_params, epoch_progress, cur_epoch): @@ -83,7 +131,24 @@ def _check_training_sanity(self, epochs=None, total_examples=None, total_words=N raise NotImplementedError() def _worker_loop(self, job_queue, progress_queue): - """Train the model, lifting lists of data from the job_queue.""" + """Train the model, lifting batches of data from the queue. + + This function will be called in parallel by multiple workers (threads or processes) to make + optimal use of multicore machines. + + Parameters + ---------- + job_queue : Queue of (list of objects, (str, int)) + A queue of jobs still to be processed. The worker will take up jobs from this queue. + Each job is represented by a tuple where the first element is the corpus chunk to be processed and + the second is the dictionary of parameters. + progress_queue : Queue of (int, int, int) + A queue of progress reports. Each report is represented as a tuple of these 3 elements: + * Size of data chunk processed, for example number of sentences in the corpus chunk. + * Effective word count used in training (after ignoring unknown words and trimming the sentence length). + * Total word count used in training. + + """ thread_private_mem = self._get_thread_working_mem() jobs_processed = 0 while True: @@ -106,7 +171,30 @@ def _worker_loop(self, job_queue, progress_queue): logger.debug("worker exiting, processed %i jobs", jobs_processed) def _job_producer(self, data_iterator, job_queue, cur_epoch=0, total_examples=None, total_words=None): - """Fill jobs queue using the input `data_iterator`.""" + """Fill the jobs queue using the data found in the input stream. + + Each job is represented by a tuple where the first element is the corpus chunk to be processed and + the second is a dictionary of parameters. + + Parameters + ---------- + data_iterator : iterable of list of objects + The input dataset. This will be split in chunks and these chunks will be pushed to the queue. + job_queue : Queue of (list of object, dict of (str, int)) + A queue of jobs still to be processed. The worker will take up jobs from this queue. + Each job is represented by a tuple where the first element is the corpus chunk to be processed and + the second is the dictionary of parameters. + cur_epoch : int, optional + The current training epoch, needed to compute the training parameters for each job. + For example in many implementations the learning rate would be dropping with the number of epochs. + total_examples : int, optional + Count of objects in the `data_iterator`. In the usual case this would correspond to the number of sentences + in a corpus. Used to log progress. + total_words : int, optional + Count of total objects in `data_iterator`. In the usual case this would correspond to the number of raw + words in a corpus. Used to log progress. + + """ job_batch, batch_size = [], 0 pushed_words, pushed_examples = 0, 0 next_job_params = self._get_job_params(cur_epoch) @@ -166,6 +254,40 @@ def _log_train_end(self, raw_word_count, trained_word_count, total_elapsed, job_ def _log_epoch_progress(self, progress_queue, job_queue, cur_epoch=0, total_examples=None, total_words=None, report_delay=1.0): + """Get the progress report for a single training epoch. + + Parameters + ---------- + progress_queue : Queue of (int, int, int) + A queue of progress reports. Each report is represented as a tuple of these 3 elements: + * size of data chunk processed, for example number of sentences in the corpus chunk. + * Effective word count used in training (after ignoring unknown words and trimming the sentence length). + * Total word count used in training. + job_queue : Queue of (list of object, dict of (str, int)) + A queue of jobs still to be processed. The worker will take up jobs from this queue. + Each job is represented by a tuple where the first element is the corpus chunk to be processed and + the second is the dictionary of parameters. + cur_epoch : int, optional + The current training epoch, needed to compute the training parameters for each job. + For example in many implementations the learning rate would be dropping with the number of epochs. + total_examples : int, optional + Count of objects in the `data_iterator`. In the usual case this would correspond to the number of sentences + in a corpus. Used to log progress. + total_words : int, optional + Count of total objects in `data_iterator`. In the usual case this would correspond to the number of raw + words in a corpus. Used to log progress. + report_delay : float, optional + Number of seconds between two consecutive progress report messages in the logger. + + Returns + ------- + (int, int, int) + The epoch report consisting of three elements: + * size of data chunk processed, for example number of sentences in the corpus chunk. + * Effective word count used in training (after ignoring unknown words and trimming the sentence length). + * Total word count used in training. + + """ example_count, trained_word_count, raw_word_count = 0, 0, 0 start, next_report = default_timer() - 0.00001, 1.0 job_tally = 0 @@ -202,7 +324,35 @@ def _log_epoch_progress(self, progress_queue, job_queue, cur_epoch=0, total_exam def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, total_words=None, queue_factor=2, report_delay=1.0): - """Train one epoch.""" + """Train the model for a single epoch. + + Parameters + ---------- + data_iterable : iterable of list of object + The input corpus. This will be split in chunks and these chunks will be pushed to the queue. + cur_epoch : int, optional + The current training epoch, needed to compute the training parameters for each job. + For example in many implementations the learning rate would be dropping with the number of epochs. + total_examples : int, optional + Count of objects in the `data_iterator`. In the usual case this would correspond to the number of sentences + in a corpus, used to log progress. + total_words : int, optional + Count of total objects in `data_iterator`. In the usual case this would correspond to the number of raw + words in a corpus, used to log progress. + queue_factor : int, optional + Multiplier for size of queue -> size = number of workers * queue_factor. + report_delay : float, optional + Number of seconds between two consecutive progress report messages in the logger. + + Returns + ------- + (int, int, int) + The training report for this epoch consisting of three elements: + * Size of data chunk processed, for example number of sentences in the corpus chunk. + * Effective word count used in training (after ignoring unknown words and trimming the sentence length). + * Total word count used in training. + + """ job_queue = Queue(maxsize=queue_factor * self.workers) progress_queue = Queue(maxsize=(queue_factor + 1) * self.workers) @@ -230,7 +380,37 @@ def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, def train(self, data_iterable, epochs=None, total_examples=None, total_words=None, queue_factor=2, report_delay=1.0, callbacks=(), **kwargs): - """Handle multi-worker training.""" + """Train the model for multiple epochs using multiple workers. + + Parameters + ---------- + data_iterable : iterable of list of object + The input corpus. This will be split in chunks and these chunks will be pushed to the queue. + epochs : int, optional + Number of epochs (training iterations over the whole input) of training. + total_examples : int, optional + Count of objects in the `data_iterator`. In the usual case this would correspond to the number of sentences + in a corpus, used to log progress. + total_words : int, optional + Count of total objects in `data_iterator`. In the usual case this would correspond to the number of raw + words in a corpus, used to log progress. + queue_factor : int, optional + Multiplier for size of queue -> size = number of workers * queue_factor. + report_delay : float, optional + Number of seconds between two consecutive progress report messages in the logger. + callbacks : list of :class:`~gensim.models.callbacks.CallbackAny2Vec`, optional + List of callbacks to execute at specific stages during training. + **kwargs : object + Additional key word parameters for the specific model inheriting from this class. + + Returns + ------- + (int, int) + The total training report consisting of two elements: + * size of total data processed, for example number of sentences in the whole corpus. + * Effective word count used in training (after ignoring unknown words and trimming the sentence length). + + """ self._set_train_params(**kwargs) if callbacks: self.callbacks = callbacks @@ -275,19 +455,67 @@ def train(self, data_iterable, epochs=None, total_examples=None, @classmethod def load(cls, fname_or_handle, **kwargs): + """Load a previously saved object (using :meth:`gensim.models.base_any2vec.BaseAny2VecModel.save`) from a file. + + Parameters + ---------- + fname_or_handle : {str, file-like object} + Path to file that contains needed object or handle to an open file. + **kwargs : object + Keyword arguments propagated to :meth:`~gensim.utils.SaveLoad.load`. + + See Also + -------- + :meth:`~gensim.models.base_any2vec.BaseAny2VecModel.save` + Method for save a model. + + Returns + ------- + object + Object loaded from `fname_or_handle`. + + Raises + ------ + IOError + When methods are called on an instance (should be called on a class, this is a class method). + + """ return super(BaseAny2VecModel, cls).load(fname_or_handle, **kwargs) def save(self, fname_or_handle, **kwargs): + """"Save the object to file. + + Parameters + ---------- + fname_or_handle : {str, file-like object} + Path to file where the model will be persisted. + **kwargs : object + Key word arguments propagated to :meth:`~gensim.utils.SaveLoad.save`. + + See Also + -------- + :meth:`~gensim.models.base_any2vec.BaseAny2VecModel.load` + Method for load model after current method. + + """ super(BaseAny2VecModel, self).save(fname_or_handle, **kwargs) class BaseWordEmbeddingsModel(BaseAny2VecModel): - """ - Base class containing common methods for training, using & evaluating word embeddings learning models. - For example - `Word2Vec`, `FastText`, etc. + """Base class containing common methods for training, using & evaluating word embeddings learning models. + + See Also + -------- + :class:`~gensim.models.word2vec.Word2Vec`. + Word2Vec model - embeddings for words. + :class:`~gensim.models.fasttext.FastText`. + FastText model - embeddings for words (ngram-based). + :class:`~gensim.models.doc2vec.Doc2Vec`. + Doc2Vec model - embeddings for documents. + :class:`~gensim.models.poincare.PoincareModel` + Poincare model - embeddings for graphs. """ - def _clear_post_train(self): raise NotImplementedError() @@ -300,6 +528,72 @@ def _set_train_params(self, **kwargs): def __init__(self, sentences=None, workers=3, vector_size=100, epochs=5, callbacks=(), batch_words=10000, trim_rule=None, sg=0, alpha=0.025, window=5, seed=1, hs=0, negative=5, cbow_mean=1, min_alpha=0.0001, compute_loss=False, fast_version=0, **kwargs): + """ + + Parameters + ---------- + sentences : iterable of list of str, optional + Can be simply a list of lists of tokens, but for larger corpora, + consider an iterable that streams the sentences directly from disk/network. + See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` + or :class:`~gensim.models.word2vec.LineSentence` for such examples. + workers : int, optional + Number of working threads, used for multiprocessing. + vector_size : int, optional + Dimensionality of the feature vectors. + epochs : int, optional + Number of iterations (epochs) of training through the corpus. + callbacks : list of :class:`~gensim.models.callbacks.CallbackAny2Vec`, optional + List of callbacks that need to be executed/run at specific stages during training. + batch_words : int, optional + Number of words to be processed by a single job. + trim_rule : function, optional + Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, + be trimmed away, or handled using the default (discard if word count < min_count). + Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), + or a callable that accepts parameters (word, count, min_count) and returns either + :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. + The rule, if given, is only used to prune vocabulary during current method call and is not stored as part + of the model. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + sg : {1, 0}, optional + Defines the training algorithm. If 1, skip-gram is used, otherwise, CBOW is employed. + alpha : float, optional + The beginning learning rate. This will linearly reduce with iterations until it reaches `min_alpha`. + window : int, optional + The maximum distance between the current and predicted word within a sentence. + seed : int, optional + Seed for the random number generator. Initial vectors for each word are seeded with a hash of + the concatenation of word + `str(seed)`. + Note that for a fully deterministically-reproducible run, you must also limit the model to a single worker + thread (`workers=1`), to eliminate ordering jitter from OS thread scheduling. + In Python 3, reproducibility between interpreter launches also requires use of the `PYTHONHASHSEED` + environment variable to control hash randomization. + hs : {1,0}, optional + If 1, hierarchical softmax will be used for model training. + If set to 0, and `negative` is non-zero, negative sampling will be used. + negative : int, optional + If > 0, negative sampling will be used, the int for negative specifies how many "noise words" + should be drawn (usually between 5-20). + If set to 0, no negative sampling is used. + cbow_mean : {1,0}, optional + If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used. + min_alpha : float, optional + Final learning rate. Drops linearly with the number of iterations from `alpha`. + compute_loss : bool, optional + If True, loss will be computed while training the Word2Vec model and stored in + :attr:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.running_training_loss` attribute. + fast_version : {-1, 1}, optional + Whether or not the fast cython implementation of the internal training methods is available. 1 means it is. + **kwargs : object + Key word arguments needed to allow children classes to accept more arguments. + + """ self.sg = int(sg) if vector_size % 4 != 0: logger.warning("consider setting layer size to a multiple of 4 for greater performance") @@ -455,25 +749,51 @@ def cum_table(self): del self.vocabulary.cum_table def __str__(self): + """Get a human readable representation of the object. + + Returns + ------- + str + A human readable string containing the class name, as well as the size of dictionary, number of + features and starting learning rate used by the object. + + """ return "%s(vocab=%s, size=%s, alpha=%s)" % ( self.__class__.__name__, len(self.wv.index2word), self.vector_size, self.alpha ) def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_vocab=False, trim_rule=None, **kwargs): """Build vocabulary from a sequence of sentences (can be a once-only generator stream). - Each sentence is a iterable of iterables (can simply be a list of unicode strings too). Parameters ---------- - sentences : iterable of iterables - The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, + sentences : iterable of list of str + Can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` - or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. - update : bool + or :class:`~gensim.models.word2vec.LineSentence` module for such examples. + update : bool, optional If true, the new words in `sentences` will be added to model's vocab. - progress_per : int + progress_per : int, optional Indicates how many words to process before showing/updating the progress. + keep_raw_vocab : bool, optional + If False, the raw vocabulary will be deleted after the scaling is done to free up RAM. + trim_rule : function, optional + Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, + be trimmed away, or handled using the default (discard if word count < min_count). + Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), + or a callable that accepts parameters (word, count, min_count) and returns either + :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. + The rule, if given, is only used to prune vocabulary during current method call and is not stored as part + of the model. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + **kwargs : object + Key word arguments propagated to `self.vocabulary.prepare_vocab` """ total_words, corpus_count = self.vocabulary.scan_vocab( @@ -487,34 +807,31 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca def build_vocab_from_freq(self, word_freq, keep_raw_vocab=False, corpus_count=None, trim_rule=None, update=False): """Build vocabulary from a dictionary of word frequencies. - Build model vocabulary from a passed dictionary that contains (word,word count). - Words must be of type unicode strings. Parameters ---------- - word_freq : dict - Word,Word_Count dictionary. - keep_raw_vocab : bool - If not true, delete the raw vocabulary after the scaling is done and free up RAM. - corpus_count : int + word_freq : dict of (str, int) + A mapping from a word in the vocabulary to its frequency count. + keep_raw_vocab : bool, optional + If False, delete the raw vocabulary after the scaling is done to free up RAM. + corpus_count : int, optional Even if no corpus is provided, this argument can set corpus_count explicitly. - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part + The rule, if given, is only used to prune vocabulary during current method call and is not stored as part of the model. - update : bool - If true, the new provided words in `word_freq` dict will be added to model's vocab. - Examples - -------- - >>> from gensim.models import Word2Vec - >>> - >>> model= Word2Vec() - >>> model.build_vocab_from_freq({"Word1": 15, "Word2": 20}) + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + update : bool, optional + If true, the new provided words in `word_freq` dict will be added to model's vocab. """ logger.info("Processing provided word frequencies") @@ -526,7 +843,7 @@ def build_vocab_from_freq(self, word_freq, keep_raw_vocab=False, corpus_count=No len(raw_vocab), sum(itervalues(raw_vocab)) ) - # Since no sentences are provided, this is to control the corpus_count + # Since no sentences are provided, this is to control the corpus_count. self.corpus_count = corpus_count or 0 self.vocabulary.raw_vocab = raw_vocab @@ -539,7 +856,21 @@ def build_vocab_from_freq(self, word_freq, keep_raw_vocab=False, corpus_count=No self.hs, self.negative, self.wv, update=update, vocabulary=self.vocabulary) # build tables & arrays def estimate_memory(self, vocab_size=None, report=None): - """Estimate required memory for a model using current settings and provided vocabulary size.""" + """Estimate required memory for a model using current settings and provided vocabulary size. + + Parameters + ---------- + vocab_size : int, optional + Number of unique tokens in the vocabulary + report : dict of (str, int), optional + A dictionary from string representations of the model's memory consuming members to their size in bytes. + + Returns + ------- + dict of (str, int) + A dictionary from string representations of the model's memory consuming members to their size in bytes. + + """ vocab_size = vocab_size or len(self.wv.vocab) report = report or {} report['vocab'] = vocab_size * (700 if self.hs else 500) @@ -558,6 +889,43 @@ def estimate_memory(self, vocab_size=None, report=None): def train(self, sentences, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, compute_loss=False, callbacks=()): + """Train the model. If the hyper-parameters are passed, they override the ones set in the constructor. + + Parameters + ---------- + sentences : iterable of list of str + Can be simply a list of lists of tokens, but for larger corpora, + consider an iterable that streams the sentences directly from disk/network. + See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` + or :class:`~gensim.models.word2vec.LineSentence` module for such examples. + total_examples : int, optional + Count of sentences. + total_words : int, optional + Count of raw words in sentences. + epochs : int, optional + Number of iterations (epochs) over the corpus. + start_alpha : float, optional + Initial learning rate. + end_alpha : float, optional + Final learning rate. Drops linearly with the number of iterations from `start_alpha`. + word_count : int, optional + Count of words already trained. Leave this to 0 for the usual case of training on all words in sentences. + queue_factor : int, optional + Multiplier for size of queue -> size = number of workers * queue_factor. + report_delay : float, optional + Seconds to wait before reporting progress. + compute_loss : bool, optional + If True, loss will be computed while training the Word2Vec model and stored in + :attr:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.running_training_loss`. + callbacks : list of :class:`~gensim.models.callbacks.CallbackAny2Vec`, optional + List of callbacks that need to be executed/run at specific stages during training. + + Returns + ------- + (int, int) + Tuple of (effective word count after ignoring unknown words and sentence length trimming, total word count). + + """ self.alpha = start_alpha or self.alpha self.min_alpha = end_alpha or self.min_alpha @@ -569,11 +937,40 @@ def train(self, sentences, total_examples=None, total_words=None, queue_factor=queue_factor, report_delay=report_delay, compute_loss=compute_loss, callbacks=callbacks) def _get_job_params(self, cur_epoch): - """Get the parameter required for each batch.""" + """Get the learning rate used in the current epoch. + + Parameters + ---------- + cur_epoch : int + Current iteration through the corpus + + Returns + ------- + float + The learning rate for this epoch (it is linearly reduced with epochs from `self.alpha` to `self.min_alpha`). + + """ alpha = self.alpha - ((self.alpha - self.min_alpha) * float(cur_epoch) / self.epochs) return alpha def _update_job_params(self, job_params, epoch_progress, cur_epoch): + """Get the correct learning rate for the next iteration. + + Parameters + ---------- + job_params : dict of (str, obj) + UNUSED. + epoch_progress : float + Ratio of finished work in the current epoch. + cur_epoch : int + Number of current iteration. + + Returns + ------- + float + The learning rate to be used in the next training epoch. + + """ start_alpha = self.alpha end_alpha = self.min_alpha progress = (cur_epoch + epoch_progress) / self.epochs @@ -583,15 +980,60 @@ def _update_job_params(self, job_params, epoch_progress, cur_epoch): return next_alpha def _get_thread_working_mem(self): + """Computes the memory used per worker thread. + + Returns + ------- + (np.ndarray, np.ndarray) + Each worker threads private work memory. + + """ work = matutils.zeros_aligned(self.trainables.layer1_size, dtype=REAL) # per-thread private work memory neu1 = matutils.zeros_aligned(self.trainables.layer1_size, dtype=REAL) return work, neu1 def _raw_word_count(self, job): - """Get the number of words in a given job.""" + """Get the number of words in a given job. + + Parameters + ---------- + job: iterable of list of str + The corpus chunk processed in a single batch. + + Returns + ------- + int + Number of raw words in the corpus chunk. + + """ return sum(len(sentence) for sentence in job) def _check_training_sanity(self, epochs=None, total_examples=None, total_words=None, **kwargs): + """Checks whether the training parameters make sense. + + Called right before training starts in :meth:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.train` + and raises warning or errors depending on the severity of the issue in case an inconsistent parameter + combination is detected. + + Parameters + ---------- + epochs : int, optional + Number of training epochs. Must have a (non None) value. + total_examples : int, optional + Number of documents in the corpus. Either `total_examples` or `total_words` **must** be supplied. + total_words : int, optional + Number of words in the corpus. Either `total_examples` or `total_words` **must** be supplied. + **kwargs : object + Unused. Present to preserve signature among base and inherited implementations. + + Raises + ------ + RuntimeError + If one of the required training pre/post processing steps have not been performed. + ValueError + If the combination of input parameters is inconsistent. + + """ if self.alpha > self.min_alpha_yet_reached: logger.warning("Effective 'alpha' higher than previous training cycles") if self.model_trimmed_post_training: @@ -626,6 +1068,35 @@ def _check_training_sanity(self, epochs=None, total_examples=None, total_words=N @classmethod def load(cls, *args, **kwargs): + """Load a previously saved object (using :meth:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.save`) from file. + + Also initializes extra instance attributes in case the loaded model does not include them. + `*args` or `**kwargs` **MUST** include the fname argument (path to saved file). + See :meth:`~gensim.utils.SaveLoad.load`. + + Parameters + ---------- + *args : object + Positional arguments passed to :meth:`~gensim.utils.SaveLoad.load`. + **kwargs : object + Key word arguments passed to :meth:`~gensim.utils.SaveLoad.load`. + + See Also + -------- + :meth:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.save` + Method for save a model. + + Returns + ------- + :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + Model loaded from disk. + + Raises + ------ + IOError + When methods are called on instance (should be called from class). + + """ model = super(BaseWordEmbeddingsModel, cls).load(*args, **kwargs) if model.negative and hasattr(model.wv, 'index2word'): model.vocabulary.make_cum_table(model.wv) # rebuild cum_table from vocabulary @@ -642,6 +1113,35 @@ def load(cls, *args, **kwargs): def _log_progress(self, job_queue, progress_queue, cur_epoch, example_count, total_examples, raw_word_count, total_words, trained_word_count, elapsed): + """Callback used to log progress for long running jobs. + + Parameters + ---------- + job_queue : Queue of (list of object, dict of (str, float)) + The queue of jobs still to be performed by workers. Each job is represented as a tuple containing + the batch of data to be processed and the parameters to be used for the processing as a dict. + progress_queue : Queue of (int, int, int) + A queue of progress reports. Each report is represented as a tuple of these 3 elements: + * size of data chunk processed, for example number of sentences in the corpus chunk. + * Effective word count used in training (after ignoring unknown words and trimming the sentence length). + * Total word count used in training. + cur_epoch : int + The current training iteration through the corpus. + example_count : int + Number of examples (could be sentences for example) processed until now. + total_examples : int + Number of all examples present in the input corpus. + raw_word_count : int + Number of words used in training until now. + total_words : int + Number of all words in the input corpus. + trained_word_count : int + Number of effective words used in training until now (after ignoring unknown words and trimming + the sentence length). + elapsed : int + Elapsed time since the beginning of training in seconds. + + """ if total_examples: # examples-based progress % logger.info( @@ -659,6 +1159,31 @@ def _log_progress(self, job_queue, progress_queue, cur_epoch, example_count, tot def _log_epoch_end(self, cur_epoch, example_count, total_examples, raw_word_count, total_words, trained_word_count, elapsed): + """Callback used to log the end of a training epoch. + + Parameters + ---------- + cur_epoch : int + The current training iteration through the corpus. + example_count : int + Number of examples (could be sentences for example) processed until now. + total_examples : int + Number of all examples present in the input corpus. + raw_word_count : int + Number of words used in training until now. + total_words : int + Number of all words in the input corpus. + trained_word_count : int + Number of effective words used in training until now (after ignoring unknown words and trimming + the sentence length). + elapsed : int + Elapsed time since the beginning of training in seconds. + + Warnings + -------- + In case the corpus is changed while the epoch was running. + + """ logger.info( "EPOCH - %i : training on %i raw words (%i effective words) took %.1fs, %.0f effective words/s", cur_epoch + 1, raw_word_count, trained_word_count, elapsed, trained_word_count / elapsed @@ -677,6 +1202,20 @@ def _log_epoch_end(self, cur_epoch, example_count, total_examples, raw_word_coun ) def _log_train_end(self, raw_word_count, trained_word_count, total_elapsed, job_tally): + """Callback to log the end of training. + + Parameters + ---------- + raw_word_count : int + Number of words used in the whole training. + trained_word_count : int + Number of effective words used in training (after ignoring unknown words and trimming the sentence length). + total_elapsed : int + Total time spent during training in seconds. + job_tally : int + Total number of jobs processed during training. + + """ logger.info( "training on a %i raw words (%i effective words) took %.1fs, %.0f effective words/s", raw_word_count, trained_word_count, total_elapsed, trained_word_count / total_elapsed @@ -689,73 +1228,84 @@ def _log_train_end(self, raw_word_count, trained_word_count, total_elapsed, job_ # for backward compatibility @deprecated("Method will be removed in 4.0.0, use self.wv.most_similar() instead") def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=None, indexer=None): - """ - Deprecated. Use self.wv.most_similar() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar` + """Deprecated, use self.wv.most_similar() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar`. + """ return self.wv.most_similar(positive, negative, topn, restrict_vocab, indexer) @deprecated("Method will be removed in 4.0.0, use self.wv.wmdistance() instead") def wmdistance(self, document1, document2): - """ - Deprecated. Use self.wv.wmdistance() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.wmdistance` + """Deprecated, use self.wv.wmdistance() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.wmdistance`. + """ return self.wv.wmdistance(document1, document2) @deprecated("Method will be removed in 4.0.0, use self.wv.most_similar_cosmul() instead") def most_similar_cosmul(self, positive=None, negative=None, topn=10): - """ - Deprecated. Use self.wv.most_similar_cosmul() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar_cosmul` + """Deprecated, use self.wv.most_similar_cosmul() instead. + + Refer to the documentation for + :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar_cosmul`. + """ return self.wv.most_similar_cosmul(positive, negative, topn) @deprecated("Method will be removed in 4.0.0, use self.wv.similar_by_word() instead") def similar_by_word(self, word, topn=10, restrict_vocab=None): - """ - Deprecated. Use self.wv.similar_by_word() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similar_by_word` + """Deprecated, use self.wv.similar_by_word() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similar_by_word`. + """ return self.wv.similar_by_word(word, topn, restrict_vocab) @deprecated("Method will be removed in 4.0.0, use self.wv.similar_by_vector() instead") def similar_by_vector(self, vector, topn=10, restrict_vocab=None): - """ - Deprecated. Use self.wv.similar_by_vector() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similar_by_vector` + """Deprecated, use self.wv.similar_by_vector() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similar_by_vector`. + """ return self.wv.similar_by_vector(vector, topn, restrict_vocab) @deprecated("Method will be removed in 4.0.0, use self.wv.doesnt_match() instead") def doesnt_match(self, words): - """ - Deprecated. Use self.wv.doesnt_match() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.doesnt_match` + """Deprecated, use self.wv.doesnt_match() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.doesnt_match`. + """ return self.wv.doesnt_match(words) @deprecated("Method will be removed in 4.0.0, use self.wv.similarity() instead") def similarity(self, w1, w2): - """ - Deprecated. Use self.wv.similarity() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similarity` + """Deprecated, use self.wv.similarity() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similarity`. + """ return self.wv.similarity(w1, w2) @deprecated("Method will be removed in 4.0.0, use self.wv.n_similarity() instead") def n_similarity(self, ws1, ws2): - """ - Deprecated. Use self.wv.n_similarity() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.n_similarity` + """Deprecated, use self.wv.n_similarity() instead. + + Refer to the documentation for :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.n_similarity`. + """ return self.wv.n_similarity(ws1, ws2) @deprecated("Method will be removed in 4.0.0, use self.wv.evaluate_word_pairs() instead") def evaluate_word_pairs(self, pairs, delimiter='\t', restrict_vocab=300000, case_insensitive=True, dummy4unknown=False): - """ - Deprecated. Use self.wv.evaluate_word_pairs() instead. - Refer to the documentation for `gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.evaluate_word_pairs` + """Deprecated, use self.wv.evaluate_word_pairs() instead. + + Refer to the documentation for + :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.evaluate_word_pairs`. + """ return self.wv.evaluate_word_pairs(pairs, delimiter, restrict_vocab, case_insensitive, dummy4unknown) diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py index f79f0153a5..c2cfd1e16d 100644 --- a/gensim/models/doc2vec.py +++ b/gensim/models/doc2vec.py @@ -5,43 +5,51 @@ # Copyright (C) 2018 RaRe Technologies s.r.o. # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html +"""Learn paragraph and document embeddings via the distributed memory and distributed bag of words models from +`Quoc Le and Tomas Mikolov: "Distributed Representations of Sentences and Documents" +`_. -""" -Deep learning via the distributed memory and distributed bag of words models from -[1]_, using either hierarchical softmax or negative sampling [2]_ [3]_. See [#tutorial]_ - -**Make sure you have a C compiler before installing gensim, to use optimized (compiled) -doc2vec training** (70x speedup [blog]_). +The algorithms use either hierarchical softmax or negative sampling; see +`Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean: "Efficient Estimation of Word Representations in +Vector Space, in Proceedings of Workshop at ICLR, 2013" `_ and +`Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean: "Distributed Representations of Words +and Phrases and their Compositionality. In Proceedings of NIPS, 2013" +`_. -Initialize a model with e.g.:: +For a usage example, see the `Doc2vec tutorial +`_. ->>> model = Doc2Vec(documents, size=100, window=8, min_count=5, workers=4) +**Make sure you have a C compiler before installing Gensim, to use the optimized doc2vec routines** (70x speedup +compared to plain NumPy implementation `_). -Persist a model to disk with:: - ->>> model.save(fname) ->>> model = Doc2Vec.load(fname) # you can continue training with the loaded model! -If you're finished training a model (=no more updates, only querying), you can do +Examples +-------- - >>> model.delete_temporary_training_data(keep_doctags_vectors=True, keep_inference=True): +Initialize & train a model -to trim unneeded model memory = use (much) less RAM. +>>> from gensim.test.utils import common_texts +>>> from gensim.models.doc2vec import Doc2Vec, TaggedDocument +>>> +>>> documents = [TaggedDocument(doc, [i]) for i, doc in enumerate(common_texts)] +>>> model = Doc2Vec(documents, vector_size=5, window=2, min_count=1, workers=4) +Persist a model to disk +>>> from gensim.test.utils import get_tmpfile +>>> +>>> fname = get_tmpfile("my_doc2vec_model") +>>> +>>> model.save(fname) +>>> model = Doc2Vec.load(fname) # you can continue training with the loaded model! -.. [1] Quoc Le and Tomas Mikolov. Distributed Representations of Sentences and Documents. - http://arxiv.org/pdf/1405.4053v2.pdf -.. [2] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. - Efficient Estimation of Word Representations in Vector Space. In Proceedings of Workshop at ICLR, 2013. -.. [3] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. - Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of NIPS, 2013. -.. [blog] Optimizing word2vec in gensim, http://radimrehurek.com/2013/09/word2vec-in-python-part-two-optimizing/ +If you're finished training a model (=no more updates, only querying, reduce memory usage), you can do -.. [#tutorial] Doc2vec in gensim tutorial, - https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/doc2vec-lee.ipynb +>>> model.delete_temporary_training_data(keep_doctags_vectors=True, keep_inference=True) +Infer vector for new document +>>> vector = model.infer_vector(["system", "response"]) """ @@ -85,20 +93,53 @@ def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): - """ - Update distributed bag of words model ("PV-DBOW") by training on a single document. - Called internally from `Doc2Vec.train()` and `Doc2Vec.infer_vector()`. - The document is provided as `doc_words`, a list of word tokens which are looked up - in the model's vocab dictionary, and `doctag_indexes`, which provide indexes - into the doctag_vectors array. - If `train_words` is True, simultaneously train word-to-word (not just doc-to-word) - examples, exactly as per Word2Vec skip-gram training. (Without this option, - word vectors are neither consulted nor updated during DBOW doc vector training.) - Any of `learn_doctags', `learn_words`, and `learn_hidden` may be set False to - prevent learning-updates to those respective model weights, as if using the - (partially-)frozen model to infer other compatible vectors. + """Update distributed bag of words model ("PV-DBOW") by training on a single document. + + Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`. + + Notes + ----- This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from doc2vec_inner instead. + will use the optimized version from :mod:`gensim.models.doc2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.doc2vec.Doc2Vec` + The model to train. + doc_words : list of str + The input document as a list of words to be used for training. Each word will be looked up in + the model's vocabulary. + doctag_indexes : list of int + Indices into `doctag_vectors` used to obtain the tags of the document. + alpha : float + Learning rate. + work : np.ndarray + Private working memory for each worker. + train_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_doctags : bool, optional + Whether the tag vectors should be updated. + learn_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_hidden : bool, optional + Whether or not the weights of the hidden layer will be updated. + word_vectors : object, optional + UNUSED. + word_locks : object, optional + UNUSED. + doctag_vectors : list of list of float, optional + Vector representations of the tags. If None, these will be retrieved from the model. + doctag_locks : list of float, optional + The lock factors for each tag. + + Returns + ------- + int + Number of words in the input document. + """ if doctag_vectors is None: doctag_vectors = model.docvecs.doctag_syn0 @@ -119,21 +160,55 @@ def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): - """ - Update distributed memory model ("PV-DM") by training on a single document. - Called internally from `Doc2Vec.train()` and `Doc2Vec.infer_vector()`. This - method implements the DM model with a projection (input) layer that is - either the sum or mean of the context vectors, depending on the model's - `dm_mean` configuration field. See `train_document_dm_concat()` for the DM - model with a concatenated input layer. - The document is provided as `doc_words`, a list of word tokens which are looked up - in the model's vocab dictionary, and `doctag_indexes`, which provide indexes - into the doctag_vectors array. - Any of `learn_doctags', `learn_words`, and `learn_hidden` may be set False to - prevent learning-updates to those respective model weights, as if using the - (partially-)frozen model to infer other compatible vectors. - This is the non-optimized, Python version. If you have a C compiler, gensim - will use the optimized version from doc2vec_inner instead. + """Update distributed memory model ("PV-DM") by training on a single document. + + Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`. This method implements + the DM model with a projection (input) layer that is either the sum or mean of + the context vectors, depending on the model's `dm_mean` configuration field. + + Notes + ----- + This is the non-optimized, Python version. If you have cython installed, gensim + will use the optimized version from :mod:`gensim.models.doc2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.doc2vec.Doc2Vec` + The model to train. + doc_words : list of str + The input document as a list of words to be used for training. Each word will be looked up in + the model's vocabulary. + doctag_indexes : list of int + Indices into `doctag_vectors` used to obtain the tags of the document. + alpha : float + Learning rate. + work : object + UNUSED. + neu1 : object + UNUSED. + learn_doctags : bool, optional + Whether the tag vectors should be updated. + learn_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_hidden : bool, optional + Whether or not the weights of the hidden layer will be updated. + word_vectors : iterable of list of float, optional + Vector representations of each word in the model's vocabulary. + word_locks : list of float, optional + Lock factors for each word in the vocabulary. + doctag_vectors : list of list of float, optional + Vector representations of the tags. If None, these will be retrieved from the model. + doctag_locks : list of float, optional + The lock factors for each tag. + + Returns + ------- + int + Number of words in the input document that were actually used for training (they were found in the + vocabulary and they were not discarded by negative sampling). + """ if word_vectors is None: word_vectors = model.wv.syn0 @@ -172,18 +247,55 @@ def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=N def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): - """ - Update distributed memory model ("PV-DM") by training on a single document, using a - concatenation of the context window word vectors (rather than a sum or average). - Called internally from `Doc2Vec.train()` and `Doc2Vec.infer_vector()`. - The document is provided as `doc_words`, a list of word tokens which are looked up - in the model's vocab dictionary, and `doctag_indexes`, which provide indexes - into the doctag_vectors array. - Any of `learn_doctags', `learn_words`, and `learn_hidden` may be set False to - prevent learning-updates to those respective model weights, as if using the - (partially-)frozen model to infer other compatible vectors. - This is the non-optimized, Python version. If you have a C compiler, gensim - will use the optimized version from doc2vec_inner instead. + """Update distributed memory model ("PV-DM") by training on a single document, using a + concatenation of the context window word vectors (rather than a sum or average). This + might be slower since the input at each batch will be significantly larger. + + Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`. + + Notes + ----- + This is the non-optimized, Python version. If you have cython installed, gensim + will use the optimized version from :mod:`gensim.models.doc2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.doc2vec.Doc2Vec` + The model to train. + doc_words : list of str + The input document as a list of words to be used for training. Each word will be looked up in + the model's vocabulary. + doctag_indexes : list of int + Indices into `doctag_vectors` used to obtain the tags of the document. + alpha : float + Learning rate. + work : object + UNUSED. + neu1 : object + UNUSED. + learn_doctags : bool, optional + Whether the tag vectors should be updated. + learn_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_hidden : bool, optional + Whether or not the weights of the hidden layer will be updated. + word_vectors : iterable of list of float, optional + Vector representations of each word in the model's vocabulary. + word_locks : listf of float, optional + Lock factors for each word in the vocabulary. + doctag_vectors : list of list of float, optional + Vector representations of the tags. If None, these will be retrieved from the model. + doctag_locks : list of float, optional + The lock factors for each tag. + + Returns + ------- + int + Number of words in the input document that were actually used for training (they were found in the + vocabulary and they were not discarded by negative sampling). + """ if word_vectors is None: word_vectors = model.wv.syn0 @@ -234,36 +346,49 @@ def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, class TaggedDocument(namedtuple('TaggedDocument', 'words tags')): - """ - A single document, made up of `words` (a list of unicode string tokens) - and `tags` (a list of tokens). Tags may be one or more unicode string - tokens, but typical practice (which will also be most memory-efficient) is - for the tags list to include a unique integer id as the only tag. + """Represents a document along with a tag, input document format for :class:`~gensim.models.doc2vec.Doc2Vec`. - Replaces "sentence as a list of words" from Word2Vec. + A single document, made up of `words` (a list of unicode string tokens) and `tags` (a list of tokens). + Tags may be one or more unicode string tokens, but typical practice (which will also be the most memory-efficient) + is for the tags list to include a unique integer id as the only tag. - """ + Replaces "sentence as a list of words" from :class:`gensim.models.word2vec.Word2Vec`. + """ def __str__(self): + """Human readable representation of the object's state, used for debugging. + + Returns + ------- + str + Human readable representation of the object's state (words and tags). + + """ return '%s(%s, %s)' % (self.__class__.__name__, self.words, self.tags) # for compatibility @deprecated("Class will be removed in 4.0.0, use TaggedDocument instead") class LabeledSentence(TaggedDocument): + """Deprecated, use :class:`~gensim.models.doc2vec.TaggedDocument` instead.""" pass class Doctag(namedtuple('Doctag', 'offset, word_count, doc_count')): - """A string document tag discovered during the initial vocabulary - scan. (The document-vector equivalent of a Vocab object.) + """A string document tag discovered during the initial vocabulary scan. + The document-vector equivalent of a Vocab object. Will not be used if all presented document tags are ints. - The offset is only the true index into the doctags_syn0/doctags_syn0_lockf - if-and-only-if no raw-int tags were used. If any raw-int tags were used, - string Doctag vectors begin at index (max_rawint + 1), so the true index is - (rawint_index + 1 + offset). See also _index_to_doctag(). + The offset is only the true index into the `doctags_syn0`/`doctags_syn0_lockf` + if-and-only-if no raw-int tags were used. + If any raw-int tags were used, string :class:`~gensim.models.doc2vec.Doctag` vectors begin at index + `(max_rawint + 1)`, so the true index is `(rawint_index + 1 + offset)`. + + See Also + -------- + :meth:`~gensim.models.keyedvectors.Doc2VecKeyedVectors._index_to_doctag` + """ __slots__ = () @@ -272,86 +397,124 @@ def repeat(self, word_count): class Doc2Vec(BaseWordEmbeddingsModel): - """Class for training, using and evaluating neural networks described in http://arxiv.org/pdf/1405.4053v2.pdf""" + """Class for training, using and evaluating neural networks described in + `Distributed Representations of Sentences and Documents `_. + + Some important internal attributes are the following: + + Attributes + ---------- + wv : :class:`~gensim.models.keyedvectors.Word2VecKeyedVectors` + This object essentially contains the mapping between words and embeddings. After training, it can be used + directly to query those embeddings in various ways. See the module level docstring for examples. + + docvecs : :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` + This object contains the paragraph vectors. Remember that the only difference between this model and + :class:`~gensim.models.word2vec.Word2Vec` is that besides the word vectors we also include paragraph embeddings + to capture the paragraph. + + In this way we can capture the difference between the same word used in a different context. + For example we now have a different representation of the word "leaves" in the following two sentences :: + + 1. Manos leaves the office every day at 18:00 to catch his train + 2. This season is called Fall, because leaves fall from the trees. + + In a plain :class:`~gensim.models.word2vec.Word2Vec` model the word would have exactly the same representation + in both sentences, in :class:`~gensim.models.doc2vec.Doc2Vec` it will not. + vocabulary : :class:`~gensim.models.doc2vec.Doc2VecVocab` + This object represents the vocabulary (sometimes called Dictionary in gensim) of the model. + Besides keeping track of all unique words, this object provides extra functionality, such as + sorting words by frequency, or discarding extremely rare words. + + trainables : :class:`~gensim.models.doc2vec.Doc2VecTrainables` + This object represents the inner shallow neural network used to train the embeddings. The semantics of the + network differ slightly in the two available training modes (CBOW or SG) but you can think of it as a NN with + a single projection and hidden layer which we train on the corpus. The weights are then used as our embeddings + The only addition to the underlying NN used in :class:`~gensim.models.word2vec.Word2Vec` is that the input + includes not only the word vectors of each word in the context, but also the paragraph vector. + + """ def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0, dm_tag_count=1, docvecs=None, docvecs_mapfile=None, comment=None, trim_rule=None, callbacks=(), **kwargs): - """Initialize the model from an iterable of `documents`. Each document is a - TaggedDocument object that will be used for training. + """ Parameters ---------- - documents : iterable of iterables - The `documents` iterable can be simply a list of TaggedDocument elements, but for larger corpora, - consider an iterable that streams the documents directly from disk/network. - If you don't supply `documents`, the model is left uninitialized -- use if - you plan to initialize it in some other way. - - dm : int {1,0} + documents : iterable of list of :class:`~gensim.models.doc2vec.TaggedDocument`, optional + Input corpus, can be simply a list of elements, but for larger corpora,consider an iterable that streams + the documents directly from disk/network. If you don't supply `documents`, the model is + left uninitialized -- use if you plan to initialize it in some other way. + dm : {1,0}, optional Defines the training algorithm. If `dm=1`, 'distributed memory' (PV-DM) is used. Otherwise, `distributed bag of words` (PV-DBOW) is employed. - - size : int + size : int, optional Dimensionality of the feature vectors. - window : int + window : int, optional The maximum distance between the current and predicted word within a sentence. - alpha : float + alpha : float, optional The initial learning rate. - min_alpha : float + min_alpha : float, optional Learning rate will linearly drop to `min_alpha` as training progresses. - seed : int + seed : int, optional Seed for the random number generator. Initial vectors for each word are seeded with a hash of the concatenation of word + `str(seed)`. Note that for a fully deterministically-reproducible run, you must also limit the model to a single worker thread (`workers=1`), to eliminate ordering jitter - from OS thread scheduling. (In Python 3, reproducibility between interpreter launches also requires - use of the `PYTHONHASHSEED` environment variable to control hash randomization). - min_count : int + from OS thread scheduling. + In Python 3, reproducibility between interpreter launches also requires use of the `PYTHONHASHSEED` + environment variable to control hash randomization. + min_count : int, optional Ignores all words with total frequency lower than this. - max_vocab_size : int + max_vocab_size : int, optional Limits the RAM during vocabulary building; if there are more unique words than this, then prune the infrequent ones. Every 10 million word types need about 1GB of RAM. Set to `None` for no limit. - sample : float + sample : float, optional The threshold for configuring which higher-frequency words are randomly downsampled, useful range is (0, 1e-5). - workers : int + workers : int, optional Use these many worker threads to train the model (=faster training with multicore machines). - iter : int + iter : int, optional Number of iterations (epochs) over the corpus. - hs : int {1,0} + hs : {1,0}, optional If 1, hierarchical softmax will be used for model training. If set to 0, and `negative` is non-zero, negative sampling will be used. - negative : int + negative : int, optional If > 0, negative sampling will be used, the int for negative specifies how many "noise words" should be drawn (usually between 5-20). If set to 0, no negative sampling is used. - dm_mean : int {1,0} + dm_mean : {1,0}, optional If 0 , use the sum of the context word vectors. If 1, use the mean. Only applies when `dm` is used in non-concatenative mode. - dm_concat : int {1,0} + dm_concat : {1,0}, optional If 1, use concatenation of context vectors rather than sum/average; Note concatenation results in a much-larger model, as the input is no longer the size of one (sampled or arithmetically combined) word vector, but the size of the tag(s) and all words in the context strung together. - dm_tag_count : int + dm_tag_count : int, optional Expected constant number of document tags per document, when using - dm_concat mode; default is 1. - dbow_words : int {1,0} + dm_concat mode. + dbow_words : {1,0}, optional If set to 1 trains word-vectors (in skip-gram fashion) simultaneous with DBOW doc-vector training; If 0, only trains doc-vectors (faster). - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part + The rule, if given, is only used to prune vocabulary during current method call and is not stored as part of the model. - callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec` + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec`, optional List of callbacks that need to be executed/run at specific stages during training. """ - if 'sentences' in kwargs: raise DeprecationWarning( "Parameter 'sentences' was renamed to 'documents', and will be removed in 4.0.0, " @@ -407,28 +570,41 @@ def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0 @property def dm(self): - """int {1,0} : `dm=1` indicates 'distributed memory' (PV-DM) else - `distributed bag of words` (PV-DBOW) is used.""" + """Indicates whether 'distributed memory' (PV-DM) will be used, else 'distributed bag of words' + (PV-DBOW) is used. + + """ return not self.sg # opposite of SG @property def dbow(self): - """int {1,0} : `dbow=1` indicates `distributed bag of words` (PV-DBOW) else - 'distributed memory' (PV-DM) is used.""" + """Indicates whether 'distributed bag of words' (PV-DBOW) will be used, else 'distributed memory' + (PV-DM) is used. + + """ return self.sg # same as SG def _set_train_params(self, **kwargs): pass def _clear_post_train(self): + """Alias for :meth:`~gensim.models.doc2vec.Doc2Vec.clear_sims`.""" self.clear_sims() def clear_sims(self): + """Resets the current word vectors. """ self.wv.vectors_norm = None self.wv.vectors_docs_norm = None def reset_from(self, other_model): - """Reuse shareable structures from other_model.""" + """Copy shareable data structures from another (possibly pre-trained) model. + + Parameters + ---------- + other_model : :class:`~gensim.models.doc2vec.Doc2Vec` + Other model whose internal data structures will be copied over to the current object. + + """ self.wv.vocab = other_model.wv.vocab self.wv.index2word = other_model.wv.index2word self.vocabulary.cum_table = other_model.vocabulary.cum_table @@ -439,6 +615,23 @@ def reset_from(self, other_model): self.trainables.reset_weights(self.hs, self.negative, self.wv, self.docvecs) def _do_train_job(self, job, alpha, inits): + """Train model using `job` data. + + Parameters + ---------- + job : iterable of list of :class:`~gensim.models.doc2vec.TaggedDocument` + The corpus chunk to be used for training this batch. + alpha : float + Learning rate to be used for training this batch. + inits : (np.ndarray, np.ndarray) + Each worker threads private work memory. + + Returns + ------- + (int, int) + 2-tuple (effective word count after ignoring unknown words and sentence length trimming, total word count). + + """ work, neu1 = inits tally = 0 for doc in job: @@ -465,46 +658,52 @@ def _do_train_job(self, job, alpha, inits): def train(self, documents, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, callbacks=()): - """Update the model's neural weights from a sequence of sentences (can be a once-only generator stream). - The `documents` iterable can be simply a list of TaggedDocument elements. + """Update the model's neural weights. - To support linear learning-rate decay from (initial) alpha to min_alpha, and accurate - progress-percentage logging, either total_examples (count of sentences) or total_words (count of - raw words in sentences) **MUST** be provided (if the corpus is the same as was provided to - :meth:`~gensim.models.word2vec.Word2Vec.build_vocab()`, the count of examples in that corpus - will be available in the model's :attr:`corpus_count` property). + To support linear learning-rate decay from (initial) `alpha` to `min_alpha`, and accurate + progress-percentage logging, either `total_examples` (count of sentences) or `total_words` (count of + raw words in sentences) **MUST** be provided. If `sentences` is the same corpus + that was provided to :meth:`~gensim.models.word2vec.Word2Vec.build_vocab` earlier, + you can simply use `total_examples=self.corpus_count`. To avoid common mistakes around the model's ability to do multiple training passes itself, an - explicit `epochs` argument **MUST** be provided. In the common and recommended case, - where :meth:`~gensim.models.word2vec.Word2Vec.train()` is only called once, - the model's cached `iter` value should be supplied as `epochs` value. + explicit `epochs` argument **MUST** be provided. In the common and recommended case + where :meth:`~gensim.models.word2vec.Word2Vec.train` is only called once, + you can set `epochs=self.iter`. Parameters ---------- - documents : iterable of iterables - The `documents` iterable can be simply a list of TaggedDocument elements, but for larger corpora, - consider an iterable that streams the documents directly from disk/network. - See :class:`~gensim.models.doc2vec.TaggedBrownCorpus` or :class:`~gensim.models.doc2vec.TaggedLineDocument` - in :mod:`~gensim.models.doc2vec` module for such examples. - total_examples : int + documents : iterable of list of :class:`~gensim.models.doc2vec.TaggedDocument` + Can be simply a list of elements, but for larger corpora,consider an iterable that streams + the documents directly from disk/network. If you don't supply `documents`, the model is + left uninitialized -- use if you plan to initialize it in some other way. + total_examples : int, optional Count of sentences. - total_words : int + total_words : int, optional Count of raw words in documents. - epochs : int + epochs : int, optional Number of iterations (epochs) over the corpus. - start_alpha : float - Initial learning rate. - end_alpha : float + start_alpha : float, optional + Initial learning rate. If supplied, replaces the starting `alpha` from the constructor, + for this one call to `train`. + Use only if making multiple calls to `train`, when you want to manage the alpha learning-rate yourself + (not recommended). + end_alpha : float, optional Final learning rate. Drops linearly from `start_alpha`. - word_count : int + If supplied, this replaces the final `min_alpha` from the constructor, for this one call to + :meth:`~gensim.models.doc2vec.Doc2Vec.train`. + Use only if making multiple calls to :meth:`~gensim.models.doc2vec.Doc2Vec.train`, when you want to manage + the alpha learning-rate yourself (not recommended). + word_count : int, optional Count of words already trained. Set this to 0 for the usual case of training on all words in sentences. - queue_factor : int + queue_factor : int, optional Multiplier for size of queue (number of workers * queue_factor). - report_delay : float + report_delay : float, optional Seconds to wait before reporting progress. - callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec` + callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec`, optional List of callbacks that need to be executed/run at specific stages during training. + """ super(Doc2Vec, self).train( documents, total_examples=total_examples, total_words=total_words, @@ -512,32 +711,56 @@ def train(self, documents, total_examples=None, total_words=None, queue_factor=queue_factor, report_delay=report_delay, callbacks=callbacks) def _raw_word_count(self, job): - """Return the number of words in a given job.""" + """Get the number of words in a given job. + + Parameters + ---------- + job : iterable of list of :class:`~gensim.models.doc2vec.TaggedDocument` + Corpus chunk. + + Returns + ------- + int + Number of raw words in the corpus chunk. + + """ return sum(len(sentence.words) for sentence in job) def estimated_lookup_memory(self): - """Estimated memory for tag lookup; 0 if using pure int tags.""" + """Get estimated memory for tag lookup, 0 if using pure int tags. + + Returns + ------- + int + The estimated RAM required to look up a tag in bytes. + + """ return 60 * len(self.docvecs.offset2doctag) + 140 * len(self.docvecs.doctags) def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): - """ - Infer a vector for given post-bulk training document. + """Infer a vector for given post-bulk training document. + + Notes + ----- + Subsequent calls to this function may infer different representations for the same document. + For a more stable representation, increase the number of steps to assert a stricket convergence. Parameters ---------- - doc_words : :obj: `list` of :obj: `str` - Document should be a list of (word) tokens. - alpha : float + doc_words : list of str + A document for which the vector representation will be inferred. + alpha : float, optional The initial learning rate. - min_alpha : float + min_alpha : float, optional Learning rate will linearly drop to `min_alpha` as training progresses. - steps : int - Number of times to train the new document. + steps : int, optional + Number of times to train the new document. A higher value may slow down training, but it will result in more + stable representations. Returns ------- - :obj: `numpy.ndarray` - Returns the inferred vector for the new document. + np.ndarray + The inferred paragraph vector for the new document. """ doctag_vectors, doctag_locks = self.trainables.get_doctag_trainables(doc_words, self.docvecs.vector_size) @@ -569,6 +792,19 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): return doctag_vectors[0] def __getitem__(self, tag): + """Get the vector representation of (possible multi-term) tag. + + Parameters + ---------- + tag : {str, int, list of str, list of int} + The tag (or tags) to be looked up in the model. + + Returns + ------- + np.ndarray + The vector representations of each tag as a matrix (will be 1D if `tag` was a single tag) + + """ if isinstance(tag, string_types + integer_types + (integer,)): if tag not in self.wv.vocab: return self.docvecs[tag] @@ -576,7 +812,14 @@ def __getitem__(self, tag): return vstack([self[i] for i in tag]) def __str__(self): - """Abbreviated name reflecting major configuration paramaters.""" + """Abbreviated name reflecting major configuration parameters. + + Returns + ------- + str + Human readable representation of the models internal state. + + """ segments = [] if self.comment: segments.append('"%s"' % self.comment) @@ -614,11 +857,13 @@ def delete_temporary_training_data(self, keep_doctags_vectors=True, keep_inferen Parameters ---------- - keep_doctags_vectors : bool - Set `keep_doctags_vectors` to False if you don't want to save doctags vectors, - in this case you can't to use docvecs's most_similar, similarity etc. methods. - keep_inference : bool - Set `keep_inference` to False if you don't want to store parameters that is used for infer_vector method + keep_doctags_vectors : bool, optional + Set to False if you don't want to save doctags vectors. In this case you will not be able to use + :meth:`~gensim.models.keyedvectors.Doc2VecKeyedVectors.most_similar`, + :meth:`~gensim.models.keyedvectors.Doc2VecKeyedVectors.similarity`, etc methods. + keep_inference : bool, optional + Set to False if you don't want to store parameters that are used for + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector` method. """ if not keep_inference: @@ -635,24 +880,23 @@ def delete_temporary_training_data(self, keep_doctags_vectors=True, keep_inferen del self.trainables.vectors_docs_lockf def save_word2vec_format(self, fname, doctag_vec=False, word_vec=True, prefix='*dt_', fvocab=None, binary=False): - """Store the input-hidden weight matrix in the same format used by the original - C word2vec-tool, for compatibility. + """Store the input-hidden weight matrix in the same format used by the original C word2vec-tool. Parameters ---------- fname : str The file path used to save the vectors in. - doctag_vec : bool + doctag_vec : bool, optional Indicates whether to store document vectors. - word_vec : bool + word_vec : bool, optional Indicates whether to store word vectors. - prefix : str - Uniquely identifies doctags from word vocab, and avoids collision - in case of repeated string in doctag and word vocab. - fvocab : str - Optional file path used to save the vocabulary - binary : bool - If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. + prefix : str, optional + Uniquely identifies doctags from word vocab, and avoids collision in case of repeated string in doctag + and word vocab. + fvocab : str, optional + Optional file path used to save the vocabulary. + binary : bool, optional + If True, the data wil be saved in binary word2vec format, otherwise - will be saved in plain text. """ total_vec = len(self.wv.vocab) + len(self.docvecs) @@ -672,21 +916,41 @@ def save_word2vec_format(self, fname, doctag_vec=False, word_vec=True, prefix='* binary=binary, write_first_line=write_first_line) def init_sims(self, replace=False): - """ - Precompute L2-normalized vectors. + """Pre-compute L2-normalized vectors. - If `replace` is set, forget the original vectors and only keep the normalized - ones = saves lots of memory! - - Note that you **cannot continue training or inference** after doing a replace. - The model becomes effectively read-only = you can call `most_similar`, `similarity` - etc., but not `train` or `infer_vector`. + Parameters + ---------- + replace : bool + If True - forget the original vectors and only keep the normalized ones to saved RAM (also you can't + continue training if call it with `replace=True`). """ - return self.docvecs.init_sims(replace=replace) + self.docvecs.init_sims(replace=replace) @classmethod def load(cls, *args, **kwargs): + """Load a previously saved :class:`~gensim.models.doc2vec.Doc2Vec` model. + + Parameters + ---------- + fname : str + Path to the saved file. + *args : object + Additional arguments, see `~gensim.models.base_any2vec.BaseWordEmbeddingsModel.load`. + **kwargs : object + Additional arguments, see `~gensim.models.base_any2vec.BaseWordEmbeddingsModel.load`. + + See Also + -------- + :meth:`~gensim.models.doc2vec.Doc2Vec.save` + Save :class:`~gensim.models.doc2vec.Doc2Vec` model. + + Returns + ------- + :class:`~gensim.models.doc2vec.Doc2Vec` + Loaded model. + + """ try: return super(Doc2Vec, cls).load(*args, **kwargs) except AttributeError: @@ -695,7 +959,24 @@ def load(cls, *args, **kwargs): return load_old_doc2vec(*args, **kwargs) def estimate_memory(self, vocab_size=None, report=None): - """Estimate required memory for a model using current settings.""" + """Estimate required memory for a model using current settings. + + Parameters + ---------- + vocab_size : int, optional + Number of raw words in the vocabulary. + report : dict of (str, int), optional + A dictionary from string representations of the **specific** model's memory consuming members + to their size in bytes. + + Returns + ------- + dict of (str, int), optional + A dictionary from string representations of the model's memory consuming members to their size in bytes. + Includes members from the base classes as well as weights and tag lookup memory estimation specific to the + class. + + """ report = report or {} report['doctag_lookup'] = self.estimated_lookup_memory() report['doctag_syn0'] = self.docvecs.count * self.vector_size * dtype(REAL).itemsize @@ -703,29 +984,36 @@ def estimate_memory(self, vocab_size=None, report=None): def build_vocab(self, documents, update=False, progress_per=10000, keep_raw_vocab=False, trim_rule=None, **kwargs): """Build vocabulary from a sequence of sentences (can be a once-only generator stream). - Each sentence is a iterable of iterables (can simply be a list of unicode strings too). Parameters ---------- - documents : iterable of iterables - The `documents` iterable can be simply a list of TaggedDocument elements, but for larger corpora, + documents : iterable of list of :class:`~gensim.models.doc2vec.TaggedDocument` + Can be simply a list of :class:`~gensim.models.doc2vec.TaggedDocument` elements, but for larger corpora, consider an iterable that streams the documents directly from disk/network. See :class:`~gensim.models.doc2vec.TaggedBrownCorpus` or :class:`~gensim.models.doc2vec.TaggedLineDocument` - in :mod:`~gensim.models.doc2vec` module for such examples. + update : bool + If true, the new words in `sentences` will be added to model's vocab. + progress_per : int + Indicates how many words to process before showing/updating the progress. keep_raw_vocab : bool If not true, delete the raw vocabulary after the scaling is done and free up RAM. - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part + The rule, if given, is only used to prune vocabulary during current method call and is not stored as part of the model. - progress_per : int - Indicates how many words to process before showing/updating the progress. - update : bool - If true, the new words in `sentences` will be added to model's vocab. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + **kwargs + Additional key word arguments passed to the internal vocabulary construction. + """ total_words, corpus_count = self.vocabulary.scan_vocab( documents, self.docvecs, progress_per=progress_per, trim_rule=trim_rule) @@ -739,35 +1027,36 @@ def build_vocab(self, documents, update=False, progress_per=10000, keep_raw_voca self.hs, self.negative, self.wv, self.docvecs, update=update) def build_vocab_from_freq(self, word_freq, keep_raw_vocab=False, corpus_count=None, trim_rule=None, update=False): - """ - Build vocabulary from a dictionary of word frequencies. - Build model vocabulary from a passed dictionary that contains (word,word count). + """Build vocabulary from a dictionary of word frequencies. + + Build model vocabulary from a passed dictionary that contains a (word -> word count) mapping. Words must be of type unicode strings. Parameters ---------- - word_freq : dict - Word,Word_Count dictionary. - keep_raw_vocab : bool + word_freq : dict of (str, int) + Word <-> count mapping. + keep_raw_vocab : bool, optional If not true, delete the raw vocabulary after the scaling is done and free up RAM. - corpus_count : int + corpus_count : int, optional Even if no corpus is provided, this argument can set corpus_count explicitly. - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part - of the model. - update : bool + The rule, if given, is only used to prune vocabulary during + :meth:`~gensim.models.doc2vec.Doc2Vec.build_vocab` and is not stored as part of the model. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + update : bool, optional If true, the new provided words in `word_freq` dict will be added to model's vocab. - Examples - -------- - >>> from gensim.models.word2vec import Word2Vec - >>> model= Word2Vec() - >>> model.build_vocab_from_freq({"Word1": 15, "Word2": 20}) """ logger.info("Processing provided word frequencies") # Instead of scanning text, this will assign provided word frequencies dictionary(word_freq) @@ -792,12 +1081,67 @@ def build_vocab_from_freq(self, word_freq, keep_raw_vocab=False, corpus_count=No class Doc2VecVocab(Word2VecVocab): + """Vocabulary used by :class:`~gensim.models.doc2vec.Doc2Vec`. + + This includes a mapping from words found in the corpus to their total frequency count. + + """ def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0): + """ + + Parameters + ---------- + max_vocab_size : int, optional + Maximum number of words in the Vocabulary. Used to limit the RAM during vocabulary building; + if there are more unique words than this, then prune the infrequent ones. + Every 10 million word types need about 1GB of RAM, set to `None` for no limit. + min_count : int + Words with frequency lower than this limit will be discarded form the vocabulary. + sample : float, optional + The threshold for configuring which higher-frequency words are randomly downsampled, + useful range is (0, 1e-5). + sorted_vocab : bool + If True, sort the vocabulary by descending frequency before assigning word indexes. + null_word : {0, 1} + If True, a null pseudo-word will be created for padding when using concatenative L1 (run-of-words). + This word is only ever input – never predicted – so count, huffman-point, etc doesn't matter. + + """ super(Doc2VecVocab, self).__init__( max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, sorted_vocab=sorted_vocab, null_word=null_word) def scan_vocab(self, documents, docvecs, progress_per=10000, trim_rule=None): + """Create the models Vocabulary: A mapping from unique words in the corpus to their frequency count. + + Parameters + ---------- + documents : iterable of :class:`~gensim.models.doc2vec.TaggedDocument` + The tagged documents used to create the vocabulary. Their tags can be either str tokens or ints (faster). + docvecs : list of :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` + The vector representations of the documents in our corpus. Each of them has a size == `vector_size`. + progress_per : int + Progress will be logged every `progress_per` documents. + trim_rule : function, optional + Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, + be trimmed away, or handled using the default (discard if word count < min_count). + Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), + or a callable that accepts parameters (word, count, min_count) and returns either + :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. + The rule, if given, is only used to prune vocabulary during + :meth:`~gensim.models.doc2vec.Doc2Vec.build_vocab` and is not stored as part of the model. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + Returns + ------- + (int, int) + Tuple of (Total words in the corpus, number of documents) + + """ logger.info("collecting all words and their counts") document_no = -1 total_words = 0 @@ -845,7 +1189,20 @@ def scan_vocab(self, documents, docvecs, progress_per=10000, trim_rule=None): return total_words, corpus_count def note_doctag(self, key, document_no, document_length, docvecs): - """Note a document tag during initial corpus scan, for structure sizing.""" + """Note a document tag during initial corpus scan, for correctly setting the keyedvectors size. + + Parameters + ---------- + key : {int, str} + The tag to be noted. + document_no : int + The document's index in `docvecs`. Unused. + document_length : int + The document's length in words. + docvecs : list of :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` + Vector representations of the documents in the corpus. Each vector has size == `vector_size` + + """ if isinstance(key, integer_types + (integer,)): docvecs.max_rawint = max(docvecs.max_rawint, key) else: @@ -857,12 +1214,41 @@ def note_doctag(self, key, document_no, document_length, docvecs): docvecs.count = docvecs.max_rawint + 1 + len(docvecs.offset2doctag) def indexed_doctags(self, doctag_tokens, docvecs): - """Return indexes and backing-arrays used in training examples.""" + """Get the indexes and backing-arrays used in training examples. + + Parameters + ---------- + doctag_tokens : list of {str, int} + A list of tags for which we want the index. + docvecs : list of :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` + Vector representations of the documents in the corpus. Each vector has size == `vector_size` + + Returns + ------- + list of int + Indices of the provided tag keys. + + """ return [ Doc2VecKeyedVectors._int_index(index, docvecs.doctags, docvecs.max_rawint) for index in doctag_tokens if self._tag_seen(index, docvecs)] def _tag_seen(self, index, docvecs): + """Whether or not the tag exists in our Vocabulary. + + Parameters + ---------- + index : {str, int} + The tag to be checked. + docvecs : :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` + Vector representations of the documents in the corpus. Each vector has size == `vector_size` + + Returns + ------- + bool + Whether or not the passed tag exists in our vocabulary. + + """ if isinstance(index, integer_types + (integer,)): return index < docvecs.count else: @@ -870,6 +1256,7 @@ def _tag_seen(self, index, docvecs): class Doc2VecTrainables(Word2VecTrainables): + """Represents the inner shallow neural network used to train :class:`~gensim.models.doc2vec.Doc2Vec`.""" def __init__(self, dm=1, dm_concat=0, dm_tag_count=1, vector_size=100, seed=1, hashfxn=hash, window=5): super(Doc2VecTrainables, self).__init__( vector_size=vector_size, seed=seed, hashfxn=hashfxn) @@ -917,13 +1304,28 @@ def get_doctag_trainables(self, doc_words, vector_size): class TaggedBrownCorpus(object): - """Iterate over documents from the Brown corpus (part of NLTK data), yielding - each document out as a TaggedDocument object.""" + """Reader for the `Brown corpus (part of NLTK data) `_.""" def __init__(self, dirname): + """ + + Parameters + ---------- + dirname : str + Path to folder with Brown corpus. + + """ self.dirname = dirname def __iter__(self): + """Iterate through the corpus. + + Yields + ------ + :class:`~gensim.models.doc2vec.TaggedDocument` + Document from `source`. + + """ for fname in os.listdir(self.dirname): fname = os.path.join(self.dirname, fname) if not os.path.isfile(fname): @@ -941,29 +1343,40 @@ def __iter__(self): class TaggedLineDocument(object): - """Simple format: one document = one line = one TaggedDocument object. + """Iterate over a file that contains sentences: one line = :class:`~gensim.models.doc2vec.TaggedDocument` object. - Words are expected to be already preprocessed and separated by whitespace, - tags are constructed automatically from the document line number.""" + Words are expected to be already preprocessed and separated by whitespace. Document tags are constructed + automatically from the document line number (each document gets a unique integer tag). + """ def __init__(self, source): """ - `source` can be either a string (filename) or a file object. - - Example:: - - documents = TaggedLineDocument('myfile.txt') - Or for compressed files:: + Parameters + ---------- + source : string or a file-like object + Path to the file on disk, or an already-open file object (must support `seek(0)`). - documents = TaggedLineDocument('compressed_text.txt.bz2') - documents = TaggedLineDocument('compressed_text.txt.gz') + Examples + -------- + >>> from gensim.test.utils import datapath + >>> from gensim.models.doc2vec import TaggedLineDocument + >>> + >>> for document in TaggedLineDocument(datapath("head500.noblanks.cor")): + ... pass """ self.source = source def __iter__(self): - """Iterate through the lines in the source.""" + """Iterate through the lines in the source. + + Yields + ------ + :class:`~gensim.models.doc2vec.TaggedDocument` + Document from `source` specified in the constructor. + + """ try: # Assume it is a file-like object and try treating it as such # Things that don't have seek will trigger an exception diff --git a/gensim/models/doc2vec_inner.c b/gensim/models/doc2vec_inner.c index 103f34da81..56d0478e05 100644 --- a/gensim/models/doc2vec_inner.c +++ b/gensim/models/doc2vec_inner.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.27.3 */ +/* Generated by Cython 0.28.3 */ #define PY_SSIZE_T_CLEAN #include "Python.h" @@ -7,7 +7,7 @@ #elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.6+ or Python 3.3+. #else -#define CYTHON_ABI "0_27_3" +#define CYTHON_ABI "0_28_3" #define CYTHON_FUTURE_DIVISION 0 #include #ifndef offsetof @@ -183,6 +183,103 @@ #undef BASE #undef MASK #endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) #define Py_OptimizeFlag 0 #endif @@ -211,12 +308,12 @@ #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif -#if PY_VERSION_HEX < 0x030700A0 || !defined(METH_FASTCALL) +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif - typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject **args, Py_ssize_t nargs); - typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject **args, + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast @@ -228,6 +325,18 @@ #else #define __Pyx_PyFastCFunction_Check(func) 0 #endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif #if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x03060000 @@ -237,6 +346,36 @@ #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; // PyThread_create_key reports success always +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif // TSS (Thread Specific Storage) API #if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else @@ -249,6 +388,11 @@ #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif #if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ @@ -293,18 +437,6 @@ #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif -#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) - #define PyObject_Malloc(s) PyMem_Malloc(s) - #define PyObject_Free(p) PyMem_Free(p) - #define PyObject_Realloc(p) PyMem_Realloc(p) -#endif -#if CYTHON_COMPILING_IN_PYSTON - #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) -#else - #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) -#endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 @@ -321,6 +453,7 @@ #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact + #define PyObject_Unicode PyObject_Str #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) @@ -332,7 +465,11 @@ #ifndef PySet_CheckExact #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) #endif -#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type @@ -367,16 +504,10 @@ #define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t #endif #if PY_MAJOR_VERSION >= 3 - #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func)) + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : (Py_INCREF(func), func)) #else #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) #endif -#ifndef __has_attribute - #define __has_attribute(x) 0 -#endif -#ifndef __has_cpp_attribute - #define __has_cpp_attribute(x) 0 -#endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods @@ -394,96 +525,6 @@ unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif -#ifndef CYTHON_RESTRICT - #if defined(__GNUC__) - #define CYTHON_RESTRICT __restrict__ - #elif defined(_MSC_VER) && _MSC_VER >= 1400 - #define CYTHON_RESTRICT __restrict - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_RESTRICT restrict - #else - #define CYTHON_RESTRICT - #endif -#endif -#ifndef CYTHON_UNUSED -# if defined(__GNUC__) -# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -#endif -#ifndef CYTHON_MAYBE_UNUSED_VAR -# if defined(__cplusplus) - template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } -# else -# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) -# endif -#endif -#ifndef CYTHON_NCP_UNUSED -# if CYTHON_COMPILING_IN_CPYTHON -# define CYTHON_NCP_UNUSED -# else -# define CYTHON_NCP_UNUSED CYTHON_UNUSED -# endif -#endif -#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) -#ifdef _MSC_VER - #ifndef _MSC_STDINT_H_ - #if _MSC_VER < 1300 - typedef unsigned char uint8_t; - typedef unsigned int uint32_t; - #else - typedef unsigned __int8 uint8_t; - typedef unsigned __int32 uint32_t; - #endif - #endif -#else - #include -#endif -#ifndef CYTHON_FALLTHROUGH - #if defined(__cplusplus) && __cplusplus >= 201103L - #if __has_cpp_attribute(fallthrough) - #define CYTHON_FALLTHROUGH [[fallthrough]] - #elif __has_cpp_attribute(clang::fallthrough) - #define CYTHON_FALLTHROUGH [[clang::fallthrough]] - #elif __has_cpp_attribute(gnu::fallthrough) - #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] - #endif - #endif - #ifndef CYTHON_FALLTHROUGH - #if __has_attribute(fallthrough) - #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) - #else - #define CYTHON_FALLTHROUGH - #endif - #endif - #if defined(__clang__ ) && defined(__apple_build_version__) - #if __apple_build_version__ < 7000000 - #undef CYTHON_FALLTHROUGH - #define CYTHON_FALLTHROUGH - #endif - #endif -#endif - -#ifndef CYTHON_INLINE - #if defined(__clang__) - #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) - #elif defined(__GNUC__) - #define CYTHON_INLINE __inline__ - #elif defined(_MSC_VER) - #define CYTHON_INLINE __inline - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_INLINE inline - #else - #define CYTHON_INLINE - #endif -#endif #if defined(WIN32) || defined(MS_WINDOWS) #define _USE_MATH_DEFINES @@ -520,11 +561,11 @@ static CYTHON_INLINE float __PYX_NAN() { #define __PYX_HAVE__gensim__models__doc2vec_inner #define __PYX_HAVE_API__gensim__models__doc2vec_inner +/* Early includes */ #include #include #include "numpy/arrayobject.h" #include "numpy/ufuncobject.h" -#include #include "voidptr.h" #ifdef _OPENMP #include @@ -610,7 +651,7 @@ static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) -#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False)) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ @@ -718,7 +759,7 @@ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } static PyObject *__pyx_m = NULL; static PyObject *__pyx_d; static PyObject *__pyx_b; -static PyObject *__pyx_cython_runtime; +static PyObject *__pyx_cython_runtime = NULL; static PyObject *__pyx_empty_tuple; static PyObject *__pyx_empty_bytes; static PyObject *__pyx_empty_unicode; @@ -768,7 +809,7 @@ static const char *__pyx_f[] = { #endif -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":743 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":730 * # in Cython to enable them only on the right systems. * * ctypedef npy_int8 int8_t # <<<<<<<<<<<<<< @@ -777,7 +818,7 @@ static const char *__pyx_f[] = { */ typedef npy_int8 __pyx_t_5numpy_int8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":731 * * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t # <<<<<<<<<<<<<< @@ -786,7 +827,7 @@ typedef npy_int8 __pyx_t_5numpy_int8_t; */ typedef npy_int16 __pyx_t_5numpy_int16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":732 * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t # <<<<<<<<<<<<<< @@ -795,7 +836,7 @@ typedef npy_int16 __pyx_t_5numpy_int16_t; */ typedef npy_int32 __pyx_t_5numpy_int32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":746 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":733 * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t * ctypedef npy_int64 int64_t # <<<<<<<<<<<<<< @@ -804,7 +845,7 @@ typedef npy_int32 __pyx_t_5numpy_int32_t; */ typedef npy_int64 __pyx_t_5numpy_int64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":750 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":737 * #ctypedef npy_int128 int128_t * * ctypedef npy_uint8 uint8_t # <<<<<<<<<<<<<< @@ -813,7 +854,7 @@ typedef npy_int64 __pyx_t_5numpy_int64_t; */ typedef npy_uint8 __pyx_t_5numpy_uint8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":751 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":738 * * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t # <<<<<<<<<<<<<< @@ -822,7 +863,7 @@ typedef npy_uint8 __pyx_t_5numpy_uint8_t; */ typedef npy_uint16 __pyx_t_5numpy_uint16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":752 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":739 * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t # <<<<<<<<<<<<<< @@ -831,7 +872,7 @@ typedef npy_uint16 __pyx_t_5numpy_uint16_t; */ typedef npy_uint32 __pyx_t_5numpy_uint32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":753 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":740 * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t * ctypedef npy_uint64 uint64_t # <<<<<<<<<<<<<< @@ -840,7 +881,7 @@ typedef npy_uint32 __pyx_t_5numpy_uint32_t; */ typedef npy_uint64 __pyx_t_5numpy_uint64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":757 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 * #ctypedef npy_uint128 uint128_t * * ctypedef npy_float32 float32_t # <<<<<<<<<<<<<< @@ -849,7 +890,7 @@ typedef npy_uint64 __pyx_t_5numpy_uint64_t; */ typedef npy_float32 __pyx_t_5numpy_float32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 * * ctypedef npy_float32 float32_t * ctypedef npy_float64 float64_t # <<<<<<<<<<<<<< @@ -858,7 +899,7 @@ typedef npy_float32 __pyx_t_5numpy_float32_t; */ typedef npy_float64 __pyx_t_5numpy_float64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":754 * # The int types are mapped a bit surprising -- * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t # <<<<<<<<<<<<<< @@ -867,7 +908,7 @@ typedef npy_float64 __pyx_t_5numpy_float64_t; */ typedef npy_long __pyx_t_5numpy_int_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":768 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":755 * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t * ctypedef npy_longlong long_t # <<<<<<<<<<<<<< @@ -876,7 +917,7 @@ typedef npy_long __pyx_t_5numpy_int_t; */ typedef npy_longlong __pyx_t_5numpy_long_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":756 * ctypedef npy_long int_t * ctypedef npy_longlong long_t * ctypedef npy_longlong longlong_t # <<<<<<<<<<<<<< @@ -885,7 +926,7 @@ typedef npy_longlong __pyx_t_5numpy_long_t; */ typedef npy_longlong __pyx_t_5numpy_longlong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 * ctypedef npy_longlong longlong_t * * ctypedef npy_ulong uint_t # <<<<<<<<<<<<<< @@ -894,7 +935,7 @@ typedef npy_longlong __pyx_t_5numpy_longlong_t; */ typedef npy_ulong __pyx_t_5numpy_uint_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":772 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":759 * * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t # <<<<<<<<<<<<<< @@ -903,7 +944,7 @@ typedef npy_ulong __pyx_t_5numpy_uint_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":760 * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t * ctypedef npy_ulonglong ulonglong_t # <<<<<<<<<<<<<< @@ -912,7 +953,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":762 * ctypedef npy_ulonglong ulonglong_t * * ctypedef npy_intp intp_t # <<<<<<<<<<<<<< @@ -921,7 +962,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; */ typedef npy_intp __pyx_t_5numpy_intp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":763 * * ctypedef npy_intp intp_t * ctypedef npy_uintp uintp_t # <<<<<<<<<<<<<< @@ -930,7 +971,7 @@ typedef npy_intp __pyx_t_5numpy_intp_t; */ typedef npy_uintp __pyx_t_5numpy_uintp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":765 * ctypedef npy_uintp uintp_t * * ctypedef npy_double float_t # <<<<<<<<<<<<<< @@ -939,7 +980,7 @@ typedef npy_uintp __pyx_t_5numpy_uintp_t; */ typedef npy_double __pyx_t_5numpy_float_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":766 * * ctypedef npy_double float_t * ctypedef npy_double double_t # <<<<<<<<<<<<<< @@ -948,7 +989,7 @@ typedef npy_double __pyx_t_5numpy_float_t; */ typedef npy_double __pyx_t_5numpy_double_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":780 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 * ctypedef npy_double float_t * ctypedef npy_double double_t * ctypedef npy_longdouble longdouble_t # <<<<<<<<<<<<<< @@ -992,7 +1033,7 @@ static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(do /*--- Type declarations ---*/ -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 * ctypedef npy_longdouble longdouble_t * * ctypedef npy_cfloat cfloat_t # <<<<<<<<<<<<<< @@ -1001,7 +1042,7 @@ static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(do */ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":783 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":770 * * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t # <<<<<<<<<<<<<< @@ -1010,7 +1051,7 @@ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; */ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t * ctypedef npy_clongdouble clongdouble_t # <<<<<<<<<<<<<< @@ -1019,7 +1060,7 @@ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; */ typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":786 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 * ctypedef npy_clongdouble clongdouble_t * * ctypedef npy_cdouble complex_t # <<<<<<<<<<<<<< @@ -1166,16 +1207,7 @@ typedef void (*__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr)(int const /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_getattro)) - return tp->tp_getattro(obj, attr_name); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_getattr)) - return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); -#endif - return PyObject_GetAttr(obj, attr_name); -} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif @@ -1214,24 +1246,6 @@ static CYTHON_INLINE int __Pyx_PySequence_ContainsTF(PyObject* item, PyObject* s return unlikely(result < 0) ? result : (result == (eq == Py_EQ)); } -/* PyFunctionFastCall.proto */ -#if CYTHON_FAST_PYCALL -#define __Pyx_PyFunction_FastCall(func, args, nargs)\ - __Pyx_PyFunction_FastCallDict((func), (args), (nargs), NULL) -#if 1 || PY_VERSION_HEX < 0x030600B1 -static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, int nargs, PyObject *kwargs); -#else -#define __Pyx_PyFunction_FastCallDict(func, args, nargs, kwargs) _PyFunction_FastCallDict(func, args, nargs, kwargs) -#endif -#endif - -/* PyCFunctionFastCall.proto */ -#if CYTHON_FAST_PYCCALL -static CYTHON_INLINE PyObject *__Pyx_PyCFunction_FastCall(PyObject *func, PyObject **args, Py_ssize_t nargs); -#else -#define __Pyx_PyCFunction_FastCall(func, args, nargs) (assert(0), NULL) -#endif - /* GetItemInt.proto */ #define __Pyx_GetItemInt(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ @@ -1254,6 +1268,42 @@ static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j); static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, int is_list, int wraparound, int boundscheck); +/* ObjectGetItem.proto */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key); +#else +#define __Pyx_PyObject_GetItem(obj, key) PyObject_GetItem(obj, key) +#endif + +/* PyFunctionFastCall.proto */ +#if CYTHON_FAST_PYCALL +#define __Pyx_PyFunction_FastCall(func, args, nargs)\ + __Pyx_PyFunction_FastCallDict((func), (args), (nargs), NULL) +#if 1 || PY_VERSION_HEX < 0x030600B1 +static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, int nargs, PyObject *kwargs); +#else +#define __Pyx_PyFunction_FastCallDict(func, args, nargs, kwargs) _PyFunction_FastCallDict(func, args, nargs, kwargs) +#endif +#endif + +/* PyCFunctionFastCall.proto */ +#if CYTHON_FAST_PYCCALL +static CYTHON_INLINE PyObject *__Pyx_PyCFunction_FastCall(PyObject *func, PyObject **args, Py_ssize_t nargs); +#else +#define __Pyx_PyCFunction_FastCall(func, args, nargs) (assert(0), NULL) +#endif + +/* DictGetItem.proto */ +#if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key); +#define __Pyx_PyObject_Dict_GetItem(obj, name)\ + (likely(PyDict_CheckExact(obj)) ?\ + __Pyx_PyDict_GetItem(obj, name) : PyObject_GetItem(obj, name)) +#else +#define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyObject_Dict_GetItem(obj, name) PyObject_GetItem(obj, name) +#endif + /* PyThreadStateGet.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_PyThreadState_declare PyThreadState *__pyx_tstate; @@ -1293,27 +1343,14 @@ static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject /* RaiseException.proto */ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause); -/* DictGetItem.proto */ -#if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY -static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { - PyObject *value; - value = PyDict_GetItemWithError(d, key); - if (unlikely(!value)) { - if (!PyErr_Occurred()) { - PyObject* args = PyTuple_Pack(1, key); - if (likely(args)) - PyErr_SetObject(PyExc_KeyError, args); - Py_XDECREF(args); - } - return NULL; - } - Py_INCREF(value); - return value; -} -#else - #define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +/* PyObjectCallMethO.proto */ +#if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg); #endif +/* PyObjectCallOneArg.proto */ +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg); + /* RaiseTooManyValuesToUnpack.proto */ static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected); @@ -1518,6 +1555,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) #define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) #endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) /* CheckBinaryVersion.proto */ static int __Pyx_check_binary_version(void); @@ -1578,8 +1616,6 @@ static PyTypeObject *__pyx_ptype_5numpy_ndarray = 0; static PyTypeObject *__pyx_ptype_5numpy_ufunc = 0; static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *, char *, char *, int *); /*proto*/ -/* Module declarations from 'libc.math' */ - /* Module declarations from 'gensim.models.word2vec_inner' */ static __pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr *__pyx_vp_6gensim_6models_14word2vec_inner_scopy = 0; #define __pyx_v_6gensim_6models_14word2vec_inner_scopy (*__pyx_vp_6gensim_6models_14word2vec_inner_scopy) @@ -1599,10 +1635,6 @@ static __pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr *__pyx_vp_6gensim_6m #define __pyx_v_6gensim_6models_14word2vec_inner_our_dot (*__pyx_vp_6gensim_6models_14word2vec_inner_our_dot) static __pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr *__pyx_vp_6gensim_6models_14word2vec_inner_our_saxpy = 0; #define __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy (*__pyx_vp_6gensim_6models_14word2vec_inner_our_saxpy) -static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t (*__pyx_f_6gensim_6models_14word2vec_inner_our_dot_double)(int const *, float const *, int const *, float const *, int const *); /*proto*/ -static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t (*__pyx_f_6gensim_6models_14word2vec_inner_our_dot_float)(int const *, float const *, int const *, float const *, int const *); /*proto*/ -static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t (*__pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas)(int const *, float const *, int const *, float const *, int const *); /*proto*/ -static void (*__pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas)(int const *, float const *, float const *, int const *, float *, int const *); /*proto*/ static unsigned PY_LONG_LONG (*__pyx_f_6gensim_6models_14word2vec_inner_bisect_left)(__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG); /*proto*/ static unsigned PY_LONG_LONG (*__pyx_f_6gensim_6models_14word2vec_inner_random_int32)(unsigned PY_LONG_LONG *); /*proto*/ @@ -1676,7 +1708,6 @@ static const char __pyx_k_vectors[] = "vectors"; static const char __pyx_k_vlookup[] = "vlookup"; static const char __pyx_k_codelens[] = "codelens"; static const char __pyx_k_negative[] = "negative"; -static const char __pyx_k_word2vec[] = "word2vec"; static const char __pyx_k_cbow_mean[] = "cbow_mean"; static const char __pyx_k_cum_table[] = "cum_table"; static const char __pyx_k_doc_words[] = "doc_words"; @@ -1694,7 +1725,6 @@ static const char __pyx_k_learn_words[] = "learn_words"; static const char __pyx_k_next_random[] = "next_random"; static const char __pyx_k_train_words[] = "train_words"; static const char __pyx_k_vector_size[] = "vector_size"; -static const char __pyx_k_FAST_VERSION[] = "FAST_VERSION"; static const char __pyx_k_RuntimeError[] = "RuntimeError"; static const char __pyx_k_dm_tag_count[] = "dm_tag_count"; static const char __pyx_k_doctag_locks[] = "doctag_locks"; @@ -1734,10 +1764,10 @@ static const char __pyx_k_numpy_core_multiarray_failed_to[] = "numpy.core.multia static const char __pyx_k_unknown_dtype_code_in_numpy_pxd[] = "unknown dtype code in numpy.pxd (%d)"; static const char __pyx_k_Format_string_allocated_too_shor[] = "Format string allocated too short, see comment in numpy.pxd"; static const char __pyx_k_Non_native_byte_order_not_suppor[] = "Non-native byte order not supported"; +static const char __pyx_k_Optimized_cython_functions_for_t[] = "Optimized cython functions for training :class:`~gensim.models.doc2vec.Doc2Vec` model."; static const char __pyx_k_ndarray_is_not_Fortran_contiguou[] = "ndarray is not Fortran contiguous"; static const char __pyx_k_numpy_core_umath_failed_to_impor[] = "numpy.core.umath failed to import"; static const char __pyx_k_Format_string_allocated_too_shor_2[] = "Format string allocated too short."; -static PyObject *__pyx_n_s_FAST_VERSION; static PyObject *__pyx_kp_u_Format_string_allocated_too_shor; static PyObject *__pyx_kp_u_Format_string_allocated_too_shor_2; static PyObject *__pyx_n_s_ImportError; @@ -1840,7 +1870,6 @@ static PyObject *__pyx_n_s_vocab; static PyObject *__pyx_n_s_vocabulary; static PyObject *__pyx_n_s_window; static PyObject *__pyx_n_s_window_indexes; -static PyObject *__pyx_n_s_word2vec; static PyObject *__pyx_n_s_word_locks; static PyObject *__pyx_n_s_word_locks_2; static PyObject *__pyx_n_s_word_vectors; @@ -1877,8 +1906,9 @@ static PyObject *__pyx_tuple__22; static PyObject *__pyx_codeobj__19; static PyObject *__pyx_codeobj__21; static PyObject *__pyx_codeobj__23; +/* Late includes */ -/* "gensim/models/doc2vec_inner.pyx":41 +/* "gensim/models/doc2vec_inner.pyx":37 * DEF MAX_EXP = 6 * * cdef void fast_document_dbow_hs( # <<<<<<<<<<<<<< @@ -1893,11 +1923,12 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_f; __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_g; int __pyx_t_1; - PY_LONG_LONG __pyx_t_2; - int __pyx_t_3; + int __pyx_t_2; + PY_LONG_LONG __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/doc2vec_inner.pyx":48 + /* "gensim/models/doc2vec_inner.pyx":44 * * cdef long long a, b * cdef long long row1 = context_index * size, row2 # <<<<<<<<<<<<<< @@ -1906,16 +1937,16 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_row1 = (__pyx_v_context_index * __pyx_v_size); - /* "gensim/models/doc2vec_inner.pyx":51 + /* "gensim/models/doc2vec_inner.pyx":47 * cdef REAL_t f, g * * memset(work, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * for b in range(codelen): * row2 = word_point[b] * size */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/doc2vec_inner.pyx":52 + /* "gensim/models/doc2vec_inner.pyx":48 * * memset(work, 0, size * cython.sizeof(REAL_t)) * for b in range(codelen): # <<<<<<<<<<<<<< @@ -1923,10 +1954,11 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = __pyx_v_codelen; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_b = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_b = __pyx_t_3; - /* "gensim/models/doc2vec_inner.pyx":53 + /* "gensim/models/doc2vec_inner.pyx":49 * memset(work, 0, size * cython.sizeof(REAL_t)) * for b in range(codelen): * row2 = word_point[b] * size # <<<<<<<<<<<<<< @@ -1935,7 +1967,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_size); - /* "gensim/models/doc2vec_inner.pyx":54 + /* "gensim/models/doc2vec_inner.pyx":50 * for b in range(codelen): * row2 = word_point[b] * size * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -1944,25 +1976,25 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), (&(__pyx_v_context_vectors[__pyx_v_row1])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":55 + /* "gensim/models/doc2vec_inner.pyx":51 * row2 = word_point[b] * size * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L6_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L6_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":56 + /* "gensim/models/doc2vec_inner.pyx":52 * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -1971,7 +2003,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":55 + /* "gensim/models/doc2vec_inner.pyx":51 * row2 = word_point[b] * size * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -1980,7 +2012,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ } - /* "gensim/models/doc2vec_inner.pyx":57 + /* "gensim/models/doc2vec_inner.pyx":53 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -1989,7 +2021,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/doc2vec_inner.pyx":58 + /* "gensim/models/doc2vec_inner.pyx":54 * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha # <<<<<<<<<<<<<< @@ -1998,7 +2030,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_g = (((1 - (__pyx_v_word_code[__pyx_v_b])) - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/doc2vec_inner.pyx":59 + /* "gensim/models/doc2vec_inner.pyx":55 * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2007,17 +2039,17 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":60 + /* "gensim/models/doc2vec_inner.pyx":56 * g = (1 - word_code[b] - f) * alpha * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if learn_context: */ - __pyx_t_3 = (__pyx_v_learn_hidden != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_hidden != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":61 + /* "gensim/models/doc2vec_inner.pyx":57 * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2026,7 +2058,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_context_vectors[__pyx_v_row1])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":60 + /* "gensim/models/doc2vec_inner.pyx":56 * g = (1 - word_code[b] - f) * alpha * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< @@ -2037,17 +2069,17 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ __pyx_L3_continue:; } - /* "gensim/models/doc2vec_inner.pyx":62 + /* "gensim/models/doc2vec_inner.pyx":58 * if learn_hidden: * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if learn_context: # <<<<<<<<<<<<<< * our_saxpy(&size, &context_locks[context_index], work, &ONE, &context_vectors[row1], &ONE) * */ - __pyx_t_3 = (__pyx_v_learn_context != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_context != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":63 + /* "gensim/models/doc2vec_inner.pyx":59 * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if learn_context: * our_saxpy(&size, &context_locks[context_index], work, &ONE, &context_vectors[row1], &ONE) # <<<<<<<<<<<<<< @@ -2056,7 +2088,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&(__pyx_v_context_locks[__pyx_v_context_index])), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_context_vectors[__pyx_v_row1])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":62 + /* "gensim/models/doc2vec_inner.pyx":58 * if learn_hidden: * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1[row2], &ONE) * if learn_context: # <<<<<<<<<<<<<< @@ -2065,7 +2097,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ */ } - /* "gensim/models/doc2vec_inner.pyx":41 + /* "gensim/models/doc2vec_inner.pyx":37 * DEF MAX_EXP = 6 * * cdef void fast_document_dbow_hs( # <<<<<<<<<<<<<< @@ -2076,7 +2108,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs(__pyx_ /* function exit code */ } -/* "gensim/models/doc2vec_inner.pyx":66 +/* "gensim/models/doc2vec_inner.pyx":62 * * * cdef unsigned long long fast_document_dbow_neg( # <<<<<<<<<<<<<< @@ -2095,11 +2127,12 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume int __pyx_v_d; unsigned PY_LONG_LONG __pyx_r; long __pyx_t_1; - int __pyx_t_2; + long __pyx_t_2; int __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/doc2vec_inner.pyx":73 + /* "gensim/models/doc2vec_inner.pyx":69 * * cdef long long a * cdef long long row1 = context_index * size, row2 # <<<<<<<<<<<<<< @@ -2108,7 +2141,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_row1 = (__pyx_v_context_index * __pyx_v_size); - /* "gensim/models/doc2vec_inner.pyx":74 + /* "gensim/models/doc2vec_inner.pyx":70 * cdef long long a * cdef long long row1 = context_index * size, row2 * cdef unsigned long long modulo = 281474976710655ULL # <<<<<<<<<<<<<< @@ -2117,16 +2150,16 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_modulo = 281474976710655ULL; - /* "gensim/models/doc2vec_inner.pyx":79 + /* "gensim/models/doc2vec_inner.pyx":75 * cdef int d * * memset(work, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * * for d in range(negative+1): */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/doc2vec_inner.pyx":81 + /* "gensim/models/doc2vec_inner.pyx":77 * memset(work, 0, size * cython.sizeof(REAL_t)) * * for d in range(negative+1): # <<<<<<<<<<<<<< @@ -2134,20 +2167,21 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume * target_index = word_index */ __pyx_t_1 = (__pyx_v_negative + 1); - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; - /* "gensim/models/doc2vec_inner.pyx":82 + /* "gensim/models/doc2vec_inner.pyx":78 * * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< * target_index = word_index * label = ONEF */ - __pyx_t_3 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":83 + /* "gensim/models/doc2vec_inner.pyx":79 * for d in range(negative+1): * if d == 0: * target_index = word_index # <<<<<<<<<<<<<< @@ -2156,7 +2190,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_target_index = __pyx_v_word_index; - /* "gensim/models/doc2vec_inner.pyx":84 + /* "gensim/models/doc2vec_inner.pyx":80 * if d == 0: * target_index = word_index * label = ONEF # <<<<<<<<<<<<<< @@ -2165,7 +2199,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_label = __pyx_v_6gensim_6models_13doc2vec_inner_ONEF; - /* "gensim/models/doc2vec_inner.pyx":82 + /* "gensim/models/doc2vec_inner.pyx":78 * * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< @@ -2175,7 +2209,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume goto __pyx_L5; } - /* "gensim/models/doc2vec_inner.pyx":86 + /* "gensim/models/doc2vec_inner.pyx":82 * label = ONEF * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) # <<<<<<<<<<<<<< @@ -2185,7 +2219,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume /*else*/ { __pyx_v_target_index = __pyx_f_6gensim_6models_14word2vec_inner_bisect_left(__pyx_v_cum_table, ((__pyx_v_next_random >> 16) % (__pyx_v_cum_table[(__pyx_v_cum_table_len - 1)])), 0, __pyx_v_cum_table_len); - /* "gensim/models/doc2vec_inner.pyx":87 + /* "gensim/models/doc2vec_inner.pyx":83 * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo # <<<<<<<<<<<<<< @@ -2194,17 +2228,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_next_random = (((__pyx_v_next_random * ((unsigned PY_LONG_LONG)25214903917ULL)) + 11) & __pyx_v_modulo); - /* "gensim/models/doc2vec_inner.pyx":88 + /* "gensim/models/doc2vec_inner.pyx":84 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: # <<<<<<<<<<<<<< * continue * label = 0.0 */ - __pyx_t_3 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":89 + /* "gensim/models/doc2vec_inner.pyx":85 * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: * continue # <<<<<<<<<<<<<< @@ -2213,7 +2247,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":88 + /* "gensim/models/doc2vec_inner.pyx":84 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: # <<<<<<<<<<<<<< @@ -2222,7 +2256,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":90 + /* "gensim/models/doc2vec_inner.pyx":86 * if target_index == word_index: * continue * label = 0.0 # <<<<<<<<<<<<<< @@ -2233,7 +2267,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume } __pyx_L5:; - /* "gensim/models/doc2vec_inner.pyx":91 + /* "gensim/models/doc2vec_inner.pyx":87 * continue * label = 0.0 * row2 = target_index * size # <<<<<<<<<<<<<< @@ -2242,7 +2276,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_row2 = (__pyx_v_target_index * __pyx_v_size); - /* "gensim/models/doc2vec_inner.pyx":92 + /* "gensim/models/doc2vec_inner.pyx":88 * label = 0.0 * row2 = target_index * size * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -2251,25 +2285,25 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), (&(__pyx_v_context_vectors[__pyx_v_row1])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":93 + /* "gensim/models/doc2vec_inner.pyx":89 * row2 = target_index * size * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L8_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L8_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":94 + /* "gensim/models/doc2vec_inner.pyx":90 * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2278,7 +2312,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":93 + /* "gensim/models/doc2vec_inner.pyx":89 * row2 = target_index * size * f = our_dot(&size, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2287,7 +2321,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":95 + /* "gensim/models/doc2vec_inner.pyx":91 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2296,7 +2330,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/doc2vec_inner.pyx":96 + /* "gensim/models/doc2vec_inner.pyx":92 * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha # <<<<<<<<<<<<<< @@ -2305,7 +2339,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_g = ((__pyx_v_label - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/doc2vec_inner.pyx":97 + /* "gensim/models/doc2vec_inner.pyx":93 * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2314,17 +2348,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":98 + /* "gensim/models/doc2vec_inner.pyx":94 * g = (label - f) * alpha * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if learn_context: */ - __pyx_t_3 = (__pyx_v_learn_hidden != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_hidden != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":99 + /* "gensim/models/doc2vec_inner.pyx":95 * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -2333,7 +2367,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_context_vectors[__pyx_v_row1])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":98 + /* "gensim/models/doc2vec_inner.pyx":94 * g = (label - f) * alpha * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< @@ -2344,17 +2378,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume __pyx_L3_continue:; } - /* "gensim/models/doc2vec_inner.pyx":100 + /* "gensim/models/doc2vec_inner.pyx":96 * if learn_hidden: * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if learn_context: # <<<<<<<<<<<<<< * our_saxpy(&size, &context_locks[context_index], work, &ONE, &context_vectors[row1], &ONE) * */ - __pyx_t_3 = (__pyx_v_learn_context != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_context != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":101 + /* "gensim/models/doc2vec_inner.pyx":97 * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if learn_context: * our_saxpy(&size, &context_locks[context_index], work, &ONE, &context_vectors[row1], &ONE) # <<<<<<<<<<<<<< @@ -2363,7 +2397,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&(__pyx_v_context_locks[__pyx_v_context_index])), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_context_vectors[__pyx_v_row1])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":100 + /* "gensim/models/doc2vec_inner.pyx":96 * if learn_hidden: * our_saxpy(&size, &g, &context_vectors[row1], &ONE, &syn1neg[row2], &ONE) * if learn_context: # <<<<<<<<<<<<<< @@ -2372,7 +2406,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":103 + /* "gensim/models/doc2vec_inner.pyx":99 * our_saxpy(&size, &context_locks[context_index], work, &ONE, &context_vectors[row1], &ONE) * * return next_random # <<<<<<<<<<<<<< @@ -2382,7 +2416,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume __pyx_r = __pyx_v_next_random; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":66 + /* "gensim/models/doc2vec_inner.pyx":62 * * * cdef unsigned long long fast_document_dbow_neg( # <<<<<<<<<<<<<< @@ -2395,7 +2429,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume return __pyx_r; } -/* "gensim/models/doc2vec_inner.pyx":106 +/* "gensim/models/doc2vec_inner.pyx":102 * * * cdef void fast_document_dm_hs( # <<<<<<<<<<<<<< @@ -2409,11 +2443,12 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_f; __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_g; int __pyx_t_1; - PY_LONG_LONG __pyx_t_2; - int __pyx_t_3; + int __pyx_t_2; + PY_LONG_LONG __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/doc2vec_inner.pyx":117 + /* "gensim/models/doc2vec_inner.pyx":113 * # l1 already composed by caller, passed in as neu1 * # work (also passed in) will accumulate l1 error * for b in range(word_code_len): # <<<<<<<<<<<<<< @@ -2421,10 +2456,11 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = __pyx_v_word_code_len; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_b = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_b = __pyx_t_3; - /* "gensim/models/doc2vec_inner.pyx":118 + /* "gensim/models/doc2vec_inner.pyx":114 * # work (also passed in) will accumulate l1 error * for b in range(word_code_len): * row2 = word_point[b] * size # <<<<<<<<<<<<<< @@ -2433,7 +2469,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_size); - /* "gensim/models/doc2vec_inner.pyx":119 + /* "gensim/models/doc2vec_inner.pyx":115 * for b in range(word_code_len): * row2 = word_point[b] * size * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2442,25 +2478,25 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":120 + /* "gensim/models/doc2vec_inner.pyx":116 * row2 = word_point[b] * size * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L6_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L6_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":121 + /* "gensim/models/doc2vec_inner.pyx":117 * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2469,7 +2505,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":120 + /* "gensim/models/doc2vec_inner.pyx":116 * row2 = word_point[b] * size * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2478,7 +2514,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ } - /* "gensim/models/doc2vec_inner.pyx":122 + /* "gensim/models/doc2vec_inner.pyx":118 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2487,7 +2523,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/doc2vec_inner.pyx":123 + /* "gensim/models/doc2vec_inner.pyx":119 * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha # <<<<<<<<<<<<<< @@ -2496,7 +2532,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ __pyx_v_g = (((1 - (__pyx_v_word_code[__pyx_v_b])) - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/doc2vec_inner.pyx":124 + /* "gensim/models/doc2vec_inner.pyx":120 * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2505,17 +2541,17 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":125 + /* "gensim/models/doc2vec_inner.pyx":121 * g = (1 - word_code[b] - f) * alpha * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< * our_saxpy(&size, &g, neu1, &ONE, &syn1[row2], &ONE) * */ - __pyx_t_3 = (__pyx_v_learn_hidden != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_hidden != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":126 + /* "gensim/models/doc2vec_inner.pyx":122 * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: * our_saxpy(&size, &g, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2524,7 +2560,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":125 + /* "gensim/models/doc2vec_inner.pyx":121 * g = (1 - word_code[b] - f) * alpha * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< @@ -2535,7 +2571,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ __pyx_L3_continue:; } - /* "gensim/models/doc2vec_inner.pyx":106 + /* "gensim/models/doc2vec_inner.pyx":102 * * * cdef void fast_document_dm_hs( # <<<<<<<<<<<<<< @@ -2546,7 +2582,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs(__pyx_t_ /* function exit code */ } -/* "gensim/models/doc2vec_inner.pyx":129 +/* "gensim/models/doc2vec_inner.pyx":125 * * * cdef unsigned long long fast_document_dm_neg( # <<<<<<<<<<<<<< @@ -2564,11 +2600,12 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume int __pyx_v_d; unsigned PY_LONG_LONG __pyx_r; long __pyx_t_1; - int __pyx_t_2; + long __pyx_t_2; int __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/doc2vec_inner.pyx":135 + /* "gensim/models/doc2vec_inner.pyx":131 * * cdef long long row2 * cdef unsigned long long modulo = 281474976710655ULL # <<<<<<<<<<<<<< @@ -2577,7 +2614,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_modulo = 281474976710655ULL; - /* "gensim/models/doc2vec_inner.pyx":142 + /* "gensim/models/doc2vec_inner.pyx":138 * # l1 already composed by caller, passed in as neu1 * # work (also passsed in) will accumulate l1 error for outside application * for d in range(negative+1): # <<<<<<<<<<<<<< @@ -2585,20 +2622,21 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume * target_index = predict_word_index */ __pyx_t_1 = (__pyx_v_negative + 1); - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; - /* "gensim/models/doc2vec_inner.pyx":143 + /* "gensim/models/doc2vec_inner.pyx":139 * # work (also passsed in) will accumulate l1 error for outside application * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< * target_index = predict_word_index * label = ONEF */ - __pyx_t_3 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":144 + /* "gensim/models/doc2vec_inner.pyx":140 * for d in range(negative+1): * if d == 0: * target_index = predict_word_index # <<<<<<<<<<<<<< @@ -2607,7 +2645,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_target_index = __pyx_v_predict_word_index; - /* "gensim/models/doc2vec_inner.pyx":145 + /* "gensim/models/doc2vec_inner.pyx":141 * if d == 0: * target_index = predict_word_index * label = ONEF # <<<<<<<<<<<<<< @@ -2616,7 +2654,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_label = __pyx_v_6gensim_6models_13doc2vec_inner_ONEF; - /* "gensim/models/doc2vec_inner.pyx":143 + /* "gensim/models/doc2vec_inner.pyx":139 * # work (also passsed in) will accumulate l1 error for outside application * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< @@ -2626,7 +2664,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume goto __pyx_L5; } - /* "gensim/models/doc2vec_inner.pyx":147 + /* "gensim/models/doc2vec_inner.pyx":143 * label = ONEF * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) # <<<<<<<<<<<<<< @@ -2636,7 +2674,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume /*else*/ { __pyx_v_target_index = __pyx_f_6gensim_6models_14word2vec_inner_bisect_left(__pyx_v_cum_table, ((__pyx_v_next_random >> 16) % (__pyx_v_cum_table[(__pyx_v_cum_table_len - 1)])), 0, __pyx_v_cum_table_len); - /* "gensim/models/doc2vec_inner.pyx":148 + /* "gensim/models/doc2vec_inner.pyx":144 * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo # <<<<<<<<<<<<<< @@ -2645,17 +2683,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_next_random = (((__pyx_v_next_random * ((unsigned PY_LONG_LONG)25214903917ULL)) + 11) & __pyx_v_modulo); - /* "gensim/models/doc2vec_inner.pyx":149 + /* "gensim/models/doc2vec_inner.pyx":145 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == predict_word_index: # <<<<<<<<<<<<<< * continue * label = 0.0 */ - __pyx_t_3 = ((__pyx_v_target_index == __pyx_v_predict_word_index) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_predict_word_index) != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":150 + /* "gensim/models/doc2vec_inner.pyx":146 * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == predict_word_index: * continue # <<<<<<<<<<<<<< @@ -2664,7 +2702,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":149 + /* "gensim/models/doc2vec_inner.pyx":145 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == predict_word_index: # <<<<<<<<<<<<<< @@ -2673,7 +2711,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":151 + /* "gensim/models/doc2vec_inner.pyx":147 * if target_index == predict_word_index: * continue * label = 0.0 # <<<<<<<<<<<<<< @@ -2684,7 +2722,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume } __pyx_L5:; - /* "gensim/models/doc2vec_inner.pyx":153 + /* "gensim/models/doc2vec_inner.pyx":149 * label = 0.0 * * row2 = target_index * size # <<<<<<<<<<<<<< @@ -2693,7 +2731,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_row2 = (__pyx_v_target_index * __pyx_v_size); - /* "gensim/models/doc2vec_inner.pyx":154 + /* "gensim/models/doc2vec_inner.pyx":150 * * row2 = target_index * size * f = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -2702,25 +2740,25 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":155 + /* "gensim/models/doc2vec_inner.pyx":151 * row2 = target_index * size * f = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L8_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L8_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":156 + /* "gensim/models/doc2vec_inner.pyx":152 * f = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2729,7 +2767,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":155 + /* "gensim/models/doc2vec_inner.pyx":151 * row2 = target_index * size * f = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2738,7 +2776,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":157 + /* "gensim/models/doc2vec_inner.pyx":153 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2747,7 +2785,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/doc2vec_inner.pyx":158 + /* "gensim/models/doc2vec_inner.pyx":154 * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha # <<<<<<<<<<<<<< @@ -2756,7 +2794,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_g = ((__pyx_v_label - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/doc2vec_inner.pyx":159 + /* "gensim/models/doc2vec_inner.pyx":155 * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2765,17 +2803,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":160 + /* "gensim/models/doc2vec_inner.pyx":156 * g = (label - f) * alpha * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< * our_saxpy(&size, &g, neu1, &ONE, &syn1neg[row2], &ONE) * */ - __pyx_t_3 = (__pyx_v_learn_hidden != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_hidden != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":161 + /* "gensim/models/doc2vec_inner.pyx":157 * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: * our_saxpy(&size, &g, neu1, &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -2784,7 +2822,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":160 + /* "gensim/models/doc2vec_inner.pyx":156 * g = (label - f) * alpha * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< @@ -2795,7 +2833,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume __pyx_L3_continue:; } - /* "gensim/models/doc2vec_inner.pyx":163 + /* "gensim/models/doc2vec_inner.pyx":159 * our_saxpy(&size, &g, neu1, &ONE, &syn1neg[row2], &ONE) * * return next_random # <<<<<<<<<<<<<< @@ -2805,7 +2843,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume __pyx_r = __pyx_v_next_random; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":129 + /* "gensim/models/doc2vec_inner.pyx":125 * * * cdef unsigned long long fast_document_dm_neg( # <<<<<<<<<<<<<< @@ -2818,7 +2856,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume return __pyx_r; } -/* "gensim/models/doc2vec_inner.pyx":165 +/* "gensim/models/doc2vec_inner.pyx":161 * return next_random * * cdef void fast_document_dmc_hs( # <<<<<<<<<<<<<< @@ -2832,11 +2870,12 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_f; __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_g; int __pyx_t_1; - PY_LONG_LONG __pyx_t_2; - int __pyx_t_3; + int __pyx_t_2; + PY_LONG_LONG __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/doc2vec_inner.pyx":177 + /* "gensim/models/doc2vec_inner.pyx":173 * # l1 already composed by caller, passed in as neu1 * # work accumulates net l1 error; eventually applied by caller * for b in range(word_code_len): # <<<<<<<<<<<<<< @@ -2844,10 +2883,11 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t * f = our_dot(&layer1_size, neu1, &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = __pyx_v_word_code_len; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_b = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_b = __pyx_t_3; - /* "gensim/models/doc2vec_inner.pyx":178 + /* "gensim/models/doc2vec_inner.pyx":174 * # work accumulates net l1 error; eventually applied by caller * for b in range(word_code_len): * row2 = word_point[b] * layer1_size # <<<<<<<<<<<<<< @@ -2856,7 +2896,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_layer1_size); - /* "gensim/models/doc2vec_inner.pyx":179 + /* "gensim/models/doc2vec_inner.pyx":175 * for b in range(word_code_len): * row2 = word_point[b] * layer1_size * f = our_dot(&layer1_size, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2865,25 +2905,25 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_layer1_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":180 + /* "gensim/models/doc2vec_inner.pyx":176 * row2 = word_point[b] * layer1_size * f = our_dot(&layer1_size, neu1, &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L6_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L6_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":181 + /* "gensim/models/doc2vec_inner.pyx":177 * f = our_dot(&layer1_size, neu1, &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2892,7 +2932,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":180 + /* "gensim/models/doc2vec_inner.pyx":176 * row2 = word_point[b] * layer1_size * f = our_dot(&layer1_size, neu1, &ONE, &syn1[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2901,7 +2941,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ } - /* "gensim/models/doc2vec_inner.pyx":182 + /* "gensim/models/doc2vec_inner.pyx":178 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2910,7 +2950,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/doc2vec_inner.pyx":183 + /* "gensim/models/doc2vec_inner.pyx":179 * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha # <<<<<<<<<<<<<< @@ -2919,7 +2959,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ __pyx_v_g = (((1 - (__pyx_v_word_code[__pyx_v_b])) - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/doc2vec_inner.pyx":184 + /* "gensim/models/doc2vec_inner.pyx":180 * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha * our_saxpy(&layer1_size, &g, &syn1[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2928,17 +2968,17 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_layer1_size), (&__pyx_v_g), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":185 + /* "gensim/models/doc2vec_inner.pyx":181 * g = (1 - word_code[b] - f) * alpha * our_saxpy(&layer1_size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< * our_saxpy(&layer1_size, &g, neu1, &ONE, &syn1[row2], &ONE) * */ - __pyx_t_3 = (__pyx_v_learn_hidden != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_hidden != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":186 + /* "gensim/models/doc2vec_inner.pyx":182 * our_saxpy(&layer1_size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: * our_saxpy(&layer1_size, &g, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2947,7 +2987,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_layer1_size), (&__pyx_v_g), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":185 + /* "gensim/models/doc2vec_inner.pyx":181 * g = (1 - word_code[b] - f) * alpha * our_saxpy(&layer1_size, &g, &syn1[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< @@ -2958,7 +2998,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t __pyx_L3_continue:; } - /* "gensim/models/doc2vec_inner.pyx":165 + /* "gensim/models/doc2vec_inner.pyx":161 * return next_random * * cdef void fast_document_dmc_hs( # <<<<<<<<<<<<<< @@ -2969,7 +3009,7 @@ static void __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs(__pyx_t /* function exit code */ } -/* "gensim/models/doc2vec_inner.pyx":189 +/* "gensim/models/doc2vec_inner.pyx":185 * * * cdef unsigned long long fast_document_dmc_neg( # <<<<<<<<<<<<<< @@ -2987,11 +3027,12 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume int __pyx_v_d; unsigned PY_LONG_LONG __pyx_r; long __pyx_t_1; - int __pyx_t_2; + long __pyx_t_2; int __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/doc2vec_inner.pyx":196 + /* "gensim/models/doc2vec_inner.pyx":192 * cdef long long a * cdef long long row2 * cdef unsigned long long modulo = 281474976710655ULL # <<<<<<<<<<<<<< @@ -3000,7 +3041,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_modulo = 281474976710655ULL; - /* "gensim/models/doc2vec_inner.pyx":203 + /* "gensim/models/doc2vec_inner.pyx":199 * # l1 already composed by caller, passed in as neu1 * # work accumulates net l1 error; eventually applied by caller * for d in range(negative+1): # <<<<<<<<<<<<<< @@ -3008,20 +3049,21 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume * target_index = predict_word_index */ __pyx_t_1 = (__pyx_v_negative + 1); - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; - /* "gensim/models/doc2vec_inner.pyx":204 + /* "gensim/models/doc2vec_inner.pyx":200 * # work accumulates net l1 error; eventually applied by caller * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< * target_index = predict_word_index * label = ONEF */ - __pyx_t_3 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":205 + /* "gensim/models/doc2vec_inner.pyx":201 * for d in range(negative+1): * if d == 0: * target_index = predict_word_index # <<<<<<<<<<<<<< @@ -3030,7 +3072,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_target_index = __pyx_v_predict_word_index; - /* "gensim/models/doc2vec_inner.pyx":206 + /* "gensim/models/doc2vec_inner.pyx":202 * if d == 0: * target_index = predict_word_index * label = ONEF # <<<<<<<<<<<<<< @@ -3039,7 +3081,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_label = __pyx_v_6gensim_6models_13doc2vec_inner_ONEF; - /* "gensim/models/doc2vec_inner.pyx":204 + /* "gensim/models/doc2vec_inner.pyx":200 * # work accumulates net l1 error; eventually applied by caller * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< @@ -3049,7 +3091,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume goto __pyx_L5; } - /* "gensim/models/doc2vec_inner.pyx":208 + /* "gensim/models/doc2vec_inner.pyx":204 * label = ONEF * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) # <<<<<<<<<<<<<< @@ -3059,7 +3101,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume /*else*/ { __pyx_v_target_index = __pyx_f_6gensim_6models_14word2vec_inner_bisect_left(__pyx_v_cum_table, ((__pyx_v_next_random >> 16) % (__pyx_v_cum_table[(__pyx_v_cum_table_len - 1)])), 0, __pyx_v_cum_table_len); - /* "gensim/models/doc2vec_inner.pyx":209 + /* "gensim/models/doc2vec_inner.pyx":205 * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo # <<<<<<<<<<<<<< @@ -3068,17 +3110,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_next_random = (((__pyx_v_next_random * ((unsigned PY_LONG_LONG)25214903917ULL)) + 11) & __pyx_v_modulo); - /* "gensim/models/doc2vec_inner.pyx":210 + /* "gensim/models/doc2vec_inner.pyx":206 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == predict_word_index: # <<<<<<<<<<<<<< * continue * label = 0.0 */ - __pyx_t_3 = ((__pyx_v_target_index == __pyx_v_predict_word_index) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_predict_word_index) != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":211 + /* "gensim/models/doc2vec_inner.pyx":207 * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == predict_word_index: * continue # <<<<<<<<<<<<<< @@ -3087,7 +3129,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":210 + /* "gensim/models/doc2vec_inner.pyx":206 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == predict_word_index: # <<<<<<<<<<<<<< @@ -3096,7 +3138,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":212 + /* "gensim/models/doc2vec_inner.pyx":208 * if target_index == predict_word_index: * continue * label = 0.0 # <<<<<<<<<<<<<< @@ -3107,7 +3149,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume } __pyx_L5:; - /* "gensim/models/doc2vec_inner.pyx":214 + /* "gensim/models/doc2vec_inner.pyx":210 * label = 0.0 * * row2 = target_index * layer1_size # <<<<<<<<<<<<<< @@ -3116,7 +3158,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_row2 = (__pyx_v_target_index * __pyx_v_layer1_size); - /* "gensim/models/doc2vec_inner.pyx":215 + /* "gensim/models/doc2vec_inner.pyx":211 * * row2 = target_index * layer1_size * f = our_dot(&layer1_size, neu1, &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -3125,25 +3167,25 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_layer1_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":216 + /* "gensim/models/doc2vec_inner.pyx":212 * row2 = target_index * layer1_size * f = our_dot(&layer1_size, neu1, &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L8_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L8_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":217 + /* "gensim/models/doc2vec_inner.pyx":213 * f = our_dot(&layer1_size, neu1, &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -3152,7 +3194,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ goto __pyx_L3_continue; - /* "gensim/models/doc2vec_inner.pyx":216 + /* "gensim/models/doc2vec_inner.pyx":212 * row2 = target_index * layer1_size * f = our_dot(&layer1_size, neu1, &ONE, &syn1neg[row2], &ONE) * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -3161,7 +3203,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ } - /* "gensim/models/doc2vec_inner.pyx":218 + /* "gensim/models/doc2vec_inner.pyx":214 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -3170,7 +3212,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/doc2vec_inner.pyx":219 + /* "gensim/models/doc2vec_inner.pyx":215 * continue * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha # <<<<<<<<<<<<<< @@ -3179,7 +3221,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_g = ((__pyx_v_label - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/doc2vec_inner.pyx":220 + /* "gensim/models/doc2vec_inner.pyx":216 * f = EXP_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha * our_saxpy(&layer1_size, &g, &syn1neg[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -3188,17 +3230,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_layer1_size), (&__pyx_v_g), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":221 + /* "gensim/models/doc2vec_inner.pyx":217 * g = (label - f) * alpha * our_saxpy(&layer1_size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< * our_saxpy(&layer1_size, &g, neu1, &ONE, &syn1neg[row2], &ONE) * */ - __pyx_t_3 = (__pyx_v_learn_hidden != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_learn_hidden != 0); + if (__pyx_t_4) { - /* "gensim/models/doc2vec_inner.pyx":222 + /* "gensim/models/doc2vec_inner.pyx":218 * our_saxpy(&layer1_size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: * our_saxpy(&layer1_size, &g, neu1, &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -3207,7 +3249,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_layer1_size), (&__pyx_v_g), __pyx_v_neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":221 + /* "gensim/models/doc2vec_inner.pyx":217 * g = (label - f) * alpha * our_saxpy(&layer1_size, &g, &syn1neg[row2], &ONE, work, &ONE) * if learn_hidden: # <<<<<<<<<<<<<< @@ -3218,7 +3260,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume __pyx_L3_continue:; } - /* "gensim/models/doc2vec_inner.pyx":224 + /* "gensim/models/doc2vec_inner.pyx":220 * our_saxpy(&layer1_size, &g, neu1, &ONE, &syn1neg[row2], &ONE) * * return next_random # <<<<<<<<<<<<<< @@ -3228,7 +3270,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume __pyx_r = __pyx_v_next_random; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":189 + /* "gensim/models/doc2vec_inner.pyx":185 * * * cdef unsigned long long fast_document_dmc_neg( # <<<<<<<<<<<<<< @@ -3241,7 +3283,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume return __pyx_r; } -/* "gensim/models/doc2vec_inner.pyx":227 +/* "gensim/models/doc2vec_inner.pyx":223 * * * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, # <<<<<<<<<<<<<< @@ -3251,7 +3293,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_13doc2vec_inner_fast_docume /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_13doc2vec_inner_1train_document_dbow = {"train_document_dbow", (PyCFunction)__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_13doc2vec_inner_train_document_dbow[] = "train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None)\nUpdate distributed bag of words model (\"PV-DBOW\") by training on a single document.\n\n Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and\n :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.doc2vec.Doc2Vec`\n The model to train.\n doc_words : list of str\n The input document as a list of words to be used for training. Each word will be looked up in\n the model's vocabulary.\n doctag_indexes : list of int\n Indices into `doctag_vectors` used to obtain the tags of the document.\n alpha : float\n Learning rate.\n work : list of float, optional\n Updates to be performed on each neuron in the hidden layer of the underlying network.\n train_words : bool, optional\n Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** `learn_words`\n and `train_words` are set to True.\n learn_doctags : bool, optional\n Whether the tag vectors should be updated.\n learn_words : bool, optional\n Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both**\n `learn_words` and `train_words` are set to True.\n learn_hidden : bool, optional\n Whether or not the weights of the hidden layer will be updated.\n word_vectors : numpy.ndarray, optional\n The vector representation for each word in the vocabulary. If None, these will be retrieved from the model.\n word_locks : numpy.ndarray, optional\n A learning lock factor for each weight in the hidden layer for words, value 0 completely blocks updates,\n a value of 1 allows to update word-vectors.\n doctag_vectors : numpy.ndarray, ""optional\n Vector representations of the tags. If None, these will be retrieved from the model.\n doctag_locks : numpy.ndarray, optional\n The lock factors for each tag, same as `word_locks`, but for document-vectors.\n\n Returns\n -------\n int\n Number of words in the input document that were actually used for training.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_13doc2vec_inner_1train_document_dbow = {"train_document_dbow", (PyCFunction)__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_13doc2vec_inner_train_document_dbow}; static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_doc_words = 0; @@ -3274,24 +3317,24 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow(P PyObject* values[13] = {0,0,0,0,0,0,0,0,0,0,0,0,0}; values[4] = ((PyObject *)Py_None); - /* "gensim/models/doc2vec_inner.pyx":228 + /* "gensim/models/doc2vec_inner.pyx":224 * * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, * train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, # <<<<<<<<<<<<<< * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): - * cdef int hs = model.hs + * """Update distributed bag of words model ("PV-DBOW") by training on a single document. */ values[5] = ((PyObject *)Py_False); values[6] = ((PyObject *)Py_True); values[7] = ((PyObject *)Py_True); values[8] = ((PyObject *)Py_True); - /* "gensim/models/doc2vec_inner.pyx":229 + /* "gensim/models/doc2vec_inner.pyx":225 * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, * train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update distributed bag of words model ("PV-DBOW") by training on a single document. + * */ values[9] = ((PyObject *)Py_None); values[10] = ((PyObject *)Py_None); @@ -3333,83 +3376,83 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow(P kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doc_words)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doc_words)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, 1); __PYX_ERR(0, 227, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, 1); __PYX_ERR(0, 223, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_indexes)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_indexes)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, 2); __PYX_ERR(0, 227, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, 2); __PYX_ERR(0, 223, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, 3); __PYX_ERR(0, 227, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, 3); __PYX_ERR(0, 223, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work); if (value) { values[4] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 5: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_train_words); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_train_words); if (value) { values[5] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 6: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_doctags); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_doctags); if (value) { values[6] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 7: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_words); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_words); if (value) { values[7] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 8: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_hidden); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_hidden); if (value) { values[8] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 9: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word_vectors); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word_vectors); if (value) { values[9] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 10: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word_locks); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word_locks); if (value) { values[10] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 11: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_vectors); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_vectors); if (value) { values[11] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 12: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_locks); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_locks); if (value) { values[12] = value; kw_args--; } } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_document_dbow") < 0)) __PYX_ERR(0, 227, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_document_dbow") < 0)) __PYX_ERR(0, 223, __pyx_L3_error) } } else { switch (PyTuple_GET_SIZE(__pyx_args)) { @@ -3455,7 +3498,7 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow(P } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 227, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dbow", 0, 4, 13, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 223, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.doc2vec_inner.train_document_dbow", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -3463,7 +3506,7 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_1train_document_dbow(P __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(__pyx_self, __pyx_v_model, __pyx_v_doc_words, __pyx_v_doctag_indexes, __pyx_v_alpha, __pyx_v_work, __pyx_v_train_words, __pyx_v_learn_doctags, __pyx_v_learn_words, __pyx_v_learn_hidden, __pyx_v_word_vectors, __pyx_v_word_locks, __pyx_v_doctag_vectors, __pyx_v_doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":227 + /* "gensim/models/doc2vec_inner.pyx":223 * * * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, # <<<<<<<<<<<<<< @@ -3533,7 +3576,10 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY PyObject *__pyx_t_16 = NULL; long __pyx_t_17; int __pyx_t_18; - int __pyx_t_19; + long __pyx_t_19; + int __pyx_t_20; + int __pyx_t_21; + int __pyx_t_22; __Pyx_RefNannySetupContext("train_document_dbow", 0); __Pyx_INCREF(__pyx_v_work); __Pyx_INCREF(__pyx_v_word_vectors); @@ -3541,130 +3587,130 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __Pyx_INCREF(__pyx_v_doctag_vectors); __Pyx_INCREF(__pyx_v_doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":230 - * train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, - * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + /* "gensim/models/doc2vec_inner.pyx":270 + * + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 230, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 270, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 230, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 270, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":231 - * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + /* "gensim/models/doc2vec_inner.pyx":271 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * cdef int _train_words = train_words */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 231, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 271, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 231, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 271, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":232 + /* "gensim/models/doc2vec_inner.pyx":272 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * cdef int _train_words = train_words * cdef int _learn_words = learn_words */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 232, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 272, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 232, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 272, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 232, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 272, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 232, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 272, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":233 + /* "gensim/models/doc2vec_inner.pyx":273 * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) * cdef int _train_words = train_words # <<<<<<<<<<<<<< * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_train_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 233, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_train_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 273, __pyx_L1_error) __pyx_v__train_words = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":234 + /* "gensim/models/doc2vec_inner.pyx":274 * cdef int sample = (model.vocabulary.sample != 0) * cdef int _train_words = train_words * cdef int _learn_words = learn_words # <<<<<<<<<<<<<< * cdef int _learn_hidden = learn_hidden * cdef int _learn_doctags = learn_doctags */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 234, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 274, __pyx_L1_error) __pyx_v__learn_words = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":235 + /* "gensim/models/doc2vec_inner.pyx":275 * cdef int _train_words = train_words * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden # <<<<<<<<<<<<<< * cdef int _learn_doctags = learn_doctags * */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_hidden); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 235, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_hidden); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 275, __pyx_L1_error) __pyx_v__learn_hidden = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":236 + /* "gensim/models/doc2vec_inner.pyx":276 * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden * cdef int _learn_doctags = learn_doctags # <<<<<<<<<<<<<< * * cdef REAL_t *_word_vectors */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_doctags); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 236, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_doctags); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 276, __pyx_L1_error) __pyx_v__learn_doctags = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":243 + /* "gensim/models/doc2vec_inner.pyx":283 * cdef REAL_t *_doctag_locks * cdef REAL_t *_work * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int size = model.trainables.layer1_size * */ - __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 243, __pyx_L1_error) + __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 283, __pyx_L1_error) __pyx_v__alpha = __pyx_t_4; - /* "gensim/models/doc2vec_inner.pyx":244 + /* "gensim/models/doc2vec_inner.pyx":284 * cdef REAL_t *_work * cdef REAL_t _alpha = alpha * cdef int size = model.trainables.layer1_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_DOCUMENT_LEN] */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 244, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 284, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 244, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 284, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 244, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 284, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":252 + /* "gensim/models/doc2vec_inner.pyx":292 * cdef int document_len * cdef int doctag_len * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 252, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 292, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 252, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 292, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":256 + /* "gensim/models/doc2vec_inner.pyx":296 * cdef int i, j * cdef unsigned long long r * cdef long result = 0 # <<<<<<<<<<<<<< @@ -3673,7 +3719,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_result = 0; - /* "gensim/models/doc2vec_inner.pyx":270 + /* "gensim/models/doc2vec_inner.pyx":310 * * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: # <<<<<<<<<<<<<< @@ -3684,22 +3730,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":271 + /* "gensim/models/doc2vec_inner.pyx":311 * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: * word_vectors = model.wv.vectors # <<<<<<<<<<<<<< * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 271, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 311, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 271, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 311, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_word_vectors, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":270 + /* "gensim/models/doc2vec_inner.pyx":310 * * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: # <<<<<<<<<<<<<< @@ -3708,17 +3754,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":272 + /* "gensim/models/doc2vec_inner.pyx":312 * if word_vectors is None: * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) # <<<<<<<<<<<<<< * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs */ - if (!(likely(((__pyx_v_word_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 272, __pyx_L1_error) + if (!(likely(((__pyx_v_word_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 312, __pyx_L1_error) __pyx_v__word_vectors = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_vectors))); - /* "gensim/models/doc2vec_inner.pyx":273 + /* "gensim/models/doc2vec_inner.pyx":313 * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: # <<<<<<<<<<<<<< @@ -3729,22 +3775,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_t_6 != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":274 + /* "gensim/models/doc2vec_inner.pyx":314 * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs # <<<<<<<<<<<<<< * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 274, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 314, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 274, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 314, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF_SET(__pyx_v_doctag_vectors, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":273 + /* "gensim/models/doc2vec_inner.pyx":313 * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: # <<<<<<<<<<<<<< @@ -3753,17 +3799,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":275 + /* "gensim/models/doc2vec_inner.pyx":315 * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) # <<<<<<<<<<<<<< * if word_locks is None: * word_locks = model.trainables.vectors_lockf */ - if (!(likely(((__pyx_v_doctag_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 275, __pyx_L1_error) + if (!(likely(((__pyx_v_doctag_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 315, __pyx_L1_error) __pyx_v__doctag_vectors = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_doctag_vectors))); - /* "gensim/models/doc2vec_inner.pyx":276 + /* "gensim/models/doc2vec_inner.pyx":316 * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: # <<<<<<<<<<<<<< @@ -3774,22 +3820,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":277 + /* "gensim/models/doc2vec_inner.pyx":317 * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: * word_locks = model.trainables.vectors_lockf # <<<<<<<<<<<<<< * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 277, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 317, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 277, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 317, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_word_locks, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":276 + /* "gensim/models/doc2vec_inner.pyx":316 * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: # <<<<<<<<<<<<<< @@ -3798,17 +3844,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":278 + /* "gensim/models/doc2vec_inner.pyx":318 * if word_locks is None: * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) # <<<<<<<<<<<<<< * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf */ - if (!(likely(((__pyx_v_word_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 278, __pyx_L1_error) + if (!(likely(((__pyx_v_word_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 318, __pyx_L1_error) __pyx_v__word_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_locks))); - /* "gensim/models/doc2vec_inner.pyx":279 + /* "gensim/models/doc2vec_inner.pyx":319 * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: # <<<<<<<<<<<<<< @@ -3819,22 +3865,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_t_6 != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":280 + /* "gensim/models/doc2vec_inner.pyx":320 * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf # <<<<<<<<<<<<<< * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 280, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 320, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs_lockf); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 280, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs_lockf); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 320, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF_SET(__pyx_v_doctag_locks, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":279 + /* "gensim/models/doc2vec_inner.pyx":319 * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: # <<<<<<<<<<<<<< @@ -3843,17 +3889,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":281 + /* "gensim/models/doc2vec_inner.pyx":321 * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf * _doctag_locks = (np.PyArray_DATA(doctag_locks)) # <<<<<<<<<<<<<< * * if hs: */ - if (!(likely(((__pyx_v_doctag_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 281, __pyx_L1_error) + if (!(likely(((__pyx_v_doctag_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 321, __pyx_L1_error) __pyx_v__doctag_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_doctag_locks))); - /* "gensim/models/doc2vec_inner.pyx":283 + /* "gensim/models/doc2vec_inner.pyx":323 * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * * if hs: # <<<<<<<<<<<<<< @@ -3863,23 +3909,23 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":284 + /* "gensim/models/doc2vec_inner.pyx":324 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 284, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 324, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 284, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 324, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 284, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 324, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":283 + /* "gensim/models/doc2vec_inner.pyx":323 * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * * if hs: # <<<<<<<<<<<<<< @@ -3888,7 +3934,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":286 + /* "gensim/models/doc2vec_inner.pyx":326 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -3898,55 +3944,55 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":287 + /* "gensim/models/doc2vec_inner.pyx":327 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 287, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 327, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 287, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 327, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 287, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 327, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":288 + /* "gensim/models/doc2vec_inner.pyx":328 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 288, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 328, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 288, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 328, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 288, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 328, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":289 + /* "gensim/models/doc2vec_inner.pyx":329 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 289, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 329, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 289, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 329, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_7 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 289, __pyx_L1_error) + __pyx_t_7 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 329, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_7; - /* "gensim/models/doc2vec_inner.pyx":286 + /* "gensim/models/doc2vec_inner.pyx":326 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -3955,7 +4001,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":290 + /* "gensim/models/doc2vec_inner.pyx":330 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -3973,41 +4019,41 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_L10_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":291 + /* "gensim/models/doc2vec_inner.pyx":331 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_next_random = __pyx_t_9; - /* "gensim/models/doc2vec_inner.pyx":290 + /* "gensim/models/doc2vec_inner.pyx":330 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -4016,7 +4062,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":294 + /* "gensim/models/doc2vec_inner.pyx":334 * * # convert Python structures to primitive types, so we can release the GIL * if work is None: # <<<<<<<<<<<<<< @@ -4027,32 +4073,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":295 + /* "gensim/models/doc2vec_inner.pyx":335 * # convert Python structures to primitive types, so we can release the GIL * if work is None: * work = zeros(model.trainables.layer1_size, dtype=REAL) # <<<<<<<<<<<<<< * _work = np.PyArray_DATA(work) * */ - __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_10) < 0) __PYX_ERR(0, 295, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_10) < 0) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; @@ -4060,7 +4106,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __Pyx_DECREF_SET(__pyx_v_work, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":294 + /* "gensim/models/doc2vec_inner.pyx":334 * * # convert Python structures to primitive types, so we can release the GIL * if work is None: # <<<<<<<<<<<<<< @@ -4069,32 +4115,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":296 + /* "gensim/models/doc2vec_inner.pyx":336 * if work is None: * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) # <<<<<<<<<<<<<< * * vlookup = model.wv.vocab */ - if (!(likely(((__pyx_v_work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 296, __pyx_L1_error) + if (!(likely(((__pyx_v_work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 336, __pyx_L1_error) __pyx_v__work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_work))); - /* "gensim/models/doc2vec_inner.pyx":298 + /* "gensim/models/doc2vec_inner.pyx":338 * _work = np.PyArray_DATA(work) * * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * i = 0 * for token in doc_words: */ - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 298, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 338, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_vocab); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 298, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_vocab); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 338, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __pyx_v_vlookup = __pyx_t_1; __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":299 + /* "gensim/models/doc2vec_inner.pyx":339 * * vlookup = model.wv.vocab * i = 0 # <<<<<<<<<<<<<< @@ -4103,7 +4149,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_i = 0; - /* "gensim/models/doc2vec_inner.pyx":300 + /* "gensim/models/doc2vec_inner.pyx":340 * vlookup = model.wv.vocab * i = 0 * for token in doc_words: # <<<<<<<<<<<<<< @@ -4114,26 +4160,26 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_1 = __pyx_v_doc_words; __Pyx_INCREF(__pyx_t_1); __pyx_t_7 = 0; __pyx_t_11 = NULL; } else { - __pyx_t_7 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_doc_words); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 300, __pyx_L1_error) + __pyx_t_7 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_doc_words); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 340, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_11 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 300, __pyx_L1_error) + __pyx_t_11 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 340, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_11)) { if (likely(PyList_CheckExact(__pyx_t_1))) { if (__pyx_t_7 >= PyList_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_10 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 300, __pyx_L1_error) + __pyx_t_10 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 340, __pyx_L1_error) #else - __pyx_t_10 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 300, __pyx_L1_error) + __pyx_t_10 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 340, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); #endif } else { if (__pyx_t_7 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_10 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 300, __pyx_L1_error) + __pyx_t_10 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 340, __pyx_L1_error) #else - __pyx_t_10 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 300, __pyx_L1_error) + __pyx_t_10 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 340, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); #endif } @@ -4143,7 +4189,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 300, __pyx_L1_error) + else __PYX_ERR(0, 340, __pyx_L1_error) } break; } @@ -4152,16 +4198,16 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":301 + /* "gensim/models/doc2vec_inner.pyx":341 * i = 0 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged */ - __pyx_t_6 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 301, __pyx_L1_error) + __pyx_t_6 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 341, __pyx_L1_error) if ((__pyx_t_6 != 0)) { - __pyx_t_3 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 301, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 341, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_10 = __pyx_t_3; __pyx_t_3 = 0; @@ -4172,7 +4218,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __Pyx_XDECREF_SET(__pyx_v_predict_word, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":302 + /* "gensim/models/doc2vec_inner.pyx":342 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word # <<<<<<<<<<<<<< @@ -4183,7 +4229,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_t_6 != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":303 + /* "gensim/models/doc2vec_inner.pyx":343 * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged # <<<<<<<<<<<<<< @@ -4192,7 +4238,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ goto __pyx_L13_continue; - /* "gensim/models/doc2vec_inner.pyx":302 + /* "gensim/models/doc2vec_inner.pyx":342 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word # <<<<<<<<<<<<<< @@ -4201,7 +4247,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":304 + /* "gensim/models/doc2vec_inner.pyx":344 * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -4214,20 +4260,20 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = __pyx_t_6; goto __pyx_L17_bool_binop_done; } - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 304, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_3 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 304, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = PyObject_RichCompare(__pyx_t_10, __pyx_t_3, Py_LT); __Pyx_XGOTREF(__pyx_t_8); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 304, __pyx_L1_error) + __pyx_t_8 = PyObject_RichCompare(__pyx_t_10, __pyx_t_3, Py_LT); __Pyx_XGOTREF(__pyx_t_8); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_8); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 304, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_8); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_t_5 = __pyx_t_6; __pyx_L17_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":305 + /* "gensim/models/doc2vec_inner.pyx":345 * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -4236,7 +4282,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ goto __pyx_L13_continue; - /* "gensim/models/doc2vec_inner.pyx":304 + /* "gensim/models/doc2vec_inner.pyx":344 * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -4245,20 +4291,20 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":306 + /* "gensim/models/doc2vec_inner.pyx":346 * if sample and predict_word.sample_int < random_int32(&next_random): * continue * indexes[i] = predict_word.index # <<<<<<<<<<<<<< * if hs: * codelens[i] = len(predict_word.code) */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_index); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 306, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_index); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 346, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_8); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 306, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_8); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 346, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; (__pyx_v_indexes[__pyx_v_i]) = __pyx_t_12; - /* "gensim/models/doc2vec_inner.pyx":307 + /* "gensim/models/doc2vec_inner.pyx":347 * continue * indexes[i] = predict_word.index * if hs: # <<<<<<<<<<<<<< @@ -4268,46 +4314,46 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":308 + /* "gensim/models/doc2vec_inner.pyx":348 * indexes[i] = predict_word.index * if hs: * codelens[i] = len(predict_word.code) # <<<<<<<<<<<<<< * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 348, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_13 = PyObject_Length(__pyx_t_8); if (unlikely(__pyx_t_13 == ((Py_ssize_t)-1))) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_13 = PyObject_Length(__pyx_t_8); if (unlikely(__pyx_t_13 == ((Py_ssize_t)-1))) __PYX_ERR(0, 348, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; (__pyx_v_codelens[__pyx_v_i]) = ((int)__pyx_t_13); - /* "gensim/models/doc2vec_inner.pyx":309 + /* "gensim/models/doc2vec_inner.pyx":349 * if hs: * codelens[i] = len(predict_word.code) * codes[i] = np.PyArray_DATA(predict_word.code) # <<<<<<<<<<<<<< * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 309, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 349, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - if (!(likely(((__pyx_t_8) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_8, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 309, __pyx_L1_error) + if (!(likely(((__pyx_t_8) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_8, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 349, __pyx_L1_error) (__pyx_v_codes[__pyx_v_i]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_8))); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/doc2vec_inner.pyx":310 + /* "gensim/models/doc2vec_inner.pyx":350 * codelens[i] = len(predict_word.code) * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) # <<<<<<<<<<<<<< * result += 1 * i += 1 */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_point); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 310, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_point); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 350, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - if (!(likely(((__pyx_t_8) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_8, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 310, __pyx_L1_error) + if (!(likely(((__pyx_t_8) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_8, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 350, __pyx_L1_error) (__pyx_v_points[__pyx_v_i]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_8))); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/doc2vec_inner.pyx":307 + /* "gensim/models/doc2vec_inner.pyx":347 * continue * indexes[i] = predict_word.index * if hs: # <<<<<<<<<<<<<< @@ -4316,7 +4362,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":311 + /* "gensim/models/doc2vec_inner.pyx":351 * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 # <<<<<<<<<<<<<< @@ -4325,7 +4371,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_result = (__pyx_v_result + 1); - /* "gensim/models/doc2vec_inner.pyx":312 + /* "gensim/models/doc2vec_inner.pyx":352 * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 * i += 1 # <<<<<<<<<<<<<< @@ -4334,7 +4380,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_i = (__pyx_v_i + 1); - /* "gensim/models/doc2vec_inner.pyx":313 + /* "gensim/models/doc2vec_inner.pyx":353 * result += 1 * i += 1 * if i == MAX_DOCUMENT_LEN: # <<<<<<<<<<<<<< @@ -4344,7 +4390,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = ((__pyx_v_i == 0x2710) != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":314 + /* "gensim/models/doc2vec_inner.pyx":354 * i += 1 * if i == MAX_DOCUMENT_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -4353,7 +4399,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ goto __pyx_L14_break; - /* "gensim/models/doc2vec_inner.pyx":313 + /* "gensim/models/doc2vec_inner.pyx":353 * result += 1 * i += 1 * if i == MAX_DOCUMENT_LEN: # <<<<<<<<<<<<<< @@ -4362,7 +4408,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":300 + /* "gensim/models/doc2vec_inner.pyx":340 * vlookup = model.wv.vocab * i = 0 * for token in doc_words: # <<<<<<<<<<<<<< @@ -4374,7 +4420,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_L14_break:; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":315 + /* "gensim/models/doc2vec_inner.pyx":355 * if i == MAX_DOCUMENT_LEN: * break # TODO: log warning, tally overflow? * document_len = i # <<<<<<<<<<<<<< @@ -4383,7 +4429,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_document_len = __pyx_v_i; - /* "gensim/models/doc2vec_inner.pyx":317 + /* "gensim/models/doc2vec_inner.pyx":357 * document_len = i * * if _train_words: # <<<<<<<<<<<<<< @@ -4393,7 +4439,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v__train_words != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":319 + /* "gensim/models/doc2vec_inner.pyx":359 * if _train_words: * # single randint() call avoids a big thread-synchronization slowdown * for i, item in enumerate(model.random.randint(0, window, document_len)): # <<<<<<<<<<<<<< @@ -4401,14 +4447,14 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY * */ __pyx_t_2 = 0; - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_randint); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_randint); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = __Pyx_PyInt_From_int(__pyx_v_window); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyInt_From_int(__pyx_v_window); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_10 = __Pyx_PyInt_From_int(__pyx_v_document_len); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyInt_From_int(__pyx_v_document_len); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __pyx_t_14 = NULL; __pyx_t_15 = 0; @@ -4425,7 +4471,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[4] = {__pyx_t_14, __pyx_int_0, __pyx_t_8, __pyx_t_10}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; @@ -4435,7 +4481,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[4] = {__pyx_t_14, __pyx_int_0, __pyx_t_8, __pyx_t_10}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; @@ -4443,7 +4489,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY } else #endif { - __pyx_t_16 = PyTuple_New(3+__pyx_t_15); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_16 = PyTuple_New(3+__pyx_t_15); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_16); if (__pyx_t_14) { __Pyx_GIVEREF(__pyx_t_14); PyTuple_SET_ITEM(__pyx_t_16, 0, __pyx_t_14); __pyx_t_14 = NULL; @@ -4457,7 +4503,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY PyTuple_SET_ITEM(__pyx_t_16, 2+__pyx_t_15, __pyx_t_10); __pyx_t_8 = 0; __pyx_t_10 = 0; - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_16, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_16, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_16); __pyx_t_16 = 0; } @@ -4466,9 +4512,9 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_3 = __pyx_t_1; __Pyx_INCREF(__pyx_t_3); __pyx_t_7 = 0; __pyx_t_11 = NULL; } else { - __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_11 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_11 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 359, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; for (;;) { @@ -4476,17 +4522,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_7 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_1); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_1); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 359, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_7 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_1); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_1); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 359, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 359, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -4496,7 +4542,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 319, __pyx_L1_error) + else __PYX_ERR(0, 359, __pyx_L1_error) } break; } @@ -4507,17 +4553,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_v_i = __pyx_t_2; __pyx_t_2 = (__pyx_t_2 + 1); - /* "gensim/models/doc2vec_inner.pyx":320 + /* "gensim/models/doc2vec_inner.pyx":360 * # single randint() call avoids a big thread-synchronization slowdown * for i, item in enumerate(model.random.randint(0, window, document_len)): * reduced_windows[i] = item # <<<<<<<<<<<<<< * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) */ - __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 360, __pyx_L1_error) (__pyx_v_reduced_windows[__pyx_v_i]) = __pyx_t_12; - /* "gensim/models/doc2vec_inner.pyx":319 + /* "gensim/models/doc2vec_inner.pyx":359 * if _train_words: * # single randint() call avoids a big thread-synchronization slowdown * for i, item in enumerate(model.random.randint(0, window, document_len)): # <<<<<<<<<<<<<< @@ -4527,7 +4573,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":317 + /* "gensim/models/doc2vec_inner.pyx":357 * document_len = i * * if _train_words: # <<<<<<<<<<<<<< @@ -4536,14 +4582,14 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":322 + /* "gensim/models/doc2vec_inner.pyx":362 * reduced_windows[i] = item * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) # <<<<<<<<<<<<<< * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] */ - __pyx_t_7 = PyObject_Length(__pyx_v_doctag_indexes); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 322, __pyx_L1_error) + __pyx_t_7 = PyObject_Length(__pyx_v_doctag_indexes); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 362, __pyx_L1_error) __pyx_t_17 = 0x2710; if (((__pyx_t_7 < __pyx_t_17) != 0)) { __pyx_t_13 = __pyx_t_7; @@ -4552,7 +4598,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY } __pyx_v_doctag_len = ((int)__pyx_t_13); - /* "gensim/models/doc2vec_inner.pyx":323 + /* "gensim/models/doc2vec_inner.pyx":363 * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * for i in range(doctag_len): # <<<<<<<<<<<<<< @@ -4560,23 +4606,24 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY * result += 1 */ __pyx_t_2 = __pyx_v_doctag_len; - for (__pyx_t_15 = 0; __pyx_t_15 < __pyx_t_2; __pyx_t_15+=1) { - __pyx_v_i = __pyx_t_15; + __pyx_t_15 = __pyx_t_2; + for (__pyx_t_18 = 0; __pyx_t_18 < __pyx_t_15; __pyx_t_18+=1) { + __pyx_v_i = __pyx_t_18; - /* "gensim/models/doc2vec_inner.pyx":324 + /* "gensim/models/doc2vec_inner.pyx":364 * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] # <<<<<<<<<<<<<< * result += 1 * */ - __pyx_t_3 = __Pyx_GetItemInt(__pyx_v_doctag_indexes, __pyx_v_i, int, 1, __Pyx_PyInt_From_int, 0, 0, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 324, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetItemInt(__pyx_v_doctag_indexes, __pyx_v_i, int, 1, __Pyx_PyInt_From_int, 0, 0, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 364, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_3); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 324, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_3); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 364, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; (__pyx_v__doctag_indexes[__pyx_v_i]) = __pyx_t_12; - /* "gensim/models/doc2vec_inner.pyx":325 + /* "gensim/models/doc2vec_inner.pyx":365 * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] * result += 1 # <<<<<<<<<<<<<< @@ -4586,7 +4633,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_v_result = (__pyx_v_result + 1); } - /* "gensim/models/doc2vec_inner.pyx":328 + /* "gensim/models/doc2vec_inner.pyx":368 * * # release GIL & train on the document * with nogil: # <<<<<<<<<<<<<< @@ -4601,7 +4648,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY #endif /*try:*/ { - /* "gensim/models/doc2vec_inner.pyx":329 + /* "gensim/models/doc2vec_inner.pyx":369 * # release GIL & train on the document * with nogil: * for i in range(document_len): # <<<<<<<<<<<<<< @@ -4609,10 +4656,11 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY * j = i - window + reduced_windows[i] */ __pyx_t_2 = __pyx_v_document_len; - for (__pyx_t_15 = 0; __pyx_t_15 < __pyx_t_2; __pyx_t_15+=1) { - __pyx_v_i = __pyx_t_15; + __pyx_t_15 = __pyx_t_2; + for (__pyx_t_18 = 0; __pyx_t_18 < __pyx_t_15; __pyx_t_18+=1) { + __pyx_v_i = __pyx_t_18; - /* "gensim/models/doc2vec_inner.pyx":330 + /* "gensim/models/doc2vec_inner.pyx":370 * with nogil: * for i in range(document_len): * if _train_words: # simultaneous skip-gram wordvec-training # <<<<<<<<<<<<<< @@ -4622,7 +4670,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v__train_words != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":331 + /* "gensim/models/doc2vec_inner.pyx":371 * for i in range(document_len): * if _train_words: # simultaneous skip-gram wordvec-training * j = i - window + reduced_windows[i] # <<<<<<<<<<<<<< @@ -4631,7 +4679,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_j = ((__pyx_v_i - __pyx_v_window) + (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/doc2vec_inner.pyx":332 + /* "gensim/models/doc2vec_inner.pyx":372 * if _train_words: # simultaneous skip-gram wordvec-training * j = i - window + reduced_windows[i] * if j < 0: # <<<<<<<<<<<<<< @@ -4641,7 +4689,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = ((__pyx_v_j < 0) != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":333 + /* "gensim/models/doc2vec_inner.pyx":373 * j = i - window + reduced_windows[i] * if j < 0: * j = 0 # <<<<<<<<<<<<<< @@ -4650,7 +4698,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_j = 0; - /* "gensim/models/doc2vec_inner.pyx":332 + /* "gensim/models/doc2vec_inner.pyx":372 * if _train_words: # simultaneous skip-gram wordvec-training * j = i - window + reduced_windows[i] * if j < 0: # <<<<<<<<<<<<<< @@ -4659,7 +4707,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":334 + /* "gensim/models/doc2vec_inner.pyx":374 * if j < 0: * j = 0 * k = i + window + 1 - reduced_windows[i] # <<<<<<<<<<<<<< @@ -4668,7 +4716,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_k = (((__pyx_v_i + __pyx_v_window) + 1) - (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/doc2vec_inner.pyx":335 + /* "gensim/models/doc2vec_inner.pyx":375 * j = 0 * k = i + window + 1 - reduced_windows[i] * if k > document_len: # <<<<<<<<<<<<<< @@ -4678,7 +4726,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = ((__pyx_v_k > __pyx_v_document_len) != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":336 + /* "gensim/models/doc2vec_inner.pyx":376 * k = i + window + 1 - reduced_windows[i] * if k > document_len: * k = document_len # <<<<<<<<<<<<<< @@ -4687,7 +4735,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_k = __pyx_v_document_len; - /* "gensim/models/doc2vec_inner.pyx":335 + /* "gensim/models/doc2vec_inner.pyx":375 * j = 0 * k = i + window + 1 - reduced_windows[i] * if k > document_len: # <<<<<<<<<<<<<< @@ -4696,7 +4744,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":337 + /* "gensim/models/doc2vec_inner.pyx":377 * if k > document_len: * k = document_len * for j in range(j, k): # <<<<<<<<<<<<<< @@ -4704,10 +4752,11 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY * continue */ __pyx_t_17 = __pyx_v_k; - for (__pyx_t_18 = __pyx_v_j; __pyx_t_18 < __pyx_t_17; __pyx_t_18+=1) { - __pyx_v_j = __pyx_t_18; + __pyx_t_19 = __pyx_t_17; + for (__pyx_t_20 = __pyx_v_j; __pyx_t_20 < __pyx_t_19; __pyx_t_20+=1) { + __pyx_v_j = __pyx_t_20; - /* "gensim/models/doc2vec_inner.pyx":338 + /* "gensim/models/doc2vec_inner.pyx":378 * k = document_len * for j in range(j, k): * if j == i: # <<<<<<<<<<<<<< @@ -4717,7 +4766,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = ((__pyx_v_j == __pyx_v_i) != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":339 + /* "gensim/models/doc2vec_inner.pyx":379 * for j in range(j, k): * if j == i: * continue # <<<<<<<<<<<<<< @@ -4726,7 +4775,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ goto __pyx_L34_continue; - /* "gensim/models/doc2vec_inner.pyx":338 + /* "gensim/models/doc2vec_inner.pyx":378 * k = document_len * for j in range(j, k): * if j == i: # <<<<<<<<<<<<<< @@ -4735,7 +4784,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":340 + /* "gensim/models/doc2vec_inner.pyx":380 * if j == i: * continue * if hs: # <<<<<<<<<<<<<< @@ -4745,7 +4794,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":342 + /* "gensim/models/doc2vec_inner.pyx":382 * if hs: * # we reuse the DBOW function, as it is equivalent to skip-gram for this purpose * fast_document_dbow_hs(points[i], codes[i], codelens[i], _word_vectors, syn1, size, indexes[j], # <<<<<<<<<<<<<< @@ -4754,7 +4803,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), (__pyx_v_codelens[__pyx_v_i]), __pyx_v__word_vectors, __pyx_v_syn1, __pyx_v_size, (__pyx_v_indexes[__pyx_v_j]), __pyx_v__alpha, __pyx_v__work, __pyx_v__learn_words, __pyx_v__learn_hidden, __pyx_v__word_locks); - /* "gensim/models/doc2vec_inner.pyx":340 + /* "gensim/models/doc2vec_inner.pyx":380 * if j == i: * continue * if hs: # <<<<<<<<<<<<<< @@ -4763,7 +4812,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":344 + /* "gensim/models/doc2vec_inner.pyx":384 * fast_document_dbow_hs(points[i], codes[i], codelens[i], _word_vectors, syn1, size, indexes[j], * _alpha, _work, _learn_words, _learn_hidden, _word_locks) * if negative: # <<<<<<<<<<<<<< @@ -4773,7 +4822,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":346 + /* "gensim/models/doc2vec_inner.pyx":386 * if negative: * # we reuse the DBOW function, as it is equivalent to skip-gram for this purpose * next_random = fast_document_dbow_neg(negative, cum_table, cum_table_len, _word_vectors, syn1neg, size, # <<<<<<<<<<<<<< @@ -4782,7 +4831,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_next_random = __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v__word_vectors, __pyx_v_syn1neg, __pyx_v_size, (__pyx_v_indexes[__pyx_v_i]), (__pyx_v_indexes[__pyx_v_j]), __pyx_v__alpha, __pyx_v__work, __pyx_v_next_random, __pyx_v__learn_words, __pyx_v__learn_hidden, __pyx_v__word_locks); - /* "gensim/models/doc2vec_inner.pyx":344 + /* "gensim/models/doc2vec_inner.pyx":384 * fast_document_dbow_hs(points[i], codes[i], codelens[i], _word_vectors, syn1, size, indexes[j], * _alpha, _work, _learn_words, _learn_hidden, _word_locks) * if negative: # <<<<<<<<<<<<<< @@ -4793,7 +4842,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_L34_continue:; } - /* "gensim/models/doc2vec_inner.pyx":330 + /* "gensim/models/doc2vec_inner.pyx":370 * with nogil: * for i in range(document_len): * if _train_words: # simultaneous skip-gram wordvec-training # <<<<<<<<<<<<<< @@ -4802,18 +4851,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":351 + /* "gensim/models/doc2vec_inner.pyx":391 * * # docvec-training * for j in range(doctag_len): # <<<<<<<<<<<<<< * if hs: * fast_document_dbow_hs(points[i], codes[i], codelens[i], _doctag_vectors, syn1, size, _doctag_indexes[j], */ - __pyx_t_18 = __pyx_v_doctag_len; - for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { - __pyx_v_j = __pyx_t_19; + __pyx_t_20 = __pyx_v_doctag_len; + __pyx_t_21 = __pyx_t_20; + for (__pyx_t_22 = 0; __pyx_t_22 < __pyx_t_21; __pyx_t_22+=1) { + __pyx_v_j = __pyx_t_22; - /* "gensim/models/doc2vec_inner.pyx":352 + /* "gensim/models/doc2vec_inner.pyx":392 * # docvec-training * for j in range(doctag_len): * if hs: # <<<<<<<<<<<<<< @@ -4823,7 +4873,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":353 + /* "gensim/models/doc2vec_inner.pyx":393 * for j in range(doctag_len): * if hs: * fast_document_dbow_hs(points[i], codes[i], codelens[i], _doctag_vectors, syn1, size, _doctag_indexes[j], # <<<<<<<<<<<<<< @@ -4832,7 +4882,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), (__pyx_v_codelens[__pyx_v_i]), __pyx_v__doctag_vectors, __pyx_v_syn1, __pyx_v_size, (__pyx_v__doctag_indexes[__pyx_v_j]), __pyx_v__alpha, __pyx_v__work, __pyx_v__learn_doctags, __pyx_v__learn_hidden, __pyx_v__doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":352 + /* "gensim/models/doc2vec_inner.pyx":392 * # docvec-training * for j in range(doctag_len): * if hs: # <<<<<<<<<<<<<< @@ -4841,7 +4891,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ } - /* "gensim/models/doc2vec_inner.pyx":355 + /* "gensim/models/doc2vec_inner.pyx":395 * fast_document_dbow_hs(points[i], codes[i], codelens[i], _doctag_vectors, syn1, size, _doctag_indexes[j], * _alpha, _work, _learn_doctags, _learn_hidden, _doctag_locks) * if negative: # <<<<<<<<<<<<<< @@ -4851,7 +4901,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":356 + /* "gensim/models/doc2vec_inner.pyx":396 * _alpha, _work, _learn_doctags, _learn_hidden, _doctag_locks) * if negative: * next_random = fast_document_dbow_neg(negative, cum_table, cum_table_len, _doctag_vectors, syn1neg, size, # <<<<<<<<<<<<<< @@ -4860,7 +4910,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY */ __pyx_v_next_random = __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dbow_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v__doctag_vectors, __pyx_v_syn1neg, __pyx_v_size, (__pyx_v_indexes[__pyx_v_i]), (__pyx_v__doctag_indexes[__pyx_v_j]), __pyx_v__alpha, __pyx_v__work, __pyx_v_next_random, __pyx_v__learn_doctags, __pyx_v__learn_hidden, __pyx_v__doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":355 + /* "gensim/models/doc2vec_inner.pyx":395 * fast_document_dbow_hs(points[i], codes[i], codelens[i], _doctag_vectors, syn1, size, _doctag_indexes[j], * _alpha, _work, _learn_doctags, _learn_hidden, _doctag_locks) * if negative: # <<<<<<<<<<<<<< @@ -4872,7 +4922,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY } } - /* "gensim/models/doc2vec_inner.pyx":328 + /* "gensim/models/doc2vec_inner.pyx":368 * * # release GIL & train on the document * with nogil: # <<<<<<<<<<<<<< @@ -4891,7 +4941,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY } } - /* "gensim/models/doc2vec_inner.pyx":360 + /* "gensim/models/doc2vec_inner.pyx":400 * _learn_doctags, _learn_hidden, _doctag_locks) * * return result # <<<<<<<<<<<<<< @@ -4899,13 +4949,13 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_3 = __Pyx_PyInt_From_long(__pyx_v_result); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 360, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_long(__pyx_v_result); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 400, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":227 + /* "gensim/models/doc2vec_inner.pyx":223 * * * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, # <<<<<<<<<<<<<< @@ -4938,7 +4988,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY return __pyx_r; } -/* "gensim/models/doc2vec_inner.pyx":363 +/* "gensim/models/doc2vec_inner.pyx":403 * * * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< @@ -4948,7 +4998,8 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_train_document_dbow(CY /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_13doc2vec_inner_3train_document_dm = {"train_document_dm", (PyCFunction)__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_13doc2vec_inner_2train_document_dm[] = "train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None)\nUpdate distributed memory model (\"PV-DM\") by training on a single document.\n This method implements the DM model with a projection (input) layer that is either the sum or mean of the context\n vectors, depending on the model's `dm_mean` configuration field.\n\n Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and\n :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.doc2vec.Doc2Vec`\n The model to train.\n doc_words : list of str\n The input document as a list of words to be used for training. Each word will be looked up in\n the model's vocabulary.\n doctag_indexes : list of int\n Indices into `doctag_vectors` used to obtain the tags of the document.\n alpha : float\n Learning rate.\n work : np.ndarray, optional\n Private working memory for each worker.\n neu1 : np.ndarray, optional\n Private working memory for each worker.\n learn_doctags : bool, optional\n Whether the tag vectors should be updated.\n learn_words : bool, optional\n Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both**\n `learn_words` and `train_words` are set to True.\n learn_hidden : bool, optional\n Whether or not the weights of the hidden layer will be updated.\n word_vectors : numpy.ndarray, optional\n The vector representation for each word in the vocabulary. If None, these will be retrieved from the model.\n word_locks : numpy.ndarray, optional\n A learning lock factor for each weight in the hidden layer for words, value 0 completely blocks updates,\n a value of 1 allows to update word-vectors.\n doctag_vectors : n""umpy.ndarray, optional\n Vector representations of the tags. If None, these will be retrieved from the model.\n doctag_locks : numpy.ndarray, optional\n The lock factors for each tag, same as `word_locks`, but for document-vectors.\n\n Returns\n -------\n int\n Number of words in the input document that were actually used for training.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_13doc2vec_inner_3train_document_dm = {"train_document_dm", (PyCFunction)__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_13doc2vec_inner_2train_document_dm}; static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_doc_words = 0; @@ -4972,23 +5023,23 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm(PyO values[4] = ((PyObject *)Py_None); values[5] = ((PyObject *)Py_None); - /* "gensim/models/doc2vec_inner.pyx":364 + /* "gensim/models/doc2vec_inner.pyx":404 * * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, * learn_doctags=True, learn_words=True, learn_hidden=True, # <<<<<<<<<<<<<< * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): - * cdef int hs = model.hs + * """Update distributed memory model ("PV-DM") by training on a single document. */ values[6] = ((PyObject *)Py_True); values[7] = ((PyObject *)Py_True); values[8] = ((PyObject *)Py_True); - /* "gensim/models/doc2vec_inner.pyx":365 + /* "gensim/models/doc2vec_inner.pyx":405 * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, * learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update distributed memory model ("PV-DM") by training on a single document. + * This method implements the DM model with a projection (input) layer that is either the sum or mean of the context */ values[9] = ((PyObject *)Py_None); values[10] = ((PyObject *)Py_None); @@ -5030,83 +5081,83 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm(PyO kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doc_words)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doc_words)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, 1); __PYX_ERR(0, 363, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, 1); __PYX_ERR(0, 403, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_indexes)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_indexes)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, 2); __PYX_ERR(0, 363, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, 2); __PYX_ERR(0, 403, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, 3); __PYX_ERR(0, 363, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, 3); __PYX_ERR(0, 403, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work); if (value) { values[4] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 5: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_neu1); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_neu1); if (value) { values[5] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 6: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_doctags); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_doctags); if (value) { values[6] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 7: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_words); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_words); if (value) { values[7] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 8: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_hidden); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_hidden); if (value) { values[8] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 9: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word_vectors); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word_vectors); if (value) { values[9] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 10: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word_locks); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word_locks); if (value) { values[10] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 11: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_vectors); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_vectors); if (value) { values[11] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 12: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_locks); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_locks); if (value) { values[12] = value; kw_args--; } } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_document_dm") < 0)) __PYX_ERR(0, 363, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_document_dm") < 0)) __PYX_ERR(0, 403, __pyx_L3_error) } } else { switch (PyTuple_GET_SIZE(__pyx_args)) { @@ -5152,7 +5203,7 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm(PyO } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 363, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm", 0, 4, 13, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 403, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.doc2vec_inner.train_document_dm", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -5160,7 +5211,7 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_3train_document_dm(PyO __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(__pyx_self, __pyx_v_model, __pyx_v_doc_words, __pyx_v_doctag_indexes, __pyx_v_alpha, __pyx_v_work, __pyx_v_neu1, __pyx_v_learn_doctags, __pyx_v_learn_words, __pyx_v_learn_hidden, __pyx_v_word_vectors, __pyx_v_word_locks, __pyx_v_doctag_vectors, __pyx_v_doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":363 + /* "gensim/models/doc2vec_inner.pyx":403 * * * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< @@ -5235,6 +5286,8 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT long __pyx_t_17; int __pyx_t_18; int __pyx_t_19; + int __pyx_t_20; + int __pyx_t_21; __Pyx_RefNannySetupContext("train_document_dm", 0); __Pyx_INCREF(__pyx_v_work); __Pyx_INCREF(__pyx_v_neu1); @@ -5243,94 +5296,94 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __Pyx_INCREF(__pyx_v_doctag_vectors); __Pyx_INCREF(__pyx_v_doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":366 - * learn_doctags=True, learn_words=True, learn_hidden=True, - * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + /* "gensim/models/doc2vec_inner.pyx":451 + * + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 366, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 451, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 366, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 451, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":367 - * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + /* "gensim/models/doc2vec_inner.pyx":452 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * cdef int _learn_doctags = learn_doctags */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 367, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 452, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 367, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 452, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":368 + /* "gensim/models/doc2vec_inner.pyx":453 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * cdef int _learn_doctags = learn_doctags * cdef int _learn_words = learn_words */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 368, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 453, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 368, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 453, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 368, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 453, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 368, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 453, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":369 + /* "gensim/models/doc2vec_inner.pyx":454 * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) * cdef int _learn_doctags = learn_doctags # <<<<<<<<<<<<<< * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_doctags); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 369, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_doctags); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 454, __pyx_L1_error) __pyx_v__learn_doctags = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":370 + /* "gensim/models/doc2vec_inner.pyx":455 * cdef int sample = (model.vocabulary.sample != 0) * cdef int _learn_doctags = learn_doctags * cdef int _learn_words = learn_words # <<<<<<<<<<<<<< * cdef int _learn_hidden = learn_hidden * cdef int cbow_mean = model.cbow_mean */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 370, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 455, __pyx_L1_error) __pyx_v__learn_words = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":371 + /* "gensim/models/doc2vec_inner.pyx":456 * cdef int _learn_doctags = learn_doctags * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden # <<<<<<<<<<<<<< * cdef int cbow_mean = model.cbow_mean * cdef REAL_t count, inv_count = 1.0 */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_hidden); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 371, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_hidden); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 456, __pyx_L1_error) __pyx_v__learn_hidden = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":372 + /* "gensim/models/doc2vec_inner.pyx":457 * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden * cdef int cbow_mean = model.cbow_mean # <<<<<<<<<<<<<< * cdef REAL_t count, inv_count = 1.0 * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 372, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 457, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 372, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 457, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_cbow_mean = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":373 + /* "gensim/models/doc2vec_inner.pyx":458 * cdef int _learn_hidden = learn_hidden * cdef int cbow_mean = model.cbow_mean * cdef REAL_t count, inv_count = 1.0 # <<<<<<<<<<<<<< @@ -5339,46 +5392,46 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_inv_count = 1.0; - /* "gensim/models/doc2vec_inner.pyx":381 + /* "gensim/models/doc2vec_inner.pyx":466 * cdef REAL_t *_work * cdef REAL_t *_neu1 * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int size = model.trainables.layer1_size * */ - __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 381, __pyx_L1_error) + __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 466, __pyx_L1_error) __pyx_v__alpha = __pyx_t_4; - /* "gensim/models/doc2vec_inner.pyx":382 + /* "gensim/models/doc2vec_inner.pyx":467 * cdef REAL_t *_neu1 * cdef REAL_t _alpha = alpha * cdef int size = model.trainables.layer1_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_DOCUMENT_LEN] */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 382, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 467, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 382, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 467, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 382, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 467, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":390 + /* "gensim/models/doc2vec_inner.pyx":475 * cdef int document_len * cdef int doctag_len * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k, m */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 390, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 390, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":393 + /* "gensim/models/doc2vec_inner.pyx":478 * * cdef int i, j, k, m * cdef long result = 0 # <<<<<<<<<<<<<< @@ -5387,7 +5440,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_result = 0; - /* "gensim/models/doc2vec_inner.pyx":408 + /* "gensim/models/doc2vec_inner.pyx":493 * * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: # <<<<<<<<<<<<<< @@ -5398,22 +5451,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":409 + /* "gensim/models/doc2vec_inner.pyx":494 * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: * word_vectors = model.wv.vectors # <<<<<<<<<<<<<< * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 409, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 494, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 409, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 494, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_word_vectors, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":408 + /* "gensim/models/doc2vec_inner.pyx":493 * * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: # <<<<<<<<<<<<<< @@ -5422,17 +5475,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":410 + /* "gensim/models/doc2vec_inner.pyx":495 * if word_vectors is None: * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) # <<<<<<<<<<<<<< * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs */ - if (!(likely(((__pyx_v_word_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 410, __pyx_L1_error) + if (!(likely(((__pyx_v_word_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 495, __pyx_L1_error) __pyx_v__word_vectors = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_vectors))); - /* "gensim/models/doc2vec_inner.pyx":411 + /* "gensim/models/doc2vec_inner.pyx":496 * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: # <<<<<<<<<<<<<< @@ -5443,22 +5496,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_5 = (__pyx_t_6 != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":412 + /* "gensim/models/doc2vec_inner.pyx":497 * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs # <<<<<<<<<<<<<< * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 412, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 497, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 412, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 497, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF_SET(__pyx_v_doctag_vectors, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":411 + /* "gensim/models/doc2vec_inner.pyx":496 * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: # <<<<<<<<<<<<<< @@ -5467,17 +5520,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":413 + /* "gensim/models/doc2vec_inner.pyx":498 * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) # <<<<<<<<<<<<<< * if word_locks is None: * word_locks = model.trainables.vectors_lockf */ - if (!(likely(((__pyx_v_doctag_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 413, __pyx_L1_error) + if (!(likely(((__pyx_v_doctag_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 498, __pyx_L1_error) __pyx_v__doctag_vectors = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_doctag_vectors))); - /* "gensim/models/doc2vec_inner.pyx":414 + /* "gensim/models/doc2vec_inner.pyx":499 * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: # <<<<<<<<<<<<<< @@ -5488,22 +5541,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":415 + /* "gensim/models/doc2vec_inner.pyx":500 * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: * word_locks = model.trainables.vectors_lockf # <<<<<<<<<<<<<< * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 415, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 500, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 415, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 500, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_word_locks, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":414 + /* "gensim/models/doc2vec_inner.pyx":499 * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: # <<<<<<<<<<<<<< @@ -5512,17 +5565,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":416 + /* "gensim/models/doc2vec_inner.pyx":501 * if word_locks is None: * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) # <<<<<<<<<<<<<< * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf */ - if (!(likely(((__pyx_v_word_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 416, __pyx_L1_error) + if (!(likely(((__pyx_v_word_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 501, __pyx_L1_error) __pyx_v__word_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_locks))); - /* "gensim/models/doc2vec_inner.pyx":417 + /* "gensim/models/doc2vec_inner.pyx":502 * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: # <<<<<<<<<<<<<< @@ -5533,22 +5586,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_5 = (__pyx_t_6 != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":418 + /* "gensim/models/doc2vec_inner.pyx":503 * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf # <<<<<<<<<<<<<< * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 418, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 503, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs_lockf); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 418, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs_lockf); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 503, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF_SET(__pyx_v_doctag_locks, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":417 + /* "gensim/models/doc2vec_inner.pyx":502 * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: # <<<<<<<<<<<<<< @@ -5557,17 +5610,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":419 + /* "gensim/models/doc2vec_inner.pyx":504 * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf * _doctag_locks = (np.PyArray_DATA(doctag_locks)) # <<<<<<<<<<<<<< * * if hs: */ - if (!(likely(((__pyx_v_doctag_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 419, __pyx_L1_error) + if (!(likely(((__pyx_v_doctag_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 504, __pyx_L1_error) __pyx_v__doctag_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_doctag_locks))); - /* "gensim/models/doc2vec_inner.pyx":421 + /* "gensim/models/doc2vec_inner.pyx":506 * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * * if hs: # <<<<<<<<<<<<<< @@ -5577,23 +5630,23 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":422 + /* "gensim/models/doc2vec_inner.pyx":507 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 422, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 422, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 422, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 507, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":421 + /* "gensim/models/doc2vec_inner.pyx":506 * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * * if hs: # <<<<<<<<<<<<<< @@ -5602,7 +5655,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":424 + /* "gensim/models/doc2vec_inner.pyx":509 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -5612,55 +5665,55 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":425 + /* "gensim/models/doc2vec_inner.pyx":510 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 425, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 510, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 425, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 510, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 425, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 510, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":426 + /* "gensim/models/doc2vec_inner.pyx":511 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 426, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 511, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 426, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 511, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 426, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 511, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":427 + /* "gensim/models/doc2vec_inner.pyx":512 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 427, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 512, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 427, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 512, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_7 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 427, __pyx_L1_error) + __pyx_t_7 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 512, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_7; - /* "gensim/models/doc2vec_inner.pyx":424 + /* "gensim/models/doc2vec_inner.pyx":509 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -5669,7 +5722,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":428 + /* "gensim/models/doc2vec_inner.pyx":513 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -5687,41 +5740,41 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_L10_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":429 + /* "gensim/models/doc2vec_inner.pyx":514 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_next_random = __pyx_t_9; - /* "gensim/models/doc2vec_inner.pyx":428 + /* "gensim/models/doc2vec_inner.pyx":513 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -5730,7 +5783,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":432 + /* "gensim/models/doc2vec_inner.pyx":517 * * # convert Python structures to primitive types, so we can release the GIL * if work is None: # <<<<<<<<<<<<<< @@ -5741,32 +5794,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":433 + /* "gensim/models/doc2vec_inner.pyx":518 * # convert Python structures to primitive types, so we can release the GIL * if work is None: * work = zeros(model.trainables.layer1_size, dtype=REAL) # <<<<<<<<<<<<<< * _work = np.PyArray_DATA(work) * if neu1 is None: */ - __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_10) < 0) __PYX_ERR(0, 433, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_10) < 0) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 433, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 518, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; @@ -5774,7 +5827,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __Pyx_DECREF_SET(__pyx_v_work, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":432 + /* "gensim/models/doc2vec_inner.pyx":517 * * # convert Python structures to primitive types, so we can release the GIL * if work is None: # <<<<<<<<<<<<<< @@ -5783,17 +5836,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":434 + /* "gensim/models/doc2vec_inner.pyx":519 * if work is None: * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) # <<<<<<<<<<<<<< * if neu1 is None: * neu1 = zeros(model.trainables.layer1_size, dtype=REAL) */ - if (!(likely(((__pyx_v_work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 434, __pyx_L1_error) + if (!(likely(((__pyx_v_work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 519, __pyx_L1_error) __pyx_v__work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_work))); - /* "gensim/models/doc2vec_inner.pyx":435 + /* "gensim/models/doc2vec_inner.pyx":520 * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) * if neu1 is None: # <<<<<<<<<<<<<< @@ -5804,32 +5857,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_5 = (__pyx_t_6 != 0); if (__pyx_t_5) { - /* "gensim/models/doc2vec_inner.pyx":436 + /* "gensim/models/doc2vec_inner.pyx":521 * _work = np.PyArray_DATA(work) * if neu1 is None: * neu1 = zeros(model.trainables.layer1_size, dtype=REAL) # <<<<<<<<<<<<<< * _neu1 = np.PyArray_DATA(neu1) * */ - __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_dtype, __pyx_t_8) < 0) __PYX_ERR(0, 436, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_dtype, __pyx_t_8) < 0) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_t_10, __pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 436, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_t_10, __pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 521, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -5837,7 +5890,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __Pyx_DECREF_SET(__pyx_v_neu1, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/doc2vec_inner.pyx":435 + /* "gensim/models/doc2vec_inner.pyx":520 * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) * if neu1 is None: # <<<<<<<<<<<<<< @@ -5846,32 +5899,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":437 + /* "gensim/models/doc2vec_inner.pyx":522 * if neu1 is None: * neu1 = zeros(model.trainables.layer1_size, dtype=REAL) * _neu1 = np.PyArray_DATA(neu1) # <<<<<<<<<<<<<< * * vlookup = model.wv.vocab */ - if (!(likely(((__pyx_v_neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 437, __pyx_L1_error) + if (!(likely(((__pyx_v_neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 522, __pyx_L1_error) __pyx_v__neu1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_neu1))); - /* "gensim/models/doc2vec_inner.pyx":439 + /* "gensim/models/doc2vec_inner.pyx":524 * _neu1 = np.PyArray_DATA(neu1) * * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * i = 0 * for token in doc_words: */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 439, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 524, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 439, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 524, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_vlookup = __pyx_t_3; __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":440 + /* "gensim/models/doc2vec_inner.pyx":525 * * vlookup = model.wv.vocab * i = 0 # <<<<<<<<<<<<<< @@ -5880,7 +5933,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_i = 0; - /* "gensim/models/doc2vec_inner.pyx":441 + /* "gensim/models/doc2vec_inner.pyx":526 * vlookup = model.wv.vocab * i = 0 * for token in doc_words: # <<<<<<<<<<<<<< @@ -5891,26 +5944,26 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_3 = __pyx_v_doc_words; __Pyx_INCREF(__pyx_t_3); __pyx_t_7 = 0; __pyx_t_11 = NULL; } else { - __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_doc_words); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_doc_words); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 526, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_11 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_11 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 526, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_11)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_7 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_8); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_8); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 526, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 526, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } else { if (__pyx_t_7 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_8); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_8); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 526, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 526, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } @@ -5920,7 +5973,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 441, __pyx_L1_error) + else __PYX_ERR(0, 526, __pyx_L1_error) } break; } @@ -5929,16 +5982,16 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/doc2vec_inner.pyx":442 + /* "gensim/models/doc2vec_inner.pyx":527 * i = 0 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged */ - __pyx_t_5 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 442, __pyx_L1_error) + __pyx_t_5 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 527, __pyx_L1_error) if ((__pyx_t_5 != 0)) { - __pyx_t_1 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 442, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 527, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_8 = __pyx_t_1; __pyx_t_1 = 0; @@ -5949,7 +6002,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __Pyx_XDECREF_SET(__pyx_v_predict_word, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/doc2vec_inner.pyx":443 + /* "gensim/models/doc2vec_inner.pyx":528 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word # <<<<<<<<<<<<<< @@ -5960,7 +6013,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_t_5 != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":444 + /* "gensim/models/doc2vec_inner.pyx":529 * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged # <<<<<<<<<<<<<< @@ -5969,7 +6022,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ goto __pyx_L14_continue; - /* "gensim/models/doc2vec_inner.pyx":443 + /* "gensim/models/doc2vec_inner.pyx":528 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word # <<<<<<<<<<<<<< @@ -5978,7 +6031,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":445 + /* "gensim/models/doc2vec_inner.pyx":530 * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -5991,20 +6044,20 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = __pyx_t_5; goto __pyx_L18_bool_binop_done; } - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 445, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 530, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_1 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 445, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 530, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_10 = PyObject_RichCompare(__pyx_t_8, __pyx_t_1, Py_LT); __Pyx_XGOTREF(__pyx_t_10); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 445, __pyx_L1_error) + __pyx_t_10 = PyObject_RichCompare(__pyx_t_8, __pyx_t_1, Py_LT); __Pyx_XGOTREF(__pyx_t_10); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 530, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_5 = __Pyx_PyObject_IsTrue(__pyx_t_10); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 445, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_IsTrue(__pyx_t_10); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 530, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __pyx_t_6 = __pyx_t_5; __pyx_L18_bool_binop_done:; if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":446 + /* "gensim/models/doc2vec_inner.pyx":531 * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -6013,7 +6066,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ goto __pyx_L14_continue; - /* "gensim/models/doc2vec_inner.pyx":445 + /* "gensim/models/doc2vec_inner.pyx":530 * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -6022,20 +6075,20 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":447 + /* "gensim/models/doc2vec_inner.pyx":532 * if sample and predict_word.sample_int < random_int32(&next_random): * continue * indexes[i] = predict_word.index # <<<<<<<<<<<<<< * if hs: * codelens[i] = len(predict_word.code) */ - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_index); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 447, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_index); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 532, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_10); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 447, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_10); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 532, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; (__pyx_v_indexes[__pyx_v_i]) = __pyx_t_12; - /* "gensim/models/doc2vec_inner.pyx":448 + /* "gensim/models/doc2vec_inner.pyx":533 * continue * indexes[i] = predict_word.index * if hs: # <<<<<<<<<<<<<< @@ -6045,46 +6098,46 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_v_hs != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":449 + /* "gensim/models/doc2vec_inner.pyx":534 * indexes[i] = predict_word.index * if hs: * codelens[i] = len(predict_word.code) # <<<<<<<<<<<<<< * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) */ - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 534, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_13 = PyObject_Length(__pyx_t_10); if (unlikely(__pyx_t_13 == ((Py_ssize_t)-1))) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_13 = PyObject_Length(__pyx_t_10); if (unlikely(__pyx_t_13 == ((Py_ssize_t)-1))) __PYX_ERR(0, 534, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; (__pyx_v_codelens[__pyx_v_i]) = ((int)__pyx_t_13); - /* "gensim/models/doc2vec_inner.pyx":450 + /* "gensim/models/doc2vec_inner.pyx":535 * if hs: * codelens[i] = len(predict_word.code) * codes[i] = np.PyArray_DATA(predict_word.code) # <<<<<<<<<<<<<< * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 */ - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 450, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 535, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - if (!(likely(((__pyx_t_10) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_10, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 450, __pyx_L1_error) + if (!(likely(((__pyx_t_10) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_10, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 535, __pyx_L1_error) (__pyx_v_codes[__pyx_v_i]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_10))); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":451 + /* "gensim/models/doc2vec_inner.pyx":536 * codelens[i] = len(predict_word.code) * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) # <<<<<<<<<<<<<< * result += 1 * i += 1 */ - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_point); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 451, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_point); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 536, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - if (!(likely(((__pyx_t_10) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_10, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 451, __pyx_L1_error) + if (!(likely(((__pyx_t_10) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_10, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 536, __pyx_L1_error) (__pyx_v_points[__pyx_v_i]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_10))); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":448 + /* "gensim/models/doc2vec_inner.pyx":533 * continue * indexes[i] = predict_word.index * if hs: # <<<<<<<<<<<<<< @@ -6093,7 +6146,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":452 + /* "gensim/models/doc2vec_inner.pyx":537 * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 # <<<<<<<<<<<<<< @@ -6102,7 +6155,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_result = (__pyx_v_result + 1); - /* "gensim/models/doc2vec_inner.pyx":453 + /* "gensim/models/doc2vec_inner.pyx":538 * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 * i += 1 # <<<<<<<<<<<<<< @@ -6111,7 +6164,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_i = (__pyx_v_i + 1); - /* "gensim/models/doc2vec_inner.pyx":454 + /* "gensim/models/doc2vec_inner.pyx":539 * result += 1 * i += 1 * if i == MAX_DOCUMENT_LEN: # <<<<<<<<<<<<<< @@ -6121,7 +6174,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((__pyx_v_i == 0x2710) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":455 + /* "gensim/models/doc2vec_inner.pyx":540 * i += 1 * if i == MAX_DOCUMENT_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -6130,7 +6183,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ goto __pyx_L15_break; - /* "gensim/models/doc2vec_inner.pyx":454 + /* "gensim/models/doc2vec_inner.pyx":539 * result += 1 * i += 1 * if i == MAX_DOCUMENT_LEN: # <<<<<<<<<<<<<< @@ -6139,7 +6192,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":441 + /* "gensim/models/doc2vec_inner.pyx":526 * vlookup = model.wv.vocab * i = 0 * for token in doc_words: # <<<<<<<<<<<<<< @@ -6151,7 +6204,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_L15_break:; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":456 + /* "gensim/models/doc2vec_inner.pyx":541 * if i == MAX_DOCUMENT_LEN: * break # TODO: log warning, tally overflow? * document_len = i # <<<<<<<<<<<<<< @@ -6160,7 +6213,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_document_len = __pyx_v_i; - /* "gensim/models/doc2vec_inner.pyx":459 + /* "gensim/models/doc2vec_inner.pyx":544 * * # single randint() call avoids a big thread-sync slowdown * for i, item in enumerate(model.random.randint(0, window, document_len)): # <<<<<<<<<<<<<< @@ -6168,14 +6221,14 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT * */ __pyx_t_2 = 0; - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = __Pyx_PyInt_From_int(__pyx_v_window); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyInt_From_int(__pyx_v_window); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_8 = __Pyx_PyInt_From_int(__pyx_v_document_len); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyInt_From_int(__pyx_v_document_len); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __pyx_t_14 = NULL; __pyx_t_15 = 0; @@ -6192,7 +6245,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_1)) { PyObject *__pyx_temp[4] = {__pyx_t_14, __pyx_int_0, __pyx_t_10, __pyx_t_8}; - __pyx_t_3 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; @@ -6202,7 +6255,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_1)) { PyObject *__pyx_temp[4] = {__pyx_t_14, __pyx_int_0, __pyx_t_10, __pyx_t_8}; - __pyx_t_3 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-__pyx_t_15, 3+__pyx_t_15); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; @@ -6210,7 +6263,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT } else #endif { - __pyx_t_16 = PyTuple_New(3+__pyx_t_15); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_16 = PyTuple_New(3+__pyx_t_15); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_16); if (__pyx_t_14) { __Pyx_GIVEREF(__pyx_t_14); PyTuple_SET_ITEM(__pyx_t_16, 0, __pyx_t_14); __pyx_t_14 = NULL; @@ -6224,7 +6277,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT PyTuple_SET_ITEM(__pyx_t_16, 2+__pyx_t_15, __pyx_t_8); __pyx_t_10 = 0; __pyx_t_8 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_16, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_16, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_16); __pyx_t_16 = 0; } @@ -6233,9 +6286,9 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_1 = __pyx_t_3; __Pyx_INCREF(__pyx_t_1); __pyx_t_7 = 0; __pyx_t_11 = NULL; } else { - __pyx_t_7 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_7 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_11 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_11 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 544, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; for (;;) { @@ -6243,17 +6296,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT if (likely(PyList_CheckExact(__pyx_t_1))) { if (__pyx_t_7 >= PyList_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_3); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_3); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 544, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { if (__pyx_t_7 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_3); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_7); __Pyx_INCREF(__pyx_t_3); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 544, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 459, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } @@ -6263,7 +6316,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 459, __pyx_L1_error) + else __PYX_ERR(0, 544, __pyx_L1_error) } break; } @@ -6274,17 +6327,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_v_i = __pyx_t_2; __pyx_t_2 = (__pyx_t_2 + 1); - /* "gensim/models/doc2vec_inner.pyx":460 + /* "gensim/models/doc2vec_inner.pyx":545 * # single randint() call avoids a big thread-sync slowdown * for i, item in enumerate(model.random.randint(0, window, document_len)): * reduced_windows[i] = item # <<<<<<<<<<<<<< * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) */ - __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 545, __pyx_L1_error) (__pyx_v_reduced_windows[__pyx_v_i]) = __pyx_t_12; - /* "gensim/models/doc2vec_inner.pyx":459 + /* "gensim/models/doc2vec_inner.pyx":544 * * # single randint() call avoids a big thread-sync slowdown * for i, item in enumerate(model.random.randint(0, window, document_len)): # <<<<<<<<<<<<<< @@ -6294,14 +6347,14 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":462 + /* "gensim/models/doc2vec_inner.pyx":547 * reduced_windows[i] = item * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) # <<<<<<<<<<<<<< * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] */ - __pyx_t_7 = PyObject_Length(__pyx_v_doctag_indexes); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 462, __pyx_L1_error) + __pyx_t_7 = PyObject_Length(__pyx_v_doctag_indexes); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 547, __pyx_L1_error) __pyx_t_17 = 0x2710; if (((__pyx_t_7 < __pyx_t_17) != 0)) { __pyx_t_13 = __pyx_t_7; @@ -6310,7 +6363,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT } __pyx_v_doctag_len = ((int)__pyx_t_13); - /* "gensim/models/doc2vec_inner.pyx":463 + /* "gensim/models/doc2vec_inner.pyx":548 * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * for i in range(doctag_len): # <<<<<<<<<<<<<< @@ -6318,23 +6371,24 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT * result += 1 */ __pyx_t_2 = __pyx_v_doctag_len; - for (__pyx_t_15 = 0; __pyx_t_15 < __pyx_t_2; __pyx_t_15+=1) { - __pyx_v_i = __pyx_t_15; + __pyx_t_15 = __pyx_t_2; + for (__pyx_t_18 = 0; __pyx_t_18 < __pyx_t_15; __pyx_t_18+=1) { + __pyx_v_i = __pyx_t_18; - /* "gensim/models/doc2vec_inner.pyx":464 + /* "gensim/models/doc2vec_inner.pyx":549 * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] # <<<<<<<<<<<<<< * result += 1 * */ - __pyx_t_1 = __Pyx_GetItemInt(__pyx_v_doctag_indexes, __pyx_v_i, int, 1, __Pyx_PyInt_From_int, 0, 0, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 464, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetItemInt(__pyx_v_doctag_indexes, __pyx_v_i, int, 1, __Pyx_PyInt_From_int, 0, 0, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 549, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_1); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 464, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyInt_As_npy_uint32(__pyx_t_1); if (unlikely((__pyx_t_12 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 549, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; (__pyx_v__doctag_indexes[__pyx_v_i]) = __pyx_t_12; - /* "gensim/models/doc2vec_inner.pyx":465 + /* "gensim/models/doc2vec_inner.pyx":550 * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] * result += 1 # <<<<<<<<<<<<<< @@ -6344,7 +6398,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_v_result = (__pyx_v_result + 1); } - /* "gensim/models/doc2vec_inner.pyx":468 + /* "gensim/models/doc2vec_inner.pyx":553 * * # release GIL & train on the document * with nogil: # <<<<<<<<<<<<<< @@ -6359,7 +6413,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT #endif /*try:*/ { - /* "gensim/models/doc2vec_inner.pyx":469 + /* "gensim/models/doc2vec_inner.pyx":554 * # release GIL & train on the document * with nogil: * for i in range(document_len): # <<<<<<<<<<<<<< @@ -6367,10 +6421,11 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT * if j < 0: */ __pyx_t_2 = __pyx_v_document_len; - for (__pyx_t_15 = 0; __pyx_t_15 < __pyx_t_2; __pyx_t_15+=1) { - __pyx_v_i = __pyx_t_15; + __pyx_t_15 = __pyx_t_2; + for (__pyx_t_18 = 0; __pyx_t_18 < __pyx_t_15; __pyx_t_18+=1) { + __pyx_v_i = __pyx_t_18; - /* "gensim/models/doc2vec_inner.pyx":470 + /* "gensim/models/doc2vec_inner.pyx":555 * with nogil: * for i in range(document_len): * j = i - window + reduced_windows[i] # <<<<<<<<<<<<<< @@ -6379,7 +6434,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_j = ((__pyx_v_i - __pyx_v_window) + (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/doc2vec_inner.pyx":471 + /* "gensim/models/doc2vec_inner.pyx":556 * for i in range(document_len): * j = i - window + reduced_windows[i] * if j < 0: # <<<<<<<<<<<<<< @@ -6389,7 +6444,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((__pyx_v_j < 0) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":472 + /* "gensim/models/doc2vec_inner.pyx":557 * j = i - window + reduced_windows[i] * if j < 0: * j = 0 # <<<<<<<<<<<<<< @@ -6398,7 +6453,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_j = 0; - /* "gensim/models/doc2vec_inner.pyx":471 + /* "gensim/models/doc2vec_inner.pyx":556 * for i in range(document_len): * j = i - window + reduced_windows[i] * if j < 0: # <<<<<<<<<<<<<< @@ -6407,7 +6462,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":473 + /* "gensim/models/doc2vec_inner.pyx":558 * if j < 0: * j = 0 * k = i + window + 1 - reduced_windows[i] # <<<<<<<<<<<<<< @@ -6416,7 +6471,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_k = (((__pyx_v_i + __pyx_v_window) + 1) - (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/doc2vec_inner.pyx":474 + /* "gensim/models/doc2vec_inner.pyx":559 * j = 0 * k = i + window + 1 - reduced_windows[i] * if k > document_len: # <<<<<<<<<<<<<< @@ -6426,7 +6481,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((__pyx_v_k > __pyx_v_document_len) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":475 + /* "gensim/models/doc2vec_inner.pyx":560 * k = i + window + 1 - reduced_windows[i] * if k > document_len: * k = document_len # <<<<<<<<<<<<<< @@ -6435,7 +6490,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_k = __pyx_v_document_len; - /* "gensim/models/doc2vec_inner.pyx":474 + /* "gensim/models/doc2vec_inner.pyx":559 * j = 0 * k = i + window + 1 - reduced_windows[i] * if k > document_len: # <<<<<<<<<<<<<< @@ -6444,16 +6499,16 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":478 + /* "gensim/models/doc2vec_inner.pyx":563 * * # compose l1 (in _neu1) & clear _work * memset(_neu1, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * count = 0.0 * for m in range(j, k): */ - memset(__pyx_v__neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v__neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/doc2vec_inner.pyx":479 + /* "gensim/models/doc2vec_inner.pyx":564 * # compose l1 (in _neu1) & clear _work * memset(_neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 # <<<<<<<<<<<<<< @@ -6462,18 +6517,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_count = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.0); - /* "gensim/models/doc2vec_inner.pyx":480 + /* "gensim/models/doc2vec_inner.pyx":565 * memset(_neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 * for m in range(j, k): # <<<<<<<<<<<<<< * if m == i: * continue */ - __pyx_t_18 = __pyx_v_k; - for (__pyx_t_19 = __pyx_v_j; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { - __pyx_v_m = __pyx_t_19; + __pyx_t_19 = __pyx_v_k; + __pyx_t_20 = __pyx_t_19; + for (__pyx_t_21 = __pyx_v_j; __pyx_t_21 < __pyx_t_20; __pyx_t_21+=1) { + __pyx_v_m = __pyx_t_21; - /* "gensim/models/doc2vec_inner.pyx":481 + /* "gensim/models/doc2vec_inner.pyx":566 * count = 0.0 * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -6483,7 +6539,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((__pyx_v_m == __pyx_v_i) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":482 + /* "gensim/models/doc2vec_inner.pyx":567 * for m in range(j, k): * if m == i: * continue # <<<<<<<<<<<<<< @@ -6492,7 +6548,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ goto __pyx_L33_continue; - /* "gensim/models/doc2vec_inner.pyx":481 + /* "gensim/models/doc2vec_inner.pyx":566 * count = 0.0 * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -6501,7 +6557,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":484 + /* "gensim/models/doc2vec_inner.pyx":569 * continue * else: * count += ONEF # <<<<<<<<<<<<<< @@ -6511,7 +6567,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT /*else*/ { __pyx_v_count = (__pyx_v_count + __pyx_v_6gensim_6models_13doc2vec_inner_ONEF); - /* "gensim/models/doc2vec_inner.pyx":485 + /* "gensim/models/doc2vec_inner.pyx":570 * else: * count += ONEF * our_saxpy(&size, &ONEF, &_word_vectors[indexes[m] * size], &ONE, _neu1, &ONE) # <<<<<<<<<<<<<< @@ -6523,18 +6579,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_L33_continue:; } - /* "gensim/models/doc2vec_inner.pyx":486 + /* "gensim/models/doc2vec_inner.pyx":571 * count += ONEF * our_saxpy(&size, &ONEF, &_word_vectors[indexes[m] * size], &ONE, _neu1, &ONE) * for m in range(doctag_len): # <<<<<<<<<<<<<< * count += ONEF * our_saxpy(&size, &ONEF, &_doctag_vectors[_doctag_indexes[m] * size], &ONE, _neu1, &ONE) */ - __pyx_t_18 = __pyx_v_doctag_len; - for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { - __pyx_v_m = __pyx_t_19; + __pyx_t_19 = __pyx_v_doctag_len; + __pyx_t_20 = __pyx_t_19; + for (__pyx_t_21 = 0; __pyx_t_21 < __pyx_t_20; __pyx_t_21+=1) { + __pyx_v_m = __pyx_t_21; - /* "gensim/models/doc2vec_inner.pyx":487 + /* "gensim/models/doc2vec_inner.pyx":572 * our_saxpy(&size, &ONEF, &_word_vectors[indexes[m] * size], &ONE, _neu1, &ONE) * for m in range(doctag_len): * count += ONEF # <<<<<<<<<<<<<< @@ -6543,7 +6600,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_count = (__pyx_v_count + __pyx_v_6gensim_6models_13doc2vec_inner_ONEF); - /* "gensim/models/doc2vec_inner.pyx":488 + /* "gensim/models/doc2vec_inner.pyx":573 * for m in range(doctag_len): * count += ONEF * our_saxpy(&size, &ONEF, &_doctag_vectors[_doctag_indexes[m] * size], &ONE, _neu1, &ONE) # <<<<<<<<<<<<<< @@ -6553,7 +6610,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONEF), (&(__pyx_v__doctag_vectors[((__pyx_v__doctag_indexes[__pyx_v_m]) * __pyx_v_size)])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), __pyx_v__neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); } - /* "gensim/models/doc2vec_inner.pyx":489 + /* "gensim/models/doc2vec_inner.pyx":574 * count += ONEF * our_saxpy(&size, &ONEF, &_doctag_vectors[_doctag_indexes[m] * size], &ONE, _neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< @@ -6563,7 +6620,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":490 + /* "gensim/models/doc2vec_inner.pyx":575 * our_saxpy(&size, &ONEF, &_doctag_vectors[_doctag_indexes[m] * size], &ONE, _neu1, &ONE) * if count > (0.5): * inv_count = ONEF/count # <<<<<<<<<<<<<< @@ -6572,7 +6629,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_inv_count = (__pyx_v_6gensim_6models_13doc2vec_inner_ONEF / __pyx_v_count); - /* "gensim/models/doc2vec_inner.pyx":489 + /* "gensim/models/doc2vec_inner.pyx":574 * count += ONEF * our_saxpy(&size, &ONEF, &_doctag_vectors[_doctag_indexes[m] * size], &ONE, _neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< @@ -6581,7 +6638,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":491 + /* "gensim/models/doc2vec_inner.pyx":576 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< @@ -6591,7 +6648,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_v_cbow_mean != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":492 + /* "gensim/models/doc2vec_inner.pyx":577 * inv_count = ONEF/count * if cbow_mean: * sscal(&size, &inv_count, _neu1, &ONE) # (does this need BLAS-variants like saxpy?) # <<<<<<<<<<<<<< @@ -6600,7 +6657,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v__neu1, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":491 + /* "gensim/models/doc2vec_inner.pyx":576 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< @@ -6609,16 +6666,16 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":493 + /* "gensim/models/doc2vec_inner.pyx":578 * if cbow_mean: * sscal(&size, &inv_count, _neu1, &ONE) # (does this need BLAS-variants like saxpy?) * memset(_work, 0, size * cython.sizeof(REAL_t)) # work to accumulate l1 error # <<<<<<<<<<<<<< * if hs: * fast_document_dm_hs(points[i], codes[i], codelens[i], */ - memset(__pyx_v__work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v__work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/doc2vec_inner.pyx":494 + /* "gensim/models/doc2vec_inner.pyx":579 * sscal(&size, &inv_count, _neu1, &ONE) # (does this need BLAS-variants like saxpy?) * memset(_work, 0, size * cython.sizeof(REAL_t)) # work to accumulate l1 error * if hs: # <<<<<<<<<<<<<< @@ -6628,7 +6685,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_v_hs != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":495 + /* "gensim/models/doc2vec_inner.pyx":580 * memset(_work, 0, size * cython.sizeof(REAL_t)) # work to accumulate l1 error * if hs: * fast_document_dm_hs(points[i], codes[i], codelens[i], # <<<<<<<<<<<<<< @@ -6637,7 +6694,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), (__pyx_v_codelens[__pyx_v_i]), __pyx_v__neu1, __pyx_v_syn1, __pyx_v__alpha, __pyx_v__work, __pyx_v_size, __pyx_v__learn_hidden); - /* "gensim/models/doc2vec_inner.pyx":494 + /* "gensim/models/doc2vec_inner.pyx":579 * sscal(&size, &inv_count, _neu1, &ONE) # (does this need BLAS-variants like saxpy?) * memset(_work, 0, size * cython.sizeof(REAL_t)) # work to accumulate l1 error * if hs: # <<<<<<<<<<<<<< @@ -6646,7 +6703,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":498 + /* "gensim/models/doc2vec_inner.pyx":583 * _neu1, syn1, _alpha, _work, * size, _learn_hidden) * if negative: # <<<<<<<<<<<<<< @@ -6656,7 +6713,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_v_negative != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":499 + /* "gensim/models/doc2vec_inner.pyx":584 * size, _learn_hidden) * if negative: * next_random = fast_document_dm_neg(negative, cum_table, cum_table_len, next_random, # <<<<<<<<<<<<<< @@ -6665,7 +6722,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_next_random = __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dm_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v_next_random, __pyx_v__neu1, __pyx_v_syn1neg, (__pyx_v_indexes[__pyx_v_i]), __pyx_v__alpha, __pyx_v__work, __pyx_v_size, __pyx_v__learn_hidden); - /* "gensim/models/doc2vec_inner.pyx":498 + /* "gensim/models/doc2vec_inner.pyx":583 * _neu1, syn1, _alpha, _work, * size, _learn_hidden) * if negative: # <<<<<<<<<<<<<< @@ -6674,7 +6731,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":503 + /* "gensim/models/doc2vec_inner.pyx":588 * size, _learn_hidden) * * if not cbow_mean: # <<<<<<<<<<<<<< @@ -6684,7 +6741,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((!(__pyx_v_cbow_mean != 0)) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":504 + /* "gensim/models/doc2vec_inner.pyx":589 * * if not cbow_mean: * sscal(&size, &inv_count, _work, &ONE) # (does this need BLAS-variants like saxpy?) # <<<<<<<<<<<<<< @@ -6693,7 +6750,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v__work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); - /* "gensim/models/doc2vec_inner.pyx":503 + /* "gensim/models/doc2vec_inner.pyx":588 * size, _learn_hidden) * * if not cbow_mean: # <<<<<<<<<<<<<< @@ -6702,7 +6759,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":506 + /* "gensim/models/doc2vec_inner.pyx":591 * sscal(&size, &inv_count, _work, &ONE) # (does this need BLAS-variants like saxpy?) * # apply accumulated error in work * if _learn_doctags: # <<<<<<<<<<<<<< @@ -6712,18 +6769,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_v__learn_doctags != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":507 + /* "gensim/models/doc2vec_inner.pyx":592 * # apply accumulated error in work * if _learn_doctags: * for m in range(doctag_len): # <<<<<<<<<<<<<< * our_saxpy(&size, &_doctag_locks[_doctag_indexes[m]], _work, * &ONE, &_doctag_vectors[_doctag_indexes[m] * size], &ONE) */ - __pyx_t_18 = __pyx_v_doctag_len; - for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { - __pyx_v_m = __pyx_t_19; + __pyx_t_19 = __pyx_v_doctag_len; + __pyx_t_20 = __pyx_t_19; + for (__pyx_t_21 = 0; __pyx_t_21 < __pyx_t_20; __pyx_t_21+=1) { + __pyx_v_m = __pyx_t_21; - /* "gensim/models/doc2vec_inner.pyx":508 + /* "gensim/models/doc2vec_inner.pyx":593 * if _learn_doctags: * for m in range(doctag_len): * our_saxpy(&size, &_doctag_locks[_doctag_indexes[m]], _work, # <<<<<<<<<<<<<< @@ -6733,7 +6791,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&(__pyx_v__doctag_locks[(__pyx_v__doctag_indexes[__pyx_v_m])])), __pyx_v__work, (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v__doctag_vectors[((__pyx_v__doctag_indexes[__pyx_v_m]) * __pyx_v_size)])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); } - /* "gensim/models/doc2vec_inner.pyx":506 + /* "gensim/models/doc2vec_inner.pyx":591 * sscal(&size, &inv_count, _work, &ONE) # (does this need BLAS-variants like saxpy?) * # apply accumulated error in work * if _learn_doctags: # <<<<<<<<<<<<<< @@ -6742,7 +6800,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":510 + /* "gensim/models/doc2vec_inner.pyx":595 * our_saxpy(&size, &_doctag_locks[_doctag_indexes[m]], _work, * &ONE, &_doctag_vectors[_doctag_indexes[m] * size], &ONE) * if _learn_words: # <<<<<<<<<<<<<< @@ -6752,18 +6810,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = (__pyx_v__learn_words != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":511 + /* "gensim/models/doc2vec_inner.pyx":596 * &ONE, &_doctag_vectors[_doctag_indexes[m] * size], &ONE) * if _learn_words: * for m in range(j, k): # <<<<<<<<<<<<<< * if m == i: * continue */ - __pyx_t_18 = __pyx_v_k; - for (__pyx_t_19 = __pyx_v_j; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { - __pyx_v_m = __pyx_t_19; + __pyx_t_19 = __pyx_v_k; + __pyx_t_20 = __pyx_t_19; + for (__pyx_t_21 = __pyx_v_j; __pyx_t_21 < __pyx_t_20; __pyx_t_21+=1) { + __pyx_v_m = __pyx_t_21; - /* "gensim/models/doc2vec_inner.pyx":512 + /* "gensim/models/doc2vec_inner.pyx":597 * if _learn_words: * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -6773,7 +6832,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_t_6 = ((__pyx_v_m == __pyx_v_i) != 0); if (__pyx_t_6) { - /* "gensim/models/doc2vec_inner.pyx":513 + /* "gensim/models/doc2vec_inner.pyx":598 * for m in range(j, k): * if m == i: * continue # <<<<<<<<<<<<<< @@ -6782,7 +6841,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ goto __pyx_L47_continue; - /* "gensim/models/doc2vec_inner.pyx":512 + /* "gensim/models/doc2vec_inner.pyx":597 * if _learn_words: * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -6791,7 +6850,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ } - /* "gensim/models/doc2vec_inner.pyx":515 + /* "gensim/models/doc2vec_inner.pyx":600 * continue * else: * our_saxpy(&size, &_word_locks[indexes[m]], _work, &ONE, # <<<<<<<<<<<<<< @@ -6800,7 +6859,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT */ /*else*/ { - /* "gensim/models/doc2vec_inner.pyx":516 + /* "gensim/models/doc2vec_inner.pyx":601 * else: * our_saxpy(&size, &_word_locks[indexes[m]], _work, &ONE, * &_word_vectors[indexes[m] * size], &ONE) # <<<<<<<<<<<<<< @@ -6812,7 +6871,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT __pyx_L47_continue:; } - /* "gensim/models/doc2vec_inner.pyx":510 + /* "gensim/models/doc2vec_inner.pyx":595 * our_saxpy(&size, &_doctag_locks[_doctag_indexes[m]], _work, * &ONE, &_doctag_vectors[_doctag_indexes[m] * size], &ONE) * if _learn_words: # <<<<<<<<<<<<<< @@ -6823,7 +6882,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT } } - /* "gensim/models/doc2vec_inner.pyx":468 + /* "gensim/models/doc2vec_inner.pyx":553 * * # release GIL & train on the document * with nogil: # <<<<<<<<<<<<<< @@ -6842,7 +6901,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT } } - /* "gensim/models/doc2vec_inner.pyx":518 + /* "gensim/models/doc2vec_inner.pyx":603 * &_word_vectors[indexes[m] * size], &ONE) * * return result # <<<<<<<<<<<<<< @@ -6850,13 +6909,13 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyInt_From_long(__pyx_v_result); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 518, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_long(__pyx_v_result); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 603, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":363 + /* "gensim/models/doc2vec_inner.pyx":403 * * * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< @@ -6890,7 +6949,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT return __pyx_r; } -/* "gensim/models/doc2vec_inner.pyx":521 +/* "gensim/models/doc2vec_inner.pyx":606 * * * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< @@ -6900,7 +6959,8 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_2train_document_dm(CYT /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_concat(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_13doc2vec_inner_5train_document_dm_concat = {"train_document_dm_concat", (PyCFunction)__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_concat, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_13doc2vec_inner_4train_document_dm_concat[] = "train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None)\nUpdate distributed memory model (\"PV-DM\") by training on a single document, using a concatenation of the context\n window word vectors (rather than a sum or average).\n This might be slower since the input at each batch will be significantly larger.\n\n Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and\n :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.doc2vec.Doc2Vec`\n The model to train.\n doc_words : list of str\n The input document as a list of words to be used for training. Each word will be looked up in\n the model's vocabulary.\n doctag_indexes : list of int\n Indices into `doctag_vectors` used to obtain the tags of the document.\n alpha : float, optional\n Learning rate.\n work : np.ndarray, optional\n Private working memory for each worker.\n neu1 : np.ndarray, optional\n Private working memory for each worker.\n learn_doctags : bool, optional\n Whether the tag vectors should be updated.\n learn_words : bool, optional\n Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both**\n `learn_words` and `train_words` are set to True.\n learn_hidden : bool, optional\n Whether or not the weights of the hidden layer will be updated.\n word_vectors : numpy.ndarray, optional\n The vector representation for each word in the vocabulary. If None, these will be retrieved from the model.\n word_locks : numpy.ndarray, optional\n A learning lock factor for each weight in the hidden layer for words, value 0 completely blocks updates,\n a value of 1 allows to update word-vectors.\n doctag_v""ectors : numpy.ndarray, optional\n Vector representations of the tags. If None, these will be retrieved from the model.\n doctag_locks : numpy.ndarray, optional\n The lock factors for each tag, same as `word_locks`, but for document-vectors.\n\n Returns\n -------\n int\n Number of words in the input document that were actually used for training.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_13doc2vec_inner_5train_document_dm_concat = {"train_document_dm_concat", (PyCFunction)__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_concat, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_13doc2vec_inner_4train_document_dm_concat}; static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_concat(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_doc_words = 0; @@ -6924,23 +6984,23 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_con values[4] = ((PyObject *)Py_None); values[5] = ((PyObject *)Py_None); - /* "gensim/models/doc2vec_inner.pyx":522 + /* "gensim/models/doc2vec_inner.pyx":607 * * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, * learn_doctags=True, learn_words=True, learn_hidden=True, # <<<<<<<<<<<<<< * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): - * cdef int hs = model.hs + * """Update distributed memory model ("PV-DM") by training on a single document, using a concatenation of the context */ values[6] = ((PyObject *)Py_True); values[7] = ((PyObject *)Py_True); values[8] = ((PyObject *)Py_True); - /* "gensim/models/doc2vec_inner.pyx":523 + /* "gensim/models/doc2vec_inner.pyx":608 * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, * learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update distributed memory model ("PV-DM") by training on a single document, using a concatenation of the context + * window word vectors (rather than a sum or average). */ values[9] = ((PyObject *)Py_None); values[10] = ((PyObject *)Py_None); @@ -6982,83 +7042,83 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_con kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doc_words)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doc_words)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, 1); __PYX_ERR(0, 521, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, 1); __PYX_ERR(0, 606, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_indexes)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_indexes)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, 2); __PYX_ERR(0, 521, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, 2); __PYX_ERR(0, 606, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, 3); __PYX_ERR(0, 521, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, 3); __PYX_ERR(0, 606, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work); if (value) { values[4] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 5: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_neu1); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_neu1); if (value) { values[5] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 6: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_doctags); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_doctags); if (value) { values[6] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 7: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_words); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_words); if (value) { values[7] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 8: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_learn_hidden); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_learn_hidden); if (value) { values[8] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 9: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word_vectors); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word_vectors); if (value) { values[9] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 10: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_word_locks); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_word_locks); if (value) { values[10] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 11: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_vectors); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_vectors); if (value) { values[11] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 12: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_doctag_locks); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_doctag_locks); if (value) { values[12] = value; kw_args--; } } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_document_dm_concat") < 0)) __PYX_ERR(0, 521, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_document_dm_concat") < 0)) __PYX_ERR(0, 606, __pyx_L3_error) } } else { switch (PyTuple_GET_SIZE(__pyx_args)) { @@ -7104,7 +7164,7 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_con } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 521, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_document_dm_concat", 0, 4, 13, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 606, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.doc2vec_inner.train_document_dm_concat", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -7112,7 +7172,7 @@ static PyObject *__pyx_pw_6gensim_6models_13doc2vec_inner_5train_document_dm_con __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_concat(__pyx_self, __pyx_v_model, __pyx_v_doc_words, __pyx_v_doctag_indexes, __pyx_v_alpha, __pyx_v_work, __pyx_v_neu1, __pyx_v_learn_doctags, __pyx_v_learn_words, __pyx_v_learn_hidden, __pyx_v_word_vectors, __pyx_v_word_locks, __pyx_v_doctag_vectors, __pyx_v_doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":521 + /* "gensim/models/doc2vec_inner.pyx":606 * * * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< @@ -7185,6 +7245,9 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con int __pyx_t_15; int __pyx_t_16; int __pyx_t_17; + int __pyx_t_18; + int __pyx_t_19; + long __pyx_t_20; __Pyx_RefNannySetupContext("train_document_dm_concat", 0); __Pyx_INCREF(__pyx_v_work); __Pyx_INCREF(__pyx_v_neu1); @@ -7193,149 +7256,149 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __Pyx_INCREF(__pyx_v_doctag_vectors); __Pyx_INCREF(__pyx_v_doctag_locks); - /* "gensim/models/doc2vec_inner.pyx":524 - * learn_doctags=True, learn_words=True, learn_hidden=True, - * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + /* "gensim/models/doc2vec_inner.pyx":654 + * + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 524, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 654, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 524, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 654, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":525 - * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + /* "gensim/models/doc2vec_inner.pyx":655 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * cdef int _learn_doctags = learn_doctags */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 525, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 655, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 525, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 655, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":526 + /* "gensim/models/doc2vec_inner.pyx":656 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * cdef int _learn_doctags = learn_doctags * cdef int _learn_words = learn_words */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 526, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 656, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 526, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 656, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 526, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 656, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 526, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 656, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":527 + /* "gensim/models/doc2vec_inner.pyx":657 * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) * cdef int _learn_doctags = learn_doctags # <<<<<<<<<<<<<< * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_doctags); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 527, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_doctags); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 657, __pyx_L1_error) __pyx_v__learn_doctags = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":528 + /* "gensim/models/doc2vec_inner.pyx":658 * cdef int sample = (model.vocabulary.sample != 0) * cdef int _learn_doctags = learn_doctags * cdef int _learn_words = learn_words # <<<<<<<<<<<<<< * cdef int _learn_hidden = learn_hidden * */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 528, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_words); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 658, __pyx_L1_error) __pyx_v__learn_words = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":529 + /* "gensim/models/doc2vec_inner.pyx":659 * cdef int _learn_doctags = learn_doctags * cdef int _learn_words = learn_words * cdef int _learn_hidden = learn_hidden # <<<<<<<<<<<<<< * * cdef REAL_t *_word_vectors */ - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_hidden); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 529, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_v_learn_hidden); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 659, __pyx_L1_error) __pyx_v__learn_hidden = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":537 + /* "gensim/models/doc2vec_inner.pyx":667 * cdef REAL_t *_work * cdef REAL_t *_neu1 * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int layer1_size = model.trainables.layer1_size * cdef int vector_size = model.docvecs.vector_size */ - __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 537, __pyx_L1_error) + __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 667, __pyx_L1_error) __pyx_v__alpha = __pyx_t_4; - /* "gensim/models/doc2vec_inner.pyx":538 + /* "gensim/models/doc2vec_inner.pyx":668 * cdef REAL_t *_neu1 * cdef REAL_t _alpha = alpha * cdef int layer1_size = model.trainables.layer1_size # <<<<<<<<<<<<<< * cdef int vector_size = model.docvecs.vector_size * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 538, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 668, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 538, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 668, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 538, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 668, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_layer1_size = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":539 + /* "gensim/models/doc2vec_inner.pyx":669 * cdef REAL_t _alpha = alpha * cdef int layer1_size = model.trainables.layer1_size * cdef int vector_size = model.docvecs.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_DOCUMENT_LEN] */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 539, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 669, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 539, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 669, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 539, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 669, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_vector_size = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":547 + /* "gensim/models/doc2vec_inner.pyx":677 * cdef int document_len * cdef int doctag_len * cdef int window = model.window # <<<<<<<<<<<<<< * cdef int expected_doctag_len = model.dm_tag_count * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 547, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 677, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 547, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 677, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":548 + /* "gensim/models/doc2vec_inner.pyx":678 * cdef int doctag_len * cdef int window = model.window * cdef int expected_doctag_len = model.dm_tag_count # <<<<<<<<<<<<<< * * cdef int i, j, k, m, n */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_dm_tag_count); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 548, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_dm_tag_count); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 678, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 548, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 678, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_expected_doctag_len = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":551 + /* "gensim/models/doc2vec_inner.pyx":681 * * cdef int i, j, k, m, n * cdef long result = 0 # <<<<<<<<<<<<<< @@ -7344,36 +7407,36 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_result = 0; - /* "gensim/models/doc2vec_inner.pyx":552 + /* "gensim/models/doc2vec_inner.pyx":682 * cdef int i, j, k, m, n * cdef long result = 0 * cdef int null_word_index = model.wv.vocab['\0'].index # <<<<<<<<<<<<<< * * # For hierarchical softmax */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 552, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 552, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_GetItem(__pyx_t_3, __pyx_kp_s__5); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 552, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Dict_GetItem(__pyx_t_3, __pyx_kp_s__5); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_index); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 552, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_index); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 552, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_null_word_index = __pyx_t_2; - /* "gensim/models/doc2vec_inner.pyx":565 + /* "gensim/models/doc2vec_inner.pyx":695 * cdef unsigned long long next_random * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) # <<<<<<<<<<<<<< * if doctag_len != expected_doctag_len: * return 0 # skip doc without expected number of tags */ - __pyx_t_5 = PyObject_Length(__pyx_v_doctag_indexes); if (unlikely(__pyx_t_5 == ((Py_ssize_t)-1))) __PYX_ERR(0, 565, __pyx_L1_error) + __pyx_t_5 = PyObject_Length(__pyx_v_doctag_indexes); if (unlikely(__pyx_t_5 == ((Py_ssize_t)-1))) __PYX_ERR(0, 695, __pyx_L1_error) __pyx_t_6 = 0x2710; if (((__pyx_t_5 < __pyx_t_6) != 0)) { __pyx_t_7 = __pyx_t_5; @@ -7382,7 +7445,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con } __pyx_v_doctag_len = ((int)__pyx_t_7); - /* "gensim/models/doc2vec_inner.pyx":566 + /* "gensim/models/doc2vec_inner.pyx":696 * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * if doctag_len != expected_doctag_len: # <<<<<<<<<<<<<< @@ -7392,7 +7455,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_8 = ((__pyx_v_doctag_len != __pyx_v_expected_doctag_len) != 0); if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":567 + /* "gensim/models/doc2vec_inner.pyx":697 * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * if doctag_len != expected_doctag_len: * return 0 # skip doc without expected number of tags # <<<<<<<<<<<<<< @@ -7404,7 +7467,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_r = __pyx_int_0; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":566 + /* "gensim/models/doc2vec_inner.pyx":696 * * doctag_len = min(MAX_DOCUMENT_LEN, len(doctag_indexes)) * if doctag_len != expected_doctag_len: # <<<<<<<<<<<<<< @@ -7413,7 +7476,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":570 + /* "gensim/models/doc2vec_inner.pyx":700 * * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: # <<<<<<<<<<<<<< @@ -7424,22 +7487,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_t_8 != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":571 + /* "gensim/models/doc2vec_inner.pyx":701 * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: * word_vectors = model.wv.vectors # <<<<<<<<<<<<<< * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 571, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 701, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 571, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 701, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_word_vectors, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":570 + /* "gensim/models/doc2vec_inner.pyx":700 * * # default vectors, locks from syn0/doctag_syn0 * if word_vectors is None: # <<<<<<<<<<<<<< @@ -7448,17 +7511,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":572 + /* "gensim/models/doc2vec_inner.pyx":702 * if word_vectors is None: * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) # <<<<<<<<<<<<<< * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs */ - if (!(likely(((__pyx_v_word_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 572, __pyx_L1_error) + if (!(likely(((__pyx_v_word_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 702, __pyx_L1_error) __pyx_v__word_vectors = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_vectors))); - /* "gensim/models/doc2vec_inner.pyx":573 + /* "gensim/models/doc2vec_inner.pyx":703 * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: # <<<<<<<<<<<<<< @@ -7469,22 +7532,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_8 = (__pyx_t_9 != 0); if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":574 + /* "gensim/models/doc2vec_inner.pyx":704 * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs # <<<<<<<<<<<<<< * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 574, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_docvecs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 704, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 574, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 704, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF_SET(__pyx_v_doctag_vectors, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":573 + /* "gensim/models/doc2vec_inner.pyx":703 * word_vectors = model.wv.vectors * _word_vectors = (np.PyArray_DATA(word_vectors)) * if doctag_vectors is None: # <<<<<<<<<<<<<< @@ -7493,17 +7556,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":575 + /* "gensim/models/doc2vec_inner.pyx":705 * if doctag_vectors is None: * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) # <<<<<<<<<<<<<< * if word_locks is None: * word_locks = model.trainables.vectors_lockf */ - if (!(likely(((__pyx_v_doctag_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 575, __pyx_L1_error) + if (!(likely(((__pyx_v_doctag_vectors) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_vectors, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 705, __pyx_L1_error) __pyx_v__doctag_vectors = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_doctag_vectors))); - /* "gensim/models/doc2vec_inner.pyx":576 + /* "gensim/models/doc2vec_inner.pyx":706 * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: # <<<<<<<<<<<<<< @@ -7514,22 +7577,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_t_8 != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":577 + /* "gensim/models/doc2vec_inner.pyx":707 * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: * word_locks = model.trainables.vectors_lockf # <<<<<<<<<<<<<< * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 577, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 707, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 577, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 707, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_word_locks, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":576 + /* "gensim/models/doc2vec_inner.pyx":706 * doctag_vectors = model.docvecs.vectors_docs * _doctag_vectors = (np.PyArray_DATA(doctag_vectors)) * if word_locks is None: # <<<<<<<<<<<<<< @@ -7538,17 +7601,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":578 + /* "gensim/models/doc2vec_inner.pyx":708 * if word_locks is None: * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) # <<<<<<<<<<<<<< * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf */ - if (!(likely(((__pyx_v_word_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 578, __pyx_L1_error) + if (!(likely(((__pyx_v_word_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 708, __pyx_L1_error) __pyx_v__word_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_locks))); - /* "gensim/models/doc2vec_inner.pyx":579 + /* "gensim/models/doc2vec_inner.pyx":709 * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: # <<<<<<<<<<<<<< @@ -7559,22 +7622,22 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_8 = (__pyx_t_9 != 0); if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":580 + /* "gensim/models/doc2vec_inner.pyx":710 * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf # <<<<<<<<<<<<<< * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 580, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 710, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs_lockf); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 580, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_docs_lockf); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 710, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF_SET(__pyx_v_doctag_locks, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":579 + /* "gensim/models/doc2vec_inner.pyx":709 * word_locks = model.trainables.vectors_lockf * _word_locks = (np.PyArray_DATA(word_locks)) * if doctag_locks is None: # <<<<<<<<<<<<<< @@ -7583,17 +7646,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":581 + /* "gensim/models/doc2vec_inner.pyx":711 * if doctag_locks is None: * doctag_locks = model.trainables.vectors_docs_lockf * _doctag_locks = (np.PyArray_DATA(doctag_locks)) # <<<<<<<<<<<<<< * * if hs: */ - if (!(likely(((__pyx_v_doctag_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 581, __pyx_L1_error) + if (!(likely(((__pyx_v_doctag_locks) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_doctag_locks, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 711, __pyx_L1_error) __pyx_v__doctag_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_doctag_locks))); - /* "gensim/models/doc2vec_inner.pyx":583 + /* "gensim/models/doc2vec_inner.pyx":713 * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * * if hs: # <<<<<<<<<<<<<< @@ -7603,23 +7666,23 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_8 = (__pyx_v_hs != 0); if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":584 + /* "gensim/models/doc2vec_inner.pyx":714 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 584, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 714, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 584, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 714, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 584, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 714, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":583 + /* "gensim/models/doc2vec_inner.pyx":713 * _doctag_locks = (np.PyArray_DATA(doctag_locks)) * * if hs: # <<<<<<<<<<<<<< @@ -7628,7 +7691,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":586 + /* "gensim/models/doc2vec_inner.pyx":716 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -7638,55 +7701,55 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_8 = (__pyx_v_negative != 0); if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":587 + /* "gensim/models/doc2vec_inner.pyx":717 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 587, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 717, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 587, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 717, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 587, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 717, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":588 + /* "gensim/models/doc2vec_inner.pyx":718 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 588, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 718, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 588, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 718, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 588, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 718, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":589 + /* "gensim/models/doc2vec_inner.pyx":719 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 589, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 719, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 589, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 719, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_7 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 589, __pyx_L1_error) + __pyx_t_7 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 719, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_7; - /* "gensim/models/doc2vec_inner.pyx":586 + /* "gensim/models/doc2vec_inner.pyx":716 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -7695,7 +7758,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":590 + /* "gensim/models/doc2vec_inner.pyx":720 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -7713,41 +7776,41 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_L11_bool_binop_done:; if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":591 + /* "gensim/models/doc2vec_inner.pyx":721 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_10, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_10, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_10 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_11 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_10); if (unlikely((__pyx_t_11 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_t_11 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_10); if (unlikely((__pyx_t_11 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __pyx_v_next_random = __pyx_t_11; - /* "gensim/models/doc2vec_inner.pyx":590 + /* "gensim/models/doc2vec_inner.pyx":720 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -7756,7 +7819,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":594 + /* "gensim/models/doc2vec_inner.pyx":724 * * # convert Python structures to primitive types, so we can release the GIL * if work is None: # <<<<<<<<<<<<<< @@ -7767,32 +7830,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_t_8 != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":595 + /* "gensim/models/doc2vec_inner.pyx":725 * # convert Python structures to primitive types, so we can release the GIL * if work is None: * work = zeros(model.trainables.layer1_size, dtype=REAL) # <<<<<<<<<<<<<< * _work = np.PyArray_DATA(work) * if neu1 is None: */ - __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_12 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_12 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); - if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_12) < 0) __PYX_ERR(0, 595, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_12) < 0) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; - __pyx_t_12 = __Pyx_PyObject_Call(__pyx_t_10, __pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyObject_Call(__pyx_t_10, __pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 725, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; @@ -7800,7 +7863,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __Pyx_DECREF_SET(__pyx_v_work, __pyx_t_12); __pyx_t_12 = 0; - /* "gensim/models/doc2vec_inner.pyx":594 + /* "gensim/models/doc2vec_inner.pyx":724 * * # convert Python structures to primitive types, so we can release the GIL * if work is None: # <<<<<<<<<<<<<< @@ -7809,17 +7872,17 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":596 + /* "gensim/models/doc2vec_inner.pyx":726 * if work is None: * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) # <<<<<<<<<<<<<< * if neu1 is None: * neu1 = zeros(model.trainables.layer1_size, dtype=REAL) */ - if (!(likely(((__pyx_v_work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 596, __pyx_L1_error) + if (!(likely(((__pyx_v_work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 726, __pyx_L1_error) __pyx_v__work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_work))); - /* "gensim/models/doc2vec_inner.pyx":597 + /* "gensim/models/doc2vec_inner.pyx":727 * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) * if neu1 is None: # <<<<<<<<<<<<<< @@ -7830,32 +7893,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_8 = (__pyx_t_9 != 0); if (__pyx_t_8) { - /* "gensim/models/doc2vec_inner.pyx":598 + /* "gensim/models/doc2vec_inner.pyx":728 * _work = np.PyArray_DATA(work) * if neu1 is None: * neu1 = zeros(model.trainables.layer1_size, dtype=REAL) # <<<<<<<<<<<<<< * _neu1 = np.PyArray_DATA(neu1) * */ - __pyx_t_12 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_12 = __Pyx_GetModuleGlobalName(__pyx_n_s_zeros); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_layer1_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_10 = __Pyx_GetModuleGlobalName(__pyx_n_s_REAL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_dtype, __pyx_t_10) < 0) __PYX_ERR(0, 598, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_dtype, __pyx_t_10) < 0) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_12, __pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 598, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_12, __pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 728, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -7863,7 +7926,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __Pyx_DECREF_SET(__pyx_v_neu1, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":597 + /* "gensim/models/doc2vec_inner.pyx":727 * work = zeros(model.trainables.layer1_size, dtype=REAL) * _work = np.PyArray_DATA(work) * if neu1 is None: # <<<<<<<<<<<<<< @@ -7872,32 +7935,32 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":599 + /* "gensim/models/doc2vec_inner.pyx":729 * if neu1 is None: * neu1 = zeros(model.trainables.layer1_size, dtype=REAL) * _neu1 = np.PyArray_DATA(neu1) # <<<<<<<<<<<<<< * * vlookup = model.wv.vocab */ - if (!(likely(((__pyx_v_neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 599, __pyx_L1_error) + if (!(likely(((__pyx_v_neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 729, __pyx_L1_error) __pyx_v__neu1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_neu1))); - /* "gensim/models/doc2vec_inner.pyx":601 + /* "gensim/models/doc2vec_inner.pyx":731 * _neu1 = np.PyArray_DATA(neu1) * * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * i = 0 * for token in doc_words: */ - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 601, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 731, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 601, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 731, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __pyx_v_vlookup = __pyx_t_3; __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":602 + /* "gensim/models/doc2vec_inner.pyx":732 * * vlookup = model.wv.vocab * i = 0 # <<<<<<<<<<<<<< @@ -7906,7 +7969,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_i = 0; - /* "gensim/models/doc2vec_inner.pyx":603 + /* "gensim/models/doc2vec_inner.pyx":733 * vlookup = model.wv.vocab * i = 0 * for token in doc_words: # <<<<<<<<<<<<<< @@ -7917,26 +7980,26 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_3 = __pyx_v_doc_words; __Pyx_INCREF(__pyx_t_3); __pyx_t_7 = 0; __pyx_t_13 = NULL; } else { - __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_doc_words); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 603, __pyx_L1_error) + __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_doc_words); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 733, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_13 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 603, __pyx_L1_error) + __pyx_t_13 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 733, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_13)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_7 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_10 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 603, __pyx_L1_error) + __pyx_t_10 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 733, __pyx_L1_error) #else - __pyx_t_10 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 603, __pyx_L1_error) + __pyx_t_10 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 733, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); #endif } else { if (__pyx_t_7 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_10 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 603, __pyx_L1_error) + __pyx_t_10 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_10); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(0, 733, __pyx_L1_error) #else - __pyx_t_10 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 603, __pyx_L1_error) + __pyx_t_10 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 733, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); #endif } @@ -7946,7 +8009,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 603, __pyx_L1_error) + else __PYX_ERR(0, 733, __pyx_L1_error) } break; } @@ -7955,16 +8018,16 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":604 + /* "gensim/models/doc2vec_inner.pyx":734 * i = 0 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged */ - __pyx_t_8 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_8 < 0)) __PYX_ERR(0, 604, __pyx_L1_error) + __pyx_t_8 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_8 < 0)) __PYX_ERR(0, 734, __pyx_L1_error) if ((__pyx_t_8 != 0)) { - __pyx_t_1 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 604, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 734, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_10 = __pyx_t_1; __pyx_t_1 = 0; @@ -7975,7 +8038,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __Pyx_XDECREF_SET(__pyx_v_predict_word, __pyx_t_10); __pyx_t_10 = 0; - /* "gensim/models/doc2vec_inner.pyx":605 + /* "gensim/models/doc2vec_inner.pyx":735 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word # <<<<<<<<<<<<<< @@ -7986,7 +8049,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_t_8 != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":606 + /* "gensim/models/doc2vec_inner.pyx":736 * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged # <<<<<<<<<<<<<< @@ -7995,7 +8058,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ goto __pyx_L15_continue; - /* "gensim/models/doc2vec_inner.pyx":605 + /* "gensim/models/doc2vec_inner.pyx":735 * for token in doc_words: * predict_word = vlookup[token] if token in vlookup else None * if predict_word is None: # shrink document to leave out word # <<<<<<<<<<<<<< @@ -8004,7 +8067,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":607 + /* "gensim/models/doc2vec_inner.pyx":737 * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -8017,20 +8080,20 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = __pyx_t_8; goto __pyx_L19_bool_binop_done; } - __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 607, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 737, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_1 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 607, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 737, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_12 = PyObject_RichCompare(__pyx_t_10, __pyx_t_1, Py_LT); __Pyx_XGOTREF(__pyx_t_12); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 607, __pyx_L1_error) + __pyx_t_12 = PyObject_RichCompare(__pyx_t_10, __pyx_t_1, Py_LT); __Pyx_XGOTREF(__pyx_t_12); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 737, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_8 = __Pyx_PyObject_IsTrue(__pyx_t_12); if (unlikely(__pyx_t_8 < 0)) __PYX_ERR(0, 607, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_IsTrue(__pyx_t_12); if (unlikely(__pyx_t_8 < 0)) __PYX_ERR(0, 737, __pyx_L1_error) __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; __pyx_t_9 = __pyx_t_8; __pyx_L19_bool_binop_done:; if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":608 + /* "gensim/models/doc2vec_inner.pyx":738 * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -8039,7 +8102,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ goto __pyx_L15_continue; - /* "gensim/models/doc2vec_inner.pyx":607 + /* "gensim/models/doc2vec_inner.pyx":737 * if predict_word is None: # shrink document to leave out word * continue # leaving i unchanged * if sample and predict_word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -8048,20 +8111,20 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":609 + /* "gensim/models/doc2vec_inner.pyx":739 * if sample and predict_word.sample_int < random_int32(&next_random): * continue * indexes[i] = predict_word.index # <<<<<<<<<<<<<< * if hs: * codelens[i] = len(predict_word.code) */ - __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_index); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 609, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_index); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 739, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); - __pyx_t_14 = __Pyx_PyInt_As_npy_uint32(__pyx_t_12); if (unlikely((__pyx_t_14 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 609, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyInt_As_npy_uint32(__pyx_t_12); if (unlikely((__pyx_t_14 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 739, __pyx_L1_error) __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; (__pyx_v_indexes[__pyx_v_i]) = __pyx_t_14; - /* "gensim/models/doc2vec_inner.pyx":610 + /* "gensim/models/doc2vec_inner.pyx":740 * continue * indexes[i] = predict_word.index * if hs: # <<<<<<<<<<<<<< @@ -8071,46 +8134,46 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_v_hs != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":611 + /* "gensim/models/doc2vec_inner.pyx":741 * indexes[i] = predict_word.index * if hs: * codelens[i] = len(predict_word.code) # <<<<<<<<<<<<<< * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) */ - __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 611, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 741, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); - __pyx_t_5 = PyObject_Length(__pyx_t_12); if (unlikely(__pyx_t_5 == ((Py_ssize_t)-1))) __PYX_ERR(0, 611, __pyx_L1_error) + __pyx_t_5 = PyObject_Length(__pyx_t_12); if (unlikely(__pyx_t_5 == ((Py_ssize_t)-1))) __PYX_ERR(0, 741, __pyx_L1_error) __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; (__pyx_v_codelens[__pyx_v_i]) = ((int)__pyx_t_5); - /* "gensim/models/doc2vec_inner.pyx":612 + /* "gensim/models/doc2vec_inner.pyx":742 * if hs: * codelens[i] = len(predict_word.code) * codes[i] = np.PyArray_DATA(predict_word.code) # <<<<<<<<<<<<<< * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 */ - __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 612, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_code); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 742, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); - if (!(likely(((__pyx_t_12) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_12, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 612, __pyx_L1_error) + if (!(likely(((__pyx_t_12) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_12, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 742, __pyx_L1_error) (__pyx_v_codes[__pyx_v_i]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_12))); __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; - /* "gensim/models/doc2vec_inner.pyx":613 + /* "gensim/models/doc2vec_inner.pyx":743 * codelens[i] = len(predict_word.code) * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) # <<<<<<<<<<<<<< * result += 1 * i += 1 */ - __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_point); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 613, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyObject_GetAttrStr(__pyx_v_predict_word, __pyx_n_s_point); if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 743, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_12); - if (!(likely(((__pyx_t_12) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_12, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 613, __pyx_L1_error) + if (!(likely(((__pyx_t_12) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_12, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 743, __pyx_L1_error) (__pyx_v_points[__pyx_v_i]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_12))); __Pyx_DECREF(__pyx_t_12); __pyx_t_12 = 0; - /* "gensim/models/doc2vec_inner.pyx":610 + /* "gensim/models/doc2vec_inner.pyx":740 * continue * indexes[i] = predict_word.index * if hs: # <<<<<<<<<<<<<< @@ -8119,7 +8182,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":614 + /* "gensim/models/doc2vec_inner.pyx":744 * codes[i] = np.PyArray_DATA(predict_word.code) * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 # <<<<<<<<<<<<<< @@ -8128,7 +8191,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_result = (__pyx_v_result + 1); - /* "gensim/models/doc2vec_inner.pyx":615 + /* "gensim/models/doc2vec_inner.pyx":745 * points[i] = np.PyArray_DATA(predict_word.point) * result += 1 * i += 1 # <<<<<<<<<<<<<< @@ -8137,7 +8200,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_i = (__pyx_v_i + 1); - /* "gensim/models/doc2vec_inner.pyx":616 + /* "gensim/models/doc2vec_inner.pyx":746 * result += 1 * i += 1 * if i == MAX_DOCUMENT_LEN: # <<<<<<<<<<<<<< @@ -8147,7 +8210,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = ((__pyx_v_i == 0x2710) != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":617 + /* "gensim/models/doc2vec_inner.pyx":747 * i += 1 * if i == MAX_DOCUMENT_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -8156,7 +8219,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ goto __pyx_L16_break; - /* "gensim/models/doc2vec_inner.pyx":616 + /* "gensim/models/doc2vec_inner.pyx":746 * result += 1 * i += 1 * if i == MAX_DOCUMENT_LEN: # <<<<<<<<<<<<<< @@ -8165,7 +8228,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":603 + /* "gensim/models/doc2vec_inner.pyx":733 * vlookup = model.wv.vocab * i = 0 * for token in doc_words: # <<<<<<<<<<<<<< @@ -8177,7 +8240,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_L16_break:; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/doc2vec_inner.pyx":618 + /* "gensim/models/doc2vec_inner.pyx":748 * if i == MAX_DOCUMENT_LEN: * break # TODO: log warning, tally overflow? * document_len = i # <<<<<<<<<<<<<< @@ -8186,7 +8249,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_document_len = __pyx_v_i; - /* "gensim/models/doc2vec_inner.pyx":620 + /* "gensim/models/doc2vec_inner.pyx":750 * document_len = i * * for i in range(doctag_len): # <<<<<<<<<<<<<< @@ -8194,23 +8257,24 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con * result += 1 */ __pyx_t_2 = __pyx_v_doctag_len; - for (__pyx_t_15 = 0; __pyx_t_15 < __pyx_t_2; __pyx_t_15+=1) { - __pyx_v_i = __pyx_t_15; + __pyx_t_15 = __pyx_t_2; + for (__pyx_t_16 = 0; __pyx_t_16 < __pyx_t_15; __pyx_t_16+=1) { + __pyx_v_i = __pyx_t_16; - /* "gensim/models/doc2vec_inner.pyx":621 + /* "gensim/models/doc2vec_inner.pyx":751 * * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] # <<<<<<<<<<<<<< * result += 1 * */ - __pyx_t_3 = __Pyx_GetItemInt(__pyx_v_doctag_indexes, __pyx_v_i, int, 1, __Pyx_PyInt_From_int, 0, 0, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 621, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetItemInt(__pyx_v_doctag_indexes, __pyx_v_i, int, 1, __Pyx_PyInt_From_int, 0, 0, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 751, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_14 = __Pyx_PyInt_As_npy_uint32(__pyx_t_3); if (unlikely((__pyx_t_14 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 621, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyInt_As_npy_uint32(__pyx_t_3); if (unlikely((__pyx_t_14 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 751, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; (__pyx_v__doctag_indexes[__pyx_v_i]) = __pyx_t_14; - /* "gensim/models/doc2vec_inner.pyx":622 + /* "gensim/models/doc2vec_inner.pyx":752 * for i in range(doctag_len): * _doctag_indexes[i] = doctag_indexes[i] * result += 1 # <<<<<<<<<<<<<< @@ -8220,7 +8284,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_v_result = (__pyx_v_result + 1); } - /* "gensim/models/doc2vec_inner.pyx":625 + /* "gensim/models/doc2vec_inner.pyx":755 * * # release GIL & train on the document * with nogil: # <<<<<<<<<<<<<< @@ -8235,7 +8299,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con #endif /*try:*/ { - /* "gensim/models/doc2vec_inner.pyx":626 + /* "gensim/models/doc2vec_inner.pyx":756 * # release GIL & train on the document * with nogil: * for i in range(document_len): # <<<<<<<<<<<<<< @@ -8243,10 +8307,11 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con * k = i + window + 1 # past document end OK: will pad with null word */ __pyx_t_2 = __pyx_v_document_len; - for (__pyx_t_15 = 0; __pyx_t_15 < __pyx_t_2; __pyx_t_15+=1) { - __pyx_v_i = __pyx_t_15; + __pyx_t_15 = __pyx_t_2; + for (__pyx_t_16 = 0; __pyx_t_16 < __pyx_t_15; __pyx_t_16+=1) { + __pyx_v_i = __pyx_t_16; - /* "gensim/models/doc2vec_inner.pyx":627 + /* "gensim/models/doc2vec_inner.pyx":757 * with nogil: * for i in range(document_len): * j = i - window # negative OK: will pad with null word # <<<<<<<<<<<<<< @@ -8255,7 +8320,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_j = (__pyx_v_i - __pyx_v_window); - /* "gensim/models/doc2vec_inner.pyx":628 + /* "gensim/models/doc2vec_inner.pyx":758 * for i in range(document_len): * j = i - window # negative OK: will pad with null word * k = i + window + 1 # past document end OK: will pad with null word # <<<<<<<<<<<<<< @@ -8264,28 +8329,29 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_k = ((__pyx_v_i + __pyx_v_window) + 1); - /* "gensim/models/doc2vec_inner.pyx":631 + /* "gensim/models/doc2vec_inner.pyx":761 * * # compose l1 & clear work * for m in range(doctag_len): # <<<<<<<<<<<<<< * # doc vector(s) * memcpy(&_neu1[m * vector_size], &_doctag_vectors[_doctag_indexes[m] * vector_size], */ - __pyx_t_16 = __pyx_v_doctag_len; - for (__pyx_t_17 = 0; __pyx_t_17 < __pyx_t_16; __pyx_t_17+=1) { - __pyx_v_m = __pyx_t_17; + __pyx_t_17 = __pyx_v_doctag_len; + __pyx_t_18 = __pyx_t_17; + for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { + __pyx_v_m = __pyx_t_19; - /* "gensim/models/doc2vec_inner.pyx":633 + /* "gensim/models/doc2vec_inner.pyx":763 * for m in range(doctag_len): * # doc vector(s) * memcpy(&_neu1[m * vector_size], &_doctag_vectors[_doctag_indexes[m] * vector_size], # <<<<<<<<<<<<<< * vector_size * cython.sizeof(REAL_t)) * n = 0 */ - memcpy((&(__pyx_v__neu1[(__pyx_v_m * __pyx_v_vector_size)])), (&(__pyx_v__doctag_vectors[((__pyx_v__doctag_indexes[__pyx_v_m]) * __pyx_v_vector_size)])), (__pyx_v_vector_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memcpy((&(__pyx_v__neu1[(__pyx_v_m * __pyx_v_vector_size)])), (&(__pyx_v__doctag_vectors[((__pyx_v__doctag_indexes[__pyx_v_m]) * __pyx_v_vector_size)])), (__pyx_v_vector_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); } - /* "gensim/models/doc2vec_inner.pyx":635 + /* "gensim/models/doc2vec_inner.pyx":765 * memcpy(&_neu1[m * vector_size], &_doctag_vectors[_doctag_indexes[m] * vector_size], * vector_size * cython.sizeof(REAL_t)) * n = 0 # <<<<<<<<<<<<<< @@ -8294,18 +8360,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_n = 0; - /* "gensim/models/doc2vec_inner.pyx":636 + /* "gensim/models/doc2vec_inner.pyx":766 * vector_size * cython.sizeof(REAL_t)) * n = 0 * for m in range(j, k): # <<<<<<<<<<<<<< * # word vectors in window * if m == i: */ - __pyx_t_16 = __pyx_v_k; - for (__pyx_t_17 = __pyx_v_j; __pyx_t_17 < __pyx_t_16; __pyx_t_17+=1) { - __pyx_v_m = __pyx_t_17; + __pyx_t_17 = __pyx_v_k; + __pyx_t_18 = __pyx_t_17; + for (__pyx_t_19 = __pyx_v_j; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { + __pyx_v_m = __pyx_t_19; - /* "gensim/models/doc2vec_inner.pyx":638 + /* "gensim/models/doc2vec_inner.pyx":768 * for m in range(j, k): * # word vectors in window * if m == i: # <<<<<<<<<<<<<< @@ -8315,7 +8382,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = ((__pyx_v_m == __pyx_v_i) != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":639 + /* "gensim/models/doc2vec_inner.pyx":769 * # word vectors in window * if m == i: * continue # <<<<<<<<<<<<<< @@ -8324,7 +8391,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ goto __pyx_L32_continue; - /* "gensim/models/doc2vec_inner.pyx":638 + /* "gensim/models/doc2vec_inner.pyx":768 * for m in range(j, k): * # word vectors in window * if m == i: # <<<<<<<<<<<<<< @@ -8333,7 +8400,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":640 + /* "gensim/models/doc2vec_inner.pyx":770 * if m == i: * continue * if m < 0 or m >= document_len: # <<<<<<<<<<<<<< @@ -8351,7 +8418,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_L36_bool_binop_done:; if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":641 + /* "gensim/models/doc2vec_inner.pyx":771 * continue * if m < 0 or m >= document_len: * window_indexes[n] = null_word_index # <<<<<<<<<<<<<< @@ -8360,7 +8427,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ (__pyx_v_window_indexes[__pyx_v_n]) = __pyx_v_null_word_index; - /* "gensim/models/doc2vec_inner.pyx":640 + /* "gensim/models/doc2vec_inner.pyx":770 * if m == i: * continue * if m < 0 or m >= document_len: # <<<<<<<<<<<<<< @@ -8370,7 +8437,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con goto __pyx_L35; } - /* "gensim/models/doc2vec_inner.pyx":643 + /* "gensim/models/doc2vec_inner.pyx":773 * window_indexes[n] = null_word_index * else: * window_indexes[n] = indexes[m] # <<<<<<<<<<<<<< @@ -8382,7 +8449,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con } __pyx_L35:; - /* "gensim/models/doc2vec_inner.pyx":644 + /* "gensim/models/doc2vec_inner.pyx":774 * else: * window_indexes[n] = indexes[m] * n += 1 # <<<<<<<<<<<<<< @@ -8393,7 +8460,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_L32_continue:; } - /* "gensim/models/doc2vec_inner.pyx":645 + /* "gensim/models/doc2vec_inner.pyx":775 * window_indexes[n] = indexes[m] * n += 1 * for m in range(2 * window): # <<<<<<<<<<<<<< @@ -8401,29 +8468,30 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con * vector_size * cython.sizeof(REAL_t)) */ __pyx_t_6 = (2 * __pyx_v_window); - for (__pyx_t_16 = 0; __pyx_t_16 < __pyx_t_6; __pyx_t_16+=1) { - __pyx_v_m = __pyx_t_16; + __pyx_t_20 = __pyx_t_6; + for (__pyx_t_17 = 0; __pyx_t_17 < __pyx_t_20; __pyx_t_17+=1) { + __pyx_v_m = __pyx_t_17; - /* "gensim/models/doc2vec_inner.pyx":646 + /* "gensim/models/doc2vec_inner.pyx":776 * n += 1 * for m in range(2 * window): * memcpy(&_neu1[(doctag_len + m) * vector_size], &_word_vectors[window_indexes[m] * vector_size], # <<<<<<<<<<<<<< * vector_size * cython.sizeof(REAL_t)) * memset(_work, 0, layer1_size * cython.sizeof(REAL_t)) # work to accumulate l1 error */ - memcpy((&(__pyx_v__neu1[((__pyx_v_doctag_len + __pyx_v_m) * __pyx_v_vector_size)])), (&(__pyx_v__word_vectors[((__pyx_v_window_indexes[__pyx_v_m]) * __pyx_v_vector_size)])), (__pyx_v_vector_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memcpy((&(__pyx_v__neu1[((__pyx_v_doctag_len + __pyx_v_m) * __pyx_v_vector_size)])), (&(__pyx_v__word_vectors[((__pyx_v_window_indexes[__pyx_v_m]) * __pyx_v_vector_size)])), (__pyx_v_vector_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); } - /* "gensim/models/doc2vec_inner.pyx":648 + /* "gensim/models/doc2vec_inner.pyx":778 * memcpy(&_neu1[(doctag_len + m) * vector_size], &_word_vectors[window_indexes[m] * vector_size], * vector_size * cython.sizeof(REAL_t)) * memset(_work, 0, layer1_size * cython.sizeof(REAL_t)) # work to accumulate l1 error # <<<<<<<<<<<<<< * * if hs: */ - memset(__pyx_v__work, 0, (__pyx_v_layer1_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v__work, 0, (__pyx_v_layer1_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/doc2vec_inner.pyx":650 + /* "gensim/models/doc2vec_inner.pyx":780 * memset(_work, 0, layer1_size * cython.sizeof(REAL_t)) # work to accumulate l1 error * * if hs: # <<<<<<<<<<<<<< @@ -8433,7 +8501,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_v_hs != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":651 + /* "gensim/models/doc2vec_inner.pyx":781 * * if hs: * fast_document_dmc_hs(points[i], codes[i], codelens[i], # <<<<<<<<<<<<<< @@ -8442,7 +8510,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), (__pyx_v_codelens[__pyx_v_i]), __pyx_v__neu1, __pyx_v_syn1, __pyx_v__alpha, __pyx_v__work, __pyx_v_layer1_size, __pyx_v_vector_size, __pyx_v__learn_hidden); - /* "gensim/models/doc2vec_inner.pyx":650 + /* "gensim/models/doc2vec_inner.pyx":780 * memset(_work, 0, layer1_size * cython.sizeof(REAL_t)) # work to accumulate l1 error * * if hs: # <<<<<<<<<<<<<< @@ -8451,7 +8519,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":654 + /* "gensim/models/doc2vec_inner.pyx":784 * _neu1, syn1, _alpha, _work, * layer1_size, vector_size, _learn_hidden) * if negative: # <<<<<<<<<<<<<< @@ -8461,7 +8529,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_v_negative != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":655 + /* "gensim/models/doc2vec_inner.pyx":785 * layer1_size, vector_size, _learn_hidden) * if negative: * next_random = fast_document_dmc_neg(negative, cum_table, cum_table_len, next_random, # <<<<<<<<<<<<<< @@ -8470,7 +8538,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ __pyx_v_next_random = __pyx_f_6gensim_6models_13doc2vec_inner_fast_document_dmc_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v_next_random, __pyx_v__neu1, __pyx_v_syn1neg, (__pyx_v_indexes[__pyx_v_i]), __pyx_v__alpha, __pyx_v__work, __pyx_v_layer1_size, __pyx_v_vector_size, __pyx_v__learn_hidden); - /* "gensim/models/doc2vec_inner.pyx":654 + /* "gensim/models/doc2vec_inner.pyx":784 * _neu1, syn1, _alpha, _work, * layer1_size, vector_size, _learn_hidden) * if negative: # <<<<<<<<<<<<<< @@ -8479,7 +8547,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":659 + /* "gensim/models/doc2vec_inner.pyx":789 * layer1_size, vector_size, _learn_hidden) * * if _learn_doctags: # <<<<<<<<<<<<<< @@ -8489,18 +8557,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_v__learn_doctags != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":660 + /* "gensim/models/doc2vec_inner.pyx":790 * * if _learn_doctags: * for m in range(doctag_len): # <<<<<<<<<<<<<< * our_saxpy(&vector_size, &_doctag_locks[_doctag_indexes[m]], &_work[m * vector_size], * &ONE, &_doctag_vectors[_doctag_indexes[m] * vector_size], &ONE) */ - __pyx_t_16 = __pyx_v_doctag_len; - for (__pyx_t_17 = 0; __pyx_t_17 < __pyx_t_16; __pyx_t_17+=1) { - __pyx_v_m = __pyx_t_17; + __pyx_t_17 = __pyx_v_doctag_len; + __pyx_t_18 = __pyx_t_17; + for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_18; __pyx_t_19+=1) { + __pyx_v_m = __pyx_t_19; - /* "gensim/models/doc2vec_inner.pyx":661 + /* "gensim/models/doc2vec_inner.pyx":791 * if _learn_doctags: * for m in range(doctag_len): * our_saxpy(&vector_size, &_doctag_locks[_doctag_indexes[m]], &_work[m * vector_size], # <<<<<<<<<<<<<< @@ -8510,7 +8579,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_vector_size), (&(__pyx_v__doctag_locks[(__pyx_v__doctag_indexes[__pyx_v_m])])), (&(__pyx_v__work[(__pyx_v_m * __pyx_v_vector_size)])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v__doctag_vectors[((__pyx_v__doctag_indexes[__pyx_v_m]) * __pyx_v_vector_size)])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); } - /* "gensim/models/doc2vec_inner.pyx":659 + /* "gensim/models/doc2vec_inner.pyx":789 * layer1_size, vector_size, _learn_hidden) * * if _learn_doctags: # <<<<<<<<<<<<<< @@ -8519,7 +8588,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con */ } - /* "gensim/models/doc2vec_inner.pyx":663 + /* "gensim/models/doc2vec_inner.pyx":793 * our_saxpy(&vector_size, &_doctag_locks[_doctag_indexes[m]], &_work[m * vector_size], * &ONE, &_doctag_vectors[_doctag_indexes[m] * vector_size], &ONE) * if _learn_words: # <<<<<<<<<<<<<< @@ -8529,7 +8598,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_t_9 = (__pyx_v__learn_words != 0); if (__pyx_t_9) { - /* "gensim/models/doc2vec_inner.pyx":664 + /* "gensim/models/doc2vec_inner.pyx":794 * &ONE, &_doctag_vectors[_doctag_indexes[m] * vector_size], &ONE) * if _learn_words: * for m in range(2 * window): # <<<<<<<<<<<<<< @@ -8537,10 +8606,11 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con * &ONE, &_word_vectors[window_indexes[m] * vector_size], &ONE) */ __pyx_t_6 = (2 * __pyx_v_window); - for (__pyx_t_16 = 0; __pyx_t_16 < __pyx_t_6; __pyx_t_16+=1) { - __pyx_v_m = __pyx_t_16; + __pyx_t_20 = __pyx_t_6; + for (__pyx_t_17 = 0; __pyx_t_17 < __pyx_t_20; __pyx_t_17+=1) { + __pyx_v_m = __pyx_t_17; - /* "gensim/models/doc2vec_inner.pyx":665 + /* "gensim/models/doc2vec_inner.pyx":795 * if _learn_words: * for m in range(2 * window): * our_saxpy(&vector_size, &_word_locks[window_indexes[m]], &_work[(doctag_len + m) * vector_size], # <<<<<<<<<<<<<< @@ -8550,7 +8620,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_vector_size), (&(__pyx_v__word_locks[(__pyx_v_window_indexes[__pyx_v_m])])), (&(__pyx_v__work[((__pyx_v_doctag_len + __pyx_v_m) * __pyx_v_vector_size)])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE), (&(__pyx_v__word_vectors[((__pyx_v_window_indexes[__pyx_v_m]) * __pyx_v_vector_size)])), (&__pyx_v_6gensim_6models_13doc2vec_inner_ONE)); } - /* "gensim/models/doc2vec_inner.pyx":663 + /* "gensim/models/doc2vec_inner.pyx":793 * our_saxpy(&vector_size, &_doctag_locks[_doctag_indexes[m]], &_work[m * vector_size], * &ONE, &_doctag_vectors[_doctag_indexes[m] * vector_size], &ONE) * if _learn_words: # <<<<<<<<<<<<<< @@ -8561,7 +8631,7 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con } } - /* "gensim/models/doc2vec_inner.pyx":625 + /* "gensim/models/doc2vec_inner.pyx":755 * * # release GIL & train on the document * with nogil: # <<<<<<<<<<<<<< @@ -8580,19 +8650,19 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con } } - /* "gensim/models/doc2vec_inner.pyx":668 + /* "gensim/models/doc2vec_inner.pyx":798 * &ONE, &_word_vectors[window_indexes[m] * vector_size], &ONE) * * return result # <<<<<<<<<<<<<< */ __Pyx_XDECREF(__pyx_r); - __pyx_t_3 = __Pyx_PyInt_From_long(__pyx_v_result); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 668, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_long(__pyx_v_result); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 798, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; - /* "gensim/models/doc2vec_inner.pyx":521 + /* "gensim/models/doc2vec_inner.pyx":606 * * * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< @@ -8623,12 +8693,12 @@ static PyObject *__pyx_pf_6gensim_6models_13doc2vec_inner_4train_document_dm_con return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* Python wrapper */ @@ -8645,7 +8715,6 @@ static CYTHON_UNUSED int __pyx_pw_5numpy_7ndarray_1__getbuffer__(PyObject *__pyx } static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags) { - int __pyx_v_copy_shape; int __pyx_v_i; int __pyx_v_ndim; int __pyx_v_endian_detector; @@ -8654,7 +8723,6 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P char *__pyx_v_f; PyArray_Descr *__pyx_v_descr = 0; int __pyx_v_offset; - int __pyx_v_hasfields; int __pyx_r; __Pyx_RefNannyDeclarations int __pyx_t_1; @@ -8662,97 +8730,46 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P PyObject *__pyx_t_3 = NULL; int __pyx_t_4; int __pyx_t_5; - PyObject *__pyx_t_6 = NULL; - char *__pyx_t_7; - __Pyx_RefNannySetupContext("__getbuffer__", 0); - if (__pyx_v_info != NULL) { - __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(__pyx_v_info->obj); - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":220 - * # of flags - * - * if info == NULL: return # <<<<<<<<<<<<<< - * - * cdef int copy_shape, i, ndim - */ - __pyx_t_1 = ((__pyx_v_info == NULL) != 0); - if (__pyx_t_1) { - __pyx_r = 0; - goto __pyx_L0; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 - * - * cdef int copy_shape, i, ndim - * cdef int endian_detector = 1 # <<<<<<<<<<<<<< - * cdef bint little_endian = ((&endian_detector)[0] != 0) - * - */ - __pyx_v_endian_detector = 1; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":224 - * cdef int copy_shape, i, ndim - * cdef int endian_detector = 1 - * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< - * - * ndim = PyArray_NDIM(self) - */ - __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":226 - * cdef bint little_endian = ((&endian_detector)[0] != 0) - * - * ndim = PyArray_NDIM(self) # <<<<<<<<<<<<<< - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): - */ - __pyx_v_ndim = PyArray_NDIM(__pyx_v_self); - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 - * ndim = PyArray_NDIM(self) - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); - if (__pyx_t_1) { + int __pyx_t_6; + PyObject *__pyx_t_7 = NULL; + char *__pyx_t_8; + if (__pyx_v_info == NULL) { + PyErr_SetString(PyExc_BufferError, "PyObject_GetBuffer: view==NULL argument is obsolete"); + return -1; + } + __Pyx_RefNannySetupContext("__getbuffer__", 0); + __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); + __Pyx_GIVEREF(__pyx_v_info->obj); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":222 + * + * cdef int i, ndim + * cdef int endian_detector = 1 # <<<<<<<<<<<<<< + * cdef bint little_endian = ((&endian_detector)[0] != 0) * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): - * copy_shape = 1 # <<<<<<<<<<<<<< - * else: - * copy_shape = 0 */ - __pyx_v_copy_shape = 1; + __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 - * ndim = PyArray_NDIM(self) + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + * cdef int i, ndim + * cdef int endian_detector = 1 + * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: + * ndim = PyArray_NDIM(self) */ - goto __pyx_L4; - } + __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 - * copy_shape = 1 - * else: - * copy_shape = 0 # <<<<<<<<<<<<<< + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":225 + * cdef bint little_endian = ((&endian_detector)[0] != 0) + * + * ndim = PyArray_NDIM(self) # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) */ - /*else*/ { - __pyx_v_copy_shape = 0; - } - __pyx_L4:; + __pyx_v_ndim = PyArray_NDIM(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): @@ -8762,10 +8779,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L6_bool_binop_done; + goto __pyx_L4_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":234 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -8774,32 +8791,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_C_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L6_bool_binop_done:; + __pyx_L4_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 235, __pyx_L1_error) + __PYX_ERR(1, 229, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): @@ -8807,7 +8824,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -8818,10 +8835,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L9_bool_binop_done; + goto __pyx_L7_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":238 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":232 * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -8830,31 +8847,31 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_F_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L9_bool_binop_done:; + __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 239, __pyx_L1_error) + __PYX_ERR(1, 233, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -8863,35 +8880,35 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 * raise ValueError(u"ndarray is not Fortran contiguous") * * info.buf = PyArray_DATA(self) # <<<<<<<<<<<<<< * info.ndim = ndim - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): */ __pyx_v_info->buf = PyArray_DATA(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":236 * * info.buf = PyArray_DATA(self) * info.ndim = ndim # <<<<<<<<<<<<<< - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): * # Allocate new buffer for strides and shape info. */ __pyx_v_info->ndim = __pyx_v_ndim; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - __pyx_t_1 = (__pyx_v_copy_shape != 0); + __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":240 * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) # <<<<<<<<<<<<<< @@ -8900,7 +8917,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->strides = ((Py_ssize_t *)PyObject_Malloc((((sizeof(Py_ssize_t)) * 2) * ((size_t)__pyx_v_ndim)))); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim # <<<<<<<<<<<<<< @@ -8909,7 +8926,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = (__pyx_v_info->strides + __pyx_v_ndim); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim * for i in range(ndim): # <<<<<<<<<<<<<< @@ -8917,10 +8934,11 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P * info.shape[i] = PyArray_DIMS(self)[i] */ __pyx_t_4 = __pyx_v_ndim; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 * info.shape = info.strides + ndim * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] # <<<<<<<<<<<<<< @@ -8929,7 +8947,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->strides[__pyx_v_i]) = (PyArray_STRIDES(__pyx_v_self)[__pyx_v_i]); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":244 * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] * info.shape[i] = PyArray_DIMS(self)[i] # <<<<<<<<<<<<<< @@ -8939,17 +8957,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_info->shape[__pyx_v_i]) = (PyArray_DIMS(__pyx_v_self)[__pyx_v_i]); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - goto __pyx_L11; + goto __pyx_L9; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":252 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 * info.shape[i] = PyArray_DIMS(self)[i] * else: * info.strides = PyArray_STRIDES(self) # <<<<<<<<<<<<<< @@ -8959,7 +8977,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->strides = ((Py_ssize_t *)PyArray_STRIDES(__pyx_v_self)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 * else: * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) # <<<<<<<<<<<<<< @@ -8968,9 +8986,9 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = ((Py_ssize_t *)PyArray_DIMS(__pyx_v_self)); } - __pyx_L11:; + __pyx_L9:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL # <<<<<<<<<<<<<< @@ -8979,7 +8997,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->suboffsets = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":255 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) # <<<<<<<<<<<<<< @@ -8988,7 +9006,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->itemsize = PyArray_ITEMSIZE(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":256 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) * info.readonly = not PyArray_ISWRITEABLE(self) # <<<<<<<<<<<<<< @@ -8997,7 +9015,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->readonly = (!(PyArray_ISWRITEABLE(__pyx_v_self) != 0)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 * * cdef int t * cdef char* f = NULL # <<<<<<<<<<<<<< @@ -9006,7 +9024,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_f = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 * cdef int t * cdef char* f = NULL * cdef dtype descr = self.descr # <<<<<<<<<<<<<< @@ -9018,85 +9036,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_descr = ((PyArray_Descr *)__pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":257 * cdef int offset * - * cdef bint hasfields = PyDataType_HASFIELDS(descr) # <<<<<<<<<<<<<< - * - * if not hasfields and not copy_shape: - */ - __pyx_v_hasfields = PyDataType_HASFIELDS(__pyx_v_descr); - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) - * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - __pyx_t_2 = ((!(__pyx_v_hasfields != 0)) != 0); - if (__pyx_t_2) { - } else { - __pyx_t_1 = __pyx_t_2; - goto __pyx_L15_bool_binop_done; - } - __pyx_t_2 = ((!(__pyx_v_copy_shape != 0)) != 0); - __pyx_t_1 = __pyx_t_2; - __pyx_L15_bool_binop_done:; - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 - * if not hasfields and not copy_shape: - * # do not call releasebuffer - * info.obj = None # <<<<<<<<<<<<<< - * else: - * # need to call releasebuffer - */ - __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(Py_None); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = Py_None; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) - * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - goto __pyx_L14; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 - * else: - * # need to call releasebuffer - * info.obj = self # <<<<<<<<<<<<<< + * info.obj = self # <<<<<<<<<<<<<< * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): */ - /*else*/ { - __Pyx_INCREF(((PyObject *)__pyx_v_self)); - __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - } - __pyx_L14:; + __Pyx_INCREF(((PyObject *)__pyx_v_self)); + __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); + __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ - __pyx_t_1 = ((!(__pyx_v_hasfields != 0)) != 0); + __pyx_t_1 = ((!(PyDataType_HASFIELDS(__pyx_v_descr) != 0)) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num # <<<<<<<<<<<<<< * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): @@ -9104,8 +9069,8 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_t_4 = __pyx_v_descr->type_num; __pyx_v_t = __pyx_t_4; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -9113,18 +9078,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((__pyx_v_descr->byteorder == '>') != 0); if (!__pyx_t_2) { - goto __pyx_L20_next_or; + goto __pyx_L15_next_or; } else { } __pyx_t_2 = (__pyx_v_little_endian != 0); if (!__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } - __pyx_L20_next_or:; + __pyx_L15_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":262 * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -9135,36 +9100,36 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } __pyx_t_2 = ((!(__pyx_v_little_endian != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L19_bool_binop_done:; + __pyx_L14_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 276, __pyx_L1_error) + __PYX_ERR(1, 263, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -9172,7 +9137,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":264 * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" # <<<<<<<<<<<<<< @@ -9184,7 +9149,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"b"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" # <<<<<<<<<<<<<< @@ -9195,7 +9160,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"B"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":266 * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" # <<<<<<<<<<<<<< @@ -9206,7 +9171,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"h"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" # <<<<<<<<<<<<<< @@ -9217,7 +9182,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"H"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":281 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":268 * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" # <<<<<<<<<<<<<< @@ -9228,7 +9193,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"i"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":269 * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" # <<<<<<<<<<<<<< @@ -9239,7 +9204,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"I"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" # <<<<<<<<<<<<<< @@ -9250,7 +9215,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"l"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":271 * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" # <<<<<<<<<<<<<< @@ -9261,7 +9226,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"L"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":285 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" # <<<<<<<<<<<<<< @@ -9272,7 +9237,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" # <<<<<<<<<<<<<< @@ -9283,7 +9248,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" # <<<<<<<<<<<<<< @@ -9294,7 +9259,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"f"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" # <<<<<<<<<<<<<< @@ -9305,7 +9270,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"d"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" # <<<<<<<<<<<<<< @@ -9316,7 +9281,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"g"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":290 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" # <<<<<<<<<<<<<< @@ -9327,7 +9292,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zf"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":291 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" # <<<<<<<<<<<<<< @@ -9338,7 +9303,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zd"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" # <<<<<<<<<<<<<< @@ -9349,7 +9314,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zg"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":293 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" * elif t == NPY_OBJECT: f = "O" # <<<<<<<<<<<<<< @@ -9361,33 +9326,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P break; default: - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 * elif t == NPY_OBJECT: f = "O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< * info.format = f * return */ - __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_6 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __pyx_t_7 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_7)) __PYX_ERR(1, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_7); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_GIVEREF(__pyx_t_6); - PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_6); - __pyx_t_6 = 0; - __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_3, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; + __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_Raise(__pyx_t_6, 0, 0, 0); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __PYX_ERR(1, 295, __pyx_L1_error) + __PYX_ERR(1, 282, __pyx_L1_error) break; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f # <<<<<<<<<<<<<< @@ -9396,7 +9356,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->format = __pyx_v_f; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f * return # <<<<<<<<<<<<<< @@ -9406,16 +9366,16 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_r = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":299 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 * return * else: * info.format = PyObject_Malloc(_buffer_format_string_len) # <<<<<<<<<<<<<< @@ -9425,7 +9385,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->format = ((char *)PyObject_Malloc(0xFF)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":300 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 * else: * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment # <<<<<<<<<<<<<< @@ -9434,7 +9394,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->format[0]) = '^'; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":301 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 # <<<<<<<<<<<<<< @@ -9443,17 +9403,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_offset = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":302 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 * f = _util_dtypestring(descr, info.format + 1, # <<<<<<<<<<<<<< * info.format + _buffer_format_string_len, * &offset) */ - __pyx_t_7 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_7 == ((char *)NULL))) __PYX_ERR(1, 302, __pyx_L1_error) - __pyx_v_f = __pyx_t_7; + __pyx_t_8 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_8 == ((char *)NULL))) __PYX_ERR(1, 289, __pyx_L1_error) + __pyx_v_f = __pyx_t_8; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":305 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 * info.format + _buffer_format_string_len, * &offset) * f[0] = c'\0' # Terminate format string # <<<<<<<<<<<<<< @@ -9463,12 +9423,12 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_f[0]) = '\x00'; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* function exit code */ @@ -9476,18 +9436,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_3); - __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); __Pyx_AddTraceback("numpy.ndarray.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; - if (__pyx_v_info != NULL && __pyx_v_info->obj != NULL) { + if (__pyx_v_info->obj != NULL) { __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = NULL; + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } goto __pyx_L2; __pyx_L0:; - if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) { - __Pyx_GOTREF(Py_None); - __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL; + if (__pyx_v_info->obj == Py_None) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } __pyx_L2:; __Pyx_XDECREF((PyObject *)__pyx_v_descr); @@ -9495,7 +9455,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -9519,7 +9479,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s int __pyx_t_1; __Pyx_RefNannySetupContext("__releasebuffer__", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -9529,7 +9489,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (PyArray_HASFIELDS(__pyx_v_self) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":309 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) # <<<<<<<<<<<<<< @@ -9538,7 +9498,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->format); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -9547,7 +9507,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -9557,7 +9517,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":311 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":298 * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): * PyObject_Free(info.strides) # <<<<<<<<<<<<<< @@ -9566,7 +9526,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->strides); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -9575,7 +9535,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -9587,7 +9547,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -9601,7 +9561,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew1", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":789 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 * * cdef inline object PyArray_MultiIterNew1(a): * return PyArray_MultiIterNew(1, a) # <<<<<<<<<<<<<< @@ -9609,13 +9569,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ * cdef inline object PyArray_MultiIterNew2(a, b): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 789, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 776, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -9634,7 +9594,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -9648,7 +9608,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew2", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 * * cdef inline object PyArray_MultiIterNew2(a, b): * return PyArray_MultiIterNew(2, a, b) # <<<<<<<<<<<<<< @@ -9656,13 +9616,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ * cdef inline object PyArray_MultiIterNew3(a, b, c): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 792, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 779, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -9681,7 +9641,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -9695,7 +9655,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew3", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":795 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 * * cdef inline object PyArray_MultiIterNew3(a, b, c): * return PyArray_MultiIterNew(3, a, b, c) # <<<<<<<<<<<<<< @@ -9703,13 +9663,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ * cdef inline object PyArray_MultiIterNew4(a, b, c, d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 795, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 782, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -9728,7 +9688,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -9742,7 +9702,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew4", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":798 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":785 * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): * return PyArray_MultiIterNew(4, a, b, c, d) # <<<<<<<<<<<<<< @@ -9750,13 +9710,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 798, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 785, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -9775,7 +9735,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -9789,7 +9749,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew5", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): * return PyArray_MultiIterNew(5, a, b, c, d, e) # <<<<<<<<<<<<<< @@ -9797,13 +9757,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ * cdef inline tuple PyDataType_SHAPE(dtype d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 801, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 788, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -9822,7 +9782,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -9836,7 +9796,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ int __pyx_t_1; __Pyx_RefNannySetupContext("PyDataType_SHAPE", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -9846,7 +9806,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_t_1 = (PyDataType_HASSUBARRAY(__pyx_v_d) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): * return d.subarray.shape # <<<<<<<<<<<<<< @@ -9858,7 +9818,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_r = ((PyObject*)__pyx_v_d->subarray->shape); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -9867,7 +9827,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 * return d.subarray.shape * else: * return () # <<<<<<<<<<<<<< @@ -9881,7 +9841,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -9896,7 +9856,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -9925,7 +9885,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx char *__pyx_t_9; __Pyx_RefNannySetupContext("_util_dtypestring", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 * * cdef dtype child * cdef int endian_detector = 1 # <<<<<<<<<<<<<< @@ -9934,7 +9894,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":815 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":802 * cdef dtype child * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< @@ -9943,7 +9903,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -9952,21 +9912,21 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->names == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); - __PYX_ERR(1, 818, __pyx_L1_error) + __PYX_ERR(1, 805, __pyx_L1_error) } __pyx_t_1 = __pyx_v_descr->names; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; for (;;) { if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 805, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 805, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif __Pyx_XDECREF_SET(__pyx_v_childname, __pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":819 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":806 * * for childname in descr.names: * fields = descr.fields[childname] # <<<<<<<<<<<<<< @@ -9975,15 +9935,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->fields == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); - __PYX_ERR(1, 819, __pyx_L1_error) + __PYX_ERR(1, 806, __pyx_L1_error) } - __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 819, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 819, __pyx_L1_error) + if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_fields, ((PyObject*)__pyx_t_3)); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":820 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 * for childname in descr.names: * fields = descr.fields[childname] * child, new_offset = fields # <<<<<<<<<<<<<< @@ -9992,15 +9952,11 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (likely(__pyx_v_fields != Py_None)) { PyObject* sequence = __pyx_v_fields; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(1, 820, __pyx_L1_error) + __PYX_ERR(1, 807, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyTuple_GET_ITEM(sequence, 0); @@ -10008,51 +9964,51 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(__pyx_t_4); #else - __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { - __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 820, __pyx_L1_error) + __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 807, __pyx_L1_error) } - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 820, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_child, ((PyArray_Descr *)__pyx_t_3)); __pyx_t_3 = 0; __Pyx_XDECREF_SET(__pyx_v_new_offset, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * */ - __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_6 = ((((__pyx_v_end - __pyx_v_f) - ((int)__pyx_t_5)) < 15) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 823, __pyx_L1_error) + __PYX_ERR(1, 810, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< @@ -10061,7 +10017,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -10081,7 +10037,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __pyx_L8_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":813 * * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -10098,29 +10054,29 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = __pyx_t_7; __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 827, __pyx_L1_error) + __PYX_ERR(1, 814, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -10129,7 +10085,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":824 * * # Output padding bytes * while offset[0] < new_offset: # <<<<<<<<<<<<<< @@ -10137,15 +10093,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * f += 1 */ while (1) { - __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (!__pyx_t_6) break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 * # Output padding bytes * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte # <<<<<<<<<<<<<< @@ -10154,7 +10110,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ (__pyx_v_f[0]) = 0x78; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte * f += 1 # <<<<<<<<<<<<<< @@ -10163,7 +10119,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 * f[0] = 120 # "x"; pad byte * f += 1 * offset[0] += 1 # <<<<<<<<<<<<<< @@ -10174,7 +10130,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + 1); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":829 * offset[0] += 1 * * offset[0] += child.itemsize # <<<<<<<<<<<<<< @@ -10184,7 +10140,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_8 = 0; (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + __pyx_v_child->elsize); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -10194,19 +10150,19 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = ((!(PyDataType_HASFIELDS(__pyx_v_child) != 0)) != 0); if (__pyx_t_6) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":832 * * if not PyDataType_HASFIELDS(child): * t = child.type_num # <<<<<<<<<<<<<< * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") */ - __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 832, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_XDECREF_SET(__pyx_v_t, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -10214,22 +10170,22 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ __pyx_t_6 = (((__pyx_v_end - __pyx_v_f) < 5) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_Raise(__pyx_t_4, 0, 0, 0); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __PYX_ERR(1, 847, __pyx_L1_error) + __PYX_ERR(1, 834, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -10238,252 +10194,252 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 * * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" # <<<<<<<<<<<<<< * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 98; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" # <<<<<<<<<<<<<< * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" # <<<<<<<<<<<<<< * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x68; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" # <<<<<<<<<<<<<< * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 72; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":854 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":841 * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" # <<<<<<<<<<<<<< * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x69; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" # <<<<<<<<<<<<<< * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 73; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":843 * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" # <<<<<<<<<<<<<< * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x6C; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":857 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" # <<<<<<<<<<<<<< * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 76; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":858 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" # <<<<<<<<<<<<<< * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x71; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":859 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" # <<<<<<<<<<<<<< * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 81; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" # <<<<<<<<<<<<<< * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":848 * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" # <<<<<<<<<<<<<< * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x64; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":862 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":849 * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" # <<<<<<<<<<<<<< * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x67; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":863 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf # <<<<<<<<<<<<<< * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -10492,18 +10448,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":864 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd # <<<<<<<<<<<<<< * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -10512,18 +10468,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":865 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg # <<<<<<<<<<<<<< * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -10532,25 +10488,25 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":866 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" # <<<<<<<<<<<<<< * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (__pyx_t_6) { + if (likely(__pyx_t_6)) { (__pyx_v_f[0]) = 79; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":868 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< @@ -10558,23 +10514,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * else: */ /*else*/ { - __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 868, __pyx_L1_error) + __Pyx_Raise(__pyx_t_4, 0, 0, 0); + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __PYX_ERR(1, 855, __pyx_L1_error) } __pyx_L15:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":869 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * f += 1 # <<<<<<<<<<<<<< @@ -10583,7 +10534,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -10593,7 +10544,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L13; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":873 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 * # Cython ignores struct boundary information ("T{...}"), * # so don't output it * f = _util_dtypestring(child, f, end, offset) # <<<<<<<<<<<<<< @@ -10601,12 +10552,12 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ /*else*/ { - __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 873, __pyx_L1_error) + __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 860, __pyx_L1_error) __pyx_v_f = __pyx_t_9; } __pyx_L13:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -10616,7 +10567,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":874 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 * # so don't output it * f = _util_dtypestring(child, f, end, offset) * return f # <<<<<<<<<<<<<< @@ -10626,7 +10577,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_r = __pyx_v_f; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -10651,7 +10602,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -10666,7 +10617,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a int __pyx_t_2; __Pyx_RefNannySetupContext("set_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -10677,7 +10628,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":993 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":980 * cdef PyObject* baseptr * if base is None: * baseptr = NULL # <<<<<<<<<<<<<< @@ -10686,7 +10637,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_baseptr = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -10696,7 +10647,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a goto __pyx_L3; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":995 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":982 * baseptr = NULL * else: * Py_INCREF(base) # important to do this before decref below! # <<<<<<<<<<<<<< @@ -10706,7 +10657,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a /*else*/ { Py_INCREF(__pyx_v_base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":983 * else: * Py_INCREF(base) # important to do this before decref below! * baseptr = base # <<<<<<<<<<<<<< @@ -10717,7 +10668,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a } __pyx_L3:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":984 * Py_INCREF(base) # important to do this before decref below! * baseptr = base * Py_XDECREF(arr.base) # <<<<<<<<<<<<<< @@ -10726,7 +10677,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ Py_XDECREF(__pyx_v_arr->base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":985 * baseptr = base * Py_XDECREF(arr.base) * arr.base = baseptr # <<<<<<<<<<<<<< @@ -10735,7 +10686,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_arr->base = __pyx_v_baseptr; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -10747,7 +10698,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -10761,7 +10712,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py int __pyx_t_1; __Pyx_RefNannySetupContext("get_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -10771,7 +10722,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py __pyx_t_1 = ((__pyx_v_arr->base == NULL) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":989 * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: * return None # <<<<<<<<<<<<<< @@ -10779,11 +10730,10 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py * return arr.base */ __Pyx_XDECREF(__pyx_r); - __Pyx_INCREF(Py_None); - __pyx_r = Py_None; + __pyx_r = Py_None; __Pyx_INCREF(Py_None); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -10792,7 +10742,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":991 * return None * else: * return arr.base # <<<<<<<<<<<<<< @@ -10806,7 +10756,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -10821,7 +10771,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -10842,7 +10792,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_array", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -10858,16 +10808,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 * cdef inline int import_array() except -1: * try: * _import_array() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.multiarray failed to import") */ - __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1011, __pyx_L3_error) + __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 998, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -10881,7 +10831,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":999 * try: * _import_array() * except Exception: # <<<<<<<<<<<<<< @@ -10891,28 +10841,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_array", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1012, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 999, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__14, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1013, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__14, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1000, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1013, __pyx_L5_except_error) + __PYX_ERR(1, 1000, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -10927,7 +10877,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -10950,7 +10900,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -10971,7 +10921,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_umath", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -10987,16 +10937,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1017 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 * cdef inline int import_umath() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1017, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1004, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -11010,7 +10960,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1018 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1005 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -11020,28 +10970,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_umath", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1018, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1005, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__15, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1019, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__15, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1006, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1019, __pyx_L5_except_error) + __PYX_ERR(1, 1006, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -11056,7 +11006,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -11079,7 +11029,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -11100,7 +11050,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_ufunc", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -11116,16 +11066,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1023 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 * cdef inline int import_ufunc() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1023, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1010, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -11139,7 +11089,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1024 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -11148,26 +11098,26 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_ufunc", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1024, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1011, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__16, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1025, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__16, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1012, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1025, __pyx_L5_except_error) + __PYX_ERR(1, 1012, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -11182,7 +11132,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -11223,7 +11173,7 @@ static PyModuleDef_Slot __pyx_moduledef_slots[] = { static struct PyModuleDef __pyx_moduledef = { PyModuleDef_HEAD_INIT, "doc2vec_inner", - 0, /* m_doc */ + __pyx_k_Optimized_cython_functions_for_t, /* m_doc */ #if CYTHON_PEP489_MULTI_PHASE_INIT 0, /* m_size */ #else @@ -11242,7 +11192,6 @@ static struct PyModuleDef __pyx_moduledef = { #endif static __Pyx_StringTabEntry __pyx_string_tab[] = { - {&__pyx_n_s_FAST_VERSION, __pyx_k_FAST_VERSION, sizeof(__pyx_k_FAST_VERSION), 0, 0, 1, 1}, {&__pyx_kp_u_Format_string_allocated_too_shor, __pyx_k_Format_string_allocated_too_shor, sizeof(__pyx_k_Format_string_allocated_too_shor), 0, 1, 0, 0}, {&__pyx_kp_u_Format_string_allocated_too_shor_2, __pyx_k_Format_string_allocated_too_shor_2, sizeof(__pyx_k_Format_string_allocated_too_shor_2), 0, 1, 0, 0}, {&__pyx_n_s_ImportError, __pyx_k_ImportError, sizeof(__pyx_k_ImportError), 0, 0, 1, 1}, @@ -11345,7 +11294,6 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {&__pyx_n_s_vocabulary, __pyx_k_vocabulary, sizeof(__pyx_k_vocabulary), 0, 0, 1, 1}, {&__pyx_n_s_window, __pyx_k_window, sizeof(__pyx_k_window), 0, 0, 1, 1}, {&__pyx_n_s_window_indexes, __pyx_k_window_indexes, sizeof(__pyx_k_window_indexes), 0, 0, 1, 1}, - {&__pyx_n_s_word2vec, __pyx_k_word2vec, sizeof(__pyx_k_word2vec), 0, 0, 1, 1}, {&__pyx_n_s_word_locks, __pyx_k_word_locks, sizeof(__pyx_k_word_locks), 0, 0, 1, 1}, {&__pyx_n_s_word_locks_2, __pyx_k_word_locks_2, sizeof(__pyx_k_word_locks_2), 0, 0, 1, 1}, {&__pyx_n_s_word_vectors, __pyx_k_word_vectors, sizeof(__pyx_k_word_vectors), 0, 0, 1, 1}, @@ -11357,11 +11305,11 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {0, 0, 0, 0, 0, 0, 0} }; static int __Pyx_InitCachedBuiltins(void) { - __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(0, 21, __pyx_L1_error) - __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 52, __pyx_L1_error) - __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 319, __pyx_L1_error) - __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(1, 235, __pyx_L1_error) - __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(0, 23, __pyx_L1_error) + __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 48, __pyx_L1_error) + __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 359, __pyx_L1_error) + __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(1, 229, __pyx_L1_error) + __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 810, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; @@ -11371,180 +11319,180 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0); - /* "gensim/models/doc2vec_inner.pyx":291 + /* "gensim/models/doc2vec_inner.pyx":331 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple_ = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_tuple_ = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple_); __Pyx_GIVEREF(__pyx_tuple_); - __pyx_tuple__2 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(0, 291, __pyx_L1_error) + __pyx_tuple__2 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(0, 331, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__2); __Pyx_GIVEREF(__pyx_tuple__2); - /* "gensim/models/doc2vec_inner.pyx":429 + /* "gensim/models/doc2vec_inner.pyx":514 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple__3 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_tuple__3 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__3); __Pyx_GIVEREF(__pyx_tuple__3); - __pyx_tuple__4 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 429, __pyx_L1_error) + __pyx_tuple__4 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 514, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__4); __Pyx_GIVEREF(__pyx_tuple__4); - /* "gensim/models/doc2vec_inner.pyx":591 + /* "gensim/models/doc2vec_inner.pyx":721 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple__6 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_tuple__6 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__6); __Pyx_GIVEREF(__pyx_tuple__6); - __pyx_tuple__7 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__7)) __PYX_ERR(0, 591, __pyx_L1_error) + __pyx_tuple__7 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__7)) __PYX_ERR(0, 721, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__7); __Pyx_GIVEREF(__pyx_tuple__7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_tuple__8 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_tuple__8 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__8); __Pyx_GIVEREF(__pyx_tuple__8); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__9); __Pyx_GIVEREF(__pyx_tuple__9); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__10); __Pyx_GIVEREF(__pyx_tuple__10); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__11); __Pyx_GIVEREF(__pyx_tuple__11); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__12); __Pyx_GIVEREF(__pyx_tuple__12); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__13); __Pyx_GIVEREF(__pyx_tuple__13); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_tuple__14 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__14)) __PYX_ERR(1, 1013, __pyx_L1_error) + __pyx_tuple__14 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__14)) __PYX_ERR(1, 1000, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__14); __Pyx_GIVEREF(__pyx_tuple__14); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_tuple__15 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(1, 1019, __pyx_L1_error) + __pyx_tuple__15 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(1, 1006, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__15); __Pyx_GIVEREF(__pyx_tuple__15); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_tuple__16 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__16)) __PYX_ERR(1, 1025, __pyx_L1_error) + __pyx_tuple__16 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__16)) __PYX_ERR(1, 1012, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__16); __Pyx_GIVEREF(__pyx_tuple__16); - /* "gensim/models/doc2vec_inner.pyx":227 + /* "gensim/models/doc2vec_inner.pyx":223 * * * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, # <<<<<<<<<<<<<< * train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): */ - __pyx_tuple__18 = PyTuple_Pack(50, __pyx_n_s_model, __pyx_n_s_doc_words, __pyx_n_s_doctag_indexes, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_train_words, __pyx_n_s_learn_doctags, __pyx_n_s_learn_words, __pyx_n_s_learn_hidden, __pyx_n_s_word_vectors, __pyx_n_s_word_locks, __pyx_n_s_doctag_vectors, __pyx_n_s_doctag_locks, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_train_words_2, __pyx_n_s_learn_words_2, __pyx_n_s_learn_hidden_2, __pyx_n_s_learn_doctags_2, __pyx_n_s_word_vectors_2, __pyx_n_s_doctag_vectors_2, __pyx_n_s_word_locks_2, __pyx_n_s_doctag_locks_2, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_doctag_indexes_2, __pyx_n_s_reduced_windows, __pyx_n_s_document_len, __pyx_n_s_doctag_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_r, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_predict_word, __pyx_n_s_item, __pyx_n_s_k); if (unlikely(!__pyx_tuple__18)) __PYX_ERR(0, 227, __pyx_L1_error) + __pyx_tuple__18 = PyTuple_Pack(50, __pyx_n_s_model, __pyx_n_s_doc_words, __pyx_n_s_doctag_indexes, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_train_words, __pyx_n_s_learn_doctags, __pyx_n_s_learn_words, __pyx_n_s_learn_hidden, __pyx_n_s_word_vectors, __pyx_n_s_word_locks, __pyx_n_s_doctag_vectors, __pyx_n_s_doctag_locks, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_train_words_2, __pyx_n_s_learn_words_2, __pyx_n_s_learn_hidden_2, __pyx_n_s_learn_doctags_2, __pyx_n_s_word_vectors_2, __pyx_n_s_doctag_vectors_2, __pyx_n_s_word_locks_2, __pyx_n_s_doctag_locks_2, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_doctag_indexes_2, __pyx_n_s_reduced_windows, __pyx_n_s_document_len, __pyx_n_s_doctag_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_r, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_predict_word, __pyx_n_s_item, __pyx_n_s_k); if (unlikely(!__pyx_tuple__18)) __PYX_ERR(0, 223, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__18); __Pyx_GIVEREF(__pyx_tuple__18); - __pyx_codeobj__19 = (PyObject*)__Pyx_PyCode_New(13, 0, 50, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__18, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_doc2vec_inner_pyx, __pyx_n_s_train_document_dbow, 227, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__19)) __PYX_ERR(0, 227, __pyx_L1_error) + __pyx_codeobj__19 = (PyObject*)__Pyx_PyCode_New(13, 0, 50, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__18, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_doc2vec_inner_pyx, __pyx_n_s_train_document_dbow, 223, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__19)) __PYX_ERR(0, 223, __pyx_L1_error) - /* "gensim/models/doc2vec_inner.pyx":363 + /* "gensim/models/doc2vec_inner.pyx":403 * * * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< * learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): */ - __pyx_tuple__20 = PyTuple_Pack(53, __pyx_n_s_model, __pyx_n_s_doc_words, __pyx_n_s_doctag_indexes, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_learn_doctags, __pyx_n_s_learn_words, __pyx_n_s_learn_hidden, __pyx_n_s_word_vectors, __pyx_n_s_word_locks, __pyx_n_s_doctag_vectors, __pyx_n_s_doctag_locks, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_learn_doctags_2, __pyx_n_s_learn_words_2, __pyx_n_s_learn_hidden_2, __pyx_n_s_cbow_mean, __pyx_n_s_count, __pyx_n_s_inv_count, __pyx_n_s_word_vectors_2, __pyx_n_s_doctag_vectors_2, __pyx_n_s_word_locks_2, __pyx_n_s_doctag_locks_2, __pyx_n_s_work_2, __pyx_n_s_neu1_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_doctag_indexes_2, __pyx_n_s_reduced_windows, __pyx_n_s_document_len, __pyx_n_s_doctag_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_m, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_predict_word, __pyx_n_s_item); if (unlikely(!__pyx_tuple__20)) __PYX_ERR(0, 363, __pyx_L1_error) + __pyx_tuple__20 = PyTuple_Pack(53, __pyx_n_s_model, __pyx_n_s_doc_words, __pyx_n_s_doctag_indexes, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_learn_doctags, __pyx_n_s_learn_words, __pyx_n_s_learn_hidden, __pyx_n_s_word_vectors, __pyx_n_s_word_locks, __pyx_n_s_doctag_vectors, __pyx_n_s_doctag_locks, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_learn_doctags_2, __pyx_n_s_learn_words_2, __pyx_n_s_learn_hidden_2, __pyx_n_s_cbow_mean, __pyx_n_s_count, __pyx_n_s_inv_count, __pyx_n_s_word_vectors_2, __pyx_n_s_doctag_vectors_2, __pyx_n_s_word_locks_2, __pyx_n_s_doctag_locks_2, __pyx_n_s_work_2, __pyx_n_s_neu1_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_doctag_indexes_2, __pyx_n_s_reduced_windows, __pyx_n_s_document_len, __pyx_n_s_doctag_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_m, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_predict_word, __pyx_n_s_item); if (unlikely(!__pyx_tuple__20)) __PYX_ERR(0, 403, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__20); __Pyx_GIVEREF(__pyx_tuple__20); - __pyx_codeobj__21 = (PyObject*)__Pyx_PyCode_New(13, 0, 53, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__20, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_doc2vec_inner_pyx, __pyx_n_s_train_document_dm, 363, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__21)) __PYX_ERR(0, 363, __pyx_L1_error) + __pyx_codeobj__21 = (PyObject*)__Pyx_PyCode_New(13, 0, 53, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__20, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_doc2vec_inner_pyx, __pyx_n_s_train_document_dm, 403, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__21)) __PYX_ERR(0, 403, __pyx_L1_error) - /* "gensim/models/doc2vec_inner.pyx":521 + /* "gensim/models/doc2vec_inner.pyx":606 * * * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< * learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): */ - __pyx_tuple__22 = PyTuple_Pack(53, __pyx_n_s_model, __pyx_n_s_doc_words, __pyx_n_s_doctag_indexes, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_learn_doctags, __pyx_n_s_learn_words, __pyx_n_s_learn_hidden, __pyx_n_s_word_vectors, __pyx_n_s_word_locks, __pyx_n_s_doctag_vectors, __pyx_n_s_doctag_locks, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_learn_doctags_2, __pyx_n_s_learn_words_2, __pyx_n_s_learn_hidden_2, __pyx_n_s_word_vectors_2, __pyx_n_s_doctag_vectors_2, __pyx_n_s_word_locks_2, __pyx_n_s_doctag_locks_2, __pyx_n_s_work_2, __pyx_n_s_neu1_2, __pyx_n_s_alpha_2, __pyx_n_s_layer1_size, __pyx_n_s_vector_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_doctag_indexes_2, __pyx_n_s_window_indexes, __pyx_n_s_document_len, __pyx_n_s_doctag_len, __pyx_n_s_window, __pyx_n_s_expected_doctag_len, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_m, __pyx_n_s_n, __pyx_n_s_result, __pyx_n_s_null_word_index, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_predict_word); if (unlikely(!__pyx_tuple__22)) __PYX_ERR(0, 521, __pyx_L1_error) + __pyx_tuple__22 = PyTuple_Pack(53, __pyx_n_s_model, __pyx_n_s_doc_words, __pyx_n_s_doctag_indexes, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_learn_doctags, __pyx_n_s_learn_words, __pyx_n_s_learn_hidden, __pyx_n_s_word_vectors, __pyx_n_s_word_locks, __pyx_n_s_doctag_vectors, __pyx_n_s_doctag_locks, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_learn_doctags_2, __pyx_n_s_learn_words_2, __pyx_n_s_learn_hidden_2, __pyx_n_s_word_vectors_2, __pyx_n_s_doctag_vectors_2, __pyx_n_s_word_locks_2, __pyx_n_s_doctag_locks_2, __pyx_n_s_work_2, __pyx_n_s_neu1_2, __pyx_n_s_alpha_2, __pyx_n_s_layer1_size, __pyx_n_s_vector_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_doctag_indexes_2, __pyx_n_s_window_indexes, __pyx_n_s_document_len, __pyx_n_s_doctag_len, __pyx_n_s_window, __pyx_n_s_expected_doctag_len, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_m, __pyx_n_s_n, __pyx_n_s_result, __pyx_n_s_null_word_index, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_predict_word); if (unlikely(!__pyx_tuple__22)) __PYX_ERR(0, 606, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__22); __Pyx_GIVEREF(__pyx_tuple__22); - __pyx_codeobj__23 = (PyObject*)__Pyx_PyCode_New(13, 0, 53, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__22, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_doc2vec_inner_pyx, __pyx_n_s_train_document_dm_concat, 521, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__23)) __PYX_ERR(0, 521, __pyx_L1_error) + __pyx_codeobj__23 = (PyObject*)__Pyx_PyCode_New(13, 0, 53, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__22, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_doc2vec_inner_pyx, __pyx_n_s_train_document_dm_concat, 606, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__23)) __PYX_ERR(0, 606, __pyx_L1_error) __Pyx_RefNannyFinishContext(); return 0; __pyx_L1_error:; @@ -11561,12 +11509,141 @@ static int __Pyx_InitGlobals(void) { return -1; } +static int __Pyx_modinit_global_init_code(void); /*proto*/ +static int __Pyx_modinit_variable_export_code(void); /*proto*/ +static int __Pyx_modinit_function_export_code(void); /*proto*/ +static int __Pyx_modinit_type_init_code(void); /*proto*/ +static int __Pyx_modinit_type_import_code(void); /*proto*/ +static int __Pyx_modinit_variable_import_code(void); /*proto*/ +static int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", + #if defined(PYPY_VERSION_NUM) && PYPY_VERSION_NUM < 0x050B0000 + sizeof(PyTypeObject), + #else + sizeof(PyHeapTypeObject), + #endif + 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(2, 9, __pyx_L1_error) + __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 164, __pyx_L1_error) + __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 186, __pyx_L1_error) + __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 190, __pyx_L1_error) + __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 199, __pyx_L1_error) + __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 872, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __pyx_t_1 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_1) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "scopy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_scopy, "__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "sdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sdot, "__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "dsdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_dsdot, "__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "snrm2", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_snrm2, "__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "sscal", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sscal, "__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "EXP_TABLE", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_EXP_TABLE, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t [0x3E8]") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_dot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_dot, "__pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + Py_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __pyx_t_1 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_1) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "bisect_left", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_bisect_left, "unsigned PY_LONG_LONG (__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "random_int32", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_random_int32, "unsigned PY_LONG_LONG (unsigned PY_LONG_LONG *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + Py_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_RefNannyFinishContext(); + return -1; +} + + +#if PY_MAJOR_VERSION < 3 +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC void +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#else +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyObject * +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (!(defined(__cplusplus)) || (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ > 4))) + #define CYTHON_SMALL_CODE __attribute__((optimize("Os"))) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + + #if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initdoc2vec_inner(void); /*proto*/ -PyMODINIT_FUNC initdoc2vec_inner(void) +__Pyx_PyMODINIT_FUNC initdoc2vec_inner(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC initdoc2vec_inner(void) #else -PyMODINIT_FUNC PyInit_doc2vec_inner(void); /*proto*/ -PyMODINIT_FUNC PyInit_doc2vec_inner(void) +__Pyx_PyMODINIT_FUNC PyInit_doc2vec_inner(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit_doc2vec_inner(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); @@ -11615,26 +11692,26 @@ static int __pyx_pymod_exec_doc2vec_inner(PyObject *__pyx_pyinit_module) PyObject *__pyx_t_3 = NULL; PyObject *__pyx_t_4 = NULL; PyObject *__pyx_t_5 = NULL; - PyObject *__pyx_t_6 = NULL; + int __pyx_t_6; PyObject *__pyx_t_7 = NULL; - int __pyx_t_8; + PyObject *__pyx_t_8 = NULL; PyObject *__pyx_t_9 = NULL; - PyObject *__pyx_t_10 = NULL; - PyObject *__pyx_t_11 = NULL; __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m && __pyx_m == __pyx_pyinit_module) return 0; + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif #if CYTHON_REFNANNY - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); - if (!__Pyx_RefNanny) { - PyErr_Clear(); - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); - if (!__Pyx_RefNanny) - Py_FatalError("failed to import 'refnanny' module"); - } - #endif - __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit_doc2vec_inner(void)", 0); +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit_doc2vec_inner(void)", 0); if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) @@ -11670,7 +11747,7 @@ static int __pyx_pymod_exec_doc2vec_inner(PyObject *__pyx_pyinit_module) Py_INCREF(__pyx_m); #else #if PY_MAJOR_VERSION < 3 - __pyx_m = Py_InitModule4("doc2vec_inner", __pyx_methods, 0, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); + __pyx_m = Py_InitModule4("doc2vec_inner", __pyx_methods, __pyx_k_Optimized_cython_functions_for_t, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); #else __pyx_m = PyModule_Create(&__pyx_moduledef); #endif @@ -11704,224 +11781,173 @@ static int __pyx_pymod_exec_doc2vec_inner(PyObject *__pyx_pyinit_module) if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) /*--- Constants init code ---*/ if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Global init code ---*/ - /*--- Variable export code ---*/ - /*--- Function export code ---*/ - /*--- Type init code ---*/ - /*--- Type import code ---*/ - __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", - #if CYTHON_COMPILING_IN_PYPY - sizeof(PyTypeObject), - #else - sizeof(PyHeapTypeObject), - #endif - 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(2, 9, __pyx_L1_error) - __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 163, __pyx_L1_error) - __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 185, __pyx_L1_error) - __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 189, __pyx_L1_error) - __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 198, __pyx_L1_error) - __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 885, __pyx_L1_error) - /*--- Variable import code ---*/ - __pyx_t_1 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_1) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "scopy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_scopy, "__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "sdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sdot, "__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "dsdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_dsdot, "__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "snrm2", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_snrm2, "__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "sscal", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sscal, "__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "EXP_TABLE", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_EXP_TABLE, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t [0x3E8]") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_dot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_dot, "__pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - Py_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /*--- Function import code ---*/ - __pyx_t_2 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_2) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_dot_double", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_double, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_dot_float", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_float, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_dot_noblas", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_saxpy_noblas", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas, "void (int const *, float const *, float const *, int const *, float *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "bisect_left", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_bisect_left, "unsigned PY_LONG_LONG (__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "random_int32", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_random_int32, "unsigned PY_LONG_LONG (unsigned PY_LONG_LONG *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - Py_DECREF(__pyx_t_2); __pyx_t_2 = 0; + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + (void)__Pyx_modinit_variable_export_code(); + (void)__Pyx_modinit_function_export_code(); + (void)__Pyx_modinit_type_init_code(); + if (unlikely(__Pyx_modinit_type_import_code() != 0)) goto __pyx_L1_error; + if (unlikely(__Pyx_modinit_variable_import_code() != 0)) goto __pyx_L1_error; + if (unlikely(__Pyx_modinit_function_import_code() != 0)) goto __pyx_L1_error; /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif - /* "gensim/models/doc2vec_inner.pyx":11 + /* "gensim/models/doc2vec_inner.pyx":14 * * import cython * import numpy as np # <<<<<<<<<<<<<< * from numpy import zeros, float32 as REAL * cimport numpy as np */ - __pyx_t_3 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 11, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_3) < 0) __PYX_ERR(0, 11, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_1 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 14, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_1) < 0) __PYX_ERR(0, 14, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":12 + /* "gensim/models/doc2vec_inner.pyx":15 * import cython * import numpy as np * from numpy import zeros, float32 as REAL # <<<<<<<<<<<<<< * cimport numpy as np * */ - __pyx_t_3 = PyList_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 12, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); + __pyx_t_1 = PyList_New(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_n_s_zeros); __Pyx_GIVEREF(__pyx_n_s_zeros); - PyList_SET_ITEM(__pyx_t_3, 0, __pyx_n_s_zeros); + PyList_SET_ITEM(__pyx_t_1, 0, __pyx_n_s_zeros); __Pyx_INCREF(__pyx_n_s_float32); __Pyx_GIVEREF(__pyx_n_s_float32); - PyList_SET_ITEM(__pyx_t_3, 1, __pyx_n_s_float32); - __pyx_t_4 = __Pyx_Import(__pyx_n_s_numpy, __pyx_t_3, -1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 12, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_ImportFrom(__pyx_t_4, __pyx_n_s_zeros); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 12, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_zeros, __pyx_t_3) < 0) __PYX_ERR(0, 12, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_ImportFrom(__pyx_t_4, __pyx_n_s_float32); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 12, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_REAL, __pyx_t_3) < 0) __PYX_ERR(0, 12, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + PyList_SET_ITEM(__pyx_t_1, 1, __pyx_n_s_float32); + __pyx_t_2 = __Pyx_Import(__pyx_n_s_numpy, __pyx_t_1, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_zeros); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_zeros, __pyx_t_1) < 0) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_float32); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_REAL, __pyx_t_1) < 0) __PYX_ERR(0, 15, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/doc2vec_inner.pyx":19 + /* "gensim/models/doc2vec_inner.pyx":21 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< - * from scipy.linalg.blas import fblas + * from scipy.linalg.blas import fblas * except ImportError: */ { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign - __Pyx_ExceptionSave(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7); + __Pyx_ExceptionSave(&__pyx_t_3, &__pyx_t_4, &__pyx_t_5); + __Pyx_XGOTREF(__pyx_t_3); + __Pyx_XGOTREF(__pyx_t_4); __Pyx_XGOTREF(__pyx_t_5); - __Pyx_XGOTREF(__pyx_t_6); - __Pyx_XGOTREF(__pyx_t_7); /*try:*/ { - /* "gensim/models/doc2vec_inner.pyx":20 + /* "gensim/models/doc2vec_inner.pyx":22 * # scipy <= 0.15 * try: - * from scipy.linalg.blas import fblas # <<<<<<<<<<<<<< + * from scipy.linalg.blas import fblas # <<<<<<<<<<<<<< * except ImportError: - * # in scipy > 0.15, fblas function has been removed + * # in scipy > 0.15, fblas function has been removed */ - __pyx_t_4 = PyList_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 20, __pyx_L2_error) - __Pyx_GOTREF(__pyx_t_4); + __pyx_t_2 = PyList_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 22, __pyx_L2_error) + __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_n_s_fblas); __Pyx_GIVEREF(__pyx_n_s_fblas); - PyList_SET_ITEM(__pyx_t_4, 0, __pyx_n_s_fblas); - __pyx_t_3 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_4, -1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 20, __pyx_L2_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_4 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_fblas); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 20, __pyx_L2_error) - __Pyx_GOTREF(__pyx_t_4); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_4) < 0) __PYX_ERR(0, 20, __pyx_L2_error) - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + PyList_SET_ITEM(__pyx_t_2, 0, __pyx_n_s_fblas); + __pyx_t_1 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_2, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 22, __pyx_L2_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_1, __pyx_n_s_fblas); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 22, __pyx_L2_error) + __Pyx_GOTREF(__pyx_t_2); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_2) < 0) __PYX_ERR(0, 22, __pyx_L2_error) + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":19 + /* "gensim/models/doc2vec_inner.pyx":21 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< - * from scipy.linalg.blas import fblas + * from scipy.linalg.blas import fblas * except ImportError: */ } + __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_XDECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; - __Pyx_XDECREF(__pyx_t_6); __pyx_t_6 = 0; - __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; goto __pyx_L7_try_end; __pyx_L2_error:; - __Pyx_XDECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/doc2vec_inner.pyx":21 + /* "gensim/models/doc2vec_inner.pyx":23 * try: - * from scipy.linalg.blas import fblas + * from scipy.linalg.blas import fblas * except ImportError: # <<<<<<<<<<<<<< - * # in scipy > 0.15, fblas function has been removed - * import scipy.linalg.blas as fblas + * # in scipy > 0.15, fblas function has been removed + * import scipy.linalg.blas as fblas */ - __pyx_t_8 = __Pyx_PyErr_ExceptionMatches(__pyx_builtin_ImportError); - if (__pyx_t_8) { + __pyx_t_6 = __Pyx_PyErr_ExceptionMatches(__pyx_builtin_ImportError); + if (__pyx_t_6) { __Pyx_AddTraceback("gensim.models.doc2vec_inner", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_3, &__pyx_t_4, &__pyx_t_9) < 0) __PYX_ERR(0, 21, __pyx_L4_except_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_GOTREF(__pyx_t_4); - __Pyx_GOTREF(__pyx_t_9); + if (__Pyx_GetException(&__pyx_t_1, &__pyx_t_2, &__pyx_t_7) < 0) __PYX_ERR(0, 23, __pyx_L4_except_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_GOTREF(__pyx_t_2); + __Pyx_GOTREF(__pyx_t_7); - /* "gensim/models/doc2vec_inner.pyx":23 + /* "gensim/models/doc2vec_inner.pyx":25 * except ImportError: - * # in scipy > 0.15, fblas function has been removed - * import scipy.linalg.blas as fblas # <<<<<<<<<<<<<< + * # in scipy > 0.15, fblas function has been removed + * import scipy.linalg.blas as fblas # <<<<<<<<<<<<<< * - * from word2vec_inner cimport bisect_left, random_int32, \ + * from word2vec_inner cimport bisect_left, random_int32, sscal, REAL_t, EXP_TABLE, our_dot, our_saxpy */ - __pyx_t_10 = PyList_New(1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 23, __pyx_L4_except_error) - __Pyx_GOTREF(__pyx_t_10); + __pyx_t_8 = PyList_New(1); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 25, __pyx_L4_except_error) + __Pyx_GOTREF(__pyx_t_8); __Pyx_INCREF(__pyx_n_s__17); __Pyx_GIVEREF(__pyx_n_s__17); - PyList_SET_ITEM(__pyx_t_10, 0, __pyx_n_s__17); - __pyx_t_11 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_10, -1); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 23, __pyx_L4_except_error) - __Pyx_GOTREF(__pyx_t_11); - __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_11) < 0) __PYX_ERR(0, 23, __pyx_L4_except_error) - __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + PyList_SET_ITEM(__pyx_t_8, 0, __pyx_n_s__17); + __pyx_t_9 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_8, -1); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 25, __pyx_L4_except_error) + __Pyx_GOTREF(__pyx_t_9); + __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_9) < 0) __PYX_ERR(0, 25, __pyx_L4_except_error) __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; goto __pyx_L3_exception_handled; } goto __pyx_L4_except_error; __pyx_L4_except_error:; - /* "gensim/models/doc2vec_inner.pyx":19 + /* "gensim/models/doc2vec_inner.pyx":21 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< - * from scipy.linalg.blas import fblas + * from scipy.linalg.blas import fblas * except ImportError: */ + __Pyx_XGIVEREF(__pyx_t_3); + __Pyx_XGIVEREF(__pyx_t_4); __Pyx_XGIVEREF(__pyx_t_5); - __Pyx_XGIVEREF(__pyx_t_6); - __Pyx_XGIVEREF(__pyx_t_7); - __Pyx_ExceptionReset(__pyx_t_5, __pyx_t_6, __pyx_t_7); + __Pyx_ExceptionReset(__pyx_t_3, __pyx_t_4, __pyx_t_5); goto __pyx_L1_error; __pyx_L3_exception_handled:; + __Pyx_XGIVEREF(__pyx_t_3); + __Pyx_XGIVEREF(__pyx_t_4); __Pyx_XGIVEREF(__pyx_t_5); - __Pyx_XGIVEREF(__pyx_t_6); - __Pyx_XGIVEREF(__pyx_t_7); - __Pyx_ExceptionReset(__pyx_t_5, __pyx_t_6, __pyx_t_7); + __Pyx_ExceptionReset(__pyx_t_3, __pyx_t_4, __pyx_t_5); __pyx_L7_try_end:; } /* "gensim/models/doc2vec_inner.pyx":31 - * our_dot_double, our_dot_float, our_dot_noblas, our_saxpy_noblas - * - * from word2vec import FAST_VERSION # <<<<<<<<<<<<<< - * - * DEF MAX_DOCUMENT_LEN = 10000 - */ - __pyx_t_9 = PyList_New(1); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 31, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_9); - __Pyx_INCREF(__pyx_n_s_FAST_VERSION); - __Pyx_GIVEREF(__pyx_n_s_FAST_VERSION); - PyList_SET_ITEM(__pyx_t_9, 0, __pyx_n_s_FAST_VERSION); - __pyx_t_4 = __Pyx_Import(__pyx_n_s_word2vec, __pyx_t_9, -1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 31, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; - __pyx_t_9 = __Pyx_ImportFrom(__pyx_t_4, __pyx_n_s_FAST_VERSION); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 31, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_9); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_FAST_VERSION, __pyx_t_9) < 0) __PYX_ERR(0, 31, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - - /* "gensim/models/doc2vec_inner.pyx":35 * DEF MAX_DOCUMENT_LEN = 10000 * * cdef int ONE = 1 # <<<<<<<<<<<<<< @@ -11930,7 +11956,7 @@ static int __pyx_pymod_exec_doc2vec_inner(PyObject *__pyx_pyinit_module) */ __pyx_v_6gensim_6models_13doc2vec_inner_ONE = 1; - /* "gensim/models/doc2vec_inner.pyx":36 + /* "gensim/models/doc2vec_inner.pyx":32 * * cdef int ONE = 1 * cdef REAL_t ONEF = 1.0 # <<<<<<<<<<<<<< @@ -11939,53 +11965,53 @@ static int __pyx_pymod_exec_doc2vec_inner(PyObject *__pyx_pyinit_module) */ __pyx_v_6gensim_6models_13doc2vec_inner_ONEF = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)1.0); - /* "gensim/models/doc2vec_inner.pyx":227 + /* "gensim/models/doc2vec_inner.pyx":223 * * * def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, # <<<<<<<<<<<<<< * train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): */ - __pyx_t_4 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_13doc2vec_inner_1train_document_dbow, NULL, __pyx_n_s_gensim_models_doc2vec_inner); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 227, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_document_dbow, __pyx_t_4) < 0) __PYX_ERR(0, 227, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __pyx_t_7 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_13doc2vec_inner_1train_document_dbow, NULL, __pyx_n_s_gensim_models_doc2vec_inner); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 223, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_document_dbow, __pyx_t_7) < 0) __PYX_ERR(0, 223, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "gensim/models/doc2vec_inner.pyx":363 + /* "gensim/models/doc2vec_inner.pyx":403 * * * def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< * learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): */ - __pyx_t_4 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_13doc2vec_inner_3train_document_dm, NULL, __pyx_n_s_gensim_models_doc2vec_inner); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 363, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_document_dm, __pyx_t_4) < 0) __PYX_ERR(0, 363, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __pyx_t_7 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_13doc2vec_inner_3train_document_dm, NULL, __pyx_n_s_gensim_models_doc2vec_inner); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 403, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_document_dm, __pyx_t_7) < 0) __PYX_ERR(0, 403, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "gensim/models/doc2vec_inner.pyx":521 + /* "gensim/models/doc2vec_inner.pyx":606 * * * def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, # <<<<<<<<<<<<<< * learn_doctags=True, learn_words=True, learn_hidden=True, * word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): */ - __pyx_t_4 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_13doc2vec_inner_5train_document_dm_concat, NULL, __pyx_n_s_gensim_models_doc2vec_inner); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 521, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_document_dm_concat, __pyx_t_4) < 0) __PYX_ERR(0, 521, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __pyx_t_7 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_13doc2vec_inner_5train_document_dm_concat, NULL, __pyx_n_s_gensim_models_doc2vec_inner); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 606, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_document_dm_concat, __pyx_t_7) < 0) __PYX_ERR(0, 606, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; /* "gensim/models/doc2vec_inner.pyx":1 * #!/usr/bin/env cython # <<<<<<<<<<<<<< * # cython: boundscheck=False * # cython: wraparound=False */ - __pyx_t_4 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_4) < 0) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __pyx_t_7 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_7) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -11999,11 +12025,9 @@ static int __pyx_pymod_exec_doc2vec_inner(PyObject *__pyx_pyinit_module) __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); - __Pyx_XDECREF(__pyx_t_3); - __Pyx_XDECREF(__pyx_t_4); + __Pyx_XDECREF(__pyx_t_7); + __Pyx_XDECREF(__pyx_t_8); __Pyx_XDECREF(__pyx_t_9); - __Pyx_XDECREF(__pyx_t_10); - __Pyx_XDECREF(__pyx_t_11); if (__pyx_m) { if (__pyx_d) { __Pyx_AddTraceback("init gensim.models.doc2vec_inner", 0, __pyx_lineno, __pyx_filename); @@ -12041,6 +12065,20 @@ static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { } #endif +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); @@ -12234,10 +12272,19 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { PyObject *result; #if !CYTHON_AVOID_BORROWED_REFS +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 + result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); + if (likely(result)) { + Py_INCREF(result); + } else if (unlikely(PyErr_Occurred())) { + result = NULL; + } else { +#else result = PyDict_GetItem(__pyx_d, name); if (likely(result)) { Py_INCREF(result); } else { +#endif #else result = PyObject_GetItem(__pyx_d, name); if (!result) { @@ -12248,8 +12295,124 @@ static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { return result; } +/* GetItemInt */ + static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { + PyObject *r; + if (!j) return NULL; + r = PyObject_GetItem(o, j); + Py_DECREF(j); + return r; +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS + Py_ssize_t wrapped_i = i; + if (wraparound & unlikely(i < 0)) { + wrapped_i += PyList_GET_SIZE(o); + } + if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyList_GET_SIZE(o)))) { + PyObject *r = PyList_GET_ITEM(o, wrapped_i); + Py_INCREF(r); + return r; + } + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +#else + return PySequence_GetItem(o, i); +#endif +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS + Py_ssize_t wrapped_i = i; + if (wraparound & unlikely(i < 0)) { + wrapped_i += PyTuple_GET_SIZE(o); + } + if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyTuple_GET_SIZE(o)))) { + PyObject *r = PyTuple_GET_ITEM(o, wrapped_i); + Py_INCREF(r); + return r; + } + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +#else + return PySequence_GetItem(o, i); +#endif +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, int is_list, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS && CYTHON_USE_TYPE_SLOTS + if (is_list || PyList_CheckExact(o)) { + Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyList_GET_SIZE(o); + if ((!boundscheck) || (likely((n >= 0) & (n < PyList_GET_SIZE(o))))) { + PyObject *r = PyList_GET_ITEM(o, n); + Py_INCREF(r); + return r; + } + } + else if (PyTuple_CheckExact(o)) { + Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyTuple_GET_SIZE(o); + if ((!boundscheck) || likely((n >= 0) & (n < PyTuple_GET_SIZE(o)))) { + PyObject *r = PyTuple_GET_ITEM(o, n); + Py_INCREF(r); + return r; + } + } else { + PySequenceMethods *m = Py_TYPE(o)->tp_as_sequence; + if (likely(m && m->sq_item)) { + if (wraparound && unlikely(i < 0) && likely(m->sq_length)) { + Py_ssize_t l = m->sq_length(o); + if (likely(l >= 0)) { + i += l; + } else { + if (!PyErr_ExceptionMatches(PyExc_OverflowError)) + return NULL; + PyErr_Clear(); + } + } + return m->sq_item(o, i); + } + } +#else + if (is_list || PySequence_Check(o)) { + return PySequence_GetItem(o, i); + } +#endif + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +} + +/* ObjectGetItem */ + #if CYTHON_USE_TYPE_SLOTS +static PyObject *__Pyx_PyObject_GetIndex(PyObject *obj, PyObject* index) { + PyObject *runerr; + Py_ssize_t key_value; + PySequenceMethods *m = Py_TYPE(obj)->tp_as_sequence; + if (unlikely(!(m && m->sq_item))) { + PyErr_Format(PyExc_TypeError, "'%.200s' object is not subscriptable", Py_TYPE(obj)->tp_name); + return NULL; + } + key_value = __Pyx_PyIndex_AsSsize_t(index); + if (likely(key_value != -1 || !(runerr = PyErr_Occurred()))) { + return __Pyx_GetItemInt_Fast(obj, key_value, 0, 1, 1); + } + if (PyErr_GivenExceptionMatches(runerr, PyExc_OverflowError)) { + PyErr_Clear(); + PyErr_Format(PyExc_IndexError, "cannot fit '%.200s' into an index-sized integer", Py_TYPE(index)->tp_name); + } + return NULL; +} +static PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key) { + PyMappingMethods *m = Py_TYPE(obj)->tp_as_mapping; + if (likely(m && m->mp_subscript)) { + return m->mp_subscript(obj, key); + } + return __Pyx_PyObject_GetIndex(obj, key); +} +#endif + /* PyFunctionFastCall */ - #if CYTHON_FAST_PYCALL + #if CYTHON_FAST_PYCALL #include "frameobject.h" static PyObject* __Pyx_PyFunction_FastCallNoKw(PyCodeObject *co, PyObject **args, Py_ssize_t na, PyObject *globals) { @@ -12369,7 +12532,7 @@ static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, #endif /* PyCFunctionFastCall */ - #if CYTHON_FAST_PYCCALL + #if CYTHON_FAST_PYCCALL static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, PyObject **args, Py_ssize_t nargs) { PyCFunctionObject *func = (PyCFunctionObject*)func_obj; PyCFunction meth = PyCFunction_GET_FUNCTION(func); @@ -12391,95 +12554,27 @@ static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, P } #endif -/* GetItemInt */ - static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { - PyObject *r; - if (!j) return NULL; - r = PyObject_GetItem(o, j); - Py_DECREF(j); - return r; -} -static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i, - CYTHON_NCP_UNUSED int wraparound, - CYTHON_NCP_UNUSED int boundscheck) { -#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - Py_ssize_t wrapped_i = i; - if (wraparound & unlikely(i < 0)) { - wrapped_i += PyList_GET_SIZE(o); - } - if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyList_GET_SIZE(o)))) { - PyObject *r = PyList_GET_ITEM(o, wrapped_i); - Py_INCREF(r); - return r; - } - return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); -#else - return PySequence_GetItem(o, i); -#endif -} -static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i, - CYTHON_NCP_UNUSED int wraparound, - CYTHON_NCP_UNUSED int boundscheck) { -#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - Py_ssize_t wrapped_i = i; - if (wraparound & unlikely(i < 0)) { - wrapped_i += PyTuple_GET_SIZE(o); - } - if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyTuple_GET_SIZE(o)))) { - PyObject *r = PyTuple_GET_ITEM(o, wrapped_i); - Py_INCREF(r); - return r; - } - return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); -#else - return PySequence_GetItem(o, i); -#endif -} -static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, int is_list, - CYTHON_NCP_UNUSED int wraparound, - CYTHON_NCP_UNUSED int boundscheck) { -#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS && CYTHON_USE_TYPE_SLOTS - if (is_list || PyList_CheckExact(o)) { - Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyList_GET_SIZE(o); - if ((!boundscheck) || (likely((n >= 0) & (n < PyList_GET_SIZE(o))))) { - PyObject *r = PyList_GET_ITEM(o, n); - Py_INCREF(r); - return r; - } - } - else if (PyTuple_CheckExact(o)) { - Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyTuple_GET_SIZE(o); - if ((!boundscheck) || likely((n >= 0) & (n < PyTuple_GET_SIZE(o)))) { - PyObject *r = PyTuple_GET_ITEM(o, n); - Py_INCREF(r); - return r; - } - } else { - PySequenceMethods *m = Py_TYPE(o)->tp_as_sequence; - if (likely(m && m->sq_item)) { - if (wraparound && unlikely(i < 0) && likely(m->sq_length)) { - Py_ssize_t l = m->sq_length(o); - if (likely(l >= 0)) { - i += l; - } else { - if (!PyErr_ExceptionMatches(PyExc_OverflowError)) - return NULL; - PyErr_Clear(); - } - } - return m->sq_item(o, i); +/* DictGetItem */ + #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { + PyObject *value; + value = PyDict_GetItemWithError(d, key); + if (unlikely(!value)) { + if (!PyErr_Occurred()) { + PyObject* args = PyTuple_Pack(1, key); + if (likely(args)) + PyErr_SetObject(PyExc_KeyError, args); + Py_XDECREF(args); } + return NULL; } -#else - if (is_list || PySequence_Check(o)) { - return PySequence_GetItem(o, i); - } -#endif - return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); + Py_INCREF(value); + return value; } +#endif /* PyErrFetchRestore */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { PyObject *tmp_type, *tmp_value, *tmp_tb; tmp_type = tstate->curexc_type; @@ -12503,7 +12598,7 @@ static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject #endif /* RaiseException */ - #if PY_MAJOR_VERSION < 3 + #if PY_MAJOR_VERSION < 3 static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, CYTHON_UNUSED PyObject *cause) { __Pyx_PyThreadState_declare @@ -12661,26 +12756,86 @@ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject } #endif +/* PyObjectCallMethO */ + #if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { + PyObject *self, *result; + PyCFunction cfunc; + cfunc = PyCFunction_GET_FUNCTION(func); + self = PyCFunction_GET_SELF(func); + if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) + return NULL; + result = cfunc(self, arg); + Py_LeaveRecursiveCall(); + if (unlikely(!result) && unlikely(!PyErr_Occurred())) { + PyErr_SetString( + PyExc_SystemError, + "NULL result without error in PyObject_Call"); + } + return result; +} +#endif + +/* PyObjectCallOneArg */ + #if CYTHON_COMPILING_IN_CPYTHON +static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) { + PyObject *result; + PyObject *args = PyTuple_New(1); + if (unlikely(!args)) return NULL; + Py_INCREF(arg); + PyTuple_SET_ITEM(args, 0, arg); + result = __Pyx_PyObject_Call(func, args, NULL); + Py_DECREF(args); + return result; +} +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { +#if CYTHON_FAST_PYCALL + if (PyFunction_Check(func)) { + return __Pyx_PyFunction_FastCall(func, &arg, 1); + } +#endif + if (likely(PyCFunction_Check(func))) { + if (likely(PyCFunction_GET_FLAGS(func) & METH_O)) { + return __Pyx_PyObject_CallMethO(func, arg); +#if CYTHON_FAST_PYCCALL + } else if (PyCFunction_GET_FLAGS(func) & METH_FASTCALL) { + return __Pyx_PyCFunction_FastCall(func, &arg, 1); +#endif + } + } + return __Pyx__PyObject_CallOneArg(func, arg); +} +#else +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { + PyObject *result; + PyObject *args = PyTuple_Pack(1, arg); + if (unlikely(!args)) return NULL; + result = __Pyx_PyObject_Call(func, args, NULL); + Py_DECREF(args); + return result; +} +#endif + /* RaiseTooManyValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { + static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { PyErr_Format(PyExc_ValueError, "too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected); } /* RaiseNeedMoreValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { + static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { PyErr_Format(PyExc_ValueError, "need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack", index, (index == 1) ? "" : "s"); } /* RaiseNoneIterError */ - static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) { + static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); } /* SaveResetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #if PY_VERSION_HEX >= 0x030700A2 *type = tstate->exc_state.exc_type; @@ -12719,7 +12874,7 @@ static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject #endif /* PyErrExceptionMatches */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx_PyErr_ExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(tuple); @@ -12744,7 +12899,7 @@ static CYTHON_INLINE int __Pyx_PyErr_ExceptionMatchesInState(PyThreadState* tsta #endif /* GetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #else static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) { @@ -12814,7 +12969,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* Import */ - static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { + static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { PyObject *empty_list = 0; PyObject *module = 0; PyObject *global_dict = 0; @@ -12879,7 +13034,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* ImportFrom */ - static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { + static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { PyObject* value = __Pyx_PyObject_GetAttrStr(module, name); if (unlikely(!value) && PyErr_ExceptionMatches(PyExc_AttributeError)) { PyErr_Format(PyExc_ImportError, @@ -12893,18 +13048,21 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* CLineInTraceback */ - #ifndef CYTHON_CLINE_IN_TRACEBACK + #ifndef CYTHON_CLINE_IN_TRACEBACK static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_line) { PyObject *use_cline; PyObject *ptype, *pvalue, *ptraceback; #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { - use_cline = PyDict_GetItem(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); + use_cline = __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); } else #endif { @@ -12930,7 +13088,7 @@ static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_li #endif /* CodeObjectCache */ - static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { + static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { int start = 0, mid = 0, end = count - 1; if (end >= 0 && code_line > entries[end].code_line) { return count; @@ -13010,7 +13168,7 @@ static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { } /* AddTraceback */ - #include "compile.h" + #include "compile.h" #include "frameobject.h" #include "traceback.h" static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( @@ -13095,7 +13253,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13126,7 +13284,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPyVerify */ - #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ + #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) #define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) @@ -13148,7 +13306,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13179,7 +13337,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_PY_LONG_LONG(unsigned PY_LONG_LONG value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_PY_LONG_LONG(unsigned PY_LONG_LONG value) { const unsigned PY_LONG_LONG neg_one = (unsigned PY_LONG_LONG) -1, const_zero = (unsigned PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13210,7 +13368,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { return ::std::complex< float >(x, y); @@ -13230,7 +13388,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -13365,7 +13523,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { return ::std::complex< double >(x, y); @@ -13385,7 +13543,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -13520,7 +13678,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { const enum NPY_TYPES neg_one = (enum NPY_TYPES) -1, const_zero = (enum NPY_TYPES) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13551,7 +13709,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { const PY_LONG_LONG neg_one = (PY_LONG_LONG) -1, const_zero = (PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -13740,7 +13898,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { + static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -13929,7 +14087,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE unsigned PY_LONG_LONG __Pyx_PyInt_As_unsigned_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE unsigned PY_LONG_LONG __Pyx_PyInt_As_unsigned_PY_LONG_LONG(PyObject *x) { const unsigned PY_LONG_LONG neg_one = (unsigned PY_LONG_LONG) -1, const_zero = (unsigned PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14118,7 +14276,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE npy_uint32 __Pyx_PyInt_As_npy_uint32(PyObject *x) { + static CYTHON_INLINE npy_uint32 __Pyx_PyInt_As_npy_uint32(PyObject *x) { const npy_uint32 neg_one = (npy_uint32) -1, const_zero = (npy_uint32) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14307,7 +14465,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { + static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14496,7 +14654,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* FastTypeChecks */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { while (a) { a = a->tp_base; @@ -14568,7 +14726,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #endif /* CheckBinaryVersion */ - static int __Pyx_check_binary_version(void) { + static int __Pyx_check_binary_version(void) { char ctversion[4], rtversion[4]; PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION); PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion()); @@ -14584,7 +14742,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* ModuleImport */ - #ifndef __PYX_HAVE_RT_ImportModule + #ifndef __PYX_HAVE_RT_ImportModule #define __PYX_HAVE_RT_ImportModule static PyObject *__Pyx_ImportModule(const char *name) { PyObject *py_name = 0; @@ -14602,7 +14760,7 @@ static PyObject *__Pyx_ImportModule(const char *name) { #endif /* TypeImport */ - #ifndef __PYX_HAVE_RT_ImportType + #ifndef __PYX_HAVE_RT_ImportType #define __PYX_HAVE_RT_ImportType static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class_name, size_t size, int strict) @@ -14667,7 +14825,7 @@ static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class #endif /* VoidPtrImport */ - #ifndef __PYX_HAVE_RT_ImportVoidPtr + #ifndef __PYX_HAVE_RT_ImportVoidPtr #define __PYX_HAVE_RT_ImportVoidPtr static int __Pyx_ImportVoidPtr(PyObject *module, const char *name, void **p, const char *sig) { PyObject *d = 0; @@ -14716,7 +14874,7 @@ static int __Pyx_ImportVoidPtr(PyObject *module, const char *name, void **p, con #endif /* FunctionImport */ - #ifndef __PYX_HAVE_RT_ImportFunction + #ifndef __PYX_HAVE_RT_ImportFunction #define __PYX_HAVE_RT_ImportFunction static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig) { PyObject *d = 0; @@ -14770,7 +14928,7 @@ static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (** #endif /* InitStrings */ - static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { + static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { while (t->p) { #if PY_MAJOR_VERSION < 3 if (t->is_unicode) { @@ -14796,7 +14954,7 @@ static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (** if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) - PyErr_Clear(); + return -1; ++t; } return 0; @@ -15010,6 +15168,9 @@ static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_DECREF(x); return ival; } +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } diff --git a/gensim/models/doc2vec_inner.pyx b/gensim/models/doc2vec_inner.pyx index b41e8a8a3a..e0226e3dc0 100644 --- a/gensim/models/doc2vec_inner.pyx +++ b/gensim/models/doc2vec_inner.pyx @@ -2,33 +2,29 @@ # cython: boundscheck=False # cython: wraparound=False # cython: cdivision=True +# cython: embedsignature=True # coding: utf-8 # # Copyright (C) 2013 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html +"""Optimized cython functions for training :class:`~gensim.models.doc2vec.Doc2Vec` model.""" + import cython import numpy as np from numpy import zeros, float32 as REAL cimport numpy as np -from libc.math cimport exp from libc.string cimport memset, memcpy # scipy <= 0.15 try: - from scipy.linalg.blas import fblas + from scipy.linalg.blas import fblas except ImportError: - # in scipy > 0.15, fblas function has been removed - import scipy.linalg.blas as fblas - -from word2vec_inner cimport bisect_left, random_int32, \ - scopy, saxpy, sdot, dsdot, snrm2, sscal, \ - REAL_t, EXP_TABLE, \ - our_dot, our_saxpy, \ - our_dot_double, our_dot_float, our_dot_noblas, our_saxpy_noblas + # in scipy > 0.15, fblas function has been removed + import scipy.linalg.blas as fblas -from word2vec import FAST_VERSION +from word2vec_inner cimport bisect_left, random_int32, sscal, REAL_t, EXP_TABLE, our_dot, our_saxpy DEF MAX_DOCUMENT_LEN = 10000 @@ -227,6 +223,50 @@ cdef unsigned long long fast_document_dmc_neg( def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + """Update distributed bag of words model ("PV-DBOW") by training on a single document. + + Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`. + + Parameters + ---------- + model : :class:`~gensim.models.doc2vec.Doc2Vec` + The model to train. + doc_words : list of str + The input document as a list of words to be used for training. Each word will be looked up in + the model's vocabulary. + doctag_indexes : list of int + Indices into `doctag_vectors` used to obtain the tags of the document. + alpha : float + Learning rate. + work : list of float, optional + Updates to be performed on each neuron in the hidden layer of the underlying network. + train_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** `learn_words` + and `train_words` are set to True. + learn_doctags : bool, optional + Whether the tag vectors should be updated. + learn_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_hidden : bool, optional + Whether or not the weights of the hidden layer will be updated. + word_vectors : numpy.ndarray, optional + The vector representation for each word in the vocabulary. If None, these will be retrieved from the model. + word_locks : numpy.ndarray, optional + A learning lock factor for each weight in the hidden layer for words, value 0 completely blocks updates, + a value of 1 allows to update word-vectors. + doctag_vectors : numpy.ndarray, optional + Vector representations of the tags. If None, these will be retrieved from the model. + doctag_locks : numpy.ndarray, optional + The lock factors for each tag, same as `word_locks`, but for document-vectors. + + Returns + ------- + int + Number of words in the input document that were actually used for training. + + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) @@ -363,6 +403,51 @@ def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None, def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + """Update distributed memory model ("PV-DM") by training on a single document. + This method implements the DM model with a projection (input) layer that is either the sum or mean of the context + vectors, depending on the model's `dm_mean` configuration field. + + Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`. + + Parameters + ---------- + model : :class:`~gensim.models.doc2vec.Doc2Vec` + The model to train. + doc_words : list of str + The input document as a list of words to be used for training. Each word will be looked up in + the model's vocabulary. + doctag_indexes : list of int + Indices into `doctag_vectors` used to obtain the tags of the document. + alpha : float + Learning rate. + work : np.ndarray, optional + Private working memory for each worker. + neu1 : np.ndarray, optional + Private working memory for each worker. + learn_doctags : bool, optional + Whether the tag vectors should be updated. + learn_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_hidden : bool, optional + Whether or not the weights of the hidden layer will be updated. + word_vectors : numpy.ndarray, optional + The vector representation for each word in the vocabulary. If None, these will be retrieved from the model. + word_locks : numpy.ndarray, optional + A learning lock factor for each weight in the hidden layer for words, value 0 completely blocks updates, + a value of 1 allows to update word-vectors. + doctag_vectors : numpy.ndarray, optional + Vector representations of the tags. If None, these will be retrieved from the model. + doctag_locks : numpy.ndarray, optional + The lock factors for each tag, same as `word_locks`, but for document-vectors. + + Returns + ------- + int + Number of words in the input document that were actually used for training. + + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) @@ -521,6 +606,51 @@ def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=N def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None, neu1=None, learn_doctags=True, learn_words=True, learn_hidden=True, word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None): + """Update distributed memory model ("PV-DM") by training on a single document, using a concatenation of the context + window word vectors (rather than a sum or average). + This might be slower since the input at each batch will be significantly larger. + + Called internally from :meth:`~gensim.models.doc2vec.Doc2Vec.train` and + :meth:`~gensim.models.doc2vec.Doc2Vec.infer_vector`. + + Parameters + ---------- + model : :class:`~gensim.models.doc2vec.Doc2Vec` + The model to train. + doc_words : list of str + The input document as a list of words to be used for training. Each word will be looked up in + the model's vocabulary. + doctag_indexes : list of int + Indices into `doctag_vectors` used to obtain the tags of the document. + alpha : float, optional + Learning rate. + work : np.ndarray, optional + Private working memory for each worker. + neu1 : np.ndarray, optional + Private working memory for each worker. + learn_doctags : bool, optional + Whether the tag vectors should be updated. + learn_words : bool, optional + Word vectors will be updated exactly as per Word2Vec skip-gram training only if **both** + `learn_words` and `train_words` are set to True. + learn_hidden : bool, optional + Whether or not the weights of the hidden layer will be updated. + word_vectors : numpy.ndarray, optional + The vector representation for each word in the vocabulary. If None, these will be retrieved from the model. + word_locks : numpy.ndarray, optional + A learning lock factor for each weight in the hidden layer for words, value 0 completely blocks updates, + a value of 1 allows to update word-vectors. + doctag_vectors : numpy.ndarray, optional + Vector representations of the tags. If None, these will be retrieved from the model. + doctag_locks : numpy.ndarray, optional + The lock factors for each tag, same as `word_locks`, but for document-vectors. + + Returns + ------- + int + Number of words in the input document that were actually used for training. + + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index 46e68b44ec..e9c3dda239 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -5,26 +5,72 @@ # Copyright (C) 2018 RaRe Technologies s.r.o. # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""Learn word representations via fasttext's "skip-gram and CBOW models", using either -hierarchical softmax or negative sampling [1]_. +"""Learn word representations via Fasttext: `Enriching Word Vectors with Subword Information +`_. -Notes ------ -There are more ways to get word vectors in Gensim than just FastText. -See wrappers for VarEmbed and WordRank or Word2Vec +This module allows training word embeddings from a training corpus with the additional ability to obtain word vectors +for out-of-vocabulary words. -This module allows training a word embedding from a training corpus with the additional ability -to obtain word vectors for out-of-vocabulary words. +This module contains a fast native C implementation of Fasttext with Python interfaces. It is **not** only a wrapper +around Facebook's implementation. +For a tutorial see `this noteboook +`_. -For a tutorial on gensim's native fasttext, refer to the noteboook -- [2]_ +**Make sure you have a C compiler before installing Gensim, to use the optimized (compiled) Fasttext +training routines.** -**Make sure you have a C compiler before installing gensim, to use optimized (compiled) fasttext training** +Usage examples +-------------- -.. [1] P. Bojanowski, E. Grave, A. Joulin, T. Mikolov - Enriching Word Vectors with Subword Information. In arXiv preprint arXiv:1607.04606. - https://arxiv.org/abs/1607.04606 +Initialize and train a model -.. [2] https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/FastText_Tutorial.ipynb +>>> from gensim.test.utils import common_texts +>>> from gensim.models import FastText +>>> +>>> model = FastText(common_texts, size=4, window=3, min_count=1, iter=10) + +Persist a model to disk with + +>>> from gensim.test.utils import get_tmpfile +>>> +>>> fname = get_tmpfile("fasttext.model") +>>> +>>> model.save(fname) +>>> model = FastText.load(fname) # you can continue training with the loaded model! + +Retrieve word-vector for vocab and out-of-vocab word + +>>> existent_word = "computer" +>>> existent_word in model.wv.vocab +True +>>> computer_vec = model.wv[existent_word] # numpy vector of a word +>>> +>>> oov_word = "graph-out-of-vocab" +>>> oov_word in model.wv.vocab +False +>>> oov_vec = model.wv[oov_word] # numpy vector for OOV word + +You can perform various NLP word tasks with the model, some of them are already built-in + +>>> similarities = model.wv.most_similar(positive=['computer', 'human'], negative=['interface']) +>>> most_similar = similarities[0] +>>> +>>> similarities = model.wv.most_similar_cosmul(positive=['computer', 'human'], negative=['interface']) +>>> most_similar = similarities[0] +>>> +>>> not_matching = model.wv.doesnt_match("human computer interface tree".split()) +>>> +>>> sim_score = model.wv.similarity('computer', 'human') + +Correlation with human opinion on word similarity + +>>> from gensim.test.utils import datapath +>>> +>>> similarities = model.wv.evaluate_word_pairs(datapath('wordsim353.tsv')) + +And on word analogies + +>>> analogies_result = model.wv.accuracy(datapath('questions-words.txt')) """ @@ -55,26 +101,31 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None): """Update CBOW model by training on a sequence of sentences. - Each sentence is a list of string tokens, which are looked up in the model's - vocab dictionary. Called internally from :meth:`gensim.models.fasttext.FastText.train()`. - This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from fasttext_inner instead. + + Called internally from :meth:`~gensim.models.fasttext.FastText.train`. + + Notes + ----- + This is the non-optimized, Python version. If you have cython installed, gensim will use the optimized version + from :mod:`gensim.models.fasttext_inner` instead. + Parameters ---------- model : :class:`~gensim.models.fasttext.FastText` - `FastText` instance. - sentences : iterable of iterables - Iterable of the sentences directly from disk/network. + Model instance. + sentences : iterable of list of str + Iterable of the sentences. alpha : float Learning rate. - work : :class:`numpy.ndarray` - Private working memory for each worker. - neu1 : :class:`numpy.ndarray` - Private working memory for each worker. + work : :class:`numpy.ndarray`, optional + UNUSED. + neu1 : :class:`numpy.ndarray`, optional + UNUSED. Returns ------- int Effective number of words trained. + """ result = 0 for sentence in sentences: @@ -108,26 +159,32 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None): def train_batch_sg(model, sentences, alpha, work=None, neu1=None): """Update skip-gram model by training on a sequence of sentences. - Each sentence is a list of string tokens, which are looked up in the model's - vocab dictionary. Called internally from :meth:`gensim.models.fasttext.FastText.train()`. - This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from fasttext_inner instead. + + Called internally from :meth:`~gensim.models.fasttext.FastText.train`. + + Notes + ----- + This is the non-optimized, Python version. If you have cython installed, gensim will use the optimized version + from :mod:`gensim.models.fasttext_inner` instead. + Parameters ---------- model : :class:`~gensim.models.fasttext.FastText` `FastText` instance. - sentences : iterable of iterables + sentences : iterable of list of str Iterable of the sentences directly from disk/network. alpha : float Learning rate. - work : :class:`numpy.ndarray` - Private working memory for each worker. - neu1 : :class:`numpy.ndarray` - Private working memory for each worker. + work : :class:`numpy.ndarray`, optional + UNUSED. + neu1 : :class:`numpy.ndarray`, optional + UNUSED. + Returns ------- int Effective number of words trained. + """ result = 0 for sentence in sentences: @@ -152,109 +209,137 @@ def train_batch_sg(model, sentences, alpha, work=None, neu1=None): class FastText(BaseWordEmbeddingsModel): - """Class for training, using and evaluating word representations learned using method - described in [1]_ aka Fasttext. - - The model can be stored/loaded via its :meth:`~gensim.models.fasttext.FastText.save()` and - :meth:`~gensim.models.fasttext.FastText.load()` methods, or loaded in a format compatible with the original - fasttext implementation via :meth:`~gensim.models.fasttext.FastText.load_fasttext_format()`. + """Train, use and evaluate word representations learned using the method + described in `Enriching Word Vectors with Subword Information `_, aka FastText. + + The model can be stored/loaded via its :meth:`~gensim.models.fasttext.FastText.save` and + :meth:`~gensim.models.fasttext.FastText.load` methods, or loaded from a format compatible with the original + Fasttext implementation via :meth:`~gensim.models.fasttext.FastText.load_fasttext_format`. + + Some important internal attributes are the following: + + Attributes + ---------- + wv : :class:`~gensim.models.keyedvectors.FastTextKeyedVectors` + This object essentially contains the mapping between words and embeddings. These are similar to the embeddings + computed in the :class:`~gensim.models.word2vec.Word2Vec`, however here we also include vectors for n-grams. + This allows the model to compute embeddings even for **unseen** words (that do not exist in the vocabulary), + as the aggregate of the n-grams included in the word. After training the model, this attribute can be used + directly to query those embeddings in various ways. Check the module level docstring from some examples. + vocabulary : :class:`~gensim.models.fasttext.FastTextVocab` + This object represents the vocabulary of the model. + Besides keeping track of all unique words, this object provides extra functionality, such as + constructing a huffman tree (frequent words are closer to the root), or discarding extremely rare words. + trainables : :class:`~gensim.models.fasttext.FastTextTrainables` + This object represents the inner shallow neural network used to train the embeddings. This is very + similar to the network of the :class:`~gensim.models.word2vec.Word2Vec` model, but it also trains weights + for the N-Grams (sequences of more than 1 words). The semantics of the network are almost the same as + the one used for the :class:`~gensim.models.word2vec.Word2Vec` model. + You can think of it as a NN with a single projection and hidden layer which we train on the corpus. + The weights are then used as our embeddings. An important difference however between the two models, is the + scoring function used to compute the loss. In the case of FastText, this is modified in word to also account + for the internal structure of words, besides their concurrence counts. """ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, word_ngrams=1, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, negative=5, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, min_n=3, max_n=6, sorted_vocab=1, bucket=2000000, trim_rule=None, batch_words=MAX_WORDS_IN_BATCH, callbacks=()): - """Initialize the model from an iterable of `sentences`. Each sentence is a - list of words (unicode strings) that will be used for training. + """ Parameters ---------- - sentences : iterable of iterables - The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, + sentences : iterable of list of str, optional + Can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. If you don't supply `sentences`, the model is left uninitialized -- use if you plan to initialize it in some other way. - sg : int {1, 0} - Defines the training algorithm. If 1, skip-gram is used, otherwise, CBOW is employed. - size : int - Dimensionality of the feature vectors. - window : int + min_count : int, optional + The model ignores all words with total frequency lower than this. + size : int, optional + Dimensionality of the word vectors. + window : int, optional The maximum distance between the current and predicted word within a sentence. - alpha : float + workers : int, optional + Use these many worker threads to train the model (=faster training with multicore machines). + alpha : float, optional The initial learning rate. - min_alpha : float + min_alpha : float, optional Learning rate will linearly drop to `min_alpha` as training progresses. - seed : int + sg : {1, 0}, optional + Training algorithm: skip-gram if `sg=1`, otherwise CBOW. + hs : {1,0}, optional + If 1, hierarchical softmax will be used for model training. + If set to 0, and `negative` is non-zero, negative sampling will be used. + seed : int, optional Seed for the random number generator. Initial vectors for each word are seeded with a hash of the concatenation of word + `str(seed)`. Note that for a fully deterministically-reproducible run, you must also limit the model to a single worker thread (`workers=1`), to eliminate ordering jitter from OS thread scheduling. (In Python 3, reproducibility between interpreter launches also requires use of the `PYTHONHASHSEED` environment variable to control hash randomization). - min_count : int - Ignores all words with total frequency lower than this. - max_vocab_size : int + max_vocab_size : int, optional Limits the RAM during vocabulary building; if there are more unique words than this, then prune the infrequent ones. Every 10 million word types need about 1GB of RAM. Set to `None` for no limit. - sample : float + sample : float, optional The threshold for configuring which higher-frequency words are randomly downsampled, useful range is (0, 1e-5). - workers : int - Use these many worker threads to train the model (=faster training with multicore machines). - hs : int {1,0} - If 1, hierarchical softmax will be used for model training. - If set to 0, and `negative` is non-zero, negative sampling will be used. - negative : int + negative : int, optional If > 0, negative sampling will be used, the int for negative specifies how many "noise words" should be drawn (usually between 5-20). If set to 0, no negative sampling is used. - cbow_mean : int {1,0} + cbow_mean : {1,0}, optional If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used. - hashfxn : function + hashfxn : function, optional Hash function to use to randomly initialize weights, for increased training reproducibility. - iter : int + iter : int, optional Number of iterations (epochs) over the corpus. - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part - of the model. - sorted_vocab : int {1,0} - If 1, sort the vocabulary by descending frequency before assigning word indexes. - batch_words : int + The rule, if given, is only used to prune vocabulary during + :meth:`~gensim.models.fasttext.FastText.build_vocab` and is not stored as part of themodel. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + sorted_vocab : {1,0}, optional + If 1, sort the vocabulary by descending frequency before assigning word indices. + batch_words : int, optional Target size (in words) for batches of examples passed to worker threads (and thus cython routines).(Larger batches will be passed if individual texts are longer than 10000 words, but the standard cython code truncates to that maximum.) - min_n : int - Min length of char ngrams to be used for training word representations. - max_n : int + min_n : int, optional + Minimum length of char n-grams to be used for training word representations. + max_n : int, optional Max length of char ngrams to be used for training word representations. Set `max_n` to be lesser than `min_n` to avoid char ngrams being used. - word_ngrams : int {1,0} - If 1, uses enriches word vectors with subword(ngrams) information. - If 0, this is equivalent to word2vec. - bucket : int + word_ngrams : {1,0}, optional + If 1, uses enriches word vectors with subword(n-grams) information. + If 0, this is equivalent to :class:`~gensim.models.word2vec.Word2Vec`. + bucket : int, optional Character ngrams are hashed into a fixed number of buckets, in order to limit the memory usage of the model. This option specifies the number of buckets used by the model. - callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec` + callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec`, optional List of callbacks that need to be executed/run at specific stages during training. Examples -------- - Initialize and train a `FastText` model + Initialize and train a `FastText` model:: >>> from gensim.models import FastText >>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]] >>> >>> model = FastText(sentences, min_count=1) - >>> say_vector = model['say'] # get vector for word - >>> of_vector = model['of'] # get vector for out-of-vocab word - + >>> say_vector = model['say'] # get vector for a word + >>> of_vector = model['of'] # get vector for an out-of-vocab word """ self.load = call_on_class_only @@ -333,28 +418,37 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca Parameters ---------- - sentences : iterable of iterables - The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, + sentences : iterable of list of str + Can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. + update : bool + If true, the new words in `sentences` will be added to model's vocab. + progress_per : int + Indicates how many words to process before showing/updating the progress. keep_raw_vocab : bool If not true, delete the raw vocabulary after the scaling is done and free up RAM. - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part - of the model. - progress_per : int - Indicates how many words to process before showing/updating the progress. - update : bool - If true, the new words in `sentences` will be added to model's vocab. + The rule, if given, is only used to prune vocabulary during + :meth:`~gensim.models.fasttext.FastText.build_vocab` and is not stored as part of the model. - Example - ------- + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + **kwargs + Additional key word parameters passed to + :meth:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.build_vocab`. + + Examples + -------- Train a model and update vocab for online training >>> from gensim.models import FastText @@ -364,6 +458,7 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca >>> model = FastText(min_count=1) >>> model.build_vocab(sentences_1) >>> model.train(sentences_1, total_examples=model.corpus_count, epochs=model.iter) + >>> >>> model.build_vocab(sentences_2, update=True) >>> model.train(sentences_2, total_examples=model.corpus_count, epochs=model.iter) @@ -385,6 +480,7 @@ def _set_train_params(self, **kwargs): pass def _clear_post_train(self): + """Clear the model's internal structures after training has finished to free up RAM.""" self.wv.vectors_norm = None self.wv.vectors_vocab_norm = None self.wv.vectors_ngrams_norm = None @@ -432,14 +528,14 @@ def _do_train_job(self, sentences, alpha, inits): Parameters ---------- - sentences : iterable of iterables - The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, + sentences : iterable of list of str + Can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. alpha : float The current learning rate. - inits : (:class:`numpy.ndarray`, :class:`numpy.ndarray`) + inits : tuple of (:class:`numpy.ndarray`, :class:`numpy.ndarray`) Each worker's private work memory. Returns @@ -463,16 +559,15 @@ def train(self, sentences, total_examples=None, total_words=None, """Update the model's neural weights from a sequence of sentences (can be a once-only generator stream). For FastText, each sentence must be a list of unicode strings. - To support linear learning-rate decay from (initial) alpha to min_alpha, and accurate - progress-percentage logging, either total_examples (count of sentences) or total_words (count of - raw words in sentences) **MUST** be provided (if the corpus is the same as was provided to - :meth:`~gensim.models.fasttext.FastText.build_vocab()`, the count of examples in that corpus - will be available in the model's :attr:`corpus_count` property). + To support linear learning-rate decay from (initial) `alpha` to `min_alpha`, and accurate + progress-percentage logging, either `total_examples` (count of sentences) or `total_words` (count of + raw words in sentences) **MUST** be provided. If `sentences` is the same corpus + that was provided to :meth:`~gensim.models.fasttext.FastText.build_vocab` earlier, + you can simply use `total_examples=self.corpus_count`. To avoid common mistakes around the model's ability to do multiple training passes itself, an - explicit `epochs` argument **MUST** be provided. In the common and recommended case, - where :meth:`~gensim.models.fasttext.FastText.train()` is only called once, - the model's cached `iter` value should be supplied as `epochs` value. + explicit `epochs` argument **MUST** be provided. In the common and recommended case + where :meth:`~gensim.models.fasttext.FastText.train` is only called once, you can set `epochs=self.iter`. Parameters ---------- @@ -487,10 +582,17 @@ def train(self, sentences, total_examples=None, total_words=None, Count of raw words in sentences. epochs : int Number of iterations (epochs) over the corpus. - start_alpha : float - Initial learning rate. - end_alpha : float + start_alpha : float, optional + Initial learning rate. If supplied, replaces the starting `alpha` from the constructor, + for this one call to :meth:`~gensim.models.fasttext.FastText.train`. + Use only if making multiple calls to :meth:`~gensim.models.fasttext.FastText.train`, when you want to manage + the alpha learning-rate yourself (not recommended). + end_alpha : float, optional Final learning rate. Drops linearly from `start_alpha`. + If supplied, this replaces the final `min_alpha` from the constructor, for this one call to + :meth:`~gensim.models.fasttext.FastText.train`. + Use only if making multiple calls to :meth:`~gensim.models.fasttext.FastText.train`, when you want to manage + the alpha learning-rate yourself (not recommended). word_count : int Count of words already trained. Set this to 0 for the usual case of training on all words in sentences. @@ -511,7 +613,6 @@ def train(self, sentences, total_examples=None, total_words=None, >>> model.train(sentences, total_examples=model.corpus_count, epochs=model.iter) """ - super(FastText, self).train( sentences, total_examples=total_examples, total_words=total_words, epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, @@ -520,44 +621,54 @@ def train(self, sentences, total_examples=None, total_words=None, def init_sims(self, replace=False): """ - init_sims() resides in KeyedVectors because it deals with syn0 mainly, but because syn1 is not an attribute - of KeyedVectors, it has to be deleted in this class, and the normalizing of syn0 happens inside of KeyedVectors + Precompute L2-normalized vectors. + + Parameters + ---------- + replace : bool + If True, forget the original vectors and only keep the normalized ones to save RAM. + """ + # init_sims() resides in KeyedVectors because it deals with input layer mainly, but because the + # hidden layer is not an attribute of KeyedVectors, it has to be deleted in this class. + # The normalizing of input layer happens inside of KeyedVectors. if replace and hasattr(self.trainables, 'syn1'): del self.trainables.syn1 - return self.wv.init_sims(replace) + self.wv.init_sims(replace) def clear_sims(self): - """ - Removes all L2-normalized vectors for words from the model. - You will have to recompute them using init_sims method. - """ + """Remove all L2-normalized word vectors from the model, to free up memory. + You can recompute them later again using the :meth:`~gensim.models.fasttext.FastText.init_sims` method. + + """ self._clear_post_train() @deprecated("Method will be removed in 4.0.0, use self.wv.__getitem__() instead") def __getitem__(self, words): - """ - Deprecated. Use self.wv.__getitem__() instead. - Refer to the documentation for `gensim.models.KeyedVectors.__getitem__` + """Deprecated. Use self.wv.__getitem__() instead. + + Refer to the documentation for :meth:`gensim.models.keyedvectors.KeyedVectors.__getitem__` + """ return self.wv.__getitem__(words) @deprecated("Method will be removed in 4.0.0, use self.wv.__contains__() instead") def __contains__(self, word): - """ - Deprecated. Use self.wv.__contains__() instead. - Refer to the documentation for `gensim.models.KeyedVectors.__contains__` + """Deprecated. Use self.wv.__contains__() instead. + + Refer to the documentation for :meth:`gensim.models.keyedvectors.KeyedVectors.__contains__` + """ return self.wv.__contains__(word) @classmethod def load_fasttext_format(cls, model_file, encoding='utf8'): - """ - Load the input-hidden weight matrix from the fast text output files. + """Load the input-hidden weight matrix from Facebook's native fasttext `.bin` and `.vec` output files. - Note that due to limitations in the FastText API, you cannot continue training - with a model loaded this way, though you can query for word similarity etc. + Notes + ------ + Due to limitations in the FastText API, you cannot continue training with a model loaded this way. Parameters ---------- @@ -565,14 +676,14 @@ def load_fasttext_format(cls, model_file, encoding='utf8'): Path to the FastText output files. FastText outputs two model files - `/path/to/model.vec` and `/path/to/model.bin` Expected value for this example: `/path/to/model` or `/path/to/model.bin`, - as gensim requires only `.bin` file to load entire fastText model. - encoding : str - Specifies the encoding. + as Gensim requires only `.bin` file to the load entire fastText model. + encoding : str, optional + Specifies the file encoding. Returns ------- - :obj: `~gensim.models.fasttext.FastText` - Returns the loaded model as an instance of :class: `~gensim.models.fasttext.FastText`. + :class: `~gensim.models.fasttext.FastText` + The loaded model. """ model = cls() @@ -583,13 +694,28 @@ def load_fasttext_format(cls, model_file, encoding='utf8'): return model def load_binary_data(self, encoding='utf8'): - """Loads data from the output binary file created by FastText training""" + """Load data from a binary file created by Facebook's native FastText. + + Parameters + ---------- + encoding : str, optional + Specifies the encoding. + + """ with utils.smart_open(self.file_name, 'rb') as f: self._load_model_params(f) self._load_dict(f, encoding=encoding) self._load_vectors(f) def _load_model_params(self, file_handle): + """Load model parameters from Facebook's native fasttext file. + + Parameters + ---------- + file_handle : file-like object + Handle to an open file. + + """ magic, version = self.struct_unpack(file_handle, '@2i') if magic == FASTTEXT_FILEFORMAT_MAGIC: # newer format self.new_format = True @@ -616,6 +742,16 @@ def _load_model_params(self, file_handle): self.vocabulary.sample = t def _load_dict(self, file_handle, encoding='utf8'): + """Load a previously saved dictionary from disk, stored in Facebook's native fasttext format. + + Parameters + ---------- + file_handle : file-like object + The opened file handle to the persisted dictionary. + encoding : str + Specifies the encoding. + + """ vocab_size, nwords, nlabels = self.struct_unpack(file_handle, '@3i') # Vocab stored by [Dictionary::save](https://github.com/facebookresearch/fastText/blob/master/src/dictionary.cc) if nlabels > 0: @@ -653,6 +789,14 @@ def _load_dict(self, file_handle, encoding='utf8'): self.struct_unpack(file_handle, '@2i') def _load_vectors(self, file_handle): + """Load word vectors stored in Facebook's native fasttext format from disk. + + Parameters + ---------- + file_handle : file-like object + Open file handle to persisted vectors. + + """ if self.new_format: self.struct_unpack(file_handle, '@?') # bool quant_input in fasttext.cc num_vectors, dim = self.struct_unpack(file_handle, '@2q') @@ -681,17 +825,38 @@ def _load_vectors(self, file_handle): self._clear_post_train() def struct_unpack(self, file_handle, fmt): + """Read a single object from an open file. + + Parameters + ---------- + file_handle : file_like object + Handle to an open file + fmt : str + Byte format in which the structure is saved. + + Returns + ------- + Tuple of (str) + Unpacked structure. + + """ num_bytes = struct.calcsize(fmt) return struct.unpack(fmt, file_handle.read(num_bytes)) def save(self, *args, **kwargs): - """Save the model. This saved model can be loaded again using :func:`~gensim.models.fasttext.FastText.load`, - which supports online training and getting vectors for out-of-vocabulary words. + """Save the Fasttext model. This saved model can be loaded again using + :meth:`~gensim.models.fasttext.FastText.load`, which supports incremental training + and getting vectors for out-of-vocabulary words. Parameters ---------- fname : str - Path to the file. + Store the model to this file. + + See Also + -------- + :meth:`~gensim.models.fasttext.FastText.load` + Load :class:`~gensim.models.fasttext.FastText` model. """ kwargs['ignore'] = kwargs.get( @@ -700,7 +865,7 @@ def save(self, *args, **kwargs): @classmethod def load(cls, *args, **kwargs): - """Loads a previously saved `FastText` model. Also see `save()`. + """Load a previously saved `FastText` model. Parameters ---------- @@ -709,8 +874,14 @@ def load(cls, *args, **kwargs): Returns ------- - :obj: `~gensim.models.fasttext.FastText` - Returns the loaded model as an instance of :class: `~gensim.models.fasttext.FastText`. + :class:`~gensim.models.fasttext.FastText` + Loaded model. + + See Also + -------- + :meth:`~gensim.models.fasttext.FastText.save` + Save :class:`~gensim.models.fasttext.FastText` model. + """ try: model = super(FastText, cls).load(*args, **kwargs) @@ -731,6 +902,7 @@ def accuracy(self, questions, restrict_vocab=30000, most_similar=None, case_inse class FastTextVocab(Word2VecVocab): + """Vocabulary used by :class:`~gensim.models.fasttext.FastText`.""" def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0): super(FastTextVocab, self).__init__( max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, @@ -745,6 +917,7 @@ def prepare_vocab(self, hs, negative, wv, update=False, keep_raw_vocab=False, tr class FastTextTrainables(Word2VecTrainables): + """Represents the inner shallow neural network used to train :class:`~gensim.models.fasttext.FastText`.""" def __init__(self, vector_size=100, seed=1, hashfxn=hash, bucket=2000000): super(FastTextTrainables, self).__init__( vector_size=vector_size, seed=seed, hashfxn=hashfxn) @@ -855,8 +1028,8 @@ def get_vocab_word_vecs(self, wv): wv.vectors[v.index] = word_vec def init_ngrams_post_load(self, file_name, wv): - """ - Computes ngrams of all words present in vocabulary and stores vectors for only those ngrams. + """Compute ngrams of all words present in vocabulary, and store vectors for only those ngrams. + Vectors for other ngrams are initialized with a random uniform distribution in FastText. These vectors are discarded here to save space. diff --git a/gensim/models/fasttext_inner.c b/gensim/models/fasttext_inner.c index b879df5a61..5a13de4924 100644 --- a/gensim/models/fasttext_inner.c +++ b/gensim/models/fasttext_inner.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.27.3 */ +/* Generated by Cython 0.28.3 */ #define PY_SSIZE_T_CLEAN #include "Python.h" @@ -7,7 +7,7 @@ #elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.6+ or Python 3.3+. #else -#define CYTHON_ABI "0_27_3" +#define CYTHON_ABI "0_28_3" #define CYTHON_FUTURE_DIVISION 0 #include #ifndef offsetof @@ -183,6 +183,103 @@ #undef BASE #undef MASK #endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) #define Py_OptimizeFlag 0 #endif @@ -211,12 +308,12 @@ #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif -#if PY_VERSION_HEX < 0x030700A0 || !defined(METH_FASTCALL) +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif - typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject **args, Py_ssize_t nargs); - typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject **args, + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast @@ -228,6 +325,18 @@ #else #define __Pyx_PyFastCFunction_Check(func) 0 #endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif #if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x03060000 @@ -237,6 +346,36 @@ #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; // PyThread_create_key reports success always +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif // TSS (Thread Specific Storage) API #if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else @@ -249,6 +388,11 @@ #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif #if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ @@ -293,18 +437,6 @@ #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif -#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) - #define PyObject_Malloc(s) PyMem_Malloc(s) - #define PyObject_Free(p) PyMem_Free(p) - #define PyObject_Realloc(p) PyMem_Realloc(p) -#endif -#if CYTHON_COMPILING_IN_PYSTON - #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) -#else - #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) -#endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 @@ -321,6 +453,7 @@ #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact + #define PyObject_Unicode PyObject_Str #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) @@ -332,7 +465,11 @@ #ifndef PySet_CheckExact #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) #endif -#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type @@ -367,16 +504,10 @@ #define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t #endif #if PY_MAJOR_VERSION >= 3 - #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func)) + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : (Py_INCREF(func), func)) #else #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) #endif -#ifndef __has_attribute - #define __has_attribute(x) 0 -#endif -#ifndef __has_cpp_attribute - #define __has_cpp_attribute(x) 0 -#endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods @@ -394,96 +525,6 @@ unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif -#ifndef CYTHON_RESTRICT - #if defined(__GNUC__) - #define CYTHON_RESTRICT __restrict__ - #elif defined(_MSC_VER) && _MSC_VER >= 1400 - #define CYTHON_RESTRICT __restrict - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_RESTRICT restrict - #else - #define CYTHON_RESTRICT - #endif -#endif -#ifndef CYTHON_UNUSED -# if defined(__GNUC__) -# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -#endif -#ifndef CYTHON_MAYBE_UNUSED_VAR -# if defined(__cplusplus) - template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } -# else -# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) -# endif -#endif -#ifndef CYTHON_NCP_UNUSED -# if CYTHON_COMPILING_IN_CPYTHON -# define CYTHON_NCP_UNUSED -# else -# define CYTHON_NCP_UNUSED CYTHON_UNUSED -# endif -#endif -#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) -#ifdef _MSC_VER - #ifndef _MSC_STDINT_H_ - #if _MSC_VER < 1300 - typedef unsigned char uint8_t; - typedef unsigned int uint32_t; - #else - typedef unsigned __int8 uint8_t; - typedef unsigned __int32 uint32_t; - #endif - #endif -#else - #include -#endif -#ifndef CYTHON_FALLTHROUGH - #if defined(__cplusplus) && __cplusplus >= 201103L - #if __has_cpp_attribute(fallthrough) - #define CYTHON_FALLTHROUGH [[fallthrough]] - #elif __has_cpp_attribute(clang::fallthrough) - #define CYTHON_FALLTHROUGH [[clang::fallthrough]] - #elif __has_cpp_attribute(gnu::fallthrough) - #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] - #endif - #endif - #ifndef CYTHON_FALLTHROUGH - #if __has_attribute(fallthrough) - #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) - #else - #define CYTHON_FALLTHROUGH - #endif - #endif - #if defined(__clang__ ) && defined(__apple_build_version__) - #if __apple_build_version__ < 7000000 - #undef CYTHON_FALLTHROUGH - #define CYTHON_FALLTHROUGH - #endif - #endif -#endif - -#ifndef CYTHON_INLINE - #if defined(__clang__) - #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) - #elif defined(__GNUC__) - #define CYTHON_INLINE __inline__ - #elif defined(_MSC_VER) - #define CYTHON_INLINE __inline - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_INLINE inline - #else - #define CYTHON_INLINE - #endif -#endif #if defined(WIN32) || defined(MS_WINDOWS) #define _USE_MATH_DEFINES @@ -520,6 +561,7 @@ static CYTHON_INLINE float __PYX_NAN() { #define __PYX_HAVE__gensim__models__fasttext_inner #define __PYX_HAVE_API__gensim__models__fasttext_inner +/* Early includes */ #include #include #include "numpy/arrayobject.h" @@ -610,7 +652,7 @@ static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) -#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False)) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ @@ -718,7 +760,7 @@ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } static PyObject *__pyx_m = NULL; static PyObject *__pyx_d; static PyObject *__pyx_b; -static PyObject *__pyx_cython_runtime; +static PyObject *__pyx_cython_runtime = NULL; static PyObject *__pyx_empty_tuple; static PyObject *__pyx_empty_bytes; static PyObject *__pyx_empty_unicode; @@ -768,7 +810,7 @@ static const char *__pyx_f[] = { #endif -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":743 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":730 * # in Cython to enable them only on the right systems. * * ctypedef npy_int8 int8_t # <<<<<<<<<<<<<< @@ -777,7 +819,7 @@ static const char *__pyx_f[] = { */ typedef npy_int8 __pyx_t_5numpy_int8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":731 * * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t # <<<<<<<<<<<<<< @@ -786,7 +828,7 @@ typedef npy_int8 __pyx_t_5numpy_int8_t; */ typedef npy_int16 __pyx_t_5numpy_int16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":732 * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t # <<<<<<<<<<<<<< @@ -795,7 +837,7 @@ typedef npy_int16 __pyx_t_5numpy_int16_t; */ typedef npy_int32 __pyx_t_5numpy_int32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":746 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":733 * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t * ctypedef npy_int64 int64_t # <<<<<<<<<<<<<< @@ -804,7 +846,7 @@ typedef npy_int32 __pyx_t_5numpy_int32_t; */ typedef npy_int64 __pyx_t_5numpy_int64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":750 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":737 * #ctypedef npy_int128 int128_t * * ctypedef npy_uint8 uint8_t # <<<<<<<<<<<<<< @@ -813,7 +855,7 @@ typedef npy_int64 __pyx_t_5numpy_int64_t; */ typedef npy_uint8 __pyx_t_5numpy_uint8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":751 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":738 * * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t # <<<<<<<<<<<<<< @@ -822,7 +864,7 @@ typedef npy_uint8 __pyx_t_5numpy_uint8_t; */ typedef npy_uint16 __pyx_t_5numpy_uint16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":752 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":739 * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t # <<<<<<<<<<<<<< @@ -831,7 +873,7 @@ typedef npy_uint16 __pyx_t_5numpy_uint16_t; */ typedef npy_uint32 __pyx_t_5numpy_uint32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":753 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":740 * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t * ctypedef npy_uint64 uint64_t # <<<<<<<<<<<<<< @@ -840,7 +882,7 @@ typedef npy_uint32 __pyx_t_5numpy_uint32_t; */ typedef npy_uint64 __pyx_t_5numpy_uint64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":757 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 * #ctypedef npy_uint128 uint128_t * * ctypedef npy_float32 float32_t # <<<<<<<<<<<<<< @@ -849,7 +891,7 @@ typedef npy_uint64 __pyx_t_5numpy_uint64_t; */ typedef npy_float32 __pyx_t_5numpy_float32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 * * ctypedef npy_float32 float32_t * ctypedef npy_float64 float64_t # <<<<<<<<<<<<<< @@ -858,7 +900,7 @@ typedef npy_float32 __pyx_t_5numpy_float32_t; */ typedef npy_float64 __pyx_t_5numpy_float64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":754 * # The int types are mapped a bit surprising -- * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t # <<<<<<<<<<<<<< @@ -867,7 +909,7 @@ typedef npy_float64 __pyx_t_5numpy_float64_t; */ typedef npy_long __pyx_t_5numpy_int_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":768 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":755 * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t * ctypedef npy_longlong long_t # <<<<<<<<<<<<<< @@ -876,7 +918,7 @@ typedef npy_long __pyx_t_5numpy_int_t; */ typedef npy_longlong __pyx_t_5numpy_long_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":756 * ctypedef npy_long int_t * ctypedef npy_longlong long_t * ctypedef npy_longlong longlong_t # <<<<<<<<<<<<<< @@ -885,7 +927,7 @@ typedef npy_longlong __pyx_t_5numpy_long_t; */ typedef npy_longlong __pyx_t_5numpy_longlong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 * ctypedef npy_longlong longlong_t * * ctypedef npy_ulong uint_t # <<<<<<<<<<<<<< @@ -894,7 +936,7 @@ typedef npy_longlong __pyx_t_5numpy_longlong_t; */ typedef npy_ulong __pyx_t_5numpy_uint_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":772 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":759 * * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t # <<<<<<<<<<<<<< @@ -903,7 +945,7 @@ typedef npy_ulong __pyx_t_5numpy_uint_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":760 * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t * ctypedef npy_ulonglong ulonglong_t # <<<<<<<<<<<<<< @@ -912,7 +954,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":762 * ctypedef npy_ulonglong ulonglong_t * * ctypedef npy_intp intp_t # <<<<<<<<<<<<<< @@ -921,7 +963,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; */ typedef npy_intp __pyx_t_5numpy_intp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":763 * * ctypedef npy_intp intp_t * ctypedef npy_uintp uintp_t # <<<<<<<<<<<<<< @@ -930,7 +972,7 @@ typedef npy_intp __pyx_t_5numpy_intp_t; */ typedef npy_uintp __pyx_t_5numpy_uintp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":765 * ctypedef npy_uintp uintp_t * * ctypedef npy_double float_t # <<<<<<<<<<<<<< @@ -939,7 +981,7 @@ typedef npy_uintp __pyx_t_5numpy_uintp_t; */ typedef npy_double __pyx_t_5numpy_float_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":766 * * ctypedef npy_double float_t * ctypedef npy_double double_t # <<<<<<<<<<<<<< @@ -948,7 +990,7 @@ typedef npy_double __pyx_t_5numpy_float_t; */ typedef npy_double __pyx_t_5numpy_double_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":780 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 * ctypedef npy_double float_t * ctypedef npy_double double_t * ctypedef npy_longdouble longdouble_t # <<<<<<<<<<<<<< @@ -992,7 +1034,7 @@ static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(do /*--- Type declarations ---*/ -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 * ctypedef npy_longdouble longdouble_t * * ctypedef npy_cfloat cfloat_t # <<<<<<<<<<<<<< @@ -1001,7 +1043,7 @@ static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(do */ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":783 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":770 * * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t # <<<<<<<<<<<<<< @@ -1010,7 +1052,7 @@ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; */ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t * ctypedef npy_clongdouble clongdouble_t # <<<<<<<<<<<<<< @@ -1019,7 +1061,7 @@ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; */ typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":786 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 * ctypedef npy_clongdouble clongdouble_t * * ctypedef npy_cdouble complex_t # <<<<<<<<<<<<<< @@ -1166,16 +1208,7 @@ typedef void (*__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr)(int const /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_getattro)) - return tp->tp_getattro(obj, attr_name); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_getattr)) - return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); -#endif - return PyObject_GetAttr(obj, attr_name); -} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif @@ -1211,6 +1244,35 @@ static CYTHON_INLINE int __Pyx_PySequence_ContainsTF(PyObject* item, PyObject* s return unlikely(result < 0) ? result : (result == (eq == Py_EQ)); } +/* GetItemInt.proto */ +#define __Pyx_GetItemInt(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ + (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ + __Pyx_GetItemInt_Fast(o, (Py_ssize_t)i, is_list, wraparound, boundscheck) :\ + (is_list ? (PyErr_SetString(PyExc_IndexError, "list index out of range"), (PyObject*)NULL) :\ + __Pyx_GetItemInt_Generic(o, to_py_func(i)))) +#define __Pyx_GetItemInt_List(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ + (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ + __Pyx_GetItemInt_List_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) :\ + (PyErr_SetString(PyExc_IndexError, "list index out of range"), (PyObject*)NULL)) +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i, + int wraparound, int boundscheck); +#define __Pyx_GetItemInt_Tuple(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ + (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ + __Pyx_GetItemInt_Tuple_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) :\ + (PyErr_SetString(PyExc_IndexError, "tuple index out of range"), (PyObject*)NULL)) +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i, + int wraparound, int boundscheck); +static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j); +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, + int is_list, int wraparound, int boundscheck); + +/* ObjectGetItem.proto */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key); +#else +#define __Pyx_PyObject_GetItem(obj, key) PyObject_GetItem(obj, key) +#endif + /* GetModuleGlobalName.proto */ static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name); @@ -1271,25 +1333,23 @@ static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject /* RaiseException.proto */ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause); +/* PyObjectCallMethO.proto */ +#if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg); +#endif + +/* PyObjectCallOneArg.proto */ +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg); + /* DictGetItem.proto */ #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY -static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { - PyObject *value; - value = PyDict_GetItemWithError(d, key); - if (unlikely(!value)) { - if (!PyErr_Occurred()) { - PyObject* args = PyTuple_Pack(1, key); - if (likely(args)) - PyErr_SetObject(PyExc_KeyError, args); - Py_XDECREF(args); - } - return NULL; - } - Py_INCREF(value); - return value; -} +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key); +#define __Pyx_PyObject_Dict_GetItem(obj, name)\ + (likely(PyDict_CheckExact(obj)) ?\ + __Pyx_PyDict_GetItem(obj, name) : PyObject_GetItem(obj, name)) #else - #define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyObject_Dict_GetItem(obj, name) PyObject_GetItem(obj, name) #endif /* RaiseTooManyValuesToUnpack.proto */ @@ -1334,14 +1394,6 @@ static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level); /* ImportFrom.proto */ static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name); -/* PyObjectCallMethO.proto */ -#if CYTHON_COMPILING_IN_CPYTHON -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg); -#endif - -/* PyObjectCallOneArg.proto */ -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg); - /* PyObjectCallNoArg.proto */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func); @@ -1514,6 +1566,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) #define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) #endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) /* CheckBinaryVersion.proto */ static int __Pyx_check_binary_version(void); @@ -1720,6 +1773,7 @@ static const char __pyx_k_numpy_core_multiarray_failed_to[] = "numpy.core.multia static const char __pyx_k_unknown_dtype_code_in_numpy_pxd[] = "unknown dtype code in numpy.pxd (%d)"; static const char __pyx_k_Format_string_allocated_too_shor[] = "Format string allocated too short, see comment in numpy.pxd"; static const char __pyx_k_Non_native_byte_order_not_suppor[] = "Non-native byte order not supported"; +static const char __pyx_k_Optimized_cython_functions_for_t[] = "Optimized cython functions for training :class:`~gensim.models.fasttext.FastText` model."; static const char __pyx_k_gensim_models_fasttext_inner_pyx[] = "gensim/models/fasttext_inner.pyx"; static const char __pyx_k_ndarray_is_not_Fortran_contiguou[] = "ndarray is not Fortran contiguous"; static const char __pyx_k_numpy_core_umath_failed_to_impor[] = "numpy.core.umath failed to import"; @@ -1857,6 +1911,7 @@ static PyObject *__pyx_tuple__19; static PyObject *__pyx_codeobj__16; static PyObject *__pyx_codeobj__18; static PyObject *__pyx_codeobj__20; +/* Late includes */ /* "gensim/models/fasttext_inner.pyx":42 * cdef REAL_t ONEF = 1.0 @@ -1880,10 +1935,12 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_norm_factor; unsigned PY_LONG_LONG __pyx_r; __pyx_t_5numpy_uint32_t __pyx_t_1; - int __pyx_t_2; - long __pyx_t_3; - int __pyx_t_4; - int __pyx_t_5; + __pyx_t_5numpy_uint32_t __pyx_t_2; + int __pyx_t_3; + long __pyx_t_4; + long __pyx_t_5; + int __pyx_t_6; + int __pyx_t_7; /* "gensim/models/fasttext_inner.pyx":50 * @@ -1919,7 +1976,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * memset(l1, 0, size * cython.sizeof(REAL_t)) * */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":58 * @@ -1928,7 +1985,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * * scopy(&size, &syn0_vocab[row1], &ONE, l1, &ONE) */ - memset(__pyx_v_l1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_l1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":60 * memset(l1, 0, size * cython.sizeof(REAL_t)) @@ -1947,8 +2004,9 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * cdef REAL_t norm_factor = ONEF / subwords_len */ __pyx_t_1 = __pyx_v_subwords_len; - for (__pyx_t_2 = 1; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 1; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":62 * scopy(&size, &syn0_vocab[row1], &ONE, l1, &ONE) @@ -1985,9 +2043,10 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * if d == 0: * target_index = word_index */ - __pyx_t_3 = (__pyx_v_negative + 1); - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_3; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_4 = (__pyx_v_negative + 1); + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_5; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":67 * @@ -1996,8 +2055,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * target_index = word_index * label = ONEF */ - __pyx_t_4 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_4) { + __pyx_t_6 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_6) { /* "gensim/models/fasttext_inner.pyx":68 * for d in range(negative+1): @@ -2053,8 +2112,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue * label = 0.0 */ - __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); - if (__pyx_t_4) { + __pyx_t_6 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); + if (__pyx_t_6) { /* "gensim/models/fasttext_inner.pyx":74 * next_random = (next_random * 25214903917ULL + 11) & modulo @@ -2110,16 +2169,16 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_5) { + __pyx_t_7 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_7) { } else { - __pyx_t_4 = __pyx_t_5; + __pyx_t_6 = __pyx_t_7; goto __pyx_L10_bool_binop_done; } - __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_4 = __pyx_t_5; + __pyx_t_7 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_6 = __pyx_t_7; __pyx_L10_bool_binop_done:; - if (__pyx_t_4) { + if (__pyx_t_6) { /* "gensim/models/fasttext_inner.pyx":80 * f_dot = our_dot(&size, l1, &ONE, &syn1neg[row2], &ONE) @@ -2194,8 +2253,9 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * return next_random */ __pyx_t_1 = __pyx_v_subwords_len; - for (__pyx_t_2 = 1; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 1; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":87 * our_saxpy(&size, &word_locks_vocab[word2_index], work, &ONE, &syn0_vocab[row1], &ONE) @@ -2249,11 +2309,13 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t long __pyx_v_d; __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_norm_factor; __pyx_t_5numpy_uint32_t __pyx_t_1; - long __pyx_t_2; - int __pyx_t_3; - PY_LONG_LONG __pyx_t_4; + __pyx_t_5numpy_uint32_t __pyx_t_2; + long __pyx_t_3; + int __pyx_t_4; int __pyx_t_5; - int __pyx_t_6; + PY_LONG_LONG __pyx_t_6; + int __pyx_t_7; + int __pyx_t_8; /* "gensim/models/fasttext_inner.pyx":99 * @@ -2280,7 +2342,7 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t * memset(l1, 0, size * cython.sizeof(REAL_t)) * */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":104 * @@ -2289,7 +2351,7 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t * * scopy(&size, &syn0_vocab[row1], &ONE, l1, &ONE) */ - memset(__pyx_v_l1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_l1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":106 * memset(l1, 0, size * cython.sizeof(REAL_t)) @@ -2308,8 +2370,9 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t * cdef REAL_t norm_factor = ONEF / subwords_len */ __pyx_t_1 = __pyx_v_subwords_len; - for (__pyx_t_2 = 1; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 1; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":108 * scopy(&size, &syn0_vocab[row1], &ONE, l1, &ONE) @@ -2346,9 +2409,10 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t * row2 = word_point[b] * size * f_dot = our_dot(&size, l1, &ONE, &syn1[row2], &ONE) */ - __pyx_t_3 = __pyx_v_codelen; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_b = __pyx_t_4; + __pyx_t_4 = __pyx_v_codelen; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_b = __pyx_t_6; /* "gensim/models/fasttext_inner.pyx":113 * @@ -2375,16 +2439,16 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_6 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_6) { + __pyx_t_8 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_8) { } else { - __pyx_t_5 = __pyx_t_6; + __pyx_t_7 = __pyx_t_8; goto __pyx_L8_bool_binop_done; } - __pyx_t_6 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_5 = __pyx_t_6; + __pyx_t_8 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_7 = __pyx_t_8; __pyx_L8_bool_binop_done:; - if (__pyx_t_5) { + if (__pyx_t_7) { /* "gensim/models/fasttext_inner.pyx":116 * f_dot = our_dot(&size, l1, &ONE, &syn1[row2], &ONE) @@ -2459,8 +2523,9 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs(__pyx_t * */ __pyx_t_1 = __pyx_v_subwords_len; - for (__pyx_t_2 = 1; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 1; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":125 * our_saxpy(&size, &word_locks_vocab[word2_index], work, &ONE, &syn0_vocab[row1], &ONE) @@ -2510,8 +2575,11 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente int __pyx_t_3; int __pyx_t_4; int __pyx_t_5; - long __pyx_t_6; + int __pyx_t_6; int __pyx_t_7; + long __pyx_t_8; + long __pyx_t_9; + int __pyx_t_10; /* "gensim/models/fasttext_inner.pyx":137 * cdef long long a @@ -2547,7 +2615,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * count = 0.0 * for m in range(j, k): */ - memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":145 * @@ -2566,8 +2634,9 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":147 * count = 0.0 @@ -2576,8 +2645,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue * count += ONEF */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":148 * for m in range(j, k): @@ -2622,9 +2691,10 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * count += ONEF * our_saxpy(&size, &ONEF, &syn0_ngrams[subwords_idx[m][d] * size], &ONE, neu1, &ONE) */ - __pyx_t_4 = (__pyx_v_subwords_idx_len[__pyx_v_m]); - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_d = __pyx_t_5; + __pyx_t_5 = (__pyx_v_subwords_idx_len[__pyx_v_m]); + __pyx_t_6 = __pyx_t_5; + for (__pyx_t_7 = 0; __pyx_t_7 < __pyx_t_6; __pyx_t_7+=1) { + __pyx_v_d = __pyx_t_7; /* "gensim/models/fasttext_inner.pyx":152 * our_saxpy(&size, &ONEF, &syn0_vocab[indexes[m] * size], &ONE, neu1, &ONE) @@ -2654,8 +2724,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * inv_count = ONEF / count * if cbow_mean: */ - __pyx_t_3 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":156 * @@ -2682,8 +2752,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * sscal(&size, &inv_count, neu1, &ONE) * */ - __pyx_t_3 = (__pyx_v_cbow_mean != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_cbow_mean != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":158 * inv_count = ONEF / count @@ -2710,7 +2780,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * * for d in range(negative+1): */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":162 * memset(work, 0, size * cython.sizeof(REAL_t)) @@ -2719,8 +2789,9 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * if d == 0: * target_index = word_index */ - __pyx_t_6 = (__pyx_v_negative + 1); - for (__pyx_t_1 = 0; __pyx_t_1 < __pyx_t_6; __pyx_t_1+=1) { + __pyx_t_8 = (__pyx_v_negative + 1); + __pyx_t_9 = __pyx_t_8; + for (__pyx_t_1 = 0; __pyx_t_1 < __pyx_t_9; __pyx_t_1+=1) { __pyx_v_d = __pyx_t_1; /* "gensim/models/fasttext_inner.pyx":163 @@ -2730,8 +2801,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * target_index = word_index * label = ONEF */ - __pyx_t_3 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":164 * for d in range(negative+1): @@ -2787,8 +2858,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue * label = 0.0 */ - __pyx_t_3 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":170 * next_random = (next_random * 25214903917ULL + 11) & modulo @@ -2844,16 +2915,16 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_7 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_7) { + __pyx_t_10 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_10) { } else { - __pyx_t_3 = __pyx_t_7; + __pyx_t_4 = __pyx_t_10; goto __pyx_L15_bool_binop_done; } - __pyx_t_7 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_7; + __pyx_t_10 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_10; __pyx_L15_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":176 * f_dot = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) @@ -2918,8 +2989,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * sscal(&size, &inv_count, work, &ONE) * */ - __pyx_t_3 = ((!(__pyx_v_cbow_mean != 0)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((!(__pyx_v_cbow_mean != 0)) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":184 * @@ -2947,8 +3018,9 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":187 * @@ -2957,8 +3029,8 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * continue * our_saxpy(&size, &word_locks_vocab[indexes[m]], work, &ONE, &syn0_vocab[indexes[m]*size], &ONE) */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":188 * for m in range(j,k): @@ -2994,9 +3066,10 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14fasttext_inner_fast_sente * our_saxpy(&size, &word_locks_ngrams[subwords_idx[m][d]], work, &ONE, &syn0_ngrams[subwords_idx[m][d]*size], &ONE) * */ - __pyx_t_4 = (__pyx_v_subwords_idx_len[__pyx_v_m]); - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_d = __pyx_t_5; + __pyx_t_5 = (__pyx_v_subwords_idx_len[__pyx_v_m]); + __pyx_t_6 = __pyx_t_5; + for (__pyx_t_7 = 0; __pyx_t_7 < __pyx_t_6; __pyx_t_7+=1) { + __pyx_v_d = __pyx_t_7; /* "gensim/models/fasttext_inner.pyx":191 * our_saxpy(&size, &word_locks_vocab[indexes[m]], work, &ONE, &syn0_vocab[indexes[m]*size], &ONE) @@ -3056,8 +3129,10 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx int __pyx_t_3; int __pyx_t_4; int __pyx_t_5; - PY_LONG_LONG __pyx_t_6; + int __pyx_t_6; int __pyx_t_7; + PY_LONG_LONG __pyx_t_8; + int __pyx_t_9; /* "gensim/models/fasttext_inner.pyx":205 * cdef long long a, b @@ -3075,7 +3150,7 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * count = 0.0 * for m in range(j, k): */ - memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":209 * @@ -3094,8 +3169,9 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":211 * count = 0.0 @@ -3104,8 +3180,8 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * continue * count += ONEF */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":212 * for m in range(j, k): @@ -3150,9 +3226,10 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * count += ONEF * our_saxpy(&size, &ONEF, &syn0_ngrams[subwords_idx[m][d] * size], &ONE, neu1, &ONE) */ - __pyx_t_4 = (__pyx_v_subwords_idx_len[__pyx_v_m]); - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_d = __pyx_t_5; + __pyx_t_5 = (__pyx_v_subwords_idx_len[__pyx_v_m]); + __pyx_t_6 = __pyx_t_5; + for (__pyx_t_7 = 0; __pyx_t_7 < __pyx_t_6; __pyx_t_7+=1) { + __pyx_v_d = __pyx_t_7; /* "gensim/models/fasttext_inner.pyx":216 * our_saxpy(&size, &ONEF, &syn0_vocab[indexes[m] * size], &ONE, neu1, &ONE) @@ -3182,8 +3259,8 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * inv_count = ONEF / count * if cbow_mean: */ - __pyx_t_3 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":219 * our_saxpy(&size, &ONEF, &syn0_ngrams[subwords_idx[m][d] * size], &ONE, neu1, &ONE) @@ -3210,8 +3287,8 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * sscal(&size, &inv_count, neu1, &ONE) * */ - __pyx_t_3 = (__pyx_v_cbow_mean != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_cbow_mean != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":221 * inv_count = ONEF / count @@ -3238,7 +3315,7 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * for b in range(codelens[i]): * row2 = word_point[b] * size */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); /* "gensim/models/fasttext_inner.pyx":224 * @@ -3248,8 +3325,9 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = (__pyx_v_codelens[__pyx_v_i]); - for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_1; __pyx_t_6+=1) { - __pyx_v_b = __pyx_t_6; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_2; __pyx_t_8+=1) { + __pyx_v_b = __pyx_t_8; /* "gensim/models/fasttext_inner.pyx":225 * memset(work, 0, size * cython.sizeof(REAL_t)) @@ -3276,16 +3354,16 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_7 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_7) { + __pyx_t_9 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_9) { } else { - __pyx_t_3 = __pyx_t_7; + __pyx_t_4 = __pyx_t_9; goto __pyx_L13_bool_binop_done; } - __pyx_t_7 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_7; + __pyx_t_9 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_9; __pyx_L13_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":228 * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) @@ -3350,8 +3428,8 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * sscal(&size, &inv_count, work, &ONE) * */ - __pyx_t_3 = ((!(__pyx_v_cbow_mean != 0)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((!(__pyx_v_cbow_mean != 0)) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":236 * @@ -3379,8 +3457,9 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; /* "gensim/models/fasttext_inner.pyx":239 * @@ -3389,8 +3468,8 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * continue * our_saxpy(&size, &word_locks_vocab[indexes[m]], work, &ONE, &syn0_vocab[indexes[m]*size], &ONE) */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { /* "gensim/models/fasttext_inner.pyx":240 * for m in range(j,k): @@ -3426,9 +3505,10 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * our_saxpy(&size, &word_locks_ngrams[subwords_idx[m][d]], work, &ONE, &syn0_ngrams[subwords_idx[m][d]*size], &ONE) * */ - __pyx_t_4 = (__pyx_v_subwords_idx_len[__pyx_v_m]); - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_d = __pyx_t_5; + __pyx_t_5 = (__pyx_v_subwords_idx_len[__pyx_v_m]); + __pyx_t_6 = __pyx_t_5; + for (__pyx_t_7 = 0; __pyx_t_7 < __pyx_t_6; __pyx_t_7+=1) { + __pyx_v_d = __pyx_t_7; /* "gensim/models/fasttext_inner.pyx":243 * our_saxpy(&size, &word_locks_vocab[indexes[m]], work, &ONE, &syn0_vocab[indexes[m]*size], &ONE) @@ -3457,13 +3537,14 @@ static void __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs(__pyx * * * def train_batch_sg(model, sentences, alpha, _work, _l1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a sequence of sentences. + * */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_1train_batch_sg(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_14fasttext_inner_1train_batch_sg = {"train_batch_sg", (PyCFunction)__pyx_pw_6gensim_6models_14fasttext_inner_1train_batch_sg, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_14fasttext_inner_train_batch_sg[] = "train_batch_sg(model, sentences, alpha, _work, _l1)\nUpdate skip-gram model by training on a sequence of sentences.\n\n Each sentence is a list of string tokens, which are looked up in the model's\n vocab dictionary. Called internally from :meth:`gensim.models.fasttext.FastText.train`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.fasttext.FastText`\n Model to be trained.\n sentences : iterable of list of str\n Corpus streamed directly from disk/network.\n alpha : float\n Learning rate.\n _work : np.ndarray\n Private working memory for each worker.\n _l1 : np.ndarray\n Private working memory for each worker.\n\n Returns\n -------\n int\n Effective number of words trained.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_14fasttext_inner_1train_batch_sg = {"train_batch_sg", (PyCFunction)__pyx_pw_6gensim_6models_14fasttext_inner_1train_batch_sg, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_14fasttext_inner_train_batch_sg}; static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_1train_batch_sg(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_sentences = 0; @@ -3496,29 +3577,29 @@ static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_1train_batch_sg(PyObj kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 1); __PYX_ERR(0, 246, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 2); __PYX_ERR(0, 246, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 3); __PYX_ERR(0, 246, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: - if (likely((values[4] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_l1)) != 0)) kw_args--; + if (likely((values[4] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_l1)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 4); __PYX_ERR(0, 246, __pyx_L3_error) } @@ -3623,156 +3704,159 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON int __pyx_t_21; int __pyx_t_22; int __pyx_t_23; + int __pyx_t_24; + int __pyx_t_25; + int __pyx_t_26; __Pyx_RefNannySetupContext("train_batch_sg", 0); - /* "gensim/models/fasttext_inner.pyx":247 + /* "gensim/models/fasttext_inner.pyx":271 * - * def train_batch_sg(model, sentences, alpha, _work, _l1): + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 247, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 271, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 247, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 271, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":248 - * def train_batch_sg(model, sentences, alpha, _work, _l1): + /* "gensim/models/fasttext_inner.pyx":272 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 248, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 272, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 248, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 272, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":249 + /* "gensim/models/fasttext_inner.pyx":273 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 249, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 273, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 249, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 273, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 249, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 273, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 249, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 273, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":251 + /* "gensim/models/fasttext_inner.pyx":275 * cdef int sample = (model.vocabulary.sample != 0) * * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) # <<<<<<<<<<<<<< * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 251, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 275, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 251, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 275, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 251, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 275, __pyx_L1_error) __pyx_v_syn0_vocab = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":252 + /* "gensim/models/fasttext_inner.pyx":276 * * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) # <<<<<<<<<<<<<< * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) * cdef REAL_t *word_locks_ngrams = (np.PyArray_DATA(model.trainables.vectors_ngrams_lockf)) */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 252, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 276, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_vocab_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 252, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_vocab_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 276, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 252, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 276, __pyx_L1_error) __pyx_v_word_locks_vocab = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":253 + /* "gensim/models/fasttext_inner.pyx":277 * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) # <<<<<<<<<<<<<< * cdef REAL_t *word_locks_ngrams = (np.PyArray_DATA(model.trainables.vectors_ngrams_lockf)) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 253, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 277, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_ngrams); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 253, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_ngrams); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 277, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 253, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 277, __pyx_L1_error) __pyx_v_syn0_ngrams = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":254 + /* "gensim/models/fasttext_inner.pyx":278 * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) * cdef REAL_t *word_locks_ngrams = (np.PyArray_DATA(model.trainables.vectors_ngrams_lockf)) # <<<<<<<<<<<<<< * * cdef REAL_t *work */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 254, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 278, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_ngrams_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 254, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_ngrams_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 278, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 254, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 278, __pyx_L1_error) __pyx_v_word_locks_ngrams = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":259 + /* "gensim/models/fasttext_inner.pyx":283 * cdef REAL_t *l1 * * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int size = model.wv.vector_size * */ - __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 259, __pyx_L1_error) + __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 283, __pyx_L1_error) __pyx_v__alpha = __pyx_t_4; - /* "gensim/models/fasttext_inner.pyx":260 + /* "gensim/models/fasttext_inner.pyx":284 * * cdef REAL_t _alpha = alpha * cdef int size = model.wv.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_SENTENCE_LEN] */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 260, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 284, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 260, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 284, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 260, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 284, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":266 + /* "gensim/models/fasttext_inner.pyx":290 * cdef np.uint32_t reduced_windows[MAX_SENTENCE_LEN] * cdef int sentence_idx[MAX_SENTENCE_LEN + 1] * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 266, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 290, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 266, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 290, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":269 + /* "gensim/models/fasttext_inner.pyx":293 * * cdef int i, j, k * cdef int effective_words = 0, effective_sentences = 0 # <<<<<<<<<<<<<< @@ -3782,19 +3866,19 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_v_effective_words = 0; __pyx_v_effective_sentences = 0; - /* "gensim/models/fasttext_inner.pyx":289 + /* "gensim/models/fasttext_inner.pyx":313 * # dummy dictionary to ensure that the memory locations that subwords_idx point to * # are referenced throughout so that it isn't put back to free memory pool by Python's memory manager * subword_arrays = {} # <<<<<<<<<<<<<< * * if hs: */ - __pyx_t_3 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 289, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 313, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_v_subword_arrays = ((PyObject*)__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":291 + /* "gensim/models/fasttext_inner.pyx":315 * subword_arrays = {} * * if hs: # <<<<<<<<<<<<<< @@ -3804,23 +3888,23 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":292 + /* "gensim/models/fasttext_inner.pyx":316 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 292, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 316, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 292, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 316, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 292, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 316, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":291 + /* "gensim/models/fasttext_inner.pyx":315 * subword_arrays = {} * * if hs: # <<<<<<<<<<<<<< @@ -3829,7 +3913,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":294 + /* "gensim/models/fasttext_inner.pyx":318 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -3839,55 +3923,55 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":295 + /* "gensim/models/fasttext_inner.pyx":319 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 319, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 295, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 319, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":296 + /* "gensim/models/fasttext_inner.pyx":320 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 296, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 320, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 296, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 320, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 296, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 320, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":297 + /* "gensim/models/fasttext_inner.pyx":321 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 297, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 321, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 297, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 321, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 297, __pyx_L1_error) + __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 321, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_6; - /* "gensim/models/fasttext_inner.pyx":294 + /* "gensim/models/fasttext_inner.pyx":318 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -3896,7 +3980,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":298 + /* "gensim/models/fasttext_inner.pyx":322 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -3914,41 +3998,41 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_L6_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":299 + /* "gensim/models/fasttext_inner.pyx":323 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_next_random = __pyx_t_9; - /* "gensim/models/fasttext_inner.pyx":298 + /* "gensim/models/fasttext_inner.pyx":322 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -3957,42 +4041,42 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":302 + /* "gensim/models/fasttext_inner.pyx":326 * * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) # <<<<<<<<<<<<<< * l1 = np.PyArray_DATA(_l1) * */ - if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 302, __pyx_L1_error) + if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 326, __pyx_L1_error) __pyx_v_work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__work))); - /* "gensim/models/fasttext_inner.pyx":303 + /* "gensim/models/fasttext_inner.pyx":327 * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) * l1 = np.PyArray_DATA(_l1) # <<<<<<<<<<<<<< * * # prepare C structures so we can go "full C" and release the Python GIL */ - if (!(likely(((__pyx_v__l1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__l1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 303, __pyx_L1_error) + if (!(likely(((__pyx_v__l1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__l1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 327, __pyx_L1_error) __pyx_v_l1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__l1))); - /* "gensim/models/fasttext_inner.pyx":306 + /* "gensim/models/fasttext_inner.pyx":330 * * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 306, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 330, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 306, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 330, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_vlookup = __pyx_t_3; __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":307 + /* "gensim/models/fasttext_inner.pyx":331 * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 # <<<<<<<<<<<<<< @@ -4001,7 +4085,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ (__pyx_v_sentence_idx[0]) = 0; - /* "gensim/models/fasttext_inner.pyx":308 + /* "gensim/models/fasttext_inner.pyx":332 * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: # <<<<<<<<<<<<<< @@ -4012,26 +4096,26 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_3 = __pyx_v_sentences; __Pyx_INCREF(__pyx_t_3); __pyx_t_6 = 0; __pyx_t_10 = NULL; } else { - __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 332, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 332, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_10)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 332, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 332, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 332, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 332, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } @@ -4041,7 +4125,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 308, __pyx_L1_error) + else __PYX_ERR(0, 332, __pyx_L1_error) } break; } @@ -4050,18 +4134,18 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_sent, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/fasttext_inner.pyx":309 + /* "gensim/models/fasttext_inner.pyx":333 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: */ - __pyx_t_5 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 309, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 333, __pyx_L1_error) __pyx_t_7 = ((!__pyx_t_5) != 0); if (__pyx_t_7) { - /* "gensim/models/fasttext_inner.pyx":310 + /* "gensim/models/fasttext_inner.pyx":334 * for sent in sentences: * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged # <<<<<<<<<<<<<< @@ -4070,7 +4154,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ goto __pyx_L8_continue; - /* "gensim/models/fasttext_inner.pyx":309 + /* "gensim/models/fasttext_inner.pyx":333 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< @@ -4079,7 +4163,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":311 + /* "gensim/models/fasttext_inner.pyx":335 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -4090,26 +4174,26 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_8 = __pyx_v_sent; __Pyx_INCREF(__pyx_t_8); __pyx_t_11 = 0; __pyx_t_12 = NULL; } else { - __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 311, __pyx_L1_error) + __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 311, __pyx_L1_error) + __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 335, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_12)) { if (likely(PyList_CheckExact(__pyx_t_8))) { if (__pyx_t_11 >= PyList_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 311, __pyx_L1_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 335, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 311, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_11 >= PyTuple_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 311, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 335, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 311, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 335, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -4119,7 +4203,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 311, __pyx_L1_error) + else __PYX_ERR(0, 335, __pyx_L1_error) } break; } @@ -4128,16 +4212,16 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":312 + /* "gensim/models/fasttext_inner.pyx":336 * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: * word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window */ - __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 312, __pyx_L1_error) + __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 336, __pyx_L1_error) if ((__pyx_t_7 != 0)) { - __pyx_t_13 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 312, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 336, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __pyx_t_1 = __pyx_t_13; __pyx_t_13 = 0; @@ -4148,7 +4232,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_word, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":313 + /* "gensim/models/fasttext_inner.pyx":337 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -4159,7 +4243,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = (__pyx_t_7 != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":314 + /* "gensim/models/fasttext_inner.pyx":338 * word = vlookup[token] if token in vlookup else None * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window # <<<<<<<<<<<<<< @@ -4168,7 +4252,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ goto __pyx_L11_continue; - /* "gensim/models/fasttext_inner.pyx":313 + /* "gensim/models/fasttext_inner.pyx":337 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -4177,7 +4261,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":315 + /* "gensim/models/fasttext_inner.pyx":339 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -4190,20 +4274,20 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = __pyx_t_7; goto __pyx_L15_bool_binop_done; } - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 315, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 339, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 315, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 339, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 315, __pyx_L1_error) + __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 339, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; - __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 315, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 339, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __pyx_t_5 = __pyx_t_7; __pyx_L15_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":316 + /* "gensim/models/fasttext_inner.pyx":340 * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -4212,7 +4296,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ goto __pyx_L11_continue; - /* "gensim/models/fasttext_inner.pyx":315 + /* "gensim/models/fasttext_inner.pyx":339 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -4221,77 +4305,77 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":317 + /* "gensim/models/fasttext_inner.pyx":341 * if sample and word.sample_int < random_int32(&next_random): * continue * indexes[effective_words] = word.index # <<<<<<<<<<<<<< * * subwords = model.wv.buckets_word[word.index] */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 317, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 341, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 317, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 341, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; (__pyx_v_indexes[__pyx_v_effective_words]) = __pyx_t_15; - /* "gensim/models/fasttext_inner.pyx":319 + /* "gensim/models/fasttext_inner.pyx":343 * indexes[effective_words] = word.index * * subwords = model.wv.buckets_word[word.index] # <<<<<<<<<<<<<< * word_subwords = np.array((word.index,) + subwords, dtype=np.uint32) * subwords_idx_len[effective_words] = (len(subwords) + 1) */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 343, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_13 = __Pyx_PyObject_GetAttrStr(__pyx_t_14, __pyx_n_s_buckets_word); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyObject_GetAttrStr(__pyx_t_14, __pyx_n_s_buckets_word); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 343, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 343, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_1 = PyObject_GetItem(__pyx_t_13, __pyx_t_14); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 319, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetItem(__pyx_t_13, __pyx_t_14); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 343, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_XDECREF_SET(__pyx_v_subwords, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":320 + /* "gensim/models/fasttext_inner.pyx":344 * * subwords = model.wv.buckets_word[word.index] * word_subwords = np.array((word.index,) + subwords, dtype=np.uint32) # <<<<<<<<<<<<<< * subwords_idx_len[effective_words] = (len(subwords) + 1) * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_array); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_array); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_13 = PyTuple_New(1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_13 = PyTuple_New(1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_13, 0, __pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Add(__pyx_t_13, __pyx_v_subwords); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_1 = PyNumber_Add(__pyx_t_13, __pyx_v_subwords); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; - __pyx_t_13 = PyTuple_New(1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_13 = PyTuple_New(1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_13, 0, __pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_16 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_16 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_16); - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_t_16, __pyx_n_s_uint32); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_t_16, __pyx_n_s_uint32); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); __Pyx_DECREF(__pyx_t_16); __pyx_t_16 = 0; - if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_17) < 0) __PYX_ERR(0, 320, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_dtype, __pyx_t_17) < 0) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - __pyx_t_17 = __Pyx_PyObject_Call(__pyx_t_14, __pyx_t_13, __pyx_t_1); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 320, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_Call(__pyx_t_14, __pyx_t_13, __pyx_t_1); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 344, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; @@ -4299,39 +4383,39 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_word_subwords, __pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":321 + /* "gensim/models/fasttext_inner.pyx":345 * subwords = model.wv.buckets_word[word.index] * word_subwords = np.array((word.index,) + subwords, dtype=np.uint32) * subwords_idx_len[effective_words] = (len(subwords) + 1) # <<<<<<<<<<<<<< * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) * # ensures reference count of word_subwords doesn't reach 0 */ - __pyx_t_18 = PyObject_Length(__pyx_v_subwords); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 321, __pyx_L1_error) + __pyx_t_18 = PyObject_Length(__pyx_v_subwords); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 345, __pyx_L1_error) (__pyx_v_subwords_idx_len[__pyx_v_effective_words]) = ((int)(__pyx_t_18 + 1)); - /* "gensim/models/fasttext_inner.pyx":322 + /* "gensim/models/fasttext_inner.pyx":346 * word_subwords = np.array((word.index,) + subwords, dtype=np.uint32) * subwords_idx_len[effective_words] = (len(subwords) + 1) * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) # <<<<<<<<<<<<<< * # ensures reference count of word_subwords doesn't reach 0 * subword_arrays[effective_words] = word_subwords */ - if (!(likely(((__pyx_v_word_subwords) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_subwords, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 322, __pyx_L1_error) + if (!(likely(((__pyx_v_word_subwords) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_subwords, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 346, __pyx_L1_error) (__pyx_v_subwords_idx[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_subwords))); - /* "gensim/models/fasttext_inner.pyx":324 + /* "gensim/models/fasttext_inner.pyx":348 * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) * # ensures reference count of word_subwords doesn't reach 0 * subword_arrays[effective_words] = word_subwords # <<<<<<<<<<<<<< * * if hs: */ - __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 324, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 348, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - if (unlikely(PyDict_SetItem(__pyx_v_subword_arrays, __pyx_t_17, __pyx_v_word_subwords) < 0)) __PYX_ERR(0, 324, __pyx_L1_error) + if (unlikely(PyDict_SetItem(__pyx_v_subword_arrays, __pyx_t_17, __pyx_v_word_subwords) < 0)) __PYX_ERR(0, 348, __pyx_L1_error) __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":326 + /* "gensim/models/fasttext_inner.pyx":350 * subword_arrays[effective_words] = word_subwords * * if hs: # <<<<<<<<<<<<<< @@ -4341,46 +4425,46 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":327 + /* "gensim/models/fasttext_inner.pyx":351 * * if hs: * codelens[effective_words] = len(word.code) # <<<<<<<<<<<<<< * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) */ - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 327, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 351, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - __pyx_t_18 = PyObject_Length(__pyx_t_17); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 327, __pyx_L1_error) + __pyx_t_18 = PyObject_Length(__pyx_t_17); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 351, __pyx_L1_error) __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; (__pyx_v_codelens[__pyx_v_effective_words]) = ((int)__pyx_t_18); - /* "gensim/models/fasttext_inner.pyx":328 + /* "gensim/models/fasttext_inner.pyx":352 * if hs: * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) # <<<<<<<<<<<<<< * points[effective_words] = np.PyArray_DATA(word.point) * */ - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 328, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 352, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 328, __pyx_L1_error) + if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 352, __pyx_L1_error) (__pyx_v_codes[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_17))); __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":329 + /* "gensim/models/fasttext_inner.pyx":353 * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) # <<<<<<<<<<<<<< * * effective_words += 1 */ - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 329, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 353, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 329, __pyx_L1_error) + if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 353, __pyx_L1_error) (__pyx_v_points[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_17))); __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":326 + /* "gensim/models/fasttext_inner.pyx":350 * subword_arrays[effective_words] = word_subwords * * if hs: # <<<<<<<<<<<<<< @@ -4389,7 +4473,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":331 + /* "gensim/models/fasttext_inner.pyx":355 * points[effective_words] = np.PyArray_DATA(word.point) * * effective_words += 1 # <<<<<<<<<<<<<< @@ -4398,7 +4482,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_effective_words = (__pyx_v_effective_words + 1); - /* "gensim/models/fasttext_inner.pyx":332 + /* "gensim/models/fasttext_inner.pyx":356 * * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -4408,7 +4492,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = ((__pyx_v_effective_words == 0x2710) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":333 + /* "gensim/models/fasttext_inner.pyx":357 * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: * break # <<<<<<<<<<<<<< @@ -4417,7 +4501,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ goto __pyx_L12_break; - /* "gensim/models/fasttext_inner.pyx":332 + /* "gensim/models/fasttext_inner.pyx":356 * * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -4426,7 +4510,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":311 + /* "gensim/models/fasttext_inner.pyx":335 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -4438,7 +4522,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_L12_break:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/fasttext_inner.pyx":338 + /* "gensim/models/fasttext_inner.pyx":362 * # across sentence boundaries. * # indices of sentence number X are between tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 345, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_17)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 369, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; for (;;) { @@ -4579,17 +4663,17 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON if (likely(PyList_CheckExact(__pyx_t_17))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_17)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyList_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 345, __pyx_L1_error) + __pyx_t_3 = PyList_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 369, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 345, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 369, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_17)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 345, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 369, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 345, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 369, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } @@ -4599,7 +4683,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 345, __pyx_L1_error) + else __PYX_ERR(0, 369, __pyx_L1_error) } break; } @@ -4610,17 +4694,17 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_v_i = __pyx_t_2; __pyx_t_2 = (__pyx_t_2 + 1); - /* "gensim/models/fasttext_inner.pyx":346 + /* "gensim/models/fasttext_inner.pyx":370 * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): * reduced_windows[i] = item # <<<<<<<<<<<<<< * * with nogil: */ - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 346, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 370, __pyx_L1_error) (__pyx_v_reduced_windows[__pyx_v_i]) = __pyx_t_15; - /* "gensim/models/fasttext_inner.pyx":345 + /* "gensim/models/fasttext_inner.pyx":369 * * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): # <<<<<<<<<<<<<< @@ -4630,7 +4714,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON } __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":348 + /* "gensim/models/fasttext_inner.pyx":372 * reduced_windows[i] = item * * with nogil: # <<<<<<<<<<<<<< @@ -4645,7 +4729,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON #endif /*try:*/ { - /* "gensim/models/fasttext_inner.pyx":349 + /* "gensim/models/fasttext_inner.pyx":373 * * with nogil: * for sent_idx in range(effective_sentences): # <<<<<<<<<<<<<< @@ -4653,10 +4737,11 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON * idx_end = sentence_idx[sent_idx + 1] */ __pyx_t_2 = __pyx_v_effective_sentences; - for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_2; __pyx_t_19+=1) { - __pyx_v_sent_idx = __pyx_t_19; + __pyx_t_19 = __pyx_t_2; + for (__pyx_t_20 = 0; __pyx_t_20 < __pyx_t_19; __pyx_t_20+=1) { + __pyx_v_sent_idx = __pyx_t_20; - /* "gensim/models/fasttext_inner.pyx":350 + /* "gensim/models/fasttext_inner.pyx":374 * with nogil: * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] # <<<<<<<<<<<<<< @@ -4665,7 +4750,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_idx_start = (__pyx_v_sentence_idx[__pyx_v_sent_idx]); - /* "gensim/models/fasttext_inner.pyx":351 + /* "gensim/models/fasttext_inner.pyx":375 * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] # <<<<<<<<<<<<<< @@ -4674,18 +4759,19 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_idx_end = (__pyx_v_sentence_idx[(__pyx_v_sent_idx + 1)]); - /* "gensim/models/fasttext_inner.pyx":352 + /* "gensim/models/fasttext_inner.pyx":376 * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): # <<<<<<<<<<<<<< * j = i - window + reduced_windows[i] * if j < idx_start: */ - __pyx_t_20 = __pyx_v_idx_end; - for (__pyx_t_21 = __pyx_v_idx_start; __pyx_t_21 < __pyx_t_20; __pyx_t_21+=1) { - __pyx_v_i = __pyx_t_21; + __pyx_t_21 = __pyx_v_idx_end; + __pyx_t_22 = __pyx_t_21; + for (__pyx_t_23 = __pyx_v_idx_start; __pyx_t_23 < __pyx_t_22; __pyx_t_23+=1) { + __pyx_v_i = __pyx_t_23; - /* "gensim/models/fasttext_inner.pyx":353 + /* "gensim/models/fasttext_inner.pyx":377 * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] # <<<<<<<<<<<<<< @@ -4694,7 +4780,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_j = ((__pyx_v_i - __pyx_v_window) + (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/fasttext_inner.pyx":354 + /* "gensim/models/fasttext_inner.pyx":378 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -4704,7 +4790,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = ((__pyx_v_j < __pyx_v_idx_start) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":355 + /* "gensim/models/fasttext_inner.pyx":379 * j = i - window + reduced_windows[i] * if j < idx_start: * j = idx_start # <<<<<<<<<<<<<< @@ -4713,7 +4799,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_j = __pyx_v_idx_start; - /* "gensim/models/fasttext_inner.pyx":354 + /* "gensim/models/fasttext_inner.pyx":378 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -4722,7 +4808,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":356 + /* "gensim/models/fasttext_inner.pyx":380 * if j < idx_start: * j = idx_start * k = i + window + 1 - reduced_windows[i] # <<<<<<<<<<<<<< @@ -4731,7 +4817,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_k = (((__pyx_v_i + __pyx_v_window) + 1) - (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/fasttext_inner.pyx":357 + /* "gensim/models/fasttext_inner.pyx":381 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -4741,7 +4827,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = ((__pyx_v_k > __pyx_v_idx_end) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":358 + /* "gensim/models/fasttext_inner.pyx":382 * k = i + window + 1 - reduced_windows[i] * if k > idx_end: * k = idx_end # <<<<<<<<<<<<<< @@ -4750,7 +4836,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_k = __pyx_v_idx_end; - /* "gensim/models/fasttext_inner.pyx":357 + /* "gensim/models/fasttext_inner.pyx":381 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -4759,18 +4845,19 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":359 + /* "gensim/models/fasttext_inner.pyx":383 * if k > idx_end: * k = idx_end * for j in range(j, k): # <<<<<<<<<<<<<< * if j == i: * continue */ - __pyx_t_22 = __pyx_v_k; - for (__pyx_t_23 = __pyx_v_j; __pyx_t_23 < __pyx_t_22; __pyx_t_23+=1) { - __pyx_v_j = __pyx_t_23; + __pyx_t_24 = __pyx_v_k; + __pyx_t_25 = __pyx_t_24; + for (__pyx_t_26 = __pyx_v_j; __pyx_t_26 < __pyx_t_25; __pyx_t_26+=1) { + __pyx_v_j = __pyx_t_26; - /* "gensim/models/fasttext_inner.pyx":360 + /* "gensim/models/fasttext_inner.pyx":384 * k = idx_end * for j in range(j, k): * if j == i: # <<<<<<<<<<<<<< @@ -4780,7 +4867,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = ((__pyx_v_j == __pyx_v_i) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":361 + /* "gensim/models/fasttext_inner.pyx":385 * for j in range(j, k): * if j == i: * continue # <<<<<<<<<<<<<< @@ -4789,7 +4876,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ goto __pyx_L31_continue; - /* "gensim/models/fasttext_inner.pyx":360 + /* "gensim/models/fasttext_inner.pyx":384 * k = idx_end * for j in range(j, k): * if j == i: # <<<<<<<<<<<<<< @@ -4798,7 +4885,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":362 + /* "gensim/models/fasttext_inner.pyx":386 * if j == i: * continue * if hs: # <<<<<<<<<<<<<< @@ -4808,7 +4895,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":363 + /* "gensim/models/fasttext_inner.pyx":387 * continue * if hs: * fast_sentence_sg_hs( # <<<<<<<<<<<<<< @@ -4817,7 +4904,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_hs((__pyx_v_points[__pyx_v_j]), (__pyx_v_codes[__pyx_v_j]), (__pyx_v_codelens[__pyx_v_j]), __pyx_v_syn0_vocab, __pyx_v_syn0_ngrams, __pyx_v_syn1, __pyx_v_size, (__pyx_v_subwords_idx[__pyx_v_i]), (__pyx_v_subwords_idx_len[__pyx_v_i]), __pyx_v__alpha, __pyx_v_work, __pyx_v_l1, __pyx_v_word_locks_vocab, __pyx_v_word_locks_ngrams); - /* "gensim/models/fasttext_inner.pyx":362 + /* "gensim/models/fasttext_inner.pyx":386 * if j == i: * continue * if hs: # <<<<<<<<<<<<<< @@ -4826,7 +4913,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/fasttext_inner.pyx":367 + /* "gensim/models/fasttext_inner.pyx":391 * subwords_idx[i], subwords_idx_len[i], _alpha, work, l1, word_locks_vocab, * word_locks_ngrams) * if negative: # <<<<<<<<<<<<<< @@ -4836,7 +4923,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":368 + /* "gensim/models/fasttext_inner.pyx":392 * word_locks_ngrams) * if negative: * next_random = fast_sentence_sg_neg( # <<<<<<<<<<<<<< @@ -4845,7 +4932,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON */ __pyx_v_next_random = __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_sg_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v_syn0_vocab, __pyx_v_syn0_ngrams, __pyx_v_syn1neg, __pyx_v_size, (__pyx_v_indexes[__pyx_v_j]), (__pyx_v_subwords_idx[__pyx_v_i]), (__pyx_v_subwords_idx_len[__pyx_v_i]), __pyx_v__alpha, __pyx_v_work, __pyx_v_l1, __pyx_v_next_random, __pyx_v_word_locks_vocab, __pyx_v_word_locks_ngrams); - /* "gensim/models/fasttext_inner.pyx":367 + /* "gensim/models/fasttext_inner.pyx":391 * subwords_idx[i], subwords_idx_len[i], _alpha, work, l1, word_locks_vocab, * word_locks_ngrams) * if negative: # <<<<<<<<<<<<<< @@ -4859,7 +4946,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON } } - /* "gensim/models/fasttext_inner.pyx":348 + /* "gensim/models/fasttext_inner.pyx":372 * reduced_windows[i] = item * * with nogil: # <<<<<<<<<<<<<< @@ -4878,7 +4965,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON } } - /* "gensim/models/fasttext_inner.pyx":373 + /* "gensim/models/fasttext_inner.pyx":397 * next_random, word_locks_vocab, word_locks_ngrams) * * return effective_words # <<<<<<<<<<<<<< @@ -4886,7 +4973,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 373, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 397, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); __pyx_r = __pyx_t_17; __pyx_t_17 = 0; @@ -4896,8 +4983,8 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON * * * def train_batch_sg(model, sentences, alpha, _work, _l1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a sequence of sentences. + * */ /* function exit code */ @@ -4925,17 +5012,18 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_train_batch_sg(CYTHON return __pyx_r; } -/* "gensim/models/fasttext_inner.pyx":376 +/* "gensim/models/fasttext_inner.pyx":400 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update the CBOW model by training on a sequence of sentences. + * */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_3train_batch_cbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_14fasttext_inner_3train_batch_cbow = {"train_batch_cbow", (PyCFunction)__pyx_pw_6gensim_6models_14fasttext_inner_3train_batch_cbow, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_14fasttext_inner_2train_batch_cbow[] = "train_batch_cbow(model, sentences, alpha, _work, _neu1)\nUpdate the CBOW model by training on a sequence of sentences.\n\n Each sentence is a list of string tokens, which are looked up in the model's\n vocab dictionary. Called internally from :meth:`gensim.models.fasttext.FastText.train`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.fasttext.FastText`\n Model to be trained.\n sentences : iterable of list of str\n Corpus streamed directly from disk/network.\n alpha : float\n Learning rate.\n _work : np.ndarray\n Private working memory for each worker.\n _neu1 : np.ndarray\n Private working memory for each worker.\n Returns\n -------\n int\n Effective number of words trained.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_14fasttext_inner_3train_batch_cbow = {"train_batch_cbow", (PyCFunction)__pyx_pw_6gensim_6models_14fasttext_inner_3train_batch_cbow, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_14fasttext_inner_2train_batch_cbow}; static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_3train_batch_cbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_sentences = 0; @@ -4968,35 +5056,35 @@ static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_3train_batch_cbow(PyO kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 1); __PYX_ERR(0, 376, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 1); __PYX_ERR(0, 400, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 2); __PYX_ERR(0, 376, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 2); __PYX_ERR(0, 400, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 3); __PYX_ERR(0, 376, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 3); __PYX_ERR(0, 400, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: - if (likely((values[4] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_neu1)) != 0)) kw_args--; + if (likely((values[4] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_neu1)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 4); __PYX_ERR(0, 376, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, 4); __PYX_ERR(0, 400, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_batch_cbow") < 0)) __PYX_ERR(0, 376, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_batch_cbow") < 0)) __PYX_ERR(0, 400, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 5) { goto __pyx_L5_argtuple_error; @@ -5015,7 +5103,7 @@ static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_3train_batch_cbow(PyO } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 376, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 5, 5, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 400, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.fasttext_inner.train_batch_cbow", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -5094,169 +5182,171 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT int __pyx_t_19; int __pyx_t_20; int __pyx_t_21; + int __pyx_t_22; + int __pyx_t_23; __Pyx_RefNannySetupContext("train_batch_cbow", 0); - /* "gensim/models/fasttext_inner.pyx":377 + /* "gensim/models/fasttext_inner.pyx":424 * - * def train_batch_cbow(model, sentences, alpha, _work, _neu1): + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 377, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 424, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 377, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 424, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":378 - * def train_batch_cbow(model, sentences, alpha, _work, _neu1): + /* "gensim/models/fasttext_inner.pyx":425 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * cdef int cbow_mean = model.cbow_mean */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 378, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 425, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 378, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 425, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":379 + /* "gensim/models/fasttext_inner.pyx":426 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * cdef int cbow_mean = model.cbow_mean * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 379, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 426, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 379, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 426, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 379, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 426, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 379, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 426, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":380 + /* "gensim/models/fasttext_inner.pyx":427 * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) * cdef int cbow_mean = model.cbow_mean # <<<<<<<<<<<<<< * * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 380, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 427, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 380, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 427, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_cbow_mean = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":382 + /* "gensim/models/fasttext_inner.pyx":429 * cdef int cbow_mean = model.cbow_mean * * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) # <<<<<<<<<<<<<< * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 382, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 429, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 382, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 429, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 382, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 429, __pyx_L1_error) __pyx_v_syn0_vocab = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":383 + /* "gensim/models/fasttext_inner.pyx":430 * * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) # <<<<<<<<<<<<<< * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) * cdef REAL_t *word_locks_ngrams = (np.PyArray_DATA(model.trainables.vectors_ngrams_lockf)) */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 383, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 430, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_vocab_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 383, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_vocab_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 430, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 383, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 430, __pyx_L1_error) __pyx_v_word_locks_vocab = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":384 + /* "gensim/models/fasttext_inner.pyx":431 * cdef REAL_t *syn0_vocab = (np.PyArray_DATA(model.wv.vectors_vocab)) * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) # <<<<<<<<<<<<<< * cdef REAL_t *word_locks_ngrams = (np.PyArray_DATA(model.trainables.vectors_ngrams_lockf)) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 384, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 431, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_ngrams); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 384, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors_ngrams); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 431, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 384, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 431, __pyx_L1_error) __pyx_v_syn0_ngrams = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":385 + /* "gensim/models/fasttext_inner.pyx":432 * cdef REAL_t *word_locks_vocab = (np.PyArray_DATA(model.trainables.vectors_vocab_lockf)) * cdef REAL_t *syn0_ngrams = (np.PyArray_DATA(model.wv.vectors_ngrams)) * cdef REAL_t *word_locks_ngrams = (np.PyArray_DATA(model.trainables.vectors_ngrams_lockf)) # <<<<<<<<<<<<<< * * cdef REAL_t *work */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 385, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 432, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_ngrams_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 385, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_ngrams_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 432, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 385, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 432, __pyx_L1_error) __pyx_v_word_locks_ngrams = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":388 + /* "gensim/models/fasttext_inner.pyx":435 * * cdef REAL_t *work * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int size = model.wv.vector_size * */ - __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 388, __pyx_L1_error) + __pyx_t_4 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_4 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 435, __pyx_L1_error) __pyx_v__alpha = __pyx_t_4; - /* "gensim/models/fasttext_inner.pyx":389 + /* "gensim/models/fasttext_inner.pyx":436 * cdef REAL_t *work * cdef REAL_t _alpha = alpha * cdef int size = model.wv.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_SENTENCE_LEN] */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 389, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 436, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 389, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 436, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 389, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 436, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":395 + /* "gensim/models/fasttext_inner.pyx":442 * cdef np.uint32_t reduced_windows[MAX_SENTENCE_LEN] * cdef int sentence_idx[MAX_SENTENCE_LEN + 1] * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 395, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 442, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 395, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 442, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":398 + /* "gensim/models/fasttext_inner.pyx":445 * * cdef int i, j, k * cdef int effective_words = 0, effective_sentences = 0 # <<<<<<<<<<<<<< @@ -5266,19 +5356,19 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_v_effective_words = 0; __pyx_v_effective_sentences = 0; - /* "gensim/models/fasttext_inner.pyx":418 + /* "gensim/models/fasttext_inner.pyx":465 * # dummy dictionary to ensure that the memory locations that subwords_idx point to * # are referenced throughout so that it isn't put back to free memory pool by Python's memory manager * subword_arrays = {} # <<<<<<<<<<<<<< * * if hs: */ - __pyx_t_3 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 418, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 465, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_v_subword_arrays = ((PyObject*)__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":420 + /* "gensim/models/fasttext_inner.pyx":467 * subword_arrays = {} * * if hs: # <<<<<<<<<<<<<< @@ -5288,23 +5378,23 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":421 + /* "gensim/models/fasttext_inner.pyx":468 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 421, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 468, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 421, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 468, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 421, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 468, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":420 + /* "gensim/models/fasttext_inner.pyx":467 * subword_arrays = {} * * if hs: # <<<<<<<<<<<<<< @@ -5313,7 +5403,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":423 + /* "gensim/models/fasttext_inner.pyx":470 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -5323,55 +5413,55 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":424 + /* "gensim/models/fasttext_inner.pyx":471 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 424, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 471, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 424, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 471, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 424, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 471, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":425 + /* "gensim/models/fasttext_inner.pyx":472 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 425, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 472, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 425, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 472, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 425, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 472, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":426 + /* "gensim/models/fasttext_inner.pyx":473 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 426, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 473, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 426, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 473, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 426, __pyx_L1_error) + __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 473, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_6; - /* "gensim/models/fasttext_inner.pyx":423 + /* "gensim/models/fasttext_inner.pyx":470 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -5380,7 +5470,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":427 + /* "gensim/models/fasttext_inner.pyx":474 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -5398,41 +5488,41 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_L6_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":428 + /* "gensim/models/fasttext_inner.pyx":475 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_next_random = __pyx_t_9; - /* "gensim/models/fasttext_inner.pyx":427 + /* "gensim/models/fasttext_inner.pyx":474 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -5441,42 +5531,42 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":431 + /* "gensim/models/fasttext_inner.pyx":478 * * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) # <<<<<<<<<<<<<< * neu1 = np.PyArray_DATA(_neu1) * */ - if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 431, __pyx_L1_error) + if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 478, __pyx_L1_error) __pyx_v_work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__work))); - /* "gensim/models/fasttext_inner.pyx":432 + /* "gensim/models/fasttext_inner.pyx":479 * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) * neu1 = np.PyArray_DATA(_neu1) # <<<<<<<<<<<<<< * * # prepare C structures so we can go "full C" and release the Python GIL */ - if (!(likely(((__pyx_v__neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 432, __pyx_L1_error) + if (!(likely(((__pyx_v__neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 479, __pyx_L1_error) __pyx_v_neu1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__neu1))); - /* "gensim/models/fasttext_inner.pyx":435 + /* "gensim/models/fasttext_inner.pyx":482 * * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 435, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 482, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 435, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 482, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_vlookup = __pyx_t_3; __pyx_t_3 = 0; - /* "gensim/models/fasttext_inner.pyx":436 + /* "gensim/models/fasttext_inner.pyx":483 * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 # <<<<<<<<<<<<<< @@ -5485,7 +5575,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ (__pyx_v_sentence_idx[0]) = 0; - /* "gensim/models/fasttext_inner.pyx":437 + /* "gensim/models/fasttext_inner.pyx":484 * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: # <<<<<<<<<<<<<< @@ -5496,26 +5586,26 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_3 = __pyx_v_sentences; __Pyx_INCREF(__pyx_t_3); __pyx_t_6 = 0; __pyx_t_10 = NULL; } else { - __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 437, __pyx_L1_error) + __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 484, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 437, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 484, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_10)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 437, __pyx_L1_error) + __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 484, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 437, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 484, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 437, __pyx_L1_error) + __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 484, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 437, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 484, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } @@ -5525,7 +5615,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 437, __pyx_L1_error) + else __PYX_ERR(0, 484, __pyx_L1_error) } break; } @@ -5534,18 +5624,18 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_sent, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/fasttext_inner.pyx":438 + /* "gensim/models/fasttext_inner.pyx":485 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: */ - __pyx_t_5 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 438, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_5 < 0)) __PYX_ERR(0, 485, __pyx_L1_error) __pyx_t_7 = ((!__pyx_t_5) != 0); if (__pyx_t_7) { - /* "gensim/models/fasttext_inner.pyx":439 + /* "gensim/models/fasttext_inner.pyx":486 * for sent in sentences: * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged # <<<<<<<<<<<<<< @@ -5554,7 +5644,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ goto __pyx_L8_continue; - /* "gensim/models/fasttext_inner.pyx":438 + /* "gensim/models/fasttext_inner.pyx":485 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< @@ -5563,7 +5653,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":440 + /* "gensim/models/fasttext_inner.pyx":487 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -5574,26 +5664,26 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_8 = __pyx_v_sent; __Pyx_INCREF(__pyx_t_8); __pyx_t_11 = 0; __pyx_t_12 = NULL; } else { - __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 440, __pyx_L1_error) + __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 487, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 440, __pyx_L1_error) + __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 487, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_12)) { if (likely(PyList_CheckExact(__pyx_t_8))) { if (__pyx_t_11 >= PyList_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 440, __pyx_L1_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 487, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 440, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 487, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_11 >= PyTuple_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 440, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 487, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 440, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 487, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -5603,7 +5693,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 440, __pyx_L1_error) + else __PYX_ERR(0, 487, __pyx_L1_error) } break; } @@ -5612,16 +5702,16 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":441 + /* "gensim/models/fasttext_inner.pyx":488 * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: * word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window */ - __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 488, __pyx_L1_error) if ((__pyx_t_7 != 0)) { - __pyx_t_13 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 488, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __pyx_t_1 = __pyx_t_13; __pyx_t_13 = 0; @@ -5632,7 +5722,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_word, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":442 + /* "gensim/models/fasttext_inner.pyx":489 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -5643,7 +5733,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = (__pyx_t_7 != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":443 + /* "gensim/models/fasttext_inner.pyx":490 * word = vlookup[token] if token in vlookup else None * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window # <<<<<<<<<<<<<< @@ -5652,7 +5742,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ goto __pyx_L11_continue; - /* "gensim/models/fasttext_inner.pyx":442 + /* "gensim/models/fasttext_inner.pyx":489 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -5661,7 +5751,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":444 + /* "gensim/models/fasttext_inner.pyx":491 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -5674,20 +5764,20 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = __pyx_t_7; goto __pyx_L15_bool_binop_done; } - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 444, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 491, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 444, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 491, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 444, __pyx_L1_error) + __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 491, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; - __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 444, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 491, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __pyx_t_5 = __pyx_t_7; __pyx_L15_bool_binop_done:; if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":445 + /* "gensim/models/fasttext_inner.pyx":492 * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -5696,7 +5786,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ goto __pyx_L11_continue; - /* "gensim/models/fasttext_inner.pyx":444 + /* "gensim/models/fasttext_inner.pyx":491 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -5705,67 +5795,67 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":446 + /* "gensim/models/fasttext_inner.pyx":493 * if sample and word.sample_int < random_int32(&next_random): * continue * indexes[effective_words] = word.index # <<<<<<<<<<<<<< * * subwords = model.wv.buckets_word[word.index] */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 446, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 493, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 446, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 493, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; (__pyx_v_indexes[__pyx_v_effective_words]) = __pyx_t_15; - /* "gensim/models/fasttext_inner.pyx":448 + /* "gensim/models/fasttext_inner.pyx":495 * indexes[effective_words] = word.index * * subwords = model.wv.buckets_word[word.index] # <<<<<<<<<<<<<< * word_subwords = np.array(subwords, dtype=np.uint32) * subwords_idx_len[effective_words] = len(subwords) */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 495, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_13 = __Pyx_PyObject_GetAttrStr(__pyx_t_14, __pyx_n_s_buckets_word); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyObject_GetAttrStr(__pyx_t_14, __pyx_n_s_buckets_word); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 495, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 495, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_1 = PyObject_GetItem(__pyx_t_13, __pyx_t_14); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetItem(__pyx_t_13, __pyx_t_14); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 495, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_XDECREF_SET(__pyx_v_subwords, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":449 + /* "gensim/models/fasttext_inner.pyx":496 * * subwords = model.wv.buckets_word[word.index] * word_subwords = np.array(subwords, dtype=np.uint32) # <<<<<<<<<<<<<< * subwords_idx_len[effective_words] = len(subwords) * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_array); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_array); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_v_subwords); __Pyx_GIVEREF(__pyx_v_subwords); PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_v_subwords); - __pyx_t_13 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_16 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_16 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_16)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_16); - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_t_16, __pyx_n_s_uint32); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_t_16, __pyx_n_s_uint32); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); __Pyx_DECREF(__pyx_t_16); __pyx_t_16 = 0; - if (PyDict_SetItem(__pyx_t_13, __pyx_n_s_dtype, __pyx_t_17) < 0) __PYX_ERR(0, 449, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_13, __pyx_n_s_dtype, __pyx_t_17) < 0) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - __pyx_t_17 = __Pyx_PyObject_Call(__pyx_t_14, __pyx_t_1, __pyx_t_13); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 449, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_Call(__pyx_t_14, __pyx_t_1, __pyx_t_13); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 496, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -5773,39 +5863,39 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_word_subwords, __pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":450 + /* "gensim/models/fasttext_inner.pyx":497 * subwords = model.wv.buckets_word[word.index] * word_subwords = np.array(subwords, dtype=np.uint32) * subwords_idx_len[effective_words] = len(subwords) # <<<<<<<<<<<<<< * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) * # ensures reference count of word_subwords doesn't reach 0 */ - __pyx_t_18 = PyObject_Length(__pyx_v_subwords); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 450, __pyx_L1_error) + __pyx_t_18 = PyObject_Length(__pyx_v_subwords); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 497, __pyx_L1_error) (__pyx_v_subwords_idx_len[__pyx_v_effective_words]) = ((int)__pyx_t_18); - /* "gensim/models/fasttext_inner.pyx":451 + /* "gensim/models/fasttext_inner.pyx":498 * word_subwords = np.array(subwords, dtype=np.uint32) * subwords_idx_len[effective_words] = len(subwords) * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) # <<<<<<<<<<<<<< * # ensures reference count of word_subwords doesn't reach 0 * subword_arrays[effective_words] = word_subwords */ - if (!(likely(((__pyx_v_word_subwords) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_subwords, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 451, __pyx_L1_error) + if (!(likely(((__pyx_v_word_subwords) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_word_subwords, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 498, __pyx_L1_error) (__pyx_v_subwords_idx[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_v_word_subwords))); - /* "gensim/models/fasttext_inner.pyx":453 + /* "gensim/models/fasttext_inner.pyx":500 * subwords_idx[effective_words] = np.PyArray_DATA(word_subwords) * # ensures reference count of word_subwords doesn't reach 0 * subword_arrays[effective_words] = word_subwords # <<<<<<<<<<<<<< * * if hs: */ - __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 453, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 500, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - if (unlikely(PyDict_SetItem(__pyx_v_subword_arrays, __pyx_t_17, __pyx_v_word_subwords) < 0)) __PYX_ERR(0, 453, __pyx_L1_error) + if (unlikely(PyDict_SetItem(__pyx_v_subword_arrays, __pyx_t_17, __pyx_v_word_subwords) < 0)) __PYX_ERR(0, 500, __pyx_L1_error) __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":455 + /* "gensim/models/fasttext_inner.pyx":502 * subword_arrays[effective_words] = word_subwords * * if hs: # <<<<<<<<<<<<<< @@ -5815,46 +5905,46 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":456 + /* "gensim/models/fasttext_inner.pyx":503 * * if hs: * codelens[effective_words] = len(word.code) # <<<<<<<<<<<<<< * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) */ - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 456, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 503, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - __pyx_t_18 = PyObject_Length(__pyx_t_17); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 456, __pyx_L1_error) + __pyx_t_18 = PyObject_Length(__pyx_t_17); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 503, __pyx_L1_error) __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; (__pyx_v_codelens[__pyx_v_effective_words]) = ((int)__pyx_t_18); - /* "gensim/models/fasttext_inner.pyx":457 + /* "gensim/models/fasttext_inner.pyx":504 * if hs: * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) # <<<<<<<<<<<<<< * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 */ - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 504, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 457, __pyx_L1_error) + if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 504, __pyx_L1_error) (__pyx_v_codes[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_17))); __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":458 + /* "gensim/models/fasttext_inner.pyx":505 * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) # <<<<<<<<<<<<<< * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: */ - __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 458, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); - if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 458, __pyx_L1_error) + if (!(likely(((__pyx_t_17) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_17, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 505, __pyx_L1_error) (__pyx_v_points[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_17))); __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":455 + /* "gensim/models/fasttext_inner.pyx":502 * subword_arrays[effective_words] = word_subwords * * if hs: # <<<<<<<<<<<<<< @@ -5863,7 +5953,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":459 + /* "gensim/models/fasttext_inner.pyx":506 * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 # <<<<<<<<<<<<<< @@ -5872,7 +5962,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_effective_words = (__pyx_v_effective_words + 1); - /* "gensim/models/fasttext_inner.pyx":460 + /* "gensim/models/fasttext_inner.pyx":507 * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -5882,7 +5972,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = ((__pyx_v_effective_words == 0x2710) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":461 + /* "gensim/models/fasttext_inner.pyx":508 * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: * break # <<<<<<<<<<<<<< @@ -5891,7 +5981,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ goto __pyx_L12_break; - /* "gensim/models/fasttext_inner.pyx":460 + /* "gensim/models/fasttext_inner.pyx":507 * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -5900,7 +5990,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":440 + /* "gensim/models/fasttext_inner.pyx":487 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -5912,7 +6002,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_L12_break:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/fasttext_inner.pyx":466 + /* "gensim/models/fasttext_inner.pyx":513 * # across sentence boundaries. * # indices of sentence number X are between tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 473, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_17)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 520, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; for (;;) { @@ -6053,17 +6143,17 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT if (likely(PyList_CheckExact(__pyx_t_17))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_17)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyList_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 473, __pyx_L1_error) + __pyx_t_3 = PyList_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 520, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 473, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 520, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_17)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 473, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_17, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 520, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 473, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_17, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 520, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } @@ -6073,7 +6163,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 473, __pyx_L1_error) + else __PYX_ERR(0, 520, __pyx_L1_error) } break; } @@ -6084,17 +6174,17 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_v_i = __pyx_t_2; __pyx_t_2 = (__pyx_t_2 + 1); - /* "gensim/models/fasttext_inner.pyx":474 + /* "gensim/models/fasttext_inner.pyx":521 * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): * reduced_windows[i] = item # <<<<<<<<<<<<<< * * # release GIL & train on all sentences */ - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 474, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 521, __pyx_L1_error) (__pyx_v_reduced_windows[__pyx_v_i]) = __pyx_t_15; - /* "gensim/models/fasttext_inner.pyx":473 + /* "gensim/models/fasttext_inner.pyx":520 * * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): # <<<<<<<<<<<<<< @@ -6104,7 +6194,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT } __Pyx_DECREF(__pyx_t_17); __pyx_t_17 = 0; - /* "gensim/models/fasttext_inner.pyx":477 + /* "gensim/models/fasttext_inner.pyx":524 * * # release GIL & train on all sentences * with nogil: # <<<<<<<<<<<<<< @@ -6119,7 +6209,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT #endif /*try:*/ { - /* "gensim/models/fasttext_inner.pyx":478 + /* "gensim/models/fasttext_inner.pyx":525 * # release GIL & train on all sentences * with nogil: * for sent_idx in range(effective_sentences): # <<<<<<<<<<<<<< @@ -6127,10 +6217,11 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT * idx_end = sentence_idx[sent_idx + 1] */ __pyx_t_2 = __pyx_v_effective_sentences; - for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_2; __pyx_t_19+=1) { - __pyx_v_sent_idx = __pyx_t_19; + __pyx_t_19 = __pyx_t_2; + for (__pyx_t_20 = 0; __pyx_t_20 < __pyx_t_19; __pyx_t_20+=1) { + __pyx_v_sent_idx = __pyx_t_20; - /* "gensim/models/fasttext_inner.pyx":479 + /* "gensim/models/fasttext_inner.pyx":526 * with nogil: * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] # <<<<<<<<<<<<<< @@ -6139,7 +6230,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_idx_start = (__pyx_v_sentence_idx[__pyx_v_sent_idx]); - /* "gensim/models/fasttext_inner.pyx":480 + /* "gensim/models/fasttext_inner.pyx":527 * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] # <<<<<<<<<<<<<< @@ -6148,18 +6239,19 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_idx_end = (__pyx_v_sentence_idx[(__pyx_v_sent_idx + 1)]); - /* "gensim/models/fasttext_inner.pyx":481 + /* "gensim/models/fasttext_inner.pyx":528 * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): # <<<<<<<<<<<<<< * j = i - window + reduced_windows[i] * if j < idx_start: */ - __pyx_t_20 = __pyx_v_idx_end; - for (__pyx_t_21 = __pyx_v_idx_start; __pyx_t_21 < __pyx_t_20; __pyx_t_21+=1) { - __pyx_v_i = __pyx_t_21; + __pyx_t_21 = __pyx_v_idx_end; + __pyx_t_22 = __pyx_t_21; + for (__pyx_t_23 = __pyx_v_idx_start; __pyx_t_23 < __pyx_t_22; __pyx_t_23+=1) { + __pyx_v_i = __pyx_t_23; - /* "gensim/models/fasttext_inner.pyx":482 + /* "gensim/models/fasttext_inner.pyx":529 * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] # <<<<<<<<<<<<<< @@ -6168,7 +6260,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_j = ((__pyx_v_i - __pyx_v_window) + (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/fasttext_inner.pyx":483 + /* "gensim/models/fasttext_inner.pyx":530 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -6178,7 +6270,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = ((__pyx_v_j < __pyx_v_idx_start) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":484 + /* "gensim/models/fasttext_inner.pyx":531 * j = i - window + reduced_windows[i] * if j < idx_start: * j = idx_start # <<<<<<<<<<<<<< @@ -6187,7 +6279,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_j = __pyx_v_idx_start; - /* "gensim/models/fasttext_inner.pyx":483 + /* "gensim/models/fasttext_inner.pyx":530 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -6196,7 +6288,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":485 + /* "gensim/models/fasttext_inner.pyx":532 * if j < idx_start: * j = idx_start * k = i + window + 1 - reduced_windows[i] # <<<<<<<<<<<<<< @@ -6205,7 +6297,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_k = (((__pyx_v_i + __pyx_v_window) + 1) - (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/fasttext_inner.pyx":486 + /* "gensim/models/fasttext_inner.pyx":533 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -6215,7 +6307,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = ((__pyx_v_k > __pyx_v_idx_end) != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":487 + /* "gensim/models/fasttext_inner.pyx":534 * k = i + window + 1 - reduced_windows[i] * if k > idx_end: * k = idx_end # <<<<<<<<<<<<<< @@ -6224,7 +6316,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_k = __pyx_v_idx_end; - /* "gensim/models/fasttext_inner.pyx":486 + /* "gensim/models/fasttext_inner.pyx":533 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -6233,7 +6325,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":489 + /* "gensim/models/fasttext_inner.pyx":536 * k = idx_end * * if hs: # <<<<<<<<<<<<<< @@ -6243,7 +6335,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = (__pyx_v_hs != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":490 + /* "gensim/models/fasttext_inner.pyx":537 * * if hs: * fast_sentence_cbow_hs( # <<<<<<<<<<<<<< @@ -6252,7 +6344,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), __pyx_v_codelens, __pyx_v_neu1, __pyx_v_syn0_vocab, __pyx_v_syn0_ngrams, __pyx_v_syn1, __pyx_v_size, __pyx_v_indexes, __pyx_v_subwords_idx, __pyx_v_subwords_idx_len, __pyx_v__alpha, __pyx_v_work, __pyx_v_i, __pyx_v_j, __pyx_v_k, __pyx_v_cbow_mean, __pyx_v_word_locks_vocab, __pyx_v_word_locks_ngrams); - /* "gensim/models/fasttext_inner.pyx":489 + /* "gensim/models/fasttext_inner.pyx":536 * k = idx_end * * if hs: # <<<<<<<<<<<<<< @@ -6261,7 +6353,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/fasttext_inner.pyx":494 + /* "gensim/models/fasttext_inner.pyx":541 * subwords_idx,subwords_idx_len,_alpha, work, i, j, k, cbow_mean, word_locks_vocab, * word_locks_ngrams) * if negative: # <<<<<<<<<<<<<< @@ -6271,7 +6363,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT __pyx_t_5 = (__pyx_v_negative != 0); if (__pyx_t_5) { - /* "gensim/models/fasttext_inner.pyx":495 + /* "gensim/models/fasttext_inner.pyx":542 * word_locks_ngrams) * if negative: * next_random = fast_sentence_cbow_neg( # <<<<<<<<<<<<<< @@ -6280,7 +6372,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT */ __pyx_v_next_random = __pyx_f_6gensim_6models_14fasttext_inner_fast_sentence_cbow_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v_codelens, __pyx_v_neu1, __pyx_v_syn0_vocab, __pyx_v_syn0_ngrams, __pyx_v_syn1neg, __pyx_v_size, __pyx_v_indexes, __pyx_v_subwords_idx, __pyx_v_subwords_idx_len, __pyx_v__alpha, __pyx_v_work, __pyx_v_i, __pyx_v_j, __pyx_v_k, __pyx_v_cbow_mean, __pyx_v_next_random, __pyx_v_word_locks_vocab, __pyx_v_word_locks_ngrams); - /* "gensim/models/fasttext_inner.pyx":494 + /* "gensim/models/fasttext_inner.pyx":541 * subwords_idx,subwords_idx_len,_alpha, work, i, j, k, cbow_mean, word_locks_vocab, * word_locks_ngrams) * if negative: # <<<<<<<<<<<<<< @@ -6292,7 +6384,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT } } - /* "gensim/models/fasttext_inner.pyx":477 + /* "gensim/models/fasttext_inner.pyx":524 * * # release GIL & train on all sentences * with nogil: # <<<<<<<<<<<<<< @@ -6311,7 +6403,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT } } - /* "gensim/models/fasttext_inner.pyx":500 + /* "gensim/models/fasttext_inner.pyx":547 * cbow_mean, next_random, word_locks_vocab, word_locks_ngrams) * * return effective_words # <<<<<<<<<<<<<< @@ -6319,18 +6411,18 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 500, __pyx_L1_error) + __pyx_t_17 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_17)) __PYX_ERR(0, 547, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_17); __pyx_r = __pyx_t_17; __pyx_t_17 = 0; goto __pyx_L0; - /* "gensim/models/fasttext_inner.pyx":376 + /* "gensim/models/fasttext_inner.pyx":400 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update the CBOW model by training on a sequence of sentences. + * */ /* function exit code */ @@ -6358,17 +6450,17 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_2train_batch_cbow(CYT return __pyx_r; } -/* "gensim/models/fasttext_inner.pyx":503 +/* "gensim/models/fasttext_inner.pyx":550 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_5init(PyObject *__pyx_self, CYTHON_UNUSED PyObject *unused); /*proto*/ -static char __pyx_doc_6gensim_6models_14fasttext_inner_4init[] = "\n Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized\n into table EXP_TABLE. Also calculate log(sigmoid(x)) into LOG_TABLE.\n "; +static char __pyx_doc_6gensim_6models_14fasttext_inner_4init[] = "init()\nPrecompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE.\n Also calculate log(sigmoid(x)) into LOG_TABLE.\n\n Returns\n -------\n {0, 1, 2}\n Enumeration to signify underlying data type returned by the BLAS dot product calculation.\n 0 signifies double, 1 signifies double, and 2 signifies that custom cython loops were used\n instead of BLAS.\n\n "; static PyMethodDef __pyx_mdef_6gensim_6models_14fasttext_inner_5init = {"init", (PyCFunction)__pyx_pw_6gensim_6models_14fasttext_inner_5init, METH_NOARGS, __pyx_doc_6gensim_6models_14fasttext_inner_4init}; static PyObject *__pyx_pw_6gensim_6models_14fasttext_inner_5init(PyObject *__pyx_self, CYTHON_UNUSED PyObject *unused) { PyObject *__pyx_r = 0; @@ -6397,7 +6489,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P int __pyx_t_4; __Pyx_RefNannySetupContext("init", 0); - /* "gensim/models/fasttext_inner.pyx":512 + /* "gensim/models/fasttext_inner.pyx":566 * * cdef int i * cdef float *x = [10.0] # <<<<<<<<<<<<<< @@ -6407,7 +6499,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P __pyx_t_1[0] = ((float)10.0); __pyx_v_x = __pyx_t_1; - /* "gensim/models/fasttext_inner.pyx":513 + /* "gensim/models/fasttext_inner.pyx":567 * cdef int i * cdef float *x = [10.0] * cdef float *y = [0.01] # <<<<<<<<<<<<<< @@ -6417,7 +6509,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P __pyx_t_2[0] = ((float)0.01); __pyx_v_y = __pyx_t_2; - /* "gensim/models/fasttext_inner.pyx":514 + /* "gensim/models/fasttext_inner.pyx":568 * cdef float *x = [10.0] * cdef float *y = [0.01] * cdef float expected = 0.1 # <<<<<<<<<<<<<< @@ -6426,7 +6518,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P */ __pyx_v_expected = ((float)0.1); - /* "gensim/models/fasttext_inner.pyx":515 + /* "gensim/models/fasttext_inner.pyx":569 * cdef float *y = [0.01] * cdef float expected = 0.1 * cdef int size = 1 # <<<<<<<<<<<<<< @@ -6435,7 +6527,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P */ __pyx_v_size = 1; - /* "gensim/models/fasttext_inner.pyx":520 + /* "gensim/models/fasttext_inner.pyx":574 * * # build the sigmoid table * for i in range(EXP_TABLE_SIZE): # <<<<<<<<<<<<<< @@ -6445,7 +6537,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P for (__pyx_t_3 = 0; __pyx_t_3 < 0x3E8; __pyx_t_3+=1) { __pyx_v_i = __pyx_t_3; - /* "gensim/models/fasttext_inner.pyx":521 + /* "gensim/models/fasttext_inner.pyx":575 * # build the sigmoid table * for i in range(EXP_TABLE_SIZE): * EXP_TABLE[i] = exp((i / EXP_TABLE_SIZE * 2 - 1) * MAX_EXP) # <<<<<<<<<<<<<< @@ -6454,7 +6546,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P */ (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)exp(((((__pyx_v_i / ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0x3E8)) * 2.0) - 1.0) * 6.0))); - /* "gensim/models/fasttext_inner.pyx":522 + /* "gensim/models/fasttext_inner.pyx":576 * for i in range(EXP_TABLE_SIZE): * EXP_TABLE[i] = exp((i / EXP_TABLE_SIZE * 2 - 1) * MAX_EXP) * EXP_TABLE[i] = (EXP_TABLE[i] / (EXP_TABLE[i] + 1)) # <<<<<<<<<<<<<< @@ -6463,7 +6555,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P */ (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)((__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) / ((__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) + 1.0))); - /* "gensim/models/fasttext_inner.pyx":523 + /* "gensim/models/fasttext_inner.pyx":577 * EXP_TABLE[i] = exp((i / EXP_TABLE_SIZE * 2 - 1) * MAX_EXP) * EXP_TABLE[i] = (EXP_TABLE[i] / (EXP_TABLE[i] + 1)) * LOG_TABLE[i] = log( EXP_TABLE[i] ) # <<<<<<<<<<<<<< @@ -6473,57 +6565,57 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P (__pyx_v_6gensim_6models_14fasttext_inner_LOG_TABLE[__pyx_v_i]) = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)log((__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]))); } - /* "gensim/models/fasttext_inner.pyx":526 + /* "gensim/models/fasttext_inner.pyx":580 * * # check whether sdot returns double or float * d_res = dsdot(&size, x, &ONE, y, &ONE) # <<<<<<<<<<<<<< * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): + * if abs(d_res - expected) < 0.0001: */ __pyx_v_d_res = __pyx_v_6gensim_6models_14word2vec_inner_dsdot((&__pyx_v_size), __pyx_v_x, (&__pyx_v_6gensim_6models_14fasttext_inner_ONE), __pyx_v_y, (&__pyx_v_6gensim_6models_14fasttext_inner_ONE)); - /* "gensim/models/fasttext_inner.pyx":527 + /* "gensim/models/fasttext_inner.pyx":581 * # check whether sdot returns double or float * d_res = dsdot(&size, x, &ONE, y, &ONE) * p_res = &d_res # <<<<<<<<<<<<<< - * if (abs(d_res - expected) < 0.0001): + * if abs(d_res - expected) < 0.0001: * our_dot = our_dot_double */ __pyx_v_p_res = ((float *)(&__pyx_v_d_res)); - /* "gensim/models/fasttext_inner.pyx":528 + /* "gensim/models/fasttext_inner.pyx":582 * d_res = dsdot(&size, x, &ONE, y, &ONE) * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): # <<<<<<<<<<<<<< + * if abs(d_res - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_double * our_saxpy = saxpy */ __pyx_t_4 = ((fabs((__pyx_v_d_res - __pyx_v_expected)) < 0.0001) != 0); if (__pyx_t_4) { - /* "gensim/models/fasttext_inner.pyx":529 + /* "gensim/models/fasttext_inner.pyx":583 * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): + * if abs(d_res - expected) < 0.0001: * our_dot = our_dot_double # <<<<<<<<<<<<<< * our_saxpy = saxpy * return 0 # double */ __pyx_v_6gensim_6models_14word2vec_inner_our_dot = __pyx_f_6gensim_6models_14word2vec_inner_our_dot_double; - /* "gensim/models/fasttext_inner.pyx":530 - * if (abs(d_res - expected) < 0.0001): + /* "gensim/models/fasttext_inner.pyx":584 + * if abs(d_res - expected) < 0.0001: * our_dot = our_dot_double * our_saxpy = saxpy # <<<<<<<<<<<<<< * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): + * elif abs(p_res[0] - expected) < 0.0001: */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy = __pyx_v_6gensim_6models_14word2vec_inner_saxpy; - /* "gensim/models/fasttext_inner.pyx":531 + /* "gensim/models/fasttext_inner.pyx":585 * our_dot = our_dot_double * our_saxpy = saxpy * return 0 # double # <<<<<<<<<<<<<< - * elif (abs(p_res[0] - expected) < 0.0001): + * elif abs(p_res[0] - expected) < 0.0001: * our_dot = our_dot_float */ __Pyx_XDECREF(__pyx_r); @@ -6531,36 +6623,36 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P __pyx_r = __pyx_int_0; goto __pyx_L0; - /* "gensim/models/fasttext_inner.pyx":528 + /* "gensim/models/fasttext_inner.pyx":582 * d_res = dsdot(&size, x, &ONE, y, &ONE) * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): # <<<<<<<<<<<<<< + * if abs(d_res - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_double * our_saxpy = saxpy */ } - /* "gensim/models/fasttext_inner.pyx":532 + /* "gensim/models/fasttext_inner.pyx":586 * our_saxpy = saxpy * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): # <<<<<<<<<<<<<< + * elif abs(p_res[0] - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_float * our_saxpy = saxpy */ __pyx_t_4 = ((fabsf(((__pyx_v_p_res[0]) - __pyx_v_expected)) < 0.0001) != 0); if (__pyx_t_4) { - /* "gensim/models/fasttext_inner.pyx":533 + /* "gensim/models/fasttext_inner.pyx":587 * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): + * elif abs(p_res[0] - expected) < 0.0001: * our_dot = our_dot_float # <<<<<<<<<<<<<< * our_saxpy = saxpy * return 1 # float */ __pyx_v_6gensim_6models_14word2vec_inner_our_dot = __pyx_f_6gensim_6models_14word2vec_inner_our_dot_float; - /* "gensim/models/fasttext_inner.pyx":534 - * elif (abs(p_res[0] - expected) < 0.0001): + /* "gensim/models/fasttext_inner.pyx":588 + * elif abs(p_res[0] - expected) < 0.0001: * our_dot = our_dot_float * our_saxpy = saxpy # <<<<<<<<<<<<<< * return 1 # float @@ -6568,7 +6660,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy = __pyx_v_6gensim_6models_14word2vec_inner_saxpy; - /* "gensim/models/fasttext_inner.pyx":535 + /* "gensim/models/fasttext_inner.pyx":589 * our_dot = our_dot_float * our_saxpy = saxpy * return 1 # float # <<<<<<<<<<<<<< @@ -6580,16 +6672,16 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P __pyx_r = __pyx_int_1; goto __pyx_L0; - /* "gensim/models/fasttext_inner.pyx":532 + /* "gensim/models/fasttext_inner.pyx":586 * our_saxpy = saxpy * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): # <<<<<<<<<<<<<< + * elif abs(p_res[0] - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_float * our_saxpy = saxpy */ } - /* "gensim/models/fasttext_inner.pyx":539 + /* "gensim/models/fasttext_inner.pyx":593 * # neither => use cython loops, no BLAS * # actually, the BLAS is so messed up we'll probably have segfaulted above and never even reach here * our_dot = our_dot_noblas # <<<<<<<<<<<<<< @@ -6599,7 +6691,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P /*else*/ { __pyx_v_6gensim_6models_14word2vec_inner_our_dot = __pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas; - /* "gensim/models/fasttext_inner.pyx":540 + /* "gensim/models/fasttext_inner.pyx":594 * # actually, the BLAS is so messed up we'll probably have segfaulted above and never even reach here * our_dot = our_dot_noblas * our_saxpy = our_saxpy_noblas # <<<<<<<<<<<<<< @@ -6608,7 +6700,7 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy = __pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas; - /* "gensim/models/fasttext_inner.pyx":541 + /* "gensim/models/fasttext_inner.pyx":595 * our_dot = our_dot_noblas * our_saxpy = our_saxpy_noblas * return 2 # <<<<<<<<<<<<<< @@ -6621,12 +6713,12 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P goto __pyx_L0; } - /* "gensim/models/fasttext_inner.pyx":503 + /* "gensim/models/fasttext_inner.pyx":550 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ /* function exit code */ @@ -6636,12 +6728,12 @@ static PyObject *__pyx_pf_6gensim_6models_14fasttext_inner_4init(CYTHON_UNUSED P return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* Python wrapper */ @@ -6658,7 +6750,6 @@ static CYTHON_UNUSED int __pyx_pw_5numpy_7ndarray_1__getbuffer__(PyObject *__pyx } static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags) { - int __pyx_v_copy_shape; int __pyx_v_i; int __pyx_v_ndim; int __pyx_v_endian_detector; @@ -6667,7 +6758,6 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P char *__pyx_v_f; PyArray_Descr *__pyx_v_descr = 0; int __pyx_v_offset; - int __pyx_v_hasfields; int __pyx_r; __Pyx_RefNannyDeclarations int __pyx_t_1; @@ -6675,38 +6765,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P PyObject *__pyx_t_3 = NULL; int __pyx_t_4; int __pyx_t_5; - PyObject *__pyx_t_6 = NULL; - char *__pyx_t_7; - __Pyx_RefNannySetupContext("__getbuffer__", 0); - if (__pyx_v_info != NULL) { - __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(__pyx_v_info->obj); - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":220 - * # of flags - * - * if info == NULL: return # <<<<<<<<<<<<<< - * - * cdef int copy_shape, i, ndim - */ - __pyx_t_1 = ((__pyx_v_info == NULL) != 0); - if (__pyx_t_1) { - __pyx_r = 0; - goto __pyx_L0; + int __pyx_t_6; + PyObject *__pyx_t_7 = NULL; + char *__pyx_t_8; + if (__pyx_v_info == NULL) { + PyErr_SetString(PyExc_BufferError, "PyObject_GetBuffer: view==NULL argument is obsolete"); + return -1; } + __Pyx_RefNannySetupContext("__getbuffer__", 0); + __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); + __Pyx_GIVEREF(__pyx_v_info->obj); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":222 * - * cdef int copy_shape, i, ndim + * cdef int i, ndim * cdef int endian_detector = 1 # <<<<<<<<<<<<<< * cdef bint little_endian = ((&endian_detector)[0] != 0) * */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":224 - * cdef int copy_shape, i, ndim + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + * cdef int i, ndim * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< * @@ -6714,59 +6794,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":226 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":225 * cdef bint little_endian = ((&endian_detector)[0] != 0) * * ndim = PyArray_NDIM(self) # <<<<<<<<<<<<<< * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): + * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) */ __pyx_v_ndim = PyArray_NDIM(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 - * ndim = PyArray_NDIM(self) - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): - * copy_shape = 1 # <<<<<<<<<<<<<< - * else: - * copy_shape = 0 - */ - __pyx_v_copy_shape = 1; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 * ndim = PyArray_NDIM(self) * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - goto __pyx_L4; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 - * copy_shape = 1 - * else: - * copy_shape = 0 # <<<<<<<<<<<<<< - * - * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) - */ - /*else*/ { - __pyx_v_copy_shape = 0; - } - __pyx_L4:; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 - * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") @@ -6775,10 +6814,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L6_bool_binop_done; + goto __pyx_L4_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":234 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -6787,32 +6826,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_C_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L6_bool_binop_done:; + __pyx_L4_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 235, __pyx_L1_error) + __PYX_ERR(1, 229, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): @@ -6820,7 +6859,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -6831,10 +6870,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L9_bool_binop_done; + goto __pyx_L7_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":238 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":232 * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -6843,31 +6882,31 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_F_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L9_bool_binop_done:; + __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 239, __pyx_L1_error) + __PYX_ERR(1, 233, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -6876,35 +6915,35 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 * raise ValueError(u"ndarray is not Fortran contiguous") * * info.buf = PyArray_DATA(self) # <<<<<<<<<<<<<< * info.ndim = ndim - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): */ __pyx_v_info->buf = PyArray_DATA(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":236 * * info.buf = PyArray_DATA(self) * info.ndim = ndim # <<<<<<<<<<<<<< - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): * # Allocate new buffer for strides and shape info. */ __pyx_v_info->ndim = __pyx_v_ndim; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - __pyx_t_1 = (__pyx_v_copy_shape != 0); + __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":240 * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) # <<<<<<<<<<<<<< @@ -6913,7 +6952,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->strides = ((Py_ssize_t *)PyObject_Malloc((((sizeof(Py_ssize_t)) * 2) * ((size_t)__pyx_v_ndim)))); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim # <<<<<<<<<<<<<< @@ -6922,7 +6961,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = (__pyx_v_info->strides + __pyx_v_ndim); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim * for i in range(ndim): # <<<<<<<<<<<<<< @@ -6930,10 +6969,11 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P * info.shape[i] = PyArray_DIMS(self)[i] */ __pyx_t_4 = __pyx_v_ndim; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 * info.shape = info.strides + ndim * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] # <<<<<<<<<<<<<< @@ -6942,7 +6982,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->strides[__pyx_v_i]) = (PyArray_STRIDES(__pyx_v_self)[__pyx_v_i]); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":244 * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] * info.shape[i] = PyArray_DIMS(self)[i] # <<<<<<<<<<<<<< @@ -6952,17 +6992,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_info->shape[__pyx_v_i]) = (PyArray_DIMS(__pyx_v_self)[__pyx_v_i]); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - goto __pyx_L11; + goto __pyx_L9; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":252 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 * info.shape[i] = PyArray_DIMS(self)[i] * else: * info.strides = PyArray_STRIDES(self) # <<<<<<<<<<<<<< @@ -6972,7 +7012,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->strides = ((Py_ssize_t *)PyArray_STRIDES(__pyx_v_self)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 * else: * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) # <<<<<<<<<<<<<< @@ -6981,9 +7021,9 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = ((Py_ssize_t *)PyArray_DIMS(__pyx_v_self)); } - __pyx_L11:; + __pyx_L9:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL # <<<<<<<<<<<<<< @@ -6992,7 +7032,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->suboffsets = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":255 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) # <<<<<<<<<<<<<< @@ -7001,7 +7041,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->itemsize = PyArray_ITEMSIZE(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":256 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) * info.readonly = not PyArray_ISWRITEABLE(self) # <<<<<<<<<<<<<< @@ -7010,7 +7050,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->readonly = (!(PyArray_ISWRITEABLE(__pyx_v_self) != 0)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 * * cdef int t * cdef char* f = NULL # <<<<<<<<<<<<<< @@ -7019,7 +7059,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_f = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 * cdef int t * cdef char* f = NULL * cdef dtype descr = self.descr # <<<<<<<<<<<<<< @@ -7031,85 +7071,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_descr = ((PyArray_Descr *)__pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":257 * cdef int offset * - * cdef bint hasfields = PyDataType_HASFIELDS(descr) # <<<<<<<<<<<<<< - * - * if not hasfields and not copy_shape: - */ - __pyx_v_hasfields = PyDataType_HASFIELDS(__pyx_v_descr); - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) - * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - __pyx_t_2 = ((!(__pyx_v_hasfields != 0)) != 0); - if (__pyx_t_2) { - } else { - __pyx_t_1 = __pyx_t_2; - goto __pyx_L15_bool_binop_done; - } - __pyx_t_2 = ((!(__pyx_v_copy_shape != 0)) != 0); - __pyx_t_1 = __pyx_t_2; - __pyx_L15_bool_binop_done:; - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 - * if not hasfields and not copy_shape: - * # do not call releasebuffer - * info.obj = None # <<<<<<<<<<<<<< - * else: - * # need to call releasebuffer - */ - __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(Py_None); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = Py_None; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) - * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - goto __pyx_L14; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 - * else: - * # need to call releasebuffer - * info.obj = self # <<<<<<<<<<<<<< + * info.obj = self # <<<<<<<<<<<<<< * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): */ - /*else*/ { - __Pyx_INCREF(((PyObject *)__pyx_v_self)); - __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - } - __pyx_L14:; + __Pyx_INCREF(((PyObject *)__pyx_v_self)); + __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); + __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ - __pyx_t_1 = ((!(__pyx_v_hasfields != 0)) != 0); + __pyx_t_1 = ((!(PyDataType_HASFIELDS(__pyx_v_descr) != 0)) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num # <<<<<<<<<<<<<< * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): @@ -7117,8 +7104,8 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_t_4 = __pyx_v_descr->type_num; __pyx_v_t = __pyx_t_4; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -7126,18 +7113,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((__pyx_v_descr->byteorder == '>') != 0); if (!__pyx_t_2) { - goto __pyx_L20_next_or; + goto __pyx_L15_next_or; } else { } __pyx_t_2 = (__pyx_v_little_endian != 0); if (!__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } - __pyx_L20_next_or:; + __pyx_L15_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":262 * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -7148,36 +7135,36 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } __pyx_t_2 = ((!(__pyx_v_little_endian != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L19_bool_binop_done:; + __pyx_L14_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 276, __pyx_L1_error) + __PYX_ERR(1, 263, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -7185,7 +7172,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":264 * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" # <<<<<<<<<<<<<< @@ -7197,7 +7184,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"b"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" # <<<<<<<<<<<<<< @@ -7208,7 +7195,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"B"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":266 * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" # <<<<<<<<<<<<<< @@ -7219,7 +7206,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"h"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" # <<<<<<<<<<<<<< @@ -7230,7 +7217,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"H"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":281 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":268 * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" # <<<<<<<<<<<<<< @@ -7241,7 +7228,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"i"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":269 * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" # <<<<<<<<<<<<<< @@ -7252,7 +7239,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"I"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" # <<<<<<<<<<<<<< @@ -7263,7 +7250,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"l"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":271 * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" # <<<<<<<<<<<<<< @@ -7274,7 +7261,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"L"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":285 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" # <<<<<<<<<<<<<< @@ -7285,7 +7272,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" # <<<<<<<<<<<<<< @@ -7296,7 +7283,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" # <<<<<<<<<<<<<< @@ -7307,7 +7294,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"f"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" # <<<<<<<<<<<<<< @@ -7318,7 +7305,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"d"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" # <<<<<<<<<<<<<< @@ -7329,7 +7316,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"g"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":290 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" # <<<<<<<<<<<<<< @@ -7340,7 +7327,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zf"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":291 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" # <<<<<<<<<<<<<< @@ -7351,7 +7338,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zd"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" # <<<<<<<<<<<<<< @@ -7362,7 +7349,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zg"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":293 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" * elif t == NPY_OBJECT: f = "O" # <<<<<<<<<<<<<< @@ -7374,33 +7361,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P break; default: - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 * elif t == NPY_OBJECT: f = "O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< * info.format = f * return */ - __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_6 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __pyx_t_7 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_7)) __PYX_ERR(1, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_7); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_GIVEREF(__pyx_t_6); - PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_6); - __pyx_t_6 = 0; - __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_3, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; + __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_Raise(__pyx_t_6, 0, 0, 0); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __PYX_ERR(1, 295, __pyx_L1_error) + __PYX_ERR(1, 282, __pyx_L1_error) break; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f # <<<<<<<<<<<<<< @@ -7409,7 +7391,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->format = __pyx_v_f; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f * return # <<<<<<<<<<<<<< @@ -7419,16 +7401,16 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_r = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":299 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 * return * else: * info.format = PyObject_Malloc(_buffer_format_string_len) # <<<<<<<<<<<<<< @@ -7438,7 +7420,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->format = ((char *)PyObject_Malloc(0xFF)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":300 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 * else: * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment # <<<<<<<<<<<<<< @@ -7447,7 +7429,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->format[0]) = '^'; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":301 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 # <<<<<<<<<<<<<< @@ -7456,17 +7438,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_offset = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":302 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 * f = _util_dtypestring(descr, info.format + 1, # <<<<<<<<<<<<<< * info.format + _buffer_format_string_len, * &offset) */ - __pyx_t_7 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_7 == ((char *)NULL))) __PYX_ERR(1, 302, __pyx_L1_error) - __pyx_v_f = __pyx_t_7; + __pyx_t_8 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_8 == ((char *)NULL))) __PYX_ERR(1, 289, __pyx_L1_error) + __pyx_v_f = __pyx_t_8; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":305 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 * info.format + _buffer_format_string_len, * &offset) * f[0] = c'\0' # Terminate format string # <<<<<<<<<<<<<< @@ -7476,12 +7458,12 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_f[0]) = '\x00'; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* function exit code */ @@ -7489,18 +7471,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_3); - __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); __Pyx_AddTraceback("numpy.ndarray.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; - if (__pyx_v_info != NULL && __pyx_v_info->obj != NULL) { + if (__pyx_v_info->obj != NULL) { __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = NULL; + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } goto __pyx_L2; __pyx_L0:; - if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) { - __Pyx_GOTREF(Py_None); - __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL; + if (__pyx_v_info->obj == Py_None) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } __pyx_L2:; __Pyx_XDECREF((PyObject *)__pyx_v_descr); @@ -7508,7 +7490,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -7532,7 +7514,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s int __pyx_t_1; __Pyx_RefNannySetupContext("__releasebuffer__", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -7542,7 +7524,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (PyArray_HASFIELDS(__pyx_v_self) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":309 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) # <<<<<<<<<<<<<< @@ -7551,7 +7533,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->format); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -7560,7 +7542,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -7570,7 +7552,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":311 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":298 * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): * PyObject_Free(info.strides) # <<<<<<<<<<<<<< @@ -7579,7 +7561,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->strides); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -7588,7 +7570,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -7600,7 +7582,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -7614,7 +7596,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew1", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":789 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 * * cdef inline object PyArray_MultiIterNew1(a): * return PyArray_MultiIterNew(1, a) # <<<<<<<<<<<<<< @@ -7622,13 +7604,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ * cdef inline object PyArray_MultiIterNew2(a, b): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 789, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 776, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -7647,7 +7629,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -7661,7 +7643,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew2", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 * * cdef inline object PyArray_MultiIterNew2(a, b): * return PyArray_MultiIterNew(2, a, b) # <<<<<<<<<<<<<< @@ -7669,13 +7651,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ * cdef inline object PyArray_MultiIterNew3(a, b, c): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 792, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 779, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -7694,7 +7676,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -7708,7 +7690,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew3", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":795 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 * * cdef inline object PyArray_MultiIterNew3(a, b, c): * return PyArray_MultiIterNew(3, a, b, c) # <<<<<<<<<<<<<< @@ -7716,13 +7698,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ * cdef inline object PyArray_MultiIterNew4(a, b, c, d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 795, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 782, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -7741,7 +7723,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -7755,7 +7737,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew4", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":798 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":785 * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): * return PyArray_MultiIterNew(4, a, b, c, d) # <<<<<<<<<<<<<< @@ -7763,13 +7745,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 798, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 785, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -7788,7 +7770,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -7802,7 +7784,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew5", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): * return PyArray_MultiIterNew(5, a, b, c, d, e) # <<<<<<<<<<<<<< @@ -7810,13 +7792,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ * cdef inline tuple PyDataType_SHAPE(dtype d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 801, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 788, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -7835,7 +7817,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -7849,7 +7831,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ int __pyx_t_1; __Pyx_RefNannySetupContext("PyDataType_SHAPE", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -7859,7 +7841,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_t_1 = (PyDataType_HASSUBARRAY(__pyx_v_d) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): * return d.subarray.shape # <<<<<<<<<<<<<< @@ -7871,7 +7853,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_r = ((PyObject*)__pyx_v_d->subarray->shape); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -7880,7 +7862,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 * return d.subarray.shape * else: * return () # <<<<<<<<<<<<<< @@ -7894,7 +7876,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -7909,7 +7891,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -7938,7 +7920,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx char *__pyx_t_9; __Pyx_RefNannySetupContext("_util_dtypestring", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 * * cdef dtype child * cdef int endian_detector = 1 # <<<<<<<<<<<<<< @@ -7947,7 +7929,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":815 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":802 * cdef dtype child * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< @@ -7956,7 +7938,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -7965,21 +7947,21 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->names == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); - __PYX_ERR(1, 818, __pyx_L1_error) + __PYX_ERR(1, 805, __pyx_L1_error) } __pyx_t_1 = __pyx_v_descr->names; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; for (;;) { if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 805, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 805, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif __Pyx_XDECREF_SET(__pyx_v_childname, __pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":819 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":806 * * for childname in descr.names: * fields = descr.fields[childname] # <<<<<<<<<<<<<< @@ -7988,15 +7970,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->fields == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); - __PYX_ERR(1, 819, __pyx_L1_error) + __PYX_ERR(1, 806, __pyx_L1_error) } - __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 819, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 819, __pyx_L1_error) + if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_fields, ((PyObject*)__pyx_t_3)); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":820 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 * for childname in descr.names: * fields = descr.fields[childname] * child, new_offset = fields # <<<<<<<<<<<<<< @@ -8005,15 +7987,11 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (likely(__pyx_v_fields != Py_None)) { PyObject* sequence = __pyx_v_fields; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(1, 820, __pyx_L1_error) + __PYX_ERR(1, 807, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyTuple_GET_ITEM(sequence, 0); @@ -8021,51 +7999,51 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(__pyx_t_4); #else - __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { - __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 820, __pyx_L1_error) + __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 807, __pyx_L1_error) } - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 820, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_child, ((PyArray_Descr *)__pyx_t_3)); __pyx_t_3 = 0; __Pyx_XDECREF_SET(__pyx_v_new_offset, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * */ - __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_6 = ((((__pyx_v_end - __pyx_v_f) - ((int)__pyx_t_5)) < 15) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 823, __pyx_L1_error) + __PYX_ERR(1, 810, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< @@ -8074,7 +8052,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -8094,7 +8072,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __pyx_L8_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":813 * * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -8111,29 +8089,29 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = __pyx_t_7; __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 827, __pyx_L1_error) + __PYX_ERR(1, 814, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -8142,7 +8120,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":824 * * # Output padding bytes * while offset[0] < new_offset: # <<<<<<<<<<<<<< @@ -8150,15 +8128,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * f += 1 */ while (1) { - __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (!__pyx_t_6) break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 * # Output padding bytes * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte # <<<<<<<<<<<<<< @@ -8167,7 +8145,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ (__pyx_v_f[0]) = 0x78; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte * f += 1 # <<<<<<<<<<<<<< @@ -8176,7 +8154,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 * f[0] = 120 # "x"; pad byte * f += 1 * offset[0] += 1 # <<<<<<<<<<<<<< @@ -8187,7 +8165,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + 1); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":829 * offset[0] += 1 * * offset[0] += child.itemsize # <<<<<<<<<<<<<< @@ -8197,7 +8175,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_8 = 0; (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + __pyx_v_child->elsize); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -8207,19 +8185,19 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = ((!(PyDataType_HASFIELDS(__pyx_v_child) != 0)) != 0); if (__pyx_t_6) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":832 * * if not PyDataType_HASFIELDS(child): * t = child.type_num # <<<<<<<<<<<<<< * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") */ - __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 832, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_XDECREF_SET(__pyx_v_t, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -8227,22 +8205,22 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ __pyx_t_6 = (((__pyx_v_end - __pyx_v_f) < 5) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_Raise(__pyx_t_4, 0, 0, 0); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __PYX_ERR(1, 847, __pyx_L1_error) + __PYX_ERR(1, 834, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -8251,252 +8229,252 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 * * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" # <<<<<<<<<<<<<< * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 98; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" # <<<<<<<<<<<<<< * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" # <<<<<<<<<<<<<< * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x68; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" # <<<<<<<<<<<<<< * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 72; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":854 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":841 * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" # <<<<<<<<<<<<<< * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x69; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" # <<<<<<<<<<<<<< * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 73; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":843 * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" # <<<<<<<<<<<<<< * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x6C; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":857 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" # <<<<<<<<<<<<<< * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 76; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":858 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" # <<<<<<<<<<<<<< * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x71; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":859 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" # <<<<<<<<<<<<<< * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 81; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" # <<<<<<<<<<<<<< * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":848 * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" # <<<<<<<<<<<<<< * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x64; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":862 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":849 * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" # <<<<<<<<<<<<<< * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x67; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":863 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf # <<<<<<<<<<<<<< * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -8505,18 +8483,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":864 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd # <<<<<<<<<<<<<< * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -8525,18 +8503,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":865 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg # <<<<<<<<<<<<<< * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -8545,25 +8523,25 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":866 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" # <<<<<<<<<<<<<< * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (__pyx_t_6) { + if (likely(__pyx_t_6)) { (__pyx_v_f[0]) = 79; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":868 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< @@ -8571,23 +8549,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * else: */ /*else*/ { - __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 868, __pyx_L1_error) + __Pyx_Raise(__pyx_t_4, 0, 0, 0); + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __PYX_ERR(1, 855, __pyx_L1_error) } __pyx_L15:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":869 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * f += 1 # <<<<<<<<<<<<<< @@ -8596,7 +8569,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -8606,7 +8579,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L13; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":873 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 * # Cython ignores struct boundary information ("T{...}"), * # so don't output it * f = _util_dtypestring(child, f, end, offset) # <<<<<<<<<<<<<< @@ -8614,12 +8587,12 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ /*else*/ { - __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 873, __pyx_L1_error) + __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 860, __pyx_L1_error) __pyx_v_f = __pyx_t_9; } __pyx_L13:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -8629,7 +8602,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":874 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 * # so don't output it * f = _util_dtypestring(child, f, end, offset) * return f # <<<<<<<<<<<<<< @@ -8639,7 +8612,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_r = __pyx_v_f; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -8664,7 +8637,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -8679,7 +8652,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a int __pyx_t_2; __Pyx_RefNannySetupContext("set_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -8690,7 +8663,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":993 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":980 * cdef PyObject* baseptr * if base is None: * baseptr = NULL # <<<<<<<<<<<<<< @@ -8699,7 +8672,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_baseptr = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -8709,7 +8682,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a goto __pyx_L3; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":995 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":982 * baseptr = NULL * else: * Py_INCREF(base) # important to do this before decref below! # <<<<<<<<<<<<<< @@ -8719,7 +8692,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a /*else*/ { Py_INCREF(__pyx_v_base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":983 * else: * Py_INCREF(base) # important to do this before decref below! * baseptr = base # <<<<<<<<<<<<<< @@ -8730,7 +8703,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a } __pyx_L3:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":984 * Py_INCREF(base) # important to do this before decref below! * baseptr = base * Py_XDECREF(arr.base) # <<<<<<<<<<<<<< @@ -8739,7 +8712,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ Py_XDECREF(__pyx_v_arr->base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":985 * baseptr = base * Py_XDECREF(arr.base) * arr.base = baseptr # <<<<<<<<<<<<<< @@ -8748,7 +8721,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_arr->base = __pyx_v_baseptr; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -8760,7 +8733,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -8774,7 +8747,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py int __pyx_t_1; __Pyx_RefNannySetupContext("get_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -8784,7 +8757,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py __pyx_t_1 = ((__pyx_v_arr->base == NULL) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":989 * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: * return None # <<<<<<<<<<<<<< @@ -8792,11 +8765,10 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py * return arr.base */ __Pyx_XDECREF(__pyx_r); - __Pyx_INCREF(Py_None); - __pyx_r = Py_None; + __pyx_r = Py_None; __Pyx_INCREF(Py_None); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -8805,7 +8777,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":991 * return None * else: * return arr.base # <<<<<<<<<<<<<< @@ -8819,7 +8791,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -8834,7 +8806,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -8855,7 +8827,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_array", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -8871,16 +8843,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 * cdef inline int import_array() except -1: * try: * _import_array() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.multiarray failed to import") */ - __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1011, __pyx_L3_error) + __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 998, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -8894,7 +8866,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":999 * try: * _import_array() * except Exception: # <<<<<<<<<<<<<< @@ -8904,28 +8876,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_array", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1012, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 999, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1013, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1000, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1013, __pyx_L5_except_error) + __PYX_ERR(1, 1000, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -8940,7 +8912,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -8963,7 +8935,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -8984,7 +8956,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_umath", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -9000,16 +8972,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1017 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 * cdef inline int import_umath() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1017, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1004, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -9023,7 +8995,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1018 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1005 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -9033,28 +9005,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_umath", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1018, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1005, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1019, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1006, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1019, __pyx_L5_except_error) + __PYX_ERR(1, 1006, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -9069,7 +9041,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -9092,7 +9064,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -9113,7 +9085,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_ufunc", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -9129,16 +9101,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1023 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 * cdef inline int import_ufunc() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1023, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1010, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -9152,7 +9124,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1024 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -9161,26 +9133,26 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_ufunc", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1024, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1011, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1025, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1012, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1025, __pyx_L5_except_error) + __PYX_ERR(1, 1012, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -9195,7 +9167,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -9236,7 +9208,7 @@ static PyModuleDef_Slot __pyx_moduledef_slots[] = { static struct PyModuleDef __pyx_moduledef = { PyModuleDef_HEAD_INIT, "fasttext_inner", - 0, /* m_doc */ + __pyx_k_Optimized_cython_functions_for_t, /* m_doc */ #if CYTHON_PEP489_MULTI_PHASE_INIT 0, /* m_size */ #else @@ -9362,11 +9334,11 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {0, 0, 0, 0, 0, 0, 0} }; static int __Pyx_InitCachedBuiltins(void) { - __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(0, 18, __pyx_L1_error) + __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(0, 21, __pyx_L1_error) __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 61, __pyx_L1_error) - __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 345, __pyx_L1_error) - __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(1, 235, __pyx_L1_error) - __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 369, __pyx_L1_error) + __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(1, 229, __pyx_L1_error) + __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 810, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; @@ -9376,128 +9348,128 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0); - /* "gensim/models/fasttext_inner.pyx":299 + /* "gensim/models/fasttext_inner.pyx":323 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple_ = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_tuple_ = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple_); __Pyx_GIVEREF(__pyx_tuple_); - __pyx_tuple__2 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_tuple__2 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(0, 323, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__2); __Pyx_GIVEREF(__pyx_tuple__2); - /* "gensim/models/fasttext_inner.pyx":428 + /* "gensim/models/fasttext_inner.pyx":475 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple__3 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_tuple__3 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__3); __Pyx_GIVEREF(__pyx_tuple__3); - __pyx_tuple__4 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 428, __pyx_L1_error) + __pyx_tuple__4 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 475, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__4); __Pyx_GIVEREF(__pyx_tuple__4); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__5)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__5)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__5); __Pyx_GIVEREF(__pyx_tuple__5); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_tuple__6 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_tuple__6 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__6); __Pyx_GIVEREF(__pyx_tuple__6); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_tuple__7 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__7)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_tuple__7 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__7)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__7); __Pyx_GIVEREF(__pyx_tuple__7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_tuple__8 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_tuple__8 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__8); __Pyx_GIVEREF(__pyx_tuple__8); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__9); __Pyx_GIVEREF(__pyx_tuple__9); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__10); __Pyx_GIVEREF(__pyx_tuple__10); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 1013, __pyx_L1_error) + __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 1000, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__11); __Pyx_GIVEREF(__pyx_tuple__11); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 1019, __pyx_L1_error) + __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 1006, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__12); __Pyx_GIVEREF(__pyx_tuple__12); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 1025, __pyx_L1_error) + __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 1012, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__13); __Pyx_GIVEREF(__pyx_tuple__13); @@ -9505,37 +9477,37 @@ static int __Pyx_InitCachedConstants(void) { * * * def train_batch_sg(model, sentences, alpha, _work, _l1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a sequence of sentences. + * */ __pyx_tuple__15 = PyTuple_Pack(46, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_l1, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_syn0_vocab, __pyx_n_s_word_locks_vocab, __pyx_n_s_syn0_ngrams, __pyx_n_s_word_locks_ngrams, __pyx_n_s_work_2, __pyx_n_s_l1_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_subwords_idx_len, __pyx_n_s_subwords_idx, __pyx_n_s_subword_arrays, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_subwords, __pyx_n_s_word_subwords, __pyx_n_s_item); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(0, 246, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__15); __Pyx_GIVEREF(__pyx_tuple__15); __pyx_codeobj__16 = (PyObject*)__Pyx_PyCode_New(5, 0, 46, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__15, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_fasttext_inner_pyx, __pyx_n_s_train_batch_sg, 246, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__16)) __PYX_ERR(0, 246, __pyx_L1_error) - /* "gensim/models/fasttext_inner.pyx":376 + /* "gensim/models/fasttext_inner.pyx":400 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update the CBOW model by training on a sequence of sentences. + * */ - __pyx_tuple__17 = PyTuple_Pack(47, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_cbow_mean, __pyx_n_s_syn0_vocab, __pyx_n_s_word_locks_vocab, __pyx_n_s_syn0_ngrams, __pyx_n_s_word_locks_ngrams, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_subwords_idx_len, __pyx_n_s_subwords_idx, __pyx_n_s_subword_arrays, __pyx_n_s_neu1_2, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_subwords, __pyx_n_s_word_subwords, __pyx_n_s_item); if (unlikely(!__pyx_tuple__17)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_tuple__17 = PyTuple_Pack(47, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_cbow_mean, __pyx_n_s_syn0_vocab, __pyx_n_s_word_locks_vocab, __pyx_n_s_syn0_ngrams, __pyx_n_s_word_locks_ngrams, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_subwords_idx_len, __pyx_n_s_subwords_idx, __pyx_n_s_subword_arrays, __pyx_n_s_neu1_2, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_subwords, __pyx_n_s_word_subwords, __pyx_n_s_item); if (unlikely(!__pyx_tuple__17)) __PYX_ERR(0, 400, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__17); __Pyx_GIVEREF(__pyx_tuple__17); - __pyx_codeobj__18 = (PyObject*)__Pyx_PyCode_New(5, 0, 47, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__17, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_fasttext_inner_pyx, __pyx_n_s_train_batch_cbow, 376, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__18)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_codeobj__18 = (PyObject*)__Pyx_PyCode_New(5, 0, 47, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__17, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_fasttext_inner_pyx, __pyx_n_s_train_batch_cbow, 400, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__18)) __PYX_ERR(0, 400, __pyx_L1_error) - /* "gensim/models/fasttext_inner.pyx":503 + /* "gensim/models/fasttext_inner.pyx":550 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ - __pyx_tuple__19 = PyTuple_Pack(7, __pyx_n_s_i, __pyx_n_s_x, __pyx_n_s_y, __pyx_n_s_expected, __pyx_n_s_size, __pyx_n_s_d_res, __pyx_n_s_p_res); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(0, 503, __pyx_L1_error) + __pyx_tuple__19 = PyTuple_Pack(7, __pyx_n_s_i, __pyx_n_s_x, __pyx_n_s_y, __pyx_n_s_expected, __pyx_n_s_size, __pyx_n_s_d_res, __pyx_n_s_p_res); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(0, 550, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__19); __Pyx_GIVEREF(__pyx_tuple__19); - __pyx_codeobj__20 = (PyObject*)__Pyx_PyCode_New(0, 0, 7, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__19, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_fasttext_inner_pyx, __pyx_n_s_init, 503, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__20)) __PYX_ERR(0, 503, __pyx_L1_error) + __pyx_codeobj__20 = (PyObject*)__Pyx_PyCode_New(0, 0, 7, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__19, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_fasttext_inner_pyx, __pyx_n_s_init, 550, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__20)) __PYX_ERR(0, 550, __pyx_L1_error) __Pyx_RefNannyFinishContext(); return 0; __pyx_L1_error:; @@ -9555,12 +9527,145 @@ static int __Pyx_InitGlobals(void) { return -1; } +static int __Pyx_modinit_global_init_code(void); /*proto*/ +static int __Pyx_modinit_variable_export_code(void); /*proto*/ +static int __Pyx_modinit_function_export_code(void); /*proto*/ +static int __Pyx_modinit_type_init_code(void); /*proto*/ +static int __Pyx_modinit_type_import_code(void); /*proto*/ +static int __Pyx_modinit_variable_import_code(void); /*proto*/ +static int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", + #if defined(PYPY_VERSION_NUM) && PYPY_VERSION_NUM < 0x050B0000 + sizeof(PyTypeObject), + #else + sizeof(PyHeapTypeObject), + #endif + 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(2, 9, __pyx_L1_error) + __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 164, __pyx_L1_error) + __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 186, __pyx_L1_error) + __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 190, __pyx_L1_error) + __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 199, __pyx_L1_error) + __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 872, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __pyx_t_1 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_1) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "scopy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_scopy, "__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "sdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sdot, "__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "dsdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_dsdot, "__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "snrm2", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_snrm2, "__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "sscal", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sscal, "__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "EXP_TABLE", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_EXP_TABLE, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t [0x3E8]") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_dot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_dot, "__pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + Py_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + PyObject *__pyx_t_1 = NULL; + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __pyx_t_1 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_1) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "our_dot_double", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_double, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "our_dot_float", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_float, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "our_dot_noblas", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "our_saxpy_noblas", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas, "void (int const *, float const *, float const *, int const *, float *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "bisect_left", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_bisect_left, "unsigned PY_LONG_LONG (__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ImportFunction(__pyx_t_1, "random_int32", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_random_int32, "unsigned PY_LONG_LONG (unsigned PY_LONG_LONG *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + Py_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_1); + __Pyx_RefNannyFinishContext(); + return -1; +} + + +#if PY_MAJOR_VERSION < 3 +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC void +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#else +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyObject * +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (!(defined(__cplusplus)) || (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ > 4))) + #define CYTHON_SMALL_CODE __attribute__((optimize("Os"))) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + + #if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initfasttext_inner(void); /*proto*/ -PyMODINIT_FUNC initfasttext_inner(void) +__Pyx_PyMODINIT_FUNC initfasttext_inner(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC initfasttext_inner(void) #else -PyMODINIT_FUNC PyInit_fasttext_inner(void); /*proto*/ -PyMODINIT_FUNC PyInit_fasttext_inner(void) +__Pyx_PyMODINIT_FUNC PyInit_fasttext_inner(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit_fasttext_inner(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); @@ -9609,26 +9714,26 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) PyObject *__pyx_t_3 = NULL; PyObject *__pyx_t_4 = NULL; PyObject *__pyx_t_5 = NULL; - PyObject *__pyx_t_6 = NULL; + int __pyx_t_6; PyObject *__pyx_t_7 = NULL; - int __pyx_t_8; + PyObject *__pyx_t_8 = NULL; PyObject *__pyx_t_9 = NULL; - PyObject *__pyx_t_10 = NULL; - PyObject *__pyx_t_11 = NULL; __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m && __pyx_m == __pyx_pyinit_module) return 0; + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif #if CYTHON_REFNANNY - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); - if (!__Pyx_RefNanny) { - PyErr_Clear(); - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); - if (!__Pyx_RefNanny) - Py_FatalError("failed to import 'refnanny' module"); - } - #endif - __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit_fasttext_inner(void)", 0); +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit_fasttext_inner(void)", 0); if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) @@ -9664,7 +9769,7 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) Py_INCREF(__pyx_m); #else #if PY_MAJOR_VERSION < 3 - __pyx_m = Py_InitModule4("fasttext_inner", __pyx_methods, 0, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); + __pyx_m = Py_InitModule4("fasttext_inner", __pyx_methods, __pyx_k_Optimized_cython_functions_for_t, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); #else __pyx_m = PyModule_Create(&__pyx_moduledef); #endif @@ -9698,62 +9803,32 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) /*--- Constants init code ---*/ if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Global init code ---*/ - /*--- Variable export code ---*/ - /*--- Function export code ---*/ - /*--- Type init code ---*/ - /*--- Type import code ---*/ - __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", - #if CYTHON_COMPILING_IN_PYPY - sizeof(PyTypeObject), - #else - sizeof(PyHeapTypeObject), - #endif - 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(2, 9, __pyx_L1_error) - __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 163, __pyx_L1_error) - __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 185, __pyx_L1_error) - __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 189, __pyx_L1_error) - __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 198, __pyx_L1_error) - __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 885, __pyx_L1_error) - /*--- Variable import code ---*/ - __pyx_t_1 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_1) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "scopy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_scopy, "__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "sdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sdot, "__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "dsdot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_dsdot, "__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "snrm2", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_snrm2, "__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "sscal", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_sscal, "__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "EXP_TABLE", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_EXP_TABLE, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t [0x3E8]") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_dot", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_dot, "__pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportVoidPtr(__pyx_t_1, "our_saxpy", (void **)&__pyx_vp_6gensim_6models_14word2vec_inner_our_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - Py_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /*--- Function import code ---*/ - __pyx_t_2 = __Pyx_ImportModule("gensim.models.word2vec_inner"); if (!__pyx_t_2) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_dot_double", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_double, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_dot_float", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_float, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_dot_noblas", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "our_saxpy_noblas", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas, "void (int const *, float const *, float const *, int const *, float *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "bisect_left", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_bisect_left, "unsigned PY_LONG_LONG (__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ImportFunction(__pyx_t_2, "random_int32", (void (**)(void))&__pyx_f_6gensim_6models_14word2vec_inner_random_int32, "unsigned PY_LONG_LONG (unsigned PY_LONG_LONG *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - Py_DECREF(__pyx_t_2); __pyx_t_2 = 0; + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + (void)__Pyx_modinit_variable_export_code(); + (void)__Pyx_modinit_function_export_code(); + (void)__Pyx_modinit_type_init_code(); + if (unlikely(__Pyx_modinit_type_import_code() != 0)) goto __pyx_L1_error; + if (unlikely(__Pyx_modinit_variable_import_code() != 0)) goto __pyx_L1_error; + if (unlikely(__Pyx_modinit_function_import_code() != 0)) goto __pyx_L1_error; /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif - /* "gensim/models/fasttext_inner.pyx":8 + /* "gensim/models/fasttext_inner.pyx":11 * * import cython * import numpy as np # <<<<<<<<<<<<<< * cimport numpy as np * */ - __pyx_t_3 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 8, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_3) < 0) __PYX_ERR(0, 8, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_1 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 11, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_1) < 0) __PYX_ERR(0, 11, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":16 + /* "gensim/models/fasttext_inner.pyx":19 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< @@ -9763,34 +9838,34 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign - __Pyx_ExceptionSave(&__pyx_t_4, &__pyx_t_5, &__pyx_t_6); + __Pyx_ExceptionSave(&__pyx_t_2, &__pyx_t_3, &__pyx_t_4); + __Pyx_XGOTREF(__pyx_t_2); + __Pyx_XGOTREF(__pyx_t_3); __Pyx_XGOTREF(__pyx_t_4); - __Pyx_XGOTREF(__pyx_t_5); - __Pyx_XGOTREF(__pyx_t_6); /*try:*/ { - /* "gensim/models/fasttext_inner.pyx":17 + /* "gensim/models/fasttext_inner.pyx":20 * # scipy <= 0.15 * try: * from scipy.linalg.blas import fblas # <<<<<<<<<<<<<< * except ImportError: * # in scipy > 0.15, fblas function has been removed */ - __pyx_t_3 = PyList_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 17, __pyx_L2_error) - __Pyx_GOTREF(__pyx_t_3); + __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 20, __pyx_L2_error) + __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_n_s_fblas); __Pyx_GIVEREF(__pyx_n_s_fblas); - PyList_SET_ITEM(__pyx_t_3, 0, __pyx_n_s_fblas); - __pyx_t_7 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_3, -1); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 17, __pyx_L2_error) - __Pyx_GOTREF(__pyx_t_7); - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_ImportFrom(__pyx_t_7, __pyx_n_s_fblas); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 17, __pyx_L2_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_3) < 0) __PYX_ERR(0, 17, __pyx_L2_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; + PyList_SET_ITEM(__pyx_t_1, 0, __pyx_n_s_fblas); + __pyx_t_5 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_1, -1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 20, __pyx_L2_error) + __Pyx_GOTREF(__pyx_t_5); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_5, __pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 20, __pyx_L2_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_1) < 0) __PYX_ERR(0, 20, __pyx_L2_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - /* "gensim/models/fasttext_inner.pyx":16 + /* "gensim/models/fasttext_inner.pyx":19 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< @@ -9798,88 +9873,88 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) * except ImportError: */ } + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; - __Pyx_XDECREF(__pyx_t_6); __pyx_t_6 = 0; goto __pyx_L7_try_end; __pyx_L2_error:; - __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; - /* "gensim/models/fasttext_inner.pyx":18 + /* "gensim/models/fasttext_inner.pyx":21 * try: * from scipy.linalg.blas import fblas * except ImportError: # <<<<<<<<<<<<<< * # in scipy > 0.15, fblas function has been removed * import scipy.linalg.blas as fblas */ - __pyx_t_8 = __Pyx_PyErr_ExceptionMatches(__pyx_builtin_ImportError); - if (__pyx_t_8) { + __pyx_t_6 = __Pyx_PyErr_ExceptionMatches(__pyx_builtin_ImportError); + if (__pyx_t_6) { __Pyx_AddTraceback("gensim.models.fasttext_inner", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_7, &__pyx_t_3, &__pyx_t_9) < 0) __PYX_ERR(0, 18, __pyx_L4_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_1, &__pyx_t_7) < 0) __PYX_ERR(0, 21, __pyx_L4_except_error) + __Pyx_GOTREF(__pyx_t_5); + __Pyx_GOTREF(__pyx_t_1); __Pyx_GOTREF(__pyx_t_7); - __Pyx_GOTREF(__pyx_t_3); - __Pyx_GOTREF(__pyx_t_9); - /* "gensim/models/fasttext_inner.pyx":20 + /* "gensim/models/fasttext_inner.pyx":23 * except ImportError: * # in scipy > 0.15, fblas function has been removed * import scipy.linalg.blas as fblas # <<<<<<<<<<<<<< * - * from word2vec_inner cimport bisect_left, random_int32, \ + * from word2vec_inner cimport bisect_left, random_int32, scopy, saxpy, dsdot, sscal, \ */ - __pyx_t_10 = PyList_New(1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 20, __pyx_L4_except_error) - __Pyx_GOTREF(__pyx_t_10); + __pyx_t_8 = PyList_New(1); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 23, __pyx_L4_except_error) + __Pyx_GOTREF(__pyx_t_8); __Pyx_INCREF(__pyx_n_s__14); __Pyx_GIVEREF(__pyx_n_s__14); - PyList_SET_ITEM(__pyx_t_10, 0, __pyx_n_s__14); - __pyx_t_11 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_10, -1); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 20, __pyx_L4_except_error) - __Pyx_GOTREF(__pyx_t_11); - __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_11) < 0) __PYX_ERR(0, 20, __pyx_L4_except_error) - __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + PyList_SET_ITEM(__pyx_t_8, 0, __pyx_n_s__14); + __pyx_t_9 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_8, -1); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 23, __pyx_L4_except_error) + __Pyx_GOTREF(__pyx_t_9); + __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_9) < 0) __PYX_ERR(0, 23, __pyx_L4_except_error) __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; + __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; goto __pyx_L3_exception_handled; } goto __pyx_L4_except_error; __pyx_L4_except_error:; - /* "gensim/models/fasttext_inner.pyx":16 + /* "gensim/models/fasttext_inner.pyx":19 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< * from scipy.linalg.blas import fblas * except ImportError: */ + __Pyx_XGIVEREF(__pyx_t_2); + __Pyx_XGIVEREF(__pyx_t_3); __Pyx_XGIVEREF(__pyx_t_4); - __Pyx_XGIVEREF(__pyx_t_5); - __Pyx_XGIVEREF(__pyx_t_6); - __Pyx_ExceptionReset(__pyx_t_4, __pyx_t_5, __pyx_t_6); + __Pyx_ExceptionReset(__pyx_t_2, __pyx_t_3, __pyx_t_4); goto __pyx_L1_error; __pyx_L3_exception_handled:; + __Pyx_XGIVEREF(__pyx_t_2); + __Pyx_XGIVEREF(__pyx_t_3); __Pyx_XGIVEREF(__pyx_t_4); - __Pyx_XGIVEREF(__pyx_t_5); - __Pyx_XGIVEREF(__pyx_t_6); - __Pyx_ExceptionReset(__pyx_t_4, __pyx_t_5, __pyx_t_6); + __Pyx_ExceptionReset(__pyx_t_2, __pyx_t_3, __pyx_t_4); __pyx_L7_try_end:; } /* "gensim/models/fasttext_inner.pyx":28 - * our_dot_double, our_dot_float, our_dot_noblas, our_saxpy_noblas + * REAL_t, EXP_TABLE, our_dot, our_saxpy, our_dot_double, our_dot_float, our_dot_noblas, our_saxpy_noblas * * REAL = np.float32 # <<<<<<<<<<<<<< * * DEF MAX_SENTENCE_LEN = 10000 */ - __pyx_t_9 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 28, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_9); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_9, __pyx_n_s_float32); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 28, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_REAL, __pyx_t_3) < 0) __PYX_ERR(0, 28, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_7 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 28, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_float32); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 28, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_REAL, __pyx_t_1) < 0) __PYX_ERR(0, 28, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "gensim/models/fasttext_inner.pyx":39 * cdef REAL_t[EXP_TABLE_SIZE] LOG_TABLE @@ -9903,87 +9978,70 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) * * * def train_batch_sg(model, sentences, alpha, _work, _l1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a sequence of sentences. + * */ - __pyx_t_3 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14fasttext_inner_1train_batch_sg, NULL, __pyx_n_s_gensim_models_fasttext_inner); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 246, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_sg, __pyx_t_3) < 0) __PYX_ERR(0, 246, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14fasttext_inner_1train_batch_sg, NULL, __pyx_n_s_gensim_models_fasttext_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 246, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_sg, __pyx_t_1) < 0) __PYX_ERR(0, 246, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":376 + /* "gensim/models/fasttext_inner.pyx":400 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update the CBOW model by training on a sequence of sentences. + * */ - __pyx_t_3 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14fasttext_inner_3train_batch_cbow, NULL, __pyx_n_s_gensim_models_fasttext_inner); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 376, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_cbow, __pyx_t_3) < 0) __PYX_ERR(0, 376, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14fasttext_inner_3train_batch_cbow, NULL, __pyx_n_s_gensim_models_fasttext_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 400, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_cbow, __pyx_t_1) < 0) __PYX_ERR(0, 400, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":503 + /* "gensim/models/fasttext_inner.pyx":550 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ - __pyx_t_3 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14fasttext_inner_5init, NULL, __pyx_n_s_gensim_models_fasttext_inner); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 503, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_init, __pyx_t_3) < 0) __PYX_ERR(0, 503, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14fasttext_inner_5init, NULL, __pyx_n_s_gensim_models_fasttext_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 550, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_init, __pyx_t_1) < 0) __PYX_ERR(0, 550, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/fasttext_inner.pyx":543 + /* "gensim/models/fasttext_inner.pyx":597 * return 2 * * FAST_VERSION = init() # initialize the module # <<<<<<<<<<<<<< * MAX_WORDS_IN_BATCH = MAX_SENTENCE_LEN - * */ - __pyx_t_9 = __Pyx_GetModuleGlobalName(__pyx_n_s_init); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 543, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_9); - __pyx_t_7 = NULL; - if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_9))) { - __pyx_t_7 = PyMethod_GET_SELF(__pyx_t_9); - if (likely(__pyx_t_7)) { - PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_9); - __Pyx_INCREF(__pyx_t_7); - __Pyx_INCREF(function); - __Pyx_DECREF_SET(__pyx_t_9, function); - } - } - if (__pyx_t_7) { - __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_9, __pyx_t_7); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 543, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - } else { - __pyx_t_3 = __Pyx_PyObject_CallNoArg(__pyx_t_9); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 543, __pyx_L1_error) - } - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_FAST_VERSION, __pyx_t_3) < 0) __PYX_ERR(0, 543, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_init); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 597, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_t_7 = __Pyx_PyObject_CallNoArg(__pyx_t_1); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 597, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_FAST_VERSION, __pyx_t_7) < 0) __PYX_ERR(0, 597, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "gensim/models/fasttext_inner.pyx":544 + /* "gensim/models/fasttext_inner.pyx":598 * * FAST_VERSION = init() # initialize the module * MAX_WORDS_IN_BATCH = MAX_SENTENCE_LEN # <<<<<<<<<<<<<< - * */ - if (PyDict_SetItem(__pyx_d, __pyx_n_s_MAX_WORDS_IN_BATCH, __pyx_int_10000) < 0) __PYX_ERR(0, 544, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_MAX_WORDS_IN_BATCH, __pyx_int_10000) < 0) __PYX_ERR(0, 598, __pyx_L1_error) /* "gensim/models/fasttext_inner.pyx":1 * #!/usr/bin/env cython # <<<<<<<<<<<<<< * # cython: boundscheck=False * # cython: wraparound=False */ - __pyx_t_3 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_3) < 0) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_7 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_7) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -9996,12 +10054,10 @@ static int __pyx_pymod_exec_fasttext_inner(PyObject *__pyx_pyinit_module) goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); - __Pyx_XDECREF(__pyx_t_2); - __Pyx_XDECREF(__pyx_t_3); + __Pyx_XDECREF(__pyx_t_5); __Pyx_XDECREF(__pyx_t_7); + __Pyx_XDECREF(__pyx_t_8); __Pyx_XDECREF(__pyx_t_9); - __Pyx_XDECREF(__pyx_t_10); - __Pyx_XDECREF(__pyx_t_11); if (__pyx_m) { if (__pyx_d) { __Pyx_AddTraceback("init gensim.models.fasttext_inner", 0, __pyx_lineno, __pyx_filename); @@ -10039,6 +10095,20 @@ static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { } #endif +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); @@ -10228,14 +10298,139 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg } #endif +/* GetItemInt */ +static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { + PyObject *r; + if (!j) return NULL; + r = PyObject_GetItem(o, j); + Py_DECREF(j); + return r; +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS + Py_ssize_t wrapped_i = i; + if (wraparound & unlikely(i < 0)) { + wrapped_i += PyList_GET_SIZE(o); + } + if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyList_GET_SIZE(o)))) { + PyObject *r = PyList_GET_ITEM(o, wrapped_i); + Py_INCREF(r); + return r; + } + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +#else + return PySequence_GetItem(o, i); +#endif +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS + Py_ssize_t wrapped_i = i; + if (wraparound & unlikely(i < 0)) { + wrapped_i += PyTuple_GET_SIZE(o); + } + if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyTuple_GET_SIZE(o)))) { + PyObject *r = PyTuple_GET_ITEM(o, wrapped_i); + Py_INCREF(r); + return r; + } + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +#else + return PySequence_GetItem(o, i); +#endif +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, int is_list, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS && CYTHON_USE_TYPE_SLOTS + if (is_list || PyList_CheckExact(o)) { + Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyList_GET_SIZE(o); + if ((!boundscheck) || (likely((n >= 0) & (n < PyList_GET_SIZE(o))))) { + PyObject *r = PyList_GET_ITEM(o, n); + Py_INCREF(r); + return r; + } + } + else if (PyTuple_CheckExact(o)) { + Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyTuple_GET_SIZE(o); + if ((!boundscheck) || likely((n >= 0) & (n < PyTuple_GET_SIZE(o)))) { + PyObject *r = PyTuple_GET_ITEM(o, n); + Py_INCREF(r); + return r; + } + } else { + PySequenceMethods *m = Py_TYPE(o)->tp_as_sequence; + if (likely(m && m->sq_item)) { + if (wraparound && unlikely(i < 0) && likely(m->sq_length)) { + Py_ssize_t l = m->sq_length(o); + if (likely(l >= 0)) { + i += l; + } else { + if (!PyErr_ExceptionMatches(PyExc_OverflowError)) + return NULL; + PyErr_Clear(); + } + } + return m->sq_item(o, i); + } + } +#else + if (is_list || PySequence_Check(o)) { + return PySequence_GetItem(o, i); + } +#endif + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +} + +/* ObjectGetItem */ +#if CYTHON_USE_TYPE_SLOTS +static PyObject *__Pyx_PyObject_GetIndex(PyObject *obj, PyObject* index) { + PyObject *runerr; + Py_ssize_t key_value; + PySequenceMethods *m = Py_TYPE(obj)->tp_as_sequence; + if (unlikely(!(m && m->sq_item))) { + PyErr_Format(PyExc_TypeError, "'%.200s' object is not subscriptable", Py_TYPE(obj)->tp_name); + return NULL; + } + key_value = __Pyx_PyIndex_AsSsize_t(index); + if (likely(key_value != -1 || !(runerr = PyErr_Occurred()))) { + return __Pyx_GetItemInt_Fast(obj, key_value, 0, 1, 1); + } + if (PyErr_GivenExceptionMatches(runerr, PyExc_OverflowError)) { + PyErr_Clear(); + PyErr_Format(PyExc_IndexError, "cannot fit '%.200s' into an index-sized integer", Py_TYPE(index)->tp_name); + } + return NULL; +} +static PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key) { + PyMappingMethods *m = Py_TYPE(obj)->tp_as_mapping; + if (likely(m && m->mp_subscript)) { + return m->mp_subscript(obj, key); + } + return __Pyx_PyObject_GetIndex(obj, key); +} +#endif + /* GetModuleGlobalName */ static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { PyObject *result; #if !CYTHON_AVOID_BORROWED_REFS +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 + result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); + if (likely(result)) { + Py_INCREF(result); + } else if (unlikely(PyErr_Occurred())) { + result = NULL; + } else { +#else result = PyDict_GetItem(__pyx_d, name); if (likely(result)) { Py_INCREF(result); } else { +#endif #else result = PyObject_GetItem(__pyx_d, name); if (!result) { @@ -10247,7 +10442,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { } /* PyFunctionFastCall */ - #if CYTHON_FAST_PYCALL + #if CYTHON_FAST_PYCALL #include "frameobject.h" static PyObject* __Pyx_PyFunction_FastCallNoKw(PyCodeObject *co, PyObject **args, Py_ssize_t na, PyObject *globals) { @@ -10367,7 +10562,7 @@ static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, #endif /* PyCFunctionFastCall */ - #if CYTHON_FAST_PYCCALL + #if CYTHON_FAST_PYCCALL static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, PyObject **args, Py_ssize_t nargs) { PyCFunctionObject *func = (PyCFunctionObject*)func_obj; PyCFunction meth = PyCFunction_GET_FUNCTION(func); @@ -10390,7 +10585,7 @@ static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, P #endif /* PyErrFetchRestore */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { PyObject *tmp_type, *tmp_value, *tmp_tb; tmp_type = tstate->curexc_type; @@ -10414,7 +10609,7 @@ static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject #endif /* RaiseException */ - #if PY_MAJOR_VERSION < 3 + #if PY_MAJOR_VERSION < 3 static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, CYTHON_UNUSED PyObject *cause) { __Pyx_PyThreadState_declare @@ -10572,26 +10767,105 @@ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject } #endif +/* PyObjectCallMethO */ + #if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { + PyObject *self, *result; + PyCFunction cfunc; + cfunc = PyCFunction_GET_FUNCTION(func); + self = PyCFunction_GET_SELF(func); + if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) + return NULL; + result = cfunc(self, arg); + Py_LeaveRecursiveCall(); + if (unlikely(!result) && unlikely(!PyErr_Occurred())) { + PyErr_SetString( + PyExc_SystemError, + "NULL result without error in PyObject_Call"); + } + return result; +} +#endif + +/* PyObjectCallOneArg */ + #if CYTHON_COMPILING_IN_CPYTHON +static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) { + PyObject *result; + PyObject *args = PyTuple_New(1); + if (unlikely(!args)) return NULL; + Py_INCREF(arg); + PyTuple_SET_ITEM(args, 0, arg); + result = __Pyx_PyObject_Call(func, args, NULL); + Py_DECREF(args); + return result; +} +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { +#if CYTHON_FAST_PYCALL + if (PyFunction_Check(func)) { + return __Pyx_PyFunction_FastCall(func, &arg, 1); + } +#endif + if (likely(PyCFunction_Check(func))) { + if (likely(PyCFunction_GET_FLAGS(func) & METH_O)) { + return __Pyx_PyObject_CallMethO(func, arg); +#if CYTHON_FAST_PYCCALL + } else if (PyCFunction_GET_FLAGS(func) & METH_FASTCALL) { + return __Pyx_PyCFunction_FastCall(func, &arg, 1); +#endif + } + } + return __Pyx__PyObject_CallOneArg(func, arg); +} +#else +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { + PyObject *result; + PyObject *args = PyTuple_Pack(1, arg); + if (unlikely(!args)) return NULL; + result = __Pyx_PyObject_Call(func, args, NULL); + Py_DECREF(args); + return result; +} +#endif + +/* DictGetItem */ + #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { + PyObject *value; + value = PyDict_GetItemWithError(d, key); + if (unlikely(!value)) { + if (!PyErr_Occurred()) { + PyObject* args = PyTuple_Pack(1, key); + if (likely(args)) + PyErr_SetObject(PyExc_KeyError, args); + Py_XDECREF(args); + } + return NULL; + } + Py_INCREF(value); + return value; +} +#endif + /* RaiseTooManyValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { + static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { PyErr_Format(PyExc_ValueError, "too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected); } /* RaiseNeedMoreValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { + static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { PyErr_Format(PyExc_ValueError, "need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack", index, (index == 1) ? "" : "s"); } /* RaiseNoneIterError */ - static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) { + static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); } /* SaveResetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #if PY_VERSION_HEX >= 0x030700A2 *type = tstate->exc_state.exc_type; @@ -10630,7 +10904,7 @@ static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject #endif /* PyErrExceptionMatches */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx_PyErr_ExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(tuple); @@ -10655,7 +10929,7 @@ static CYTHON_INLINE int __Pyx_PyErr_ExceptionMatchesInState(PyThreadState* tsta #endif /* GetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #else static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) { @@ -10725,7 +10999,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* Import */ - static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { + static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { PyObject *empty_list = 0; PyObject *module = 0; PyObject *global_dict = 0; @@ -10790,7 +11064,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* ImportFrom */ - static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { + static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { PyObject* value = __Pyx_PyObject_GetAttrStr(module, name); if (unlikely(!value) && PyErr_ExceptionMatches(PyExc_AttributeError)) { PyErr_Format(PyExc_ImportError, @@ -10803,68 +11077,8 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) return value; } -/* PyObjectCallMethO */ - #if CYTHON_COMPILING_IN_CPYTHON -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { - PyObject *self, *result; - PyCFunction cfunc; - cfunc = PyCFunction_GET_FUNCTION(func); - self = PyCFunction_GET_SELF(func); - if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) - return NULL; - result = cfunc(self, arg); - Py_LeaveRecursiveCall(); - if (unlikely(!result) && unlikely(!PyErr_Occurred())) { - PyErr_SetString( - PyExc_SystemError, - "NULL result without error in PyObject_Call"); - } - return result; -} -#endif - -/* PyObjectCallOneArg */ - #if CYTHON_COMPILING_IN_CPYTHON -static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) { - PyObject *result; - PyObject *args = PyTuple_New(1); - if (unlikely(!args)) return NULL; - Py_INCREF(arg); - PyTuple_SET_ITEM(args, 0, arg); - result = __Pyx_PyObject_Call(func, args, NULL); - Py_DECREF(args); - return result; -} -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { -#if CYTHON_FAST_PYCALL - if (PyFunction_Check(func)) { - return __Pyx_PyFunction_FastCall(func, &arg, 1); - } -#endif - if (likely(PyCFunction_Check(func))) { - if (likely(PyCFunction_GET_FLAGS(func) & METH_O)) { - return __Pyx_PyObject_CallMethO(func, arg); -#if CYTHON_FAST_PYCCALL - } else if (PyCFunction_GET_FLAGS(func) & METH_FASTCALL) { - return __Pyx_PyCFunction_FastCall(func, &arg, 1); -#endif - } - } - return __Pyx__PyObject_CallOneArg(func, arg); -} -#else -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { - PyObject *result; - PyObject *args = PyTuple_Pack(1, arg); - if (unlikely(!args)) return NULL; - result = __Pyx_PyObject_Call(func, args, NULL); - Py_DECREF(args); - return result; -} -#endif - /* PyObjectCallNoArg */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { #if CYTHON_FAST_PYCALL if (PyFunction_Check(func)) { @@ -10885,18 +11099,21 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { #endif /* CLineInTraceback */ - #ifndef CYTHON_CLINE_IN_TRACEBACK + #ifndef CYTHON_CLINE_IN_TRACEBACK static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_line) { PyObject *use_cline; PyObject *ptype, *pvalue, *ptraceback; #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { - use_cline = PyDict_GetItem(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); + use_cline = __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); } else #endif { @@ -10922,7 +11139,7 @@ static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_li #endif /* CodeObjectCache */ - static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { + static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { int start = 0, mid = 0, end = count - 1; if (end >= 0 && code_line > entries[end].code_line) { return count; @@ -11002,7 +11219,7 @@ static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { } /* AddTraceback */ - #include "compile.h" + #include "compile.h" #include "frameobject.h" #include "traceback.h" static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( @@ -11087,7 +11304,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_npy_uint32(npy_uint32 value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_npy_uint32(npy_uint32 value) { const npy_uint32 neg_one = (npy_uint32) -1, const_zero = (npy_uint32) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -11118,7 +11335,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPyVerify */ - #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ + #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) #define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) @@ -11140,7 +11357,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -11171,7 +11388,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -11202,7 +11419,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_PY_LONG_LONG(unsigned PY_LONG_LONG value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_PY_LONG_LONG(unsigned PY_LONG_LONG value) { const unsigned PY_LONG_LONG neg_one = (unsigned PY_LONG_LONG) -1, const_zero = (unsigned PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -11233,7 +11450,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { return ::std::complex< float >(x, y); @@ -11253,7 +11470,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -11388,7 +11605,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { return ::std::complex< double >(x, y); @@ -11408,7 +11625,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -11543,7 +11760,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { const enum NPY_TYPES neg_one = (enum NPY_TYPES) -1, const_zero = (enum NPY_TYPES) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -11574,7 +11791,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { + static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -11763,7 +11980,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { + static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -11952,7 +12169,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { const PY_LONG_LONG neg_one = (PY_LONG_LONG) -1, const_zero = (PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -12141,7 +12358,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE unsigned PY_LONG_LONG __Pyx_PyInt_As_unsigned_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE unsigned PY_LONG_LONG __Pyx_PyInt_As_unsigned_PY_LONG_LONG(PyObject *x) { const unsigned PY_LONG_LONG neg_one = (unsigned PY_LONG_LONG) -1, const_zero = (unsigned PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -12330,7 +12547,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE npy_uint32 __Pyx_PyInt_As_npy_uint32(PyObject *x) { + static CYTHON_INLINE npy_uint32 __Pyx_PyInt_As_npy_uint32(PyObject *x) { const npy_uint32 neg_one = (npy_uint32) -1, const_zero = (npy_uint32) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -12519,7 +12736,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* FastTypeChecks */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { while (a) { a = a->tp_base; @@ -12591,7 +12808,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #endif /* CheckBinaryVersion */ - static int __Pyx_check_binary_version(void) { + static int __Pyx_check_binary_version(void) { char ctversion[4], rtversion[4]; PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION); PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion()); @@ -12607,7 +12824,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* ModuleImport */ - #ifndef __PYX_HAVE_RT_ImportModule + #ifndef __PYX_HAVE_RT_ImportModule #define __PYX_HAVE_RT_ImportModule static PyObject *__Pyx_ImportModule(const char *name) { PyObject *py_name = 0; @@ -12625,7 +12842,7 @@ static PyObject *__Pyx_ImportModule(const char *name) { #endif /* TypeImport */ - #ifndef __PYX_HAVE_RT_ImportType + #ifndef __PYX_HAVE_RT_ImportType #define __PYX_HAVE_RT_ImportType static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class_name, size_t size, int strict) @@ -12690,7 +12907,7 @@ static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class #endif /* VoidPtrImport */ - #ifndef __PYX_HAVE_RT_ImportVoidPtr + #ifndef __PYX_HAVE_RT_ImportVoidPtr #define __PYX_HAVE_RT_ImportVoidPtr static int __Pyx_ImportVoidPtr(PyObject *module, const char *name, void **p, const char *sig) { PyObject *d = 0; @@ -12739,7 +12956,7 @@ static int __Pyx_ImportVoidPtr(PyObject *module, const char *name, void **p, con #endif /* FunctionImport */ - #ifndef __PYX_HAVE_RT_ImportFunction + #ifndef __PYX_HAVE_RT_ImportFunction #define __PYX_HAVE_RT_ImportFunction static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig) { PyObject *d = 0; @@ -12793,7 +13010,7 @@ static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (** #endif /* InitStrings */ - static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { + static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { while (t->p) { #if PY_MAJOR_VERSION < 3 if (t->is_unicode) { @@ -12819,7 +13036,7 @@ static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (** if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) - PyErr_Clear(); + return -1; ++t; } return 0; @@ -13033,6 +13250,9 @@ static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_DECREF(x); return ival; } +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } diff --git a/gensim/models/fasttext_inner.pyx b/gensim/models/fasttext_inner.pyx index ac7cdafbd5..0cdd20a4e4 100644 --- a/gensim/models/fasttext_inner.pyx +++ b/gensim/models/fasttext_inner.pyx @@ -2,8 +2,11 @@ # cython: boundscheck=False # cython: wraparound=False # cython: cdivision=True +# cython: embedsignature=True # coding: utf-8 +"""Optimized cython functions for training :class:`~gensim.models.fasttext.FastText` model.""" + import cython import numpy as np cimport numpy as np @@ -19,11 +22,8 @@ except ImportError: # in scipy > 0.15, fblas function has been removed import scipy.linalg.blas as fblas -from word2vec_inner cimport bisect_left, random_int32, \ - scopy, saxpy, sdot, dsdot, snrm2, sscal, \ - REAL_t, EXP_TABLE, \ - our_dot, our_saxpy, \ - our_dot_double, our_dot_float, our_dot_noblas, our_saxpy_noblas +from word2vec_inner cimport bisect_left, random_int32, scopy, saxpy, dsdot, sscal, \ + REAL_t, EXP_TABLE, our_dot, our_saxpy, our_dot_double, our_dot_float, our_dot_noblas, our_saxpy_noblas REAL = np.float32 @@ -244,6 +244,30 @@ cdef void fast_sentence_cbow_hs( def train_batch_sg(model, sentences, alpha, _work, _l1): + """Update skip-gram model by training on a sequence of sentences. + + Each sentence is a list of string tokens, which are looked up in the model's + vocab dictionary. Called internally from :meth:`gensim.models.fasttext.FastText.train`. + + Parameters + ---------- + model : :class:`~gensim.models.fasttext.FastText` + Model to be trained. + sentences : iterable of list of str + Corpus streamed directly from disk/network. + alpha : float + Learning rate. + _work : np.ndarray + Private working memory for each worker. + _l1 : np.ndarray + Private working memory for each worker. + + Returns + ------- + int + Effective number of words trained. + + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) @@ -374,6 +398,29 @@ def train_batch_sg(model, sentences, alpha, _work, _l1): def train_batch_cbow(model, sentences, alpha, _work, _neu1): + """Update the CBOW model by training on a sequence of sentences. + + Each sentence is a list of string tokens, which are looked up in the model's + vocab dictionary. Called internally from :meth:`gensim.models.fasttext.FastText.train`. + + Parameters + ---------- + model : :class:`~gensim.models.fasttext.FastText` + Model to be trained. + sentences : iterable of list of str + Corpus streamed directly from disk/network. + alpha : float + Learning rate. + _work : np.ndarray + Private working memory for each worker. + _neu1 : np.ndarray + Private working memory for each worker. + Returns + ------- + int + Effective number of words trained. + + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) @@ -501,9 +548,16 @@ def train_batch_cbow(model, sentences, alpha, _work, _neu1): def init(): - """ - Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized - into table EXP_TABLE. Also calculate log(sigmoid(x)) into LOG_TABLE. + """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + Also calculate log(sigmoid(x)) into LOG_TABLE. + + Returns + ------- + {0, 1, 2} + Enumeration to signify underlying data type returned by the BLAS dot product calculation. + 0 signifies double, 1 signifies double, and 2 signifies that custom cython loops were used + instead of BLAS. + """ global our_dot global our_saxpy @@ -525,11 +579,11 @@ def init(): # check whether sdot returns double or float d_res = dsdot(&size, x, &ONE, y, &ONE) p_res = &d_res - if (abs(d_res - expected) < 0.0001): + if abs(d_res - expected) < 0.0001: our_dot = our_dot_double our_saxpy = saxpy return 0 # double - elif (abs(p_res[0] - expected) < 0.0001): + elif abs(p_res[0] - expected) < 0.0001: our_dot = our_dot_float our_saxpy = saxpy return 1 # float @@ -542,4 +596,3 @@ def init(): FAST_VERSION = init() # initialize the module MAX_WORDS_IN_BATCH = MAX_SENTENCE_LEN - diff --git a/gensim/models/keyedvectors.py b/gensim/models/keyedvectors.py index 2dac7c7443..3ac3bff062 100644 --- a/gensim/models/keyedvectors.py +++ b/gensim/models/keyedvectors.py @@ -5,57 +5,147 @@ # Copyright (C) 2018 RaRe Technologies s.r.o. # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -""" -Word vector storage and similarity look-ups. -Common code independent of the way the vectors are trained(Word2Vec, FastText, WordRank, VarEmbed etc) - -The word vectors are considered read-only in this class. - -Initialize the vectors by training e.g. Word2Vec:: - ->>> model = Word2Vec(sentences, size=100, window=5, min_count=5, workers=4) +"""This module implements word vectors and their similarity look-ups. + +Since trained word vectors are independent from the way they were trained (:class:`~gensim.models.word2vec.Word2Vec`, +:class:`~gensim.models.fasttext.FastText`, :class:`~gensim.models.wrappers.wordrank.WordRank`, +:class:`~gensim.models.wrappers.varembed.VarEmbed` etc), they can be represented by a standalone structure, +as implemented in this module. + +The structure is called "KeyedVectors" and is essentially a mapping between *entities* +and *vectors*. Each entity is identified by its string id, so this is a mapping between {str => 1D numpy array}. + +The entity typically corresponds to a word (so the mapping maps words to 1D vectors), +but for some models, they key can also correspond to a document, a graph node etc. To generalize +over different use-cases, this module calls the keys **entities**. Each entity is +always represented by its string id, no matter whether the entity is a word, a document or a graph node. + +Why use KeyedVectors instead of a full model? +============================================= + ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| capability | KeyedVectors | full model | note | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| continue training vectors | ❌ | ✅ | You need the full model to train or update vectors. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| smaller objects | ✅ | ❌ | KeyedVectors are smaller and need less RAM, because they | +| | | | don't need to store the model state that enables training. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| save/load from native | | | Vectors exported by the Facebook and Google tools | +| fasttext/word2vec format | ✅ | ❌ | do not support further training, but you can still load | +| | | | them into KeyedVectors. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| append new vectors | ✅ | ✅ | Add new entity-vector entries to the mapping dynamically. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| concurrency | ✅ | ✅ | Thread-safe, allows concurrent vector queries. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| shared RAM | ✅ | ✅ | Multiple processes can re-use the same data, keeping only | +| | | | a single copy in RAM using | +| | | | `mmap `_. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ +| fast load | ✅ | ✅ | Supports `mmap `_ | +| | | | to load data from disk instantaneously. | ++---------------------------+--------------+------------+-------------------------------------------------------------+ + +TL;DR: the main difference is that KeyedVectors do not support further training. +On the other hand, by shedding the internal data structures necessary for training, KeyedVectors offer a smaller RAM +footprint and a simpler interface. + +How to obtain word vectors? +=========================== + +Train a full model, then access its `model.wv` property, which holds the standalone keyed vectors. +For example, using the Word2Vec algorithm to train the vectors + +>>> from gensim.test.utils import common_texts +>>> from gensim.models import Word2Vec +>>> +>>> model = Word2Vec(common_texts, size=100, window=5, min_count=1, workers=4) >>> word_vectors = model.wv -Persist the word vectors to disk with:: +Persist the word vectors to disk with +>>> from gensim.test.utils import get_tmpfile +>>> from gensim.models import KeyedVectors +>>> +>>> fname = get_tmpfile("vectors.kv") >>> word_vectors.save(fname) ->>> word_vectors = KeyedVectors.load(fname) +>>> word_vectors = KeyedVectors.load(fname, mmap='r') The vectors can also be instantiated from an existing file on disk -in the original Google's word2vec C format as a KeyedVectors instance:: - - >>> from gensim.models import KeyedVectors - >>> word_vectors = KeyedVectors.load_word2vec_format('/tmp/vectors.txt', binary=False) # C text format - >>> word_vectors = KeyedVectors.load_word2vec_format('/tmp/vectors.bin', binary=True) # C binary format - -You can perform various syntactic/semantic NLP word tasks with the vectors. Some of them -are already built-in:: - - >>> word_vectors.most_similar(positive=['woman', 'king'], negative=['man']) - [('queen', 0.50882536), ...] - - >>> word_vectors.most_similar_cosmul(positive=['woman', 'king'], negative=['man']) - [('queen', 0.71382287), ...] - - >>> word_vectors.doesnt_match("breakfast cereal dinner lunch".split()) - 'cereal' - - >>> word_vectors.similarity('woman', 'man') - 0.73723527 - -Correlation with human opinion on word similarity:: - - >>> word_vectors.evaluate_word_pairs(os.path.join(module_path, 'test_data','wordsim353.tsv')) - 0.51, 0.62, 0.13 - -And on analogies:: - - >>> word_vectors.evaluate_word_analogies(os.path.join(module_path, 'test_data', 'questions-words.txt'))[0] - 0.58 +in the original Google's word2vec C format as a KeyedVectors instance + +>>> from gensim.test.utils import datapath +>>> +>>> wv_from_text = KeyedVectors.load_word2vec_format(datapath('word2vec_pre_kv_c'), binary=False) # C text format +>>> wv_from_bin = KeyedVectors.load_word2vec_format(datapath("euclidean_vectors.bin"), binary=True) # C binary format + +What can I do with word vectors? +================================ + +You can perform various syntactic/semantic NLP word tasks with the trained vectors. +Some of them are already built-in + +>>> import gensim.downloader as api +>>> +>>> word_vectors = api.load("glove-wiki-gigaword-100") # load pre-trained word-vectors from gensim-data +>>> +>>> result = word_vectors.most_similar(positive=['woman', 'king'], negative=['man']) +>>> print("{}: {:.4f}".format(*result[0])) +queen: 0.7699 +>>> +>>> result = word_vectors.most_similar_cosmul(positive=['woman', 'king'], negative=['man']) +>>> print("{}: {:.4f}".format(*result[0])) +queen: 0.8965 +>>> +>>> print(word_vectors.doesnt_match("breakfast cereal dinner lunch".split())) +cereal +>>> +>>> similarity = word_vectors.similarity('woman', 'man') +>>> similarity > 0.8 +True +>>> +>>> result = word_vectors.similar_by_word("cat") +>>> print("{}: {:.4f}".format(*result[0])) +dog: 0.8798 +>>> +>>> sentence_obama = 'Obama speaks to the media in Illinois'.lower().split() +>>> sentence_president = 'The president greets the press in Chicago'.lower().split() +>>> +>>> similarity = word_vectors.wmdistance(sentence_obama, sentence_president) +>>> print("{:.4f}".format(similarity)) +3.4893 +>>> +>>> distance = word_vectors.distance("media", "media") +>>> print("{:.1f}".format(distance)) +0.0 +>>> +>>> sim = word_vectors.n_similarity(['sushi', 'shop'], ['japanese', 'restaurant']) +>>> print("{:.4f}".format(sim)) +0.7067 +>>> +>>> vector = word_vectors['computer'] # numpy vector of a word +>>> vector.shape +(100,) +>>> +>>> vector = word_vectors.wv.word_vec('office', use_norm=True) +>>> vector.shape +(100,) + +Correlation with human opinion on word similarity + +>>> from gensim.test.utils import datapath +>>> +>>> similarities = model.wv.evaluate_word_pairs(datapath('wordsim353.tsv')) + +And on word analogies + +>>> analogy_scores = model.wv.accuracy(datapath('questions-words.txt')) and so on. """ + from __future__ import division # py3 "true division" import logging @@ -89,12 +179,10 @@ class Vocab(object): - """ - A single vocabulary item, used internally for collecting per-word frequency/sampling info, + """A single vocabulary item, used internally for collecting per-word frequency/sampling info, and for constructing binary trees (incl. both word leaves and inner nodes). """ - def __init__(self, **kwargs): self.count = 0 self.__dict__.update(kwargs) @@ -108,7 +196,7 @@ def __str__(self): class BaseKeyedVectors(utils.SaveLoad): - + """Abstract base class / interface for various types of word vectors.""" def __init__(self, vector_size): self.vectors = zeros((0, vector_size)) self.vocab = {} @@ -123,30 +211,45 @@ def load(cls, fname_or_handle, **kwargs): return super(BaseKeyedVectors, cls).load(fname_or_handle, **kwargs) def similarity(self, entity1, entity2): - """Compute cosine similarity between entities, specified by string tag. - """ + """Compute cosine similarity between two entities, specified by their string id.""" raise NotImplementedError() def most_similar(self, **kwargs): """Find the top-N most similar entities. Possibly have `positive` and `negative` list of entities in `**kwargs`. + """ return NotImplementedError() def distance(self, entity1, entity2): - """Compute distance between vectors of two input entities, specified by string tag. - """ + """Compute distance between vectors of two input entities, specified by their string id.""" raise NotImplementedError() def distances(self, entity1, other_entities=()): - """Compute distances from given entity (string tag) to all entities in `other_entity`. - If `other_entities` is empty, return distance between `entity1` and all entities in vocab. + """Compute distances from a given entity (its string id) to all entities in `other_entity`. + If `other_entities` is empty, return the distance between `entity1` and all entities in vocab. + """ raise NotImplementedError() def get_vector(self, entity): - """Accept a single entity as input, specified by string tag. - Returns the entity's representations in vector space, as a 1D numpy array. + """Get the entity's representations in vector space, as a 1D numpy array. + + Parameters + ---------- + entity : str + Identifier of the entity to return the vector for. + + Returns + ------- + numpy.ndarray + Vector for the specified entity. + + Raises + ------ + KeyError + If the given entity identifier doesn't exist. + """ if entity in self.vocab: result = self.vectors[self.vocab[entity].index] @@ -156,17 +259,17 @@ def get_vector(self, entity): raise KeyError("'%s' not in vocabulary" % entity) def add(self, entities, weights, replace=False): - """Add entities and theirs vectors in a manual way. - If some entity is already in the vocabulary, old vector is keeped unless `replace` flag is True. + """Append entities and theirs vectors in a manual way. + If some entity is already in the vocabulary, the old vector is kept unless `replace` flag is True. Parameters ---------- entities : list of str - Entities specified by string tags. + Entities specified by string ids. weights: {list of numpy.ndarray, numpy.ndarray} - List of 1D np.array vectors or 2D np.array of vectors. + List of 1D np.array vectors or a 2D np.array of vectors. replace: bool, optional - Flag indicating whether to replace vectors for entities which are already in the vocabulary, + Flag indicating whether to replace vectors for entities which already exist in the vocabulary, if True - replace vectors, otherwise - keep old vectors. """ @@ -198,12 +301,12 @@ def add(self, entities, weights, replace=False): def __setitem__(self, entities, weights): """Add entities and theirs vectors in a manual way. If some entity is already in the vocabulary, old vector is replaced with the new one. - This method is alias for `add` with `replace=True`. + This method is alias for :meth:`~gensim.models.keyedvectors.BaseKeyedVectors.add` with `replace=True`. Parameters ---------- entities : {str, list of str} - Entities specified by string tags. + Entities specified by their string ids. weights: {list of numpy.ndarray, numpy.ndarray} List of 1D np.array vectors or 2D np.array of vectors. @@ -215,14 +318,17 @@ def __setitem__(self, entities, weights): self.add(entities, weights, replace=True) def __getitem__(self, entities): - """ - Accept a single entity (string tag) or list of entities as input. + """Get vector representation of `entities`. - If a single string or int, return designated tag's vector - representation, as a 1D numpy array. + Parameters + ---------- + entities : {str, list of str} + Input entity/entities. - If a list, return designated tags' vector representations as a - 2D numpy array: #tags x #vector_size. + Returns + ------- + numpy.ndarray + Vector representation for `entities` (1D if `entities` is string, otherwise - 2D). """ if isinstance(entities, string_types): @@ -235,11 +341,11 @@ def __contains__(self, entity): return entity in self.vocab def most_similar_to_given(self, entity1, entities_list): - """Return the entity from entities_list most similar to entity1.""" + """Get the `entity` from `entities_list` most similar to `entity1`.""" return entities_list[argmax([self.similarity(entity1, entity) for entity in entities_list])] def closer_than(self, entity1, entity2): - """Returns all entities that are closer to `entity1` than `entity2` is to `entity1`.""" + """Get all entities that are closer to `entity1` than `entity2` is to `entity1`.""" all_distances = self.distances(entity1) e1_index = self.vocab[entity1].index e2_index = self.vocab[entity2].index @@ -253,7 +359,6 @@ def rank(self, entity1, entity2): class WordEmbeddingsKeyedVectors(BaseKeyedVectors): """Class containing common methods for operations over word vectors.""" - def __init__(self, vector_size): super(WordEmbeddingsKeyedVectors, self).__init__(vector_size=vector_size) self.vectors_norm = None @@ -296,14 +401,17 @@ def __contains__(self, word): return word in self.vocab def save(self, *args, **kwargs): - """Saves the keyedvectors. This saved model can be loaded again using - :func:`~gensim.models.*2vec.*2VecKeyedVectors.load` which supports - operations on trained word vectors like `most_similar`. + """Save KeyedVectors. Parameters ---------- fname : str - Path to the file. + Path to the output file. + + See Also + -------- + :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.load` + Load saved model. """ # don't bother storing the cached normalized vectors @@ -311,16 +419,24 @@ def save(self, *args, **kwargs): super(WordEmbeddingsKeyedVectors, self).save(*args, **kwargs) def word_vec(self, word, use_norm=False): - """ - Accept a single word as input. - Returns the word's representations in vector space, as a 1D numpy array. + """Get `word` representations in vector space, as a 1D numpy array. + + Parameters + ---------- + word : str + Input word + use_norm : bool, optional + If True - resulting vector will be L2-normalized (unit euclidean length). - If `use_norm` is True, returns the normalized word vector. + Returns + ------- + numpy.ndarray + Vector representation of `word`. - Examples - -------- - >>> trained_model['office'] - array([ -1.40128313e-02, ...]) + Raises + ------ + KeyError + If word not in vocabulary. """ if word in self.vocab: @@ -338,8 +454,7 @@ def get_vector(self, word): return self.word_vec(word) def words_closer_than(self, w1, w2): - """ - Returns all words that are closer to `w1` than `w2` is to `w1`. + """Get all words that are closer to `w1` than `w2` is to `w1`. Parameters ---------- @@ -353,18 +468,12 @@ def words_closer_than(self, w1, w2): list (str) List of words that are closer to `w1` than `w2` is to `w1`. - Examples - -------- - >>> model.words_closer_than('carnivore', 'mammal') - ['dog', 'canine'] - """ return super(WordEmbeddingsKeyedVectors, self).closer_than(w1, w2) def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=None, indexer=None): - """ - Find the top-N most similar words. Positive words contribute positively towards the - similarity, negative words negatively. + """Find the top-N most similar words. + Positive words contribute positively towards the similarity, negative words negatively. This method computes cosine similarity between a simple mean of the projection weight vectors of the given words and the vectors for each word in the model. @@ -373,13 +482,13 @@ def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=Non Parameters ---------- - positive : :obj: `list` of :obj: `str` + positive : list of str, optional List of words that contribute positively. - negative : :obj: `list` of :obj: `str` + negative : list of str, optional List of words that contribute negatively. - topn : int + topn : int, optional Number of top-N similar words to return. - restrict_vocab : int + restrict_vocab : int, optional Optional integer which limits the range of vectors which are searched for most-similar values. For example, restrict_vocab=10000 would only check the first 10000 word vectors in the vocabulary order. (This may be @@ -387,13 +496,8 @@ def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=Non Returns ------- - :obj: `list` of :obj: `tuple` - Returns a list of tuples (word, similarity) - - Examples - -------- - >>> trained_model.most_similar(positive=['woman', 'king'], negative=['man']) - [('queen', 0.50882536), ...] + list of (str, float) + Sequence of (word, similarity). """ if positive is None: @@ -443,17 +547,16 @@ def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=Non return result[:topn] def similar_by_word(self, word, topn=10, restrict_vocab=None): - """ - Find the top-N most similar words. + """Find the top-N most similar words. Parameters ---------- word : str Word - topn : int + topn : {int, False}, optional Number of top-N similar words to return. If topn is False, similar_by_word returns the vector of similarity scores. - restrict_vocab : int + restrict_vocab : int, optional Optional integer which limits the range of vectors which are searched for most-similar values. For example, restrict_vocab=10000 would only check the first 10000 word vectors in the vocabulary order. (This may be @@ -461,30 +564,23 @@ def similar_by_word(self, word, topn=10, restrict_vocab=None): Returns ------- - :obj: `list` of :obj: `tuple` - Returns a list of tuples (word, similarity) - - Example:: - - >>> trained_model.similar_by_word('graph') - [('user', 0.9999163150787354), ...] + list of (str, float) + Sequence of (word, similarity). """ return self.most_similar(positive=[word], topn=topn, restrict_vocab=restrict_vocab) def similar_by_vector(self, vector, topn=10, restrict_vocab=None): - """ - Find the top-N most similar words by vector. + """Find the top-N most similar words by vector. Parameters ---------- vector : numpy.array - vector from which similarities are to be computed. - expected shape (dim,) - topn : int + Vector from which similarities are to be computed. + topn : {int, False}, optional Number of top-N similar words to return. If topn is False, similar_by_vector returns the vector of similarity scores. - restrict_vocab : int + restrict_vocab : int, optional Optional integer which limits the range of vectors which are searched for most-similar values. For example, restrict_vocab=10000 would only check the first 10000 word vectors in the vocabulary order. (This may be @@ -492,16 +588,16 @@ def similar_by_vector(self, vector, topn=10, restrict_vocab=None): Returns ------- - :obj: `list` of :obj: `tuple` - Returns a list of tuples (word, similarity) + list of (str, float) + Sequence of (word, similarity). """ return self.most_similar(positive=[vector], topn=topn, restrict_vocab=restrict_vocab) def similarity_matrix(self, dictionary, tfidf=None, threshold=0.0, exponent=2.0, nonzero_limit=100, dtype=REAL): - """Constructs a term similarity matrix for computing Soft Cosine Measure. + """Construct a term similarity matrix for computing Soft Cosine Measure. - Constructs a a sparse term similarity matrix in the :class:`scipy.sparse.csc_matrix` format for computing + This creates a sparse term similarity matrix in the :class:`scipy.sparse.csc_matrix` format for computing Soft Cosine Measure between documents. Parameters @@ -535,16 +631,15 @@ def similarity_matrix(self, dictionary, tfidf=None, threshold=0.0, exponent=2.0, -------- :func:`gensim.matutils.softcossim` The Soft Cosine Measure. - :class:`gensim.similarities.docsim.SoftCosineSimilarity` + :class:`~gensim.similarities.docsim.SoftCosineSimilarity` A class for performing corpus-based similarity queries with Soft Cosine Measure. - Notes ----- The constructed matrix corresponds to the matrix Mrel defined in section 2.1 of `Delphine Charlet and Geraldine Damnati, "SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering", 2017 - `__. + `_. """ logger.info("constructing a term similarity matrix") @@ -608,37 +703,42 @@ def similarity_matrix(self, dictionary, tfidf=None, threshold=0.0, exponent=2.0, return matrix.tocsc() def wmdistance(self, document1, document2): - """ - Compute the Word Mover's Distance between two documents. When using this - code, please consider citing the following papers: + """Compute the Word Mover's Distance between two documents. - .. Ofir Pele and Michael Werman, "A linear time histogram metric for improved SIFT matching". - .. Ofir Pele and Michael Werman, "Fast and robust earth mover's distances". - .. Matt Kusner et al. "From Word Embeddings To Document Distances". + When using this code, please consider citing the following papers: - Note that if one of the documents have no words that exist in the - Word2Vec vocab, `float('inf')` (i.e. infinity) will be returned. + * `Ofir Pele and Michael Werman "A linear time histogram metric for improved SIFT matching" + `_ + * `Ofir Pele and Michael Werman "Fast and robust earth mover's distances" + `_ + * `Matt Kusner et al. "From Word Embeddings To Document Distances" + `_. - This method only works if `pyemd` is installed (can be installed via pip, but requires a C compiler). + Parameters + ---------- + document1 : list of str + Input document. + document2 : list of str + Input document. - Example: - >>> # Train word2vec model. - >>> model = Word2Vec(sentences) + Returns + ------- + float + Word Mover's distance between `document1` and `document2`. - >>> # Some sentences to test. - >>> sentence_obama = 'Obama speaks to the media in Illinois'.lower().split() - >>> sentence_president = 'The president greets the press in Chicago'.lower().split() + Warnings + -------- + This method only works if `pyemd `_ is installed. - >>> # Remove their stopwords. - >>> from nltk.corpus import stopwords - >>> stopwords = nltk.corpus.stopwords.words('english') - >>> sentence_obama = [w for w in sentence_obama if w not in stopwords] - >>> sentence_president = [w for w in sentence_president if w not in stopwords] + If one of the documents have no words that exist in the vocab, `float('inf')` (i.e. infinity) + will be returned. - >>> # Compute WMD. - >>> distance = model.wmdistance(sentence_obama, sentence_president) - """ + Raises + ------ + ImportError + If `pyemd `_ isn't installed. + """ if not PYEMD_EXT: raise ImportError("Please install pyemd Python package to compute WMD.") @@ -700,25 +800,31 @@ def nbow(document): return emd(d1, d2, distance_matrix) def most_similar_cosmul(self, positive=None, negative=None, topn=10): - """ - Find the top-N most similar words, using the multiplicative combination objective - proposed by Omer Levy and Yoav Goldberg. Positive words still contribute - positively towards the similarity, negative words negatively, but with less - susceptibility to one large distance dominating the calculation. - + """Find the top-N most similar words, using the multiplicative combination objective, + proposed by `Omer Levy and Yoav Goldberg "Linguistic Regularities in Sparse and Explicit Word Representations" + `_. Positive words still contribute positively towards the similarity, + negative words negatively, but with less susceptibility to one large distance dominating the calculation. In the common analogy-solving case, of two positive and one negative examples, this method is equivalent to the "3CosMul" objective (equation (4)) of Levy and Goldberg. Additional positive or negative examples contribute to the numerator or denominator, - respectively – a potentially sensible but untested extension of the method. (With - a single positive example, rankings will be the same as in the default most_similar.) + respectively - a potentially sensible but untested extension of the method. + With a single positive example, rankings will be the same as in the default + :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar`. - Example:: - - >>> trained_model.most_similar_cosmul(positive=['baghdad', 'england'], negative=['london']) - [(u'iraq', 0.8488819003105164), ...] + Parameters + ---------- + positive : list of str, optional + List of words that contribute positively. + negative : list of str, optional + List of words that contribute negatively. + topn : int, optional + Number of top-N similar words to return. - .. Omer Levy and Yoav Goldberg. Linguistic Regularities in Sparse and Explicit Word Representations, 2014. + Returns + ------- + list of (str, float) + Sequence of (word, similarity). """ if positive is None: @@ -763,24 +869,18 @@ def most_similar_cosmul(self, positive=None, negative=None, topn=10): return result[:topn] def doesnt_match(self, words): - """ - Which word from the given list doesn't go with the others? + """Which word from the given list doesn't go with the others? Parameters ---------- - words : :obj: `list` of :obj: `str` - List of words + words : list of str + List of words. Returns ------- str The word further away from the mean of all words. - Example - ------- - >>> trained_model.doesnt_match("breakfast cereal dinner lunch".split()) - 'cereal' - """ self.init_sims() @@ -797,23 +897,19 @@ def doesnt_match(self, words): @staticmethod def cosine_similarities(vector_1, vectors_all): - """ - Return cosine similarities between one vector and a set of other vectors. + """Compute cosine similarities between one vector and a set of other vectors. Parameters ---------- - vector_1 : numpy.array - vector from which similarities are to be computed. - expected shape (dim,) - vectors_all : numpy.array - for each row in vectors_all, distance from vector_1 is computed. - expected shape (num_vectors, dim) + vector_1 : numpy.ndarray + Vector from which similarities are to be computed, expected shape (dim,). + vectors_all : numpy.ndarray + For each row in vectors_all, distance from vector_1 is computed, expected shape (num_vectors, dim). Returns ------- - :obj: `numpy.array` - Contains cosine distance between vector_1 and each row in vectors_all. - shape (num_vectors,) + numpy.ndarray + Contains cosine distance between `vector_1` and each row in `vectors_all`, shape (num_vectors,). """ norm = np.linalg.norm(vector_1) @@ -823,28 +919,26 @@ def cosine_similarities(vector_1, vectors_all): return similarities def distances(self, word_or_vector, other_words=()): - """ - Compute cosine distances from given word or vector to all words in `other_words`. + """Compute cosine distances from given word or vector to all words in `other_words`. If `other_words` is empty, return distance between `word_or_vectors` and all words in vocab. Parameters ---------- - word_or_vector : str or numpy.array + word_or_vector : {str, numpy.ndarray} Word or vector from which distances are to be computed. - - other_words : iterable(str) or None + other_words : iterable of str For each word in `other_words` distance from `word_or_vector` is computed. If None or empty, distance of `word_or_vector` from all words in vocab is computed (including itself). Returns ------- numpy.array - Array containing distances to all words in `other_words` from input `word_or_vector`, - in the same order as `other_words`. + Array containing distances to all words in `other_words` from input `word_or_vector`. - Notes + Raises ----- - Raises KeyError if either `word_or_vector` or any word in `other_words` is absent from vocab. + KeyError + If either `word_or_vector` or any word in `other_words` is absent from vocab. """ if isinstance(word_or_vector, string_types): @@ -859,52 +953,56 @@ def distances(self, word_or_vector, other_words=()): return 1 - self.cosine_similarities(input_vector, other_vectors) def distance(self, w1, w2): - """ - Compute cosine distance between two words. - - Examples - -------- + """Compute cosine distance between two words. + Calculate 1 - :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similarity`. - >>> trained_model.distance('woman', 'man') - 0.34 + Parameters + ---------- + w1 : str + Input word. + w2 : str + Input word. - >>> trained_model.distance('woman', 'woman') - 0.0 + Returns + ------- + float + Distance between `w1` and `w2`. """ return 1 - self.similarity(w1, w2) def similarity(self, w1, w2): - """ - Compute cosine similarity between two words. - - Examples - -------- + """Compute cosine similarity between two words. - >>> trained_model.similarity('woman', 'man') - 0.73723527 + Parameters + ---------- + w1 : str + Input word. + w2 : str + Input word. - >>> trained_model.similarity('woman', 'woman') - 1.0 + Returns + ------- + float + Cosine similarity between `w1` and `w2`. """ return dot(matutils.unitvec(self[w1]), matutils.unitvec(self[w2])) def n_similarity(self, ws1, ws2): - """ - Compute cosine similarity between two sets of words. + """Compute cosine similarity between two sets of words. - Examples - -------- - - >>> trained_model.n_similarity(['sushi', 'shop'], ['japanese', 'restaurant']) - 0.61540466561049689 - - >>> trained_model.n_similarity(['restaurant', 'japanese'], ['japanese', 'restaurant']) - 1.0000000000000004 + Parameters + ---------- + ws1 : list of str + Sequence of words. + ws2: list of str + Sequence of words. - >>> trained_model.n_similarity(['sushi'], ['restaurant']) == trained_model.similarity('sushi', 'restaurant') - True + Returns + ------- + numpy.ndarray + Similarities between `ws1` and `ws2`. """ if not(len(ws1) and len(ws2)): @@ -1057,27 +1155,33 @@ def log_accuracy(section): @deprecated("Method will be removed in 4.0.0, use self.evaluate_word_analogies() instead") def accuracy(self, questions, restrict_vocab=30000, most_similar=most_similar, case_insensitive=True): - """ - Compute accuracy of the model. `questions` is a filename where lines are - 4-tuples of words, split into sections by ": SECTION NAME" lines. - See questions-words.txt in - https://storage.googleapis.com/google-code-archive-source/v2/code.google.com/word2vec/source-archive.zip - for an example. + """Compute accuracy of the model. The accuracy is reported (=printed to log and returned as a list) for each section separately, plus there's one aggregate summary at the end. - Use `restrict_vocab` to ignore all questions containing a word not in the first `restrict_vocab` - words (default 30,000). This may be meaningful if you've sorted the vocabulary by descending frequency. - In case `case_insensitive` is True, the first `restrict_vocab` words are taken first, and then - case normalization is performed. + Parameters + ---------- + questions : str + Path to file, where lines are 4-tuples of words, split into sections by ": SECTION NAME" lines. + See `gensim/test/test_data/questions-words.txt` as example. + restrict_vocab : int, optional + Ignore all 4-tuples containing a word not in the first `restrict_vocab` words. + This may be meaningful if you've sorted the model vocabulary by descending frequency (which is standard + in modern word embedding models). + most_similar : function, optional + Function used for similarity calculation. + case_insensitive : bool, optional + If True - convert all words to their uppercase form before evaluating the performance. + Useful to handle case-mismatch between training tokens and words in the test set. + In case of multiple case variants of a single word, the vector for the first occurrence + (also the most frequent if vocabulary is sorted) is taken. - Use `case_insensitive` to convert all words in questions and vocab to their uppercase form before - evaluating the accuracy (default True). Useful in case of case-mismatch between training tokens - and question words. In case of multiple case variants of a single word, the vector for the first - occurrence (also the most frequent if vocabulary is sorted) is taken. + Returns + ------- + list of dict of (str, (str, str, str) + Full lists of correct and incorrect predictions divided by sections. - This method corresponds to the `compute-accuracy` script of the original C word2vec. """ ok_vocab = [(w, self.vocab[w]) for w in self.index2word[:restrict_vocab]] ok_vocab = {w.upper(): v for w, v in reversed(ok_vocab)} if case_insensitive else dict(ok_vocab) @@ -1145,28 +1249,40 @@ def log_evaluate_word_pairs(pearson, spearman, oov, pairs): def evaluate_word_pairs(self, pairs, delimiter='\t', restrict_vocab=300000, case_insensitive=True, dummy4unknown=False): - """ - Compute correlation of the model with human similarity judgments. `pairs` is a filename of a dataset where - lines are 3-tuples, each consisting of a word pair and a similarity value, separated by `delimiter`. - An example dataset is included in Gensim (test/test_data/wordsim353.tsv). More datasets can be found at - http://technion.ac.il/~ira.leviant/MultilingualVSMdata.html or https://www.cl.cam.ac.uk/~fh295/simlex.html. - - The model is evaluated using Pearson correlation coefficient and Spearman rank-order correlation coefficient - between the similarities from the dataset and the similarities produced by the model itself. - The results are printed to log and returned as a triple (pearson, spearman, ratio of pairs with unknown words). - - Use `restrict_vocab` to ignore all word pairs containing a word not in the first `restrict_vocab` - words (default 300,000). This may be meaningful if you've sorted the vocabulary by descending frequency. - If `case_insensitive` is True, the first `restrict_vocab` words are taken, and then case normalization - is performed. - - Use `case_insensitive` to convert all words in the pairs and vocab to their uppercase form before - evaluating the model (default True). Useful when you expect case-mismatch between training tokens - and words pairs in the dataset. If there are multiple case variants of a single word, the vector for the first - occurrence (also the most frequent if vocabulary is sorted) is taken. - - Use `dummy4unknown=True` to produce zero-valued similarities for pairs with out-of-vocabulary words. - Otherwise (default False), these pairs are skipped entirely. + """Compute correlation of the model with human similarity judgments. + + Notes + ----- + More datasets can be found at + * http://technion.ac.il/~ira.leviant/MultilingualVSMdata.html + * https://www.cl.cam.ac.uk/~fh295/simlex.html. + + Parameters + ---------- + pairs : str + Path to file, where lines are 3-tuples, each consisting of a word pair and a similarity value. + See `test/test_data/wordsim353.tsv` as example. + delimiter : str, optional + Separator in `pairs` file. + restrict_vocab : int, optional + Ignore all 4-tuples containing a word not in the first `restrict_vocab` words. + This may be meaningful if you've sorted the model vocabulary by descending frequency (which is standard + in modern word embedding models). + case_insensitive : bool, optional + If True - convert all words to their uppercase form before evaluating the performance. + Useful to handle case-mismatch between training tokens and words in the test set. + In case of multiple case variants of a single word, the vector for the first occurrence + (also the most frequent if vocabulary is sorted) is taken. + dummy4unknown : bool, optional + If True - produce zero accuracies for 4-tuples with out-of-vocabulary words. + Otherwise, these tuples are skipped entirely and not used in the evaluation. + + Returns + ------- + (float, float, float) + Pearson correlation coefficient, Spearman rank-order correlation coefficient between the similarities + from the dataset and the similarities produced by the model itself, ratio of pairs with unknown words. + """ ok_vocab = [(w, self.vocab[w]) for w in self.index2word[:restrict_vocab]] ok_vocab = {w.upper(): v for w, v in reversed(ok_vocab)} if case_insensitive else dict(ok_vocab) @@ -1223,14 +1339,19 @@ def evaluate_word_pairs(self, pairs, delimiter='\t', restrict_vocab=300000, return pearson, spearman, oov_ratio def init_sims(self, replace=False): - """ - Precompute L2-normalized vectors. + """Precompute L2-normalized vectors. - If `replace` is set, forget the original vectors and only keep the normalized - ones = saves lots of memory! + Parameters + ---------- + replace : bool, optional + If True - forget the original vectors and only keep the normalized ones = saves lots of memory! - Note that you **cannot continue training** after doing a replace. The model becomes - effectively read-only = you can call `most_similar`, `similarity` etc., but not `train`. + Warnings + -------- + You **cannot continue training** after doing a replace. + The model becomes effectively read-only: you can call + :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar`, + :meth:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similarity`, etc., but not train. """ if getattr(self, 'vectors_norm', None) is None or replace: @@ -1244,8 +1365,9 @@ def init_sims(self, replace=False): class Word2VecKeyedVectors(WordEmbeddingsKeyedVectors): - """Class to contain vectors and vocab for word2vec model. + """Mapping between words and vectors for the :class:`~gensim.models.Word2Vec` model. Used to perform operations on the vectors such as vector lookup, distance, similarity etc. + """ def save_word2vec_format(self, fname, fvocab=None, binary=False, total_vec=None): """Store the input-hidden weight matrix in the same format used by the original @@ -1255,13 +1377,13 @@ def save_word2vec_format(self, fname, fvocab=None, binary=False, total_vec=None) ---------- fname : str The file path used to save the vectors in - fvocab : str + fvocab : str, optional Optional file path used to save the vocabulary - binary : bool + binary : bool, optional If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. - total_vec : int + total_vec : int, optional Optional parameter to explicitly specify total no. of vectors - (in case word vectors are appended with document vectors afterwards) + (in case word vectors are appended with document vectors afterwards). """ # from gensim.models.word2vec import save_word2vec_format @@ -1273,7 +1395,9 @@ def load_word2vec_format(cls, fname, fvocab=None, binary=False, encoding='utf8', limit=None, datatype=REAL): """Load the input-hidden weight matrix from the original C word2vec-tool format. - Note that the information stored in the file is incomplete (the binary tree is missing), + Warnings + -------- + The information stored in the file is incomplete (the binary tree is missing), so while you can query for word similarity etc., you cannot continue training with a model loaded this way. @@ -1281,31 +1405,29 @@ def load_word2vec_format(cls, fname, fvocab=None, binary=False, encoding='utf8', ---------- fname : str The file path to the saved word2vec-format file. - fvocab : str - Optional file path to the vocabulary.Word counts are read from `fvocab` filename, - if set (this is the file generated by `-save-vocab` flag of the original C tool). - binary : bool + fvocab : str, optional + File path to the vocabulary.Word counts are read from `fvocab` filename, if set + (this is the file generated by `-save-vocab` flag of the original C tool). + binary : bool, optional If True, indicates whether the data is in binary word2vec format. - encoding : str - If you trained the C model using non-utf8 encoding for words, specify that - encoding in `encoding`. - unicode_errors : str + encoding : str, optional + If you trained the C model using non-utf8 encoding for words, specify that encoding in `encoding`. + unicode_errors : str, optional default 'strict', is a string suitable to be passed as the `errors` argument to the unicode() (Python 2.x) or str() (Python 3.x) function. If your source file may include word tokens truncated in the middle of a multibyte unicode character (as is common from the original word2vec.c tool), 'ignore' or 'replace' may help. - limit : int + limit : int, optional Sets a maximum number of word-vectors to read from the file. The default, None, means read all. - datatype : :class: `numpy.float*` - (Experimental) Can coerce dimensions to a non-default float type (such - as np.float16) to save memory. (Such types may result in much slower bulk operations - or incompatibility with optimized routines.) + datatype : type, optional + (Experimental) Can coerce dimensions to a non-default float type (such as `np.float16`) to save memory. + Such types may result in much slower bulk operations or incompatibility with optimized routines.) Returns ------- - :obj: `~gensim.models.word2vec.Wod2Vec` - Returns the loaded model as an instance of :class: `~gensim.models.word2vec.Wod2Vec`. + :class:`~gensim.models.keyedvectors.Word2VecKeyedVectors` + Loaded model. """ # from gensim.models.word2vec import load_word2vec_format @@ -1314,7 +1436,7 @@ def load_word2vec_format(cls, fname, fvocab=None, binary=False, encoding='utf8', limit=limit, datatype=datatype) def get_keras_embedding(self, train_embeddings=False): - """Return a Keras 'Embedding' layer with weights set as the Word2Vec model's learned word embeddings + """Get a Keras 'Embedding' layer with weights set as the Word2Vec model's learned word embeddings. Parameters ---------- @@ -1324,8 +1446,17 @@ def get_keras_embedding(self, train_embeddings=False): Returns ------- - :obj: `keras.layers.Embedding` - Embedding layer + `keras.layers.Embedding` + Embedding layer. + + Raises + ------ + ImportError + If `Keras `_ not installed. + + Warnings + -------- + Current method work only if `Keras `_ installed. """ try: @@ -1378,14 +1509,18 @@ def doctag_syn0norm(self): return self.vectors_docs_norm def __getitem__(self, index): - """ - Accept a single key (int or string tag) or list of keys as input. + """Get vector representation of `index`. - If a single string or int, return designated tag's vector - representation, as a 1D numpy array. + Parameters + ---------- + index : {str, list of str} + Doctag or sequence of doctags. + + Returns + ------- + numpy.ndarray + Vector representation for `index` (1D if `index` is string, otherwise - 2D). - If a list, return designated tags' vector representations as a - 2D numpy array: #tags x #vector_size. """ if index in self: if isinstance(index, string_types + integer_types + (integer,)): @@ -1403,14 +1538,17 @@ def __len__(self): return self.count def save(self, *args, **kwargs): - """Saves the keyedvectors. This saved model can be loaded again using - :func:`~gensim.models.doc2vec.Doc2VecKeyedVectors.load` which supports - operations on trained document vectors like `most_similar`. + """Save object. Parameters ---------- fname : str - Path to the file. + Path to the output file. + + See Also + -------- + :meth:`~gensim.models.keyedvectors.Doc2VecKeyedVectors.load` + Load object. """ # don't bother storing the cached normalized vectors @@ -1418,15 +1556,19 @@ def save(self, *args, **kwargs): super(Doc2VecKeyedVectors, self).save(*args, **kwargs) def init_sims(self, replace=False): - """ - Precompute L2-normalized vectors. + """Precompute L2-normalized vectors. - If `replace` is set, forget the original vectors and only keep the normalized - ones = saves lots of memory! + Parameters + ---------- + replace : bool, optional + If True - forget the original vectors and only keep the normalized ones = saves lots of memory! - Note that you **cannot continue training or inference** after doing a replace. - The model becomes effectively read-only = you can call `most_similar`, `similarity` - etc., but not `train` or `infer_vector`. + Warnings + -------- + You **cannot continue training** after doing a replace. + The model becomes effectively read-only: you can call + :meth:`~gensim.models.keyedvectors.Doc2VecKeyedVectors.most_similar`, + :meth:`~gensim.models.keyedvectors.Doc2VecKeyedVectors.similarity`, etc., but not train and infer_vector. """ if getattr(self, 'vectors_docs_norm', None) is None or replace: @@ -1446,28 +1588,23 @@ def init_sims(self, replace=False): self.vectors_docs, sqrt((self.vectors_docs ** 2).sum(-1))[..., newaxis], self.vectors_docs_norm) def most_similar(self, positive=None, negative=None, topn=10, clip_start=0, clip_end=None, indexer=None): - """ - Find the top-N most similar docvecs known from training. Positive docs contribute - positively towards the similarity, negative docs negatively. + """Find the top-N most similar docvecs from the training set. + Positive docvecs contribute positively towards the similarity, negative docvecs negatively. This method computes cosine similarity between a simple mean of the projection weight vectors of the given docs. Docs may be specified as vectors, integer indexes of trained docvecs, or if the documents were originally presented with string tags, by the corresponding tags. - The 'clip_start' and 'clip_end' allow limiting results to a particular contiguous - range of the underlying `vectors_docs_norm` vectors. (This may be useful if the ordering - there was chosen to be significant, such as more popular tag IDs in lower indexes.) + TODO: Accept vectors of out-of-training-set docs, as if from inference. Parameters ---------- - positive : :obj: `list` - List of Docs specifed as vectors, integer indexes of trained docvecs or string tags - that contribute positively. - negative : :obj: `list` - List of Docs specifed as vectors, integer indexes of trained docvecs or string tags - that contribute negatively. - topn : int + positive : list of {str, int}, optional + List of doctags/indexes that contribute positively. + negative : list of {str, int}, optional + List of doctags/indexes that contribute negatively. + topn : int, optional Number of top-N similar docvecs to return. clip_start : int Start clipping index. @@ -1476,8 +1613,8 @@ def most_similar(self, positive=None, negative=None, topn=10, clip_start=0, clip Returns ------- - :obj: `list` of :obj: `tuple` - Returns a list of tuples (doc, similarity) + list of ({str, int}, float) + Sequence of (doctag/index, similarity). """ if positive is None: @@ -1532,20 +1669,19 @@ def most_similar(self, positive=None, negative=None, topn=10, clip_start=0, clip return result[:topn] def doesnt_match(self, docs): - """ - Which doc from the given list doesn't go with the others? + """Which document from the given list doesn't go with the others from the training set? - (TODO: Accept vectors of out-of-training-set docs, as if from inference.) + TODO: Accept vectors of out-of-training-set docs, as if from inference. Parameters ---------- - docs : :obj: `list` of (str or int) - List of seen documents specified by their corresponding string tags or integer indices. + docs : list of {str, int} + Sequence of doctags/indexes. Returns ------- - str or int - The document further away from the mean of all the documents. + {str, int} + Doctag/index of the document farthest away from the mean of all the documents. """ self.init_sims() @@ -1561,16 +1697,16 @@ def doesnt_match(self, docs): return sorted(zip(dists, docs))[0][1] def similarity(self, d1, d2): - """ - Compute cosine similarity between two docvecs in the trained set, specified by int index or - string tag. (TODO: Accept vectors of out-of-training-set docs, as if from inference.) + """Compute cosine similarity between two docvecs from the training set. + + TODO: Accept vectors of out-of-training-set docs, as if from inference. Parameters ---------- - d1 : int or str - Indicate the first document by it's string tag or integer index. - d2 : int or str - Indicate the second document by it's string tag or integer index. + d1 : {int, str} + Doctag/index of document. + d2 : {int, str} + Doctag/index of document. Returns ------- @@ -1581,16 +1717,16 @@ def similarity(self, d1, d2): return dot(matutils.unitvec(self[d1]), matutils.unitvec(self[d2])) def n_similarity(self, ds1, ds2): - """ - Compute cosine similarity between two sets of docvecs from the trained set, specified by int - index or string tag. (TODO: Accept vectors of out-of-training-set docs, as if from inference.) + """Compute cosine similarity between two sets of docvecs from the trained set. + + TODO: Accept vectors of out-of-training-set docs, as if from inference. Parameters ---------- - ds1 : :obj: `list` of (str or int) - Specify the first set of documents as a list of their integer indices or string tags. - ds2 : :obj: `list` of (str or int) - Specify the second set of documents as a list of their integer indices or string tags. + ds1 : list of {str, int} + Set of document as sequence of doctags/indexes. + ds2 : list of {str, int} + Set of document as sequence of doctags/indexes. Returns ------- @@ -1611,8 +1747,23 @@ def distance(self, d1, d2): # required by base keyed vectors class def distances(self, d1, other_docs=()): - """Compute distances from given document (string tag or int index) to all documents in `other_docs`. - If `other_docs` is empty, return distance between `d1` and all documents seen during training. + """Compute cosine distances from given `d1` to all documents in `other_docs`. + + TODO: Accept vectors of out-of-training-set docs, as if from inference. + + Parameters + ---------- + d1 : {str, numpy.ndarray} + Doctag/index of document. + other_docs : iterable of {str, int} + Sequence of doctags/indexes. + If None or empty, distance of `d1` from all doctags in vocab is computed (including itself). + + Returns + ------- + numpy.array + Array containing distances to all documents in `other_docs` from input `d1`. + """ input_vector = self[d1] if not other_docs: @@ -1622,28 +1773,27 @@ def distances(self, d1, other_docs=()): return 1 - WordEmbeddingsKeyedVectors.cosine_similarities(input_vector, other_vectors) def similarity_unseen_docs(self, model, doc_words1, doc_words2, alpha=0.1, min_alpha=0.0001, steps=5): - """ - Compute cosine similarity between two post-bulk out of training documents. + """Compute cosine similarity between two post-bulk out of training documents. Parameters ---------- - model : :obj: `~gensim.models.doc2vec.Doc2Vec` + model : :class:`~gensim.models.doc2vec.Doc2Vec` An instance of a trained `Doc2Vec` model. - doc_words1 : :obj: `list` of :obj: `str` - The first document. Document should be a list of (word) tokens. - doc_words2 : :obj: `list` of :obj: `str` - The second document. Document should be a list of (word) tokens. - alpha : float + doc_words1 : list of str + Input document. + doc_words2 : list of str + Input document. + alpha : float, optional The initial learning rate. - min_alpha : float + min_alpha : float, optional Learning rate will linearly drop to `min_alpha` as training progresses. - steps : int - Number of times to train the new document. + steps : int, optional + Number of epoch to train the new document. Returns ------- float - The cosine similarity between the unseen documents. + The cosine similarity between `doc_words1` and `doc_words2`. """ d1 = model.infer_vector(doc_words=doc_words1, alpha=alpha, min_alpha=min_alpha, steps=steps) @@ -1659,17 +1809,17 @@ def save_word2vec_format(self, fname, prefix='*dt_', fvocab=None, ---------- fname : str The file path used to save the vectors in. - prefix : str + prefix : str, optional Uniquely identifies doctags from word vocab, and avoids collision in case of repeated string in doctag and word vocab. - fvocab : str - Optional file path used to save the vocabulary - binary : bool - If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. - total_vec : int - Optional parameter to explicitly specify total no. of vectors + fvocab : str, optional + UNUSED. + total_vec : int, optional + Explicitly specify total no. of vectors (in case word vectors are appended with document vectors afterwards) - write_first_line : bool + binary : bool, optional + If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. + write_first_line : bool, optional Whether to print the first line in the file. Useful when saving doc-vectors after word-vectors. """ @@ -1689,7 +1839,7 @@ def save_word2vec_format(self, fname, prefix='*dt_', fvocab=None, @staticmethod def _int_index(index, doctags, max_rawint): - """Return int index for either string or int index""" + """Get int index for either string or int index.""" if isinstance(index, integer_types + (integer,)): return index else: @@ -1697,7 +1847,7 @@ def _int_index(index, doctags, max_rawint): @staticmethod def _index_to_doctag(i_index, offset2doctag, max_rawint): - """Return string key for given i_index, if available. Otherwise return raw int doctag (same int).""" + """Get string key for given `i_index`, if available. Otherwise return raw int doctag (same int).""" candidate_offset = i_index - max_rawint - 1 if 0 <= candidate_offset < len(offset2doctag): return offset2doctag[candidate_offset] @@ -1706,7 +1856,7 @@ def _index_to_doctag(i_index, offset2doctag, max_rawint): # for backward compatibility def index_to_doctag(self, i_index): - """Return string key for given i_index, if available. Otherwise return raw int doctag (same int).""" + """Get string key for given `i_index`, if available. Otherwise return raw int doctag (same int).""" candidate_offset = i_index - self.max_rawint - 1 if 0 <= candidate_offset < len(self.offset2doctag): return self.offset2doctag[candidate_offset] @@ -1715,7 +1865,7 @@ def index_to_doctag(self, i_index): # for backward compatibility def int_index(self, index, doctags, max_rawint): - """Return int index for either string or int index""" + """Get int index for either string or int index""" if isinstance(index, integer_types + (integer,)): return index else: @@ -1723,11 +1873,7 @@ def int_index(self, index, doctags, max_rawint): class FastTextKeyedVectors(WordEmbeddingsKeyedVectors): - """ - Class to contain vectors and vocab for the FastText training class and other methods not directly - involved in training such as most_similar() - """ - + """Vectors and vocab for :class:`~gensim.models.fasttext.FastText`.""" def __init__(self, vector_size, min_n, max_n): super(FastTextKeyedVectors, self).__init__(vector_size=vector_size) self.vectors_vocab = None @@ -1761,9 +1907,19 @@ def syn0_ngrams_norm(self): return self.vectors_ngrams_norm def __contains__(self, word): - """ - Check if `word` or any character ngrams in `word` are present in the vocabulary. - A vector for the word is guaranteed to exist if `__contains__` returns True. + """Check if `word` or any character ngrams in `word` are present in the vocabulary. + A vector for the word is guaranteed to exist if current method returns True. + + Parameters + ---------- + word : str + Input word. + + Returns + ------- + bool + True if `word` or any character ngrams in `word` are present in the vocabulary, False otherwise. + """ if word in self.vocab: return True @@ -1772,14 +1928,17 @@ def __contains__(self, word): return any(_ft_hash(ng) % self.bucket in self.hash2index for ng in char_ngrams) def save(self, *args, **kwargs): - """Saves the keyedvectors. This saved model can be loaded again using - :func:`~gensim.models.fasttext.FastTextKeyedVectors.load` which supports - getting vectors for out-of-vocabulary words. + """Save object. Parameters ---------- fname : str - Path to the file. + Path to the output file. + + See Also + -------- + :meth:`~gensim.models.keyedvectors.FastTextKeyedVectors.load` + Load object. """ # don't bother storing the cached normalized vectors @@ -1788,11 +1947,24 @@ def save(self, *args, **kwargs): super(FastTextKeyedVectors, self).save(*args, **kwargs) def word_vec(self, word, use_norm=False): - """ - Accept a single word as input. - Returns the word's representations in vector space, as a 1D numpy array. + """Get `word` representations in vector space, as a 1D numpy array. - If `use_norm` is True, returns the normalized word vector. + Parameters + ---------- + word : str + Input word + use_norm : bool, optional + If True - resulting vector will be L2-normalized (unit euclidean length). + + Returns + ------- + numpy.ndarray + Vector representation of `word`. + + Raises + ------ + KeyError + If word and all ngrams not in vocabulary. """ if word in self.vocab: @@ -1817,14 +1989,19 @@ def word_vec(self, word, use_norm=False): raise KeyError('all ngrams for word %s absent from model' % word) def init_sims(self, replace=False): - """ - Precompute L2-normalized vectors. + """Precompute L2-normalized vectors. - If `replace` is set, forget the original vectors and only keep the normalized - ones = saves lots of memory! + Parameters + ---------- + replace : bool, optional + If True - forget the original vectors and only keep the normalized ones = saves lots of memory! - Note that you **cannot continue training** after doing a replace. The model becomes - effectively read-only = you can only call `most_similar`, `similarity` etc. + Warnings + -------- + You **cannot continue training** after doing a replace. + The model becomes effectively read-only: you can call + :meth:`~gensim.models.keyedvectors.FastTextKeyedVectors.most_similar`, + :meth:`~gensim.models.keyedvectors.FastTextKeyedVectors.similarity`, etc., but not train. """ super(FastTextKeyedVectors, self).init_sims(replace) @@ -1845,12 +2022,12 @@ def save_word2vec_format(self, fname, fvocab=None, binary=False, total_vec=None) Parameters ---------- fname : str - The file path used to save the vectors in. - fvocab : str - Optional file path used to save the vocabulary. - binary : bool + The file path used to save the vectors in + fvocab : str, optional + Optional file path used to save the vocabulary + binary : bool, optional If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. - total_vec : int + total_vec : int, optional Optional parameter to explicitly specify total no. of vectors (in case word vectors are appended with document vectors afterwards). diff --git a/gensim/models/poincare.py b/gensim/models/poincare.py index cb9bce4aba..b753ce944a 100644 --- a/gensim/models/poincare.py +++ b/gensim/models/poincare.py @@ -5,30 +5,31 @@ # Copyright (C) 2017 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html +"""Python implementation of Poincaré Embeddings. -"""Python implementation of Poincaré Embeddings [1]_, an embedding that is better at capturing latent hierarchical -information than traditional Euclidean embeddings. The method is described in more detail in [1]_. +These embeddings are better at capturing latent hierarchical information than traditional Euclidean embeddings. +The method is described in detail in `Maximilian Nickel, Douwe Kiela - +"Poincaré Embeddings for Learning Hierarchical Representations" `_. The main use-case is to automatically learn hierarchical representations of nodes from a tree-like structure, -such as a Directed Acyclic Graph, using a transitive closure of the relations. Representations of nodes in a -symmetric graph can also be learned, using an iterable of the direct relations in the graph. +such as a Directed Acyclic Graph (DAG), using a transitive closure of the relations. Representations of nodes in a +symmetric graph can also be learned. -This module allows training a Poincaré Embedding from a training file containing relations of graph in a -csv-like format, or a Python iterable of relations. +This module allows training Poincaré Embeddings from a training file containing relations of graph in a +csv-like format, or from a Python iterable of relations. -.. [1] Maximilian Nickel, Douwe Kiela - "Poincaré Embeddings for Learning Hierarchical Representations" - https://arxiv.org/abs/1705.08039 Examples -------- -Initialize and train a model from a list: + +Initialize and train a model from a list >>> from gensim.models.poincare import PoincareModel >>> relations = [('kangaroo', 'marsupial'), ('kangaroo', 'mammal'), ('gib', 'cat')] >>> model = PoincareModel(relations, negative=2) >>> model.train(epochs=50) -Initialize and train a model from a file containing one relation per line: +Initialize and train a model from a file containing one relation per line >>> from gensim.models.poincare import PoincareModel, PoincareRelations >>> from gensim.test.utils import datapath @@ -38,7 +39,6 @@ """ - import csv import logging import sys @@ -67,16 +67,27 @@ class PoincareModel(utils.SaveLoad): - """Class for training, using and evaluating Poincare Embeddings. + """Train, use and evaluate Poincare Embeddings. The model can be stored/loaded via its :meth:`~gensim.models.poincare.PoincareModel.save` and :meth:`~gensim.models.poincare.PoincareModel.load` methods, or stored/loaded in the word2vec format via `model.kv.save_word2vec_format` and :meth:`~gensim.models.poincare.PoincareKeyedVectors.load_word2vec_format`. - Note that training cannot be resumed from a model loaded via `load_word2vec_format`, if you wish to train further, + Notes + ----- + Training cannot be resumed from a model loaded via `load_word2vec_format`, if you wish to train further, use :meth:`~gensim.models.poincare.PoincareModel.save` and :meth:`~gensim.models.poincare.PoincareModel.load` methods instead. + An important attribute (that provides a lot of additional functionality when directly accessed) are the + keyed vectors: + + self.kv : :class:`~gensim.models.poincare.PoincareKeyedVectors` + This object essentially contains the mapping between nodes and embeddings, as well the vocabulary of the model + (set of unique nodes seen by the model). After training, it can be used to perform operations on the vectors + such as vector lookup, distance and similarity calculations etc. + See the documentation of its class for usage examples. + """ def __init__(self, train_data, size=50, alpha=0.1, negative=10, workers=1, epsilon=1e-5, regularization_coeff=1.0, burn_in=10, burn_in_alpha=0.01, init_range=(-0.001, 0.001), dtype=np.float64, seed=0): @@ -84,11 +95,11 @@ def __init__(self, train_data, size=50, alpha=0.1, negative=10, workers=1, epsil Parameters ---------- - train_data : iterable of (str, str) - Iterable of relations, e.g. a list of tuples, or a PoincareRelations instance streaming from a file. - Note that the relations are treated as ordered pairs, i.e. a relation (a, b) does not imply the - opposite relation (b, a). In case the relations are symmetric, the data should contain both relations - (a, b) and (b, a). + train_data : {iterable of (str, str), :class:`gensim.models.poincare.PoincareRelations`} + Iterable of relations, e.g. a list of tuples, or a :class:`gensim.models.poincare.PoincareRelations` + instance streaming from a file. Note that the relations are treated as ordered pairs, + i.e. a relation (a, b) does not imply the opposite relation (b, a). In case the relations are symmetric, + the data should contain both relations (a, b) and (b, a). size : int, optional Number of dimensions of the trained model. alpha : float, optional @@ -158,7 +169,7 @@ def _load_relations(self): all_relations = [] # List of all relation pairs node_relations = defaultdict(set) # Mapping from node index to its related node indices - logger.info("Loading relations from train data..") + logger.info("loading relations from train data..") for relation in self.train_data: if len(relation) != 2: raise ValueError('Relation pair "%s" should have exactly two items' % repr(relation)) @@ -173,7 +184,7 @@ def _load_relations(self): node_relations[node_1_index].add(node_2_index) relation = (node_1_index, node_2_index) all_relations.append(relation) - logger.info("Loaded %d relations from train data, %d nodes", len(all_relations), len(vocab)) + logger.info("loaded %d relations from train data, %d nodes", len(all_relations), len(vocab)) self.kv.vocab = vocab self.kv.index2word = index2word self.indices_set = set((range(len(index2word)))) # Set of all node indices @@ -190,6 +201,7 @@ def _init_embeddings(self): self.kv.syn0 = self._np_random.uniform(self.init_range[0], self.init_range[1], shape).astype(self.dtype) def _init_node_probabilities(self): + """Initialize a-priori probabilities.""" counts = np.array([ self.kv.vocab[self.kv.index2word[i]].count for i in range(len(self.kv.index2word)) @@ -199,7 +211,7 @@ def _init_node_probabilities(self): self._node_probabilities = counts / counts.sum() def _get_candidate_negatives(self): - """Returns candidate negatives of size `self.negative` from the negative examples buffer. + """Get candidate negatives of size `self.negative` from the negative examples buffer. Returns ------- @@ -207,7 +219,6 @@ def _get_candidate_negatives(self): Array of shape (`self.negative`,) containing indices of negative nodes. """ - if self._negatives_buffer.num_items() < self.negative: # cumsum table of counts used instead of the standard approach of a probability cumsum table # this is to avoid floating point errors that result when the number of nodes is very high @@ -219,7 +230,7 @@ def _get_candidate_negatives(self): return self._negatives_buffer.get_items(self.negative) def _sample_negatives(self, node_index): - """Return a sample of negatives for the given node. + """Get a sample of negatives for the given node. Parameters ---------- @@ -252,7 +263,7 @@ def _sample_negatives(self, node_index): indices = self._get_candidate_negatives() unique_indices = set(indices) if times_sampled > 1: - logger.debug('Sampled %d times, positive fraction %.5f', times_sampled, positive_fraction) + logger.debug('sampled %d times, positive fraction %.5f', times_sampled, positive_fraction) else: # If number of positive relations is a significant fraction of total nodes # subtract positively connected nodes from set of choices and sample from the remaining @@ -265,13 +276,13 @@ def _sample_negatives(self, node_index): @staticmethod def _loss_fn(matrix, regularization_coeff=1.0): - """Given a numpy array with vectors for u, v and negative samples, computes loss value. + """Computes loss value. Parameters ---------- matrix : numpy.array Array containing vectors for u, v and negative samples, of shape (2 + negative_size, dim). - regularization_coeff : float + regularization_coeff : float, optional Coefficient to use for l2-regularization Returns @@ -305,7 +316,7 @@ def _clip_vectors(vectors, epsilon): Parameters ---------- vectors : numpy.array - Can be 1-D,or 2-D (in which case the norm for each row is checked). + Can be 1-D, or 2-D (in which case the norm for each row is checked). epsilon : float Parameter for numerical stability, each dimension of the vector is reduced by `epsilon` if the norm of the vector is greater than or equal to 1. @@ -334,7 +345,20 @@ def _clip_vectors(vectors, epsilon): return vectors def save(self, *args, **kwargs): - """Save complete model to disk, inherited from :class:`gensim.utils.SaveLoad`.""" + """Save complete model to disk, inherited from :class:`~gensim.utils.SaveLoad`. + + See also + -------- + :meth:`~gensim.models.poincare.PoincareModel.load` + + Parameters + ---------- + *args + Positional arguments passed to :meth:`~gensim.utils.SaveLoad.save`. + **kwargs + Keyword arguments passed to :meth:`~gensim.utils.SaveLoad.save`. + + """ self._loss_grad = None # Can't pickle autograd fn to disk attrs_to_ignore = ['_node_probabilities', '_node_counts_cumsum'] kwargs['ignore'] = set(list(kwargs.get('ignore', [])) + attrs_to_ignore) @@ -342,17 +366,34 @@ def save(self, *args, **kwargs): @classmethod def load(cls, *args, **kwargs): - """Load model from disk, inherited from :class:`~gensim.utils.SaveLoad`.""" + """Load model from disk, inherited from :class:`~gensim.utils.SaveLoad`. + + See also + -------- + :meth:`~gensim.models.poincare.PoincareModel.save` + + Parameters + ---------- + *args + Positional arguments passed to :meth:`~gensim.utils.SaveLoad.load`. + **kwargs + Keyword arguments passed to :meth:`~gensim.utils.SaveLoad.load`. + + Returns + ------- + :class:`~gensim.models.poincare.PoincareModel` + The loaded model. + + """ model = super(PoincareModel, cls).load(*args, **kwargs) model._init_node_probabilities() return model def _prepare_training_batch(self, relations, all_negatives, check_gradients=False): - """Creates training batch and computes gradients and loss for the batch. + """Create a training batch and compute gradients and loss for the batch. Parameters ---------- - relations : list of tuples List of tuples of positive examples of the form (node_1_index, node_2_index). all_negatives : list of lists @@ -363,7 +404,7 @@ def _prepare_training_batch(self, relations, all_negatives, check_gradients=Fals Returns ------- :class:`~gensim.models.poincare.PoincareBatch` - Contains node indices, computed gradients and loss for the batch. + Node indices, computed gradients and loss for the batch. """ batch_size = len(relations) @@ -390,12 +431,14 @@ def _check_gradients(self, relations, all_negatives, batch, tol=1e-8): Parameters ---------- - batch : PoincareBatch instance - Batch for which computed gradients are to checked. relations : list of tuples List of tuples of positive examples of the form (node_1_index, node_2_index). all_negatives : list of lists List of lists of negative samples for each node_1 in the positive examples. + batch : :class:`~gensim.models.poincare.PoincareBatch` + Batch for which computed gradients are to be checked. + tol : float, optional + The maximum error between our computed gradients and the reference ones from autograd. """ if not AUTOGRAD_PRESENT: @@ -415,34 +458,34 @@ def _check_gradients(self, relations, all_negatives, batch, tol=1e-8): diff = np.abs(auto_gradients - computed_gradients).max() if diff > max_diff: max_diff = diff - logger.info('Max difference between computed gradients and autograd gradients: %.10f', max_diff) + logger.info('max difference between computed gradients and autograd gradients: %.10f', max_diff) assert max_diff < tol, ( - 'Max difference between computed gradients and autograd gradients %.10f, ' - 'greater than tolerance %.10f' % (max_diff, tol)) + 'Max difference between computed gradients and autograd gradients %.10f, ' + 'greater than tolerance %.10f' % (max_diff, tol)) def _sample_negatives_batch(self, nodes): - """Return negative examples for each node in the given nodes. + """Get negative examples for each node. Parameters ---------- - nodes : list + nodes : list of int List of node indices for which negative samples are to be returned. Returns ------- list of lists - Each inner list is a list of negative sample for a single node in the input list. + Each inner list is a list of negative samples for a single node in the input list. """ all_indices = [self._sample_negatives(node) for node in nodes] return all_indices def _train_on_batch(self, relations, check_gradients=False): - """Performs training for a single training batch. + """Perform training for a single training batch. Parameters ---------- - relations : list of tuples + relations : list of tuples of (int, int) List of tuples of positive examples of the form (node_1_index, node_2_index). check_gradients : bool, optional Whether to compare the computed gradients to autograd gradients for this batch. @@ -460,13 +503,13 @@ def _train_on_batch(self, relations, check_gradients=False): @staticmethod def _handle_duplicates(vector_updates, node_indices): - """Handles occurrences of multiple updates to the same node in a batch of vector updates. + """Handle occurrences of multiple updates to the same node in a batch of vector updates. Parameters ---------- vector_updates : numpy.array Array with each row containing updates to be performed on a certain node. - node_indices : list + node_indices : list of int Node indices on which the above updates are to be performed on. Notes @@ -487,7 +530,7 @@ def _handle_duplicates(vector_updates, node_indices): vector_updates[positions[:-1]] = 0 def _update_vectors_batch(self, batch): - """Updates vectors for nodes in the given batch. + """Update vectors for nodes in the given batch. Parameters ---------- @@ -514,15 +557,15 @@ def _update_vectors_batch(self, batch): self.kv.syn0[indices_v] = self._clip_vectors(self.kv.syn0[indices_v], self.epsilon) def train(self, epochs, batch_size=10, print_every=1000, check_gradients_every=None): - """Trains Poincare embeddings using loaded data and model parameters. + """Train Poincare embeddings using loaded data and model parameters. Parameters ---------- - - batch_size : int, optional - Number of examples to train on in a single batch. epochs : int Number of iterations (epochs) over the corpus. + batch_size : int, optional + Number of examples to train on in a single batch. + print_every : int, optional Prints progress and average loss after every `print_every` batches. check_gradients_every : int or None, optional @@ -550,25 +593,25 @@ def train(self, epochs, batch_size=10, print_every=1000, check_gradients_every=N ) if self.burn_in > 0 and not self._burn_in_done: - logger.info("Starting burn-in (%d epochs)----------------------------------------", self.burn_in) + logger.info("starting burn-in (%d epochs)----------------------------------------", self.burn_in) self.alpha = self.burn_in_alpha self._train_batchwise( epochs=self.burn_in, batch_size=batch_size, print_every=print_every, check_gradients_every=check_gradients_every) self._burn_in_done = True - logger.info("Burn-in finished") + logger.info("burn-in finished") self.alpha = self.train_alpha - logger.info("Starting training (%d epochs)----------------------------------------", epochs) + logger.info("starting training (%d epochs)----------------------------------------", epochs) self._train_batchwise( epochs=epochs, batch_size=batch_size, print_every=print_every, check_gradients_every=check_gradients_every) - logger.info("Training finished") + logger.info("training finished") np.seterr(**old_settings) def _train_batchwise(self, epochs, batch_size=10, print_every=1000, check_gradients_every=None): - """Trains Poincare embeddings using specified parameters. + """Train Poincare embeddings using specified parameters. Parameters ---------- @@ -602,10 +645,10 @@ def _train_batchwise(self, epochs, batch_size=10, print_every=1000, check_gradie time_taken = time.time() - last_time speed = print_every * batch_size / time_taken logger.info( - 'Training on epoch %d, examples #%d-#%d, loss: %.2f' + 'training on epoch %d, examples #%d-#%d, loss: %.2f' % (epoch, i, i + batch_size, avg_loss)) logger.info( - 'Time taken for %d examples: %.2f s, %.2f examples / s' + 'time taken for %d examples: %.2f s, %.2f examples / s' % (print_every * batch_size, time_taken, speed)) last_time = time.time() avg_loss = 0.0 @@ -614,8 +657,7 @@ def _train_batchwise(self, epochs, batch_size=10, print_every=1000, check_gradie class PoincareBatch(object): """Compute Poincare distances, gradients and loss for a training batch. - Class for computing Poincare distances, gradients and loss for a training batch, - and storing intermediate state to avoid recomputing multiple times. + Store intermediate state to avoid recomputing multiple times. """ def __init__(self, vectors_u, vectors_v, indices_u, indices_v, regularization_coeff=1.0): @@ -625,18 +667,16 @@ def __init__(self, vectors_u, vectors_v, indices_u, indices_v, regularization_co Parameters ---------- vectors_u : numpy.array - Vectors of all nodes `u` in the batch. - Expected shape (batch_size, dim). + Vectors of all nodes `u` in the batch. Expected shape (batch_size, dim). vectors_v : numpy.array Vectors of all positively related nodes `v` and negatively sampled nodes `v'`, - for each node `u` in the batch. - Expected shape (1 + neg_size, dim, batch_size). - indices_u : list + for each node `u` in the batch. Expected shape (1 + neg_size, dim, batch_size). + indices_u : list of int List of node indices for each of the vectors in `vectors_u`. - indices_v : list + indices_v : list of lists of int Nested list of lists, each of which is a list of node indices for each of the vectors in `vectors_v` for a specific node `u`. - regularization_coeff : float + regularization_coeff : float, optional Coefficient to use for l2-regularization """ @@ -770,12 +810,11 @@ def compute_loss(self): class PoincareKeyedVectors(BaseKeyedVectors): - """Class to contain vectors and vocab for the :class:`~gensim.models.poincare.PoincareModel` training class. + """Vectors and vocab for the :class:`~gensim.models.poincare.PoincareModel` training class. - Used to perform operations on the vectors such as vector lookup, distance etc. + Used to perform operations on the vectors such as vector lookup, distance calculations etc. """ - def __init__(self, vector_size): super(PoincareKeyedVectors, self).__init__(vector_size) self.max_distance = 0 @@ -798,21 +837,26 @@ def index2entity(self, value): self.index2word = value def word_vec(self, word): - """ - Accept a single word as input. - Returns the word's representations in vector space, as a 1D numpy array. + """Get the word's representations in vector space, as a 1D numpy array. - Example:: + Examples + -------- - >>> trained_model.word_vec('office') - array([ -1.40128313e-02, ...]) + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # Query the trained model. + >>> wv = model.kv.word_vec('kangaroo.n.01') """ return super(PoincareKeyedVectors, self).get_vector(word) def words_closer_than(self, w1, w2): - """ - Returns all words that are closer to `w1` than `w2` is to `w1`. + """Get all words that are closer to `w1` than `w2` is to `w1`. Parameters ---------- @@ -828,24 +872,35 @@ def words_closer_than(self, w1, w2): Examples -------- - - >>> model.words_closer_than('carnivore.n.01', 'mammal.n.01') - ['dog.n.01', 'canine.n.02'] + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # Which term is closer to 'kangaroo' than 'metatherian' is to 'kangaroo'? + >>> model.kv.words_closer_than('kangaroo.n.01', 'metatherian.n.01') + [u'marsupial.n.01', u'phalanger.n.01'] """ return super(PoincareKeyedVectors, self).closer_than(w1, w2) def save_word2vec_format(self, fname, fvocab=None, binary=False, total_vec=None): - """ - Store the input-hidden weight matrix in the same format used by the original - C word2vec-tool, for compatibility. + """Store the input-hidden weight matrix in the same format used by the original + C word2vec-tool, for compatibility, using :func:`~gensim.models.utils_any2vec._save_word2vec_format`. - `fname` is the file used to save the vectors in - `fvocab` is an optional file used to save the vocabulary - `binary` is an optional boolean indicating whether the data is to be saved - in binary word2vec format (default: False) - `total_vec` is an optional parameter to explicitly specify total no. of vectors - (in case word vectors are appended with document vectors afterwards) + Parameters + ---------- + fname : str + Path to file that will be used for storing. + fvocab : str, optional + File path used to save the vocabulary. + binary : bool, optional + If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. + total_vec : int, optional + Explicitly specify total number of vectors + (in case word vectors are appended with document vectors afterwards). """ _save_word2vec_format(fname, self.vocab, self.syn0, fvocab=fvocab, binary=binary, total_vec=total_vec) @@ -853,32 +908,40 @@ def save_word2vec_format(self, fname, fvocab=None, binary=False, total_vec=None) @classmethod def load_word2vec_format(cls, fname, fvocab=None, binary=False, encoding='utf8', unicode_errors='strict', limit=None, datatype=REAL): - """ - Load the input-hidden weight matrix from the original C word2vec-tool format. + """Load the input-hidden weight matrix from the original C word2vec-tool format. + Use :func:`~gensim.models.utils_any2vec._load_word2vec_format`. Note that the information stored in the file is incomplete (the binary tree is missing), so while you can query for word similarity etc., you cannot continue training with a model loaded this way. - `binary` is a boolean indicating whether the data is in binary word2vec format. - `norm_only` is a boolean indicating whether to only store normalised word2vec vectors in memory. - Word counts are read from `fvocab` filename, if set (this is the file generated - by `-save-vocab` flag of the original C tool). - - If you trained the C model using non-utf8 encoding for words, specify that - encoding in `encoding`. - - `unicode_errors`, default 'strict', is a string suitable to be passed as the `errors` - argument to the unicode() (Python 2.x) or str() (Python 3.x) function. If your source - file may include word tokens truncated in the middle of a multibyte unicode character - (as is common from the original word2vec.c tool), 'ignore' or 'replace' may help. - - `limit` sets a maximum number of word-vectors to read from the file. The default, - None, means read all. + Parameters + ---------- + fname : str + The file path to the saved word2vec-format file. + fvocab : str, optional + File path to the vocabulary.Word counts are read from `fvocab` filename, if set + (this is the file generated by `-save-vocab` flag of the original C tool). + binary : bool, optional + If True, indicates whether the data is in binary word2vec format. + encoding : str, optional + If you trained the C model using non-utf8 encoding for words, specify that encoding in `encoding`. + unicode_errors : str, optional + default 'strict', is a string suitable to be passed as the `errors` + argument to the unicode() (Python 2.x) or str() (Python 3.x) function. If your source + file may include word tokens truncated in the middle of a multibyte unicode character + (as is common from the original word2vec.c tool), 'ignore' or 'replace' may help. + limit : int, optional + Sets a maximum number of word-vectors to read from the file. The default, + None, means read all. + datatype : type, optional + (Experimental) Can coerce dimensions to a non-default float type (such as `np.float16`) to save memory. + Such types may result in much slower bulk operations or incompatibility with optimized routines.) - `datatype` (experimental) can coerce dimensions to a non-default float type (such - as np.float16) to save memory. (Such types may result in much slower bulk operations - or incompatibility with optimized routines.) + Returns + ------- + :class:`~gensim.models.poincare.PoincareModel` + Loaded Poincare model. """ return _load_word2vec_format( @@ -887,15 +950,14 @@ def load_word2vec_format(cls, fname, fvocab=None, binary=False, encoding='utf8', @staticmethod def vector_distance(vector_1, vector_2): - """ - Return poincare distance between two input vectors. Convenience method over `vector_distance_batch`. + """Compute poincare distance between two input vectors. Convenience method over `vector_distance_batch`. Parameters ---------- vector_1 : numpy.array - input vector + Input vector. vector_2 : numpy.array - input vector + Input vector. Returns ------- @@ -907,23 +969,19 @@ def vector_distance(vector_1, vector_2): @staticmethod def vector_distance_batch(vector_1, vectors_all): - """ - Return poincare distances between one vector and a set of other vectors. + """Compute poincare distances between one vector and a set of other vectors. Parameters ---------- vector_1 : numpy.array - vector from which Poincare distances are to be computed. - expected shape (dim,) + vector from which Poincare distances are to be computed, expected shape (dim,). vectors_all : numpy.array - for each row in vectors_all, distance from vector_1 is computed. - expected shape (num_vectors, dim) + for each row in vectors_all, distance from vector_1 is computed, expected shape (num_vectors, dim). Returns ------- numpy.array - Contains Poincare distance between vector_1 and each row in vectors_all. - shape (num_vectors,) + Poincare distance between `vector_1` and each row in `vectors_all`, shape (num_vectors,). """ euclidean_dists = np.linalg.norm(vector_1 - vectors_all, axis=1) @@ -936,17 +994,16 @@ def vector_distance_batch(vector_1, vectors_all): ) def closest_child(self, node): - """ - Returns the node closest to `node` that is lower in the hierarchy than `node`. + """Get the node closest to `node` that is lower in the hierarchy than `node`. Parameters ---------- - node : str or int + node : {str, int} Key for node for which closest child is to be found. Returns ------- - str or None + {str, None} Node closest to `node` that is lower in the hierarchy than `node`. If there are no nodes lower in the hierarchy, None is returned. @@ -962,17 +1019,16 @@ def closest_child(self, node): return self.index2word[closest_child_index] def closest_parent(self, node): - """ - Returns the node closest to `node` that is higher in the hierarchy than `node`. + """Get the node closest to `node` that is higher in the hierarchy than `node`. Parameters ---------- - node : str or int + node : {str, int} Key for node for which closest parent is to be found. Returns ------- - str or None + {str, None} Node closest to `node` that is higher in the hierarchy than `node`. If there are no nodes higher in the hierarchy, None is returned. @@ -988,19 +1044,18 @@ def closest_parent(self, node): return self.index2word[closest_child_index] def descendants(self, node, max_depth=5): - """ - Returns the list of recursively closest children from the given node, upto a max depth of `max_depth`. + """Get the list of recursively closest children from the given node, up to a max depth of `max_depth`. Parameters ---------- - node : str or int + node : {str, int} Key for node for which descendants are to be found. max_depth : int Maximum number of descendants to return. Returns ------- - list (str) + list of str Descendant nodes from the node `node`. """ @@ -1014,17 +1069,16 @@ def descendants(self, node, max_depth=5): return descendants def ancestors(self, node): - """ - Returns the list of recursively closest parents from the given node. + """Get the list of recursively closest parents from the given node. Parameters ---------- - node : str or int + node : {str, int} Key for node for which ancestors are to be found. Returns ------- - list (str) + list of str Ancestor nodes of the node `node`. """ @@ -1037,14 +1091,13 @@ def ancestors(self, node): return ancestors def distance(self, w1, w2): - """ - Return Poincare distance between vectors for nodes `w1` and `w2`. + """Calculate Poincare distance between vectors for nodes `w1` and `w2`. Parameters ---------- - w1 : str or int + w1 : {str, int} Key for first node. - w2 : str or int + w2 : {str, int} Key for second node. Returns @@ -1054,13 +1107,21 @@ def distance(self, w1, w2): Examples -------- + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # What is the distance between the words 'mammal' and 'carnivore'? + >>> model.kv.distance('mammal.n.01', 'carnivore.n.01') + 2.9742298803339304 - >>> model.distance('mammal.n.01', 'carnivore.n.01') - 2.13 - - Notes - ----- - Raises KeyError if either of `w1` and `w2` is absent from vocab. + Raises + ------ + KeyError + If either of `w1` and `w2` is absent from vocab. """ vector_1 = self.word_vec(w1) @@ -1068,14 +1129,13 @@ def distance(self, w1, w2): return self.vector_distance(vector_1, vector_2) def similarity(self, w1, w2): - """ - Return similarity based on Poincare distance between vectors for nodes `w1` and `w2`. + """Compute similarity based on Poincare distance between vectors for nodes `w1` and `w2`. Parameters ---------- - w1 : str or int + w1 : {str, int} Key for first node. - w2 : str or int + w2 : {str, int} Key for second node. Returns @@ -1085,26 +1145,31 @@ def similarity(self, w1, w2): Examples -------- + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # What is the similarity between the words 'mammal' and 'carnivore'? + >>> model.kv.similarity('mammal.n.01', 'carnivore.n.01') + 0.25162107631176484 - >>> model.similarity('mammal.n.01', 'carnivore.n.01') - 0.73 - - Notes - ----- - Raises KeyError if either of `w1` and `w2` is absent from vocab. - Similarity lies between 0 and 1. + Raises + ------ + KeyError + If either of `w1` and `w2` is absent from vocab. """ return 1 / (1 + self.distance(w1, w2)) def most_similar(self, node_or_vector, topn=10, restrict_vocab=None): - """ - Find the top-N most similar nodes to the given node or vector, sorted in increasing order of distance. + """Find the top-N most similar nodes to the given node or vector, sorted in increasing order of distance. Parameters ---------- - - node_or_vector : str/int or numpy.array + node_or_vector : {str, int, numpy.array} node key or vector for which similar nodes are to be found. topn : int or None, optional number of similar nodes to return, if `None`, returns all. @@ -1115,13 +1180,21 @@ def most_similar(self, node_or_vector, topn=10, restrict_vocab=None): Returns -------- - list of tuples (str, float) + list of (str, float) List of tuples containing (node, distance) pairs in increasing order of distance. Examples -------- - >>> vectors.most_similar('lion.n.01') - [('lion_cub.n.01', 0.4484), ('lionet.n.01', 0.6552), ...] + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # Which words are most similar to 'kangaroo'? + >>> model.kv.most_similar('kangaroo.n.01', topn=2) + [(u'kangaroo.n.01', 0.0), (u'marsupial.n.01', 0.26524229460827725)] """ if not restrict_vocab: @@ -1147,16 +1220,14 @@ def most_similar(self, node_or_vector, topn=10, restrict_vocab=None): return result def distances(self, node_or_vector, other_nodes=()): - """ - Compute Poincare distances from given node or vector to all nodes in `other_nodes`. + """Compute Poincare distances from given `node_or_vector` to all nodes in `other_nodes`. If `other_nodes` is empty, return distance between `node_or_vector` and all nodes in vocab. Parameters ---------- - node_or_vector : str/int or numpy.array + node_or_vector : {str, int, numpy.array} Node key or vector from which distances are to be computed. - - other_nodes : iterable of str/int or None + other_nodes : {iterable of str, iterable of int, None}, optional For each node in `other_nodes` distance from `node_or_vector` is computed. If None or empty, distance of `node_or_vector` from all nodes in vocab is computed (including itself). @@ -1168,16 +1239,24 @@ def distances(self, node_or_vector, other_nodes=()): Examples -------- + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # Check the distances between a word and a list of other words. + >>> model.kv.distances('mammal.n.01', ['carnivore.n.01', 'dog.n.01']) + array([2.97422988, 2.83007402]) - >>> model.distances('mammal.n.01', ['carnivore.n.01', 'dog.n.01']) - np.array([2.1199, 2.0710] + >>> # Check the distances between a word and every other word in the vocab. + >>> all_distances = model.kv.distances('mammal.n.01') - >>> model.distances('mammal.n.01') - np.array([0.43753847, 3.67973852, ..., 6.66172886]) - - Notes - ----- - Raises KeyError if either `node_or_vector` or any node in `other_nodes` is absent from vocab. + Raises + ------ + KeyError + If either `node_or_vector` or any node in `other_nodes` is absent from vocab. """ if isinstance(node_or_vector, string_types): @@ -1192,13 +1271,12 @@ def distances(self, node_or_vector, other_nodes=()): return self.vector_distance_batch(input_vector, other_vectors) def norm(self, node_or_vector): - """ - Return absolute position in hierarchy of input node or vector. + """Compute absolute position in hierarchy of input node or vector. Values range between 0 and 1. A lower value indicates the input node or vector is higher in the hierarchy. Parameters ---------- - node_or_vector : str/int or numpy.array + node_or_vector : {str, int, numpy.array} Input node key or vector for which position in hierarchy is to be returned. Returns @@ -1208,9 +1286,16 @@ def norm(self, node_or_vector): Examples -------- - - >>> model.norm('mammal.n.01') - 0.9 + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> # Get the norm of the embedding of the word `mammal`. + >>> model.kv.norm('mammal.n.01') + 0.6423008703542398 Notes ----- @@ -1224,16 +1309,14 @@ def norm(self, node_or_vector): return np.linalg.norm(input_vector) def difference_in_hierarchy(self, node_or_vector_1, node_or_vector_2): - """ - Relative position in hierarchy of `node_or_vector_1` relative to `node_or_vector_2`. + """Compute relative position in hierarchy of `node_or_vector_1` relative to `node_or_vector_2`. A positive value indicates `node_or_vector_1` is higher in the hierarchy than `node_or_vector_2`. Parameters ---------- - node_or_vector_1 : str/int or numpy.array + node_or_vector_1 : {str, int, numpy.array} Input node key or vector. - - node_or_vector_2 : str/int or numpy.array + node_or_vector_2 : {str, int, numpy.array} Input node key or vector. Returns @@ -1243,12 +1326,18 @@ def difference_in_hierarchy(self, node_or_vector_1, node_or_vector_2): Examples -------- + >>> from gensim.test.utils import datapath + >>> + >>> # Read the sample relations file and train the model + >>> relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv')) + >>> model = PoincareModel(train_data=relations) + >>> model.train(epochs=50) + >>> + >>> model.kv.difference_in_hierarchy('mammal.n.01', 'dog.n.01') + 0.05382517902410999 - >>> model.difference_in_hierarchy('mammal.n.01', 'dog.n.01') - 0.51 - - >>> model.difference_in_hierarchy('dog.n.01', 'mammal.n.01') - -0.51 + >>> model.kv.difference_in_hierarchy('dog.n.01', 'mammal.n.01') + -0.05382517902410999 Notes ----- @@ -1260,7 +1349,7 @@ def difference_in_hierarchy(self, node_or_vector_1, node_or_vector_2): class PoincareRelations(object): - """Class to stream relations for `PoincareModel` from a tsv-like file.""" + """Stream relations for `PoincareModel` from a tsv-like file.""" def __init__(self, file_path, encoding='utf8', delimiter='\t'): """Initialize instance from file containing a pair of nodes (a relation) per line. @@ -1281,11 +1370,11 @@ def __init__(self, file_path, encoding='utf8', delimiter='\t'): self.delimiter = delimiter def __iter__(self): - """Streams relations from self.file_path decoded into unicode strings. + """Stream relations from self.file_path decoded into unicode strings. Yields ------- - 2-tuple (unicode, unicode) + (unicode, unicode) Relation from input file. """ @@ -1303,7 +1392,7 @@ def __iter__(self): class NegativesBuffer(object): - """Class to buffer and return negative samples.""" + """Buffer and return negative samples.""" def __init__(self, items): """Initialize instance from list or numpy array of samples. @@ -1314,12 +1403,11 @@ def __init__(self, items): List or array containing negative samples. """ - self._items = items self._current_index = 0 def num_items(self): - """Returns number of items remaining in the buffer. + """Get the number of items remaining in the buffer. Returns ------- @@ -1330,7 +1418,7 @@ def num_items(self): return len(self._items) - self._current_index def get_items(self, num_items): - """Returns next `num_items` from buffer. + """Get the next `num_items` from buffer. Parameters ---------- @@ -1355,7 +1443,7 @@ def get_items(self, num_items): class ReconstructionEvaluation(object): - """Evaluating reconstruction on given network for given embedding.""" + """Evaluate reconstruction on given network for given embedding.""" def __init__(self, file_path, embedding): """Initialize evaluation instance with tsv file containing relation pairs and embedding to be evaluated. @@ -1364,7 +1452,7 @@ def __init__(self, file_path, embedding): ---------- file_path : str Path to tsv file containing relation pairs. - embedding : PoincareKeyedVectors instance + embedding : :class:`~gensim.models.poincare.PoincareKeyedVectors` Embedding to be evaluated. """ @@ -1385,23 +1473,20 @@ def __init__(self, file_path, embedding): @staticmethod def get_positive_relation_ranks_and_avg_prec(all_distances, positive_relations): - """ - Given a numpy array of all distances from an item and indices of its positive relations, - compute ranks and Average Precision of positive relations. + """Compute ranks and Average Precision of positive relations. Parameters ---------- - all_distances : numpy.array (float) + all_distances : numpy.array of float Array of all distances (floats) for a specific item. positive_relations : list List of indices of positive relations for the item. Returns ------- - tuple (list, float) - The list contains ranks (int) of positive relations in the same order as `positive_relations`. - The float is the Average Precision of the ranking. - e.g. ([1, 2, 3, 20], 0.610). + (list of int, float) + The list contains ranks of positive relations in the same order as `positive_relations`. + The float is the Average Precision of the ranking, e.g. ([1, 2, 3, 20], 0.610). """ positive_relation_distances = all_distances[positive_relations] @@ -1418,14 +1503,13 @@ def evaluate(self, max_n=None): Parameters ---------- - max_n : int or None + max_n : int, optional Maximum number of positive relations to evaluate, all if `max_n` is None. Returns ------- - dict - Contains (metric_name, metric_value) pairs. - e.g. {'mean_rank': 50.3, 'MAP': 0.31}. + dict of (str, float) + (metric_name, metric_value) pairs, e.g. {'mean_rank': 50.3, 'MAP': 0.31}. """ mean_rank, map_ = self.evaluate_mean_rank_and_map(max_n) @@ -1436,14 +1520,13 @@ def evaluate_mean_rank_and_map(self, max_n=None): Parameters ---------- - max_n : int or None + max_n : int, optional Maximum number of positive relations to evaluate, all if `max_n` is None. Returns ------- - tuple (float, float) - Contains (mean_rank, MAP). - e.g (50.3, 0.31) + (float, float) + (mean_rank, MAP), e.g (50.3, 0.31). """ ranks = [] @@ -1464,7 +1547,7 @@ def evaluate_mean_rank_and_map(self, max_n=None): class LinkPredictionEvaluation(object): - """Evaluating reconstruction on given network for given embedding.""" + """Evaluate reconstruction on given network for given embedding.""" def __init__(self, train_path, test_path, embedding): """Initialize evaluation instance with tsv file containing relation pairs and embedding to be evaluated. @@ -1475,7 +1558,7 @@ def __init__(self, train_path, test_path, embedding): Path to tsv file containing relation pairs used for training. test_path : str Path to tsv file containing relation pairs to evaluate. - embedding : PoincareKeyedVectors instance + embedding : :class:`~gensim.models.poincare.PoincareKeyedVectors` Embedding to be evaluated. """ @@ -1498,25 +1581,22 @@ def __init__(self, train_path, test_path, embedding): @staticmethod def get_unknown_relation_ranks_and_avg_prec(all_distances, unknown_relations, known_relations): - """ - Given a numpy array of distances and indices of known and unknown positive relations, - compute ranks and Average Precision of unknown positive relations. + """Compute ranks and Average Precision of unknown positive relations. Parameters ---------- - all_distances : numpy.array (float) + all_distances : numpy.array of float Array of all distances for a specific item. - unknown_relations : list + unknown_relations : list of int List of indices of unknown positive relations. - known_relations : list + known_relations : list of int List of indices of known positive relations. Returns ------- - tuple (list, float) - The list contains ranks (int) of positive relations in the same order as `positive_relations`. - The float is the Average Precision of the ranking. - e.g. ([1, 2, 3, 20], 0.610). + tuple (list of int, float) + The list contains ranks of positive relations in the same order as `positive_relations`. + The float is the Average Precision of the ranking, e.g. ([1, 2, 3, 20], 0.610). """ unknown_relation_distances = all_distances[unknown_relations] @@ -1534,14 +1614,13 @@ def evaluate(self, max_n=None): Parameters ---------- - max_n : int or None + max_n : int, optional Maximum number of positive relations to evaluate, all if `max_n` is None. Returns ------- - dict - Contains (metric_name, metric_value) pairs. - e.g. {'mean_rank': 50.3, 'MAP': 0.31}. + dict of (str, float) + (metric_name, metric_value) pairs, e.g. {'mean_rank': 50.3, 'MAP': 0.31}. """ mean_rank, map_ = self.evaluate_mean_rank_and_map(max_n) @@ -1552,14 +1631,13 @@ def evaluate_mean_rank_and_map(self, max_n=None): Parameters ---------- - max_n : int or None + max_n : int, optional Maximum number of positive relations to evaluate, all if `max_n` is None. Returns ------- tuple (float, float) - Contains (mean_rank, MAP). - e.g (50.3, 0.31). + (mean_rank, MAP), e.g (50.3, 0.31). """ ranks = [] @@ -1581,7 +1659,7 @@ def evaluate_mean_rank_and_map(self, max_n=None): class LexicalEntailmentEvaluation(object): - """Evaluating reconstruction on given network for any embedding.""" + """Evaluate reconstruction on given network for any embedding.""" def __init__(self, filepath): """Initialize evaluation instance with HyperLex text file containing relation pairs. @@ -1602,15 +1680,13 @@ def __init__(self, filepath): self.alpha = 1000 def score_function(self, embedding, trie, term_1, term_2): - """ - Given an embedding and two terms, return the predicted score for them - - extent to which `term_1` is a type of `term_2`. + """Compute predicted score - extent to which `term_1` is a type of `term_2`. Parameters ---------- - embedding : PoincareKeyedVectors instance + embedding : :class:`~gensim.models.poincare.PoincareKeyedVectors` Embedding to use for computing predicted score. - trie : pygtrie.Trie instance + trie : :class:`pygtrie.Trie` Trie to use for finding matching vocab terms for input terms. term_1 : str Input term. @@ -1643,19 +1719,18 @@ def score_function(self, embedding, trie, term_1, term_2): @staticmethod def find_matching_terms(trie, word): - """ - Given a trie and a word, find terms in the trie beginning with the word. + """Find terms in the `trie` beginning with the `word`. Parameters ---------- - trie : pygtrie.Trie instance + trie : :class:`pygtrie.Trie` Trie to use for finding matching terms. word : str Input word to use for prefix search. Returns ------- - list (str) + list of str List of matching terms. """ @@ -1669,12 +1744,12 @@ def create_vocab_trie(embedding): Parameters ---------- - embedding : PoincareKeyedVectors instance + embedding : :class:`~gensim.models.poincare.PoincareKeyedVectors` Embedding for which trie is to be created. Returns ------- - pygtrie.Trie instance + :class:`pygtrie.Trie` Trie containing vocab terms of the input embedding. """ @@ -1694,7 +1769,7 @@ def evaluate_spearman(self, embedding): Parameters ---------- - embedding : PoincareKeyedVectors instance + embedding : :class:`~gensim.models.poincare.PoincareKeyedVectors` Embedding for which evaluation is to be done. Returns @@ -1717,6 +1792,6 @@ def evaluate_spearman(self, embedding): count += 1 predicted_scores.append(predicted_score) expected_scores.append(expected_score) - print('Skipped pairs: %d out of %d' % (skipped, len(self.scores))) + logger.info('skipped pairs: %d out of %d' % (skipped, len(self.scores))) spearman = spearmanr(expected_scores, predicted_scores) return spearman.correlation diff --git a/gensim/models/utils_any2vec.py b/gensim/models/utils_any2vec.py index 5cf56fbcca..cc1e057afd 100644 --- a/gensim/models/utils_any2vec.py +++ b/gensim/models/utils_any2vec.py @@ -82,18 +82,18 @@ def _save_word2vec_format(fname, vocab, vectors, fvocab=None, binary=False, tota Parameters ---------- fname : str - The file path used to save the vectors in + The file path used to save the vectors in. vocab : dict - The vocabulary of words + The vocabulary of words. vectors : numpy.array - The vectors to be stored - fvocab : str - Optional file path used to save the vocabulary - binary : bool + The vectors to be stored. + fvocab : str, optional + File path used to save the vocabulary. + binary : bool, optional If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. - total_vec : int - Optional parameter to explicitly specify total no. of vectors - (in case word vectors are appended with document vectors afterwards) + total_vec : int, optional + Explicitly specify total number of vectors + (in case word vectors are appended with document vectors afterwards). """ if not (vocab or vectors): @@ -132,31 +132,29 @@ def _load_word2vec_format(cls, fname, fvocab=None, binary=False, encoding='utf8' ---------- fname : str The file path to the saved word2vec-format file. - fvocab : str - Optional file path to the vocabulary.Word counts are read from `fvocab` filename, - if set (this is the file generated by `-save-vocab` flag of the original C tool). - binary : bool + fvocab : str, optional + File path to the vocabulary.Word counts are read from `fvocab` filename, if set + (this is the file generated by `-save-vocab` flag of the original C tool). + binary : bool, optional If True, indicates whether the data is in binary word2vec format. - encoding : str - If you trained the C model using non-utf8 encoding for words, specify that - encoding in `encoding`. - unicode_errors : str + encoding : str, optional + If you trained the C model using non-utf8 encoding for words, specify that encoding in `encoding`. + unicode_errors : str, optional default 'strict', is a string suitable to be passed as the `errors` argument to the unicode() (Python 2.x) or str() (Python 3.x) function. If your source file may include word tokens truncated in the middle of a multibyte unicode character (as is common from the original word2vec.c tool), 'ignore' or 'replace' may help. - limit : int + limit : int, optional Sets a maximum number of word-vectors to read from the file. The default, None, means read all. - datatype : :class: `numpy.float*` - (Experimental) Can coerce dimensions to a non-default float type (such - as np.float16) to save memory. (Such types may result in much slower bulk operations - or incompatibility with optimized routines.) + datatype : type, optional + (Experimental) Can coerce dimensions to a non-default float type (such as `np.float16`) to save memory. + Such types may result in much slower bulk operations or incompatibility with optimized routines.) Returns ------- - :obj: `cls` - Returns the loaded model as an instance of :class: `cls`. + object + Returns the loaded model as an instance of :class:`cls`. """ from gensim.models.keyedvectors import Vocab diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py index 9539aa8d2c..018a19c467 100755 --- a/gensim/models/word2vec.py +++ b/gensim/models/word2vec.py @@ -5,101 +5,104 @@ # Copyright (C) 2018 RaRe Technologies s.r.o. # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""Produce word vectors with deep learning via word2vec's "skip-gram and CBOW models", using either -hierarchical softmax or negative sampling [1]_ [2]_. +"""This module implements the word2vec family of algorithms, using highly optimized C routines, +data streaming and Pythonic interfaces. -NOTE: There are more ways to get word vectors in Gensim than just Word2Vec. -See FastText and wrappers for VarEmbed and WordRank. +The word2vec algorithms include skip-gram and CBOW models, using either +hierarchical softmax or negative sampling: `Tomas Mikolov et al: Efficient Estimation of Word Representations +in Vector Space `_, `Tomas Mikolov et al: Distributed Representations of Words +and Phrases and their Compositionality `_. -The training algorithms were originally ported from the C package https://code.google.com/p/word2vec/ -and extended with additional functionality. - -For a blog tutorial on gensim word2vec, with an interactive web app trained on GoogleNews, -visit http://radimrehurek.com/2014/02/word2vec-tutorial/ - -**Make sure you have a C compiler before installing gensim, to use optimized (compiled) word2vec training** -(70x speedup compared to plain NumPy implementation [3]_). - -Initialize a model with e.g.:: - - >>> model = Word2Vec(sentences, size=100, window=5, min_count=5, workers=4) - -Persist a model to disk with:: +Other embeddings +================ - >>> model.save(fname) - >>> model = Word2Vec.load(fname) # you can continue training with the loaded model! +There are more ways to train word vectors in Gensim than just Word2Vec. +See also :class:`~gensim.models.doc2vec.Doc2Vec`, :class:`~gensim.models.fasttext.FastText` and +wrappers for :class:`~gensim.models.wrappers.VarEmbed` and :class:`~gensim.models.wrappers.WordRank`. -The word vectors are stored in a KeyedVectors instance in model.wv. -This separates the read-only word vector lookup operations in KeyedVectors from the training code in Word2Vec:: - - >>> model.wv['computer'] # numpy vector of a word - array([-0.00449447, -0.00310097, 0.02421786, ...], dtype=float32) - -The word vectors can also be instantiated from an existing file on disk in the word2vec C format -as a KeyedVectors instance. +The training algorithms were originally ported from the C package https://code.google.com/p/word2vec/ +and extended with additional functionality and optimizations over the years. -NOTE: It is impossible to continue training the vectors loaded from the C format because hidden weights, -vocabulary frequency and the binary tree is missing:: +For a tutorial on Gensim word2vec, with an interactive web app trained on GoogleNews, +visit https://rare-technologies.com/word2vec-tutorial/. - >>> from gensim.models import KeyedVectors - >>> word_vectors = KeyedVectors.load_word2vec_format('/tmp/vectors.txt', binary=False) # C text format - >>> word_vectors = KeyedVectors.load_word2vec_format('/tmp/vectors.bin', binary=True) # C binary format +**Make sure you have a C compiler before installing Gensim, to use the optimized word2vec routines** +(70x speedup compared to plain NumPy implementation, https://rare-technologies.com/parallelizing-word2vec-in-python/. +Usage examples +============== -You can perform various NLP word tasks with the model. Some of them -are already built-in:: +Initialize a model with e.g. - >>> model.wv.most_similar(positive=['woman', 'king'], negative=['man']) - [('queen', 0.50882536), ...] +>>> from gensim.test.utils import common_texts, get_tmpfile +>>> from gensim.models import Word2Vec +>>> +>>> path = get_tmpfile("word2vec.model") +>>> +>>> model = Word2Vec(common_texts, size=100, window=5, min_count=1, workers=4) +>>> model.save("word2vec.model") - >>> model.wv.most_similar_cosmul(positive=['woman', 'king'], negative=['man']) - [('queen', 0.71382287), ...] +The training is streamed, meaning `sentences` can be a generator, reading input data +from disk on-the-fly, without loading the entire corpus into RAM. +It also means you can continue training the model later - >>> model.wv.doesnt_match("breakfast cereal dinner lunch".split()) - 'cereal' +>>> model = Word2Vec.load("word2vec.model") +>>> model.train([["hello", "world"]], total_examples=1, epochs=1) +(0, 2) - >>> model.wv.similarity('woman', 'man') - 0.73723527 +The trained word vectors are stored in a :class:`~gensim.models.KeyedVectors` instance in `model.wv`: -Probability of a text under the model:: +>>> vector = model.wv['computer'] # numpy vector of a word - >>> model.score(["The fox jumped over a lazy dog".split()]) - 0.2158356 +The reason for separating the trained vectors into `KeyedVectors` is that if you don't +need the full model state any more (don't need to continue training), the state can discarded, +resulting in a much smaller and faster object that can be mmapped for lightning +fast loading and sharing the vectors in RAM between processes:: -Correlation with human opinion on word similarity:: +>>> from gensim.models import KeyedVectors +>>> +>>> path = get_tmpfile("wordvectors.kv") +>>> +>>> model.wv.save(path) +>>> wv = KeyedVectors.load("model.wv", mmap='r') +>>> vector = wv['computer'] # numpy vector of a word - >>> model.wv.evaluate_word_pairs(os.path.join(module_path, 'test_data','wordsim353.tsv')) - 0.51, 0.62, 0.13 +Gensim can also load word vectors in the "word2vec C format", as this :class:`~gensim.models.KeyedVectors` instance:: -And on analogies:: +>>> from gensim.test.utils import datapath +>>> +>>> wv_from_text = KeyedVectors.load_word2vec_format(datapath('word2vec_pre_kv_c'), binary=False) # C text format +>>> wv_from_bin = KeyedVectors.load_word2vec_format(datapath("euclidean_vectors.bin"), binary=True) # C binary format - >>> model.wv.evaluate_word_analogies(os.path.join(module_path, 'test_data', 'questions-words.txt'))[0] - 0.58 +It is impossible to continue training the vectors loaded from the C format because the hidden weights, +vocabulary frequencies and the binary tree are missing. To continue training, you'll need the +full :class:`~gensim.models.word2vec.Word2Vec` object state, as stored by :meth:`~gensim.models.word2vec.Word2Vec.save`, +not just the :class:`~gensim.models.keyedvectors.KeyedVectors`. -and so on. +You can perform various NLP word tasks with a trained model. Some of them +are already built-in - you can see it in :mod:`gensim.models.keyedvectors`. If you're finished training a model (i.e. no more updates, only querying), -then switch to the :mod:`gensim.models.KeyedVectors` instance in wv +you can switch to the :class:`~gensim.models.KeyedVectors` instance - >>> word_vectors = model.wv - >>> del model +>>> word_vectors = model.wv +>>> del model -to trim unneeded model memory = use much less RAM. +to trim unneeded model state = use much less RAM and allow fast loading and memory sharing (mmap). Note that there is a :mod:`gensim.models.phrases` module which lets you automatically detect phrases longer than one word. Using phrases, you can learn a word2vec model where "words" are actually multiword expressions, such as `new_york_times` or `financial_crisis`: - >>> bigram_transformer = gensim.models.Phrases(sentences) - >>> model = Word2Vec(bigram_transformer[sentences], size=100, ...) +>>> from gensim.test.utils import common_texts +>>> from gensim.models import Phrases +>>> +>>> bigram_transformer = Phrases(common_texts) +>>> model = Word2Vec(bigram_transformer[common_texts], min_count=1) -.. [1] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. - Efficient Estimation of Word Representations in Vector Space. In Proceedings of Workshop at ICLR, 2013. -.. [2] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. - Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of NIPS, 2013. -.. [3] Optimizing word2vec in gensim, http://radimrehurek.com/2013/09/word2vec-in-python-part-two-optimizing/ """ + from __future__ import division # py3 "true division" import logging @@ -146,12 +149,34 @@ MAX_WORDS_IN_BATCH = 10000 def train_batch_sg(model, sentences, alpha, work=None, compute_loss=False): - """ - Update skip-gram model by training on a sequence of sentences. - Each sentence is a list of string tokens, which are looked up in the model's - vocab dictionary. Called internally from `Word2Vec.train()`. - This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from word2vec_inner instead. + """Update skip-gram model by training on a sequence of sentences. + + Called internally from :meth:`~gensim.models.word2vec.Word2Vec.train`. + + Warnings + -------- + This is the non-optimized, pure Python version. If you have a C compiler, Gensim + will use an optimized code path from :mod:`gensim.models.word2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.word2Vec.Word2Vec` + The Word2Vec model instance to train. + sentences : iterable of list of str + The corpus used to train the model. + alpha : float + The learning rate + work : object, optional + Unused. + compute_loss : bool, optional + Whether or not the training loss should be computed in this batch. + + Returns + ------- + int + Number of words in the vocabulary actually used for training (that already existed in the vocabulary + and were not discarded by negative sampling). + """ result = 0 for sentence in sentences: @@ -173,17 +198,43 @@ def train_batch_sg(model, sentences, alpha, work=None, compute_loss=False): return result def train_batch_cbow(model, sentences, alpha, work=None, neu1=None, compute_loss=False): - """ - Update CBOW model by training on a sequence of sentences. - Each sentence is a list of string tokens, which are looked up in the model's - vocab dictionary. Called internally from `Word2Vec.train()`. - This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from word2vec_inner instead. + """Update CBOW model by training on a sequence of sentences. + + Called internally from :meth:`~gensim.models.word2vec.Word2Vec.train`. + + Warnings + -------- + This is the non-optimized, pure Python version. If you have a C compiler, Gensim + will use an optimized code path from :mod:`gensim.models.word2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The Word2Vec model instance to train. + sentences : iterable of list of str + The corpus used to train the model. + alpha : float + The learning rate + work : object, optional + Unused. + neu1 : object, optional + Unused. + compute_loss : bool, optional + Whether or not the training loss should be computed in this batch. + + Returns + ------- + int + Number of words in the vocabulary actually used for training (that already existed in the vocabulary + and were not discarded by negative sampling). + """ result = 0 for sentence in sentences: - word_vocabs = [model.wv.vocab[w] for w in sentence if w in model.wv.vocab and - model.wv.vocab[w].sample_int > model.random.rand() * 2 ** 32] + word_vocabs = [ + model.wv.vocab[w] for w in sentence if w in model.wv.vocab and + model.wv.vocab[w].sample_int > model.random.rand() * 2 ** 32 + ] for pos, word in enumerate(word_vocabs): reduced_window = model.random.randint(model.window) # `b` in the original word2vec code start = max(0, pos - model.window + reduced_window) @@ -197,12 +248,27 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None, compute_loss return result def score_sentence_sg(model, sentence, work=None): - """ - Obtain likelihood score for a single sentence in a fitted skip-gram representaion. - The sentence is a list of Vocab objects (or None, when the corresponding - word is not in the vocabulary). Called internally from `Word2Vec.score()`. - This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from word2vec_inner instead. + """Obtain likelihood score for a single sentence in a fitted skip-gram representation. + + Notes + ----- + This is the non-optimized, pure Python version. If you have a C compiler, Gensim + will use an optimized code path from :mod:`gensim.models.word2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The trained model. It **MUST** have been trained using hierarchical softmax and the skip-gram algorithm. + sentence : list of str + The words comprising the sentence to be scored. + work : object, optional + Unused. For interface compatibility only. + + Returns + ------- + float + The probability assigned to this sentence by the Skip-Gram model. + """ log_prob_sentence = 0.0 if model.negative: @@ -223,12 +289,29 @@ def score_sentence_sg(model, sentence, work=None): return log_prob_sentence def score_sentence_cbow(model, sentence, work=None, neu1=None): - """ - Obtain likelihood score for a single sentence in a fitted CBOW representaion. - The sentence is a list of Vocab objects (or None, where the corresponding - word is not in the vocabulary. Called internally from `Word2Vec.score()`. - This is the non-optimized, Python version. If you have cython installed, gensim - will use the optimized version from word2vec_inner instead. + """Obtain likelihood score for a single sentence in a fitted CBOW representation. + + Notes + ----- + This is the non-optimized, pure Python version. If you have a C compiler, Gensim + will use an optimized code path from :mod:`gensim.models.word2vec_inner` instead. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The trained model. It **MUST** have been trained using hierarchical softmax and the CBOW algorithm. + sentence : list of str + The words comprising the sentence to be scored. + work : object, optional + Unused. For interface compatibility only. + neu1 : object, optional + Unused. For interface compatibility only. + + Returns + ------- + float + The probability assigned to this sentence by the CBOW model. + """ log_prob_sentence = 0.0 if model.negative: @@ -252,6 +335,38 @@ def score_sentence_cbow(model, sentence, work=None, neu1=None): def train_sg_pair(model, word, context_index, alpha, learn_vectors=True, learn_hidden=True, context_vectors=None, context_locks=None, compute_loss=False, is_ft=False): + """Train the passed model instance on a word and its context, using the Skip-gram algorithm. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The model to be trained. + word : str + The label (predicted) word. + context_index : list of int + The vocabulary indices of the words in the context. + alpha : float + Learning rate. + learn_vectors : bool, optional + Whether the vectors should be updated. + learn_hidden : bool, optional + Whether the weights of the hidden layer should be updated. + context_vectors : list of list of float, optional + Vector representations of the words in the context. If None, these will be retrieved from the model. + context_locks : list of float, optional + The lock factors for each word in the context. + compute_loss : bool, optional + Whether or not the training loss should be computed. + is_ft : bool, optional + If True, weights will be computed using `model.wv.syn0_vocab` and `model.wv.syn0_ngrams` + instead of `model.wv.syn0`. + + Returns + ------- + numpy.ndarray + Error vector to be back-propagated. + + """ if context_vectors is None: if is_ft: context_vectors_vocab = model.wv.syn0_vocab @@ -328,6 +443,40 @@ def train_sg_pair(model, word, context_index, alpha, learn_vectors=True, learn_h def train_cbow_pair(model, word, input_word_indices, l1, alpha, learn_vectors=True, learn_hidden=True, compute_loss=False, context_vectors=None, context_locks=None, is_ft=False): + """Train the passed model instance on a word and its context, using the CBOW algorithm. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The model to be trained. + word : str + The label (predicted) word. + input_word_indices : list of int + The vocabulary indices of the words in the context. + l1 : list of float + Vector representation of the label word. + alpha : float + Learning rate. + learn_vectors : bool, optional + Whether the vectors should be updated. + learn_hidden : bool, optional + Whether the weights of the hidden layer should be updated. + compute_loss : bool, optional + Whether or not the training loss should be computed. + context_vectors : list of list of float, optional + Vector representations of the words in the context. If None, these will be retrieved from the model. + context_locks : list of float, optional + The lock factors for each word in the context. + is_ft : bool, optional + If True, weights will be computed using `model.wv.syn0_vocab` and `model.wv.syn0_ngrams` + instead of `model.wv.syn0`. + + Returns + ------- + numpy.ndarray + Error vector to be back-propagated. + + """ if context_vectors is None: if is_ft: context_vectors_vocab = model.wv.syn0_vocab @@ -396,6 +545,23 @@ def train_cbow_pair(model, word, input_word_indices, l1, alpha, learn_vectors=Tr def score_sg_pair(model, word, word2): + """Score the trained Skip-gram model on a pair of words. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The trained model. + word : :class:`~gensim.models.keyedvectors.Vocab` + Vocabulary representation of the first word. + word2 : :class:`~gensim.models.keyedvectors.Vocab` + Vocabulary representation of the second word. + + Returns + ------- + float + Logarithm of the sum of exponentiations of input words. + + """ l1 = model.wv.syn0[word2.index] l2a = deepcopy(model.syn1[word.point]) # 2d matrix, codelen x layer1_size sgn = (-1.0) ** word.code # ch function, 0-> 1, 1 -> -1 @@ -404,6 +570,23 @@ def score_sg_pair(model, word, word2): def score_cbow_pair(model, word, l1): + """Score the trained CBOW model on a pair of words. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The trained model. + word : :class:`~gensim.models.keyedvectors.Vocab` + Vocabulary representation of the first word. + l1 : list of float + Vector representation of the second word. + + Returns + ------- + float + Logarithm of the sum of exponentiations of input words. + + """ l2a = model.syn1[word.point] # 2d matrix, codelen x layer1_size sgn = (-1.0) ** word.code # ch function, 0-> 1, 1 -> -1 lprob = -logaddexp(0, -sgn * dot(l1, l2a.T)) @@ -411,109 +594,134 @@ def score_cbow_pair(model, word, l1): class Word2Vec(BaseWordEmbeddingsModel): - """Class for training, using and evaluating neural networks described in https://code.google.com/p/word2vec/ + """Train, use and evaluate neural networks described in https://code.google.com/p/word2vec/. - If you're finished training a model (=no more updates, only querying) - then switch to the :mod:`gensim.models.KeyedVectors` instance in wv + Once you're finished training a model (=no more updates, only querying) + store and use only the :class:`~gensim.models.keyedvectors.KeyedVectors` instance in `self.wv` to reduce memory. - The model can be stored/loaded via its :meth:`~gensim.models.word2vec.Word2Vec.save()` and - :meth:`~gensim.models.word2vec.Word2Vec.load()` methods, or stored/loaded in a format - compatible with the original word2vec implementation via `wv.save_word2vec_format()` - and `Word2VecKeyedVectors.load_word2vec_format()`. + The model can be stored/loaded via its :meth:`~gensim.models.word2vec.Word2Vec.save` and + :meth:`~gensim.models.word2vec.Word2Vec.load` methods. - """ + The trained word vectors can also be stored/loaded from a format compatible with the + original word2vec implementation via `self.wv.save_word2vec_format` + and :meth:`gensim.models.keyedvectors.KeyedVectors.load_word2vec_format`. + Some important attributes are the following: + + Attributes + ---------- + wv : :class:`~gensim.models.keyedvectors.Word2VecKeyedVectors` + This object essentially contains the mapping between words and embeddings. After training, it can be used + directly to query those embeddings in various ways. See the module level docstring for examples. + + vocabulary : :class:'~gensim.models.word2vec.Word2VecVocab' + This object represents the vocabulary (sometimes called Dictionary in gensim) of the model. + Besides keeping track of all unique words, this object provides extra functionality, such as + constructing a huffman tree (frequent words are closer to the root), or discarding extremely rare words. + + trainables : :class:`~gensim.models.word2vec.Word2VecTrainables` + This object represents the inner shallow neural network used to train the embeddings. The semantics of the + network differ slightly in the two available training modes (CBOW or SG) but you can think of it as a NN with + a single projection and hidden layer which we train on the corpus. The weights are then used as our embeddings + (which means that the size of the hidden layer is equal to the number of features `self.size`). + + """ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, sg=0, hs=0, negative=5, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, trim_rule=None, sorted_vocab=1, batch_words=MAX_WORDS_IN_BATCH, compute_loss=False, callbacks=(), max_final_vocab=None): """ - Initialize the model from an iterable of `sentences`. Each sentence is a - list of words (unicode strings) that will be used for training. Parameters ---------- - sentences : iterable of iterables + sentences : iterable of iterables, optional The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. + See also the `tutorial on data streaming in Python + `_. If you don't supply `sentences`, the model is left uninitialized -- use if you plan to initialize it in some other way. - - sg : int {1, 0} - Defines the training algorithm. If 1, skip-gram is employed; otherwise, CBOW is used. - size : int - Dimensionality of the feature vectors. - window : int - The maximum distance between the current and predicted word within a sentence. - alpha : float + size : int, optional + Dimensionality of the word vectors. + window : int, optional + Maximum distance between the current and predicted word within a sentence. + min_count : int, optional + Ignores all words with total frequency lower than this. + workers : int, optional + Use these many worker threads to train the model (=faster training with multicore machines). + sg : {0, 1}, optional + Training algorithm: 1 for skip-gram; otherwise CBOW. + hs : {0, 1}, optional + If 1, hierarchical softmax will be used for model training. + If 0, and `negative` is non-zero, negative sampling will be used. + negative : int, optional + If > 0, negative sampling will be used, the int for negative specifies how many "noise words" + should be drawn (usually between 5-20). + If set to 0, no negative sampling is used. + cbow_mean : {0, 1}, optional + If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used. + alpha : float, optional The initial learning rate. - min_alpha : float + min_alpha : float, optional Learning rate will linearly drop to `min_alpha` as training progresses. - seed : int + seed : int, optional Seed for the random number generator. Initial vectors for each word are seeded with a hash of the concatenation of word + `str(seed)`. Note that for a fully deterministically-reproducible run, you must also limit the model to a single worker thread (`workers=1`), to eliminate ordering jitter from OS thread scheduling. (In Python 3, reproducibility between interpreter launches also requires use of the `PYTHONHASHSEED` environment variable to control hash randomization). - min_count : int - Ignores all words with total frequency lower than this. - max_vocab_size : int + max_vocab_size : int, optional Limits the RAM during vocabulary building; if there are more unique words than this, then prune the infrequent ones. Every 10 million word types need about 1GB of RAM. Set to `None` for no limit. - max_final_vocab : int + max_final_vocab : int, optional Limits the vocab to a target vocab size by automatically picking a matching min_count. If the specified min_count is more than the calculated min_count, the specified min_count will be used. Set to `None` if not required. - sample : float + sample : float, optional The threshold for configuring which higher-frequency words are randomly downsampled, useful range is (0, 1e-5). - workers : int - Use these many worker threads to train the model (=faster training with multicore machines). - hs : int {1,0} - If 1, hierarchical softmax will be used for model training. - If set to 0, and `negative` is non-zero, negative sampling will be used. - negative : int - If > 0, negative sampling will be used, the int for negative specifies how many "noise words" - should be drawn (usually between 5-20). - If set to 0, no negative sampling is used. - cbow_mean : int {1,0} - If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used. - hashfxn : function + hashfxn : function, optional Hash function to use to randomly initialize weights, for increased training reproducibility. - iter : int + iter : int, optional Number of iterations (epochs) over the corpus. - trim_rule : function + trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), or a callable that accepts parameters (word, count, min_count) and returns either :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part - of the model. - sorted_vocab : int {1,0} + The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part of the + model. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + sorted_vocab : {0, 1}, optional If 1, sort the vocabulary by descending frequency before assigning word indexes. - batch_words : int + See :meth:`~gensim.models.word2vec.Word2VecVocab.sort_vocab()`. + batch_words : int, optional Target size (in words) for batches of examples passed to worker threads (and thus cython routines).(Larger batches will be passed if individual texts are longer than 10000 words, but the standard cython code truncates to that maximum.) - compute_loss: bool - If True, computes and stores loss value which can be retrieved using `model.get_latest_training_loss()`. - callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec` - List of callbacks that need to be executed/run at specific stages during training. + compute_loss: bool, optional + If True, computes and stores loss value which can be retrieved using + :meth:`~gensim.models.word2vec.Word2Vec.get_latest_training_loss`. + callbacks : iterable of :class:`~gensim.models.callbacks.CallbackAny2Vec`, optional + Sequence of callbacks to be executed at specific stages during training. Examples -------- - Initialize and train a `Word2Vec` model + Initialize and train a :class:`~gensim.models.word2vec.Word2Vec` model >>> from gensim.models import Word2Vec >>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]] - >>> >>> model = Word2Vec(sentences, min_count=1) - >>> say_vector = model['say'] # get vector for word """ self.max_final_vocab = max_final_vocab @@ -534,9 +742,22 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, fast_version=FAST_VERSION) def _do_train_job(self, sentences, alpha, inits): - """ - Train a single batch of sentences. Return 2-tuple `(effective word count after - ignoring unknown words and sentence length trimming, total word count)`. + """Train the model on a single batch of sentences. + + Parameters + ---------- + sentences : iterable of list of str + Corpus chunk to be used in this training batch. + alpha : float + The learning rate used in this batch. + inits : (np.ndarray, np.ndarray) + Each worker threads private work memory. + + Returns + ------- + (int, int) + 2-tuple (effective word count after ignoring unknown words and sentence length trimming, total word count). + """ work, neu1 = inits tally = 0 @@ -547,7 +768,7 @@ def _do_train_job(self, sentences, alpha, inits): return tally, self._raw_word_count(sentences) def _clear_post_train(self): - """Resets certain properties of the model, post training.""" + """Remove all L2-normalized word vectors from the model.""" self.wv.vectors_norm = None def _set_train_params(self, **kwargs): @@ -558,48 +779,59 @@ def _set_train_params(self, **kwargs): def train(self, sentences, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, compute_loss=False, callbacks=()): - """Update the model's neural weights from a sequence of sentences (can be a once-only generator stream). - For Word2Vec, each sentence must be a list of unicode strings. (Subclasses may accept other examples.) + """Update the model's neural weights from a sequence of sentences. - To support linear learning-rate decay from (initial) alpha to min_alpha, and accurate - progress-percentage logging, either total_examples (count of sentences) or total_words (count of - raw words in sentences) **MUST** be provided (if the corpus is the same as was provided to - :meth:`~gensim.models.word2vec.Word2Vec.build_vocab()`, the count of examples in that corpus - will be available in the model's :attr:`corpus_count` property). + Notes + ----- + To support linear learning-rate decay from (initial) `alpha` to `min_alpha`, and accurate + progress-percentage logging, either `total_examples` (count of sentences) or `total_words` (count of + raw words in sentences) **MUST** be provided. If `sentences` is the same corpus + that was provided to :meth:`~gensim.models.word2vec.Word2Vec.build_vocab` earlier, + you can simply use `total_examples=self.corpus_count`. + Warnings + -------- To avoid common mistakes around the model's ability to do multiple training passes itself, an - explicit `epochs` argument **MUST** be provided. In the common and recommended case, - where :meth:`~gensim.models.word2vec.Word2Vec.train()` is only called once, - the model's cached `iter` value should be supplied as `epochs` value. + explicit `epochs` argument **MUST** be provided. In the common and recommended case + where :meth:`~gensim.models.word2vec.Word2Vec.train` is only called once, you can set `epochs=self.iter`. Parameters ---------- - sentences : iterable of iterables + sentences : iterable of list of str The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. - total_examples : int - Count of sentences. - total_words : int - Count of raw words in sentences. - epochs : int + See also the `tutorial on data streaming in Python + `_. + total_examples : int, optional + Count of sentences. Used to decay the `alpha` learning rate. + total_words : int, optional + Count of raw words in sentences. Used to decay the `alpha` learning rate. + epochs : int, optional Number of iterations (epochs) over the corpus. - start_alpha : float - Initial learning rate. - end_alpha : float + start_alpha : float, optional + Initial learning rate. If supplied, replaces the starting `alpha` from the constructor, + for this one call to`train()`. + Use only if making multiple calls to `train()`, when you want to manage the alpha learning-rate yourself + (not recommended). + end_alpha : float, optional Final learning rate. Drops linearly from `start_alpha`. - word_count : int + If supplied, this replaces the final `min_alpha` from the constructor, for this one call to `train()`. + Use only if making multiple calls to `train()`, when you want to manage the alpha learning-rate yourself + (not recommended). + word_count : int, optional Count of words already trained. Set this to 0 for the usual case of training on all words in sentences. - queue_factor : int + queue_factor : int, optional Multiplier for size of queue (number of workers * queue_factor). - report_delay : float + report_delay : float, optional Seconds to wait before reporting progress. - compute_loss: bool - If True, computes and stores loss value which can be retrieved using `model.get_latest_training_loss()`. - callbacks : :obj: `list` of :obj: `~gensim.models.callbacks.CallbackAny2Vec` - List of callbacks that need to be executed/run at specific stages during training. + compute_loss: bool, optional + If True, computes and stores loss value which can be retrieved using + :meth:`~gensim.models.word2vec.Word2Vec.get_latest_training_loss`. + callbacks : iterable of :class:`~gensim.models.callbacks.CallbackAny2Vec`, optional + Sequence of callbacks to be executed at specific stages during training. Examples -------- @@ -607,48 +839,45 @@ def train(self, sentences, total_examples=None, total_words=None, >>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]] >>> >>> model = Word2Vec(min_count=1) - >>> model.build_vocab(sentences) - >>> model.train(sentences, total_examples=model.corpus_count, epochs=model.iter) + >>> model.build_vocab(sentences) # prepare the model vocabulary + >>> model.train(sentences, total_examples=model.corpus_count, epochs=model.iter) # train word vectors + (1, 30) """ - return super(Word2Vec, self).train( sentences, total_examples=total_examples, total_words=total_words, epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, queue_factor=queue_factor, report_delay=report_delay, compute_loss=compute_loss, callbacks=callbacks) def score(self, sentences, total_sentences=int(1e6), chunksize=100, queue_factor=2, report_delay=1): - """Score the log probability for a sequence of sentences (can be a once-only generator stream). - Each sentence must be a list of unicode strings. - This does not change the fitted model in any way (see Word2Vec.train() for that). + """Score the log probability for a sequence of sentences. + This does not change the fitted model in any way (see :meth:`~gensim.models.word2vec.Word2Vec.train` for that). - We have currently only implemented score for the hierarchical softmax scheme, - so you need to have run word2vec with hs=1 and negative=0 for this to work. + Gensim has currently only implemented score for the hierarchical softmax scheme, + so you need to have run word2vec with `hs=1` and `negative=0` for this to work. - Note that you should specify total_sentences; we'll run into problems if you ask to + Note that you should specify `total_sentences`; you'll run into problems if you ask to score more than this number of sentences but it is inefficient to set the value too high. - See the article by [#taddy]_ and the gensim demo at [#deepir]_ for examples of + See the `article by Matt Taddy: "Document Classification by Inversion of Distributed Language Representations" + `_ and the + `gensim demo `_ for examples of how to use such scores in document classification. - .. [#taddy] Taddy, Matt. Document Classification by Inversion of Distributed Language Representations, - in Proceedings of the 2015 Conference of the Association of Computational Linguistics. - .. [#deepir] https://github.com/piskvorky/gensim/blob/develop/docs/notebooks/deepir.ipynb - Parameters ---------- - sentences : iterable of iterables + sentences : iterable of list of str The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. - total_sentences : int + total_sentences : int, optional Count of sentences. - chunksize : int + chunksize : int, optional Chunksize of jobs - queue_factor : int + queue_factor : int, optional Multiplier for size of queue (number of workers * queue_factor). - report_delay : float + report_delay : float, optional Seconds to wait before reporting progress. """ @@ -756,30 +985,34 @@ def worker_loop(): return sentence_scores[:sentence_count] def clear_sims(self): - """Removes all L2-normalized vectors for words from the model. - You will have to recompute them using init_sims method. - """ + """Remove all L2-normalized word vectors from the model, to free up memory. + + You can recompute them later again using the :meth:`~gensim.models.word2vec.Word2Vec.init_sims` method. + """ self.wv.vectors_norm = None def intersect_word2vec_format(self, fname, lockf=0.0, binary=False, encoding='utf8', unicode_errors='strict'): - """Merge the input-hidden weight matrix from the original C word2vec-tool format - given, where it intersects with the current vocabulary. (No words are added to the - existing vocabulary, but intersecting words adopt the file's weights, and - non-intersecting words are left alone.) + """Merge in an input-hidden weight matrix loaded from the original C word2vec-tool format, + where it intersects with the current vocabulary. + + No words are added to the existing vocabulary, but intersecting words adopt the file's weights, and + non-intersecting words are left alone. Parameters ---------- fname : str - The file path used to save the vectors in - - binary : bool - If True, the data wil be saved in binary word2vec format, else it will be saved in plain text. - - lockf : float + The file path to load the vectors from. + lockf : float, optional Lock-factor value to be set for any imported word-vectors; the default value of 0.0 prevents further updating of the vector during subsequent training. Use 1.0 to allow further training updates of merged vectors. + binary : bool, optional + If True, `fname` is in the binary word2vec C format. + encoding : str, optional + Encoding of `text` for `unicode` function (python2 only). + unicode_errors : str, optional + Error handling behaviour, used as parameter for `unicode` function (python2 only). """ overlap_count = 0 @@ -821,35 +1054,34 @@ def intersect_word2vec_format(self, fname, lockf=0.0, binary=False, encoding='ut @deprecated("Method will be removed in 4.0.0, use self.wv.__getitem__() instead") def __getitem__(self, words): - """ - Deprecated. Use self.wv.__getitem__() instead. - Refer to the documentation for `gensim.models.keyedvectors.Word2VecKeyedVectors.__getitem__` + """Deprecated. Use `self.wv.__getitem__` instead. + Refer to the documentation for :meth:`~gensim.models.keyedvectors.Word2VecKeyedVectors.__getitem__`. + """ return self.wv.__getitem__(words) @deprecated("Method will be removed in 4.0.0, use self.wv.__contains__() instead") def __contains__(self, word): - """ - Deprecated. Use self.wv.__contains__() instead. - Refer to the documentation for `gensim.models.keyedvectors.Word2VecKeyedVectors.__contains__` + """Deprecated. Use `self.wv.__contains__` instead. + Refer to the documentation for :meth:`~gensim.models.keyedvectors.Word2VecKeyedVectors.__contains__`. + """ return self.wv.__contains__(word) def predict_output_word(self, context_words_list, topn=10): - """Report the probability distribution of the center word given the context words - as input to the trained model. + """Get the probability distribution of the center word given context words. Parameters ---------- - context_words_list : :obj: `list` of :obj: `str` - List of context words - topn: int - Return `topn` words and their probabilities + context_words_list : list of str + List of context words. + topn : int, optional + Return `topn` words and their probabilities. Returns ------- - :obj: `list` of :obj: `tuple` - `topn` length list of tuples of (word, probability) + list of (str, float) + `topn` length list of tuples of (word, probability). """ if not self.negative: @@ -880,18 +1112,30 @@ def predict_output_word(self, context_words_list, topn=10): return [(self.wv.index2word[index1], prob_values[index1]) for index1 in top_indices] def init_sims(self, replace=False): - """ - init_sims() resides in KeyedVectors because it deals with syn0/vectors mainly, but because syn1 is not an - attribute of KeyedVectors, it has to be deleted in this class, and the normalizing of syn0/vectors happens - inside of KeyedVectors + """Deprecated. Use `self.wv.init_sims` instead. + See :meth:`~gensim.models.keyedvectors.Word2VecKeyedVectors.init_sims`. + """ if replace and hasattr(self.trainables, 'syn1'): del self.trainables.syn1 return self.wv.init_sims(replace) def reset_from(self, other_model): - """Borrow shareable pre-built structures (like vocab) from the other_model. Useful - if testing multiple models in parallel on the same corpus. + """Borrow shareable pre-built structures from `other_model` and reset hidden layer weights. + + Structures copied are: + * Vocabulary + * Index to word mapping + * Cumulative frequency table (used for negative sampling) + * Cached corpus length + + Useful when testing multiple models on the same corpus in parallel. + + Parameters + ---------- + other_model : :class:`~gensim.models.word2vec.Word2Vec` + Another model to copy the internal structures from. + """ self.wv.vocab = other_model.wv.vocab self.wv.index2word = other_model.wv.index2word @@ -901,30 +1145,57 @@ def reset_from(self, other_model): @staticmethod def log_accuracy(section): + """Deprecated. Use `self.wv.log_accuracy` instead. + See :meth:`~gensim.models.word2vec.Word2VecKeyedVectors.log_accuracy`. + + """ return Word2VecKeyedVectors.log_accuracy(section) @deprecated("Method will be removed in 4.0.0, use self.wv.evaluate_word_analogies() instead") def accuracy(self, questions, restrict_vocab=30000, most_similar=None, case_insensitive=True): + """Deprecated. Use `self.wv.accuracy` instead. + See :meth:`~gensim.models.word2vec.Word2VecKeyedVectors.accuracy`. + + """ most_similar = most_similar or Word2VecKeyedVectors.most_similar return self.wv.accuracy(questions, restrict_vocab, most_similar, case_insensitive) def __str__(self): + """Human readable representation of the model's state. + + Returns + ------- + str + Human readable representation of the model's state, including the vocabulary size, vector size + and learning rate. + + """ return "%s(vocab=%s, size=%s, alpha=%s)" % ( self.__class__.__name__, len(self.wv.index2word), self.wv.vector_size, self.alpha ) def delete_temporary_training_data(self, replace_word_vectors_with_normalized=False): - """Discard parameters that are used in training and score. Use if you're sure you're done training a model. - If `replace_word_vectors_with_normalized` is set, forget the original vectors and only keep the normalized - ones = saves lots of memory! + """Discard parameters that are used in training and scoring, to save memory. + + Warnings + -------- + Use only if you're sure you're done training a model. + + Parameters + ---------- + replace_word_vectors_with_normalized : bool, optional + If True, forget the original (not normalized) word vectors and only keep + the L2-normalized word vectors, to save even more memory. + """ if replace_word_vectors_with_normalized: self.init_sims(replace=True) self._minimize_model() def save(self, *args, **kwargs): - """Save the model. This saved model can be loaded again using :func:`~gensim.models.word2vec.Word2Vec.load`, - which supports online training and getting vectors for vocabulary words. + """Save the model. + This saved model can be loaded again using :func:`~gensim.models.word2vec.Word2Vec.load`, which supports + online training and getting vectors for vocabulary words. Parameters ---------- @@ -937,6 +1208,14 @@ def save(self, *args, **kwargs): super(Word2Vec, self).save(*args, **kwargs) def get_latest_training_loss(self): + """Get current value of the training loss. + + Returns + ------- + float + Current training loss. + + """ return self.running_training_loss @deprecated( @@ -957,16 +1236,24 @@ def _minimize_model(self, save_syn1=False, save_syn1neg=False, save_vectors_lock def load_word2vec_format( cls, fname, fvocab=None, binary=False, encoding='utf8', unicode_errors='strict', limit=None, datatype=REAL): - """Deprecated. Use gensim.models.KeyedVectors.load_word2vec_format instead.""" + """Deprecated. Use :meth:`gensim.models.KeyedVectors.load_word2vec_format` instead.""" raise DeprecationWarning("Deprecated. Use gensim.models.KeyedVectors.load_word2vec_format instead.") def save_word2vec_format(self, fname, fvocab=None, binary=False): - """Deprecated. Use model.wv.save_word2vec_format instead.""" + """Deprecated. Use `model.wv.save_word2vec_format` instead. + See :meth:`gensim.models.KeyedVectors.save_word2vec_format`. + + """ raise DeprecationWarning("Deprecated. Use model.wv.save_word2vec_format instead.") @classmethod def load(cls, *args, **kwargs): - """Loads a previously saved `Word2Vec` model. Also see `save()`. + """Load a previously saved :class:`~gensim.models.word2vec.Word2Vec` model. + + See Also + -------- + :meth:`~gensim.models.word2vec.Word2Vec.save` + Save model. Parameters ---------- @@ -975,8 +1262,9 @@ def load(cls, *args, **kwargs): Returns ------- - :obj: `~gensim.models.word2vec.Word2Vec` - Returns the loaded model as an instance of :class: `~gensim.models.word2vec.Word2Vec`. + :class:`~gensim.models.word2vec.Word2Vec` + Loaded model. + """ try: model = super(Word2Vec, cls).load(*args, **kwargs) @@ -994,8 +1282,10 @@ def load(cls, *args, **kwargs): class BrownCorpus(object): - """Iterate over sentences from the Brown corpus (part of NLTK data).""" + """Iterate over sentences from the `Brown corpus `_ + (part of `NLTK data `_). + """ def __init__(self, dirname): self.dirname = dirname @@ -1017,8 +1307,7 @@ def __iter__(self): class Text8Corpus(object): - """Iterate over sentences from the "text8" corpus, unzipped from http://mattmahoney.net/dc/text8.zip .""" - + """Iterate over sentences from the "text8" corpus, unzipped from http://mattmahoney.net/dc/text8.zip.""" def __init__(self, fname, max_sentence_length=MAX_WORDS_IN_BATCH): self.fname = fname self.max_sentence_length = max_sentence_length @@ -1046,22 +1335,26 @@ def __iter__(self): class LineSentence(object): - """Simple format: one sentence = one line; words already preprocessed and separated by whitespace. - """ + """Iterate over a file that contains sentences: one line = one sentence. + Words must be already preprocessed and separated by whitespace. + """ def __init__(self, source, max_sentence_length=MAX_WORDS_IN_BATCH, limit=None): """ - `source` can be either a string or a file object. Clip the file to the first - `limit` lines (or not clipped if limit is None, the default). - Example:: - - sentences = LineSentence('myfile.txt') - - Or for compressed files:: + Parameters + ---------- + source : string or a file-like object + Path to the file on disk, or an already-open file object (must support `seek(0)`). + limit : int or None + Clip the file to the first `limit` lines. Do no clipping if `limit is None` (the default). - sentences = LineSentence('compressed_text.txt.bz2') - sentences = LineSentence('compressed_text.txt.gz') + Examples + -------- + >>> from gensim.test.utils import datapath + >>> sentences = LineSentence(datapath('lee_background.cor')) + >>> for sentence in sentences: + ... pass """ self.source = source @@ -1092,25 +1385,28 @@ def __iter__(self): class PathLineSentences(object): - """Works like word2vec.LineSentence, but will process all files in a directory in alphabetical order by filename. - The directory can only contain files that can be read by LineSentence: .bz2, .gz, and text files. - Any file not ending with .bz2 or .gz is assumed to be a text file. Does not work with subdirectories. + """Like :class:`~gensim.models.word2vec.LineSentence`, but process all files in a directory + in alphabetical order by filename. + + The directory must only contain files that can be read by :class:`gensim.models.word2vec.LineSentence`: + .bz2, .gz, and text files. Any file not ending with .bz2 or .gz is assumed to be a text file. The format of files (either text, or compressed text files) in the path is one sentence = one line, with words already preprocessed and separated by whitespace. - """ + Warnings + -------- + Does **not recurse** into subdirectories. + """ def __init__(self, source, max_sentence_length=MAX_WORDS_IN_BATCH, limit=None): """ - `source` should be a path to a directory (as a string) where all files can be opened by the - LineSentence class. Each file will be read up to `limit` lines (or not clipped if limit is None, the default). - - Example:: - - sentences = PathLineSentences(os.getcwd() + '\\corpus\\') - - The files in the directory should be either text files, .bz2 files, or .gz files. + Parameters + ---------- + source : str + Path to the directory. + limit : int or None + Read only the first `limit` lines from each file. Read all if limit is None (the default). """ self.source = source @@ -1145,8 +1441,10 @@ def __iter__(self): class Word2VecVocab(utils.SaveLoad): - def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0, - max_final_vocab=None): + """Vocabulary used by :class:`~gensim.models.word2vec.Word2Vec`.""" + def __init__( + self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0, + max_final_vocab=None): self.max_vocab_size = max_vocab_size self.min_count = min_count self.sample = sample @@ -1202,8 +1500,9 @@ def sort_vocab(self, wv): for i, word in enumerate(wv.index2word): wv.vocab[word].index = i - def prepare_vocab(self, hs, negative, wv, update=False, keep_raw_vocab=False, trim_rule=None, - min_count=None, sample=None, dry_run=False): + def prepare_vocab( + self, hs, negative, wv, update=False, keep_raw_vocab=False, trim_rule=None, + min_count=None, sample=None, dry_run=False): """Apply vocabulary settings for `min_count` (discarding less-frequent words) and `sample` (controlling the downsampling of more-frequent words). @@ -1233,9 +1532,10 @@ def prepare_vocab(self, hs, negative, wv, update=False, keep_raw_vocab=False, tr calc_min_count = self.raw_vocab[sorted_vocab[self.max_final_vocab]] + 1 self.effective_min_count = max(calc_min_count, min_count) - logger.info("max_final_vocab=%d and min_count=%d resulted in calc_min_count=%d, effective_min_count=%d", - self.max_final_vocab, min_count, calc_min_count, self.effective_min_count - ) + logger.info( + "max_final_vocab=%d and min_count=%d resulted in calc_min_count=%d, effective_min_count=%d", + self.max_final_vocab, min_count, calc_min_count, self.effective_min_count + ) if not update: logger.info("Loading a fresh vocabulary") @@ -1365,8 +1665,9 @@ def add_null_word(self, wv): wv.vocab[word] = v def create_binary_tree(self, wv): - """Create a binary Huffman tree using stored vocabulary word counts. Frequent words - will have shorter binary codes. Called internally from `build_vocab()`. + """Create a `binary Huffman tree `_ using stored vocabulary + word counts. Frequent words will have shorter binary codes. + Called internally from :meth:`~gensim.models.word2vec.Word2VecVocab.build_vocab`. """ logger.info("constructing a huffman tree from %i words", len(wv.vocab)) @@ -1398,15 +1699,15 @@ def create_binary_tree(self, wv): logger.info("built huffman tree with maximum node depth %i", max_depth) def make_cum_table(self, wv, power=0.75, domain=2**31 - 1): - """Create a cumulative-distribution table using stored vocabulary word counts for - drawing random words in the negative-sampling training routines. + """Create a cumulative-distribution table using stored vocabulary word counts for drawing random words + in the negative-sampling training routines. + + To draw a word index, choose a random integer up to the maximum value in the table (cum_table[-1]), + then finding that integer's sorted insertion point (as if by `bisect_left` or `ndarray.searchsorted()`). + That insertion point is the drawn index, coming up in proportion equal to the increment at that slot. - To draw a word index, choose a random integer up to the maximum value in the - table (cum_table[-1]), then finding that integer's sorted insertion point - (as if by bisect_left or ndarray.searchsorted()). That insertion point is the - drawn index, coming up in proportion equal to the increment at that slot. + Called internally from :meth:`~gensim.models.word2vec.Word2VecVocab.build_vocab`. - Called internally from 'build_vocab()'. """ vocab_size = len(wv.index2word) self.cum_table = zeros(vocab_size, dtype=uint32) @@ -1423,6 +1724,7 @@ def make_cum_table(self, wv, power=0.75, domain=2**31 - 1): class Word2VecTrainables(utils.SaveLoad): + """Represents the inner shallow neural network used to train :class:`~gensim.models.word2vec.Word2Vec`.""" def __init__(self, vector_size=100, seed=1, hashfxn=hash): self.hashfxn = hashfxn self.layer1_size = vector_size @@ -1437,7 +1739,7 @@ def prepare_weights(self, hs, negative, wv, update=False, vocabulary=None): self.update_weights(hs, negative, wv) def seeded_vector(self, seed_string, vector_size): - """Create one 'random' vector (but deterministic by seed_string)""" + """Get a random vector (but deterministic by seed_string).""" # Note: built-in hash() may vary by Python version or even (in Py3.x) per launch once = random.RandomState(self.hashfxn(seed_string) & 0xffffffff) return (once.rand(vector_size) - 0.5) / vector_size @@ -1459,10 +1761,7 @@ def reset_weights(self, hs, negative, wv): self.vectors_lockf = ones(len(wv.vocab), dtype=REAL) # zeros suppress learning def update_weights(self, hs, negative, wv): - """ - Copy all the existing weights, and reset the weights for the newly - added vocabulary. - """ + """Copy all the existing weights, and reset the weights for the newly added vocabulary.""" logger.info("updating layer weights") gained_vocab = len(wv.vocab) - len(wv.vectors) newvectors = empty((gained_vocab, wv.vector_size), dtype=REAL) diff --git a/gensim/models/word2vec_inner.c b/gensim/models/word2vec_inner.c index bdb21349a2..a164655853 100644 --- a/gensim/models/word2vec_inner.c +++ b/gensim/models/word2vec_inner.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.27.3 */ +/* Generated by Cython 0.28.3 */ #define PY_SSIZE_T_CLEAN #include "Python.h" @@ -7,7 +7,7 @@ #elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.6+ or Python 3.3+. #else -#define CYTHON_ABI "0_27_3" +#define CYTHON_ABI "0_28_3" #define CYTHON_FUTURE_DIVISION 0 #include #ifndef offsetof @@ -183,6 +183,103 @@ #undef BASE #undef MASK #endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) #define Py_OptimizeFlag 0 #endif @@ -211,12 +308,12 @@ #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif -#if PY_VERSION_HEX < 0x030700A0 || !defined(METH_FASTCALL) +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif - typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject **args, Py_ssize_t nargs); - typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject **args, + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast @@ -228,6 +325,18 @@ #else #define __Pyx_PyFastCFunction_Check(func) 0 #endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif #if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x03060000 @@ -237,6 +346,36 @@ #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; // PyThread_create_key reports success always +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif // TSS (Thread Specific Storage) API #if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else @@ -249,6 +388,11 @@ #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif #if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ @@ -293,18 +437,6 @@ #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif -#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) - #define PyObject_Malloc(s) PyMem_Malloc(s) - #define PyObject_Free(p) PyMem_Free(p) - #define PyObject_Realloc(p) PyMem_Realloc(p) -#endif -#if CYTHON_COMPILING_IN_PYSTON - #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) -#else - #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) -#endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 @@ -321,6 +453,7 @@ #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact + #define PyObject_Unicode PyObject_Str #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) @@ -332,7 +465,11 @@ #ifndef PySet_CheckExact #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) #endif -#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type @@ -367,16 +504,10 @@ #define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t #endif #if PY_MAJOR_VERSION >= 3 - #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func)) + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : (Py_INCREF(func), func)) #else #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) #endif -#ifndef __has_attribute - #define __has_attribute(x) 0 -#endif -#ifndef __has_cpp_attribute - #define __has_cpp_attribute(x) 0 -#endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods @@ -394,96 +525,6 @@ unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif -#ifndef CYTHON_RESTRICT - #if defined(__GNUC__) - #define CYTHON_RESTRICT __restrict__ - #elif defined(_MSC_VER) && _MSC_VER >= 1400 - #define CYTHON_RESTRICT __restrict - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_RESTRICT restrict - #else - #define CYTHON_RESTRICT - #endif -#endif -#ifndef CYTHON_UNUSED -# if defined(__GNUC__) -# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -#endif -#ifndef CYTHON_MAYBE_UNUSED_VAR -# if defined(__cplusplus) - template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } -# else -# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) -# endif -#endif -#ifndef CYTHON_NCP_UNUSED -# if CYTHON_COMPILING_IN_CPYTHON -# define CYTHON_NCP_UNUSED -# else -# define CYTHON_NCP_UNUSED CYTHON_UNUSED -# endif -#endif -#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) -#ifdef _MSC_VER - #ifndef _MSC_STDINT_H_ - #if _MSC_VER < 1300 - typedef unsigned char uint8_t; - typedef unsigned int uint32_t; - #else - typedef unsigned __int8 uint8_t; - typedef unsigned __int32 uint32_t; - #endif - #endif -#else - #include -#endif -#ifndef CYTHON_FALLTHROUGH - #if defined(__cplusplus) && __cplusplus >= 201103L - #if __has_cpp_attribute(fallthrough) - #define CYTHON_FALLTHROUGH [[fallthrough]] - #elif __has_cpp_attribute(clang::fallthrough) - #define CYTHON_FALLTHROUGH [[clang::fallthrough]] - #elif __has_cpp_attribute(gnu::fallthrough) - #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] - #endif - #endif - #ifndef CYTHON_FALLTHROUGH - #if __has_attribute(fallthrough) - #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) - #else - #define CYTHON_FALLTHROUGH - #endif - #endif - #if defined(__clang__ ) && defined(__apple_build_version__) - #if __apple_build_version__ < 7000000 - #undef CYTHON_FALLTHROUGH - #define CYTHON_FALLTHROUGH - #endif - #endif -#endif - -#ifndef CYTHON_INLINE - #if defined(__clang__) - #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) - #elif defined(__GNUC__) - #define CYTHON_INLINE __inline__ - #elif defined(_MSC_VER) - #define CYTHON_INLINE __inline - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_INLINE inline - #else - #define CYTHON_INLINE - #endif -#endif #if defined(WIN32) || defined(MS_WINDOWS) #define _USE_MATH_DEFINES @@ -520,6 +561,7 @@ static CYTHON_INLINE float __PYX_NAN() { #define __PYX_HAVE__gensim__models__word2vec_inner #define __PYX_HAVE_API__gensim__models__word2vec_inner +/* Early includes */ #include "voidptr.h" #include #include @@ -610,7 +652,7 @@ static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) -#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False)) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ @@ -718,7 +760,7 @@ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } static PyObject *__pyx_m = NULL; static PyObject *__pyx_d; static PyObject *__pyx_b; -static PyObject *__pyx_cython_runtime; +static PyObject *__pyx_cython_runtime = NULL; static PyObject *__pyx_empty_tuple; static PyObject *__pyx_empty_bytes; static PyObject *__pyx_empty_unicode; @@ -768,7 +810,7 @@ static const char *__pyx_f[] = { #endif -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":743 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":730 * # in Cython to enable them only on the right systems. * * ctypedef npy_int8 int8_t # <<<<<<<<<<<<<< @@ -777,7 +819,7 @@ static const char *__pyx_f[] = { */ typedef npy_int8 __pyx_t_5numpy_int8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":731 * * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t # <<<<<<<<<<<<<< @@ -786,7 +828,7 @@ typedef npy_int8 __pyx_t_5numpy_int8_t; */ typedef npy_int16 __pyx_t_5numpy_int16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":732 * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t # <<<<<<<<<<<<<< @@ -795,7 +837,7 @@ typedef npy_int16 __pyx_t_5numpy_int16_t; */ typedef npy_int32 __pyx_t_5numpy_int32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":746 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":733 * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t * ctypedef npy_int64 int64_t # <<<<<<<<<<<<<< @@ -804,7 +846,7 @@ typedef npy_int32 __pyx_t_5numpy_int32_t; */ typedef npy_int64 __pyx_t_5numpy_int64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":750 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":737 * #ctypedef npy_int128 int128_t * * ctypedef npy_uint8 uint8_t # <<<<<<<<<<<<<< @@ -813,7 +855,7 @@ typedef npy_int64 __pyx_t_5numpy_int64_t; */ typedef npy_uint8 __pyx_t_5numpy_uint8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":751 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":738 * * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t # <<<<<<<<<<<<<< @@ -822,7 +864,7 @@ typedef npy_uint8 __pyx_t_5numpy_uint8_t; */ typedef npy_uint16 __pyx_t_5numpy_uint16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":752 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":739 * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t # <<<<<<<<<<<<<< @@ -831,7 +873,7 @@ typedef npy_uint16 __pyx_t_5numpy_uint16_t; */ typedef npy_uint32 __pyx_t_5numpy_uint32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":753 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":740 * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t * ctypedef npy_uint64 uint64_t # <<<<<<<<<<<<<< @@ -840,7 +882,7 @@ typedef npy_uint32 __pyx_t_5numpy_uint32_t; */ typedef npy_uint64 __pyx_t_5numpy_uint64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":757 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 * #ctypedef npy_uint128 uint128_t * * ctypedef npy_float32 float32_t # <<<<<<<<<<<<<< @@ -849,7 +891,7 @@ typedef npy_uint64 __pyx_t_5numpy_uint64_t; */ typedef npy_float32 __pyx_t_5numpy_float32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 * * ctypedef npy_float32 float32_t * ctypedef npy_float64 float64_t # <<<<<<<<<<<<<< @@ -858,7 +900,7 @@ typedef npy_float32 __pyx_t_5numpy_float32_t; */ typedef npy_float64 __pyx_t_5numpy_float64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":754 * # The int types are mapped a bit surprising -- * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t # <<<<<<<<<<<<<< @@ -867,7 +909,7 @@ typedef npy_float64 __pyx_t_5numpy_float64_t; */ typedef npy_long __pyx_t_5numpy_int_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":768 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":755 * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t * ctypedef npy_longlong long_t # <<<<<<<<<<<<<< @@ -876,7 +918,7 @@ typedef npy_long __pyx_t_5numpy_int_t; */ typedef npy_longlong __pyx_t_5numpy_long_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":756 * ctypedef npy_long int_t * ctypedef npy_longlong long_t * ctypedef npy_longlong longlong_t # <<<<<<<<<<<<<< @@ -885,7 +927,7 @@ typedef npy_longlong __pyx_t_5numpy_long_t; */ typedef npy_longlong __pyx_t_5numpy_longlong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 * ctypedef npy_longlong longlong_t * * ctypedef npy_ulong uint_t # <<<<<<<<<<<<<< @@ -894,7 +936,7 @@ typedef npy_longlong __pyx_t_5numpy_longlong_t; */ typedef npy_ulong __pyx_t_5numpy_uint_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":772 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":759 * * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t # <<<<<<<<<<<<<< @@ -903,7 +945,7 @@ typedef npy_ulong __pyx_t_5numpy_uint_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":760 * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t * ctypedef npy_ulonglong ulonglong_t # <<<<<<<<<<<<<< @@ -912,7 +954,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":762 * ctypedef npy_ulonglong ulonglong_t * * ctypedef npy_intp intp_t # <<<<<<<<<<<<<< @@ -921,7 +963,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; */ typedef npy_intp __pyx_t_5numpy_intp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":763 * * ctypedef npy_intp intp_t * ctypedef npy_uintp uintp_t # <<<<<<<<<<<<<< @@ -930,7 +972,7 @@ typedef npy_intp __pyx_t_5numpy_intp_t; */ typedef npy_uintp __pyx_t_5numpy_uintp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":765 * ctypedef npy_uintp uintp_t * * ctypedef npy_double float_t # <<<<<<<<<<<<<< @@ -939,7 +981,7 @@ typedef npy_uintp __pyx_t_5numpy_uintp_t; */ typedef npy_double __pyx_t_5numpy_float_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":766 * * ctypedef npy_double float_t * ctypedef npy_double double_t # <<<<<<<<<<<<<< @@ -948,7 +990,7 @@ typedef npy_double __pyx_t_5numpy_float_t; */ typedef npy_double __pyx_t_5numpy_double_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":780 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 * ctypedef npy_double float_t * ctypedef npy_double double_t * ctypedef npy_longdouble longdouble_t # <<<<<<<<<<<<<< @@ -992,7 +1034,7 @@ static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(do /*--- Type declarations ---*/ -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 * ctypedef npy_longdouble longdouble_t * * ctypedef npy_cfloat cfloat_t # <<<<<<<<<<<<<< @@ -1001,7 +1043,7 @@ static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(do */ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":783 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":770 * * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t # <<<<<<<<<<<<<< @@ -1010,7 +1052,7 @@ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; */ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t * ctypedef npy_clongdouble clongdouble_t # <<<<<<<<<<<<<< @@ -1019,7 +1061,7 @@ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; */ typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":786 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 * ctypedef npy_clongdouble clongdouble_t * * ctypedef npy_cdouble complex_t # <<<<<<<<<<<<<< @@ -1166,16 +1208,7 @@ typedef void (*__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr)(int const /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_getattro)) - return tp->tp_getattro(obj, attr_name); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_getattr)) - return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); -#endif - return PyObject_GetAttr(obj, attr_name); -} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif @@ -1211,6 +1244,35 @@ static CYTHON_INLINE int __Pyx_PySequence_ContainsTF(PyObject* item, PyObject* s return unlikely(result < 0) ? result : (result == (eq == Py_EQ)); } +/* GetItemInt.proto */ +#define __Pyx_GetItemInt(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ + (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ + __Pyx_GetItemInt_Fast(o, (Py_ssize_t)i, is_list, wraparound, boundscheck) :\ + (is_list ? (PyErr_SetString(PyExc_IndexError, "list index out of range"), (PyObject*)NULL) :\ + __Pyx_GetItemInt_Generic(o, to_py_func(i)))) +#define __Pyx_GetItemInt_List(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ + (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ + __Pyx_GetItemInt_List_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) :\ + (PyErr_SetString(PyExc_IndexError, "list index out of range"), (PyObject*)NULL)) +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i, + int wraparound, int boundscheck); +#define __Pyx_GetItemInt_Tuple(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck)\ + (__Pyx_fits_Py_ssize_t(i, type, is_signed) ?\ + __Pyx_GetItemInt_Tuple_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) :\ + (PyErr_SetString(PyExc_IndexError, "tuple index out of range"), (PyObject*)NULL)) +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i, + int wraparound, int boundscheck); +static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j); +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, + int is_list, int wraparound, int boundscheck); + +/* ObjectGetItem.proto */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key); +#else +#define __Pyx_PyObject_GetItem(obj, key) PyObject_GetItem(obj, key) +#endif + /* PyFunctionFastCall.proto */ #if CYTHON_FAST_PYCALL #define __Pyx_PyFunction_FastCall(func, args, nargs)\ @@ -1231,17 +1293,8 @@ static CYTHON_INLINE PyObject *__Pyx_PyCFunction_FastCall(PyObject *func, PyObje /* PyObjectSetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -#define __Pyx_PyObject_DelAttrStr(o,n) __Pyx_PyObject_SetAttrStr(o,n,NULL) -static CYTHON_INLINE int __Pyx_PyObject_SetAttrStr(PyObject* obj, PyObject* attr_name, PyObject* value) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_setattro)) - return tp->tp_setattro(obj, attr_name, value); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_setattr)) - return tp->tp_setattr(obj, PyString_AS_STRING(attr_name), value); -#endif - return PyObject_SetAttr(obj, attr_name, value); -} +#define __Pyx_PyObject_DelAttrStr(o,n) __Pyx_PyObject_SetAttrStr(o, n, NULL) +static CYTHON_INLINE int __Pyx_PyObject_SetAttrStr(PyObject* obj, PyObject* attr_name, PyObject* value); #else #define __Pyx_PyObject_DelAttrStr(o,n) PyObject_DelAttr(o,n) #define __Pyx_PyObject_SetAttrStr(o,n,v) PyObject_SetAttr(o,n,v) @@ -1285,26 +1338,24 @@ static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject /* RaiseException.proto */ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause); - -/* DictGetItem.proto */ -#if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY -static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { - PyObject *value; - value = PyDict_GetItemWithError(d, key); - if (unlikely(!value)) { - if (!PyErr_Occurred()) { - PyObject* args = PyTuple_Pack(1, key); - if (likely(args)) - PyErr_SetObject(PyExc_KeyError, args); - Py_XDECREF(args); - } - return NULL; - } - Py_INCREF(value); - return value; -} + +/* PyObjectCallMethO.proto */ +#if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg); +#endif + +/* PyObjectCallOneArg.proto */ +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg); + +/* DictGetItem.proto */ +#if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key); +#define __Pyx_PyObject_Dict_GetItem(obj, name)\ + (likely(PyDict_CheckExact(obj)) ?\ + __Pyx_PyDict_GetItem(obj, name) : PyObject_GetItem(obj, name)) #else - #define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyObject_Dict_GetItem(obj, name) PyObject_GetItem(obj, name) #endif /* RaiseTooManyValuesToUnpack.proto */ @@ -1352,14 +1403,6 @@ static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name); /* GetModuleGlobalName.proto */ static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name); -/* PyObjectCallMethO.proto */ -#if CYTHON_COMPILING_IN_CPYTHON -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg); -#endif - -/* PyObjectCallOneArg.proto */ -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg); - /* PyObjectCallNoArg.proto */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func); @@ -1532,6 +1575,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) #define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) #endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) /* CheckBinaryVersion.proto */ static int __Pyx_check_binary_version(void); @@ -1734,6 +1778,7 @@ static const char __pyx_k_numpy_core_multiarray_failed_to[] = "numpy.core.multia static const char __pyx_k_unknown_dtype_code_in_numpy_pxd[] = "unknown dtype code in numpy.pxd (%d)"; static const char __pyx_k_Format_string_allocated_too_shor[] = "Format string allocated too short, see comment in numpy.pxd"; static const char __pyx_k_Non_native_byte_order_not_suppor[] = "Non-native byte order not supported"; +static const char __pyx_k_Optimized_cython_functions_for_t[] = "Optimized cython functions for training :class:`~gensim.models.word2vec.Word2Vec` model."; static const char __pyx_k_gensim_models_word2vec_inner_pyx[] = "gensim/models/word2vec_inner.pyx"; static const char __pyx_k_ndarray_is_not_Fortran_contiguou[] = "ndarray is not Fortran contiguous"; static const char __pyx_k_numpy_core_umath_failed_to_impor[] = "numpy.core.umath failed to import"; @@ -1882,8 +1927,9 @@ static PyObject *__pyx_codeobj__18; static PyObject *__pyx_codeobj__20; static PyObject *__pyx_codeobj__22; static PyObject *__pyx_codeobj__24; +/* Late includes */ -/* "gensim/models/word2vec_inner.pyx":46 +/* "gensim/models/word2vec_inner.pyx":49 * * # for when fblas.sdot returns a double * cdef REAL_t our_dot_double(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -1894,7 +1940,7 @@ static PyObject *__pyx_codeobj__24; static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_14word2vec_inner_our_dot_double(int const *__pyx_v_N, float const *__pyx_v_X, int const *__pyx_v_incX, float const *__pyx_v_Y, int const *__pyx_v_incY) { __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_r; - /* "gensim/models/word2vec_inner.pyx":47 + /* "gensim/models/word2vec_inner.pyx":50 * # for when fblas.sdot returns a double * cdef REAL_t our_dot_double(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: * return dsdot(N, X, incX, Y, incY) # <<<<<<<<<<<<<< @@ -1904,7 +1950,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 __pyx_r = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)__pyx_v_6gensim_6models_14word2vec_inner_dsdot(__pyx_v_N, __pyx_v_X, __pyx_v_incX, __pyx_v_Y, __pyx_v_incY)); goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":46 + /* "gensim/models/word2vec_inner.pyx":49 * * # for when fblas.sdot returns a double * cdef REAL_t our_dot_double(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -1917,7 +1963,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":50 +/* "gensim/models/word2vec_inner.pyx":53 * * # for when fblas.sdot returns a float * cdef REAL_t our_dot_float(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -1928,7 +1974,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_14word2vec_inner_our_dot_float(int const *__pyx_v_N, float const *__pyx_v_X, int const *__pyx_v_incX, float const *__pyx_v_Y, int const *__pyx_v_incY) { __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_r; - /* "gensim/models/word2vec_inner.pyx":51 + /* "gensim/models/word2vec_inner.pyx":54 * # for when fblas.sdot returns a float * cdef REAL_t our_dot_float(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: * return sdot(N, X, incX, Y, incY) # <<<<<<<<<<<<<< @@ -1938,7 +1984,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 __pyx_r = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)__pyx_v_6gensim_6models_14word2vec_inner_sdot(__pyx_v_N, __pyx_v_X, __pyx_v_incX, __pyx_v_Y, __pyx_v_incY)); goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":50 + /* "gensim/models/word2vec_inner.pyx":53 * * # for when fblas.sdot returns a float * cdef REAL_t our_dot_float(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -1951,7 +1997,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":54 +/* "gensim/models/word2vec_inner.pyx":57 * * # for when no blas available * cdef REAL_t our_dot_noblas(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -1965,7 +2011,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_r; int __pyx_t_1; - /* "gensim/models/word2vec_inner.pyx":58 + /* "gensim/models/word2vec_inner.pyx":61 * cdef int i * cdef REAL_t a * a = 0.0 # <<<<<<<<<<<<<< @@ -1974,7 +2020,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 */ __pyx_v_a = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.0); - /* "gensim/models/word2vec_inner.pyx":59 + /* "gensim/models/word2vec_inner.pyx":62 * cdef REAL_t a * a = 0.0 * for i from 0 <= i < N[0] by 1: # <<<<<<<<<<<<<< @@ -1984,7 +2030,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 __pyx_t_1 = (__pyx_v_N[0]); for (__pyx_v_i = 0; __pyx_v_i < __pyx_t_1; __pyx_v_i+=1) { - /* "gensim/models/word2vec_inner.pyx":60 + /* "gensim/models/word2vec_inner.pyx":63 * a = 0.0 * for i from 0 <= i < N[0] by 1: * a += X[i] * Y[i] # <<<<<<<<<<<<<< @@ -1994,7 +2040,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 __pyx_v_a = (__pyx_v_a + ((__pyx_v_X[__pyx_v_i]) * (__pyx_v_Y[__pyx_v_i]))); } - /* "gensim/models/word2vec_inner.pyx":61 + /* "gensim/models/word2vec_inner.pyx":64 * for i from 0 <= i < N[0] by 1: * a += X[i] * Y[i] * return a # <<<<<<<<<<<<<< @@ -2004,7 +2050,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 __pyx_r = __pyx_v_a; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":54 + /* "gensim/models/word2vec_inner.pyx":57 * * # for when no blas available * cdef REAL_t our_dot_noblas(const int *N, const float *X, const int *incX, const float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -2017,7 +2063,7 @@ static __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_f_6gensim_6models_1 return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":64 +/* "gensim/models/word2vec_inner.pyx":67 * * # for when no blas available * cdef void our_saxpy_noblas(const int *N, const float *alpha, const float *X, const int *incX, float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -2029,7 +2075,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas(int const int __pyx_v_i; int __pyx_t_1; - /* "gensim/models/word2vec_inner.pyx":66 + /* "gensim/models/word2vec_inner.pyx":69 * cdef void our_saxpy_noblas(const int *N, const float *alpha, const float *X, const int *incX, float *Y, const int *incY) nogil: * cdef int i * for i from 0 <= i < N[0] by 1: # <<<<<<<<<<<<<< @@ -2039,17 +2085,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas(int const __pyx_t_1 = (__pyx_v_N[0]); for (__pyx_v_i = 0; __pyx_v_i < __pyx_t_1; __pyx_v_i+=1) { - /* "gensim/models/word2vec_inner.pyx":67 + /* "gensim/models/word2vec_inner.pyx":70 * cdef int i * for i from 0 <= i < N[0] by 1: * Y[i * (incY[0])] = (alpha[0]) * X[i * (incX[0])] + Y[i * (incY[0])] # <<<<<<<<<<<<<< * - * + * cdef void fast_sentence_sg_hs( */ (__pyx_v_Y[(__pyx_v_i * (__pyx_v_incY[0]))]) = (((__pyx_v_alpha[0]) * (__pyx_v_X[(__pyx_v_i * (__pyx_v_incX[0]))])) + (__pyx_v_Y[(__pyx_v_i * (__pyx_v_incY[0]))])); } - /* "gensim/models/word2vec_inner.pyx":64 + /* "gensim/models/word2vec_inner.pyx":67 * * # for when no blas available * cdef void our_saxpy_noblas(const int *N, const float *alpha, const float *X, const int *incX, float *Y, const int *incY) nogil: # <<<<<<<<<<<<<< @@ -2060,8 +2106,8 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas(int const /* function exit code */ } -/* "gensim/models/word2vec_inner.pyx":70 - * +/* "gensim/models/word2vec_inner.pyx":72 + * Y[i * (incY[0])] = (alpha[0]) * X[i * (incX[0])] + Y[i * (incY[0])] * * cdef void fast_sentence_sg_hs( # <<<<<<<<<<<<<< * const np.uint32_t *word_point, const np.uint8_t *word_code, const int codelen, @@ -2078,11 +2124,12 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_f_dot; __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_lprob; int __pyx_t_1; - PY_LONG_LONG __pyx_t_2; - int __pyx_t_3; + int __pyx_t_2; + PY_LONG_LONG __pyx_t_3; int __pyx_t_4; + int __pyx_t_5; - /* "gensim/models/word2vec_inner.pyx":77 + /* "gensim/models/word2vec_inner.pyx":113 * * cdef long long a, b * cdef long long row1 = word2_index * size, row2, sgn # <<<<<<<<<<<<<< @@ -2091,16 +2138,16 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_row1 = (__pyx_v_word2_index * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":80 + /* "gensim/models/word2vec_inner.pyx":116 * cdef REAL_t f, g, f_dot, lprob * * memset(work, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * for b in range(codelen): * row2 = word_point[b] * size */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":81 + /* "gensim/models/word2vec_inner.pyx":117 * * memset(work, 0, size * cython.sizeof(REAL_t)) * for b in range(codelen): # <<<<<<<<<<<<<< @@ -2108,10 +2155,11 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = __pyx_v_codelen; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_b = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_b = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":82 + /* "gensim/models/word2vec_inner.pyx":118 * memset(work, 0, size * cython.sizeof(REAL_t)) * for b in range(codelen): * row2 = word_point[b] * size # <<<<<<<<<<<<<< @@ -2120,7 +2168,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":83 + /* "gensim/models/word2vec_inner.pyx":119 * for b in range(codelen): * row2 = word_point[b] * size * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2129,25 +2177,25 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_f_dot = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), (&(__pyx_v_syn0[__pyx_v_row1])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":84 + /* "gensim/models/word2vec_inner.pyx":120 * row2 = word_point[b] * size * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L6_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L6_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":85 + /* "gensim/models/word2vec_inner.pyx":121 * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2156,7 +2204,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":84 + /* "gensim/models/word2vec_inner.pyx":120 * row2 = word_point[b] * size * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2165,7 +2213,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ } - /* "gensim/models/word2vec_inner.pyx":86 + /* "gensim/models/word2vec_inner.pyx":122 * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2174,7 +2222,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f_dot + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":87 + /* "gensim/models/word2vec_inner.pyx":123 * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha # <<<<<<<<<<<<<< @@ -2183,17 +2231,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_g = (((1 - (__pyx_v_word_code[__pyx_v_b])) - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/word2vec_inner.pyx":89 + /* "gensim/models/word2vec_inner.pyx":125 * g = (1 - word_code[b] - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot */ - __pyx_t_3 = ((__pyx_v__compute_loss == 1) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v__compute_loss == 1) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":90 + /* "gensim/models/word2vec_inner.pyx":126 * * if _compute_loss == 1: * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 # <<<<<<<<<<<<<< @@ -2202,7 +2250,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_sgn = __Pyx_pow_long(-1L, ((long)(__pyx_v_word_code[__pyx_v_b]))); - /* "gensim/models/word2vec_inner.pyx":91 + /* "gensim/models/word2vec_inner.pyx":127 * if _compute_loss == 1: * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot # <<<<<<<<<<<<<< @@ -2211,25 +2259,25 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_lprob = ((-1LL * __pyx_v_sgn) * __pyx_v_f_dot); - /* "gensim/models/word2vec_inner.pyx":92 + /* "gensim/models/word2vec_inner.pyx":128 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot * if lprob <= -MAX_EXP or lprob >= MAX_EXP: # <<<<<<<<<<<<<< * continue * lprob = LOG_TABLE[((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_lprob <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_lprob <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L10_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_lprob >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_lprob >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L10_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":93 + /* "gensim/models/word2vec_inner.pyx":129 * lprob = -1*sgn*f_dot * if lprob <= -MAX_EXP or lprob >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2238,7 +2286,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":92 + /* "gensim/models/word2vec_inner.pyx":128 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot * if lprob <= -MAX_EXP or lprob >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2247,7 +2295,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ } - /* "gensim/models/word2vec_inner.pyx":94 + /* "gensim/models/word2vec_inner.pyx":130 * if lprob <= -MAX_EXP or lprob >= MAX_EXP: * continue * lprob = LOG_TABLE[((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2256,7 +2304,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_lprob = (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[((int)((__pyx_v_lprob + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":95 + /* "gensim/models/word2vec_inner.pyx":131 * continue * lprob = LOG_TABLE[((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * _running_training_loss_param[0] = _running_training_loss_param[0] - lprob # <<<<<<<<<<<<<< @@ -2265,7 +2313,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ (__pyx_v__running_training_loss_param[0]) = ((__pyx_v__running_training_loss_param[0]) - __pyx_v_lprob); - /* "gensim/models/word2vec_inner.pyx":89 + /* "gensim/models/word2vec_inner.pyx":125 * g = (1 - word_code[b] - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< @@ -2274,7 +2322,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ } - /* "gensim/models/word2vec_inner.pyx":97 + /* "gensim/models/word2vec_inner.pyx":133 * _running_training_loss_param[0] = _running_training_loss_param[0] - lprob * * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2283,7 +2331,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":98 + /* "gensim/models/word2vec_inner.pyx":134 * * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * our_saxpy(&size, &g, &syn0[row1], &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -2294,7 +2342,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t __pyx_L3_continue:; } - /* "gensim/models/word2vec_inner.pyx":100 + /* "gensim/models/word2vec_inner.pyx":136 * our_saxpy(&size, &g, &syn0[row1], &ONE, &syn1[row2], &ONE) * * our_saxpy(&size, &word_locks[word2_index], work, &ONE, &syn0[row1], &ONE) # <<<<<<<<<<<<<< @@ -2303,8 +2351,8 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&(__pyx_v_word_locks[__pyx_v_word2_index])), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn0[__pyx_v_row1])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":70 - * + /* "gensim/models/word2vec_inner.pyx":72 + * Y[i * (incY[0])] = (alpha[0]) * X[i * (incX[0])] + Y[i * (incY[0])] * * cdef void fast_sentence_sg_hs( # <<<<<<<<<<<<<< * const np.uint32_t *word_point, const np.uint8_t *word_code, const int codelen, @@ -2314,7 +2362,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs(__pyx_t /* function exit code */ } -/* "gensim/models/word2vec_inner.pyx":104 +/* "gensim/models/word2vec_inner.pyx":140 * * # to support random draws from negative-sampling cum_table * cdef inline unsigned long long bisect_left(np.uint32_t *a, unsigned long long x, unsigned long long lo, unsigned long long hi) nogil: # <<<<<<<<<<<<<< @@ -2327,7 +2375,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in unsigned PY_LONG_LONG __pyx_r; int __pyx_t_1; - /* "gensim/models/word2vec_inner.pyx":106 + /* "gensim/models/word2vec_inner.pyx":142 * cdef inline unsigned long long bisect_left(np.uint32_t *a, unsigned long long x, unsigned long long lo, unsigned long long hi) nogil: * cdef unsigned long long mid * while hi > lo: # <<<<<<<<<<<<<< @@ -2338,7 +2386,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in __pyx_t_1 = ((__pyx_v_hi > __pyx_v_lo) != 0); if (!__pyx_t_1) break; - /* "gensim/models/word2vec_inner.pyx":107 + /* "gensim/models/word2vec_inner.pyx":143 * cdef unsigned long long mid * while hi > lo: * mid = (lo + hi) >> 1 # <<<<<<<<<<<<<< @@ -2347,7 +2395,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in */ __pyx_v_mid = ((__pyx_v_lo + __pyx_v_hi) >> 1); - /* "gensim/models/word2vec_inner.pyx":108 + /* "gensim/models/word2vec_inner.pyx":144 * while hi > lo: * mid = (lo + hi) >> 1 * if a[mid] >= x: # <<<<<<<<<<<<<< @@ -2357,7 +2405,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in __pyx_t_1 = (((__pyx_v_a[__pyx_v_mid]) >= __pyx_v_x) != 0); if (__pyx_t_1) { - /* "gensim/models/word2vec_inner.pyx":109 + /* "gensim/models/word2vec_inner.pyx":145 * mid = (lo + hi) >> 1 * if a[mid] >= x: * hi = mid # <<<<<<<<<<<<<< @@ -2366,7 +2414,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in */ __pyx_v_hi = __pyx_v_mid; - /* "gensim/models/word2vec_inner.pyx":108 + /* "gensim/models/word2vec_inner.pyx":144 * while hi > lo: * mid = (lo + hi) >> 1 * if a[mid] >= x: # <<<<<<<<<<<<<< @@ -2376,7 +2424,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in goto __pyx_L5; } - /* "gensim/models/word2vec_inner.pyx":111 + /* "gensim/models/word2vec_inner.pyx":147 * hi = mid * else: * lo = mid + 1 # <<<<<<<<<<<<<< @@ -2389,7 +2437,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in __pyx_L5:; } - /* "gensim/models/word2vec_inner.pyx":112 + /* "gensim/models/word2vec_inner.pyx":148 * else: * lo = mid + 1 * return lo # <<<<<<<<<<<<<< @@ -2399,7 +2447,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in __pyx_r = __pyx_v_lo; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":104 + /* "gensim/models/word2vec_inner.pyx":140 * * # to support random draws from negative-sampling cum_table * cdef inline unsigned long long bisect_left(np.uint32_t *a, unsigned long long x, unsigned long long lo, unsigned long long hi) nogil: # <<<<<<<<<<<<<< @@ -2412,7 +2460,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":116 +/* "gensim/models/word2vec_inner.pyx":152 * # this quick & dirty RNG apparently matches Java's (non-Secure)Random * # note this function side-effects next_random to set up the next number * cdef inline unsigned long long random_int32(unsigned long long *next_random) nogil: # <<<<<<<<<<<<<< @@ -2424,7 +2472,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in unsigned PY_LONG_LONG __pyx_v_this_random; unsigned PY_LONG_LONG __pyx_r; - /* "gensim/models/word2vec_inner.pyx":117 + /* "gensim/models/word2vec_inner.pyx":153 * # note this function side-effects next_random to set up the next number * cdef inline unsigned long long random_int32(unsigned long long *next_random) nogil: * cdef unsigned long long this_random = next_random[0] >> 16 # <<<<<<<<<<<<<< @@ -2433,7 +2481,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in */ __pyx_v_this_random = ((__pyx_v_next_random[0]) >> 16); - /* "gensim/models/word2vec_inner.pyx":118 + /* "gensim/models/word2vec_inner.pyx":154 * cdef inline unsigned long long random_int32(unsigned long long *next_random) nogil: * cdef unsigned long long this_random = next_random[0] >> 16 * next_random[0] = (next_random[0] * 25214903917ULL + 11) & 281474976710655ULL # <<<<<<<<<<<<<< @@ -2442,7 +2490,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in */ (__pyx_v_next_random[0]) = ((((__pyx_v_next_random[0]) * ((unsigned PY_LONG_LONG)25214903917ULL)) + 11) & 281474976710655ULL); - /* "gensim/models/word2vec_inner.pyx":119 + /* "gensim/models/word2vec_inner.pyx":155 * cdef unsigned long long this_random = next_random[0] >> 16 * next_random[0] = (next_random[0] * 25214903917ULL + 11) & 281474976710655ULL * return this_random # <<<<<<<<<<<<<< @@ -2452,7 +2500,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in __pyx_r = __pyx_v_this_random; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":116 + /* "gensim/models/word2vec_inner.pyx":152 * # this quick & dirty RNG apparently matches Java's (non-Secure)Random * # note this function side-effects next_random to set up the next number * cdef inline unsigned long long random_int32(unsigned long long *next_random) nogil: # <<<<<<<<<<<<<< @@ -2465,7 +2513,7 @@ static CYTHON_INLINE unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_in return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":121 +/* "gensim/models/word2vec_inner.pyx":157 * return this_random * * cdef unsigned long long fast_sentence_sg_neg( # <<<<<<<<<<<<<< @@ -2486,13 +2534,14 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente int __pyx_v_d; unsigned PY_LONG_LONG __pyx_r; long __pyx_t_1; - int __pyx_t_2; + long __pyx_t_2; int __pyx_t_3; int __pyx_t_4; - __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_t_5; + int __pyx_t_5; + __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":129 - * + /* "gensim/models/word2vec_inner.pyx":207 + * """ * cdef long long a * cdef long long row1 = word2_index * size, row2 # <<<<<<<<<<<<<< * cdef unsigned long long modulo = 281474976710655ULL @@ -2500,7 +2549,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_row1 = (__pyx_v_word2_index * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":130 + /* "gensim/models/word2vec_inner.pyx":208 * cdef long long a * cdef long long row1 = word2_index * size, row2 * cdef unsigned long long modulo = 281474976710655ULL # <<<<<<<<<<<<<< @@ -2509,16 +2558,16 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_modulo = 281474976710655ULL; - /* "gensim/models/word2vec_inner.pyx":135 + /* "gensim/models/word2vec_inner.pyx":213 * cdef int d * * memset(work, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * * for d in range(negative+1): */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":137 + /* "gensim/models/word2vec_inner.pyx":215 * memset(work, 0, size * cython.sizeof(REAL_t)) * * for d in range(negative+1): # <<<<<<<<<<<<<< @@ -2526,20 +2575,21 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente * target_index = word_index */ __pyx_t_1 = (__pyx_v_negative + 1); - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_d = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_d = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":138 + /* "gensim/models/word2vec_inner.pyx":216 * * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< * target_index = word_index * label = ONEF */ - __pyx_t_3 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":139 + /* "gensim/models/word2vec_inner.pyx":217 * for d in range(negative+1): * if d == 0: * target_index = word_index # <<<<<<<<<<<<<< @@ -2548,7 +2598,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_target_index = __pyx_v_word_index; - /* "gensim/models/word2vec_inner.pyx":140 + /* "gensim/models/word2vec_inner.pyx":218 * if d == 0: * target_index = word_index * label = ONEF # <<<<<<<<<<<<<< @@ -2557,7 +2607,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_label = __pyx_v_6gensim_6models_14word2vec_inner_ONEF; - /* "gensim/models/word2vec_inner.pyx":138 + /* "gensim/models/word2vec_inner.pyx":216 * * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< @@ -2567,7 +2617,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente goto __pyx_L5; } - /* "gensim/models/word2vec_inner.pyx":142 + /* "gensim/models/word2vec_inner.pyx":220 * label = ONEF * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) # <<<<<<<<<<<<<< @@ -2577,7 +2627,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente /*else*/ { __pyx_v_target_index = __pyx_f_6gensim_6models_14word2vec_inner_bisect_left(__pyx_v_cum_table, ((__pyx_v_next_random >> 16) % (__pyx_v_cum_table[(__pyx_v_cum_table_len - 1)])), 0, __pyx_v_cum_table_len); - /* "gensim/models/word2vec_inner.pyx":143 + /* "gensim/models/word2vec_inner.pyx":221 * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo # <<<<<<<<<<<<<< @@ -2586,17 +2636,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_next_random = (((__pyx_v_next_random * ((unsigned PY_LONG_LONG)25214903917ULL)) + 11) & __pyx_v_modulo); - /* "gensim/models/word2vec_inner.pyx":144 + /* "gensim/models/word2vec_inner.pyx":222 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: # <<<<<<<<<<<<<< * continue * label = 0.0 */ - __pyx_t_3 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":145 + /* "gensim/models/word2vec_inner.pyx":223 * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: * continue # <<<<<<<<<<<<<< @@ -2605,7 +2655,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":144 + /* "gensim/models/word2vec_inner.pyx":222 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: # <<<<<<<<<<<<<< @@ -2614,7 +2664,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":146 + /* "gensim/models/word2vec_inner.pyx":224 * if target_index == word_index: * continue * label = 0.0 # <<<<<<<<<<<<<< @@ -2625,7 +2675,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente } __pyx_L5:; - /* "gensim/models/word2vec_inner.pyx":148 + /* "gensim/models/word2vec_inner.pyx":226 * label = 0.0 * * row2 = target_index * size # <<<<<<<<<<<<<< @@ -2634,7 +2684,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_row2 = (__pyx_v_target_index * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":149 + /* "gensim/models/word2vec_inner.pyx":227 * * row2 = target_index * size * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -2643,25 +2693,25 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_f_dot = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), (&(__pyx_v_syn0[__pyx_v_row1])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":150 + /* "gensim/models/word2vec_inner.pyx":228 * row2 = target_index * size * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1neg[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L8_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L8_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":151 + /* "gensim/models/word2vec_inner.pyx":229 * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1neg[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2670,7 +2720,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":150 + /* "gensim/models/word2vec_inner.pyx":228 * row2 = target_index * size * f_dot = our_dot(&size, &syn0[row1], &ONE, &syn1neg[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2679,7 +2729,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":152 + /* "gensim/models/word2vec_inner.pyx":230 * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2688,7 +2738,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f_dot + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":153 + /* "gensim/models/word2vec_inner.pyx":231 * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha # <<<<<<<<<<<<<< @@ -2697,17 +2747,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_g = ((__pyx_v_label - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/word2vec_inner.pyx":155 + /* "gensim/models/word2vec_inner.pyx":233 * g = (label - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: */ - __pyx_t_3 = ((__pyx_v__compute_loss == 1) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v__compute_loss == 1) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":156 + /* "gensim/models/word2vec_inner.pyx":234 * * if _compute_loss == 1: * f_dot = (f_dot if d == 0 else -f_dot) # <<<<<<<<<<<<<< @@ -2715,31 +2765,31 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente * continue */ if (((__pyx_v_d == 0) != 0)) { - __pyx_t_5 = __pyx_v_f_dot; + __pyx_t_6 = __pyx_v_f_dot; } else { - __pyx_t_5 = (-__pyx_v_f_dot); + __pyx_t_6 = (-__pyx_v_f_dot); } - __pyx_v_f_dot = __pyx_t_5; + __pyx_v_f_dot = __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":157 + /* "gensim/models/word2vec_inner.pyx":235 * if _compute_loss == 1: * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< * continue * log_e_f_dot = LOG_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L12_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L12_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":158 + /* "gensim/models/word2vec_inner.pyx":236 * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -2748,7 +2798,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":157 + /* "gensim/models/word2vec_inner.pyx":235 * if _compute_loss == 1: * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< @@ -2757,7 +2807,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":159 + /* "gensim/models/word2vec_inner.pyx":237 * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue * log_e_f_dot = LOG_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -2766,7 +2816,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_log_e_f_dot = (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[((int)((__pyx_v_f_dot + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":160 + /* "gensim/models/word2vec_inner.pyx":238 * continue * log_e_f_dot = LOG_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * _running_training_loss_param[0] = _running_training_loss_param[0] - log_e_f_dot # <<<<<<<<<<<<<< @@ -2775,7 +2825,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ (__pyx_v__running_training_loss_param[0]) = ((__pyx_v__running_training_loss_param[0]) - __pyx_v_log_e_f_dot); - /* "gensim/models/word2vec_inner.pyx":155 + /* "gensim/models/word2vec_inner.pyx":233 * g = (label - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< @@ -2784,7 +2834,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":162 + /* "gensim/models/word2vec_inner.pyx":240 * _running_training_loss_param[0] = _running_training_loss_param[0] - log_e_f_dot * * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -2793,7 +2843,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":163 + /* "gensim/models/word2vec_inner.pyx":241 * * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * our_saxpy(&size, &g, &syn0[row1], &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -2804,7 +2854,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente __pyx_L3_continue:; } - /* "gensim/models/word2vec_inner.pyx":165 + /* "gensim/models/word2vec_inner.pyx":243 * our_saxpy(&size, &g, &syn0[row1], &ONE, &syn1neg[row2], &ONE) * * our_saxpy(&size, &word_locks[word2_index], work, &ONE, &syn0[row1], &ONE) # <<<<<<<<<<<<<< @@ -2813,7 +2863,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&(__pyx_v_word_locks[__pyx_v_word2_index])), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn0[__pyx_v_row1])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":167 + /* "gensim/models/word2vec_inner.pyx":245 * our_saxpy(&size, &word_locks[word2_index], work, &ONE, &syn0[row1], &ONE) * * return next_random # <<<<<<<<<<<<<< @@ -2823,7 +2873,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente __pyx_r = __pyx_v_next_random; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":121 + /* "gensim/models/word2vec_inner.pyx":157 * return this_random * * cdef unsigned long long fast_sentence_sg_neg( # <<<<<<<<<<<<<< @@ -2836,7 +2886,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":170 +/* "gensim/models/word2vec_inner.pyx":248 * * * cdef void fast_sentence_cbow_hs( # <<<<<<<<<<<<<< @@ -2858,10 +2908,11 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx int __pyx_t_1; int __pyx_t_2; int __pyx_t_3; - PY_LONG_LONG __pyx_t_4; - int __pyx_t_5; + int __pyx_t_4; + PY_LONG_LONG __pyx_t_5; + int __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":179 + /* "gensim/models/word2vec_inner.pyx":300 * cdef long long a, b * cdef long long row2, sgn * cdef REAL_t f, g, count, inv_count = 1.0, f_dot, lprob # <<<<<<<<<<<<<< @@ -2870,16 +2921,16 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_inv_count = 1.0; - /* "gensim/models/word2vec_inner.pyx":182 + /* "gensim/models/word2vec_inner.pyx":303 * cdef int m * * memset(neu1, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * count = 0.0 * for m in range(j, k): */ - memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":183 + /* "gensim/models/word2vec_inner.pyx":304 * * memset(neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 # <<<<<<<<<<<<<< @@ -2888,7 +2939,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_count = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.0); - /* "gensim/models/word2vec_inner.pyx":184 + /* "gensim/models/word2vec_inner.pyx":305 * memset(neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 * for m in range(j, k): # <<<<<<<<<<<<<< @@ -2896,20 +2947,21 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":185 + /* "gensim/models/word2vec_inner.pyx":306 * count = 0.0 * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< * continue * else: */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":186 + /* "gensim/models/word2vec_inner.pyx":307 * for m in range(j, k): * if m == i: * continue # <<<<<<<<<<<<<< @@ -2918,7 +2970,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":185 + /* "gensim/models/word2vec_inner.pyx":306 * count = 0.0 * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -2927,7 +2979,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":188 + /* "gensim/models/word2vec_inner.pyx":309 * continue * else: * count += ONEF # <<<<<<<<<<<<<< @@ -2937,7 +2989,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx /*else*/ { __pyx_v_count = (__pyx_v_count + __pyx_v_6gensim_6models_14word2vec_inner_ONEF); - /* "gensim/models/word2vec_inner.pyx":189 + /* "gensim/models/word2vec_inner.pyx":310 * else: * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) # <<<<<<<<<<<<<< @@ -2949,17 +3001,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx __pyx_L3_continue:; } - /* "gensim/models/word2vec_inner.pyx":190 + /* "gensim/models/word2vec_inner.pyx":311 * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< * inv_count = ONEF/count * if cbow_mean: */ - __pyx_t_3 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":191 + /* "gensim/models/word2vec_inner.pyx":312 * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): * inv_count = ONEF/count # <<<<<<<<<<<<<< @@ -2968,7 +3020,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_inv_count = (__pyx_v_6gensim_6models_14word2vec_inner_ONEF / __pyx_v_count); - /* "gensim/models/word2vec_inner.pyx":190 + /* "gensim/models/word2vec_inner.pyx":311 * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< @@ -2977,17 +3029,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":192 + /* "gensim/models/word2vec_inner.pyx":313 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< * sscal(&size, &inv_count, neu1, &ONE) # (does this need BLAS-variants like saxpy?) * */ - __pyx_t_3 = (__pyx_v_cbow_mean != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_cbow_mean != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":193 + /* "gensim/models/word2vec_inner.pyx":314 * inv_count = ONEF/count * if cbow_mean: * sscal(&size, &inv_count, neu1, &ONE) # (does this need BLAS-variants like saxpy?) # <<<<<<<<<<<<<< @@ -2996,7 +3048,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v_neu1, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":192 + /* "gensim/models/word2vec_inner.pyx":313 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< @@ -3005,16 +3057,16 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":195 + /* "gensim/models/word2vec_inner.pyx":316 * sscal(&size, &inv_count, neu1, &ONE) # (does this need BLAS-variants like saxpy?) * * memset(work, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * for b in range(codelens[i]): * row2 = word_point[b] * size */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":196 + /* "gensim/models/word2vec_inner.pyx":317 * * memset(work, 0, size * cython.sizeof(REAL_t)) * for b in range(codelens[i]): # <<<<<<<<<<<<<< @@ -3022,10 +3074,11 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = (__pyx_v_codelens[__pyx_v_i]); - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_1; __pyx_t_4+=1) { - __pyx_v_b = __pyx_t_4; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_2; __pyx_t_5+=1) { + __pyx_v_b = __pyx_t_5; - /* "gensim/models/word2vec_inner.pyx":197 + /* "gensim/models/word2vec_inner.pyx":318 * memset(work, 0, size * cython.sizeof(REAL_t)) * for b in range(codelens[i]): * row2 = word_point[b] * size # <<<<<<<<<<<<<< @@ -3034,7 +3087,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":198 + /* "gensim/models/word2vec_inner.pyx":319 * for b in range(codelens[i]): * row2 = word_point[b] * size * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -3043,25 +3096,25 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_f_dot = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":199 + /* "gensim/models/word2vec_inner.pyx":320 * row2 = word_point[b] * size * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_5) { + __pyx_t_6 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_6) { } else { - __pyx_t_3 = __pyx_t_5; + __pyx_t_4 = __pyx_t_6; goto __pyx_L11_bool_binop_done; } - __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_5; + __pyx_t_6 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_6; __pyx_L11_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":200 + /* "gensim/models/word2vec_inner.pyx":321 * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -3070,7 +3123,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":199 + /* "gensim/models/word2vec_inner.pyx":320 * row2 = word_point[b] * size * f_dot = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< @@ -3079,7 +3132,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":201 + /* "gensim/models/word2vec_inner.pyx":322 * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -3088,7 +3141,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f_dot + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":202 + /* "gensim/models/word2vec_inner.pyx":323 * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (1 - word_code[b] - f) * alpha # <<<<<<<<<<<<<< @@ -3097,17 +3150,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_g = (((1 - (__pyx_v_word_code[__pyx_v_b])) - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/word2vec_inner.pyx":204 + /* "gensim/models/word2vec_inner.pyx":325 * g = (1 - word_code[b] - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot */ - __pyx_t_3 = ((__pyx_v__compute_loss == 1) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v__compute_loss == 1) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":205 + /* "gensim/models/word2vec_inner.pyx":326 * * if _compute_loss == 1: * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 # <<<<<<<<<<<<<< @@ -3116,7 +3169,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_sgn = __Pyx_pow_long(-1L, ((long)(__pyx_v_word_code[__pyx_v_b]))); - /* "gensim/models/word2vec_inner.pyx":206 + /* "gensim/models/word2vec_inner.pyx":327 * if _compute_loss == 1: * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot # <<<<<<<<<<<<<< @@ -3125,25 +3178,25 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_lprob = ((-1LL * __pyx_v_sgn) * __pyx_v_f_dot); - /* "gensim/models/word2vec_inner.pyx":207 + /* "gensim/models/word2vec_inner.pyx":328 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot * if lprob <= -MAX_EXP or lprob >= MAX_EXP: # <<<<<<<<<<<<<< * continue * lprob = LOG_TABLE[((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_5 = ((__pyx_v_lprob <= -6.0) != 0); - if (!__pyx_t_5) { + __pyx_t_6 = ((__pyx_v_lprob <= -6.0) != 0); + if (!__pyx_t_6) { } else { - __pyx_t_3 = __pyx_t_5; + __pyx_t_4 = __pyx_t_6; goto __pyx_L15_bool_binop_done; } - __pyx_t_5 = ((__pyx_v_lprob >= 6.0) != 0); - __pyx_t_3 = __pyx_t_5; + __pyx_t_6 = ((__pyx_v_lprob >= 6.0) != 0); + __pyx_t_4 = __pyx_t_6; __pyx_L15_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":208 + /* "gensim/models/word2vec_inner.pyx":329 * lprob = -1*sgn*f_dot * if lprob <= -MAX_EXP or lprob >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -3152,7 +3205,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":207 + /* "gensim/models/word2vec_inner.pyx":328 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * lprob = -1*sgn*f_dot * if lprob <= -MAX_EXP or lprob >= MAX_EXP: # <<<<<<<<<<<<<< @@ -3161,7 +3214,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":209 + /* "gensim/models/word2vec_inner.pyx":330 * if lprob <= -MAX_EXP or lprob >= MAX_EXP: * continue * lprob = LOG_TABLE[((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -3170,7 +3223,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_lprob = (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[((int)((__pyx_v_lprob + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":210 + /* "gensim/models/word2vec_inner.pyx":331 * continue * lprob = LOG_TABLE[((lprob + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * _running_training_loss_param[0] = _running_training_loss_param[0] - lprob # <<<<<<<<<<<<<< @@ -3179,7 +3232,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ (__pyx_v__running_training_loss_param[0]) = ((__pyx_v__running_training_loss_param[0]) - __pyx_v_lprob); - /* "gensim/models/word2vec_inner.pyx":204 + /* "gensim/models/word2vec_inner.pyx":325 * g = (1 - word_code[b] - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< @@ -3188,7 +3241,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":212 + /* "gensim/models/word2vec_inner.pyx":333 * _running_training_loss_param[0] = _running_training_loss_param[0] - lprob * * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -3197,7 +3250,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":213 + /* "gensim/models/word2vec_inner.pyx":334 * * our_saxpy(&size, &g, &syn1[row2], &ONE, work, &ONE) * our_saxpy(&size, &g, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -3208,17 +3261,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx __pyx_L8_continue:; } - /* "gensim/models/word2vec_inner.pyx":215 + /* "gensim/models/word2vec_inner.pyx":336 * our_saxpy(&size, &g, neu1, &ONE, &syn1[row2], &ONE) * * if not cbow_mean: # divide error over summed window vectors # <<<<<<<<<<<<<< * sscal(&size, &inv_count, work, &ONE) # (does this need BLAS-variants like saxpy?) * */ - __pyx_t_3 = ((!(__pyx_v_cbow_mean != 0)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((!(__pyx_v_cbow_mean != 0)) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":216 + /* "gensim/models/word2vec_inner.pyx":337 * * if not cbow_mean: # divide error over summed window vectors * sscal(&size, &inv_count, work, &ONE) # (does this need BLAS-variants like saxpy?) # <<<<<<<<<<<<<< @@ -3227,7 +3280,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":215 + /* "gensim/models/word2vec_inner.pyx":336 * our_saxpy(&size, &g, neu1, &ONE, &syn1[row2], &ONE) * * if not cbow_mean: # divide error over summed window vectors # <<<<<<<<<<<<<< @@ -3236,7 +3289,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":218 + /* "gensim/models/word2vec_inner.pyx":339 * sscal(&size, &inv_count, work, &ONE) # (does this need BLAS-variants like saxpy?) * * for m in range(j, k): # <<<<<<<<<<<<<< @@ -3244,20 +3297,21 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":219 + /* "gensim/models/word2vec_inner.pyx":340 * * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< * continue * else: */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":220 + /* "gensim/models/word2vec_inner.pyx":341 * for m in range(j, k): * if m == i: * continue # <<<<<<<<<<<<<< @@ -3266,7 +3320,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ goto __pyx_L18_continue; - /* "gensim/models/word2vec_inner.pyx":219 + /* "gensim/models/word2vec_inner.pyx":340 * * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -3275,7 +3329,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx */ } - /* "gensim/models/word2vec_inner.pyx":222 + /* "gensim/models/word2vec_inner.pyx":343 * continue * else: * our_saxpy(&size, &word_locks[indexes[m]], work, &ONE, &syn0[indexes[m] * size], &ONE) # <<<<<<<<<<<<<< @@ -3288,7 +3342,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx __pyx_L18_continue:; } - /* "gensim/models/word2vec_inner.pyx":170 + /* "gensim/models/word2vec_inner.pyx":248 * * * cdef void fast_sentence_cbow_hs( # <<<<<<<<<<<<<< @@ -3299,7 +3353,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs(__pyx /* function exit code */ } -/* "gensim/models/word2vec_inner.pyx":225 +/* "gensim/models/word2vec_inner.pyx":346 * * * cdef unsigned long long fast_sentence_cbow_neg( # <<<<<<<<<<<<<< @@ -3325,11 +3379,13 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente int __pyx_t_1; int __pyx_t_2; int __pyx_t_3; - long __pyx_t_4; - int __pyx_t_5; - __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_t_6; + int __pyx_t_4; + long __pyx_t_5; + long __pyx_t_6; + int __pyx_t_7; + __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_t_8; - /* "gensim/models/word2vec_inner.pyx":234 + /* "gensim/models/word2vec_inner.pyx":403 * cdef long long a * cdef long long row2 * cdef unsigned long long modulo = 281474976710655ULL # <<<<<<<<<<<<<< @@ -3338,7 +3394,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_modulo = 281474976710655ULL; - /* "gensim/models/word2vec_inner.pyx":235 + /* "gensim/models/word2vec_inner.pyx":404 * cdef long long row2 * cdef unsigned long long modulo = 281474976710655ULL * cdef REAL_t f, g, count, inv_count = 1.0, label, log_e_f_dot, f_dot # <<<<<<<<<<<<<< @@ -3347,7 +3403,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_inv_count = 1.0; - /* "gensim/models/word2vec_inner.pyx":239 + /* "gensim/models/word2vec_inner.pyx":408 * cdef int d, m * * word_index = indexes[i] # <<<<<<<<<<<<<< @@ -3356,16 +3412,16 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_word_index = (__pyx_v_indexes[__pyx_v_i]); - /* "gensim/models/word2vec_inner.pyx":241 + /* "gensim/models/word2vec_inner.pyx":410 * word_index = indexes[i] * * memset(neu1, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * count = 0.0 * for m in range(j, k): */ - memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":242 + /* "gensim/models/word2vec_inner.pyx":411 * * memset(neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 # <<<<<<<<<<<<<< @@ -3374,7 +3430,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_count = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.0); - /* "gensim/models/word2vec_inner.pyx":243 + /* "gensim/models/word2vec_inner.pyx":412 * memset(neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 * for m in range(j, k): # <<<<<<<<<<<<<< @@ -3382,20 +3438,21 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":244 + /* "gensim/models/word2vec_inner.pyx":413 * count = 0.0 * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< * continue * else: */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":245 + /* "gensim/models/word2vec_inner.pyx":414 * for m in range(j, k): * if m == i: * continue # <<<<<<<<<<<<<< @@ -3404,7 +3461,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":244 + /* "gensim/models/word2vec_inner.pyx":413 * count = 0.0 * for m in range(j, k): * if m == i: # <<<<<<<<<<<<<< @@ -3413,7 +3470,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":247 + /* "gensim/models/word2vec_inner.pyx":416 * continue * else: * count += ONEF # <<<<<<<<<<<<<< @@ -3423,7 +3480,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente /*else*/ { __pyx_v_count = (__pyx_v_count + __pyx_v_6gensim_6models_14word2vec_inner_ONEF); - /* "gensim/models/word2vec_inner.pyx":248 + /* "gensim/models/word2vec_inner.pyx":417 * else: * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) # <<<<<<<<<<<<<< @@ -3435,17 +3492,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente __pyx_L3_continue:; } - /* "gensim/models/word2vec_inner.pyx":249 + /* "gensim/models/word2vec_inner.pyx":418 * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< * inv_count = ONEF/count * if cbow_mean: */ - __pyx_t_3 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":250 + /* "gensim/models/word2vec_inner.pyx":419 * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): * inv_count = ONEF/count # <<<<<<<<<<<<<< @@ -3454,7 +3511,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_inv_count = (__pyx_v_6gensim_6models_14word2vec_inner_ONEF / __pyx_v_count); - /* "gensim/models/word2vec_inner.pyx":249 + /* "gensim/models/word2vec_inner.pyx":418 * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< @@ -3463,17 +3520,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":251 + /* "gensim/models/word2vec_inner.pyx":420 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< * sscal(&size, &inv_count, neu1, &ONE) # (does this need BLAS-variants like saxpy?) * */ - __pyx_t_3 = (__pyx_v_cbow_mean != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_cbow_mean != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":252 + /* "gensim/models/word2vec_inner.pyx":421 * inv_count = ONEF/count * if cbow_mean: * sscal(&size, &inv_count, neu1, &ONE) # (does this need BLAS-variants like saxpy?) # <<<<<<<<<<<<<< @@ -3482,7 +3539,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v_neu1, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":251 + /* "gensim/models/word2vec_inner.pyx":420 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< @@ -3491,37 +3548,38 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":254 + /* "gensim/models/word2vec_inner.pyx":423 * sscal(&size, &inv_count, neu1, &ONE) # (does this need BLAS-variants like saxpy?) * * memset(work, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * * for d in range(negative+1): */ - memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_work, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":256 + /* "gensim/models/word2vec_inner.pyx":425 * memset(work, 0, size * cython.sizeof(REAL_t)) * * for d in range(negative+1): # <<<<<<<<<<<<<< * if d == 0: * target_index = word_index */ - __pyx_t_4 = (__pyx_v_negative + 1); - for (__pyx_t_1 = 0; __pyx_t_1 < __pyx_t_4; __pyx_t_1+=1) { + __pyx_t_5 = (__pyx_v_negative + 1); + __pyx_t_6 = __pyx_t_5; + for (__pyx_t_1 = 0; __pyx_t_1 < __pyx_t_6; __pyx_t_1+=1) { __pyx_v_d = __pyx_t_1; - /* "gensim/models/word2vec_inner.pyx":257 + /* "gensim/models/word2vec_inner.pyx":426 * * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< * target_index = word_index * label = ONEF */ - __pyx_t_3 = ((__pyx_v_d == 0) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_d == 0) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":258 + /* "gensim/models/word2vec_inner.pyx":427 * for d in range(negative+1): * if d == 0: * target_index = word_index # <<<<<<<<<<<<<< @@ -3530,7 +3588,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_target_index = __pyx_v_word_index; - /* "gensim/models/word2vec_inner.pyx":259 + /* "gensim/models/word2vec_inner.pyx":428 * if d == 0: * target_index = word_index * label = ONEF # <<<<<<<<<<<<<< @@ -3539,7 +3597,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_label = __pyx_v_6gensim_6models_14word2vec_inner_ONEF; - /* "gensim/models/word2vec_inner.pyx":257 + /* "gensim/models/word2vec_inner.pyx":426 * * for d in range(negative+1): * if d == 0: # <<<<<<<<<<<<<< @@ -3549,7 +3607,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente goto __pyx_L10; } - /* "gensim/models/word2vec_inner.pyx":261 + /* "gensim/models/word2vec_inner.pyx":430 * label = ONEF * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) # <<<<<<<<<<<<<< @@ -3559,7 +3617,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente /*else*/ { __pyx_v_target_index = __pyx_f_6gensim_6models_14word2vec_inner_bisect_left(__pyx_v_cum_table, ((__pyx_v_next_random >> 16) % (__pyx_v_cum_table[(__pyx_v_cum_table_len - 1)])), 0, __pyx_v_cum_table_len); - /* "gensim/models/word2vec_inner.pyx":262 + /* "gensim/models/word2vec_inner.pyx":431 * else: * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo # <<<<<<<<<<<<<< @@ -3568,17 +3626,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_next_random = (((__pyx_v_next_random * ((unsigned PY_LONG_LONG)25214903917ULL)) + 11) & __pyx_v_modulo); - /* "gensim/models/word2vec_inner.pyx":263 + /* "gensim/models/word2vec_inner.pyx":432 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: # <<<<<<<<<<<<<< * continue * label = 0.0 */ - __pyx_t_3 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_target_index == __pyx_v_word_index) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":264 + /* "gensim/models/word2vec_inner.pyx":433 * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: * continue # <<<<<<<<<<<<<< @@ -3587,7 +3645,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":263 + /* "gensim/models/word2vec_inner.pyx":432 * target_index = bisect_left(cum_table, (next_random >> 16) % cum_table[cum_table_len-1], 0, cum_table_len) * next_random = (next_random * 25214903917ULL + 11) & modulo * if target_index == word_index: # <<<<<<<<<<<<<< @@ -3596,7 +3654,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":265 + /* "gensim/models/word2vec_inner.pyx":434 * if target_index == word_index: * continue * label = 0.0 # <<<<<<<<<<<<<< @@ -3607,7 +3665,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente } __pyx_L10:; - /* "gensim/models/word2vec_inner.pyx":267 + /* "gensim/models/word2vec_inner.pyx":436 * label = 0.0 * * row2 = target_index * size # <<<<<<<<<<<<<< @@ -3616,7 +3674,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_row2 = (__pyx_v_target_index * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":268 + /* "gensim/models/word2vec_inner.pyx":437 * * row2 = target_index * size * f_dot = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -3625,25 +3683,25 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_f_dot = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":269 + /* "gensim/models/word2vec_inner.pyx":438 * row2 = target_index * size * f_dot = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_5) { + __pyx_t_7 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_7) { } else { - __pyx_t_3 = __pyx_t_5; + __pyx_t_4 = __pyx_t_7; goto __pyx_L13_bool_binop_done; } - __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_5; + __pyx_t_7 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_7; __pyx_L13_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":270 + /* "gensim/models/word2vec_inner.pyx":439 * f_dot = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -3652,7 +3710,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":269 + /* "gensim/models/word2vec_inner.pyx":438 * row2 = target_index * size * f_dot = our_dot(&size, neu1, &ONE, &syn1neg[row2], &ONE) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< @@ -3661,7 +3719,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":271 + /* "gensim/models/word2vec_inner.pyx":440 * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -3670,7 +3728,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[((int)((__pyx_v_f_dot + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":272 + /* "gensim/models/word2vec_inner.pyx":441 * continue * f = EXP_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * g = (label - f) * alpha # <<<<<<<<<<<<<< @@ -3679,17 +3737,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_g = ((__pyx_v_label - __pyx_v_f) * __pyx_v_alpha); - /* "gensim/models/word2vec_inner.pyx":274 + /* "gensim/models/word2vec_inner.pyx":443 * g = (label - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: */ - __pyx_t_3 = ((__pyx_v__compute_loss == 1) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v__compute_loss == 1) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":275 + /* "gensim/models/word2vec_inner.pyx":444 * * if _compute_loss == 1: * f_dot = (f_dot if d == 0 else -f_dot) # <<<<<<<<<<<<<< @@ -3697,31 +3755,31 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente * continue */ if (((__pyx_v_d == 0) != 0)) { - __pyx_t_6 = __pyx_v_f_dot; + __pyx_t_8 = __pyx_v_f_dot; } else { - __pyx_t_6 = (-__pyx_v_f_dot); + __pyx_t_8 = (-__pyx_v_f_dot); } - __pyx_v_f_dot = __pyx_t_6; + __pyx_v_f_dot = __pyx_t_8; - /* "gensim/models/word2vec_inner.pyx":276 + /* "gensim/models/word2vec_inner.pyx":445 * if _compute_loss == 1: * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< * continue * log_e_f_dot = LOG_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_5 = ((__pyx_v_f_dot <= -6.0) != 0); - if (!__pyx_t_5) { + __pyx_t_7 = ((__pyx_v_f_dot <= -6.0) != 0); + if (!__pyx_t_7) { } else { - __pyx_t_3 = __pyx_t_5; + __pyx_t_4 = __pyx_t_7; goto __pyx_L17_bool_binop_done; } - __pyx_t_5 = ((__pyx_v_f_dot >= 6.0) != 0); - __pyx_t_3 = __pyx_t_5; + __pyx_t_7 = ((__pyx_v_f_dot >= 6.0) != 0); + __pyx_t_4 = __pyx_t_7; __pyx_L17_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":277 + /* "gensim/models/word2vec_inner.pyx":446 * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -3730,7 +3788,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":276 + /* "gensim/models/word2vec_inner.pyx":445 * if _compute_loss == 1: * f_dot = (f_dot if d == 0 else -f_dot) * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: # <<<<<<<<<<<<<< @@ -3739,7 +3797,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":278 + /* "gensim/models/word2vec_inner.pyx":447 * if f_dot <= -MAX_EXP or f_dot >= MAX_EXP: * continue * log_e_f_dot = LOG_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -3748,7 +3806,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_log_e_f_dot = (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[((int)((__pyx_v_f_dot + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":279 + /* "gensim/models/word2vec_inner.pyx":448 * continue * log_e_f_dot = LOG_TABLE[((f_dot + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * _running_training_loss_param[0] = _running_training_loss_param[0] - log_e_f_dot # <<<<<<<<<<<<<< @@ -3757,7 +3815,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ (__pyx_v__running_training_loss_param[0]) = ((__pyx_v__running_training_loss_param[0]) - __pyx_v_log_e_f_dot); - /* "gensim/models/word2vec_inner.pyx":274 + /* "gensim/models/word2vec_inner.pyx":443 * g = (label - f) * alpha * * if _compute_loss == 1: # <<<<<<<<<<<<<< @@ -3766,7 +3824,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":281 + /* "gensim/models/word2vec_inner.pyx":450 * _running_training_loss_param[0] = _running_training_loss_param[0] - log_e_f_dot * * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) # <<<<<<<<<<<<<< @@ -3775,7 +3833,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy((&__pyx_v_size), (&__pyx_v_g), (&(__pyx_v_syn1neg[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":282 + /* "gensim/models/word2vec_inner.pyx":451 * * our_saxpy(&size, &g, &syn1neg[row2], &ONE, work, &ONE) * our_saxpy(&size, &g, neu1, &ONE, &syn1neg[row2], &ONE) # <<<<<<<<<<<<<< @@ -3786,17 +3844,17 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente __pyx_L8_continue:; } - /* "gensim/models/word2vec_inner.pyx":284 + /* "gensim/models/word2vec_inner.pyx":453 * our_saxpy(&size, &g, neu1, &ONE, &syn1neg[row2], &ONE) * * if not cbow_mean: # divide error over summed window vectors # <<<<<<<<<<<<<< * sscal(&size, &inv_count, work, &ONE) # (does this need BLAS-variants like saxpy?) * */ - __pyx_t_3 = ((!(__pyx_v_cbow_mean != 0)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((!(__pyx_v_cbow_mean != 0)) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":285 + /* "gensim/models/word2vec_inner.pyx":454 * * if not cbow_mean: # divide error over summed window vectors * sscal(&size, &inv_count, work, &ONE) # (does this need BLAS-variants like saxpy?) # <<<<<<<<<<<<<< @@ -3805,7 +3863,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v_work, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":284 + /* "gensim/models/word2vec_inner.pyx":453 * our_saxpy(&size, &g, neu1, &ONE, &syn1neg[row2], &ONE) * * if not cbow_mean: # divide error over summed window vectors # <<<<<<<<<<<<<< @@ -3814,7 +3872,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":287 + /* "gensim/models/word2vec_inner.pyx":456 * sscal(&size, &inv_count, work, &ONE) # (does this need BLAS-variants like saxpy?) * * for m in range(j,k): # <<<<<<<<<<<<<< @@ -3822,20 +3880,21 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":288 + /* "gensim/models/word2vec_inner.pyx":457 * * for m in range(j,k): * if m == i: # <<<<<<<<<<<<<< * continue * else: */ - __pyx_t_3 = ((__pyx_v_m == __pyx_v_i) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":289 + /* "gensim/models/word2vec_inner.pyx":458 * for m in range(j,k): * if m == i: * continue # <<<<<<<<<<<<<< @@ -3844,7 +3903,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ goto __pyx_L20_continue; - /* "gensim/models/word2vec_inner.pyx":288 + /* "gensim/models/word2vec_inner.pyx":457 * * for m in range(j,k): * if m == i: # <<<<<<<<<<<<<< @@ -3853,7 +3912,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente */ } - /* "gensim/models/word2vec_inner.pyx":291 + /* "gensim/models/word2vec_inner.pyx":460 * continue * else: * our_saxpy(&size, &word_locks[indexes[m]], work, &ONE, &syn0[indexes[m]*size], &ONE) # <<<<<<<<<<<<<< @@ -3866,7 +3925,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente __pyx_L20_continue:; } - /* "gensim/models/word2vec_inner.pyx":293 + /* "gensim/models/word2vec_inner.pyx":462 * our_saxpy(&size, &word_locks[indexes[m]], work, &ONE, &syn0[indexes[m]*size], &ONE) * * return next_random # <<<<<<<<<<<<<< @@ -3876,7 +3935,7 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente __pyx_r = __pyx_v_next_random; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":225 + /* "gensim/models/word2vec_inner.pyx":346 * * * cdef unsigned long long fast_sentence_cbow_neg( # <<<<<<<<<<<<<< @@ -3889,17 +3948,18 @@ static unsigned PY_LONG_LONG __pyx_f_6gensim_6models_14word2vec_inner_fast_sente return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":296 +/* "gensim/models/word2vec_inner.pyx":465 * * * def train_batch_sg(model, sentences, alpha, _work, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a batch of sentences. + * */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_1train_batch_sg(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_1train_batch_sg = {"train_batch_sg", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_1train_batch_sg, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_14word2vec_inner_train_batch_sg[] = "train_batch_sg(model, sentences, alpha, _work, compute_loss)\nUpdate skip-gram model by training on a batch of sentences.\n\n Called internally from :meth:`~gensim.models.word2vec.Word2Vec.train`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.word2Vec.Word2Vec`\n The Word2Vec model instance to train.\n sentences : iterable of list of str\n The corpus used to train the model.\n alpha : float\n The learning rate\n _work : np.ndarray\n Private working memory for each worker.\n compute_loss : bool\n Whether or not the training loss should be computed in this batch.\n\n Returns\n -------\n int\n Number of words in the vocabulary actually used for training (They already existed in the vocabulary\n and were not discarded by negative sampling).\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_1train_batch_sg = {"train_batch_sg", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_1train_batch_sg, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_14word2vec_inner_train_batch_sg}; static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_1train_batch_sg(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_sentences = 0; @@ -3932,35 +3992,35 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_1train_batch_sg(PyObj kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 1); __PYX_ERR(0, 296, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 1); __PYX_ERR(0, 465, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 2); __PYX_ERR(0, 296, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 2); __PYX_ERR(0, 465, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 3); __PYX_ERR(0, 296, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 3); __PYX_ERR(0, 465, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: - if (likely((values[4] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_compute_loss)) != 0)) kw_args--; + if (likely((values[4] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_compute_loss)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 4); __PYX_ERR(0, 296, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, 4); __PYX_ERR(0, 465, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_batch_sg") < 0)) __PYX_ERR(0, 296, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_batch_sg") < 0)) __PYX_ERR(0, 465, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 5) { goto __pyx_L5_argtuple_error; @@ -3979,7 +4039,7 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_1train_batch_sg(PyObj } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 296, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_sg", 1, 5, 5, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 465, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.word2vec_inner.train_batch_sg", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -4052,62 +4112,63 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON int __pyx_t_20; int __pyx_t_21; int __pyx_t_22; + int __pyx_t_23; + int __pyx_t_24; + int __pyx_t_25; __Pyx_RefNannySetupContext("train_batch_sg", 0); - /* "gensim/models/word2vec_inner.pyx":297 + /* "gensim/models/word2vec_inner.pyx":490 * - * def train_batch_sg(model, sentences, alpha, _work, compute_loss): + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 297, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 490, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 297, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 490, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":298 - * def train_batch_sg(model, sentences, alpha, _work, compute_loss): + /* "gensim/models/word2vec_inner.pyx":491 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 298, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 491, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 298, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 491, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":299 + /* "gensim/models/word2vec_inner.pyx":492 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * - * cdef int _compute_loss = (1 if compute_loss == True else 0) + * cdef int _compute_loss = (1 if compute_loss else 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 492, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 492, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 492, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 299, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 492, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":301 + /* "gensim/models/word2vec_inner.pyx":494 * cdef int sample = (model.vocabulary.sample != 0) * - * cdef int _compute_loss = (1 if compute_loss == True else 0) # <<<<<<<<<<<<<< + * cdef int _compute_loss = (1 if compute_loss else 0) # <<<<<<<<<<<<<< * cdef REAL_t _running_training_loss = model.running_training_loss * */ - __pyx_t_1 = PyObject_RichCompare(__pyx_v_compute_loss, Py_True, Py_EQ); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 301, __pyx_L1_error) - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_t_1); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 301, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_compute_loss); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 494, __pyx_L1_error) if (__pyx_t_4) { __pyx_t_2 = 1; } else { @@ -4115,91 +4176,91 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON } __pyx_v__compute_loss = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":302 + /* "gensim/models/word2vec_inner.pyx":495 * - * cdef int _compute_loss = (1 if compute_loss == True else 0) + * cdef int _compute_loss = (1 if compute_loss else 0) * cdef REAL_t _running_training_loss = model.running_training_loss # <<<<<<<<<<<<<< * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 302, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 495, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_t_1); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 302, __pyx_L1_error) + __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_t_1); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 495, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v__running_training_loss = __pyx_t_5; - /* "gensim/models/word2vec_inner.pyx":304 + /* "gensim/models/word2vec_inner.pyx":497 * cdef REAL_t _running_training_loss = model.running_training_loss * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) # <<<<<<<<<<<<<< * cdef REAL_t *word_locks = (np.PyArray_DATA(model.trainables.vectors_lockf)) * cdef REAL_t *work */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 304, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 497, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 304, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 497, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 304, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 497, __pyx_L1_error) __pyx_v_syn0 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":305 + /* "gensim/models/word2vec_inner.pyx":498 * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) * cdef REAL_t *word_locks = (np.PyArray_DATA(model.trainables.vectors_lockf)) # <<<<<<<<<<<<<< * cdef REAL_t *work * cdef REAL_t _alpha = alpha */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 305, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 498, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 305, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 498, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 305, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 498, __pyx_L1_error) __pyx_v_word_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":307 + /* "gensim/models/word2vec_inner.pyx":500 * cdef REAL_t *word_locks = (np.PyArray_DATA(model.trainables.vectors_lockf)) * cdef REAL_t *work * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int size = model.wv.vector_size * */ - __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 307, __pyx_L1_error) + __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 500, __pyx_L1_error) __pyx_v__alpha = __pyx_t_5; - /* "gensim/models/word2vec_inner.pyx":308 + /* "gensim/models/word2vec_inner.pyx":501 * cdef REAL_t *work * cdef REAL_t _alpha = alpha * cdef int size = model.wv.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_SENTENCE_LEN] */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 501, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 501, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 308, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 501, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":314 + /* "gensim/models/word2vec_inner.pyx":507 * cdef np.uint32_t reduced_windows[MAX_SENTENCE_LEN] * cdef int sentence_idx[MAX_SENTENCE_LEN + 1] * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 314, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 314, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 507, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":317 + /* "gensim/models/word2vec_inner.pyx":510 * * cdef int i, j, k * cdef int effective_words = 0, effective_sentences = 0 # <<<<<<<<<<<<<< @@ -4209,7 +4270,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_v_effective_words = 0; __pyx_v_effective_sentences = 0; - /* "gensim/models/word2vec_inner.pyx":332 + /* "gensim/models/word2vec_inner.pyx":525 * cdef unsigned long long next_random * * if hs: # <<<<<<<<<<<<<< @@ -4219,23 +4280,23 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = (__pyx_v_hs != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":333 + /* "gensim/models/word2vec_inner.pyx":526 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 333, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 526, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 333, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 526, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 333, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 526, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":332 + /* "gensim/models/word2vec_inner.pyx":525 * cdef unsigned long long next_random * * if hs: # <<<<<<<<<<<<<< @@ -4244,7 +4305,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":335 + /* "gensim/models/word2vec_inner.pyx":528 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -4254,55 +4315,55 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = (__pyx_v_negative != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":336 + /* "gensim/models/word2vec_inner.pyx":529 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 336, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 529, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 336, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 529, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 336, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 529, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":337 + /* "gensim/models/word2vec_inner.pyx":530 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 337, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 530, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 337, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 530, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 337, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 530, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":338 + /* "gensim/models/word2vec_inner.pyx":531 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 338, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 531, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 338, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 531, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 338, __pyx_L1_error) + __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 531, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":335 + /* "gensim/models/word2vec_inner.pyx":528 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -4311,7 +4372,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":339 + /* "gensim/models/word2vec_inner.pyx":532 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -4329,41 +4390,41 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_L6_bool_binop_done:; if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":340 + /* "gensim/models/word2vec_inner.pyx":533 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_next_random = __pyx_t_9; - /* "gensim/models/word2vec_inner.pyx":339 + /* "gensim/models/word2vec_inner.pyx":532 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -4372,32 +4433,32 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":343 + /* "gensim/models/word2vec_inner.pyx":536 * * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) # <<<<<<<<<<<<<< * * # prepare C structures so we can go "full C" and release the Python GIL */ - if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 343, __pyx_L1_error) + if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 536, __pyx_L1_error) __pyx_v_work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__work))); - /* "gensim/models/word2vec_inner.pyx":346 + /* "gensim/models/word2vec_inner.pyx":539 * * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 346, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 539, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 346, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 539, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_vlookup = __pyx_t_3; __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":347 + /* "gensim/models/word2vec_inner.pyx":540 * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 # <<<<<<<<<<<<<< @@ -4406,7 +4467,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ (__pyx_v_sentence_idx[0]) = 0; - /* "gensim/models/word2vec_inner.pyx":348 + /* "gensim/models/word2vec_inner.pyx":541 * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: # <<<<<<<<<<<<<< @@ -4417,26 +4478,26 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_3 = __pyx_v_sentences; __Pyx_INCREF(__pyx_t_3); __pyx_t_6 = 0; __pyx_t_10 = NULL; } else { - __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 348, __pyx_L1_error) + __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 541, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 348, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 541, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_10)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 348, __pyx_L1_error) + __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 541, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 348, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 541, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 348, __pyx_L1_error) + __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 541, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 348, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 541, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } @@ -4446,7 +4507,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 348, __pyx_L1_error) + else __PYX_ERR(0, 541, __pyx_L1_error) } break; } @@ -4455,18 +4516,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_sent, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/word2vec_inner.pyx":349 + /* "gensim/models/word2vec_inner.pyx":542 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: */ - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 349, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 542, __pyx_L1_error) __pyx_t_7 = ((!__pyx_t_4) != 0); if (__pyx_t_7) { - /* "gensim/models/word2vec_inner.pyx":350 + /* "gensim/models/word2vec_inner.pyx":543 * for sent in sentences: * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged # <<<<<<<<<<<<<< @@ -4475,7 +4536,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":349 + /* "gensim/models/word2vec_inner.pyx":542 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< @@ -4484,7 +4545,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":351 + /* "gensim/models/word2vec_inner.pyx":544 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -4495,26 +4556,26 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_8 = __pyx_v_sent; __Pyx_INCREF(__pyx_t_8); __pyx_t_11 = 0; __pyx_t_12 = NULL; } else { - __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 351, __pyx_L1_error) + __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 351, __pyx_L1_error) + __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 544, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_12)) { if (likely(PyList_CheckExact(__pyx_t_8))) { if (__pyx_t_11 >= PyList_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 351, __pyx_L1_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 544, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 351, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_11 >= PyTuple_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 351, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 544, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 351, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -4524,7 +4585,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 351, __pyx_L1_error) + else __PYX_ERR(0, 544, __pyx_L1_error) } break; } @@ -4533,16 +4594,16 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":352 + /* "gensim/models/word2vec_inner.pyx":545 * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: * word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window */ - __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 352, __pyx_L1_error) + __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 545, __pyx_L1_error) if ((__pyx_t_7 != 0)) { - __pyx_t_13 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 352, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 545, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __pyx_t_1 = __pyx_t_13; __pyx_t_13 = 0; @@ -4553,7 +4614,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __Pyx_XDECREF_SET(__pyx_v_word, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":353 + /* "gensim/models/word2vec_inner.pyx":546 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -4564,7 +4625,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = (__pyx_t_7 != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":354 + /* "gensim/models/word2vec_inner.pyx":547 * word = vlookup[token] if token in vlookup else None * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window # <<<<<<<<<<<<<< @@ -4573,7 +4634,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ goto __pyx_L11_continue; - /* "gensim/models/word2vec_inner.pyx":353 + /* "gensim/models/word2vec_inner.pyx":546 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -4582,7 +4643,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":355 + /* "gensim/models/word2vec_inner.pyx":548 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -4595,20 +4656,20 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = __pyx_t_7; goto __pyx_L15_bool_binop_done; } - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 355, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 548, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 355, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 548, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 355, __pyx_L1_error) + __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 548, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; - __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 355, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 548, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __pyx_t_4 = __pyx_t_7; __pyx_L15_bool_binop_done:; if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":356 + /* "gensim/models/word2vec_inner.pyx":549 * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -4617,7 +4678,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ goto __pyx_L11_continue; - /* "gensim/models/word2vec_inner.pyx":355 + /* "gensim/models/word2vec_inner.pyx":548 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -4626,20 +4687,20 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":357 + /* "gensim/models/word2vec_inner.pyx":550 * if sample and word.sample_int < random_int32(&next_random): * continue * indexes[effective_words] = word.index # <<<<<<<<<<<<<< * if hs: * codelens[effective_words] = len(word.code) */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 357, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 550, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 357, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 550, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; (__pyx_v_indexes[__pyx_v_effective_words]) = __pyx_t_15; - /* "gensim/models/word2vec_inner.pyx":358 + /* "gensim/models/word2vec_inner.pyx":551 * continue * indexes[effective_words] = word.index * if hs: # <<<<<<<<<<<<<< @@ -4649,46 +4710,46 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = (__pyx_v_hs != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":359 + /* "gensim/models/word2vec_inner.pyx":552 * indexes[effective_words] = word.index * if hs: * codelens[effective_words] = len(word.code) # <<<<<<<<<<<<<< * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 359, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 552, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_16 = PyObject_Length(__pyx_t_14); if (unlikely(__pyx_t_16 == ((Py_ssize_t)-1))) __PYX_ERR(0, 359, __pyx_L1_error) + __pyx_t_16 = PyObject_Length(__pyx_t_14); if (unlikely(__pyx_t_16 == ((Py_ssize_t)-1))) __PYX_ERR(0, 552, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; (__pyx_v_codelens[__pyx_v_effective_words]) = ((int)__pyx_t_16); - /* "gensim/models/word2vec_inner.pyx":360 + /* "gensim/models/word2vec_inner.pyx":553 * if hs: * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) # <<<<<<<<<<<<<< * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 360, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 553, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 360, __pyx_L1_error) + if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 553, __pyx_L1_error) (__pyx_v_codes[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_14))); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":361 + /* "gensim/models/word2vec_inner.pyx":554 * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) # <<<<<<<<<<<<<< * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 361, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 554, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 361, __pyx_L1_error) + if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 554, __pyx_L1_error) (__pyx_v_points[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_14))); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":358 + /* "gensim/models/word2vec_inner.pyx":551 * continue * indexes[effective_words] = word.index * if hs: # <<<<<<<<<<<<<< @@ -4697,7 +4758,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":362 + /* "gensim/models/word2vec_inner.pyx":555 * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 # <<<<<<<<<<<<<< @@ -4706,7 +4767,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_effective_words = (__pyx_v_effective_words + 1); - /* "gensim/models/word2vec_inner.pyx":363 + /* "gensim/models/word2vec_inner.pyx":556 * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -4716,7 +4777,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = ((__pyx_v_effective_words == 0x2710) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":364 + /* "gensim/models/word2vec_inner.pyx":557 * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -4725,7 +4786,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ goto __pyx_L12_break; - /* "gensim/models/word2vec_inner.pyx":363 + /* "gensim/models/word2vec_inner.pyx":556 * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -4734,7 +4795,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":351 + /* "gensim/models/word2vec_inner.pyx":544 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -4746,7 +4807,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_L12_break:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/word2vec_inner.pyx":369 + /* "gensim/models/word2vec_inner.pyx":562 * # across sentence boundaries. * # indices of sentence number X are between tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_14)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 569, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; for (;;) { @@ -4887,17 +4948,17 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON if (likely(PyList_CheckExact(__pyx_t_14))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_14)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyList_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_t_3 = PyList_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 569, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 569, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_14)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 569, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 376, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 569, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } @@ -4907,7 +4968,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 376, __pyx_L1_error) + else __PYX_ERR(0, 569, __pyx_L1_error) } break; } @@ -4918,17 +4979,17 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_v_i = __pyx_t_2; __pyx_t_2 = (__pyx_t_2 + 1); - /* "gensim/models/word2vec_inner.pyx":377 + /* "gensim/models/word2vec_inner.pyx":570 * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): * reduced_windows[i] = item # <<<<<<<<<<<<<< * * # release GIL & train on all sentences */ - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 377, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 570, __pyx_L1_error) (__pyx_v_reduced_windows[__pyx_v_i]) = __pyx_t_15; - /* "gensim/models/word2vec_inner.pyx":376 + /* "gensim/models/word2vec_inner.pyx":569 * * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): # <<<<<<<<<<<<<< @@ -4938,7 +4999,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON } __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":380 + /* "gensim/models/word2vec_inner.pyx":573 * * # release GIL & train on all sentences * with nogil: # <<<<<<<<<<<<<< @@ -4953,7 +5014,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON #endif /*try:*/ { - /* "gensim/models/word2vec_inner.pyx":381 + /* "gensim/models/word2vec_inner.pyx":574 * # release GIL & train on all sentences * with nogil: * for sent_idx in range(effective_sentences): # <<<<<<<<<<<<<< @@ -4961,10 +5022,11 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON * idx_end = sentence_idx[sent_idx + 1] */ __pyx_t_2 = __pyx_v_effective_sentences; - for (__pyx_t_17 = 0; __pyx_t_17 < __pyx_t_2; __pyx_t_17+=1) { - __pyx_v_sent_idx = __pyx_t_17; + __pyx_t_17 = __pyx_t_2; + for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_17; __pyx_t_19+=1) { + __pyx_v_sent_idx = __pyx_t_19; - /* "gensim/models/word2vec_inner.pyx":382 + /* "gensim/models/word2vec_inner.pyx":575 * with nogil: * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] # <<<<<<<<<<<<<< @@ -4973,7 +5035,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_idx_start = (__pyx_v_sentence_idx[__pyx_v_sent_idx]); - /* "gensim/models/word2vec_inner.pyx":383 + /* "gensim/models/word2vec_inner.pyx":576 * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] # <<<<<<<<<<<<<< @@ -4982,18 +5044,19 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_idx_end = (__pyx_v_sentence_idx[(__pyx_v_sent_idx + 1)]); - /* "gensim/models/word2vec_inner.pyx":384 + /* "gensim/models/word2vec_inner.pyx":577 * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): # <<<<<<<<<<<<<< * j = i - window + reduced_windows[i] * if j < idx_start: */ - __pyx_t_19 = __pyx_v_idx_end; - for (__pyx_t_20 = __pyx_v_idx_start; __pyx_t_20 < __pyx_t_19; __pyx_t_20+=1) { - __pyx_v_i = __pyx_t_20; + __pyx_t_20 = __pyx_v_idx_end; + __pyx_t_21 = __pyx_t_20; + for (__pyx_t_22 = __pyx_v_idx_start; __pyx_t_22 < __pyx_t_21; __pyx_t_22+=1) { + __pyx_v_i = __pyx_t_22; - /* "gensim/models/word2vec_inner.pyx":385 + /* "gensim/models/word2vec_inner.pyx":578 * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] # <<<<<<<<<<<<<< @@ -5002,7 +5065,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_j = ((__pyx_v_i - __pyx_v_window) + (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/word2vec_inner.pyx":386 + /* "gensim/models/word2vec_inner.pyx":579 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -5012,7 +5075,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = ((__pyx_v_j < __pyx_v_idx_start) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":387 + /* "gensim/models/word2vec_inner.pyx":580 * j = i - window + reduced_windows[i] * if j < idx_start: * j = idx_start # <<<<<<<<<<<<<< @@ -5021,7 +5084,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_j = __pyx_v_idx_start; - /* "gensim/models/word2vec_inner.pyx":386 + /* "gensim/models/word2vec_inner.pyx":579 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -5030,7 +5093,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":388 + /* "gensim/models/word2vec_inner.pyx":581 * if j < idx_start: * j = idx_start * k = i + window + 1 - reduced_windows[i] # <<<<<<<<<<<<<< @@ -5039,7 +5102,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_k = (((__pyx_v_i + __pyx_v_window) + 1) - (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/word2vec_inner.pyx":389 + /* "gensim/models/word2vec_inner.pyx":582 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -5049,7 +5112,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = ((__pyx_v_k > __pyx_v_idx_end) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":390 + /* "gensim/models/word2vec_inner.pyx":583 * k = i + window + 1 - reduced_windows[i] * if k > idx_end: * k = idx_end # <<<<<<<<<<<<<< @@ -5058,7 +5121,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_k = __pyx_v_idx_end; - /* "gensim/models/word2vec_inner.pyx":389 + /* "gensim/models/word2vec_inner.pyx":582 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -5067,18 +5130,19 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":391 + /* "gensim/models/word2vec_inner.pyx":584 * if k > idx_end: * k = idx_end * for j in range(j, k): # <<<<<<<<<<<<<< * if j == i: * continue */ - __pyx_t_21 = __pyx_v_k; - for (__pyx_t_22 = __pyx_v_j; __pyx_t_22 < __pyx_t_21; __pyx_t_22+=1) { - __pyx_v_j = __pyx_t_22; + __pyx_t_23 = __pyx_v_k; + __pyx_t_24 = __pyx_t_23; + for (__pyx_t_25 = __pyx_v_j; __pyx_t_25 < __pyx_t_24; __pyx_t_25+=1) { + __pyx_v_j = __pyx_t_25; - /* "gensim/models/word2vec_inner.pyx":392 + /* "gensim/models/word2vec_inner.pyx":585 * k = idx_end * for j in range(j, k): * if j == i: # <<<<<<<<<<<<<< @@ -5088,7 +5152,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = ((__pyx_v_j == __pyx_v_i) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":393 + /* "gensim/models/word2vec_inner.pyx":586 * for j in range(j, k): * if j == i: * continue # <<<<<<<<<<<<<< @@ -5097,7 +5161,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ goto __pyx_L31_continue; - /* "gensim/models/word2vec_inner.pyx":392 + /* "gensim/models/word2vec_inner.pyx":585 * k = idx_end * for j in range(j, k): * if j == i: # <<<<<<<<<<<<<< @@ -5106,7 +5170,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":394 + /* "gensim/models/word2vec_inner.pyx":587 * if j == i: * continue * if hs: # <<<<<<<<<<<<<< @@ -5116,7 +5180,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = (__pyx_v_hs != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":395 + /* "gensim/models/word2vec_inner.pyx":588 * continue * if hs: * fast_sentence_sg_hs(points[i], codes[i], codelens[i], syn0, syn1, size, indexes[j], _alpha, work, word_locks, _compute_loss, &_running_training_loss) # <<<<<<<<<<<<<< @@ -5125,7 +5189,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), (__pyx_v_codelens[__pyx_v_i]), __pyx_v_syn0, __pyx_v_syn1, __pyx_v_size, (__pyx_v_indexes[__pyx_v_j]), __pyx_v__alpha, __pyx_v_work, __pyx_v_word_locks, __pyx_v__compute_loss, (&__pyx_v__running_training_loss)); - /* "gensim/models/word2vec_inner.pyx":394 + /* "gensim/models/word2vec_inner.pyx":587 * if j == i: * continue * if hs: # <<<<<<<<<<<<<< @@ -5134,7 +5198,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ } - /* "gensim/models/word2vec_inner.pyx":396 + /* "gensim/models/word2vec_inner.pyx":589 * if hs: * fast_sentence_sg_hs(points[i], codes[i], codelens[i], syn0, syn1, size, indexes[j], _alpha, work, word_locks, _compute_loss, &_running_training_loss) * if negative: # <<<<<<<<<<<<<< @@ -5144,7 +5208,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON __pyx_t_4 = (__pyx_v_negative != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":397 + /* "gensim/models/word2vec_inner.pyx":590 * fast_sentence_sg_hs(points[i], codes[i], codelens[i], syn0, syn1, size, indexes[j], _alpha, work, word_locks, _compute_loss, &_running_training_loss) * if negative: * next_random = fast_sentence_sg_neg(negative, cum_table, cum_table_len, syn0, syn1neg, size, indexes[i], indexes[j], _alpha, work, next_random, word_locks, _compute_loss, &_running_training_loss) # <<<<<<<<<<<<<< @@ -5153,7 +5217,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON */ __pyx_v_next_random = __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_sg_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v_syn0, __pyx_v_syn1neg, __pyx_v_size, (__pyx_v_indexes[__pyx_v_i]), (__pyx_v_indexes[__pyx_v_j]), __pyx_v__alpha, __pyx_v_work, __pyx_v_next_random, __pyx_v_word_locks, __pyx_v__compute_loss, (&__pyx_v__running_training_loss)); - /* "gensim/models/word2vec_inner.pyx":396 + /* "gensim/models/word2vec_inner.pyx":589 * if hs: * fast_sentence_sg_hs(points[i], codes[i], codelens[i], syn0, syn1, size, indexes[j], _alpha, work, word_locks, _compute_loss, &_running_training_loss) * if negative: # <<<<<<<<<<<<<< @@ -5167,7 +5231,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON } } - /* "gensim/models/word2vec_inner.pyx":380 + /* "gensim/models/word2vec_inner.pyx":573 * * # release GIL & train on all sentences * with nogil: # <<<<<<<<<<<<<< @@ -5186,19 +5250,19 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON } } - /* "gensim/models/word2vec_inner.pyx":399 + /* "gensim/models/word2vec_inner.pyx":592 * next_random = fast_sentence_sg_neg(negative, cum_table, cum_table_len, syn0, syn1neg, size, indexes[i], indexes[j], _alpha, work, next_random, word_locks, _compute_loss, &_running_training_loss) * * model.running_training_loss = _running_training_loss # <<<<<<<<<<<<<< * return effective_words * */ - __pyx_t_14 = PyFloat_FromDouble(__pyx_v__running_training_loss); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 399, __pyx_L1_error) + __pyx_t_14 = PyFloat_FromDouble(__pyx_v__running_training_loss); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 592, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - if (__Pyx_PyObject_SetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss, __pyx_t_14) < 0) __PYX_ERR(0, 399, __pyx_L1_error) + if (__Pyx_PyObject_SetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss, __pyx_t_14) < 0) __PYX_ERR(0, 592, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":400 + /* "gensim/models/word2vec_inner.pyx":593 * * model.running_training_loss = _running_training_loss * return effective_words # <<<<<<<<<<<<<< @@ -5206,18 +5270,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_14 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 400, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 593, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); __pyx_r = __pyx_t_14; __pyx_t_14 = 0; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":296 + /* "gensim/models/word2vec_inner.pyx":465 * * * def train_batch_sg(model, sentences, alpha, _work, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a batch of sentences. + * */ /* function exit code */ @@ -5241,17 +5305,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_train_batch_sg(CYTHON return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":403 +/* "gensim/models/word2vec_inner.pyx":596 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update CBOW model by training on a batch of sentences. + * */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_3train_batch_cbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_3train_batch_cbow = {"train_batch_cbow", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_3train_batch_cbow, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_14word2vec_inner_2train_batch_cbow[] = "train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss)\nUpdate CBOW model by training on a batch of sentences.\n\n Called internally from :meth:`~gensim.models.word2vec.Word2Vec.train`.\n\n Parameters\n ----------\n model : :class:`~gensim.models.word2vec.Word2Vec`\n The Word2Vec model instance to train.\n sentences : iterable of list of str\n The corpus used to train the model.\n alpha : float\n The learning rate.\n _work : np.ndarray\n Private working memory for each worker.\n _neu1 : np.ndarray\n Private working memory for each worker.\n compute_loss : bool\n Whether or not the training loss should be computed in this batch.\n\n Returns\n -------\n int\n Number of words in the vocabulary actually used for training (They already existed in the vocabulary\n and were not discarded by negative sampling).\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_3train_batch_cbow = {"train_batch_cbow", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_3train_batch_cbow, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_14word2vec_inner_2train_batch_cbow}; static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_3train_batch_cbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_sentences = 0; @@ -5287,41 +5352,41 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_3train_batch_cbow(PyO kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_sentences)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 1); __PYX_ERR(0, 403, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 1); __PYX_ERR(0, 596, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_alpha)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 2); __PYX_ERR(0, 403, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 2); __PYX_ERR(0, 596, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 3); __PYX_ERR(0, 403, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 3); __PYX_ERR(0, 596, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 4: - if (likely((values[4] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_neu1)) != 0)) kw_args--; + if (likely((values[4] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_neu1)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 4); __PYX_ERR(0, 403, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 4); __PYX_ERR(0, 596, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 5: - if (likely((values[5] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_compute_loss)) != 0)) kw_args--; + if (likely((values[5] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_compute_loss)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 5); __PYX_ERR(0, 403, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, 5); __PYX_ERR(0, 596, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_batch_cbow") < 0)) __PYX_ERR(0, 403, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "train_batch_cbow") < 0)) __PYX_ERR(0, 596, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 6) { goto __pyx_L5_argtuple_error; @@ -5342,7 +5407,7 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_3train_batch_cbow(PyO } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 403, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("train_batch_cbow", 1, 6, 6, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 596, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.word2vec_inner.train_batch_cbow", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -5415,74 +5480,76 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT PyObject *__pyx_t_18 = NULL; int __pyx_t_19; int __pyx_t_20; + int __pyx_t_21; + int __pyx_t_22; __Pyx_RefNannySetupContext("train_batch_cbow", 0); - /* "gensim/models/word2vec_inner.pyx":404 - * - * def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): + /* "gensim/models/word2vec_inner.pyx":622 + * and were not discarded by negative sampling). + * """ * cdef int hs = model.hs # <<<<<<<<<<<<<< * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 404, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_hs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 622, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 404, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 622, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_hs = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":405 - * def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): + /* "gensim/models/word2vec_inner.pyx":623 + * """ * cdef int hs = model.hs * cdef int negative = model.negative # <<<<<<<<<<<<<< * cdef int sample = (model.vocabulary.sample != 0) * cdef int cbow_mean = model.cbow_mean */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 405, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_negative); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 623, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 405, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 623, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_negative = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":406 + /* "gensim/models/word2vec_inner.pyx":624 * cdef int hs = model.hs * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) # <<<<<<<<<<<<<< * cdef int cbow_mean = model.cbow_mean * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 406, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 624, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 406, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sample); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 624, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 406, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_3, __pyx_int_0, Py_NE); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 624, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 406, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 624, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_sample = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":407 + /* "gensim/models/word2vec_inner.pyx":625 * cdef int negative = model.negative * cdef int sample = (model.vocabulary.sample != 0) * cdef int cbow_mean = model.cbow_mean # <<<<<<<<<<<<<< * * cdef int _compute_loss = (1 if compute_loss == True else 0) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 407, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 625, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 407, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 625, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_cbow_mean = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":409 + /* "gensim/models/word2vec_inner.pyx":627 * cdef int cbow_mean = model.cbow_mean * * cdef int _compute_loss = (1 if compute_loss == True else 0) # <<<<<<<<<<<<<< * cdef REAL_t _running_training_loss = model.running_training_loss * */ - __pyx_t_1 = PyObject_RichCompare(__pyx_v_compute_loss, Py_True, Py_EQ); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 409, __pyx_L1_error) - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_t_1); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 409, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_v_compute_loss, Py_True, Py_EQ); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 627, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_t_1); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 627, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; if (__pyx_t_4) { __pyx_t_2 = 1; @@ -5491,91 +5558,91 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT } __pyx_v__compute_loss = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":410 + /* "gensim/models/word2vec_inner.pyx":628 * * cdef int _compute_loss = (1 if compute_loss == True else 0) * cdef REAL_t _running_training_loss = model.running_training_loss # <<<<<<<<<<<<<< * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 410, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 628, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_t_1); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 410, __pyx_L1_error) + __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_t_1); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 628, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v__running_training_loss = __pyx_t_5; - /* "gensim/models/word2vec_inner.pyx":412 + /* "gensim/models/word2vec_inner.pyx":630 * cdef REAL_t _running_training_loss = model.running_training_loss * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) # <<<<<<<<<<<<<< * cdef REAL_t *word_locks = (np.PyArray_DATA(model.trainables.vectors_lockf)) * cdef REAL_t *work */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 412, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 630, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 412, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 630, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 412, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 630, __pyx_L1_error) __pyx_v_syn0 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":413 + /* "gensim/models/word2vec_inner.pyx":631 * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) * cdef REAL_t *word_locks = (np.PyArray_DATA(model.trainables.vectors_lockf)) # <<<<<<<<<<<<<< * cdef REAL_t *work * cdef REAL_t _alpha = alpha */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 413, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 631, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 413, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vectors_lockf); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 631, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 413, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 631, __pyx_L1_error) __pyx_v_word_locks = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":415 + /* "gensim/models/word2vec_inner.pyx":633 * cdef REAL_t *word_locks = (np.PyArray_DATA(model.trainables.vectors_lockf)) * cdef REAL_t *work * cdef REAL_t _alpha = alpha # <<<<<<<<<<<<<< * cdef int size = model.wv.vector_size * */ - __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 415, __pyx_L1_error) + __pyx_t_5 = __pyx_PyFloat_AsFloat(__pyx_v_alpha); if (unlikely((__pyx_t_5 == ((npy_float32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 633, __pyx_L1_error) __pyx_v__alpha = __pyx_t_5; - /* "gensim/models/word2vec_inner.pyx":416 + /* "gensim/models/word2vec_inner.pyx":634 * cdef REAL_t *work * cdef REAL_t _alpha = alpha * cdef int size = model.wv.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_SENTENCE_LEN] */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 416, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 634, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 416, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 634, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 416, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 634, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":422 + /* "gensim/models/word2vec_inner.pyx":640 * cdef np.uint32_t reduced_windows[MAX_SENTENCE_LEN] * cdef int sentence_idx[MAX_SENTENCE_LEN + 1] * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 422, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 640, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 422, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 640, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":425 + /* "gensim/models/word2vec_inner.pyx":643 * * cdef int i, j, k * cdef int effective_words = 0, effective_sentences = 0 # <<<<<<<<<<<<<< @@ -5585,7 +5652,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_v_effective_words = 0; __pyx_v_effective_sentences = 0; - /* "gensim/models/word2vec_inner.pyx":440 + /* "gensim/models/word2vec_inner.pyx":658 * cdef unsigned long long next_random * * if hs: # <<<<<<<<<<<<<< @@ -5595,23 +5662,23 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = (__pyx_v_hs != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":441 + /* "gensim/models/word2vec_inner.pyx":659 * * if hs: * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * if negative: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 659, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 441, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_syn1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 659, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 441, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 659, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":440 + /* "gensim/models/word2vec_inner.pyx":658 * cdef unsigned long long next_random * * if hs: # <<<<<<<<<<<<<< @@ -5620,7 +5687,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":443 + /* "gensim/models/word2vec_inner.pyx":661 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -5630,55 +5697,55 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = (__pyx_v_negative != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":444 + /* "gensim/models/word2vec_inner.pyx":662 * * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) # <<<<<<<<<<<<<< * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 444, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 662, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 444, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1neg); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 662, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 444, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 662, __pyx_L1_error) __pyx_v_syn1neg = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":445 + /* "gensim/models/word2vec_inner.pyx":663 * if negative: * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) # <<<<<<<<<<<<<< * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 445, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 663, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 445, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 663, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 445, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 663, __pyx_L1_error) __pyx_v_cum_table = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_1))); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":446 + /* "gensim/models/word2vec_inner.pyx":664 * syn1neg = (np.PyArray_DATA(model.trainables.syn1neg)) * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) # <<<<<<<<<<<<<< * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 446, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_vocabulary); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 664, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 446, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_cum_table); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 664, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 446, __pyx_L1_error) + __pyx_t_6 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_6 == ((Py_ssize_t)-1))) __PYX_ERR(0, 664, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_cum_table_len = __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":443 + /* "gensim/models/word2vec_inner.pyx":661 * syn1 = (np.PyArray_DATA(model.trainables.syn1)) * * if negative: # <<<<<<<<<<<<<< @@ -5687,7 +5754,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":447 + /* "gensim/models/word2vec_inner.pyx":665 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -5705,41 +5772,41 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_L6_bool_binop_done:; if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":448 + /* "gensim/models/word2vec_inner.pyx":666 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_1 = PyNumber_Multiply(__pyx_int_16777216, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_random); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_randint); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_8 = PyNumber_Add(__pyx_t_1, __pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_unsigned_PY_LONG_LONG(__pyx_t_8); if (unlikely((__pyx_t_9 == (unsigned PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_next_random = __pyx_t_9; - /* "gensim/models/word2vec_inner.pyx":447 + /* "gensim/models/word2vec_inner.pyx":665 * cum_table = (np.PyArray_DATA(model.vocabulary.cum_table)) * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: # <<<<<<<<<<<<<< @@ -5748,42 +5815,42 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":451 + /* "gensim/models/word2vec_inner.pyx":669 * * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) # <<<<<<<<<<<<<< * neu1 = np.PyArray_DATA(_neu1) * */ - if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 451, __pyx_L1_error) + if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 669, __pyx_L1_error) __pyx_v_work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__work))); - /* "gensim/models/word2vec_inner.pyx":452 + /* "gensim/models/word2vec_inner.pyx":670 * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) * neu1 = np.PyArray_DATA(_neu1) # <<<<<<<<<<<<<< * * # prepare C structures so we can go "full C" and release the Python GIL */ - if (!(likely(((__pyx_v__neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 452, __pyx_L1_error) + if (!(likely(((__pyx_v__neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 670, __pyx_L1_error) __pyx_v_neu1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__neu1))); - /* "gensim/models/word2vec_inner.pyx":455 + /* "gensim/models/word2vec_inner.pyx":673 * * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: */ - __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 455, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 673, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 455, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_vocab); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 673, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_v_vlookup = __pyx_t_3; __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":456 + /* "gensim/models/word2vec_inner.pyx":674 * # prepare C structures so we can go "full C" and release the Python GIL * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 # <<<<<<<<<<<<<< @@ -5792,7 +5859,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ (__pyx_v_sentence_idx[0]) = 0; - /* "gensim/models/word2vec_inner.pyx":457 + /* "gensim/models/word2vec_inner.pyx":675 * vlookup = model.wv.vocab * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: # <<<<<<<<<<<<<< @@ -5803,26 +5870,26 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_3 = __pyx_v_sentences; __Pyx_INCREF(__pyx_t_3); __pyx_t_6 = 0; __pyx_t_10 = NULL; } else { - __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_6 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_sentences); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 675, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 675, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_10)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_8 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 675, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 675, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_8 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_6); __Pyx_INCREF(__pyx_t_8); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 675, __pyx_L1_error) #else - __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 457, __pyx_L1_error) + __pyx_t_8 = PySequence_ITEM(__pyx_t_3, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 675, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); #endif } @@ -5832,7 +5899,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 457, __pyx_L1_error) + else __PYX_ERR(0, 675, __pyx_L1_error) } break; } @@ -5841,18 +5908,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_sent, __pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/word2vec_inner.pyx":458 + /* "gensim/models/word2vec_inner.pyx":676 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: */ - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 458, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_sent); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 676, __pyx_L1_error) __pyx_t_7 = ((!__pyx_t_4) != 0); if (__pyx_t_7) { - /* "gensim/models/word2vec_inner.pyx":459 + /* "gensim/models/word2vec_inner.pyx":677 * for sent in sentences: * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged # <<<<<<<<<<<<<< @@ -5861,7 +5928,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ goto __pyx_L8_continue; - /* "gensim/models/word2vec_inner.pyx":458 + /* "gensim/models/word2vec_inner.pyx":676 * sentence_idx[0] = 0 # indices of the first sentence always start at 0 * for sent in sentences: * if not sent: # <<<<<<<<<<<<<< @@ -5870,7 +5937,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":460 + /* "gensim/models/word2vec_inner.pyx":678 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -5881,26 +5948,26 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_8 = __pyx_v_sent; __Pyx_INCREF(__pyx_t_8); __pyx_t_11 = 0; __pyx_t_12 = NULL; } else { - __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_11 = -1; __pyx_t_8 = PyObject_GetIter(__pyx_v_sent); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 678, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_12 = Py_TYPE(__pyx_t_8)->tp_iternext; if (unlikely(!__pyx_t_12)) __PYX_ERR(0, 678, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_12)) { if (likely(PyList_CheckExact(__pyx_t_8))) { if (__pyx_t_11 >= PyList_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 678, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 678, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_11 >= PyTuple_GET_SIZE(__pyx_t_8)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_8, __pyx_t_11); __Pyx_INCREF(__pyx_t_1); __pyx_t_11++; if (unlikely(0 < 0)) __PYX_ERR(0, 678, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 460, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_8, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 678, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -5910,7 +5977,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 460, __pyx_L1_error) + else __PYX_ERR(0, 678, __pyx_L1_error) } break; } @@ -5919,16 +5986,16 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":461 + /* "gensim/models/word2vec_inner.pyx":679 * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: * word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window */ - __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 461, __pyx_L1_error) + __pyx_t_7 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 679, __pyx_L1_error) if ((__pyx_t_7 != 0)) { - __pyx_t_13 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 461, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 679, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); __pyx_t_1 = __pyx_t_13; __pyx_t_13 = 0; @@ -5939,7 +6006,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __Pyx_XDECREF_SET(__pyx_v_word, __pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":462 + /* "gensim/models/word2vec_inner.pyx":680 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -5950,7 +6017,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = (__pyx_t_7 != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":463 + /* "gensim/models/word2vec_inner.pyx":681 * word = vlookup[token] if token in vlookup else None * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window # <<<<<<<<<<<<<< @@ -5959,7 +6026,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ goto __pyx_L11_continue; - /* "gensim/models/word2vec_inner.pyx":462 + /* "gensim/models/word2vec_inner.pyx":680 * for token in sent: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -5968,7 +6035,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":464 + /* "gensim/models/word2vec_inner.pyx":682 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -5981,20 +6048,20 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = __pyx_t_7; goto __pyx_L15_bool_binop_done; } - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 464, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_sample_int); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 464, __pyx_L1_error) + __pyx_t_13 = __Pyx_PyInt_From_unsigned_PY_LONG_LONG(__pyx_f_6gensim_6models_14word2vec_inner_random_int32((&__pyx_v_next_random))); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 464, __pyx_L1_error) + __pyx_t_14 = PyObject_RichCompare(__pyx_t_1, __pyx_t_13, Py_LT); __Pyx_XGOTREF(__pyx_t_14); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; - __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 464, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_IsTrue(__pyx_t_14); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(0, 682, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; __pyx_t_4 = __pyx_t_7; __pyx_L15_bool_binop_done:; if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":465 + /* "gensim/models/word2vec_inner.pyx":683 * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): * continue # <<<<<<<<<<<<<< @@ -6003,7 +6070,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ goto __pyx_L11_continue; - /* "gensim/models/word2vec_inner.pyx":464 + /* "gensim/models/word2vec_inner.pyx":682 * if word is None: * continue # leaving `effective_words` unchanged = shortening the sentence = expanding the window * if sample and word.sample_int < random_int32(&next_random): # <<<<<<<<<<<<<< @@ -6012,20 +6079,20 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":466 + /* "gensim/models/word2vec_inner.pyx":684 * if sample and word.sample_int < random_int32(&next_random): * continue * indexes[effective_words] = word.index # <<<<<<<<<<<<<< * if hs: * codelens[effective_words] = len(word.code) */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 466, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 684, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 466, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_t_14); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 684, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; (__pyx_v_indexes[__pyx_v_effective_words]) = __pyx_t_15; - /* "gensim/models/word2vec_inner.pyx":467 + /* "gensim/models/word2vec_inner.pyx":685 * continue * indexes[effective_words] = word.index * if hs: # <<<<<<<<<<<<<< @@ -6035,46 +6102,46 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = (__pyx_v_hs != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":468 + /* "gensim/models/word2vec_inner.pyx":686 * indexes[effective_words] = word.index * if hs: * codelens[effective_words] = len(word.code) # <<<<<<<<<<<<<< * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 468, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 686, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_16 = PyObject_Length(__pyx_t_14); if (unlikely(__pyx_t_16 == ((Py_ssize_t)-1))) __PYX_ERR(0, 468, __pyx_L1_error) + __pyx_t_16 = PyObject_Length(__pyx_t_14); if (unlikely(__pyx_t_16 == ((Py_ssize_t)-1))) __PYX_ERR(0, 686, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; (__pyx_v_codelens[__pyx_v_effective_words]) = ((int)__pyx_t_16); - /* "gensim/models/word2vec_inner.pyx":469 + /* "gensim/models/word2vec_inner.pyx":687 * if hs: * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) # <<<<<<<<<<<<<< * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 469, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 687, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 469, __pyx_L1_error) + if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 687, __pyx_L1_error) (__pyx_v_codes[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_14))); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":470 + /* "gensim/models/word2vec_inner.pyx":688 * codelens[effective_words] = len(word.code) * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) # <<<<<<<<<<<<<< * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: */ - __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 470, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 688, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 470, __pyx_L1_error) + if (!(likely(((__pyx_t_14) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_14, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 688, __pyx_L1_error) (__pyx_v_points[__pyx_v_effective_words]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_14))); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":467 + /* "gensim/models/word2vec_inner.pyx":685 * continue * indexes[effective_words] = word.index * if hs: # <<<<<<<<<<<<<< @@ -6083,7 +6150,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":471 + /* "gensim/models/word2vec_inner.pyx":689 * codes[effective_words] = np.PyArray_DATA(word.code) * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 # <<<<<<<<<<<<<< @@ -6092,7 +6159,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_effective_words = (__pyx_v_effective_words + 1); - /* "gensim/models/word2vec_inner.pyx":472 + /* "gensim/models/word2vec_inner.pyx":690 * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -6102,7 +6169,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = ((__pyx_v_effective_words == 0x2710) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":473 + /* "gensim/models/word2vec_inner.pyx":691 * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -6111,7 +6178,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ goto __pyx_L12_break; - /* "gensim/models/word2vec_inner.pyx":472 + /* "gensim/models/word2vec_inner.pyx":690 * points[effective_words] = np.PyArray_DATA(word.point) * effective_words += 1 * if effective_words == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -6120,7 +6187,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":460 + /* "gensim/models/word2vec_inner.pyx":678 * if not sent: * continue # ignore empty sentences; leave effective_sentences unchanged * for token in sent: # <<<<<<<<<<<<<< @@ -6132,7 +6199,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_L12_break:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - /* "gensim/models/word2vec_inner.pyx":478 + /* "gensim/models/word2vec_inner.pyx":696 * # across sentence boundaries. * # indices of sentence number X are between tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 485, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_14)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 703, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; for (;;) { @@ -6273,17 +6340,17 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT if (likely(PyList_CheckExact(__pyx_t_14))) { if (__pyx_t_6 >= PyList_GET_SIZE(__pyx_t_14)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyList_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 485, __pyx_L1_error) + __pyx_t_3 = PyList_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 703, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 485, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 703, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { if (__pyx_t_6 >= PyTuple_GET_SIZE(__pyx_t_14)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 485, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_14, __pyx_t_6); __Pyx_INCREF(__pyx_t_3); __pyx_t_6++; if (unlikely(0 < 0)) __PYX_ERR(0, 703, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 485, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_14, __pyx_t_6); __pyx_t_6++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 703, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } @@ -6293,7 +6360,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 485, __pyx_L1_error) + else __PYX_ERR(0, 703, __pyx_L1_error) } break; } @@ -6304,17 +6371,17 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_v_i = __pyx_t_2; __pyx_t_2 = (__pyx_t_2 + 1); - /* "gensim/models/word2vec_inner.pyx":486 + /* "gensim/models/word2vec_inner.pyx":704 * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): * reduced_windows[i] = item # <<<<<<<<<<<<<< * * # release GIL & train on all sentences */ - __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 486, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_npy_uint32(__pyx_v_item); if (unlikely((__pyx_t_15 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 704, __pyx_L1_error) (__pyx_v_reduced_windows[__pyx_v_i]) = __pyx_t_15; - /* "gensim/models/word2vec_inner.pyx":485 + /* "gensim/models/word2vec_inner.pyx":703 * * # precompute "reduced window" offsets in a single randint() call * for i, item in enumerate(model.random.randint(0, window, effective_words)): # <<<<<<<<<<<<<< @@ -6324,7 +6391,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT } __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":489 + /* "gensim/models/word2vec_inner.pyx":707 * * # release GIL & train on all sentences * with nogil: # <<<<<<<<<<<<<< @@ -6339,7 +6406,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT #endif /*try:*/ { - /* "gensim/models/word2vec_inner.pyx":490 + /* "gensim/models/word2vec_inner.pyx":708 * # release GIL & train on all sentences * with nogil: * for sent_idx in range(effective_sentences): # <<<<<<<<<<<<<< @@ -6347,10 +6414,11 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT * idx_end = sentence_idx[sent_idx + 1] */ __pyx_t_2 = __pyx_v_effective_sentences; - for (__pyx_t_17 = 0; __pyx_t_17 < __pyx_t_2; __pyx_t_17+=1) { - __pyx_v_sent_idx = __pyx_t_17; + __pyx_t_17 = __pyx_t_2; + for (__pyx_t_19 = 0; __pyx_t_19 < __pyx_t_17; __pyx_t_19+=1) { + __pyx_v_sent_idx = __pyx_t_19; - /* "gensim/models/word2vec_inner.pyx":491 + /* "gensim/models/word2vec_inner.pyx":709 * with nogil: * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] # <<<<<<<<<<<<<< @@ -6359,7 +6427,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_idx_start = (__pyx_v_sentence_idx[__pyx_v_sent_idx]); - /* "gensim/models/word2vec_inner.pyx":492 + /* "gensim/models/word2vec_inner.pyx":710 * for sent_idx in range(effective_sentences): * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] # <<<<<<<<<<<<<< @@ -6368,18 +6436,19 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_idx_end = (__pyx_v_sentence_idx[(__pyx_v_sent_idx + 1)]); - /* "gensim/models/word2vec_inner.pyx":493 + /* "gensim/models/word2vec_inner.pyx":711 * idx_start = sentence_idx[sent_idx] * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): # <<<<<<<<<<<<<< * j = i - window + reduced_windows[i] * if j < idx_start: */ - __pyx_t_19 = __pyx_v_idx_end; - for (__pyx_t_20 = __pyx_v_idx_start; __pyx_t_20 < __pyx_t_19; __pyx_t_20+=1) { - __pyx_v_i = __pyx_t_20; + __pyx_t_20 = __pyx_v_idx_end; + __pyx_t_21 = __pyx_t_20; + for (__pyx_t_22 = __pyx_v_idx_start; __pyx_t_22 < __pyx_t_21; __pyx_t_22+=1) { + __pyx_v_i = __pyx_t_22; - /* "gensim/models/word2vec_inner.pyx":494 + /* "gensim/models/word2vec_inner.pyx":712 * idx_end = sentence_idx[sent_idx + 1] * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] # <<<<<<<<<<<<<< @@ -6388,7 +6457,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_j = ((__pyx_v_i - __pyx_v_window) + (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/word2vec_inner.pyx":495 + /* "gensim/models/word2vec_inner.pyx":713 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -6398,7 +6467,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = ((__pyx_v_j < __pyx_v_idx_start) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":496 + /* "gensim/models/word2vec_inner.pyx":714 * j = i - window + reduced_windows[i] * if j < idx_start: * j = idx_start # <<<<<<<<<<<<<< @@ -6407,7 +6476,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_j = __pyx_v_idx_start; - /* "gensim/models/word2vec_inner.pyx":495 + /* "gensim/models/word2vec_inner.pyx":713 * for i in range(idx_start, idx_end): * j = i - window + reduced_windows[i] * if j < idx_start: # <<<<<<<<<<<<<< @@ -6416,7 +6485,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":497 + /* "gensim/models/word2vec_inner.pyx":715 * if j < idx_start: * j = idx_start * k = i + window + 1 - reduced_windows[i] # <<<<<<<<<<<<<< @@ -6425,7 +6494,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_k = (((__pyx_v_i + __pyx_v_window) + 1) - (__pyx_v_reduced_windows[__pyx_v_i])); - /* "gensim/models/word2vec_inner.pyx":498 + /* "gensim/models/word2vec_inner.pyx":716 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -6435,7 +6504,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = ((__pyx_v_k > __pyx_v_idx_end) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":499 + /* "gensim/models/word2vec_inner.pyx":717 * k = i + window + 1 - reduced_windows[i] * if k > idx_end: * k = idx_end # <<<<<<<<<<<<<< @@ -6444,7 +6513,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_k = __pyx_v_idx_end; - /* "gensim/models/word2vec_inner.pyx":498 + /* "gensim/models/word2vec_inner.pyx":716 * j = idx_start * k = i + window + 1 - reduced_windows[i] * if k > idx_end: # <<<<<<<<<<<<<< @@ -6453,7 +6522,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":500 + /* "gensim/models/word2vec_inner.pyx":718 * if k > idx_end: * k = idx_end * if hs: # <<<<<<<<<<<<<< @@ -6463,7 +6532,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = (__pyx_v_hs != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":501 + /* "gensim/models/word2vec_inner.pyx":719 * k = idx_end * if hs: * fast_sentence_cbow_hs(points[i], codes[i], codelens, neu1, syn0, syn1, size, indexes, _alpha, work, i, j, k, cbow_mean, word_locks, _compute_loss, &_running_training_loss) # <<<<<<<<<<<<<< @@ -6472,7 +6541,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_hs((__pyx_v_points[__pyx_v_i]), (__pyx_v_codes[__pyx_v_i]), __pyx_v_codelens, __pyx_v_neu1, __pyx_v_syn0, __pyx_v_syn1, __pyx_v_size, __pyx_v_indexes, __pyx_v__alpha, __pyx_v_work, __pyx_v_i, __pyx_v_j, __pyx_v_k, __pyx_v_cbow_mean, __pyx_v_word_locks, __pyx_v__compute_loss, (&__pyx_v__running_training_loss)); - /* "gensim/models/word2vec_inner.pyx":500 + /* "gensim/models/word2vec_inner.pyx":718 * if k > idx_end: * k = idx_end * if hs: # <<<<<<<<<<<<<< @@ -6481,7 +6550,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ } - /* "gensim/models/word2vec_inner.pyx":502 + /* "gensim/models/word2vec_inner.pyx":720 * if hs: * fast_sentence_cbow_hs(points[i], codes[i], codelens, neu1, syn0, syn1, size, indexes, _alpha, work, i, j, k, cbow_mean, word_locks, _compute_loss, &_running_training_loss) * if negative: # <<<<<<<<<<<<<< @@ -6491,7 +6560,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT __pyx_t_4 = (__pyx_v_negative != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":503 + /* "gensim/models/word2vec_inner.pyx":721 * fast_sentence_cbow_hs(points[i], codes[i], codelens, neu1, syn0, syn1, size, indexes, _alpha, work, i, j, k, cbow_mean, word_locks, _compute_loss, &_running_training_loss) * if negative: * next_random = fast_sentence_cbow_neg(negative, cum_table, cum_table_len, codelens, neu1, syn0, syn1neg, size, indexes, _alpha, work, i, j, k, cbow_mean, next_random, word_locks, _compute_loss, &_running_training_loss) # <<<<<<<<<<<<<< @@ -6500,7 +6569,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT */ __pyx_v_next_random = __pyx_f_6gensim_6models_14word2vec_inner_fast_sentence_cbow_neg(__pyx_v_negative, __pyx_v_cum_table, __pyx_v_cum_table_len, __pyx_v_codelens, __pyx_v_neu1, __pyx_v_syn0, __pyx_v_syn1neg, __pyx_v_size, __pyx_v_indexes, __pyx_v__alpha, __pyx_v_work, __pyx_v_i, __pyx_v_j, __pyx_v_k, __pyx_v_cbow_mean, __pyx_v_next_random, __pyx_v_word_locks, __pyx_v__compute_loss, (&__pyx_v__running_training_loss)); - /* "gensim/models/word2vec_inner.pyx":502 + /* "gensim/models/word2vec_inner.pyx":720 * if hs: * fast_sentence_cbow_hs(points[i], codes[i], codelens, neu1, syn0, syn1, size, indexes, _alpha, work, i, j, k, cbow_mean, word_locks, _compute_loss, &_running_training_loss) * if negative: # <<<<<<<<<<<<<< @@ -6512,7 +6581,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT } } - /* "gensim/models/word2vec_inner.pyx":489 + /* "gensim/models/word2vec_inner.pyx":707 * * # release GIL & train on all sentences * with nogil: # <<<<<<<<<<<<<< @@ -6531,19 +6600,19 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT } } - /* "gensim/models/word2vec_inner.pyx":505 + /* "gensim/models/word2vec_inner.pyx":723 * next_random = fast_sentence_cbow_neg(negative, cum_table, cum_table_len, codelens, neu1, syn0, syn1neg, size, indexes, _alpha, work, i, j, k, cbow_mean, next_random, word_locks, _compute_loss, &_running_training_loss) * * model.running_training_loss = _running_training_loss # <<<<<<<<<<<<<< * return effective_words * */ - __pyx_t_14 = PyFloat_FromDouble(__pyx_v__running_training_loss); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 505, __pyx_L1_error) + __pyx_t_14 = PyFloat_FromDouble(__pyx_v__running_training_loss); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 723, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); - if (__Pyx_PyObject_SetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss, __pyx_t_14) < 0) __PYX_ERR(0, 505, __pyx_L1_error) + if (__Pyx_PyObject_SetAttrStr(__pyx_v_model, __pyx_n_s_running_training_loss, __pyx_t_14) < 0) __PYX_ERR(0, 723, __pyx_L1_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - /* "gensim/models/word2vec_inner.pyx":506 + /* "gensim/models/word2vec_inner.pyx":724 * * model.running_training_loss = _running_training_loss * return effective_words # <<<<<<<<<<<<<< @@ -6551,18 +6620,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_14 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 506, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyInt_From_int(__pyx_v_effective_words); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 724, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); __pyx_r = __pyx_t_14; __pyx_t_14 = 0; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":403 + /* "gensim/models/word2vec_inner.pyx":596 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update CBOW model by training on a batch of sentences. + * */ /* function exit code */ @@ -6586,17 +6655,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_2train_batch_cbow(CYT return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":510 +/* "gensim/models/word2vec_inner.pyx":727 + * * - * # Score is only implemented for hierarchical softmax * def score_sentence_sg(model, sentence, _work): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted skip-gram representation. * - * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_5score_sentence_sg(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_5score_sentence_sg = {"score_sentence_sg", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_5score_sentence_sg, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_14word2vec_inner_4score_sentence_sg[] = "score_sentence_sg(model, sentence, _work)\nObtain likelihood score for a single sentence in a fitted skip-gram representation.\n\n Notes\n -----\n This scoring function is only implemented for hierarchical softmax (`model.hs == 1`).\n The model should have been trained using the skip-gram model (`model.sg` == 1`).\n\n Parameters\n ----------\n model : :class:`~gensim.models.word2vec.Word2Vec`\n The trained model. It **MUST** have been trained using hierarchical softmax and the skip-gram algorithm.\n sentence : list of str\n The words comprising the sentence to be scored.\n _work : np.ndarray\n Private working memory for each worker.\n\n Returns\n -------\n float\n The probability assigned to this sentence by the Skip-Gram model.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_5score_sentence_sg = {"score_sentence_sg", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_5score_sentence_sg, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_14word2vec_inner_4score_sentence_sg}; static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_5score_sentence_sg(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_sentence = 0; @@ -6623,23 +6693,23 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_5score_sentence_sg(Py kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_sentence)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_sentence)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("score_sentence_sg", 1, 3, 3, 1); __PYX_ERR(0, 510, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_sg", 1, 3, 3, 1); __PYX_ERR(0, 727, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("score_sentence_sg", 1, 3, 3, 2); __PYX_ERR(0, 510, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_sg", 1, 3, 3, 2); __PYX_ERR(0, 727, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "score_sentence_sg") < 0)) __PYX_ERR(0, 510, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "score_sentence_sg") < 0)) __PYX_ERR(0, 727, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 3) { goto __pyx_L5_argtuple_error; @@ -6654,7 +6724,7 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_5score_sentence_sg(Py } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("score_sentence_sg", 1, 3, 3, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 510, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_sg", 1, 3, 3, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 727, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.word2vec_inner.score_sentence_sg", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -6700,54 +6770,56 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY int __pyx_t_11; int __pyx_t_12; int __pyx_t_13; + int __pyx_t_14; + int __pyx_t_15; __Pyx_RefNannySetupContext("score_sentence_sg", 0); - /* "gensim/models/word2vec_inner.pyx":512 - * def score_sentence_sg(model, sentence, _work): + /* "gensim/models/word2vec_inner.pyx":751 + * """ * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) # <<<<<<<<<<<<<< * cdef REAL_t *work * cdef int size = model.wv.vector_size */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 512, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 751, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 512, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 751, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 512, __pyx_L1_error) + if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 751, __pyx_L1_error) __pyx_v_syn0 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_2))); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/word2vec_inner.pyx":514 + /* "gensim/models/word2vec_inner.pyx":753 * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) * cdef REAL_t *work * cdef int size = model.wv.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_SENTENCE_LEN] */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 514, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 753, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 514, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 753, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_3 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_3 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 514, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_3 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 753, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_size = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":519 + /* "gensim/models/word2vec_inner.pyx":758 * cdef np.uint32_t indexes[MAX_SENTENCE_LEN] * cdef int sentence_len * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 519, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 758, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_3 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 519, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_3 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 758, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_window = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":522 + /* "gensim/models/word2vec_inner.pyx":761 * * cdef int i, j, k * cdef long result = 0 # <<<<<<<<<<<<<< @@ -6756,48 +6828,48 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_result = 0; - /* "gensim/models/word2vec_inner.pyx":528 + /* "gensim/models/word2vec_inner.pyx":767 * cdef np.uint8_t *codes[MAX_SENTENCE_LEN] * * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 528, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 767, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 528, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 767, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 528, __pyx_L1_error) + if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 767, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_2))); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/word2vec_inner.pyx":531 + /* "gensim/models/word2vec_inner.pyx":770 * * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) # <<<<<<<<<<<<<< * * vlookup = model.wv.vocab */ - if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 531, __pyx_L1_error) + if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 770, __pyx_L1_error) __pyx_v_work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__work))); - /* "gensim/models/word2vec_inner.pyx":533 + /* "gensim/models/word2vec_inner.pyx":772 * work = np.PyArray_DATA(_work) * * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * i = 0 * for token in sentence: */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 533, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 772, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_vocab); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 533, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_vocab); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 772, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_v_vlookup = __pyx_t_1; __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":534 + /* "gensim/models/word2vec_inner.pyx":773 * * vlookup = model.wv.vocab * i = 0 # <<<<<<<<<<<<<< @@ -6806,7 +6878,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_i = 0; - /* "gensim/models/word2vec_inner.pyx":535 + /* "gensim/models/word2vec_inner.pyx":774 * vlookup = model.wv.vocab * i = 0 * for token in sentence: # <<<<<<<<<<<<<< @@ -6817,26 +6889,26 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_t_1 = __pyx_v_sentence; __Pyx_INCREF(__pyx_t_1); __pyx_t_4 = 0; __pyx_t_5 = NULL; } else { - __pyx_t_4 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_sentence); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 535, __pyx_L1_error) + __pyx_t_4 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_sentence); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 774, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_5 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 535, __pyx_L1_error) + __pyx_t_5 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 774, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_5)) { if (likely(PyList_CheckExact(__pyx_t_1))) { if (__pyx_t_4 >= PyList_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_2 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_2); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 535, __pyx_L1_error) + __pyx_t_2 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_2); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 774, __pyx_L1_error) #else - __pyx_t_2 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 535, __pyx_L1_error) + __pyx_t_2 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 774, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); #endif } else { if (__pyx_t_4 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_2); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 535, __pyx_L1_error) + __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_2); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 774, __pyx_L1_error) #else - __pyx_t_2 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 535, __pyx_L1_error) + __pyx_t_2 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 774, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); #endif } @@ -6846,7 +6918,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 535, __pyx_L1_error) + else __PYX_ERR(0, 774, __pyx_L1_error) } break; } @@ -6855,16 +6927,16 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/word2vec_inner.pyx":536 + /* "gensim/models/word2vec_inner.pyx":775 * i = 0 * for token in sentence: * word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if word is None: * continue # should drop the */ - __pyx_t_6 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 536, __pyx_L1_error) + __pyx_t_6 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 775, __pyx_L1_error) if ((__pyx_t_6 != 0)) { - __pyx_t_7 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 536, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 775, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_2 = __pyx_t_7; __pyx_t_7 = 0; @@ -6875,7 +6947,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __Pyx_XDECREF_SET(__pyx_v_word, __pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/word2vec_inner.pyx":537 + /* "gensim/models/word2vec_inner.pyx":776 * for token in sentence: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -6886,7 +6958,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_t_8 = (__pyx_t_6 != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":538 + /* "gensim/models/word2vec_inner.pyx":777 * word = vlookup[token] if token in vlookup else None * if word is None: * continue # should drop the # <<<<<<<<<<<<<< @@ -6895,7 +6967,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":537 + /* "gensim/models/word2vec_inner.pyx":776 * for token in sentence: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -6904,59 +6976,59 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ } - /* "gensim/models/word2vec_inner.pyx":539 + /* "gensim/models/word2vec_inner.pyx":778 * if word is None: * continue # should drop the * indexes[i] = word.index # <<<<<<<<<<<<<< * codelens[i] = len(word.code) * codes[i] = np.PyArray_DATA(word.code) */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 539, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 778, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_9 = __Pyx_PyInt_As_npy_uint32(__pyx_t_2); if (unlikely((__pyx_t_9 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 539, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_npy_uint32(__pyx_t_2); if (unlikely((__pyx_t_9 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 778, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; (__pyx_v_indexes[__pyx_v_i]) = __pyx_t_9; - /* "gensim/models/word2vec_inner.pyx":540 + /* "gensim/models/word2vec_inner.pyx":779 * continue # should drop the * indexes[i] = word.index * codelens[i] = len(word.code) # <<<<<<<<<<<<<< * codes[i] = np.PyArray_DATA(word.code) * points[i] = np.PyArray_DATA(word.point) */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 540, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 779, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_10 = PyObject_Length(__pyx_t_2); if (unlikely(__pyx_t_10 == ((Py_ssize_t)-1))) __PYX_ERR(0, 540, __pyx_L1_error) + __pyx_t_10 = PyObject_Length(__pyx_t_2); if (unlikely(__pyx_t_10 == ((Py_ssize_t)-1))) __PYX_ERR(0, 779, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; (__pyx_v_codelens[__pyx_v_i]) = ((int)__pyx_t_10); - /* "gensim/models/word2vec_inner.pyx":541 + /* "gensim/models/word2vec_inner.pyx":780 * indexes[i] = word.index * codelens[i] = len(word.code) * codes[i] = np.PyArray_DATA(word.code) # <<<<<<<<<<<<<< * points[i] = np.PyArray_DATA(word.point) * result += 1 */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 541, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 780, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 541, __pyx_L1_error) + if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 780, __pyx_L1_error) (__pyx_v_codes[__pyx_v_i]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_2))); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/word2vec_inner.pyx":542 + /* "gensim/models/word2vec_inner.pyx":781 * codelens[i] = len(word.code) * codes[i] = np.PyArray_DATA(word.code) * points[i] = np.PyArray_DATA(word.point) # <<<<<<<<<<<<<< * result += 1 * i += 1 */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 542, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 781, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 542, __pyx_L1_error) + if (!(likely(((__pyx_t_2) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_2, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 781, __pyx_L1_error) (__pyx_v_points[__pyx_v_i]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_2))); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/models/word2vec_inner.pyx":543 + /* "gensim/models/word2vec_inner.pyx":782 * codes[i] = np.PyArray_DATA(word.code) * points[i] = np.PyArray_DATA(word.point) * result += 1 # <<<<<<<<<<<<<< @@ -6965,7 +7037,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_result = (__pyx_v_result + 1); - /* "gensim/models/word2vec_inner.pyx":544 + /* "gensim/models/word2vec_inner.pyx":783 * points[i] = np.PyArray_DATA(word.point) * result += 1 * i += 1 # <<<<<<<<<<<<<< @@ -6974,7 +7046,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_i = (__pyx_v_i + 1); - /* "gensim/models/word2vec_inner.pyx":545 + /* "gensim/models/word2vec_inner.pyx":784 * result += 1 * i += 1 * if i == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -6984,7 +7056,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_t_8 = ((__pyx_v_i == 0x2710) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":546 + /* "gensim/models/word2vec_inner.pyx":785 * i += 1 * if i == MAX_SENTENCE_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -6993,7 +7065,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ goto __pyx_L4_break; - /* "gensim/models/word2vec_inner.pyx":545 + /* "gensim/models/word2vec_inner.pyx":784 * result += 1 * i += 1 * if i == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -7002,7 +7074,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ } - /* "gensim/models/word2vec_inner.pyx":535 + /* "gensim/models/word2vec_inner.pyx":774 * vlookup = model.wv.vocab * i = 0 * for token in sentence: # <<<<<<<<<<<<<< @@ -7014,7 +7086,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_L4_break:; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":547 + /* "gensim/models/word2vec_inner.pyx":786 * if i == MAX_SENTENCE_LEN: * break # TODO: log warning, tally overflow? * sentence_len = i # <<<<<<<<<<<<<< @@ -7023,7 +7095,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_sentence_len = __pyx_v_i; - /* "gensim/models/word2vec_inner.pyx":550 + /* "gensim/models/word2vec_inner.pyx":789 * * # release GIL & train on the sentence * work[0] = 0.0 # <<<<<<<<<<<<<< @@ -7032,7 +7104,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ (__pyx_v_work[0]) = 0.0; - /* "gensim/models/word2vec_inner.pyx":552 + /* "gensim/models/word2vec_inner.pyx":791 * work[0] = 0.0 * * with nogil: # <<<<<<<<<<<<<< @@ -7047,7 +7119,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY #endif /*try:*/ { - /* "gensim/models/word2vec_inner.pyx":553 + /* "gensim/models/word2vec_inner.pyx":792 * * with nogil: * for i in range(sentence_len): # <<<<<<<<<<<<<< @@ -7055,10 +7127,11 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY * continue */ __pyx_t_3 = __pyx_v_sentence_len; - for (__pyx_t_11 = 0; __pyx_t_11 < __pyx_t_3; __pyx_t_11+=1) { - __pyx_v_i = __pyx_t_11; + __pyx_t_11 = __pyx_t_3; + for (__pyx_t_12 = 0; __pyx_t_12 < __pyx_t_11; __pyx_t_12+=1) { + __pyx_v_i = __pyx_t_12; - /* "gensim/models/word2vec_inner.pyx":554 + /* "gensim/models/word2vec_inner.pyx":793 * with nogil: * for i in range(sentence_len): * if codelens[i] == 0: # <<<<<<<<<<<<<< @@ -7068,7 +7141,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_t_8 = (((__pyx_v_codelens[__pyx_v_i]) == 0) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":555 + /* "gensim/models/word2vec_inner.pyx":794 * for i in range(sentence_len): * if codelens[i] == 0: * continue # <<<<<<<<<<<<<< @@ -7077,7 +7150,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ goto __pyx_L10_continue; - /* "gensim/models/word2vec_inner.pyx":554 + /* "gensim/models/word2vec_inner.pyx":793 * with nogil: * for i in range(sentence_len): * if codelens[i] == 0: # <<<<<<<<<<<<<< @@ -7086,7 +7159,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ } - /* "gensim/models/word2vec_inner.pyx":556 + /* "gensim/models/word2vec_inner.pyx":795 * if codelens[i] == 0: * continue * j = i - window # <<<<<<<<<<<<<< @@ -7095,7 +7168,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_j = (__pyx_v_i - __pyx_v_window); - /* "gensim/models/word2vec_inner.pyx":557 + /* "gensim/models/word2vec_inner.pyx":796 * continue * j = i - window * if j < 0: # <<<<<<<<<<<<<< @@ -7105,7 +7178,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_t_8 = ((__pyx_v_j < 0) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":558 + /* "gensim/models/word2vec_inner.pyx":797 * j = i - window * if j < 0: * j = 0 # <<<<<<<<<<<<<< @@ -7114,7 +7187,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_j = 0; - /* "gensim/models/word2vec_inner.pyx":557 + /* "gensim/models/word2vec_inner.pyx":796 * continue * j = i - window * if j < 0: # <<<<<<<<<<<<<< @@ -7123,7 +7196,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ } - /* "gensim/models/word2vec_inner.pyx":559 + /* "gensim/models/word2vec_inner.pyx":798 * if j < 0: * j = 0 * k = i + window + 1 # <<<<<<<<<<<<<< @@ -7132,7 +7205,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_k = ((__pyx_v_i + __pyx_v_window) + 1); - /* "gensim/models/word2vec_inner.pyx":560 + /* "gensim/models/word2vec_inner.pyx":799 * j = 0 * k = i + window + 1 * if k > sentence_len: # <<<<<<<<<<<<<< @@ -7142,7 +7215,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_t_8 = ((__pyx_v_k > __pyx_v_sentence_len) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":561 + /* "gensim/models/word2vec_inner.pyx":800 * k = i + window + 1 * if k > sentence_len: * k = sentence_len # <<<<<<<<<<<<<< @@ -7151,7 +7224,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ __pyx_v_k = __pyx_v_sentence_len; - /* "gensim/models/word2vec_inner.pyx":560 + /* "gensim/models/word2vec_inner.pyx":799 * j = 0 * k = i + window + 1 * if k > sentence_len: # <<<<<<<<<<<<<< @@ -7160,18 +7233,19 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ } - /* "gensim/models/word2vec_inner.pyx":562 + /* "gensim/models/word2vec_inner.pyx":801 * if k > sentence_len: * k = sentence_len * for j in range(j, k): # <<<<<<<<<<<<<< * if j == i or codelens[j] == 0: * continue */ - __pyx_t_12 = __pyx_v_k; - for (__pyx_t_13 = __pyx_v_j; __pyx_t_13 < __pyx_t_12; __pyx_t_13+=1) { - __pyx_v_j = __pyx_t_13; + __pyx_t_13 = __pyx_v_k; + __pyx_t_14 = __pyx_t_13; + for (__pyx_t_15 = __pyx_v_j; __pyx_t_15 < __pyx_t_14; __pyx_t_15+=1) { + __pyx_v_j = __pyx_t_15; - /* "gensim/models/word2vec_inner.pyx":563 + /* "gensim/models/word2vec_inner.pyx":802 * k = sentence_len * for j in range(j, k): * if j == i or codelens[j] == 0: # <<<<<<<<<<<<<< @@ -7189,7 +7263,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY __pyx_L18_bool_binop_done:; if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":564 + /* "gensim/models/word2vec_inner.pyx":803 * for j in range(j, k): * if j == i or codelens[j] == 0: * continue # <<<<<<<<<<<<<< @@ -7198,7 +7272,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ goto __pyx_L15_continue; - /* "gensim/models/word2vec_inner.pyx":563 + /* "gensim/models/word2vec_inner.pyx":802 * k = sentence_len * for j in range(j, k): * if j == i or codelens[j] == 0: # <<<<<<<<<<<<<< @@ -7207,7 +7281,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY */ } - /* "gensim/models/word2vec_inner.pyx":565 + /* "gensim/models/word2vec_inner.pyx":804 * if j == i or codelens[j] == 0: * continue * score_pair_sg_hs(points[i], codes[i], codelens[i], syn0, syn1, size, indexes[j], work) # <<<<<<<<<<<<<< @@ -7221,7 +7295,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY } } - /* "gensim/models/word2vec_inner.pyx":552 + /* "gensim/models/word2vec_inner.pyx":791 * work[0] = 0.0 * * with nogil: # <<<<<<<<<<<<<< @@ -7240,7 +7314,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY } } - /* "gensim/models/word2vec_inner.pyx":567 + /* "gensim/models/word2vec_inner.pyx":806 * score_pair_sg_hs(points[i], codes[i], codelens[i], syn0, syn1, size, indexes[j], work) * * return work[0] # <<<<<<<<<<<<<< @@ -7248,18 +7322,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY * cdef void score_pair_sg_hs( */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyFloat_FromDouble((__pyx_v_work[0])); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 567, __pyx_L1_error) + __pyx_t_1 = PyFloat_FromDouble((__pyx_v_work[0])); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 806, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":510 + /* "gensim/models/word2vec_inner.pyx":727 + * * - * # Score is only implemented for hierarchical softmax * def score_sentence_sg(model, sentence, _work): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted skip-gram representation. * - * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ /* function exit code */ @@ -7278,7 +7352,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_4score_sentence_sg(CY return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":569 +/* "gensim/models/word2vec_inner.pyx":808 * return work[0] * * cdef void score_pair_sg_hs( # <<<<<<<<<<<<<< @@ -7293,12 +7367,13 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n PY_LONG_LONG __pyx_v_sgn; __pyx_t_6gensim_6models_14word2vec_inner_REAL_t __pyx_v_f; int __pyx_t_1; - PY_LONG_LONG __pyx_t_2; - int __pyx_t_3; + int __pyx_t_2; + PY_LONG_LONG __pyx_t_3; int __pyx_t_4; - long __pyx_t_5; + int __pyx_t_5; + long __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":575 + /* "gensim/models/word2vec_inner.pyx":814 * * cdef long long b * cdef long long row1 = word2_index * size, row2, sgn # <<<<<<<<<<<<<< @@ -7307,7 +7382,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ __pyx_v_row1 = (__pyx_v_word2_index * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":578 + /* "gensim/models/word2vec_inner.pyx":817 * cdef REAL_t f * * for b in range(codelen): # <<<<<<<<<<<<<< @@ -7315,10 +7390,11 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n * f = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = __pyx_v_codelen; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_b = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_b = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":579 + /* "gensim/models/word2vec_inner.pyx":818 * * for b in range(codelen): * row2 = word_point[b] * size # <<<<<<<<<<<<<< @@ -7327,7 +7403,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":580 + /* "gensim/models/word2vec_inner.pyx":819 * for b in range(codelen): * row2 = word_point[b] * size * f = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -7336,7 +7412,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), (&(__pyx_v_syn0[__pyx_v_row1])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":581 + /* "gensim/models/word2vec_inner.pyx":820 * row2 = word_point[b] * size * f = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 # <<<<<<<<<<<<<< @@ -7345,7 +7421,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ __pyx_v_sgn = __Pyx_pow_long(-1L, ((long)(__pyx_v_word_code[__pyx_v_b]))); - /* "gensim/models/word2vec_inner.pyx":582 + /* "gensim/models/word2vec_inner.pyx":821 * f = our_dot(&size, &syn0[row1], &ONE, &syn1[row2], &ONE) * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * f *= sgn # <<<<<<<<<<<<<< @@ -7354,25 +7430,25 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ __pyx_v_f = (__pyx_v_f * __pyx_v_sgn); - /* "gensim/models/word2vec_inner.pyx":583 + /* "gensim/models/word2vec_inner.pyx":822 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * f *= sgn * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = LOG_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L6_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L6_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":584 + /* "gensim/models/word2vec_inner.pyx":823 * f *= sgn * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -7381,7 +7457,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":583 + /* "gensim/models/word2vec_inner.pyx":822 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * f *= sgn * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -7390,7 +7466,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ } - /* "gensim/models/word2vec_inner.pyx":585 + /* "gensim/models/word2vec_inner.pyx":824 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = LOG_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -7399,19 +7475,19 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":586 + /* "gensim/models/word2vec_inner.pyx":825 * continue * f = LOG_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * work[0] += f # <<<<<<<<<<<<<< * * def score_sentence_cbow(model, sentence, _work, _neu1): */ - __pyx_t_5 = 0; - (__pyx_v_work[__pyx_t_5]) = ((__pyx_v_work[__pyx_t_5]) + __pyx_v_f); + __pyx_t_6 = 0; + (__pyx_v_work[__pyx_t_6]) = ((__pyx_v_work[__pyx_t_6]) + __pyx_v_f); __pyx_L3_continue:; } - /* "gensim/models/word2vec_inner.pyx":569 + /* "gensim/models/word2vec_inner.pyx":808 * return work[0] * * cdef void score_pair_sg_hs( # <<<<<<<<<<<<<< @@ -7422,17 +7498,18 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_sg_hs(__pyx_t_5n /* function exit code */ } -/* "gensim/models/word2vec_inner.pyx":588 +/* "gensim/models/word2vec_inner.pyx":827 * work[0] += f * * def score_sentence_cbow(model, sentence, _work, _neu1): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted CBOW representation. * - * cdef int cbow_mean = model.cbow_mean */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_7score_sentence_cbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_7score_sentence_cbow = {"score_sentence_cbow", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_7score_sentence_cbow, METH_VARARGS|METH_KEYWORDS, 0}; +static char __pyx_doc_6gensim_6models_14word2vec_inner_6score_sentence_cbow[] = "score_sentence_cbow(model, sentence, _work, _neu1)\nObtain likelihood score for a single sentence in a fitted CBOW representation.\n\n Notes\n -----\n This scoring function is only implemented for hierarchical softmax (`model.hs == 1`).\n The model should have been trained using the skip-gram model (`model.cbow` == 1`).\n\n Parameters\n ----------\n model : :class:`~gensim.models.word2vec.Word2Vec`\n The trained model. It **MUST** have been trained using hierarchical softmax and the CBOW algorithm.\n sentence : list of str\n The words comprising the sentence to be scored.\n _work : np.ndarray\n Private working memory for each worker.\n _neu1 : np.ndarray\n Private working memory for each worker.\n\n Returns\n -------\n float\n The probability assigned to this sentence by the Skip-Gram model.\n\n "; +static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_7score_sentence_cbow = {"score_sentence_cbow", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_7score_sentence_cbow, METH_VARARGS|METH_KEYWORDS, __pyx_doc_6gensim_6models_14word2vec_inner_6score_sentence_cbow}; static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_7score_sentence_cbow(PyObject *__pyx_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_model = 0; PyObject *__pyx_v_sentence = 0; @@ -7462,29 +7539,29 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_7score_sentence_cbow( kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_model)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_sentence)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_sentence)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, 1); __PYX_ERR(0, 588, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, 1); __PYX_ERR(0, 827, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_work)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, 2); __PYX_ERR(0, 588, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, 2); __PYX_ERR(0, 827, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_neu1)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_neu1)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, 3); __PYX_ERR(0, 588, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, 3); __PYX_ERR(0, 827, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "score_sentence_cbow") < 0)) __PYX_ERR(0, 588, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "score_sentence_cbow") < 0)) __PYX_ERR(0, 827, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 4) { goto __pyx_L5_argtuple_error; @@ -7501,7 +7578,7 @@ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_7score_sentence_cbow( } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 588, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("score_sentence_cbow", 1, 4, 4, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 827, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.models.word2vec_inner.score_sentence_cbow", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -7547,67 +7624,68 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_5numpy_uint32_t __pyx_t_9; Py_ssize_t __pyx_t_10; int __pyx_t_11; + int __pyx_t_12; __Pyx_RefNannySetupContext("score_sentence_cbow", 0); - /* "gensim/models/word2vec_inner.pyx":590 - * def score_sentence_cbow(model, sentence, _work, _neu1): + /* "gensim/models/word2vec_inner.pyx":852 * + * """ * cdef int cbow_mean = model.cbow_mean # <<<<<<<<<<<<<< * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 590, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_cbow_mean); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 852, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 590, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_cbow_mean = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":592 + /* "gensim/models/word2vec_inner.pyx":854 * cdef int cbow_mean = model.cbow_mean * * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) # <<<<<<<<<<<<<< * cdef REAL_t *work * cdef REAL_t *neu1 */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 592, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 854, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 592, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_vectors); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 854, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 592, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 854, __pyx_L1_error) __pyx_v_syn0 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":595 + /* "gensim/models/word2vec_inner.pyx":857 * cdef REAL_t *work * cdef REAL_t *neu1 * cdef int size = model.wv.vector_size # <<<<<<<<<<<<<< * * cdef int codelens[MAX_SENTENCE_LEN] */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 857, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vector_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 857, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 595, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 857, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_size = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":600 + /* "gensim/models/word2vec_inner.pyx":862 * cdef np.uint32_t indexes[MAX_SENTENCE_LEN] * cdef int sentence_len * cdef int window = model.window # <<<<<<<<<<<<<< * * cdef int i, j, k */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 600, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_window); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 862, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 600, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 862, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_v_window = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":603 + /* "gensim/models/word2vec_inner.pyx":865 * * cdef int i, j, k * cdef long result = 0 # <<<<<<<<<<<<<< @@ -7616,58 +7694,58 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_result = 0; - /* "gensim/models/word2vec_inner.pyx":610 + /* "gensim/models/word2vec_inner.pyx":872 * cdef np.uint8_t *codes[MAX_SENTENCE_LEN] * * syn1 = (np.PyArray_DATA(model.trainables.syn1)) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 610, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_trainables); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 872, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 610, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_syn1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 872, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 610, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 872, __pyx_L1_error) __pyx_v_syn1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":613 + /* "gensim/models/word2vec_inner.pyx":875 * * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) # <<<<<<<<<<<<<< * neu1 = np.PyArray_DATA(_neu1) * */ - if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 613, __pyx_L1_error) + if (!(likely(((__pyx_v__work) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__work, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 875, __pyx_L1_error) __pyx_v_work = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__work))); - /* "gensim/models/word2vec_inner.pyx":614 + /* "gensim/models/word2vec_inner.pyx":876 * # convert Python structures to primitive types, so we can release the GIL * work = np.PyArray_DATA(_work) * neu1 = np.PyArray_DATA(_neu1) # <<<<<<<<<<<<<< * * vlookup = model.wv.vocab */ - if (!(likely(((__pyx_v__neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 614, __pyx_L1_error) + if (!(likely(((__pyx_v__neu1) == Py_None) || likely(__Pyx_TypeTest(__pyx_v__neu1, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 876, __pyx_L1_error) __pyx_v_neu1 = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t *)PyArray_DATA(((PyArrayObject *)__pyx_v__neu1))); - /* "gensim/models/word2vec_inner.pyx":616 + /* "gensim/models/word2vec_inner.pyx":878 * neu1 = np.PyArray_DATA(_neu1) * * vlookup = model.wv.vocab # <<<<<<<<<<<<<< * i = 0 * for token in sentence: */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 616, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_model, __pyx_n_s_wv); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 878, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vocab); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 616, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_vocab); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 878, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_vlookup = __pyx_t_1; __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":617 + /* "gensim/models/word2vec_inner.pyx":879 * * vlookup = model.wv.vocab * i = 0 # <<<<<<<<<<<<<< @@ -7676,7 +7754,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_i = 0; - /* "gensim/models/word2vec_inner.pyx":618 + /* "gensim/models/word2vec_inner.pyx":880 * vlookup = model.wv.vocab * i = 0 * for token in sentence: # <<<<<<<<<<<<<< @@ -7687,26 +7765,26 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_1 = __pyx_v_sentence; __Pyx_INCREF(__pyx_t_1); __pyx_t_4 = 0; __pyx_t_5 = NULL; } else { - __pyx_t_4 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_sentence); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 618, __pyx_L1_error) + __pyx_t_4 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_sentence); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 880, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_5 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 618, __pyx_L1_error) + __pyx_t_5 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 880, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_5)) { if (likely(PyList_CheckExact(__pyx_t_1))) { if (__pyx_t_4 >= PyList_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_3); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 618, __pyx_L1_error) + __pyx_t_3 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_3); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 880, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 618, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 880, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { if (__pyx_t_4 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_3); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 618, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_4); __Pyx_INCREF(__pyx_t_3); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 880, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 618, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 880, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } @@ -7716,7 +7794,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 618, __pyx_L1_error) + else __PYX_ERR(0, 880, __pyx_L1_error) } break; } @@ -7725,16 +7803,16 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":619 + /* "gensim/models/word2vec_inner.pyx":881 * i = 0 * for token in sentence: * word = vlookup[token] if token in vlookup else None # <<<<<<<<<<<<<< * if word is None: * continue # for score, should this be a default negative value? */ - __pyx_t_6 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 619, __pyx_L1_error) + __pyx_t_6 = (__Pyx_PySequence_ContainsTF(__pyx_v_token, __pyx_v_vlookup, Py_EQ)); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 881, __pyx_L1_error) if ((__pyx_t_6 != 0)) { - __pyx_t_7 = PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 619, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetItem(__pyx_v_vlookup, __pyx_v_token); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 881, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_3 = __pyx_t_7; __pyx_t_7 = 0; @@ -7745,7 +7823,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __Pyx_XDECREF_SET(__pyx_v_word, __pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":620 + /* "gensim/models/word2vec_inner.pyx":882 * for token in sentence: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -7756,7 +7834,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_8 = (__pyx_t_6 != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":621 + /* "gensim/models/word2vec_inner.pyx":883 * word = vlookup[token] if token in vlookup else None * if word is None: * continue # for score, should this be a default negative value? # <<<<<<<<<<<<<< @@ -7765,7 +7843,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":620 + /* "gensim/models/word2vec_inner.pyx":882 * for token in sentence: * word = vlookup[token] if token in vlookup else None * if word is None: # <<<<<<<<<<<<<< @@ -7774,59 +7852,59 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ } - /* "gensim/models/word2vec_inner.pyx":622 + /* "gensim/models/word2vec_inner.pyx":884 * if word is None: * continue # for score, should this be a default negative value? * indexes[i] = word.index # <<<<<<<<<<<<<< * codelens[i] = len(word.code) * codes[i] = np.PyArray_DATA(word.code) */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 622, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_index); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 884, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_9 = __Pyx_PyInt_As_npy_uint32(__pyx_t_3); if (unlikely((__pyx_t_9 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 622, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyInt_As_npy_uint32(__pyx_t_3); if (unlikely((__pyx_t_9 == ((npy_uint32)-1)) && PyErr_Occurred())) __PYX_ERR(0, 884, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; (__pyx_v_indexes[__pyx_v_i]) = __pyx_t_9; - /* "gensim/models/word2vec_inner.pyx":623 + /* "gensim/models/word2vec_inner.pyx":885 * continue # for score, should this be a default negative value? * indexes[i] = word.index * codelens[i] = len(word.code) # <<<<<<<<<<<<<< * codes[i] = np.PyArray_DATA(word.code) * points[i] = np.PyArray_DATA(word.point) */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 623, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 885, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_10 == ((Py_ssize_t)-1))) __PYX_ERR(0, 623, __pyx_L1_error) + __pyx_t_10 = PyObject_Length(__pyx_t_3); if (unlikely(__pyx_t_10 == ((Py_ssize_t)-1))) __PYX_ERR(0, 885, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; (__pyx_v_codelens[__pyx_v_i]) = ((int)__pyx_t_10); - /* "gensim/models/word2vec_inner.pyx":624 + /* "gensim/models/word2vec_inner.pyx":886 * indexes[i] = word.index * codelens[i] = len(word.code) * codes[i] = np.PyArray_DATA(word.code) # <<<<<<<<<<<<<< * points[i] = np.PyArray_DATA(word.point) * result += 1 */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 624, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_code); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 886, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 624, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 886, __pyx_L1_error) (__pyx_v_codes[__pyx_v_i]) = ((__pyx_t_5numpy_uint8_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":625 + /* "gensim/models/word2vec_inner.pyx":887 * codelens[i] = len(word.code) * codes[i] = np.PyArray_DATA(word.code) * points[i] = np.PyArray_DATA(word.point) # <<<<<<<<<<<<<< * result += 1 * i += 1 */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 625, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_word, __pyx_n_s_point); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 887, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 625, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_ndarray))))) __PYX_ERR(0, 887, __pyx_L1_error) (__pyx_v_points[__pyx_v_i]) = ((__pyx_t_5numpy_uint32_t *)PyArray_DATA(((PyArrayObject *)__pyx_t_3))); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/models/word2vec_inner.pyx":626 + /* "gensim/models/word2vec_inner.pyx":888 * codes[i] = np.PyArray_DATA(word.code) * points[i] = np.PyArray_DATA(word.point) * result += 1 # <<<<<<<<<<<<<< @@ -7835,7 +7913,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_result = (__pyx_v_result + 1); - /* "gensim/models/word2vec_inner.pyx":627 + /* "gensim/models/word2vec_inner.pyx":889 * points[i] = np.PyArray_DATA(word.point) * result += 1 * i += 1 # <<<<<<<<<<<<<< @@ -7844,7 +7922,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_i = (__pyx_v_i + 1); - /* "gensim/models/word2vec_inner.pyx":628 + /* "gensim/models/word2vec_inner.pyx":890 * result += 1 * i += 1 * if i == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -7854,7 +7932,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_8 = ((__pyx_v_i == 0x2710) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":629 + /* "gensim/models/word2vec_inner.pyx":891 * i += 1 * if i == MAX_SENTENCE_LEN: * break # TODO: log warning, tally overflow? # <<<<<<<<<<<<<< @@ -7863,7 +7941,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ goto __pyx_L4_break; - /* "gensim/models/word2vec_inner.pyx":628 + /* "gensim/models/word2vec_inner.pyx":890 * result += 1 * i += 1 * if i == MAX_SENTENCE_LEN: # <<<<<<<<<<<<<< @@ -7872,7 +7950,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ } - /* "gensim/models/word2vec_inner.pyx":618 + /* "gensim/models/word2vec_inner.pyx":880 * vlookup = model.wv.vocab * i = 0 * for token in sentence: # <<<<<<<<<<<<<< @@ -7884,7 +7962,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_L4_break:; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":630 + /* "gensim/models/word2vec_inner.pyx":892 * if i == MAX_SENTENCE_LEN: * break # TODO: log warning, tally overflow? * sentence_len = i # <<<<<<<<<<<<<< @@ -7893,7 +7971,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_sentence_len = __pyx_v_i; - /* "gensim/models/word2vec_inner.pyx":633 + /* "gensim/models/word2vec_inner.pyx":895 * * # release GIL & train on the sentence * work[0] = 0.0 # <<<<<<<<<<<<<< @@ -7902,7 +7980,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ (__pyx_v_work[0]) = 0.0; - /* "gensim/models/word2vec_inner.pyx":634 + /* "gensim/models/word2vec_inner.pyx":896 * # release GIL & train on the sentence * work[0] = 0.0 * with nogil: # <<<<<<<<<<<<<< @@ -7917,7 +7995,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( #endif /*try:*/ { - /* "gensim/models/word2vec_inner.pyx":635 + /* "gensim/models/word2vec_inner.pyx":897 * work[0] = 0.0 * with nogil: * for i in range(sentence_len): # <<<<<<<<<<<<<< @@ -7925,10 +8003,11 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( * continue */ __pyx_t_2 = __pyx_v_sentence_len; - for (__pyx_t_11 = 0; __pyx_t_11 < __pyx_t_2; __pyx_t_11+=1) { - __pyx_v_i = __pyx_t_11; + __pyx_t_11 = __pyx_t_2; + for (__pyx_t_12 = 0; __pyx_t_12 < __pyx_t_11; __pyx_t_12+=1) { + __pyx_v_i = __pyx_t_12; - /* "gensim/models/word2vec_inner.pyx":636 + /* "gensim/models/word2vec_inner.pyx":898 * with nogil: * for i in range(sentence_len): * if codelens[i] == 0: # <<<<<<<<<<<<<< @@ -7938,7 +8017,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_8 = (((__pyx_v_codelens[__pyx_v_i]) == 0) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":637 + /* "gensim/models/word2vec_inner.pyx":899 * for i in range(sentence_len): * if codelens[i] == 0: * continue # <<<<<<<<<<<<<< @@ -7947,7 +8026,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ goto __pyx_L10_continue; - /* "gensim/models/word2vec_inner.pyx":636 + /* "gensim/models/word2vec_inner.pyx":898 * with nogil: * for i in range(sentence_len): * if codelens[i] == 0: # <<<<<<<<<<<<<< @@ -7956,7 +8035,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ } - /* "gensim/models/word2vec_inner.pyx":638 + /* "gensim/models/word2vec_inner.pyx":900 * if codelens[i] == 0: * continue * j = i - window # <<<<<<<<<<<<<< @@ -7965,7 +8044,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_j = (__pyx_v_i - __pyx_v_window); - /* "gensim/models/word2vec_inner.pyx":639 + /* "gensim/models/word2vec_inner.pyx":901 * continue * j = i - window * if j < 0: # <<<<<<<<<<<<<< @@ -7975,7 +8054,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_8 = ((__pyx_v_j < 0) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":640 + /* "gensim/models/word2vec_inner.pyx":902 * j = i - window * if j < 0: * j = 0 # <<<<<<<<<<<<<< @@ -7984,7 +8063,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_j = 0; - /* "gensim/models/word2vec_inner.pyx":639 + /* "gensim/models/word2vec_inner.pyx":901 * continue * j = i - window * if j < 0: # <<<<<<<<<<<<<< @@ -7993,7 +8072,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ } - /* "gensim/models/word2vec_inner.pyx":641 + /* "gensim/models/word2vec_inner.pyx":903 * if j < 0: * j = 0 * k = i + window + 1 # <<<<<<<<<<<<<< @@ -8002,7 +8081,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_k = ((__pyx_v_i + __pyx_v_window) + 1); - /* "gensim/models/word2vec_inner.pyx":642 + /* "gensim/models/word2vec_inner.pyx":904 * j = 0 * k = i + window + 1 * if k > sentence_len: # <<<<<<<<<<<<<< @@ -8012,7 +8091,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( __pyx_t_8 = ((__pyx_v_k > __pyx_v_sentence_len) != 0); if (__pyx_t_8) { - /* "gensim/models/word2vec_inner.pyx":643 + /* "gensim/models/word2vec_inner.pyx":905 * k = i + window + 1 * if k > sentence_len: * k = sentence_len # <<<<<<<<<<<<<< @@ -8021,7 +8100,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ __pyx_v_k = __pyx_v_sentence_len; - /* "gensim/models/word2vec_inner.pyx":642 + /* "gensim/models/word2vec_inner.pyx":904 * j = 0 * k = i + window + 1 * if k > sentence_len: # <<<<<<<<<<<<<< @@ -8030,7 +8109,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( */ } - /* "gensim/models/word2vec_inner.pyx":644 + /* "gensim/models/word2vec_inner.pyx":906 * if k > sentence_len: * k = sentence_len * score_pair_cbow_hs(points[i], codes[i], codelens, neu1, syn0, syn1, size, indexes, work, i, j, k, cbow_mean) # <<<<<<<<<<<<<< @@ -8042,7 +8121,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( } } - /* "gensim/models/word2vec_inner.pyx":634 + /* "gensim/models/word2vec_inner.pyx":896 * # release GIL & train on the sentence * work[0] = 0.0 * with nogil: # <<<<<<<<<<<<<< @@ -8061,7 +8140,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( } } - /* "gensim/models/word2vec_inner.pyx":646 + /* "gensim/models/word2vec_inner.pyx":908 * score_pair_cbow_hs(points[i], codes[i], codelens, neu1, syn0, syn1, size, indexes, work, i, j, k, cbow_mean) * * return work[0] # <<<<<<<<<<<<<< @@ -8069,18 +8148,18 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( * cdef void score_pair_cbow_hs( */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyFloat_FromDouble((__pyx_v_work[0])); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 646, __pyx_L1_error) + __pyx_t_1 = PyFloat_FromDouble((__pyx_v_work[0])); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 908, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":588 + /* "gensim/models/word2vec_inner.pyx":827 * work[0] += f * * def score_sentence_cbow(model, sentence, _work, _neu1): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted CBOW representation. * - * cdef int cbow_mean = model.cbow_mean */ /* function exit code */ @@ -8099,7 +8178,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_6score_sentence_cbow( return __pyx_r; } -/* "gensim/models/word2vec_inner.pyx":648 +/* "gensim/models/word2vec_inner.pyx":910 * return work[0] * * cdef void score_pair_cbow_hs( # <<<<<<<<<<<<<< @@ -8119,19 +8198,20 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ int __pyx_t_2; int __pyx_t_3; int __pyx_t_4; - PY_LONG_LONG __pyx_t_5; - long __pyx_t_6; + int __pyx_t_5; + PY_LONG_LONG __pyx_t_6; + long __pyx_t_7; - /* "gensim/models/word2vec_inner.pyx":659 + /* "gensim/models/word2vec_inner.pyx":921 * cdef int m * * memset(neu1, 0, size * cython.sizeof(REAL_t)) # <<<<<<<<<<<<<< * count = 0.0 * for m in range(j, k): */ - memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)))); + (void)(memset(__pyx_v_neu1, 0, (__pyx_v_size * (sizeof(__pyx_t_6gensim_6models_14word2vec_inner_REAL_t))))); - /* "gensim/models/word2vec_inner.pyx":660 + /* "gensim/models/word2vec_inner.pyx":922 * * memset(neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 # <<<<<<<<<<<<<< @@ -8140,7 +8220,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_count = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.0); - /* "gensim/models/word2vec_inner.pyx":661 + /* "gensim/models/word2vec_inner.pyx":923 * memset(neu1, 0, size * cython.sizeof(REAL_t)) * count = 0.0 * for m in range(j, k): # <<<<<<<<<<<<<< @@ -8148,28 +8228,29 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ * continue */ __pyx_t_1 = __pyx_v_k; - for (__pyx_t_2 = __pyx_v_j; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_m = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = __pyx_v_j; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_m = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":662 + /* "gensim/models/word2vec_inner.pyx":924 * count = 0.0 * for m in range(j, k): * if m == i or codelens[m] == 0: # <<<<<<<<<<<<<< * continue * else: */ - __pyx_t_4 = ((__pyx_v_m == __pyx_v_i) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_m == __pyx_v_i) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L6_bool_binop_done; } - __pyx_t_4 = (((__pyx_v_codelens[__pyx_v_m]) == 0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = (((__pyx_v_codelens[__pyx_v_m]) == 0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L6_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":663 + /* "gensim/models/word2vec_inner.pyx":925 * for m in range(j, k): * if m == i or codelens[m] == 0: * continue # <<<<<<<<<<<<<< @@ -8178,7 +8259,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ goto __pyx_L3_continue; - /* "gensim/models/word2vec_inner.pyx":662 + /* "gensim/models/word2vec_inner.pyx":924 * count = 0.0 * for m in range(j, k): * if m == i or codelens[m] == 0: # <<<<<<<<<<<<<< @@ -8187,7 +8268,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ } - /* "gensim/models/word2vec_inner.pyx":665 + /* "gensim/models/word2vec_inner.pyx":927 * continue * else: * count += ONEF # <<<<<<<<<<<<<< @@ -8197,7 +8278,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ /*else*/ { __pyx_v_count = (__pyx_v_count + __pyx_v_6gensim_6models_14word2vec_inner_ONEF); - /* "gensim/models/word2vec_inner.pyx":666 + /* "gensim/models/word2vec_inner.pyx":928 * else: * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) # <<<<<<<<<<<<<< @@ -8209,17 +8290,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ __pyx_L3_continue:; } - /* "gensim/models/word2vec_inner.pyx":667 + /* "gensim/models/word2vec_inner.pyx":929 * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< * inv_count = ONEF/count * if cbow_mean: */ - __pyx_t_3 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_count > ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0.5)) != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":668 + /* "gensim/models/word2vec_inner.pyx":930 * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): * inv_count = ONEF/count # <<<<<<<<<<<<<< @@ -8228,7 +8309,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_inv_count = (__pyx_v_6gensim_6models_14word2vec_inner_ONEF / __pyx_v_count); - /* "gensim/models/word2vec_inner.pyx":667 + /* "gensim/models/word2vec_inner.pyx":929 * count += ONEF * our_saxpy(&size, &ONEF, &syn0[indexes[m] * size], &ONE, neu1, &ONE) * if count > (0.5): # <<<<<<<<<<<<<< @@ -8237,17 +8318,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ } - /* "gensim/models/word2vec_inner.pyx":669 + /* "gensim/models/word2vec_inner.pyx":931 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< * sscal(&size, &inv_count, neu1, &ONE) * */ - __pyx_t_3 = (__pyx_v_cbow_mean != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_cbow_mean != 0); + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":670 + /* "gensim/models/word2vec_inner.pyx":932 * inv_count = ONEF/count * if cbow_mean: * sscal(&size, &inv_count, neu1, &ONE) # <<<<<<<<<<<<<< @@ -8256,7 +8337,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_6gensim_6models_14word2vec_inner_sscal((&__pyx_v_size), (&__pyx_v_inv_count), __pyx_v_neu1, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":669 + /* "gensim/models/word2vec_inner.pyx":931 * if count > (0.5): * inv_count = ONEF/count * if cbow_mean: # <<<<<<<<<<<<<< @@ -8265,7 +8346,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ } - /* "gensim/models/word2vec_inner.pyx":672 + /* "gensim/models/word2vec_inner.pyx":934 * sscal(&size, &inv_count, neu1, &ONE) * * for b in range(codelens[i]): # <<<<<<<<<<<<<< @@ -8273,10 +8354,11 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) */ __pyx_t_1 = (__pyx_v_codelens[__pyx_v_i]); - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_1; __pyx_t_5+=1) { - __pyx_v_b = __pyx_t_5; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_2; __pyx_t_6+=1) { + __pyx_v_b = __pyx_t_6; - /* "gensim/models/word2vec_inner.pyx":673 + /* "gensim/models/word2vec_inner.pyx":935 * * for b in range(codelens[i]): * row2 = word_point[b] * size # <<<<<<<<<<<<<< @@ -8285,7 +8367,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_row2 = ((__pyx_v_word_point[__pyx_v_b]) * __pyx_v_size); - /* "gensim/models/word2vec_inner.pyx":674 + /* "gensim/models/word2vec_inner.pyx":936 * for b in range(codelens[i]): * row2 = word_point[b] * size * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) # <<<<<<<<<<<<<< @@ -8294,7 +8376,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_f = __pyx_v_6gensim_6models_14word2vec_inner_our_dot((&__pyx_v_size), __pyx_v_neu1, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), (&(__pyx_v_syn1[__pyx_v_row2])), (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":675 + /* "gensim/models/word2vec_inner.pyx":937 * row2 = word_point[b] * size * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 # <<<<<<<<<<<<<< @@ -8303,7 +8385,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_sgn = __Pyx_pow_long(-1L, ((long)(__pyx_v_word_code[__pyx_v_b]))); - /* "gensim/models/word2vec_inner.pyx":676 + /* "gensim/models/word2vec_inner.pyx":938 * f = our_dot(&size, neu1, &ONE, &syn1[row2], &ONE) * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * f *= sgn # <<<<<<<<<<<<<< @@ -8312,25 +8394,25 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_f = (__pyx_v_f * __pyx_v_sgn); - /* "gensim/models/word2vec_inner.pyx":677 + /* "gensim/models/word2vec_inner.pyx":939 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * f *= sgn * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< * continue * f = LOG_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] */ - __pyx_t_4 = ((__pyx_v_f <= -6.0) != 0); - if (!__pyx_t_4) { + __pyx_t_5 = ((__pyx_v_f <= -6.0) != 0); + if (!__pyx_t_5) { } else { - __pyx_t_3 = __pyx_t_4; + __pyx_t_4 = __pyx_t_5; goto __pyx_L13_bool_binop_done; } - __pyx_t_4 = ((__pyx_v_f >= 6.0) != 0); - __pyx_t_3 = __pyx_t_4; + __pyx_t_5 = ((__pyx_v_f >= 6.0) != 0); + __pyx_t_4 = __pyx_t_5; __pyx_L13_bool_binop_done:; - if (__pyx_t_3) { + if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":678 + /* "gensim/models/word2vec_inner.pyx":940 * f *= sgn * if f <= -MAX_EXP or f >= MAX_EXP: * continue # <<<<<<<<<<<<<< @@ -8339,7 +8421,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ goto __pyx_L10_continue; - /* "gensim/models/word2vec_inner.pyx":677 + /* "gensim/models/word2vec_inner.pyx":939 * sgn = (-1)**word_code[b] # ch function: 0-> 1, 1 -> -1 * f *= sgn * if f <= -MAX_EXP or f >= MAX_EXP: # <<<<<<<<<<<<<< @@ -8348,7 +8430,7 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ } - /* "gensim/models/word2vec_inner.pyx":679 + /* "gensim/models/word2vec_inner.pyx":941 * if f <= -MAX_EXP or f >= MAX_EXP: * continue * f = LOG_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] # <<<<<<<<<<<<<< @@ -8357,19 +8439,19 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ */ __pyx_v_f = (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[((int)((__pyx_v_f + 6.0) * 83.0))]); - /* "gensim/models/word2vec_inner.pyx":680 + /* "gensim/models/word2vec_inner.pyx":942 * continue * f = LOG_TABLE[((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))] * work[0] += f # <<<<<<<<<<<<<< * * */ - __pyx_t_6 = 0; - (__pyx_v_work[__pyx_t_6]) = ((__pyx_v_work[__pyx_t_6]) + __pyx_v_f); + __pyx_t_7 = 0; + (__pyx_v_work[__pyx_t_7]) = ((__pyx_v_work[__pyx_t_7]) + __pyx_v_f); __pyx_L10_continue:; } - /* "gensim/models/word2vec_inner.pyx":648 + /* "gensim/models/word2vec_inner.pyx":910 * return work[0] * * cdef void score_pair_cbow_hs( # <<<<<<<<<<<<<< @@ -8380,17 +8462,17 @@ static void __pyx_f_6gensim_6models_14word2vec_inner_score_pair_cbow_hs(__pyx_t_ /* function exit code */ } -/* "gensim/models/word2vec_inner.pyx":683 +/* "gensim/models/word2vec_inner.pyx":945 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_9init(PyObject *__pyx_self, CYTHON_UNUSED PyObject *unused); /*proto*/ -static char __pyx_doc_6gensim_6models_14word2vec_inner_8init[] = "\n Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized\n into table EXP_TABLE. Also calculate log(sigmoid(x)) into LOG_TABLE.\n\n "; +static char __pyx_doc_6gensim_6models_14word2vec_inner_8init[] = "init()\nPrecompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE.\n Also calculate log(sigmoid(x)) into LOG_TABLE.\n\n Returns\n -------\n {0, 1, 2}\n Enumeration to signify underlying data type returned by the BLAS dot product calculation.\n 0 signifies double, 1 signifies double, and 2 signifies that custom cython loops were used\n instead of BLAS.\n\n "; static PyMethodDef __pyx_mdef_6gensim_6models_14word2vec_inner_9init = {"init", (PyCFunction)__pyx_pw_6gensim_6models_14word2vec_inner_9init, METH_NOARGS, __pyx_doc_6gensim_6models_14word2vec_inner_8init}; static PyObject *__pyx_pw_6gensim_6models_14word2vec_inner_9init(PyObject *__pyx_self, CYTHON_UNUSED PyObject *unused) { PyObject *__pyx_r = 0; @@ -8419,7 +8501,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P int __pyx_t_4; __Pyx_RefNannySetupContext("init", 0); - /* "gensim/models/word2vec_inner.pyx":693 + /* "gensim/models/word2vec_inner.pyx":961 * * cdef int i * cdef float *x = [10.0] # <<<<<<<<<<<<<< @@ -8429,7 +8511,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P __pyx_t_1[0] = ((float)10.0); __pyx_v_x = __pyx_t_1; - /* "gensim/models/word2vec_inner.pyx":694 + /* "gensim/models/word2vec_inner.pyx":962 * cdef int i * cdef float *x = [10.0] * cdef float *y = [0.01] # <<<<<<<<<<<<<< @@ -8439,7 +8521,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P __pyx_t_2[0] = ((float)0.01); __pyx_v_y = __pyx_t_2; - /* "gensim/models/word2vec_inner.pyx":695 + /* "gensim/models/word2vec_inner.pyx":963 * cdef float *x = [10.0] * cdef float *y = [0.01] * cdef float expected = 0.1 # <<<<<<<<<<<<<< @@ -8448,7 +8530,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P */ __pyx_v_expected = ((float)0.1); - /* "gensim/models/word2vec_inner.pyx":696 + /* "gensim/models/word2vec_inner.pyx":964 * cdef float *y = [0.01] * cdef float expected = 0.1 * cdef int size = 1 # <<<<<<<<<<<<<< @@ -8457,7 +8539,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P */ __pyx_v_size = 1; - /* "gensim/models/word2vec_inner.pyx":701 + /* "gensim/models/word2vec_inner.pyx":969 * * # build the sigmoid table * for i in range(EXP_TABLE_SIZE): # <<<<<<<<<<<<<< @@ -8467,7 +8549,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P for (__pyx_t_3 = 0; __pyx_t_3 < 0x3E8; __pyx_t_3+=1) { __pyx_v_i = __pyx_t_3; - /* "gensim/models/word2vec_inner.pyx":702 + /* "gensim/models/word2vec_inner.pyx":970 * # build the sigmoid table * for i in range(EXP_TABLE_SIZE): * EXP_TABLE[i] = exp((i / EXP_TABLE_SIZE * 2 - 1) * MAX_EXP) # <<<<<<<<<<<<<< @@ -8476,7 +8558,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P */ (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)exp(((((__pyx_v_i / ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)0x3E8)) * 2.0) - 1.0) * 6.0))); - /* "gensim/models/word2vec_inner.pyx":703 + /* "gensim/models/word2vec_inner.pyx":971 * for i in range(EXP_TABLE_SIZE): * EXP_TABLE[i] = exp((i / EXP_TABLE_SIZE * 2 - 1) * MAX_EXP) * EXP_TABLE[i] = (EXP_TABLE[i] / (EXP_TABLE[i] + 1)) # <<<<<<<<<<<<<< @@ -8485,7 +8567,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P */ (__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)((__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) / ((__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]) + 1.0))); - /* "gensim/models/word2vec_inner.pyx":704 + /* "gensim/models/word2vec_inner.pyx":972 * EXP_TABLE[i] = exp((i / EXP_TABLE_SIZE * 2 - 1) * MAX_EXP) * EXP_TABLE[i] = (EXP_TABLE[i] / (EXP_TABLE[i] + 1)) * LOG_TABLE[i] = log( EXP_TABLE[i] ) # <<<<<<<<<<<<<< @@ -8495,57 +8577,57 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P (__pyx_v_6gensim_6models_14word2vec_inner_LOG_TABLE[__pyx_v_i]) = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)log((__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE[__pyx_v_i]))); } - /* "gensim/models/word2vec_inner.pyx":707 + /* "gensim/models/word2vec_inner.pyx":975 * * # check whether sdot returns double or float * d_res = dsdot(&size, x, &ONE, y, &ONE) # <<<<<<<<<<<<<< * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): + * if abs(d_res - expected) < 0.0001: */ __pyx_v_d_res = __pyx_v_6gensim_6models_14word2vec_inner_dsdot((&__pyx_v_size), __pyx_v_x, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE), __pyx_v_y, (&__pyx_v_6gensim_6models_14word2vec_inner_ONE)); - /* "gensim/models/word2vec_inner.pyx":708 + /* "gensim/models/word2vec_inner.pyx":976 * # check whether sdot returns double or float * d_res = dsdot(&size, x, &ONE, y, &ONE) * p_res = &d_res # <<<<<<<<<<<<<< - * if (abs(d_res - expected) < 0.0001): + * if abs(d_res - expected) < 0.0001: * our_dot = our_dot_double */ __pyx_v_p_res = ((float *)(&__pyx_v_d_res)); - /* "gensim/models/word2vec_inner.pyx":709 + /* "gensim/models/word2vec_inner.pyx":977 * d_res = dsdot(&size, x, &ONE, y, &ONE) * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): # <<<<<<<<<<<<<< + * if abs(d_res - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_double * our_saxpy = saxpy */ __pyx_t_4 = ((fabs((__pyx_v_d_res - __pyx_v_expected)) < 0.0001) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":710 + /* "gensim/models/word2vec_inner.pyx":978 * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): + * if abs(d_res - expected) < 0.0001: * our_dot = our_dot_double # <<<<<<<<<<<<<< * our_saxpy = saxpy * return 0 # double */ __pyx_v_6gensim_6models_14word2vec_inner_our_dot = __pyx_f_6gensim_6models_14word2vec_inner_our_dot_double; - /* "gensim/models/word2vec_inner.pyx":711 - * if (abs(d_res - expected) < 0.0001): + /* "gensim/models/word2vec_inner.pyx":979 + * if abs(d_res - expected) < 0.0001: * our_dot = our_dot_double * our_saxpy = saxpy # <<<<<<<<<<<<<< * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): + * elif abs(p_res[0] - expected) < 0.0001: */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy = __pyx_v_6gensim_6models_14word2vec_inner_saxpy; - /* "gensim/models/word2vec_inner.pyx":712 + /* "gensim/models/word2vec_inner.pyx":980 * our_dot = our_dot_double * our_saxpy = saxpy * return 0 # double # <<<<<<<<<<<<<< - * elif (abs(p_res[0] - expected) < 0.0001): + * elif abs(p_res[0] - expected) < 0.0001: * our_dot = our_dot_float */ __Pyx_XDECREF(__pyx_r); @@ -8553,36 +8635,36 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P __pyx_r = __pyx_int_0; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":709 + /* "gensim/models/word2vec_inner.pyx":977 * d_res = dsdot(&size, x, &ONE, y, &ONE) * p_res = &d_res - * if (abs(d_res - expected) < 0.0001): # <<<<<<<<<<<<<< + * if abs(d_res - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_double * our_saxpy = saxpy */ } - /* "gensim/models/word2vec_inner.pyx":713 + /* "gensim/models/word2vec_inner.pyx":981 * our_saxpy = saxpy * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): # <<<<<<<<<<<<<< + * elif abs(p_res[0] - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_float * our_saxpy = saxpy */ __pyx_t_4 = ((fabsf(((__pyx_v_p_res[0]) - __pyx_v_expected)) < 0.0001) != 0); if (__pyx_t_4) { - /* "gensim/models/word2vec_inner.pyx":714 + /* "gensim/models/word2vec_inner.pyx":982 * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): + * elif abs(p_res[0] - expected) < 0.0001: * our_dot = our_dot_float # <<<<<<<<<<<<<< * our_saxpy = saxpy * return 1 # float */ __pyx_v_6gensim_6models_14word2vec_inner_our_dot = __pyx_f_6gensim_6models_14word2vec_inner_our_dot_float; - /* "gensim/models/word2vec_inner.pyx":715 - * elif (abs(p_res[0] - expected) < 0.0001): + /* "gensim/models/word2vec_inner.pyx":983 + * elif abs(p_res[0] - expected) < 0.0001: * our_dot = our_dot_float * our_saxpy = saxpy # <<<<<<<<<<<<<< * return 1 # float @@ -8590,7 +8672,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy = __pyx_v_6gensim_6models_14word2vec_inner_saxpy; - /* "gensim/models/word2vec_inner.pyx":716 + /* "gensim/models/word2vec_inner.pyx":984 * our_dot = our_dot_float * our_saxpy = saxpy * return 1 # float # <<<<<<<<<<<<<< @@ -8602,16 +8684,16 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P __pyx_r = __pyx_int_1; goto __pyx_L0; - /* "gensim/models/word2vec_inner.pyx":713 + /* "gensim/models/word2vec_inner.pyx":981 * our_saxpy = saxpy * return 0 # double - * elif (abs(p_res[0] - expected) < 0.0001): # <<<<<<<<<<<<<< + * elif abs(p_res[0] - expected) < 0.0001: # <<<<<<<<<<<<<< * our_dot = our_dot_float * our_saxpy = saxpy */ } - /* "gensim/models/word2vec_inner.pyx":720 + /* "gensim/models/word2vec_inner.pyx":988 * # neither => use cython loops, no BLAS * # actually, the BLAS is so messed up we'll probably have segfaulted above and never even reach here * our_dot = our_dot_noblas # <<<<<<<<<<<<<< @@ -8621,7 +8703,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P /*else*/ { __pyx_v_6gensim_6models_14word2vec_inner_our_dot = __pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas; - /* "gensim/models/word2vec_inner.pyx":721 + /* "gensim/models/word2vec_inner.pyx":989 * # actually, the BLAS is so messed up we'll probably have segfaulted above and never even reach here * our_dot = our_dot_noblas * our_saxpy = our_saxpy_noblas # <<<<<<<<<<<<<< @@ -8630,7 +8712,7 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P */ __pyx_v_6gensim_6models_14word2vec_inner_our_saxpy = __pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas; - /* "gensim/models/word2vec_inner.pyx":722 + /* "gensim/models/word2vec_inner.pyx":990 * our_dot = our_dot_noblas * our_saxpy = our_saxpy_noblas * return 2 # <<<<<<<<<<<<<< @@ -8643,12 +8725,12 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P goto __pyx_L0; } - /* "gensim/models/word2vec_inner.pyx":683 + /* "gensim/models/word2vec_inner.pyx":945 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ /* function exit code */ @@ -8658,12 +8740,12 @@ static PyObject *__pyx_pf_6gensim_6models_14word2vec_inner_8init(CYTHON_UNUSED P return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* Python wrapper */ @@ -8680,7 +8762,6 @@ static CYTHON_UNUSED int __pyx_pw_5numpy_7ndarray_1__getbuffer__(PyObject *__pyx } static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags) { - int __pyx_v_copy_shape; int __pyx_v_i; int __pyx_v_ndim; int __pyx_v_endian_detector; @@ -8689,7 +8770,6 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P char *__pyx_v_f; PyArray_Descr *__pyx_v_descr = 0; int __pyx_v_offset; - int __pyx_v_hasfields; int __pyx_r; __Pyx_RefNannyDeclarations int __pyx_t_1; @@ -8697,38 +8777,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P PyObject *__pyx_t_3 = NULL; int __pyx_t_4; int __pyx_t_5; - PyObject *__pyx_t_6 = NULL; - char *__pyx_t_7; - __Pyx_RefNannySetupContext("__getbuffer__", 0); - if (__pyx_v_info != NULL) { - __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(__pyx_v_info->obj); - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":220 - * # of flags - * - * if info == NULL: return # <<<<<<<<<<<<<< - * - * cdef int copy_shape, i, ndim - */ - __pyx_t_1 = ((__pyx_v_info == NULL) != 0); - if (__pyx_t_1) { - __pyx_r = 0; - goto __pyx_L0; + int __pyx_t_6; + PyObject *__pyx_t_7 = NULL; + char *__pyx_t_8; + if (__pyx_v_info == NULL) { + PyErr_SetString(PyExc_BufferError, "PyObject_GetBuffer: view==NULL argument is obsolete"); + return -1; } + __Pyx_RefNannySetupContext("__getbuffer__", 0); + __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); + __Pyx_GIVEREF(__pyx_v_info->obj); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":222 * - * cdef int copy_shape, i, ndim + * cdef int i, ndim * cdef int endian_detector = 1 # <<<<<<<<<<<<<< * cdef bint little_endian = ((&endian_detector)[0] != 0) * */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":224 - * cdef int copy_shape, i, ndim + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + * cdef int i, ndim * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< * @@ -8736,59 +8806,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":226 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":225 * cdef bint little_endian = ((&endian_detector)[0] != 0) * * ndim = PyArray_NDIM(self) # <<<<<<<<<<<<<< * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): + * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) */ __pyx_v_ndim = PyArray_NDIM(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 - * ndim = PyArray_NDIM(self) - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): - * copy_shape = 1 # <<<<<<<<<<<<<< - * else: - * copy_shape = 0 - */ - __pyx_v_copy_shape = 1; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 * ndim = PyArray_NDIM(self) * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - goto __pyx_L4; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 - * copy_shape = 1 - * else: - * copy_shape = 0 # <<<<<<<<<<<<<< - * - * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) - */ - /*else*/ { - __pyx_v_copy_shape = 0; - } - __pyx_L4:; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 - * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") @@ -8797,10 +8826,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L6_bool_binop_done; + goto __pyx_L4_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":234 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -8809,32 +8838,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_C_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L6_bool_binop_done:; + __pyx_L4_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 235, __pyx_L1_error) + __PYX_ERR(1, 229, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): @@ -8842,7 +8871,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -8853,10 +8882,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L9_bool_binop_done; + goto __pyx_L7_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":238 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":232 * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -8865,31 +8894,31 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_F_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L9_bool_binop_done:; + __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 239, __pyx_L1_error) + __PYX_ERR(1, 233, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -8898,35 +8927,35 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 * raise ValueError(u"ndarray is not Fortran contiguous") * * info.buf = PyArray_DATA(self) # <<<<<<<<<<<<<< * info.ndim = ndim - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): */ __pyx_v_info->buf = PyArray_DATA(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":236 * * info.buf = PyArray_DATA(self) * info.ndim = ndim # <<<<<<<<<<<<<< - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): * # Allocate new buffer for strides and shape info. */ __pyx_v_info->ndim = __pyx_v_ndim; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - __pyx_t_1 = (__pyx_v_copy_shape != 0); + __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":240 * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) # <<<<<<<<<<<<<< @@ -8935,7 +8964,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->strides = ((Py_ssize_t *)PyObject_Malloc((((sizeof(Py_ssize_t)) * 2) * ((size_t)__pyx_v_ndim)))); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim # <<<<<<<<<<<<<< @@ -8944,7 +8973,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = (__pyx_v_info->strides + __pyx_v_ndim); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim * for i in range(ndim): # <<<<<<<<<<<<<< @@ -8952,10 +8981,11 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P * info.shape[i] = PyArray_DIMS(self)[i] */ __pyx_t_4 = __pyx_v_ndim; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 * info.shape = info.strides + ndim * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] # <<<<<<<<<<<<<< @@ -8964,7 +8994,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->strides[__pyx_v_i]) = (PyArray_STRIDES(__pyx_v_self)[__pyx_v_i]); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":244 * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] * info.shape[i] = PyArray_DIMS(self)[i] # <<<<<<<<<<<<<< @@ -8974,17 +9004,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_info->shape[__pyx_v_i]) = (PyArray_DIMS(__pyx_v_self)[__pyx_v_i]); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - goto __pyx_L11; + goto __pyx_L9; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":252 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 * info.shape[i] = PyArray_DIMS(self)[i] * else: * info.strides = PyArray_STRIDES(self) # <<<<<<<<<<<<<< @@ -8994,7 +9024,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->strides = ((Py_ssize_t *)PyArray_STRIDES(__pyx_v_self)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 * else: * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) # <<<<<<<<<<<<<< @@ -9003,9 +9033,9 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = ((Py_ssize_t *)PyArray_DIMS(__pyx_v_self)); } - __pyx_L11:; + __pyx_L9:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL # <<<<<<<<<<<<<< @@ -9014,7 +9044,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->suboffsets = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":255 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) # <<<<<<<<<<<<<< @@ -9023,7 +9053,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->itemsize = PyArray_ITEMSIZE(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":256 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) * info.readonly = not PyArray_ISWRITEABLE(self) # <<<<<<<<<<<<<< @@ -9032,7 +9062,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->readonly = (!(PyArray_ISWRITEABLE(__pyx_v_self) != 0)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 * * cdef int t * cdef char* f = NULL # <<<<<<<<<<<<<< @@ -9041,7 +9071,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_f = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 * cdef int t * cdef char* f = NULL * cdef dtype descr = self.descr # <<<<<<<<<<<<<< @@ -9053,85 +9083,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_descr = ((PyArray_Descr *)__pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":257 * cdef int offset * - * cdef bint hasfields = PyDataType_HASFIELDS(descr) # <<<<<<<<<<<<<< - * - * if not hasfields and not copy_shape: - */ - __pyx_v_hasfields = PyDataType_HASFIELDS(__pyx_v_descr); - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) - * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - __pyx_t_2 = ((!(__pyx_v_hasfields != 0)) != 0); - if (__pyx_t_2) { - } else { - __pyx_t_1 = __pyx_t_2; - goto __pyx_L15_bool_binop_done; - } - __pyx_t_2 = ((!(__pyx_v_copy_shape != 0)) != 0); - __pyx_t_1 = __pyx_t_2; - __pyx_L15_bool_binop_done:; - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 - * if not hasfields and not copy_shape: - * # do not call releasebuffer - * info.obj = None # <<<<<<<<<<<<<< - * else: - * # need to call releasebuffer - */ - __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(Py_None); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = Py_None; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) - * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - goto __pyx_L14; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 - * else: - * # need to call releasebuffer - * info.obj = self # <<<<<<<<<<<<<< + * info.obj = self # <<<<<<<<<<<<<< * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): */ - /*else*/ { - __Pyx_INCREF(((PyObject *)__pyx_v_self)); - __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - } - __pyx_L14:; + __Pyx_INCREF(((PyObject *)__pyx_v_self)); + __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); + __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ - __pyx_t_1 = ((!(__pyx_v_hasfields != 0)) != 0); + __pyx_t_1 = ((!(PyDataType_HASFIELDS(__pyx_v_descr) != 0)) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num # <<<<<<<<<<<<<< * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): @@ -9139,8 +9116,8 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_t_4 = __pyx_v_descr->type_num; __pyx_v_t = __pyx_t_4; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -9148,18 +9125,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((__pyx_v_descr->byteorder == '>') != 0); if (!__pyx_t_2) { - goto __pyx_L20_next_or; + goto __pyx_L15_next_or; } else { } __pyx_t_2 = (__pyx_v_little_endian != 0); if (!__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } - __pyx_L20_next_or:; + __pyx_L15_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":262 * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -9170,36 +9147,36 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } __pyx_t_2 = ((!(__pyx_v_little_endian != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L19_bool_binop_done:; + __pyx_L14_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 276, __pyx_L1_error) + __PYX_ERR(1, 263, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -9207,7 +9184,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":264 * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" # <<<<<<<<<<<<<< @@ -9219,7 +9196,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"b"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" # <<<<<<<<<<<<<< @@ -9230,7 +9207,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"B"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":266 * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" # <<<<<<<<<<<<<< @@ -9241,7 +9218,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"h"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" # <<<<<<<<<<<<<< @@ -9252,7 +9229,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"H"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":281 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":268 * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" # <<<<<<<<<<<<<< @@ -9263,7 +9240,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"i"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":269 * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" # <<<<<<<<<<<<<< @@ -9274,7 +9251,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"I"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" # <<<<<<<<<<<<<< @@ -9285,7 +9262,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"l"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":271 * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" # <<<<<<<<<<<<<< @@ -9296,7 +9273,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"L"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":285 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" # <<<<<<<<<<<<<< @@ -9307,7 +9284,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" # <<<<<<<<<<<<<< @@ -9318,7 +9295,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" # <<<<<<<<<<<<<< @@ -9329,7 +9306,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"f"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" # <<<<<<<<<<<<<< @@ -9340,7 +9317,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"d"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" # <<<<<<<<<<<<<< @@ -9351,7 +9328,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"g"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":290 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" # <<<<<<<<<<<<<< @@ -9362,7 +9339,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zf"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":291 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" # <<<<<<<<<<<<<< @@ -9373,7 +9350,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zd"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" # <<<<<<<<<<<<<< @@ -9384,7 +9361,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zg"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":293 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" * elif t == NPY_OBJECT: f = "O" # <<<<<<<<<<<<<< @@ -9396,33 +9373,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P break; default: - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 * elif t == NPY_OBJECT: f = "O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< * info.format = f * return */ - __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_6 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __pyx_t_7 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_7)) __PYX_ERR(1, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_7); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_GIVEREF(__pyx_t_6); - PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_6); - __pyx_t_6 = 0; - __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_3, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; + __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_Raise(__pyx_t_6, 0, 0, 0); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __PYX_ERR(1, 295, __pyx_L1_error) + __PYX_ERR(1, 282, __pyx_L1_error) break; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f # <<<<<<<<<<<<<< @@ -9431,7 +9403,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->format = __pyx_v_f; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f * return # <<<<<<<<<<<<<< @@ -9441,16 +9413,16 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_r = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":299 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 * return * else: * info.format = PyObject_Malloc(_buffer_format_string_len) # <<<<<<<<<<<<<< @@ -9460,7 +9432,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->format = ((char *)PyObject_Malloc(0xFF)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":300 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 * else: * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment # <<<<<<<<<<<<<< @@ -9469,7 +9441,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->format[0]) = '^'; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":301 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 # <<<<<<<<<<<<<< @@ -9478,17 +9450,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_offset = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":302 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 * f = _util_dtypestring(descr, info.format + 1, # <<<<<<<<<<<<<< * info.format + _buffer_format_string_len, * &offset) */ - __pyx_t_7 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_7 == ((char *)NULL))) __PYX_ERR(1, 302, __pyx_L1_error) - __pyx_v_f = __pyx_t_7; + __pyx_t_8 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_8 == ((char *)NULL))) __PYX_ERR(1, 289, __pyx_L1_error) + __pyx_v_f = __pyx_t_8; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":305 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 * info.format + _buffer_format_string_len, * &offset) * f[0] = c'\0' # Terminate format string # <<<<<<<<<<<<<< @@ -9498,12 +9470,12 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_f[0]) = '\x00'; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* function exit code */ @@ -9511,18 +9483,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_3); - __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); __Pyx_AddTraceback("numpy.ndarray.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; - if (__pyx_v_info != NULL && __pyx_v_info->obj != NULL) { + if (__pyx_v_info->obj != NULL) { __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = NULL; + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } goto __pyx_L2; __pyx_L0:; - if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) { - __Pyx_GOTREF(Py_None); - __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL; + if (__pyx_v_info->obj == Py_None) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } __pyx_L2:; __Pyx_XDECREF((PyObject *)__pyx_v_descr); @@ -9530,7 +9502,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -9554,7 +9526,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s int __pyx_t_1; __Pyx_RefNannySetupContext("__releasebuffer__", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -9564,7 +9536,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (PyArray_HASFIELDS(__pyx_v_self) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":309 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) # <<<<<<<<<<<<<< @@ -9573,7 +9545,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->format); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -9582,7 +9554,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -9592,7 +9564,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":311 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":298 * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): * PyObject_Free(info.strides) # <<<<<<<<<<<<<< @@ -9601,7 +9573,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->strides); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -9610,7 +9582,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -9622,7 +9594,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -9636,7 +9608,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew1", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":789 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 * * cdef inline object PyArray_MultiIterNew1(a): * return PyArray_MultiIterNew(1, a) # <<<<<<<<<<<<<< @@ -9644,13 +9616,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ * cdef inline object PyArray_MultiIterNew2(a, b): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 789, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 776, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -9669,7 +9641,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -9683,7 +9655,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew2", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 * * cdef inline object PyArray_MultiIterNew2(a, b): * return PyArray_MultiIterNew(2, a, b) # <<<<<<<<<<<<<< @@ -9691,13 +9663,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ * cdef inline object PyArray_MultiIterNew3(a, b, c): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 792, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 779, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -9716,7 +9688,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -9730,7 +9702,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew3", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":795 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 * * cdef inline object PyArray_MultiIterNew3(a, b, c): * return PyArray_MultiIterNew(3, a, b, c) # <<<<<<<<<<<<<< @@ -9738,13 +9710,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ * cdef inline object PyArray_MultiIterNew4(a, b, c, d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 795, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 782, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -9763,7 +9735,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -9777,7 +9749,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew4", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":798 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":785 * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): * return PyArray_MultiIterNew(4, a, b, c, d) # <<<<<<<<<<<<<< @@ -9785,13 +9757,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 798, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 785, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -9810,7 +9782,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -9824,7 +9796,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew5", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): * return PyArray_MultiIterNew(5, a, b, c, d, e) # <<<<<<<<<<<<<< @@ -9832,13 +9804,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ * cdef inline tuple PyDataType_SHAPE(dtype d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 801, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 788, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -9857,7 +9829,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -9871,7 +9843,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ int __pyx_t_1; __Pyx_RefNannySetupContext("PyDataType_SHAPE", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -9881,7 +9853,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_t_1 = (PyDataType_HASSUBARRAY(__pyx_v_d) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): * return d.subarray.shape # <<<<<<<<<<<<<< @@ -9893,7 +9865,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_r = ((PyObject*)__pyx_v_d->subarray->shape); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -9902,7 +9874,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 * return d.subarray.shape * else: * return () # <<<<<<<<<<<<<< @@ -9916,7 +9888,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -9931,7 +9903,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -9960,7 +9932,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx char *__pyx_t_9; __Pyx_RefNannySetupContext("_util_dtypestring", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 * * cdef dtype child * cdef int endian_detector = 1 # <<<<<<<<<<<<<< @@ -9969,7 +9941,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":815 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":802 * cdef dtype child * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< @@ -9978,7 +9950,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -9987,21 +9959,21 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->names == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); - __PYX_ERR(1, 818, __pyx_L1_error) + __PYX_ERR(1, 805, __pyx_L1_error) } __pyx_t_1 = __pyx_v_descr->names; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; for (;;) { if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 805, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 805, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif __Pyx_XDECREF_SET(__pyx_v_childname, __pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":819 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":806 * * for childname in descr.names: * fields = descr.fields[childname] # <<<<<<<<<<<<<< @@ -10010,15 +9982,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->fields == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); - __PYX_ERR(1, 819, __pyx_L1_error) + __PYX_ERR(1, 806, __pyx_L1_error) } - __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 819, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 819, __pyx_L1_error) + if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_fields, ((PyObject*)__pyx_t_3)); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":820 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 * for childname in descr.names: * fields = descr.fields[childname] * child, new_offset = fields # <<<<<<<<<<<<<< @@ -10027,15 +9999,11 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (likely(__pyx_v_fields != Py_None)) { PyObject* sequence = __pyx_v_fields; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(1, 820, __pyx_L1_error) + __PYX_ERR(1, 807, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyTuple_GET_ITEM(sequence, 0); @@ -10043,51 +10011,51 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(__pyx_t_4); #else - __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { - __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 820, __pyx_L1_error) + __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 807, __pyx_L1_error) } - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 820, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_child, ((PyArray_Descr *)__pyx_t_3)); __pyx_t_3 = 0; __Pyx_XDECREF_SET(__pyx_v_new_offset, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * */ - __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_6 = ((((__pyx_v_end - __pyx_v_f) - ((int)__pyx_t_5)) < 15) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 823, __pyx_L1_error) + __PYX_ERR(1, 810, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< @@ -10096,7 +10064,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -10116,7 +10084,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __pyx_L8_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":813 * * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -10133,29 +10101,29 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = __pyx_t_7; __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 827, __pyx_L1_error) + __PYX_ERR(1, 814, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -10164,7 +10132,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":824 * * # Output padding bytes * while offset[0] < new_offset: # <<<<<<<<<<<<<< @@ -10172,15 +10140,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * f += 1 */ while (1) { - __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (!__pyx_t_6) break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 * # Output padding bytes * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte # <<<<<<<<<<<<<< @@ -10189,7 +10157,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ (__pyx_v_f[0]) = 0x78; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte * f += 1 # <<<<<<<<<<<<<< @@ -10198,7 +10166,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 * f[0] = 120 # "x"; pad byte * f += 1 * offset[0] += 1 # <<<<<<<<<<<<<< @@ -10209,7 +10177,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + 1); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":829 * offset[0] += 1 * * offset[0] += child.itemsize # <<<<<<<<<<<<<< @@ -10219,7 +10187,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_8 = 0; (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + __pyx_v_child->elsize); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -10229,19 +10197,19 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = ((!(PyDataType_HASFIELDS(__pyx_v_child) != 0)) != 0); if (__pyx_t_6) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":832 * * if not PyDataType_HASFIELDS(child): * t = child.type_num # <<<<<<<<<<<<<< * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") */ - __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 832, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_XDECREF_SET(__pyx_v_t, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -10249,22 +10217,22 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ __pyx_t_6 = (((__pyx_v_end - __pyx_v_f) < 5) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_Raise(__pyx_t_4, 0, 0, 0); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __PYX_ERR(1, 847, __pyx_L1_error) + __PYX_ERR(1, 834, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -10273,252 +10241,252 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 * * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" # <<<<<<<<<<<<<< * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 98; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" # <<<<<<<<<<<<<< * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" # <<<<<<<<<<<<<< * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x68; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" # <<<<<<<<<<<<<< * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 72; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":854 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":841 * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" # <<<<<<<<<<<<<< * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x69; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" # <<<<<<<<<<<<<< * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 73; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":843 * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" # <<<<<<<<<<<<<< * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x6C; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":857 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" # <<<<<<<<<<<<<< * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 76; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":858 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" # <<<<<<<<<<<<<< * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x71; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":859 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" # <<<<<<<<<<<<<< * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 81; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" # <<<<<<<<<<<<<< * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":848 * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" # <<<<<<<<<<<<<< * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x64; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":862 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":849 * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" # <<<<<<<<<<<<<< * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x67; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":863 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf # <<<<<<<<<<<<<< * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -10527,18 +10495,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":864 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd # <<<<<<<<<<<<<< * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -10547,18 +10515,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":865 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg # <<<<<<<<<<<<<< * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -10567,25 +10535,25 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":866 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" # <<<<<<<<<<<<<< * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (__pyx_t_6) { + if (likely(__pyx_t_6)) { (__pyx_v_f[0]) = 79; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":868 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< @@ -10593,23 +10561,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * else: */ /*else*/ { - __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 868, __pyx_L1_error) + __Pyx_Raise(__pyx_t_4, 0, 0, 0); + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __PYX_ERR(1, 855, __pyx_L1_error) } __pyx_L15:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":869 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * f += 1 # <<<<<<<<<<<<<< @@ -10618,7 +10581,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -10628,7 +10591,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L13; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":873 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 * # Cython ignores struct boundary information ("T{...}"), * # so don't output it * f = _util_dtypestring(child, f, end, offset) # <<<<<<<<<<<<<< @@ -10636,12 +10599,12 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ /*else*/ { - __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 873, __pyx_L1_error) + __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 860, __pyx_L1_error) __pyx_v_f = __pyx_t_9; } __pyx_L13:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -10651,7 +10614,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":874 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 * # so don't output it * f = _util_dtypestring(child, f, end, offset) * return f # <<<<<<<<<<<<<< @@ -10661,7 +10624,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_r = __pyx_v_f; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -10686,7 +10649,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -10701,7 +10664,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a int __pyx_t_2; __Pyx_RefNannySetupContext("set_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -10712,7 +10675,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":993 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":980 * cdef PyObject* baseptr * if base is None: * baseptr = NULL # <<<<<<<<<<<<<< @@ -10721,7 +10684,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_baseptr = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -10731,7 +10694,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a goto __pyx_L3; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":995 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":982 * baseptr = NULL * else: * Py_INCREF(base) # important to do this before decref below! # <<<<<<<<<<<<<< @@ -10741,7 +10704,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a /*else*/ { Py_INCREF(__pyx_v_base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":983 * else: * Py_INCREF(base) # important to do this before decref below! * baseptr = base # <<<<<<<<<<<<<< @@ -10752,7 +10715,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a } __pyx_L3:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":984 * Py_INCREF(base) # important to do this before decref below! * baseptr = base * Py_XDECREF(arr.base) # <<<<<<<<<<<<<< @@ -10761,7 +10724,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ Py_XDECREF(__pyx_v_arr->base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":985 * baseptr = base * Py_XDECREF(arr.base) * arr.base = baseptr # <<<<<<<<<<<<<< @@ -10770,7 +10733,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_arr->base = __pyx_v_baseptr; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -10782,7 +10745,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -10796,7 +10759,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py int __pyx_t_1; __Pyx_RefNannySetupContext("get_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -10806,7 +10769,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py __pyx_t_1 = ((__pyx_v_arr->base == NULL) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":989 * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: * return None # <<<<<<<<<<<<<< @@ -10814,11 +10777,10 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py * return arr.base */ __Pyx_XDECREF(__pyx_r); - __Pyx_INCREF(Py_None); - __pyx_r = Py_None; + __pyx_r = Py_None; __Pyx_INCREF(Py_None); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -10827,7 +10789,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":991 * return None * else: * return arr.base # <<<<<<<<<<<<<< @@ -10841,7 +10803,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -10856,7 +10818,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -10877,7 +10839,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_array", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -10893,16 +10855,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 * cdef inline int import_array() except -1: * try: * _import_array() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.multiarray failed to import") */ - __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1011, __pyx_L3_error) + __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 998, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -10916,7 +10878,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":999 * try: * _import_array() * except Exception: # <<<<<<<<<<<<<< @@ -10926,28 +10888,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_array", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1012, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 999, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1013, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1000, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1013, __pyx_L5_except_error) + __PYX_ERR(1, 1000, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -10962,7 +10924,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -10985,7 +10947,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -11006,7 +10968,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_umath", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -11022,16 +10984,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1017 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 * cdef inline int import_umath() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1017, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1004, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -11045,7 +11007,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1018 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1005 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -11055,28 +11017,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_umath", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1018, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1005, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1019, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1006, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1019, __pyx_L5_except_error) + __PYX_ERR(1, 1006, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -11091,7 +11053,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -11114,7 +11076,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -11135,7 +11097,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_ufunc", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -11151,16 +11113,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1023 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 * cdef inline int import_ufunc() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1023, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1010, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -11174,7 +11136,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1024 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -11183,26 +11145,26 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_ufunc", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1024, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1011, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1025, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1012, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1025, __pyx_L5_except_error) + __PYX_ERR(1, 1012, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -11217,7 +11179,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -11258,7 +11220,7 @@ static PyModuleDef_Slot __pyx_moduledef_slots[] = { static struct PyModuleDef __pyx_moduledef = { PyModuleDef_HEAD_INIT, "word2vec_inner", - 0, /* m_doc */ + __pyx_k_Optimized_cython_functions_for_t, /* m_doc */ #if CYTHON_PEP489_MULTI_PHASE_INIT 0, /* m_size */ #else @@ -11389,11 +11351,11 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {0, 0, 0, 0, 0, 0, 0} }; static int __Pyx_InitCachedBuiltins(void) { - __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(0, 21, __pyx_L1_error) - __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 81, __pyx_L1_error) - __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 376, __pyx_L1_error) - __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(1, 235, __pyx_L1_error) - __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(0, 24, __pyx_L1_error) + __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 117, __pyx_L1_error) + __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 569, __pyx_L1_error) + __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(1, 229, __pyx_L1_error) + __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 810, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; @@ -11403,190 +11365,190 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0); - /* "gensim/models/word2vec_inner.pyx":340 + /* "gensim/models/word2vec_inner.pyx":533 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple_ = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_tuple_ = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple_); __Pyx_GIVEREF(__pyx_tuple_); - __pyx_tuple__2 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(0, 340, __pyx_L1_error) + __pyx_tuple__2 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__2)) __PYX_ERR(0, 533, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__2); __Pyx_GIVEREF(__pyx_tuple__2); - /* "gensim/models/word2vec_inner.pyx":448 + /* "gensim/models/word2vec_inner.pyx":666 * cum_table_len = len(model.vocabulary.cum_table) * if negative or sample: * next_random = (2**24) * model.random.randint(0, 2**24) + model.random.randint(0, 2**24) # <<<<<<<<<<<<<< * * # convert Python structures to primitive types, so we can release the GIL */ - __pyx_tuple__3 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_tuple__3 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__3); __Pyx_GIVEREF(__pyx_tuple__3); - __pyx_tuple__4 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 448, __pyx_L1_error) + __pyx_tuple__4 = PyTuple_Pack(2, __pyx_int_0, __pyx_int_16777216); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 666, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__4); __Pyx_GIVEREF(__pyx_tuple__4); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__5)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__5)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__5); __Pyx_GIVEREF(__pyx_tuple__5); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_tuple__6 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_tuple__6 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__6); __Pyx_GIVEREF(__pyx_tuple__6); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_tuple__7 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__7)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_tuple__7 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__7)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__7); __Pyx_GIVEREF(__pyx_tuple__7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_tuple__8 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_tuple__8 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__8); __Pyx_GIVEREF(__pyx_tuple__8); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__9); __Pyx_GIVEREF(__pyx_tuple__9); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__10); __Pyx_GIVEREF(__pyx_tuple__10); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 1013, __pyx_L1_error) + __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 1000, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__11); __Pyx_GIVEREF(__pyx_tuple__11); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 1019, __pyx_L1_error) + __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 1006, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__12); __Pyx_GIVEREF(__pyx_tuple__12); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 1025, __pyx_L1_error) + __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 1012, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__13); __Pyx_GIVEREF(__pyx_tuple__13); - /* "gensim/models/word2vec_inner.pyx":296 + /* "gensim/models/word2vec_inner.pyx":465 * * * def train_batch_sg(model, sentences, alpha, _work, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a batch of sentences. + * */ - __pyx_tuple__15 = PyTuple_Pack(40, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_compute_loss, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_compute_loss_2, __pyx_n_s_running_training_loss_2, __pyx_n_s_syn0, __pyx_n_s_word_locks, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_item); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(0, 296, __pyx_L1_error) + __pyx_tuple__15 = PyTuple_Pack(40, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_compute_loss, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_compute_loss_2, __pyx_n_s_running_training_loss_2, __pyx_n_s_syn0, __pyx_n_s_word_locks, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_item); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(0, 465, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__15); __Pyx_GIVEREF(__pyx_tuple__15); - __pyx_codeobj__16 = (PyObject*)__Pyx_PyCode_New(5, 0, 40, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__15, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_train_batch_sg, 296, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__16)) __PYX_ERR(0, 296, __pyx_L1_error) + __pyx_codeobj__16 = (PyObject*)__Pyx_PyCode_New(5, 0, 40, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__15, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_train_batch_sg, 465, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__16)) __PYX_ERR(0, 465, __pyx_L1_error) - /* "gensim/models/word2vec_inner.pyx":403 + /* "gensim/models/word2vec_inner.pyx":596 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update CBOW model by training on a batch of sentences. + * */ - __pyx_tuple__17 = PyTuple_Pack(43, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_compute_loss, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_cbow_mean, __pyx_n_s_compute_loss_2, __pyx_n_s_running_training_loss_2, __pyx_n_s_syn0, __pyx_n_s_word_locks, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_neu1_2, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_item); if (unlikely(!__pyx_tuple__17)) __PYX_ERR(0, 403, __pyx_L1_error) + __pyx_tuple__17 = PyTuple_Pack(43, __pyx_n_s_model, __pyx_n_s_sentences, __pyx_n_s_alpha, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_compute_loss, __pyx_n_s_hs, __pyx_n_s_negative, __pyx_n_s_sample, __pyx_n_s_cbow_mean, __pyx_n_s_compute_loss_2, __pyx_n_s_running_training_loss_2, __pyx_n_s_syn0, __pyx_n_s_word_locks, __pyx_n_s_work_2, __pyx_n_s_alpha_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_reduced_windows, __pyx_n_s_sentence_idx, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_effective_words, __pyx_n_s_effective_sentences, __pyx_n_s_sent_idx, __pyx_n_s_idx_start, __pyx_n_s_idx_end, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_syn1neg, __pyx_n_s_cum_table, __pyx_n_s_cum_table_len, __pyx_n_s_next_random, __pyx_n_s_neu1_2, __pyx_n_s_vlookup, __pyx_n_s_sent, __pyx_n_s_token, __pyx_n_s_word, __pyx_n_s_item); if (unlikely(!__pyx_tuple__17)) __PYX_ERR(0, 596, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__17); __Pyx_GIVEREF(__pyx_tuple__17); - __pyx_codeobj__18 = (PyObject*)__Pyx_PyCode_New(6, 0, 43, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__17, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_train_batch_cbow, 403, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__18)) __PYX_ERR(0, 403, __pyx_L1_error) + __pyx_codeobj__18 = (PyObject*)__Pyx_PyCode_New(6, 0, 43, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__17, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_train_batch_cbow, 596, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__18)) __PYX_ERR(0, 596, __pyx_L1_error) - /* "gensim/models/word2vec_inner.pyx":510 + /* "gensim/models/word2vec_inner.pyx":727 + * * - * # Score is only implemented for hierarchical softmax * def score_sentence_sg(model, sentence, _work): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted skip-gram representation. * - * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ - __pyx_tuple__19 = PyTuple_Pack(20, __pyx_n_s_model, __pyx_n_s_sentence, __pyx_n_s_work, __pyx_n_s_syn0, __pyx_n_s_work_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_sentence_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_word); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(0, 510, __pyx_L1_error) + __pyx_tuple__19 = PyTuple_Pack(20, __pyx_n_s_model, __pyx_n_s_sentence, __pyx_n_s_work, __pyx_n_s_syn0, __pyx_n_s_work_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_sentence_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_word); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(0, 727, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__19); __Pyx_GIVEREF(__pyx_tuple__19); - __pyx_codeobj__20 = (PyObject*)__Pyx_PyCode_New(3, 0, 20, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__19, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_score_sentence_sg, 510, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__20)) __PYX_ERR(0, 510, __pyx_L1_error) + __pyx_codeobj__20 = (PyObject*)__Pyx_PyCode_New(3, 0, 20, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__19, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_score_sentence_sg, 727, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__20)) __PYX_ERR(0, 727, __pyx_L1_error) - /* "gensim/models/word2vec_inner.pyx":588 + /* "gensim/models/word2vec_inner.pyx":827 * work[0] += f * * def score_sentence_cbow(model, sentence, _work, _neu1): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted CBOW representation. * - * cdef int cbow_mean = model.cbow_mean */ - __pyx_tuple__21 = PyTuple_Pack(23, __pyx_n_s_model, __pyx_n_s_sentence, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_cbow_mean, __pyx_n_s_syn0, __pyx_n_s_work_2, __pyx_n_s_neu1_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_sentence_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_word); if (unlikely(!__pyx_tuple__21)) __PYX_ERR(0, 588, __pyx_L1_error) + __pyx_tuple__21 = PyTuple_Pack(23, __pyx_n_s_model, __pyx_n_s_sentence, __pyx_n_s_work, __pyx_n_s_neu1, __pyx_n_s_cbow_mean, __pyx_n_s_syn0, __pyx_n_s_work_2, __pyx_n_s_neu1_2, __pyx_n_s_size, __pyx_n_s_codelens, __pyx_n_s_indexes, __pyx_n_s_sentence_len, __pyx_n_s_window, __pyx_n_s_i, __pyx_n_s_j, __pyx_n_s_k, __pyx_n_s_result, __pyx_n_s_syn1, __pyx_n_s_points, __pyx_n_s_codes, __pyx_n_s_vlookup, __pyx_n_s_token, __pyx_n_s_word); if (unlikely(!__pyx_tuple__21)) __PYX_ERR(0, 827, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__21); __Pyx_GIVEREF(__pyx_tuple__21); - __pyx_codeobj__22 = (PyObject*)__Pyx_PyCode_New(4, 0, 23, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__21, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_score_sentence_cbow, 588, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__22)) __PYX_ERR(0, 588, __pyx_L1_error) + __pyx_codeobj__22 = (PyObject*)__Pyx_PyCode_New(4, 0, 23, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__21, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_score_sentence_cbow, 827, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__22)) __PYX_ERR(0, 827, __pyx_L1_error) - /* "gensim/models/word2vec_inner.pyx":683 + /* "gensim/models/word2vec_inner.pyx":945 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ - __pyx_tuple__23 = PyTuple_Pack(7, __pyx_n_s_i, __pyx_n_s_x, __pyx_n_s_y, __pyx_n_s_expected, __pyx_n_s_size, __pyx_n_s_d_res, __pyx_n_s_p_res); if (unlikely(!__pyx_tuple__23)) __PYX_ERR(0, 683, __pyx_L1_error) + __pyx_tuple__23 = PyTuple_Pack(7, __pyx_n_s_i, __pyx_n_s_x, __pyx_n_s_y, __pyx_n_s_expected, __pyx_n_s_size, __pyx_n_s_d_res, __pyx_n_s_p_res); if (unlikely(!__pyx_tuple__23)) __PYX_ERR(0, 945, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__23); __Pyx_GIVEREF(__pyx_tuple__23); - __pyx_codeobj__24 = (PyObject*)__Pyx_PyCode_New(0, 0, 7, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__23, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_init, 683, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__24)) __PYX_ERR(0, 683, __pyx_L1_error) + __pyx_codeobj__24 = (PyObject*)__Pyx_PyCode_New(0, 0, 7, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__23, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim_models_word2vec_inner_pyx, __pyx_n_s_init, 945, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__24)) __PYX_ERR(0, 945, __pyx_L1_error) __Pyx_RefNannyFinishContext(); return 0; __pyx_L1_error:; @@ -11606,12 +11568,137 @@ static int __Pyx_InitGlobals(void) { return -1; } +static int __Pyx_modinit_global_init_code(void); /*proto*/ +static int __Pyx_modinit_variable_export_code(void); /*proto*/ +static int __Pyx_modinit_function_export_code(void); /*proto*/ +static int __Pyx_modinit_type_init_code(void); /*proto*/ +static int __Pyx_modinit_type_import_code(void); /*proto*/ +static int __Pyx_modinit_variable_import_code(void); /*proto*/ +static int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + if (__Pyx_ExportVoidPtr(__pyx_n_s_scopy, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_scopy, "__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_saxpy, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_sdot, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_sdot, "__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_dsdot, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_dsdot, "__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_snrm2, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_snrm2, "__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_sscal, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_sscal, "__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_EXP_TABLE, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t [0x3E8]") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_our_dot, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_our_dot, "__pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportVoidPtr(__pyx_n_s_our_saxpy, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_our_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + if (__Pyx_ExportFunction("our_dot_double", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_dot_double, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportFunction("our_dot_float", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_dot_float, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportFunction("our_dot_noblas", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportFunction("our_saxpy_noblas", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas, "void (int const *, float const *, float const *, int const *, float *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportFunction("bisect_left", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_bisect_left, "unsigned PY_LONG_LONG (__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + if (__Pyx_ExportFunction("random_int32", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_random_int32, "unsigned PY_LONG_LONG (unsigned PY_LONG_LONG *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", + #if defined(PYPY_VERSION_NUM) && PYPY_VERSION_NUM < 0x050B0000 + sizeof(PyTypeObject), + #else + sizeof(PyHeapTypeObject), + #endif + 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(2, 9, __pyx_L1_error) + __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 164, __pyx_L1_error) + __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 186, __pyx_L1_error) + __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 190, __pyx_L1_error) + __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 199, __pyx_L1_error) + __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 872, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + + +#if PY_MAJOR_VERSION < 3 +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC void +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#else +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyObject * +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (!(defined(__cplusplus)) || (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ > 4))) + #define CYTHON_SMALL_CODE __attribute__((optimize("Os"))) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + + #if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initword2vec_inner(void); /*proto*/ -PyMODINIT_FUNC initword2vec_inner(void) +__Pyx_PyMODINIT_FUNC initword2vec_inner(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC initword2vec_inner(void) #else -PyMODINIT_FUNC PyInit_word2vec_inner(void); /*proto*/ -PyMODINIT_FUNC PyInit_word2vec_inner(void) +__Pyx_PyMODINIT_FUNC PyInit_word2vec_inner(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit_word2vec_inner(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); @@ -11667,17 +11754,19 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m && __pyx_m == __pyx_pyinit_module) return 0; + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif #if CYTHON_REFNANNY - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); - if (!__Pyx_RefNanny) { - PyErr_Clear(); - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); - if (!__Pyx_RefNanny) - Py_FatalError("failed to import 'refnanny' module"); - } - #endif - __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit_word2vec_inner(void)", 0); +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit_word2vec_inner(void)", 0); if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) @@ -11713,7 +11802,7 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) Py_INCREF(__pyx_m); #else #if PY_MAJOR_VERSION < 3 - __pyx_m = Py_InitModule4("word2vec_inner", __pyx_methods, 0, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); + __pyx_m = Py_InitModule4("word2vec_inner", __pyx_methods, __pyx_k_Optimized_cython_functions_for_t, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); #else __pyx_m = PyModule_Create(&__pyx_moduledef); #endif @@ -11744,61 +11833,35 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) } #endif /*--- Builtin init code ---*/ - if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Constants init code ---*/ - if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Global init code ---*/ - /*--- Variable export code ---*/ - if (__Pyx_ExportVoidPtr(__pyx_n_s_scopy, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_scopy, "__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_saxpy, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_sdot, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_sdot, "__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_dsdot, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_dsdot, "__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_snrm2, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_snrm2, "__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_sscal, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_sscal, "__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_EXP_TABLE, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_EXP_TABLE, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t [0x3E8]") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_our_dot, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_our_dot, "__pyx_t_6gensim_6models_14word2vec_inner_our_dot_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportVoidPtr(__pyx_n_s_our_saxpy, (void *)&__pyx_v_6gensim_6models_14word2vec_inner_our_saxpy, "__pyx_t_6gensim_6models_14word2vec_inner_our_saxpy_ptr") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Function export code ---*/ - if (__Pyx_ExportFunction("our_dot_double", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_dot_double, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportFunction("our_dot_float", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_dot_float, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportFunction("our_dot_noblas", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_dot_noblas, "__pyx_t_6gensim_6models_14word2vec_inner_REAL_t (int const *, float const *, int const *, float const *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportFunction("our_saxpy_noblas", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_our_saxpy_noblas, "void (int const *, float const *, float const *, int const *, float *, int const *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportFunction("bisect_left", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_bisect_left, "unsigned PY_LONG_LONG (__pyx_t_5numpy_uint32_t *, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG, unsigned PY_LONG_LONG)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - if (__Pyx_ExportFunction("random_int32", (void (*)(void))__pyx_f_6gensim_6models_14word2vec_inner_random_int32, "unsigned PY_LONG_LONG (unsigned PY_LONG_LONG *)") < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Type init code ---*/ - /*--- Type import code ---*/ - __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", - #if CYTHON_COMPILING_IN_PYPY - sizeof(PyTypeObject), - #else - sizeof(PyHeapTypeObject), - #endif - 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(2, 9, __pyx_L1_error) - __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 163, __pyx_L1_error) - __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 185, __pyx_L1_error) - __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 189, __pyx_L1_error) - __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 198, __pyx_L1_error) - __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 885, __pyx_L1_error) - /*--- Variable import code ---*/ - /*--- Function import code ---*/ + if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + /*--- Constants init code ---*/ + if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + if (unlikely(__Pyx_modinit_variable_export_code() != 0)) goto __pyx_L1_error; + if (unlikely(__Pyx_modinit_function_export_code() != 0)) goto __pyx_L1_error; + (void)__Pyx_modinit_type_init_code(); + if (unlikely(__Pyx_modinit_type_import_code() != 0)) goto __pyx_L1_error; + (void)__Pyx_modinit_variable_import_code(); + (void)__Pyx_modinit_function_import_code(); /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif - /* "gensim/models/word2vec_inner.pyx":11 + /* "gensim/models/word2vec_inner.pyx":14 * * import cython * import numpy as np # <<<<<<<<<<<<<< * cimport numpy as np * */ - __pyx_t_1 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 11, __pyx_L1_error) + __pyx_t_1 = __Pyx_Import(__pyx_n_s_numpy, 0, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 14, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_1) < 0) __PYX_ERR(0, 11, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_np, __pyx_t_1) < 0) __PYX_ERR(0, 14, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":19 + /* "gensim/models/word2vec_inner.pyx":22 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< @@ -11814,28 +11877,28 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) __Pyx_XGOTREF(__pyx_t_4); /*try:*/ { - /* "gensim/models/word2vec_inner.pyx":20 + /* "gensim/models/word2vec_inner.pyx":23 * # scipy <= 0.15 * try: * from scipy.linalg.blas import fblas # <<<<<<<<<<<<<< * except ImportError: * # in scipy > 0.15, fblas function has been removed */ - __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 20, __pyx_L2_error) + __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 23, __pyx_L2_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_n_s_fblas); __Pyx_GIVEREF(__pyx_n_s_fblas); PyList_SET_ITEM(__pyx_t_1, 0, __pyx_n_s_fblas); - __pyx_t_5 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_1, -1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 20, __pyx_L2_error) + __pyx_t_5 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_1, -1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 23, __pyx_L2_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_5, __pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 20, __pyx_L2_error) + __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_5, __pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 23, __pyx_L2_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_1) < 0) __PYX_ERR(0, 20, __pyx_L2_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_1) < 0) __PYX_ERR(0, 23, __pyx_L2_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - /* "gensim/models/word2vec_inner.pyx":19 + /* "gensim/models/word2vec_inner.pyx":22 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< @@ -11851,7 +11914,7 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; - /* "gensim/models/word2vec_inner.pyx":21 + /* "gensim/models/word2vec_inner.pyx":24 * try: * from scipy.linalg.blas import fblas * except ImportError: # <<<<<<<<<<<<<< @@ -11861,27 +11924,27 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) __pyx_t_6 = __Pyx_PyErr_ExceptionMatches(__pyx_builtin_ImportError); if (__pyx_t_6) { __Pyx_AddTraceback("gensim.models.word2vec_inner", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_1, &__pyx_t_7) < 0) __PYX_ERR(0, 21, __pyx_L4_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_1, &__pyx_t_7) < 0) __PYX_ERR(0, 24, __pyx_L4_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_1); __Pyx_GOTREF(__pyx_t_7); - /* "gensim/models/word2vec_inner.pyx":23 + /* "gensim/models/word2vec_inner.pyx":26 * except ImportError: * # in scipy > 0.15, fblas function has been removed * import scipy.linalg.blas as fblas # <<<<<<<<<<<<<< * * REAL = np.float32 */ - __pyx_t_8 = PyList_New(1); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 23, __pyx_L4_except_error) + __pyx_t_8 = PyList_New(1); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 26, __pyx_L4_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_INCREF(__pyx_n_s__14); __Pyx_GIVEREF(__pyx_n_s__14); PyList_SET_ITEM(__pyx_t_8, 0, __pyx_n_s__14); - __pyx_t_9 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_8, -1); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 23, __pyx_L4_except_error) + __pyx_t_9 = __Pyx_Import(__pyx_n_s_scipy_linalg_blas, __pyx_t_8, -1); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 26, __pyx_L4_except_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_9) < 0) __PYX_ERR(0, 23, __pyx_L4_except_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_fblas, __pyx_t_9) < 0) __PYX_ERR(0, 26, __pyx_L4_except_error) __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -11891,7 +11954,7 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) goto __pyx_L4_except_error; __pyx_L4_except_error:; - /* "gensim/models/word2vec_inner.pyx":19 + /* "gensim/models/word2vec_inner.pyx":22 * * # scipy <= 0.15 * try: # <<<<<<<<<<<<<< @@ -11911,130 +11974,130 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) __pyx_L7_try_end:; } - /* "gensim/models/word2vec_inner.pyx":25 + /* "gensim/models/word2vec_inner.pyx":28 * import scipy.linalg.blas as fblas * * REAL = np.float32 # <<<<<<<<<<<<<< * * DEF MAX_SENTENCE_LEN = 10000 */ - __pyx_t_7 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 25, __pyx_L1_error) + __pyx_t_7 = __Pyx_GetModuleGlobalName(__pyx_n_s_np); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 28, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_float32); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 25, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_float32); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 28, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_REAL, __pyx_t_1) < 0) __PYX_ERR(0, 25, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_REAL, __pyx_t_1) < 0) __PYX_ERR(0, 28, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":29 + /* "gensim/models/word2vec_inner.pyx":32 * DEF MAX_SENTENCE_LEN = 10000 * * cdef scopy_ptr scopy=PyCObject_AsVoidPtr(fblas.scopy._cpointer) # y = x # <<<<<<<<<<<<<< * cdef saxpy_ptr saxpy=PyCObject_AsVoidPtr(fblas.saxpy._cpointer) # y += alpha * x * cdef sdot_ptr sdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # float = dot(x, y) */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 29, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 32, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_scopy); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 29, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_scopy); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 32, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 29, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 32, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_v_6gensim_6models_14word2vec_inner_scopy = ((__pyx_t_6gensim_6models_14word2vec_inner_scopy_ptr)PyCObject_AsVoidPtr(__pyx_t_1)); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":30 + /* "gensim/models/word2vec_inner.pyx":33 * * cdef scopy_ptr scopy=PyCObject_AsVoidPtr(fblas.scopy._cpointer) # y = x * cdef saxpy_ptr saxpy=PyCObject_AsVoidPtr(fblas.saxpy._cpointer) # y += alpha * x # <<<<<<<<<<<<<< * cdef sdot_ptr sdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # float = dot(x, y) * cdef dsdot_ptr dsdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # double = dot(x, y) */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 30, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 33, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_saxpy); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 30, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_saxpy); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 33, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 30, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 33, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_v_6gensim_6models_14word2vec_inner_saxpy = ((__pyx_t_6gensim_6models_14word2vec_inner_saxpy_ptr)PyCObject_AsVoidPtr(__pyx_t_1)); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":31 + /* "gensim/models/word2vec_inner.pyx":34 * cdef scopy_ptr scopy=PyCObject_AsVoidPtr(fblas.scopy._cpointer) # y = x * cdef saxpy_ptr saxpy=PyCObject_AsVoidPtr(fblas.saxpy._cpointer) # y += alpha * x * cdef sdot_ptr sdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # float = dot(x, y) # <<<<<<<<<<<<<< * cdef dsdot_ptr dsdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # double = dot(x, y) * cdef snrm2_ptr snrm2=PyCObject_AsVoidPtr(fblas.snrm2._cpointer) # sqrt(x^2) */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 31, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 34, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sdot); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 31, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sdot); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 34, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 31, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 34, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_v_6gensim_6models_14word2vec_inner_sdot = ((__pyx_t_6gensim_6models_14word2vec_inner_sdot_ptr)PyCObject_AsVoidPtr(__pyx_t_1)); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":32 + /* "gensim/models/word2vec_inner.pyx":35 * cdef saxpy_ptr saxpy=PyCObject_AsVoidPtr(fblas.saxpy._cpointer) # y += alpha * x * cdef sdot_ptr sdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # float = dot(x, y) * cdef dsdot_ptr dsdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # double = dot(x, y) # <<<<<<<<<<<<<< * cdef snrm2_ptr snrm2=PyCObject_AsVoidPtr(fblas.snrm2._cpointer) # sqrt(x^2) * cdef sscal_ptr sscal=PyCObject_AsVoidPtr(fblas.sscal._cpointer) # x = alpha * x */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 32, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 35, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sdot); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 32, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sdot); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 35, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 32, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 35, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_v_6gensim_6models_14word2vec_inner_dsdot = ((__pyx_t_6gensim_6models_14word2vec_inner_dsdot_ptr)PyCObject_AsVoidPtr(__pyx_t_1)); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":33 + /* "gensim/models/word2vec_inner.pyx":36 * cdef sdot_ptr sdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # float = dot(x, y) * cdef dsdot_ptr dsdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # double = dot(x, y) * cdef snrm2_ptr snrm2=PyCObject_AsVoidPtr(fblas.snrm2._cpointer) # sqrt(x^2) # <<<<<<<<<<<<<< * cdef sscal_ptr sscal=PyCObject_AsVoidPtr(fblas.sscal._cpointer) # x = alpha * x * */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 33, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_snrm2); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 33, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_snrm2); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 33, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_v_6gensim_6models_14word2vec_inner_snrm2 = ((__pyx_t_6gensim_6models_14word2vec_inner_snrm2_ptr)PyCObject_AsVoidPtr(__pyx_t_1)); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":34 + /* "gensim/models/word2vec_inner.pyx":37 * cdef dsdot_ptr dsdot=PyCObject_AsVoidPtr(fblas.sdot._cpointer) # double = dot(x, y) * cdef snrm2_ptr snrm2=PyCObject_AsVoidPtr(fblas.snrm2._cpointer) # sqrt(x^2) * cdef sscal_ptr sscal=PyCObject_AsVoidPtr(fblas.sscal._cpointer) # x = alpha * x # <<<<<<<<<<<<<< * * DEF EXP_TABLE_SIZE = 1000 */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 34, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_fblas); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sscal); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 34, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_sscal); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 34, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_7, __pyx_n_s_cpointer); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_v_6gensim_6models_14word2vec_inner_sscal = ((__pyx_t_6gensim_6models_14word2vec_inner_sscal_ptr)PyCObject_AsVoidPtr(__pyx_t_1)); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":42 + /* "gensim/models/word2vec_inner.pyx":45 * cdef REAL_t[EXP_TABLE_SIZE] LOG_TABLE * * cdef int ONE = 1 # <<<<<<<<<<<<<< @@ -12043,7 +12106,7 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) */ __pyx_v_6gensim_6models_14word2vec_inner_ONE = 1; - /* "gensim/models/word2vec_inner.pyx":43 + /* "gensim/models/word2vec_inner.pyx":46 * * cdef int ONE = 1 * cdef REAL_t ONEF = 1.0 # <<<<<<<<<<<<<< @@ -12052,113 +12115,98 @@ static int __pyx_pymod_exec_word2vec_inner(PyObject *__pyx_pyinit_module) */ __pyx_v_6gensim_6models_14word2vec_inner_ONEF = ((__pyx_t_6gensim_6models_14word2vec_inner_REAL_t)1.0); - /* "gensim/models/word2vec_inner.pyx":296 + /* "gensim/models/word2vec_inner.pyx":465 * * * def train_batch_sg(model, sentences, alpha, _work, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update skip-gram model by training on a batch of sentences. + * */ - __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_1train_batch_sg, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 296, __pyx_L1_error) + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_1train_batch_sg, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 465, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_sg, __pyx_t_1) < 0) __PYX_ERR(0, 296, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_sg, __pyx_t_1) < 0) __PYX_ERR(0, 465, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":403 + /* "gensim/models/word2vec_inner.pyx":596 * * * def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): # <<<<<<<<<<<<<< - * cdef int hs = model.hs - * cdef int negative = model.negative + * """Update CBOW model by training on a batch of sentences. + * */ - __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_3train_batch_cbow, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 403, __pyx_L1_error) + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_3train_batch_cbow, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 596, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_cbow, __pyx_t_1) < 0) __PYX_ERR(0, 403, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_train_batch_cbow, __pyx_t_1) < 0) __PYX_ERR(0, 596, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":510 + /* "gensim/models/word2vec_inner.pyx":727 + * * - * # Score is only implemented for hierarchical softmax * def score_sentence_sg(model, sentence, _work): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted skip-gram representation. * - * cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) */ - __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_5score_sentence_sg, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 510, __pyx_L1_error) + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_5score_sentence_sg, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 727, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_score_sentence_sg, __pyx_t_1) < 0) __PYX_ERR(0, 510, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_score_sentence_sg, __pyx_t_1) < 0) __PYX_ERR(0, 727, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":588 + /* "gensim/models/word2vec_inner.pyx":827 * work[0] += f * * def score_sentence_cbow(model, sentence, _work, _neu1): # <<<<<<<<<<<<<< + * """Obtain likelihood score for a single sentence in a fitted CBOW representation. * - * cdef int cbow_mean = model.cbow_mean */ - __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_7score_sentence_cbow, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 588, __pyx_L1_error) + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_7score_sentence_cbow, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 827, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_score_sentence_cbow, __pyx_t_1) < 0) __PYX_ERR(0, 588, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_score_sentence_cbow, __pyx_t_1) < 0) __PYX_ERR(0, 827, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":683 + /* "gensim/models/word2vec_inner.pyx":945 * * * def init(): # <<<<<<<<<<<<<< - * """ - * Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized + * """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + * Also calculate log(sigmoid(x)) into LOG_TABLE. */ - __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_9init, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 683, __pyx_L1_error) + __pyx_t_1 = PyCFunction_NewEx(&__pyx_mdef_6gensim_6models_14word2vec_inner_9init, NULL, __pyx_n_s_gensim_models_word2vec_inner); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 945, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_init, __pyx_t_1) < 0) __PYX_ERR(0, 683, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_init, __pyx_t_1) < 0) __PYX_ERR(0, 945, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/models/word2vec_inner.pyx":724 + /* "gensim/models/word2vec_inner.pyx":992 * return 2 * * FAST_VERSION = init() # initialize the module # <<<<<<<<<<<<<< * MAX_WORDS_IN_BATCH = MAX_SENTENCE_LEN */ - __pyx_t_7 = __Pyx_GetModuleGlobalName(__pyx_n_s_init); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 724, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_7); - __pyx_t_5 = NULL; - if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_7))) { - __pyx_t_5 = PyMethod_GET_SELF(__pyx_t_7); - if (likely(__pyx_t_5)) { - PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_7); - __Pyx_INCREF(__pyx_t_5); - __Pyx_INCREF(function); - __Pyx_DECREF_SET(__pyx_t_7, function); - } - } - if (__pyx_t_5) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_7, __pyx_t_5); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 724, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - } else { - __pyx_t_1 = __Pyx_PyObject_CallNoArg(__pyx_t_7); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 724, __pyx_L1_error) - } + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_init); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 992, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_FAST_VERSION, __pyx_t_1) < 0) __PYX_ERR(0, 724, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_CallNoArg(__pyx_t_1); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 992, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_FAST_VERSION, __pyx_t_7) < 0) __PYX_ERR(0, 992, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "gensim/models/word2vec_inner.pyx":725 + /* "gensim/models/word2vec_inner.pyx":993 * * FAST_VERSION = init() # initialize the module * MAX_WORDS_IN_BATCH = MAX_SENTENCE_LEN # <<<<<<<<<<<<<< */ - if (PyDict_SetItem(__pyx_d, __pyx_n_s_MAX_WORDS_IN_BATCH, __pyx_int_10000) < 0) __PYX_ERR(0, 725, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_MAX_WORDS_IN_BATCH, __pyx_int_10000) < 0) __PYX_ERR(0, 993, __pyx_L1_error) /* "gensim/models/word2vec_inner.pyx":1 * #!/usr/bin/env cython # <<<<<<<<<<<<<< * # cython: boundscheck=False * # cython: wraparound=False */ - __pyx_t_1 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_1) < 0) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_7 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_7) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -12212,6 +12260,20 @@ static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { } #endif +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); @@ -12401,6 +12463,122 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg } #endif +/* GetItemInt */ +static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { + PyObject *r; + if (!j) return NULL; + r = PyObject_GetItem(o, j); + Py_DECREF(j); + return r; +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_List_Fast(PyObject *o, Py_ssize_t i, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS + Py_ssize_t wrapped_i = i; + if (wraparound & unlikely(i < 0)) { + wrapped_i += PyList_GET_SIZE(o); + } + if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyList_GET_SIZE(o)))) { + PyObject *r = PyList_GET_ITEM(o, wrapped_i); + Py_INCREF(r); + return r; + } + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +#else + return PySequence_GetItem(o, i); +#endif +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Tuple_Fast(PyObject *o, Py_ssize_t i, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS + Py_ssize_t wrapped_i = i; + if (wraparound & unlikely(i < 0)) { + wrapped_i += PyTuple_GET_SIZE(o); + } + if ((!boundscheck) || likely((0 <= wrapped_i) & (wrapped_i < PyTuple_GET_SIZE(o)))) { + PyObject *r = PyTuple_GET_ITEM(o, wrapped_i); + Py_INCREF(r); + return r; + } + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +#else + return PySequence_GetItem(o, i); +#endif +} +static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, int is_list, + CYTHON_NCP_UNUSED int wraparound, + CYTHON_NCP_UNUSED int boundscheck) { +#if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS && CYTHON_USE_TYPE_SLOTS + if (is_list || PyList_CheckExact(o)) { + Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyList_GET_SIZE(o); + if ((!boundscheck) || (likely((n >= 0) & (n < PyList_GET_SIZE(o))))) { + PyObject *r = PyList_GET_ITEM(o, n); + Py_INCREF(r); + return r; + } + } + else if (PyTuple_CheckExact(o)) { + Py_ssize_t n = ((!wraparound) | likely(i >= 0)) ? i : i + PyTuple_GET_SIZE(o); + if ((!boundscheck) || likely((n >= 0) & (n < PyTuple_GET_SIZE(o)))) { + PyObject *r = PyTuple_GET_ITEM(o, n); + Py_INCREF(r); + return r; + } + } else { + PySequenceMethods *m = Py_TYPE(o)->tp_as_sequence; + if (likely(m && m->sq_item)) { + if (wraparound && unlikely(i < 0) && likely(m->sq_length)) { + Py_ssize_t l = m->sq_length(o); + if (likely(l >= 0)) { + i += l; + } else { + if (!PyErr_ExceptionMatches(PyExc_OverflowError)) + return NULL; + PyErr_Clear(); + } + } + return m->sq_item(o, i); + } + } +#else + if (is_list || PySequence_Check(o)) { + return PySequence_GetItem(o, i); + } +#endif + return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); +} + +/* ObjectGetItem */ +#if CYTHON_USE_TYPE_SLOTS +static PyObject *__Pyx_PyObject_GetIndex(PyObject *obj, PyObject* index) { + PyObject *runerr; + Py_ssize_t key_value; + PySequenceMethods *m = Py_TYPE(obj)->tp_as_sequence; + if (unlikely(!(m && m->sq_item))) { + PyErr_Format(PyExc_TypeError, "'%.200s' object is not subscriptable", Py_TYPE(obj)->tp_name); + return NULL; + } + key_value = __Pyx_PyIndex_AsSsize_t(index); + if (likely(key_value != -1 || !(runerr = PyErr_Occurred()))) { + return __Pyx_GetItemInt_Fast(obj, key_value, 0, 1, 1); + } + if (PyErr_GivenExceptionMatches(runerr, PyExc_OverflowError)) { + PyErr_Clear(); + PyErr_Format(PyExc_IndexError, "cannot fit '%.200s' into an index-sized integer", Py_TYPE(index)->tp_name); + } + return NULL; +} +static PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key) { + PyMappingMethods *m = Py_TYPE(obj)->tp_as_mapping; + if (likely(m && m->mp_subscript)) { + return m->mp_subscript(obj, key); + } + return __Pyx_PyObject_GetIndex(obj, key); +} +#endif + /* PyFunctionFastCall */ #if CYTHON_FAST_PYCALL #include "frameobject.h" @@ -12544,6 +12722,20 @@ static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, P } #endif +/* PyObjectSetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE int __Pyx_PyObject_SetAttrStr(PyObject* obj, PyObject* attr_name, PyObject* value) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_setattro)) + return tp->tp_setattro(obj, attr_name, value); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_setattr)) + return tp->tp_setattr(obj, PyString_AS_STRING(attr_name), value); +#endif + return PyObject_SetAttr(obj, attr_name, value); +} +#endif + /* PyErrFetchRestore */ #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { @@ -12727,6 +12919,85 @@ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject } #endif +/* PyObjectCallMethO */ +#if CYTHON_COMPILING_IN_CPYTHON +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { + PyObject *self, *result; + PyCFunction cfunc; + cfunc = PyCFunction_GET_FUNCTION(func); + self = PyCFunction_GET_SELF(func); + if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) + return NULL; + result = cfunc(self, arg); + Py_LeaveRecursiveCall(); + if (unlikely(!result) && unlikely(!PyErr_Occurred())) { + PyErr_SetString( + PyExc_SystemError, + "NULL result without error in PyObject_Call"); + } + return result; +} +#endif + +/* PyObjectCallOneArg */ +#if CYTHON_COMPILING_IN_CPYTHON +static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) { + PyObject *result; + PyObject *args = PyTuple_New(1); + if (unlikely(!args)) return NULL; + Py_INCREF(arg); + PyTuple_SET_ITEM(args, 0, arg); + result = __Pyx_PyObject_Call(func, args, NULL); + Py_DECREF(args); + return result; +} +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { +#if CYTHON_FAST_PYCALL + if (PyFunction_Check(func)) { + return __Pyx_PyFunction_FastCall(func, &arg, 1); + } +#endif + if (likely(PyCFunction_Check(func))) { + if (likely(PyCFunction_GET_FLAGS(func) & METH_O)) { + return __Pyx_PyObject_CallMethO(func, arg); +#if CYTHON_FAST_PYCCALL + } else if (PyCFunction_GET_FLAGS(func) & METH_FASTCALL) { + return __Pyx_PyCFunction_FastCall(func, &arg, 1); +#endif + } + } + return __Pyx__PyObject_CallOneArg(func, arg); +} +#else +static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { + PyObject *result; + PyObject *args = PyTuple_Pack(1, arg); + if (unlikely(!args)) return NULL; + result = __Pyx_PyObject_Call(func, args, NULL); + Py_DECREF(args); + return result; +} +#endif + +/* DictGetItem */ +#if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { + PyObject *value; + value = PyDict_GetItemWithError(d, key); + if (unlikely(!value)) { + if (!PyErr_Occurred()) { + PyObject* args = PyTuple_Pack(1, key); + if (likely(args)) + PyErr_SetObject(PyExc_KeyError, args); + Py_XDECREF(args); + } + return NULL; + } + Py_INCREF(value); + return value; +} +#endif + /* RaiseTooManyValuesToUnpack */ static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { PyErr_Format(PyExc_ValueError, @@ -12962,10 +13233,19 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { PyObject *result; #if !CYTHON_AVOID_BORROWED_REFS +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 + result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); + if (likely(result)) { + Py_INCREF(result); + } else if (unlikely(PyErr_Occurred())) { + result = NULL; + } else { +#else result = PyDict_GetItem(__pyx_d, name); if (likely(result)) { Py_INCREF(result); } else { +#endif #else result = PyObject_GetItem(__pyx_d, name); if (!result) { @@ -12976,68 +13256,8 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) return result; } -/* PyObjectCallMethO */ - #if CYTHON_COMPILING_IN_CPYTHON -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { - PyObject *self, *result; - PyCFunction cfunc; - cfunc = PyCFunction_GET_FUNCTION(func); - self = PyCFunction_GET_SELF(func); - if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) - return NULL; - result = cfunc(self, arg); - Py_LeaveRecursiveCall(); - if (unlikely(!result) && unlikely(!PyErr_Occurred())) { - PyErr_SetString( - PyExc_SystemError, - "NULL result without error in PyObject_Call"); - } - return result; -} -#endif - -/* PyObjectCallOneArg */ - #if CYTHON_COMPILING_IN_CPYTHON -static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) { - PyObject *result; - PyObject *args = PyTuple_New(1); - if (unlikely(!args)) return NULL; - Py_INCREF(arg); - PyTuple_SET_ITEM(args, 0, arg); - result = __Pyx_PyObject_Call(func, args, NULL); - Py_DECREF(args); - return result; -} -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { -#if CYTHON_FAST_PYCALL - if (PyFunction_Check(func)) { - return __Pyx_PyFunction_FastCall(func, &arg, 1); - } -#endif - if (likely(PyCFunction_Check(func))) { - if (likely(PyCFunction_GET_FLAGS(func) & METH_O)) { - return __Pyx_PyObject_CallMethO(func, arg); -#if CYTHON_FAST_PYCCALL - } else if (PyCFunction_GET_FLAGS(func) & METH_FASTCALL) { - return __Pyx_PyCFunction_FastCall(func, &arg, 1); -#endif - } - } - return __Pyx__PyObject_CallOneArg(func, arg); -} -#else -static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { - PyObject *result; - PyObject *args = PyTuple_Pack(1, arg); - if (unlikely(!args)) return NULL; - result = __Pyx_PyObject_Call(func, args, NULL); - Py_DECREF(args); - return result; -} -#endif - /* PyObjectCallNoArg */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { #if CYTHON_FAST_PYCALL if (PyFunction_Check(func)) { @@ -13058,18 +13278,21 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { #endif /* CLineInTraceback */ - #ifndef CYTHON_CLINE_IN_TRACEBACK + #ifndef CYTHON_CLINE_IN_TRACEBACK static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_line) { PyObject *use_cline; PyObject *ptype, *pvalue, *ptraceback; #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { - use_cline = PyDict_GetItem(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); + use_cline = __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); } else #endif { @@ -13095,7 +13318,7 @@ static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_li #endif /* CodeObjectCache */ - static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { + static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { int start = 0, mid = 0, end = count - 1; if (end >= 0 && code_line > entries[end].code_line) { return count; @@ -13175,7 +13398,7 @@ static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { } /* AddTraceback */ - #include "compile.h" + #include "compile.h" #include "frameobject.h" #include "traceback.h" static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( @@ -13260,7 +13483,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13291,7 +13514,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPyVerify */ - #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ + #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) #define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) @@ -13313,7 +13536,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* None */ - static CYTHON_INLINE long __Pyx_pow_long(long b, long e) { + static CYTHON_INLINE long __Pyx_pow_long(long b, long e) { long t = b; switch (e) { case 3: @@ -13340,7 +13563,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13371,7 +13594,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_PY_LONG_LONG(unsigned PY_LONG_LONG value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_unsigned_PY_LONG_LONG(unsigned PY_LONG_LONG value) { const unsigned PY_LONG_LONG neg_one = (unsigned PY_LONG_LONG) -1, const_zero = (unsigned PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13402,7 +13625,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { return ::std::complex< float >(x, y); @@ -13422,7 +13645,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -13557,7 +13780,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { return ::std::complex< double >(x, y); @@ -13577,7 +13800,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -13712,7 +13935,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, #endif /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { const enum NPY_TYPES neg_one = (enum NPY_TYPES) -1, const_zero = (enum NPY_TYPES) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -13743,7 +13966,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { const PY_LONG_LONG neg_one = (PY_LONG_LONG) -1, const_zero = (PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -13932,7 +14155,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { + static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14121,7 +14344,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE unsigned PY_LONG_LONG __Pyx_PyInt_As_unsigned_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE unsigned PY_LONG_LONG __Pyx_PyInt_As_unsigned_PY_LONG_LONG(PyObject *x) { const unsigned PY_LONG_LONG neg_one = (unsigned PY_LONG_LONG) -1, const_zero = (unsigned PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14310,7 +14533,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE npy_uint32 __Pyx_PyInt_As_npy_uint32(PyObject *x) { + static CYTHON_INLINE npy_uint32 __Pyx_PyInt_As_npy_uint32(PyObject *x) { const npy_uint32 neg_one = (npy_uint32) -1, const_zero = (npy_uint32) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14499,7 +14722,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { + static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -14688,7 +14911,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* FastTypeChecks */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { while (a) { a = a->tp_base; @@ -14760,7 +14983,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #endif /* CheckBinaryVersion */ - static int __Pyx_check_binary_version(void) { + static int __Pyx_check_binary_version(void) { char ctversion[4], rtversion[4]; PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION); PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion()); @@ -14776,7 +14999,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* VoidPtrExport */ - static int __Pyx_ExportVoidPtr(PyObject *name, void *p, const char *sig) { + static int __Pyx_ExportVoidPtr(PyObject *name, void *p, const char *sig) { PyObject *d; PyObject *cobj = 0; d = PyDict_GetItem(__pyx_d, __pyx_n_s_pyx_capi); @@ -14807,7 +15030,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* FunctionExport */ - static int __Pyx_ExportFunction(const char *name, void (*f)(void), const char *sig) { + static int __Pyx_ExportFunction(const char *name, void (*f)(void), const char *sig) { PyObject *d = 0; PyObject *cobj = 0; union { @@ -14844,7 +15067,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* ModuleImport */ - #ifndef __PYX_HAVE_RT_ImportModule + #ifndef __PYX_HAVE_RT_ImportModule #define __PYX_HAVE_RT_ImportModule static PyObject *__Pyx_ImportModule(const char *name) { PyObject *py_name = 0; @@ -14862,7 +15085,7 @@ static PyObject *__Pyx_ImportModule(const char *name) { #endif /* TypeImport */ - #ifndef __PYX_HAVE_RT_ImportType + #ifndef __PYX_HAVE_RT_ImportType #define __PYX_HAVE_RT_ImportType static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class_name, size_t size, int strict) @@ -14927,7 +15150,7 @@ static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class #endif /* InitStrings */ - static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { + static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { while (t->p) { #if PY_MAJOR_VERSION < 3 if (t->is_unicode) { @@ -14953,7 +15176,7 @@ static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) - PyErr_Clear(); + return -1; ++t; } return 0; @@ -15167,6 +15390,9 @@ static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_DECREF(x); return ival; } +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } diff --git a/gensim/models/word2vec_inner.pyx b/gensim/models/word2vec_inner.pyx index 98e719c6d4..14836179cc 100755 --- a/gensim/models/word2vec_inner.pyx +++ b/gensim/models/word2vec_inner.pyx @@ -2,11 +2,14 @@ # cython: boundscheck=False # cython: wraparound=False # cython: cdivision=True +# cython: embedsignature=True # coding: utf-8 # # Copyright (C) 2013 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html +"""Optimized cython functions for training :class:`~gensim.models.word2vec.Word2Vec` model.""" + import cython import numpy as np cimport numpy as np @@ -66,12 +69,45 @@ cdef void our_saxpy_noblas(const int *N, const float *alpha, const float *X, con for i from 0 <= i < N[0] by 1: Y[i * (incY[0])] = (alpha[0]) * X[i * (incX[0])] + Y[i * (incY[0])] - cdef void fast_sentence_sg_hs( const np.uint32_t *word_point, const np.uint8_t *word_code, const int codelen, REAL_t *syn0, REAL_t *syn1, const int size, const np.uint32_t word2_index, const REAL_t alpha, REAL_t *work, REAL_t *word_locks, const int _compute_loss, REAL_t *_running_training_loss_param) nogil: + """Train on a single effective word from the current batch, using the Skip-Gram model. + + In this model we are using a given word to predict a context word (a word that is + close to the one we are using as training). Hierarchical softmax is used to speed-up + training. + + Parameters + ---------- + word_point + Vector representation of the current word. + word_code + ASCII (char == uint8) representation of the current word. + codelen + Number of characters (length) in the current word. + syn0 + Embeddings for the words in the vocabulary (`model.wv.vectors`) + syn1 + Weights of the hidden layer in the model's trainable neural network. + size + Length of the embeddings. + word2_index + Index of the context word in the vocabulary. + alpha + Learning rate. + work + Private working memory for each worker. + word_locks + Lock factors for each word. A value of 0 will block training. + _compute_loss + Whether or not the loss should be computed at this step. + _running_training_loss_param + Running loss, used to debug or inspect how training progresses. + + """ cdef long long a, b cdef long long row1 = word2_index * size, row2, sgn @@ -124,7 +160,49 @@ cdef unsigned long long fast_sentence_sg_neg( const np.uint32_t word2_index, const REAL_t alpha, REAL_t *work, unsigned long long next_random, REAL_t *word_locks, const int _compute_loss, REAL_t *_running_training_loss_param) nogil: + """Train on a single effective word from the current batch, using the Skip-Gram model. + + In this model we are using a given word to predict a context word (a word that is + close to the one we are using as training). Negative sampling is used to speed-up + training. + + Parameters + ---------- + negative + Number of negative words to be sampled. + cum_table + Cumulative-distribution table using stored vocabulary word counts for + drawing random words (with a negative label). + cum_table_len + Length of the `cum_table` + syn0 + Embeddings for the words in the vocabulary (`model.wv.vectors`) + syn1neg + Weights of the hidden layer in the model's trainable neural network. + size + Length of the embeddings. + word_index + Index of the current training word in the vocabulary. + word2_index + Index of the context word in the vocabulary. + alpha + Learning rate. + work + Private working memory for each worker. + next_random + Seed to produce the index for the next word to be randomly sampled. + word_locks + Lock factors for each word. A value of 0 will block training. + _compute_loss + Whether or not the loss should be computed at this step. + _running_training_loss_param + Running loss, used to debug or inspect how training progresses. + + Returns + ------- + Seed to draw the training word for the next iteration of the same routine. + """ cdef long long a cdef long long row1 = word2_index * size, row2 cdef unsigned long long modulo = 281474976710655ULL @@ -173,7 +251,50 @@ cdef void fast_sentence_cbow_hs( const np.uint32_t indexes[MAX_SENTENCE_LEN], const REAL_t alpha, REAL_t *work, int i, int j, int k, int cbow_mean, REAL_t *word_locks, const int _compute_loss, REAL_t *_running_training_loss_param) nogil: + """Train on a single effective word from the current batch, using the CBOW method. + + Using this method we train the trainable neural network by attempting to predict a + given word by its context (words surrounding the one we are trying to predict). + Hierarchical softmax method is used to speed-up training. + + Parameters + ---------- + word_point + Vector representation of the current word. + word_code + ASCII (char == uint8) representation of the current word. + codelens + Number of characters (length) for all words in the context. + neu1 + Private working memory for every worker. + syn0 + Embeddings for the words in the vocabulary (`model.wv.vectors`) + syn1 + Weights of the hidden layer in the model's trainable neural network. + size + Length of the embeddings. + word2_index + Index of the context word in the vocabulary. + alpha + Learning rate. + work + Private working memory for each worker. + i + Index of the word to be predicted from the context. + j + Index of the word at the beginning of the context window. + k + Index of the word at the end of the context window. + cbow_mean + If 0, use the sum of the context word vectors as the prediction. If 1, use the mean. + word_locks + Lock factors for each word. A value of 0 will block training. + _compute_loss + Whether or not the loss should be computed at this step. + _running_training_loss_param + Running loss, used to debug or inspect how training progresses. + """ cdef long long a, b cdef long long row2, sgn cdef REAL_t f, g, count, inv_count = 1.0, f_dot, lprob @@ -228,7 +349,55 @@ cdef unsigned long long fast_sentence_cbow_neg( const np.uint32_t indexes[MAX_SENTENCE_LEN], const REAL_t alpha, REAL_t *work, int i, int j, int k, int cbow_mean, unsigned long long next_random, REAL_t *word_locks, const int _compute_loss, REAL_t *_running_training_loss_param) nogil: + """Train on a single effective word from the current batch, using the CBOW method. + + Using this method we train the trainable neural network by attempting to predict a + given word by its context (words surrounding the one we are trying to predict). + Negative sampling is used to speed-up training. + + Parameters + ---------- + negative + Number of negative words to be sampled. + cum_table + Cumulative-distribution table using stored vocabulary word counts for + drawing random words (with a negative label). + cum_table_len + Length of the `cum_table` + codelens + Number of characters (length) for all words in the context. + neu1 + Private working memory for every worker. + syn0 + Embeddings for the words in the vocabulary (`model.wv.vectors`) + syn1neg + Weights of the hidden layer in the model's trainable neural network. + size + Length of the embeddings. + indexes + Indexes of the context words in the vocabulary. + alpha + Learning rate. + work + Private working memory for each worker. + i + Index of the word to be predicted from the context. + j + Index of the word at the beginning of the context window. + k + Index of the word at the end of the context window. + cbow_mean + If 0, use the sum of the context word vectors as the prediction. If 1, use the mean. + next_random + Seed for the drawing the predicted word for the next iteration of the same routine. + word_locks + Lock factors for each word. A value of 0 will block training. + _compute_loss + Whether or not the loss should be computed at this step. + _running_training_loss_param + Running loss, used to debug or inspect how training progresses. + """ cdef long long a cdef long long row2 cdef unsigned long long modulo = 281474976710655ULL @@ -294,11 +463,35 @@ cdef unsigned long long fast_sentence_cbow_neg( def train_batch_sg(model, sentences, alpha, _work, compute_loss): + """Update skip-gram model by training on a batch of sentences. + + Called internally from :meth:`~gensim.models.word2vec.Word2Vec.train`. + + Parameters + ---------- + model : :class:`~gensim.models.word2Vec.Word2Vec` + The Word2Vec model instance to train. + sentences : iterable of list of str + The corpus used to train the model. + alpha : float + The learning rate + _work : np.ndarray + Private working memory for each worker. + compute_loss : bool + Whether or not the training loss should be computed in this batch. + + Returns + ------- + int + Number of words in the vocabulary actually used for training (They already existed in the vocabulary + and were not discarded by negative sampling). + + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) - cdef int _compute_loss = (1 if compute_loss == True else 0) + cdef int _compute_loss = (1 if compute_loss else 0) cdef REAL_t _running_training_loss = model.running_training_loss cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) @@ -401,6 +594,31 @@ def train_batch_sg(model, sentences, alpha, _work, compute_loss): def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): + """Update CBOW model by training on a batch of sentences. + + Called internally from :meth:`~gensim.models.word2vec.Word2Vec.train`. + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The Word2Vec model instance to train. + sentences : iterable of list of str + The corpus used to train the model. + alpha : float + The learning rate. + _work : np.ndarray + Private working memory for each worker. + _neu1 : np.ndarray + Private working memory for each worker. + compute_loss : bool + Whether or not the training loss should be computed in this batch. + + Returns + ------- + int + Number of words in the vocabulary actually used for training (They already existed in the vocabulary + and were not discarded by negative sampling). + """ cdef int hs = model.hs cdef int negative = model.negative cdef int sample = (model.vocabulary.sample != 0) @@ -506,8 +724,29 @@ def train_batch_cbow(model, sentences, alpha, _work, _neu1, compute_loss): return effective_words -# Score is only implemented for hierarchical softmax def score_sentence_sg(model, sentence, _work): + """Obtain likelihood score for a single sentence in a fitted skip-gram representation. + + Notes + ----- + This scoring function is only implemented for hierarchical softmax (`model.hs == 1`). + The model should have been trained using the skip-gram model (`model.sg` == 1`). + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The trained model. It **MUST** have been trained using hierarchical softmax and the skip-gram algorithm. + sentence : list of str + The words comprising the sentence to be scored. + _work : np.ndarray + Private working memory for each worker. + + Returns + ------- + float + The probability assigned to this sentence by the Skip-Gram model. + + """ cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) cdef REAL_t *work @@ -586,7 +825,30 @@ cdef void score_pair_sg_hs( work[0] += f def score_sentence_cbow(model, sentence, _work, _neu1): + """Obtain likelihood score for a single sentence in a fitted CBOW representation. + + Notes + ----- + This scoring function is only implemented for hierarchical softmax (`model.hs == 1`). + The model should have been trained using the skip-gram model (`model.cbow` == 1`). + + Parameters + ---------- + model : :class:`~gensim.models.word2vec.Word2Vec` + The trained model. It **MUST** have been trained using hierarchical softmax and the CBOW algorithm. + sentence : list of str + The words comprising the sentence to be scored. + _work : np.ndarray + Private working memory for each worker. + _neu1 : np.ndarray + Private working memory for each worker. + + Returns + ------- + float + The probability assigned to this sentence by the Skip-Gram model. + """ cdef int cbow_mean = model.cbow_mean cdef REAL_t *syn0 = (np.PyArray_DATA(model.wv.vectors)) @@ -681,9 +943,15 @@ cdef void score_pair_cbow_hs( def init(): - """ - Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized - into table EXP_TABLE. Also calculate log(sigmoid(x)) into LOG_TABLE. + """Precompute function `sigmoid(x) = 1 / (1 + exp(-x))`, for x values discretized into table EXP_TABLE. + Also calculate log(sigmoid(x)) into LOG_TABLE. + + Returns + ------- + {0, 1, 2} + Enumeration to signify underlying data type returned by the BLAS dot product calculation. + 0 signifies double, 1 signifies double, and 2 signifies that custom cython loops were used + instead of BLAS. """ global our_dot @@ -706,11 +974,11 @@ def init(): # check whether sdot returns double or float d_res = dsdot(&size, x, &ONE, y, &ONE) p_res = &d_res - if (abs(d_res - expected) < 0.0001): + if abs(d_res - expected) < 0.0001: our_dot = our_dot_double our_saxpy = saxpy return 0 # double - elif (abs(p_res[0] - expected) < 0.0001): + elif abs(p_res[0] - expected) < 0.0001: our_dot = our_dot_float our_saxpy = saxpy return 1 # float From e455bc8d7bda035261c145e7e32f39cfef7dc107 Mon Sep 17 00:00:00 2001 From: Stergiadis Manos Date: Wed, 20 Jun 2018 12:23:18 +0200 Subject: [PATCH 10/40] Document LDA-related models (#2026) * Started documenting the LDA module. This is WIP, squash this commit later * More work on the LDA module * Started documenting the callbacks module * Finished documenting the Callbacks module * Finished documenting LdaModel, example fix still pending * Added documentation to the multicore version of LDA. Examples still need to be fixed. * applied code review corrections * temporary chunk of work on the sequential lda model * Fixed examples * Fixed examples for multicore LDA * Fixed examples in the callbacks module. EpochSaver raises a pickling error when binded to the model so I removed it * trivial fix * Added documentation for the DTM. Inspection and feedback probably needed. * Applied code review corrections * Documented part of the SSLM helper class. * Finished documenting all helper classes in the sequential LDA module * Improved module level docstring example * Fixed example * fix pep8 * formatting fixes in LDA based modules * fix formatting in ldaseqmodel (module seems broken) * update lsimodel docs * revert breaking code-changes * fix PEP8 and documentation build * cleanup callbacks * cleanup ldaseqmodel * cleanup ldamodel * cleanup ldamulticore (+ add link to onlineldavb.py script to ldamodel.py) --- gensim/models/callbacks.py | 535 +++++++++++++------ gensim/models/ldamodel.py | 976 +++++++++++++++++++++++----------- gensim/models/ldamulticore.py | 224 ++++---- gensim/models/ldaseqmodel.py | 848 ++++++++++++++++++++++------- gensim/models/lsimodel.py | 18 +- 5 files changed, 1855 insertions(+), 746 deletions(-) diff --git a/gensim/models/callbacks.py b/gensim/models/callbacks.py index c974a0d5e3..9935fdb3b4 100644 --- a/gensim/models/callbacks.py +++ b/gensim/models/callbacks.py @@ -1,3 +1,87 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# +# Copyright (C) 2018 RARE Technologies +# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html + + +"""Callbacks can be used to observe the training process. + +Since training in huge corpora can be time consuming, we want to offer the users some insight +into the process, in real time. In this way, convergence issues +or other potential problems can be identified early in the process, +saving precious time and resources. + +The metrics exposed through this module can be used to construct Callbacks, which will be called +at specific points in the training process, such as "epoch starts" or "epoch finished". +These metrics can be used to assess mod's convergence or correctness, for example +to save the model, visualize intermediate results, or anything else. + +Usage examples +-------------- +To implement a Callback, inherit from this base class and override one or more of its methods. + +Create a callback to save the training model after each epoch + +>>> from gensim.test.utils import common_corpus, common_texts, get_tmpfile +>>> from gensim.models.callbacks import CallbackAny2Vec +>>> from gensim.models import Word2Vec +>>> +>>> class EpochSaver(CallbackAny2Vec): +... '''Callback to save model after each epoch.''' +... +... def __init__(self, path_prefix): +... self.path_prefix = path_prefix +... self.epoch = 0 +... +... def on_epoch_end(self, model): +... output_path = get_tmpfile('{}_epoch{}.model'.format(self.path_prefix, self.epoch)) +... model.save(output_path) +... self.epoch += 1 +... + +Create a callback to print progress information to the console + +>>> class EpochLogger(CallbackAny2Vec): +... '''Callback to log information about training''' +... +... def __init__(self): +... self.epoch = 0 +... +... def on_epoch_begin(self, model): +... print("Epoch #{} start".format(self.epoch)) +... +... def on_epoch_end(self, model): +... print("Epoch #{} end".format(self.epoch)) +... self.epoch += 1 +... +>>> +>>> epoch_logger = EpochLogger() +>>> +>>> w2v_model = Word2Vec(common_texts, iter=5, size=10, min_count=0, seed=42, callbacks=[epoch_logger]) +Epoch #0 start +Epoch #0 end +Epoch #1 start +Epoch #1 end +Epoch #2 start +Epoch #2 end +Epoch #3 start +Epoch #3 end +Epoch #4 start +Epoch #4 end + +Create and bind a callback to a topic model. This callback will log the perplexity metric in real time + +>>> from gensim.models.callbacks import PerplexityMetric +>>> from gensim.models.ldamodel import LdaModel +>>> from gensim.test.utils import common_corpus, common_dictionary +>>> +>>> # Log the perplexity score at the end of each epoch. +>>> perplexity_logger = PerplexityMetric(corpus=common_corpus, logger='shell') +>>> lda = LdaModel(common_corpus, id2word=common_dictionary, num_topics=5, callbacks=[perplexity_logger]) + +""" + import gensim import logging import copy @@ -18,12 +102,24 @@ class Metric(object): - """ - Base Metric class for topic model evaluation metrics + """Base Metric class for topic model evaluation metrics. + + Concrete implementations include: + + * :class:`~gensim.models.callbacks.CoherenceMetric` + * :class:`~gensim.models.callbacks.PerplexityMetric` + * :class:`~gensim.models.callbacks.DiffMetric` + * :class:`~gensim.models.callbacks.ConvergenceMetric` + """ def __str__(self): - """ - Return a string representation of Metric class + """Get a string representation of Metric class. + + Returns + ------- + str + Human readable representation of the metric. + """ if self.title is not None: return self.title @@ -31,50 +127,88 @@ def __str__(self): return type(self).__name__[:-6] def set_parameters(self, **parameters): - """ - Set the parameters + """Set the metric parameters. + + Parameters + ---------- + **parameters + Keyword arguments to override the object's internal attributes. + """ for parameter, value in parameters.items(): setattr(self, parameter, value) def get_value(self): - pass + """Get the metric's value at this point in time. + + Warnings + -------- + The user **must** provide a concrete implementation for this method for every subclass of + this class. + + See Also + -------- + :meth:`gensim.models.callbacks.CoherenceMetric.get_value` + :meth:`gensim.models.callbacks.PerplexityMetric.get_value` + :meth:`gensim.models.callbacks.DiffMetric.get_value` + :meth:`gensim.models.callbacks.ConvergenceMetric.get_value` + + Returns + ------- + object + The metric's type depends on what exactly it measures. In the simplest case it might + be a real number corresponding to an error estimate. It could however be anything else + that is useful to report or visualize. + + """ + raise NotImplementedError("Please provide an implementation for `get_value` in your subclass.") class CoherenceMetric(Metric): - """ - Metric class for coherence evaluation + """Metric class for coherence evaluation. + + See Also + -------- + :class:`~gensim.models.coherencemodel.CoherenceModel` + """ def __init__(self, corpus=None, texts=None, dictionary=None, coherence=None, window_size=None, topn=10, logger=None, viz_env=None, title=None): """ - Args: - corpus : Gensim document corpus. - texts : Tokenized texts. Needed for coherence models that use sliding window based probability estimator, - dictionary : Gensim dictionary mapping of id word to create corpus. If model.id2word is present, - this is not needed. If both are provided, dictionary will be used. - window_size : Is the size of the window to be used for coherence measures using boolean - sliding window as their probability estimator. For 'u_mass' this doesn't matter. - If left 'None' the default window sizes are used which are: - - 'c_v' : 110 - 'c_uci' : 10 - 'c_npmi' : 10 - - coherence : Coherence measure to be used. Supported values are: - 'u_mass' - 'c_v' - 'c_uci' also popularly known as c_pmi - 'c_npmi' - For 'u_mass' corpus should be provided. If texts is provided, it will be converted - to corpus using the dictionary. For 'c_v', 'c_uci' and 'c_npmi' texts should be provided. - Corpus is not needed. - topn : Integer corresponding to the number of top words to be extracted from each topic. - logger : Monitor training process using: - "shell" : print coherence value in shell - "visdom" : visualize coherence value with increasing epochs in Visdom visualization framework - viz_env : Visdom environment to use for plotting the graph - title : title of the graph plot + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + texts : list of char (str of length 1), optional + Tokenized texts needed for coherence models that use sliding window based probability estimator. + dictionary : :class:`~gensim.corpora.dictionary.Dictionary`, optional + Gensim dictionary mapping from integer IDs to words, needed to create corpus. If `model.id2word` is present, + this is not needed. If both are provided, `dictionary` will be used. + coherence : {'u_mass', 'c_v', 'c_uci', 'c_npmi'}, optional + Coherence measure to be used. 'c_uci' is also known as 'c_pmi' in the literature. + For 'u_mass', the corpus **MUST** be provided. If `texts` is provided, it will be converted + to corpus using the dictionary. For 'c_v', 'c_uci' and 'c_npmi', `texts` **MUST** be provided. + Corpus is not needed. + window_size : int, optional + Size of the window to be used for coherence measures using boolean + sliding window as their probability estimator. For 'u_mass' this doesn't matter. + If 'None', the default window sizes are used which are: + + * `c_v` - 110 + * `c_uci` - 10 + * `c_npmi` - 10 + topn : int, optional + Number of top words to be extracted from each topic. + logger : {'shell', 'visdom'}, optional + Monitor training process using one of the available methods. 'shell' will print the coherence value in + the active shell, while 'visdom' will visualize the coherence value with increasing epochs using the Visdom + visualization framework. + viz_env : object, optional + Visdom environment to use for plotting the graph. Unused. + title : str, optional + Title of the graph plot in case `logger == 'visdom'`. Unused. + """ self.corpus = corpus self.dictionary = dictionary @@ -87,12 +221,24 @@ def __init__(self, corpus=None, texts=None, dictionary=None, coherence=None, self.title = title def get_value(self, **kwargs): - """ - Args: - model : Pre-trained topic model. Should be provided if topics is not provided. - Currently supports LdaModel, LdaMallet wrapper and LdaVowpalWabbit wrapper. Use 'topics' - parameter to plug in an as yet unsupported model. - topics : List of tokenized topics. + """Get the coherence score. + + Parameters + ---------- + **kwargs + Key word arguments to override the object's internal attributes. + One of the following parameters are expected: + + * `model` - pre-trained topic model of type :class:`~gensim.models.ldamodel.LdaModel`, or one + of its wrappers, such as :class:`~gensim.models.wrappers.ldamallet.LdaMallet` or + :class:`~gensim.models.wrappers.ldavowpalwabbit.LdaVowpalWabbit`. + * `topics` - list of tokenized topics. + + Returns + ------- + float + The coherence score. + """ # only one of the model or topic would be defined self.model = None @@ -109,18 +255,23 @@ def get_value(self, **kwargs): class PerplexityMetric(Metric): - """ - Metric class for perplexity evaluation - """ + """Metric class for perplexity evaluation.""" def __init__(self, corpus=None, logger=None, viz_env=None, title=None): """ - Args: - corpus : Gensim document corpus - logger : Monitor training process using: - "shell" : print coherence value in shell - "visdom" : visualize coherence value with increasing epochs in Visdom visualization framework - viz_env : Visdom environment to use for plotting the graph - title : title of the graph plot + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + logger : {'shell', 'visdom'}, optional + Monitor training process using one of the available methods. 'shell' will print the perplexity value in + the active shell, while 'visdom' will visualize the coherence value with increasing epochs using the Visdom + visualization framework. + viz_env : object, optional + Visdom environment to use for plotting the graph. Unused. + title : str, optional + Title of the graph plot in case `logger == 'visdom'`. Unused. + """ self.corpus = corpus self.logger = logger @@ -128,9 +279,22 @@ def __init__(self, corpus=None, logger=None, viz_env=None, title=None): self.title = title def get_value(self, **kwargs): - """ - Args: - model : Trained topic model + """Get the coherence score. + + Parameters + ---------- + **kwargs + Key word arguments to override the object's internal attributes. + A trained topic model is expected using the 'model' key. This can be of type + :class:`~gensim.models.ldamodel.LdaModel`, or one of its wrappers, such as + :class:`~gensim.models.wrappers.ldamallet.LdaMallet` or + :class:`~gensim.models.wrapper.ldavowpalwabbit.LdaVowpalWabbit`. + + Returns + ------- + float + The perplexity score. + """ super(PerplexityMetric, self).set_parameters(**kwargs) corpus_words = sum(cnt for document in self.corpus for _, cnt in document) @@ -139,28 +303,34 @@ def get_value(self, **kwargs): class DiffMetric(Metric): - """ - Metric class for topic difference evaluation - """ + """Metric class for topic difference evaluation.""" def __init__(self, distance="jaccard", num_words=100, n_ann_terms=10, diagonal=True, annotation=False, normed=True, logger=None, viz_env=None, title=None): """ - Args: - distance : measure used to calculate difference between any topic pair. Available values: - `kullback_leibler` - `hellinger` - `jaccard` - num_words : is quantity of most relevant words that used if distance == `jaccard` (also used for annotation) - n_ann_terms : max quantity of words in intersection/symmetric difference - between topics (used for annotation) - diagonal : difference between identical topic no.s - annotation : intersection or difference of words between topics - normed (bool) : If `true`, matrix/array Z will be normalized - logger : Monitor training process using: - "shell" : print coherence value in shell - "visdom" : visualize coherence value with increasing epochs in Visdom visualization framework - viz_env : Visdom environment to use for plotting the graph - title : title of the graph plot + + Parameters + ---------- + distance : {'kullback_leibler', 'hellinger', 'jaccard'}, optional + Measure used to calculate difference between any topic pair. + num_words : int, optional + The number of most relevant words used if `distance == 'jaccard'`. Also used for annotating topics. + n_ann_terms : int, optional + Max number of words in intersection/symmetric difference between topics. Used for annotation. + diagonal : bool, optional + Whether we need the difference between identical topics (the diagonal of the difference matrix). + annotation : bool, optional + Whether the intersection or difference of words between two topics should be returned. + normed : bool, optional + Whether the matrix should be normalized or not. + logger : {'shell', 'visdom'}, optional + Monitor training process using one of the available methods. 'shell' will print the coherence value in + the active shell, while 'visdom' will visualize the coherence value with increasing epochs using the Visdom + visualization framework. + viz_env : object, optional + Visdom environment to use for plotting the graph. Unused. + title : str, optional + Title of the graph plot in case `logger == 'visdom'`. Unused. + """ self.distance = distance self.num_words = num_words @@ -173,10 +343,23 @@ def __init__(self, distance="jaccard", num_words=100, n_ann_terms=10, diagonal=T self.title = title def get_value(self, **kwargs): - """ - Args: - model : Trained topic model - other_model : second topic model instance to calculate the difference from + """Get the difference between each pair of topics in two topic models. + + Parameters + ---------- + **kwargs + Key word arguments to override the object's internal attributes. + Two models of type :class:`~gensim.models.ldamodelLdaModel` or its wrappers are expected using the keys + `model` and `other_model`. + + Returns + ------- + np.ndarray of shape (`model.num_topics`, `other_model.num_topics`) + Matrix of differences between each pair of topics. + np.ndarray of shape (`model.num_topics`, `other_model.num_topics`, 2), optional + Annotation matrix where for each pair we include the word from the intersection of the two topics, + and the word from the symmetric difference of the two topics. Only included if `annotation == True`. + """ super(DiffMetric, self).set_parameters(**kwargs) diff_diagonal, _ = self.model.diff( @@ -187,29 +370,35 @@ def get_value(self, **kwargs): class ConvergenceMetric(Metric): - """ - Metric class for convergence evaluation - """ + """Metric class for convergence evaluation. """ def __init__(self, distance="jaccard", num_words=100, n_ann_terms=10, diagonal=True, annotation=False, normed=True, logger=None, viz_env=None, title=None): """ - Args: - distance : measure used to calculate difference between any topic pair. Available values: - `kullback_leibler` - `hellinger` - `jaccard` - num_words : is quantity of most relevant words that used if distance == `jaccard` (also used for annotation) - n_ann_terms : max quantity of words in intersection/symmetric difference - between topics (used for annotation) - diagonal : difference between identical topic no.s - annotation : intersection or difference of words between topics - normed (bool) : If `true`, matrix/array Z will be normalized - logger : Monitor training process using: - "shell" : print coherence value in shell - "visdom" : visualize coherence value with increasing epochs in Visdom visualization framework - viz_env : Visdom environment to use for plotting the graph - title : title of the graph plot - """ + + Parameters + ---------- + distance : {'kullback_leibler', 'hellinger', 'jaccard'}, optional + Measure used to calculate difference between any topic pair. + num_words : int, optional + The number of most relevant words used if `distance == 'jaccard'`. Also used for annotating topics. + n_ann_terms : int, optional + Max number of words in intersection/symmetric difference between topics. Used for annotation. + diagonal : bool, optional + Whether we need the difference between identical topics (the diagonal of the difference matrix). + annotation : bool, optional + Whether the intersection or difference of words between two topics should be returned. + normed : bool, optional + Whether the matrix should be normalized or not. + logger : {'shell', 'visdom'}, optional + Monitor training process using one of the available methods. 'shell' will print the coherence value in + the active shell, while 'visdom' will visualize the coherence value with increasing epochs using the Visdom + visualization framework. + viz_env : object, optional + Visdom environment to use for plotting the graph. Unused. + title : str, optional + Title of the graph plot in case `logger == 'visdom'`. Unused. + + """ self.distance = distance self.num_words = num_words self.n_ann_terms = n_ann_terms @@ -221,10 +410,24 @@ def __init__(self, distance="jaccard", num_words=100, n_ann_terms=10, diagonal=T self.title = title def get_value(self, **kwargs): - """ - Args: - model : Trained topic model - other_model : second topic model instance to calculate the difference from + """Get the sum of each element in the difference matrix between each pair of topics in two topic models. + + A small difference between the partially trained models produced by subsequent training iterations can indicate + that the model has stopped significantly improving and has therefore converged to a local or global optimum. + + Parameters + ---------- + **kwargs + Key word arguments to override the object's internal attributes. + Two models of type :class:`~gensim.models.ldamodel.LdaModel` or its wrappers are expected using the keys + `model` and `other_model`. + + Returns + ------- + float + The sum of the difference matrix between two trained topic models (usually the same model after two + subsequent training iterations). + """ super(ConvergenceMetric, self).set_parameters(**kwargs) diff_diagonal, _ = self.model.diff( @@ -235,24 +438,36 @@ def get_value(self, **kwargs): class Callback(object): - """ - Used to log/visualize the evaluation metrics during training. The values are stored at the end of each epoch. + """A class representing routines called reactively at specific phases during trained. + + These can be used to log or visualize the training progress using any of the metric scores developed before. + The values are stored at the end of each training epoch. The following metric scores are currently available: + + * :class:`~gensim.models.callbacks.CoherenceMetric` + * :class:`~gensim.models.callbacks.PerplexityMetric` + * :class:`~gensim.models.callbacks.DiffMetric` + * :class:`~gensim.models.callbacks.ConvergenceMetric` + """ def __init__(self, metrics): """ - Args: - metrics : a list of callbacks. Possible values: - "CoherenceMetric" - "PerplexityMetric" - "DiffMetric" - "ConvergenceMetric" + + Parameters + ---------- + metrics : list of :class:`~gensim.models.callbacks.Metric` + The list of metrics to be reported by the callback. + """ - # list of metrics to be plot self.metrics = metrics def set_model(self, model): - """ - Save the model instance and initialize any required variables which would be updated throughout training + """Save the model instance and initialize any required variables which would be updated throughout training. + + Parameters + ---------- + model : :class:`~gensim.models.basemodel.BaseTopicModel` + The model for which the training will be reported (logged or visualized) by the callback. + """ self.model = model self.previous = None @@ -272,12 +487,24 @@ def set_model(self, model): self.log_type = logging.getLogger('gensim.models.ldamodel') def on_epoch_end(self, epoch, topics=None): - """ - Log or visualize current epoch's metric value + """Report the current epoch's metric value. + + Called at the end of each training iteration. + + Parameters + ---------- + epoch : int + The epoch that just ended. + topics : list of list of str, optional + List of tokenized topics. This is required for the coherence metric. + + Returns + ------- + dict of (str, object) + Mapping from metric names to their values. The type of each value depends on the metric type, + for example :class:`~gensim.models.callbacks.DiffMetric` computes a matrix while + :class:`~gensim.models.callbacks.ConvergenceMetric` computes a float. - Args: - epoch : current epoch no. - topics : topic distribution from current epoch (required for coherence of unsupported topic models) """ # stores current epoch's metric values current_metrics = {} @@ -333,107 +560,77 @@ def on_epoch_end(self, epoch, topics=None): class CallbackAny2Vec(object): - """Base class to build callbacks. Callbacks are used to apply custom functions over the model at specific points - during training (epoch start, batch end etc.). To implement a Callback, subclass - :class:`~gensim.models.callbacks.CallbackAny2Vec`, look at the example below - which creates a callback to save a training model after each epoch: - - >>> from gensim.test.utils import common_texts as sentences - >>> from gensim.models.callbacks import CallbackAny2Vec - >>> from gensim.models import Word2Vec - >>> from gensim.test.utils import get_tmpfile - >>> - >>> class EpochSaver(CallbackAny2Vec): - ... "Callback to save model after every epoch" - ... def __init__(self, path_prefix): - ... self.path_prefix = path_prefix - ... self.epoch = 0 - ... def on_epoch_end(self, model): - ... output_path = '{}_epoch{}.model'.format(self.path_prefix, self.epoch) - ... print("Save model to {}".format(output_path)) - ... model.save(output_path) - ... self.epoch += 1 - ... - >>> - >>> class EpochLogger(CallbackAny2Vec): - ... "Callback to log information about training" - ... def __init__(self): - ... self.epoch = 0 - ... def on_epoch_begin(self, model): - ... print("Epoch #{} start".format(self.epoch)) - ... def on_epoch_end(self, model): - ... print("Epoch #{} end".format(self.epoch)) - ... self.epoch += 1 - ... - >>> epoch_saver = EpochSaver(get_tmpfile("temporary_model")) - >>> epoch_logger = EpochLogger() - >>> w2v_model = Word2Vec(sentences, iter=5, size=10, min_count=0, seed=42, callbacks=[epoch_saver, epoch_logger]) + """Base class to build callbacks for :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel`. - """ + Callbacks are used to apply custom functions over the model at specific points + during training (epoch start, batch end etc.). This is a base class and its purpose is to be inherited by + custom Callbacks that implement one or more of its methods (depending on the point during training where they + want some action to be taken). + See examples at the module level docstring for how to define your own callbacks by inheriting from this class. + + """ def on_epoch_begin(self, model): - """Method called on the start of epoch. + """Method called at the start of each epoch. Parameters ---------- - model : class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + model : :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` Current model. """ pass def on_epoch_end(self, model): - """Method called on the end of epoch. + """Method called at the end of each epoch. Parameters ---------- - model - - Returns - ------- + model : :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + Current model. """ pass def on_batch_begin(self, model): - """Method called on the start of batch. + """Method called at the start of each batch. Parameters ---------- - model : class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + model : :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` Current model. """ pass def on_batch_end(self, model): - """Method called on the end of batch. + """Method called at the end of each batch. Parameters ---------- - model : class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + model : :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` Current model. """ pass def on_train_begin(self, model): - """Method called on the start of training process. + """Method called at the start of the training process. Parameters ---------- - model : class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + model : :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` Current model. """ pass def on_train_end(self, model): - """Method called on the end of training process. + """Method called at the end of the training process. Parameters ---------- - model : class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` + model : :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel` Current model. """ diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py index 25698edb50..2f8fca4768 100755 --- a/gensim/models/ldamodel.py +++ b/gensim/models/ldamodel.py @@ -4,30 +4,76 @@ # Copyright (C) 2011 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html +"""Optimized `Latent Dirichlet Allocation (LDA) ` in Python. -""" -**For a faster implementation of LDA (parallelized for multicore machines), see** :mod:`gensim.models.ldamulticore`. - -Latent Dirichlet Allocation (LDA) in Python. +For a faster implementation of LDA (parallelized for multicore machines), see also :mod:`gensim.models.ldamulticore`. This module allows both LDA model estimation from a training corpus and inference of topic distribution on new, unseen documents. The model can also be updated with new documents for online training. -The core estimation code is based on the `onlineldavb.py` script by M. Hoffman [1]_, see -**Hoffman, Blei, Bach: Online Learning for Latent Dirichlet Allocation, NIPS 2010.** +The core estimation code is based on the `onlineldavb.py script +`_, by `Hoffman, Blei, Bach: +Online Learning for Latent Dirichlet Allocation, NIPS 2010 `_. The algorithm: -* is **streamed**: training documents may come in sequentially, no random access required, -* runs in **constant memory** w.r.t. the number of documents: size of the - training corpus does not affect memory footprint, can process corpora larger than RAM, and -* is **distributed**: makes use of a cluster of machines, if available, to - speed up model estimation. +#. Is **streamed**: training documents may come in sequentially, no random access required. +#. Runs in **constant memory** w.r.t. the number of documents: size of the training corpus does not affect memory + footprint, can process corpora larger than RAM. +#. Is **distributed**: makes use of a cluster of machines, if available, to speed up model estimation. + + +Usage examples +-------------- + +Train an LDA model using a Gensim corpus + +>>> from gensim.test.utils import common_texts +>>> from gensim.corpora.dictionary import Dictionary +>>> +>>> # Create a corpus from a list of texts +>>> common_dictionary = Dictionary(common_texts) +>>> common_corpus = [common_dictionary.doc2bow(text) for text in common_texts] +>>> +>>> # Train the model on the corpus. +>>> lda = LdaModel(common_corpus, num_topics=10) + +Save a model to disk, or reload a pre-trained model + +>>> from gensim.test.utils import datapath +>>> +>>> # Save model to disk. +>>> temp_file = datapath("model") +>>> lda.save(temp_file) +>>> +>>> # Load a potentially pretrained model from disk. +>>> lda = LdaModel.load(temp_file) + +Query, the model using new, unseen documents -.. [1] http://www.cs.princeton.edu/~mdhoffma +>>> # Create a new corpus, made of previously unseen documents. +>>> other_texts = [ +... ['computer', 'time', 'graph'], +... ['survey', 'response', 'eps'], +... ['human', 'system', 'computer'] +... ] +>>> other_corpus = [common_dictionary.doc2bow(text) for text in other_texts] +>>> +>>> unseen_doc = other_corpus[0] +>>> vector = lda[unseen_doc] # get topic probability distribution for a document + +Update the model by incrementally training on the new corpus + +>>> lda.update(other_corpus) +>>> vector = lda[unseen_doc] + +A lot of parameters can be tuned to optimize training for your specific case + +>>> lda = LdaModel(common_corpus, num_topics=50, alpha='auto', eval_every=5) # learn asymmetric alpha from data """ + import logging import numbers import os @@ -48,8 +94,9 @@ from gensim.models.callbacks import Callback -logger = logging.getLogger('gensim.models.ldamodel') +logger = logging.getLogger(__name__) +# Epsilon (very small) values used by each expected data type instead of 0, to avoid Arithmetic Errors. DTYPE_TO_EPS = { np.float16: 1e-5, np.float32: 1e-35, @@ -58,12 +105,27 @@ def update_dir_prior(prior, N, logphat, rho): + """Update a given prior using Newton's method, described in + `J. Huang: "Maximum Likelihood Estimation of Dirichlet Distribution Parameters" + `_. + + Parameters + ---------- + prior : list of float + The prior for each possible outcome at the previous iteration (to be updated). + N : int + Number of observations. + logphat : list of float + Log probabilities for the current estimation, also called "observed sufficient statistics". + rho : float + Learning rate. + + Returns + ------- + list of float + The updated prior. + """ - Updates a given prior using Newton's method, described in - **Huang: Maximum Likelihood Estimation of Dirichlet Distribution Parameters.** - http://jonathan-huang.org/research/dirichlet/dirichlet.pdf - """ - dprior = np.copy(prior) # TODO: unused var??? gradf = N * (psi(np.sum(prior)) - psi(prior) + logphat) c = N * polygamma(1, np.sum(prior)) @@ -82,53 +144,69 @@ def update_dir_prior(prior, N, logphat, rho): class LdaState(utils.SaveLoad): - """ - Encapsulate information for distributed computation of LdaModel objects. + """Encapsulate information for distributed computation of :class:`~gensim.models.ldamodel.LdaModel` objects. Objects of this class are sent over the network, so try to keep them lean to reduce traffic. """ - def __init__(self, eta, shape, dtype=np.float32): + """ + + Parameters + ---------- + eta : numpy.ndarray + The prior probabilities assigned to each term. + shape : tuple of (int, int) + Shape of the sufficient statistics: (number of topics to be found, number of terms in the vocabulary). + dtype : type + Overrides the numpy array default types. + + """ self.eta = eta.astype(dtype, copy=False) self.sstats = np.zeros(shape, dtype=dtype) self.numdocs = 0 self.dtype = dtype def reset(self): - """ - Prepare the state for a new EM iteration (reset sufficient stats). - - """ + """Prepare the state for a new EM iteration (reset sufficient stats).""" self.sstats[:] = 0.0 self.numdocs = 0 def merge(self, other): - """ - Merge the result of an E step from one node with that of another node - (summing up sufficient statistics). + """Merge the result of an E step from one node with that of another node (summing up sufficient statistics). The merging is trivial and after merging all cluster nodes, we have the exact same result as if the computation was run on a single node (no approximation). + Parameters + ---------- + other : :class:`~gensim.models.ldamodel.LdaState` + The state object with which the current one will be merged. + """ assert other is not None self.sstats += other.sstats self.numdocs += other.numdocs def blend(self, rhot, other, targetsize=None): - """ - Given LdaState `other`, merge it with the current state. Stretch both to - `targetsize` documents before merging, so that they are of comparable - magnitude. - - Merging is done by average weighting: in the extremes, `rhot=0.0` means - `other` is completely ignored; `rhot=1.0` means `self` is completely ignored. - - This procedure corresponds to the stochastic gradient update from Hoffman - et al., algorithm 2 (eq. 14). + """Merge the current state with another one using a weighted average for the sufficient statistics. + + The number of documents is stretched in both state objects, so that they are of comparable magnitude. + This procedure corresponds to the stochastic gradient update from + `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation" + `_, see equations (5) and (9). + + Parameters + ---------- + rhot : float + Weight of the `other` state in the computed average. A value of 0.0 means that `other` + is completely ignored. A value of 1.0 means `self` is completely ignored. + other : :class:`~gensim.models.ldamodel.LdaState` + The state object with which the current one will be merged. + targetsize : int, optional + The number of documents to stretch both states to. """ assert other is not None @@ -153,8 +231,20 @@ def blend(self, rhot, other, targetsize=None): self.numdocs = targetsize def blend2(self, rhot, other, targetsize=None): - """ - Alternative, more simple blend. + """Merge the current state with another one using a weighted sum for the sufficient statistics. + + In contrast to :meth:`~gensim.models.ldamodel.LdaState.blend`, the sufficient statistics are not scaled + prior to aggregation. + + Parameters + ---------- + rhot : float + Unused. + other : :class:`~gensim.models.ldamodel.LdaState` + The state object with which the current one will be merged. + targetsize : int, optional + The number of documents to stretch both states to. + """ assert other is not None if targetsize is None: @@ -165,42 +255,86 @@ def blend2(self, rhot, other, targetsize=None): self.numdocs = targetsize def get_lambda(self): + """Get the parameters of the posterior over the topics, also referred to as "the topics". + + Returns + ------- + numpy.ndarray + Parameters of the posterior probability over topics. + + """ return self.eta + self.sstats def get_Elogbeta(self): + """Get the log (posterior) probabilities for each topic. + + Returns + ------- + numpy.ndarray + Posterior probabilities for each topic. + """ return dirichlet_expectation(self.get_lambda()) @classmethod def load(cls, fname, *args, **kwargs): + """Load a previously stored state from disk. + + Overrides :class:`~gensim.utils.SaveLoad.load` by enforcing the `dtype` parameter + to ensure backwards compatibility. + + Parameters + ---------- + fname : str + Path to file that contains the needed object. + args : object + Positional parameters to be propagated to class:`~gensim.utils.SaveLoad.load` + kwargs : object + Key-word parameters to be propagated to class:`~gensim.utils.SaveLoad.load` + + Returns + ------- + :class:`~gensim.models.ldamodel.LdaState` + The state loaded from the given file. + + """ result = super(LdaState, cls).load(fname, *args, **kwargs) # dtype could be absent in old models if not hasattr(result, 'dtype'): - result.dtype = np.float64 # float64 was implicitly used before (cause it's default in numpy) + result.dtype = np.float64 # float64 was implicitly used before (because it's the default in numpy) logging.info("dtype was not set in saved %s file %s, assuming np.float64", result.__class__.__name__, fname) return result -# endclass LdaState class LdaModel(interfaces.TransformationABC, basemodel.BaseTopicModel): - """ - The constructor estimates Latent Dirichlet Allocation model parameters based - on a training corpus: + """Train and use Online Latent Dirichlet Allocation (OLDA) models as presented in + `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation" `_. - >>> lda = LdaModel(corpus, num_topics=10) + Examples + ------- + Initialize a model using a Gensim corpus - You can then infer topic distributions on new, unseen documents, with + >>> from gensim.test.utils import common_corpus + >>> + >>> lda = LdaModel(common_corpus, num_topics=10) + You can then infer topic distributions on new, unseen documents. + + >>> doc_bow = [(1, 0.3), (2, 0.1), (0, 0.09)] >>> doc_lda = lda[doc_bow] - The model can be updated (trained) with new documents via + The model can be updated (trained) with new documents. + >>> # In practice (corpus =/= initial training corpus), but we use the same here for simplicity. + >>> other_corpus = common_corpus + >>> >>> lda.update(other_corpus) - Model persistency is achieved through its `load`/`save` methods. - """ + Model persistency is achieved through :meth:`~gensim.models.ldamodel.LdaModel.load` and + :meth:`~gensim.models.ldamodel.LdaModel.save` methods. + """ def __init__(self, corpus=None, num_topics=100, id2word=None, distributed=False, chunksize=2000, passes=1, update_every=1, alpha='symmetric', eta=None, decay=0.5, offset=1.0, eval_every=10, @@ -208,62 +342,72 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, random_state=None, ns_conf=None, minimum_phi_value=0.01, per_word_topics=False, callbacks=None, dtype=np.float32): """ - If given, start training from the iterable `corpus` straight away. If not given, - the model is left untrained (presumably because you want to call `update()` manually). - - `num_topics` is the number of requested latent topics to be extracted from - the training corpus. - `id2word` is a mapping from word ids (integers) to words (strings). It is - used to determine the vocabulary size, as well as for debugging and topic - printing. - - `alpha` and `eta` are hyperparameters that affect sparsity of the document-topic - (theta) and topic-word (lambda) distributions. Both default to a symmetric - 1.0/num_topics prior. - - `alpha` can be set to an explicit array = prior of your choice. It also - support special values of 'asymmetric' and 'auto': the former uses a fixed - normalized asymmetric 1.0/topicno prior, the latter learns an asymmetric - prior directly from your data. - - `eta` can be a scalar for a symmetric prior over topic/word - distributions, or a vector of shape num_words, which can be used to - impose (user defined) asymmetric priors over the word distribution. - It also supports the special value 'auto', which learns an asymmetric - prior over words directly from your data. `eta` can also be a matrix - of shape num_topics x num_words, which can be used to impose - asymmetric priors over the word distribution on a per-topic basis - (can not be learned from data). - - Turn on `distributed` to force distributed computing - (see the `web tutorial `_ - on how to set up a cluster of machines for gensim). - - Calculate and log perplexity estimate from the latest mini-batch every - `eval_every` model updates (setting this to 1 slows down training ~2x; - default is 10 for better performance). Set to None to disable perplexity estimation. - - `decay` and `offset` parameters are the same as Kappa and Tau_0 in - Hoffman et al, respectively. - - `minimum_probability` controls filtering the topics returned for a document (bow). - - `random_state` can be a np.random.RandomState object or the seed for one. - - `callbacks` a list of metric callbacks to log/visualize evaluation metrics of topic model during training. - - `dtype` is data-type to use during calculations inside model. All inputs are also converted to this dtype. - Available types: `numpy.float16`, `numpy.float32`, `numpy.float64`. - - Example: - - >>> lda = LdaModel(corpus, num_topics=100) # train model - >>> print(lda[doc_bow]) # get topic probability distribution for a document - >>> lda.update(corpus2) # update the LDA model with additional documents - >>> print(lda[doc_bow]) - - >>> lda = LdaModel(corpus, num_topics=50, alpha='auto', eval_every=5) # train asymmetric alpha from data + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + If not given, the model is left untrained (presumably because you want to call + :meth:`~gensim.models.ldamodel.LdaModel.update` manually). + num_topics : int, optional + The number of requested latent topics to be extracted from the training corpus. + id2word : {dict of (int, str), :class:`gensim.corpora.dictionary.Dictionary`} + Mapping from word IDs to words. It is used to determine the vocabulary size, as well as for + debugging and topic printing. + distributed : bool, optional + Whether distributed computing should be used to accerelate training. + chunksize : int, optional + Number of documents to be used in each training chunk. + passes : int, optional + Number of passes through the corpus during training. + update_every : int, optional + Number of documents to be iterated through for each update. + Set to 0 for batch learning, > 1 for online iterative learning. + alpha : {numpy.ndarray, str}, optional + Can be set to an 1D array of length equal to the number of expected topics that expresses + our a-priori belief for the each topics' probability. + Alternatively default prior selecting strategies can be employed by supplying a string: + + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'default': Learns an asymmetric prior from the corpus. + eta : {float, np.array, str}, optional + A-priori belief on word probability, this can be: + + * scalar for a symmetric prior over topic/word probability, + * vector of length num_words to denote an asymmetric user defined probability for each word, + * matrix of shape (num_topics, num_words) to assign a probability for each word-topic combination, + * the string 'auto' to learn the asymmetric prior from the data. + decay : float, optional + A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten + when each new document is examined. Corresponds to Kappa from + `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + offset : float, optional + Hyper-parameter that controls how much we will slow down the first steps the first few iterations. + Corresponds to Tau_0 from `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + eval_every : int, optional + Log perplexity is estimated every that many updates. Setting this to one slows down training by ~2x. + iterations : int, optional + Maximum number of iterations through the corpus when inferring the topic distribution of a corpus. + gamma_threshold : float, optional + Minimum change in the value of the gamma parameters to continue iterating. + minimum_probability : float, optional + Topics with a probability lower than this threshold will be filtered out. + random_state : {np.random.RandomState, int}, optional + Either a randomState object or a seed to generate one. Useful for reproducibility. + ns_conf : dict of (str, object), optional + Key word parameters propagated to :func:`gensim.utils.getNS` to get a Pyro4 Nameserved. + Only used if `distributed` is set to True. + minimum_phi_value : float, optional + if `per_word_topics` is True, this represents a lower bound on the term probabilities. + per_word_topics : bool + If True, the model also computes a list of topics, sorted in descending order of most likely topics for + each word, along with their phi values multiplied by the feature length (i.e. word count). + callbacks : list of :class:`~gensim.models.callbacks.Callback` + Metric callbacks to log and visualize evaluation metrics of the model during training. + dtype : {numpy.float16, numpy.float32, numpy.float64}, optional + Data-type to use during calculations inside model. All inputs are also converted. """ if dtype not in DTYPE_TO_EPS: @@ -361,7 +505,7 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, self.state.sstats[...] = self.random_state.gamma(100., 1. / 100., (self.num_topics, self.num_terms)) self.expElogbeta = np.exp(dirichlet_expectation(self.state.sstats)) - # Check that we haven't accidentally fall back to np.float64 + # Check that we haven't accidentally fallen back to np.float64 assert self.eta.dtype == self.dtype assert self.expElogbeta.dtype == self.dtype @@ -371,6 +515,27 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, self.update(corpus, chunks_as_numpy=use_numpy) def init_dir_prior(self, prior, name): + """Initialize priors for the Dirichlet distribution. + + Parameters + ---------- + prior : {str, list of float, numpy.ndarray of float, float} + A-priori belief on word probability. If `name` == 'eta' then the prior can be: + + * scalar for a symmetric prior over topic/word probability, + * vector of length num_words to denote an asymmetric user defined probability for each word, + * matrix of shape (num_topics, num_words) to assign a probability for each word-topic combination, + * the string 'auto' to learn the asymmetric prior from the data. + + If `name` == 'alpha', then the prior can be: + + * an 1D array of length equal to the number of expected topics, + * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. + * 'default': Learns an assymetric prior from the corpus. + name : {'alpha', 'eta'} + Whether the `prior` is parameterized by the alpha vector (1 parameter per topic) + or by the eta (1 parameter per unique term in the vocabulary). + """ if prior is None: prior = 'symmetric' @@ -411,35 +576,51 @@ def init_dir_prior(self, prior, name): return init_prior, is_auto def __str__(self): + """Get a string representation of the current object. + + Returns + ------- + str + Human readable representation of the most important model parameters. + + """ return "LdaModel(num_terms=%s, num_topics=%s, decay=%s, chunksize=%s)" % ( self.num_terms, self.num_topics, self.decay, self.chunksize ) def sync_state(self): + """Propagate the states topic probabilities to the inner object's attribute.""" self.expElogbeta = np.exp(self.state.get_Elogbeta()) assert self.expElogbeta.dtype == self.dtype def clear(self): - """Clear model state (free up some memory). Used in the distributed algo.""" + """Clear the model's state to free some memory. Used in the distributed implementation.""" self.state = None self.Elogbeta = None def inference(self, chunk, collect_sstats=False): - """ - Given a chunk of sparse document vectors, estimate gamma (parameters - controlling the topic weights) for each document in the chunk. - - This function does not modify the model (=is read-only aka const). The - whole input chunk of document is assumed to fit in RAM; chunking of a - large corpus must be done earlier in the pipeline. - - If `collect_sstats` is True, also collect sufficient statistics needed - to update the model's topic-word distributions, and return a 2-tuple - `(gamma, sstats)`. Otherwise, return `(gamma, None)`. `gamma` is of shape - `len(chunk) x self.num_topics`. - - Avoids computing the `phi` variational parameter directly using the - optimization presented in **Lee, Seung: Algorithms for non-negative matrix factorization, NIPS 2001**. + """Given a chunk of sparse document vectors, estimate gamma (parameters controlling the topic weights) + for each document in the chunk. + + This function does not modify the model The whole input chunk of document is assumed to fit in RAM; + chunking of a large corpus must be done earlier in the pipeline. Avoids computing the `phi` variational + parameter directly using the optimization presented in + `Lee, Seung: Algorithms for non-negative matrix factorization" + `_. + + Parameters + ---------- + chunk : {list of list of (int, float), scipy.sparse.csc} + The corpus chunk on which the inference step will be performed. + collect_sstats : bool, optional + If set to True, also collect (and return) sufficient statistics needed to update the model's topic-word + distributions. + + Returns + ------- + (numpy.ndarray, {numpy.ndarray, None}) + The first element is always returned and it corresponds to the states gamma matrix. The second element is + only returned if `collect_sstats` == True and corresponds to the sufficient statistics for the M step. """ try: @@ -523,9 +704,20 @@ def inference(self, chunk, collect_sstats=False): return gamma, sstats def do_estep(self, chunk, state=None): - """ - Perform inference on a chunk of documents, and accumulate the collected - sufficient statistics in `state` (or `self.state` if None). + """Perform inference on a chunk of documents, and accumulate the collected sufficient statistics. + + Parameters + ---------- + chunk : {list of list of (int, float), scipy.sparse.csc} + The corpus chunk on which the inference step will be performed. + state : :class:`~gensim.models.ldamodel.LdaState`, optional + The state to be updated with the newly accumulated sufficient statistics. If none, the models + `self.state` is updated. + + Returns + ------- + numpy.ndarray + Gamma parameters controlling the topic weights, shape (`len(chunk)`, `self.num_topics`). """ if state is None: @@ -537,9 +729,20 @@ def do_estep(self, chunk, state=None): return gamma def update_alpha(self, gammat, rho): - """ - Update parameters for the Dirichlet prior on the per-document - topic weights `alpha` given the last `gammat`. + """Update parameters for the Dirichlet prior on the per-document topic weights. + + Parameters + ---------- + gammat : numpy.ndarray + Previous topic weight parameters. + rho : float + Learning rate. + + Returns + ------- + numpy.ndarray + Sequence of alpha parameters. + """ N = float(len(gammat)) logphat = sum(dirichlet_expectation(gamma) for gamma in gammat) / N @@ -552,9 +755,20 @@ def update_alpha(self, gammat, rho): return self.alpha def update_eta(self, lambdat, rho): - """ - Update parameters for the Dirichlet prior on the per-topic - word weights `eta` given the last `lambdat`. + """Update parameters for the Dirichlet prior on the per-topic word weights. + + Parameters + ---------- + lambdat : numpy.ndarray + Previous lambda parameters. + rho : float + Learning rate. + + Returns + ------- + numpy.ndarray + The updated eta parameters. + """ N = float(lambdat.shape[0]) logphat = (sum(dirichlet_expectation(lambda_) for lambda_ in lambdat) / N).reshape((self.num_terms,)) @@ -566,10 +780,21 @@ def update_eta(self, lambdat, rho): return self.eta def log_perplexity(self, chunk, total_docs=None): - """ - Calculate and return per-word likelihood bound, using the `chunk` of - documents as evaluation corpus. Also output the calculated statistics. incl. - perplexity=2^(-bound), to log at INFO level. + """Calculate and return per-word likelihood bound, using a chunk of documents as evaluation corpus. + + Also output the calculated statistics, including the perplexity=2^(-bound), to log at INFO level. + + Parameters + ---------- + chunk : {list of list of (int, float), scipy.sparse.csc} + The corpus chunk on which the inference step will be performed. + total_docs : int, optional + Number of docs used for evaluation of the perplexity. + + Returns + ------- + numpy.ndarray + The variational bound score calculated for each word. """ if total_docs is None: @@ -586,35 +811,52 @@ def log_perplexity(self, chunk, total_docs=None): def update(self, corpus, chunksize=None, decay=None, offset=None, passes=None, update_every=None, eval_every=None, iterations=None, gamma_threshold=None, chunks_as_numpy=False): - """ - Train the model with new documents, by EM-iterating over `corpus` until - the topics converge (or until the maximum number of allowed iterations - is reached). `corpus` must be an iterable (repeatable stream of documents), + """Train the model with new documents, by EM-iterating over the corpus until the topics converge, or until + the maximum number of allowed iterations is reached. `corpus` must be an iterable. In distributed mode, the E step is distributed over a cluster of machines. - This update also supports updating an already trained model (`self`) - with new documents from `corpus`; the two models are then merged in - proportion to the number of old vs. new documents. This feature is still - experimental for non-stationary input streams. - - For stationary input (no topic drift in new documents), on the other hand, - this equals the online update of Hoffman et al. and is guaranteed to - converge for any `decay` in (0.5, 1.0>. Additionally, for smaller - `corpus` sizes, an increasing `offset` may be beneficial (see - Table 1 in Hoffman et al.) - - Args: - corpus (gensim corpus): The corpus with which the LDA model should be updated. - - chunks_as_numpy (bool): Whether each chunk passed to `.inference` should be a np - array of not. np can in some settings turn the term IDs - into floats, these will be converted back into integers in - inference, which incurs a performance hit. For distributed - computing it may be desirable to keep the chunks as np - arrays. - - For other parameter settings, see :class:`LdaModel` constructor. + Notes + ----- + This update also supports updating an already trained model with new documents; the two models are then merged + in proportion to the number of old vs. new documents. This feature is still experimental for non-stationary + input streams. For stationary input (no topic drift in new documents), on the other hand, this equals the + online update of `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + and is guaranteed to converge for any `decay` in (0.5, 1.0). Additionally, for smaller corpus sizes, an + increasing `offset` may be beneficial (see Table 1 in the same paper). + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`) used to update the + model. + chunksize : int, optional + Number of documents to be used in each training chunk. + decay : float, optional + A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten + when each new document is examined. Corresponds to Kappa from + `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + offset : float, optional + Hyper-parameter that controls how much we will slow down the first steps the first few iterations. + Corresponds to Tau_0 from `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + passes : int, optional + Number of passes through the corpus during training. + update_every : int, optional + Number of documents to be iterated through for each update. + Set to 0 for batch learning, > 1 for online iterative learning. + eval_every : int, optional + Log perplexity is estimated every that many updates. Setting this to one slows down training by ~2x. + iterations : int, optional + Maximum number of iterations through the corpus when inferring the topic distribution of a corpus. + gamma_threshold : float, optional + Minimum change in the value of the gamma parameters to continue iterating. + chunks_as_numpy : bool, optional + Whether each chunk passed to the inference step should be a numpy.ndarray or not. Numpy can in some settings + turn the term IDs into floats, these will be converted back into integers in inference, which incurs a + performance hit. For distributed computing it may be desirable to keep the chunks as `numpy.ndarray`. """ # use parameters given in constructor, unless user explicitly overrode them @@ -741,7 +983,6 @@ def rho(): else: other = LdaState(self.eta, self.state.sstats.shape, self.dtype) dirty = False - # endfor single corpus iteration if reallen != lencorpus: raise RuntimeError("input corpus size changed during training (don't use generators as input)") @@ -762,13 +1003,19 @@ def rho(): del other dirty = False - # endfor entire corpus update - def do_mstep(self, rho, other, extra_pass=False): - """ - M step: use linear interpolation between the existing topics and + """Maximization step: use linear interpolation between the existing topics and collected sufficient statistics in `other` to update the topics. + Parameters + ---------- + rho : float + Learning rate. + other : :class:`~gensim.models.ldamodel.LdaModel` + The model whose sufficient statistics will be used to update the topics. + extra_pass : bool, optional + Whether this step required an additional pass over the corpus. + """ logger.debug("updating topics") # update self with the new blend; also keep track of how much did @@ -790,22 +1037,25 @@ def do_mstep(self, rho, other, extra_pass=False): self.num_updates += other.numdocs def bound(self, corpus, gamma=None, subsample_ratio=1.0): - """ - Estimate the variational bound of documents from `corpus`: - E_q[log p(corpus)] - E_q[log q(corpus)] - - Args: - corpus: documents to infer variational bounds from. - gamma: the variational parameters on topic weights for each `corpus` - document (=2d matrix=what comes out of `inference()`). - If not supplied, will be inferred from the model. - subsample_ratio (float): If `corpus` is a sample of the whole corpus, - pass this to inform on what proportion of the corpus it represents. - This is used as a multiplicative factor to scale the likelihood - appropriately. - - Returns: - The variational bound score calculated. + """Estimate the variational bound of documents from the corpus as E_q[log p(corpus)] - E_q[log q(corpus)]. + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`) used to estimate the + variational bounds. + gamma : numpy.ndarray, optional + Topic weight variational parameters for each document. If not supplied, it will be inferred from the model. + subsample_ratio : float, optional + Percentage of the whole corpus represented by the passed `corpus` argument (in case this was a sample). + Set to 1.0 if the whole corpus was passed.This is used as a multiplicative factor to scale the likelihood + appropriately. + + Returns + ------- + numpy.ndarray + The variational bound score calculated for each document. + """ score = 0.0 _lambda = self.state.get_lambda() @@ -849,19 +1099,29 @@ def bound(self, corpus, gamma=None, subsample_ratio=1.0): return score def show_topics(self, num_topics=10, num_words=10, log=False, formatted=True): - """ - Args: - num_topics (int): show results for first `num_topics` topics. - Unlike LSA, there is no natural ordering between the topics in LDA. - The returned `num_topics <= self.num_topics` subset of all topics is - therefore arbitrary and may change between two LDA training runs. - num_words (int): include top `num_words` with highest probabilities in topic. - log (bool): If True, log output in addition to returning it. - formatted (bool): If True, format topics as strings, otherwise return them as - `(word, probability)` 2-tuples. - Returns: - list: `num_words` most significant words for `num_topics` number of topics - (10 words for top 10 topics, by default). + """Get a representation for selected topics. + + Parameters + ---------- + num_topics : int, optional + Number of topics to be returned. Unlike LSA, there is no natural ordering between the topics in LDA. + The returned topics subset of all topics is therefore arbitrary and may change between two LDA + training runs. + num_words : int, optional + Number of words to be presented for each topic. These will be the most relevant words (assigned the highest + probability for each topic). + log : bool, optional + Whether the output is also logged, besides being returned. + formatted : bool, optional + Whether the topic representations should be formatted as strings. If False, they are returned as + 2 tuples of (word, probability). + + Returns + ------- + list of {str, tuple of (str, float)} + a list of topics, each represented either as a string (when `formatted` == True) or word-probability + pairs. + """ if num_topics < 0 or num_topics >= self.num_topics: num_topics = self.num_topics @@ -894,35 +1154,53 @@ def show_topics(self, num_topics=10, num_words=10, log=False, formatted=True): return shown def show_topic(self, topicid, topn=10): - """ - Args: - topn (int): Only return 2-tuples for the topn most probable words - (ignore the rest). + """Get the representation for a single topic. Words here are the actual strings, in constrast to + :meth:`~gensim.models.ldamodel.LdaModel.get_topic_terms` that represents words by their vocabulary ID. + + Parameters + ---------- + topicid : int + The ID of the topic to be returned + topn : int, optional + Number of the most significant words that are associated with the topic. + + Returns + ------- + list of (str, float) + Word - probability pairs for the most relevant words generated by the topic. - Returns: - list: of `(word, probability)` 2-tuples for the most probable - words in topic `topicid`. """ return [(self.id2word[id], value) for id, value in self.get_topic_terms(topicid, topn)] def get_topics(self): - """ - Returns: - np.ndarray: `num_topics` x `vocabulary_size` array of floats (self.dtype) which represents - the term topic matrix learned during inference. + """Get the term-topic matrix learned during inference. + + + Returns + ------- + numpy.ndarray + The probability for each word in each topic, shape (`num_topics`, `vocabulary_size`). + """ topics = self.state.get_lambda() return topics / topics.sum(axis=1)[:, None] def get_topic_terms(self, topicid, topn=10): - """ - Args: - topn (int): Only return 2-tuples for the topn most probable words - (ignore the rest). + """Get the representation for a single topic. Words the integer IDs, in constrast to + :meth:`~gensim.models.ldamodel.LdaModel.show_topic` that represents words by the actual strings. + + Parameters + ---------- + topicid : int + The ID of the topic to be returned + topn : int, optional + Number of the most significant words that are associated with the topic. + + Returns + ------- + list of (int, float) + Word ID - probability pairs for the most relevant words generated by the topic. - Returns: - list: `(word_id, probability)` 2-tuples for the most probable words - in topic with id `topicid`. """ topic = self.get_topics()[topicid] topic = topic / topic.sum() # normalize to probability distribution @@ -931,16 +1209,39 @@ def get_topic_terms(self, topicid, topn=10): def top_topics(self, corpus=None, texts=None, dictionary=None, window_size=None, coherence='u_mass', topn=20, processes=-1): - """ - Calculate the coherence for each topic; default is Umass coherence. + """Get the topics with the highest coherence score the coherence for each topic. + + Parameters + ---------- + corpus : iterable of list of (int, float), optional + Corpus in BoW format. + texts : list of list of str, optional + Tokenized texts, needed for coherence models that use sliding window based (i.e. coherence=`c_something`) + probability estimator . + dictionary : :class:`~gensim.corpora.dictionary.Dictionary`, optional + Gensim dictionary mapping of id word to create corpus. + If `model.id2word` is present, this is not needed. If both are provided, passed `dictionary` will be used. + window_size : int, optional + Is the size of the window to be used for coherence measures using boolean sliding window as their + probability estimator. For 'u_mass' this doesn't matter. + If None - the default window sizes are used which are: 'c_v' - 110, 'c_uci' - 10, 'c_npmi' - 10. + coherence : {'u_mass', 'c_v', 'c_uci', 'c_npmi'}, optional + Coherence measure to be used. + Fastest method - 'u_mass', 'c_uci' also known as `c_pmi`. + For 'u_mass' corpus should be provided, if texts is provided, it will be converted to corpus + using the dictionary. For 'c_v', 'c_uci' and 'c_npmi' `texts` should be provided (`corpus` isn't needed) + topn : int, optional + Integer corresponding to the number of top words to be extracted from each topic. + processes : int, optional + Number of processes to use for probability estimation phase, any value less than 1 will be interpreted as + num_cpus - 1. + + Returns + ------- + list of (list of (int, str), float) + Each element in the list is a pair of a topic representation and its coherence score. Topic representations + are distributions of words, represented as a list of pairs of word IDs and their probabilities. - See the :class:`gensim.models.CoherenceModel` constructor for more info on the - parameters and the different coherence metrics. - - Returns: - list: tuples with `(topic_repr, coherence_score)`, where `topic_repr` is a list - of representations of the `topn` terms for the topic. The terms are represented - as tuples of `(membership_in_topic, token)`. The `coherence_score` is a float. """ cm = CoherenceModel( model=self, corpus=corpus, texts=texts, dictionary=dictionary, @@ -960,22 +1261,33 @@ def top_topics(self, corpus=None, texts=None, dictionary=None, window_size=None, def get_document_topics(self, bow, minimum_probability=None, minimum_phi_value=None, per_word_topics=False): - """ - Args: - bow (list): Bag-of-words representation of the document to get topics for. - minimum_probability (float): Ignore topics with probability below this value - (None by default). If set to None, a value of 1e-8 is used to prevent 0s. - per_word_topics (bool): If True, also returns a list of topics, sorted in - descending order of most likely topics for that word. It also returns a list - of word_ids and each words corresponding topics' phi_values, multiplied by - feature length (i.e, word count). - minimum_phi_value (float): if `per_word_topics` is True, this represents a lower - bound on the term probabilities that are included (None by default). If set - to None, a value of 1e-8 is used to prevent 0s. - - Returns: - topic distribution for the given document `bow`, as a list of - `(topic_id, topic_probability)` 2-tuples. + """Get the topic distribution for the given document. + + Parameters + ---------- + bow : corpus : list of (int, float) + The document in BOW format. + minimum_probability : float + Topics with an assigned probability lower than this threshold will be discarded. + minimum_phi_value : float + f `per_word_topics` is True, this represents a lower bound on the term probabilities that are included. + If set to None, a value of 1e-8 is used to prevent 0s. + per_word_topics : bool + If True, this function will also return two extra lists as explained in the "Returns" section. + + Returns + ------- + list of (int, float) + Topic distribution for the whole document. Each element in the list is a pair of a topic's id, and + the probability that was assigned to it. + list of (int, list of (int, float), optional + Most probable topics per word. Each element in the list is a pair of a word's id, and a list of + topics sorted by their relevance to this word. Only returned if `per_word_topics` was set to True. + list of (int, list of float), optional + Phi relevance values, multipled by the feature length, for each word-topic combination. + Each element in the list is a pair of a word's id and a list of the phi values between this word and + each topic. Only returned if `per_word_topics` was set to True. + """ if minimum_probability is None: minimum_probability = self.minimum_probability @@ -1029,14 +1341,21 @@ def get_document_topics(self, bow, minimum_probability=None, minimum_phi_value=N return document_topics, word_topic, word_phi # returns 2-tuple def get_term_topics(self, word_id, minimum_probability=None): - """ - Args: - word_id (int): ID of the word to get topic probabilities for. - minimum_probability (float): Only include topic probabilities above this - value (None by default). If set to None, use 1e-8 to prevent including 0s. - Returns: - list: The most likely topics for the given word. Each topic is represented - as a tuple of `(topic_id, term_probability)`. + """Get the most relevant topics to the given word. + + Parameters + ---------- + word_id : int + The word for which the topic distribution will be computed. + minimum_probability : float, optional + Topics with an assigned probability below this threshold will be discarded. + + Returns + ------- + list of (int, float) + The relevant topics represented as pairs of their ID and their assigned probability, sorted + by relevance to the given word. + """ if minimum_probability is None: minimum_probability = self.minimum_probability @@ -1055,36 +1374,47 @@ def get_term_topics(self, word_id, minimum_probability=None): def diff(self, other, distance="kullback_leibler", num_words=100, n_ann_terms=10, diagonal=False, annotation=True, normed=True): - """ - Calculate difference topic2topic between two Lda models - `other` instances of `LdaMulticore` or `LdaModel` - `distance` is function that will be applied to calculate difference between any topic pair. - Available values: `kullback_leibler`, `hellinger`, `jaccard` and `jensen_shannon` - `num_words` is quantity of most relevant words that used if distance == `jaccard` (also used for annotation) - `n_ann_terms` is max quantity of words in intersection/symmetric difference between topics (used for annotation) - `diagonal` set to True if the difference is required only between the identical topic no.s - (returns diagonal of diff matrix) - `annotation` whether the intersection or difference of words between two topics should be returned - Returns a matrix Z with shape (m1.num_topics, m2.num_topics), - where Z[i][j] - difference between topic_i and topic_j - and matrix annotation (if True) with shape (m1.num_topics, m2.num_topics, 2, None), - where:: - - annotation[i][j] = [[`int_1`, `int_2`, ...], [`diff_1`, `diff_2`, ...]] and - `int_k` is word from intersection of `topic_i` and `topic_j` and - `diff_l` is word from symmetric difference of `topic_i` and `topic_j` - `normed` is a flag. If `true`, matrix Z will be normalized - - Example: - - >>> m1, m2 = LdaMulticore.load(path_1), LdaMulticore.load(path_2) + """Calculate the difference in topic distributions between two models: `self` and `other`. + + Parameters + ---------- + other : :class:`~gensim.models.ldamodel.LdaModel` + The model which will be compared against the current object. + distance : {'kullback_leibler', 'hellinger', 'jaccard', 'jensen_shannon'} + The distance metric to calculate the difference with. + num_words : int, optional + The number of most relevant words used if `distance == 'jaccard'`. Also used for annotating topics. + n_ann_terms : int, optional + Max number of words in intersection/symmetric difference between topics. Used for annotation. + diagonal : bool, optional + Whether we need the difference between identical topics (the diagonal of the difference matrix). + annotation : bool, optional + Whether the intersection or difference of words between two topics should be returned. + normed : bool, optional + Whether the matrix should be normalized or not. + + Returns + ------- + numpy.ndarray + A difference matrix. Each element corresponds to the difference between the two topics, + shape (`self.num_topics`, `other.num_topics`) + numpy.ndarray, optional + Annotation matrix where for each pair we include the word from the intersection of the two topics, + and the word from the symmetric difference of the two topics. Only included if `annotation == True`. + Shape (`self.num_topics`, `other_model.num_topics`, 2). + + Examples + -------- + Get the differences between each pair of topics inferred by two models + + >>> from gensim.models.ldamulticore import LdaMulticore + >>> from gensim.test.utils import datapath + >>> + >>> m1, m2 = LdaMulticore.load(datapath("lda_3_0_1_model")), LdaMulticore.load(datapath("ldamodel_python_3_5")) >>> mdiff, annotation = m1.diff(m2) - >>> print(mdiff) # get matrix with difference for each topic pair from `m1` and `m2` - >>> print(annotation) # get array with positive/negative words for each topic pair from `m1` and `m2` + >>> topic_diff = mdiff # get matrix with difference for each topic pair from `m1` and `m2` - Note: this ignores difference in model dtypes """ - distances = { "kullback_leibler": kullback_leibler, "hellinger": hellinger, @@ -1149,43 +1479,71 @@ def diff(self, other, distance="kullback_leibler", num_words=100, return z, annotation_terms def __getitem__(self, bow, eps=None): - """ - Args: - bow (list): Bag-of-words representation of a document. - eps (float): Ignore topics with probability below `eps`. + """Get the topic distribution for the given document. + + Wraps :meth:`~gensim.models.ldamodel.LdaModel.get_document_topics` to support an operator style call. + Uses the model's current state (set using constructor arguments) to fill in the additional arguments of the + wrapper method. + + Parameters + --------- + bow : list of (int, float) + The document in BOW format. + eps : float, optional + Topics with an assigned probability lower than this threshold will be discarded. + + Returns + ------- + list of (int, float) + Topic distribution for the given document. Each topic is represented as a pair of its ID and the probability + assigned to it. - Returns: - topic distribution for the given document `bow`, as a list of - `(topic_id, topic_probability)` 2-tuples. """ return self.get_document_topics(bow, eps, self.minimum_phi_value, self.per_word_topics) def save(self, fname, ignore=('state', 'dispatcher'), separately=None, *args, **kwargs): - """ - Save the model to file. + """Save the model to a file. Large internal arrays may be stored into separate files, with `fname` as prefix. - `separately` can be used to define which arrays should be stored in separate files. - - `ignore` parameter can be used to define which variables should be ignored, i.e. left - out from the pickled lda model. By default the internal `state` is ignored as it uses - its own serialisation not the one provided by `LdaModel`. The `state` and `dispatcher` - will be added to any ignore parameter defined. - - - Note: do not save as a compressed file if you intend to load the file back with `mmap`. - - Note: If you intend to use models across Python 2/3 versions there are a few things to + Notes + ----- + If you intend to use models across Python 2/3 versions there are a few things to keep in mind: 1. The pickled Python dictionaries will not work across Python versions - 2. The `save` method does not automatically save all np arrays using np, only - those ones that exceed `sep_limit` set in `gensim.utils.SaveLoad.save`. The main + 2. The `save` method does not automatically save all numpy arrays separately, only + those ones that exceed `sep_limit` set in :meth:`~gensim.utils.SaveLoad.save`. The main concern here is the `alpha` array if for instance using `alpha='auto'`. - Please refer to the wiki recipes section (goo.gl/qoje24) + Please refer to the `wiki recipes section + `_ for an example on how to work around these issues. + + See Also + -------- + :meth:`~gensim.models.ldamodel.LdaModel.load` + Load model. + + Parameters + ---------- + fname : str + Path to the system file where the model will be persisted. + ignore : tuple of str, optional + The named attributes in the tuple will be left out of the pickled model. The reason why + the internal `state` is ignored by default is that it uses its own serialisation rather than the one + provided by this method. + separately : {list of str, None}, optional + If None - automatically detect large numpy/scipy.sparse arrays in the object being stored, and store + them into separate files. This avoids pickle memory errors and allows `mmap`'ing large arrays + back on load efficiently. If list of str - this attributes will be stored in separate files, + the automatic check is not performed in this case. + *args + Positional arguments propagated to :meth:`~gensim.utils.SaveLoad.save`. + **kwargs + Key word arguments propagated to :meth:`~gensim.utils.SaveLoad.save`. + """ if self.state is not None: self.state.save(utils.smart_extension(fname, '.state'), *args, **kwargs) @@ -1226,12 +1584,30 @@ def save(self, fname, ignore=('state', 'dispatcher'), separately=None, *args, ** @classmethod def load(cls, fname, *args, **kwargs): - """ - Load a previously saved object from file (also see `save`). - + """Load a previously saved :class:`gensim.models.ldamodel.LdaModel` from file. + + See Also + -------- + :meth:`~gensim.models.ldamodel.LdaModel.save` + Save model. + + Parameters + ---------- + fname : str + Path to the file where the model is stored. + *args + Positional arguments propagated to :meth:`~gensim.utils.SaveLoad.load`. + **kwargs + Key word arguments propagated to :meth:`~gensim.utils.SaveLoad.load`. + + Examples + -------- Large arrays can be memmap'ed back as read-only (shared memory) by setting `mmap='r'`: - >>> LdaModel.load(fname, mmap='r') + >>> from gensim.test.utils import datapath + >>> + >>> fname = datapath("lda_3_0_1_model") + >>> lda = LdaModel.load(fname, mmap='r') """ kwargs['mmap'] = kwargs.get('mmap', None) diff --git a/gensim/models/ldamulticore.py b/gensim/models/ldamulticore.py index 2287b49584..d32a709f80 100644 --- a/gensim/models/ldamulticore.py +++ b/gensim/models/ldamulticore.py @@ -5,13 +5,11 @@ # Copyright (C) 2014 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -""" -Latent Dirichlet Allocation (LDA) in Python, using all CPU cores to parallelize and -speed up model training. +"""Online Latent Dirichlet Allocation (LDA) in Python, using all CPU cores to parallelize and speed up model training. -The parallelization uses multiprocessing; in case this doesn't work for you for -some reason, try the :class:`gensim.models.ldamodel.LdaModel` class which is an -equivalent, but more straightforward and single-core implementation. +The parallelization uses multiprocessing; in case this doesn't work for you for some reason, +try the :class:`gensim.models.ldamodel.LdaModel` class which is an equivalent, but more straightforward and single-core +implementation. The training algorithm: @@ -19,9 +17,8 @@ * runs in **constant memory** w.r.t. the number of documents: size of the training corpus does not affect memory footprint, can process corpora larger than RAM -Wall-clock `performance on the English Wikipedia `_ -(2G corpus positions, 3.5M documents, 100K features, 0.54G non-zero entries in the final -bag-of-words matrix), requesting 100 topics: +Wall-clock `performance on the English Wikipedia `_ (2G corpus positions, +3.5M documents, 100K features, 0.54G non-zero entries in the final bag-of-words matrix), requesting 100 topics: ====================================================== ============== @@ -37,14 +34,47 @@ (Measured on `this i7 server `_ with 4 physical cores, so that optimal `workers=3`, one less than the number of cores.) -This module allows both LDA model estimation from a training corpus and inference of topic -distribution on new, unseen documents. The model can also be updated with new documents -for online training. - -The core estimation code is based on the `onlineldavb.py` script by M. Hoffman [1]_, see -**Hoffman, Blei, Bach: Online Learning for Latent Dirichlet Allocation, NIPS 2010.** +This module allows both LDA model estimation from a training corpus and inference of topic distribution on new, +unseen documents. The model can also be updated with new documents for online training. + +The core estimation code is based on the `onlineldavb.py script +`_, by `Hoffman, Blei, Bach: +Online Learning for Latent Dirichlet Allocation, NIPS 2010 `_. + +Usage examples +-------------- +The constructor estimates Latent Dirichlet Allocation model parameters based on a training corpus + +>>> from gensim.test.utils import common_corpus, common_dictionary +>>> +>>> lda = LdaMulticore(common_corpus, id2word=common_dictionary, num_topics=10) + +Save a model to disk, or reload a pre-trained model + +>>> from gensim.test.utils import datapath +>>> +>>> # Save model to disk. +>>> temp_file = datapath("model") +>>> lda.save(temp_file) +>>> +>>> # Load a potentially pretrained model from disk. +>>> lda = LdaModel.load(temp_file) + +Query, or update the model using new, unseen documents + +>>> other_texts = [ +... ['computer', 'time', 'graph'], +... ['survey', 'response', 'eps'], +... ['human', 'system', 'computer'] +... ] +>>> other_corpus = [common_dictionary.doc2bow(text) for text in other_texts] +>>> +>>> unseen_doc = other_corpus[0] +>>> vector = lda[unseen_doc] # get topic probability distribution for a document +>>> +>>> # Update the model by incrementally training on the new corpus. +>>> lda.update(other_corpus) # update the LDA model with additional documents -.. [1] http://www.cs.princeton.edu/~mdhoffma """ import logging @@ -62,81 +92,77 @@ class LdaMulticore(LdaModel): - """ - The constructor estimates Latent Dirichlet Allocation model parameters based - on a training corpus: - - >>> lda = LdaMulticore(corpus, num_topics=10) - - You can then infer topic distributions on new, unseen documents, with - - >>> doc_lda = lda[doc_bow] - - The model can be updated (trained) with new documents via - - >>> lda.update(other_corpus) - - Model persistency is achieved through its `load`/`save` methods. + """An optimized implementation of the LDA algorithm, able to harness the power of multicore CPUs. + Follows the similar API as the parent class :class:`~gensim.models.ldamodel.LdaModel`. """ - def __init__(self, corpus=None, num_topics=100, id2word=None, workers=None, chunksize=2000, passes=1, batch=False, alpha='symmetric', eta=None, decay=0.5, offset=1.0, eval_every=10, iterations=50, gamma_threshold=0.001, random_state=None, minimum_probability=0.01, minimum_phi_value=0.01, per_word_topics=False, dtype=np.float32): """ - If given, start training from the iterable `corpus` straight away. If not given, - the model is left untrained (presumably because you want to call `update()` manually). - - `num_topics` is the number of requested latent topics to be extracted from - the training corpus. - - `id2word` is a mapping from word ids (integers) to words (strings). It is - used to determine the vocabulary size, as well as for debugging and topic - printing. - `workers` is the number of extra processes to use for parallelization. Uses - all available cores by default: `workers=cpu_count()-1`. **Note**: for - hyper-threaded CPUs, `cpu_count()` returns a useless number -- set `workers` - directly to the number of your **real** cores (not hyperthreads) minus one, - for optimal performance. - - If `batch` is not set, perform online training by updating the model once - every `workers * chunksize` documents (online training). Otherwise, - run batch LDA, updating model only once at the end of each full corpus pass. - - `alpha` and `eta` are hyperparameters that affect sparsity of the document-topic - (theta) and topic-word (lambda) distributions. Both default to a symmetric - 1.0/num_topics prior. - - `alpha` can be set to an explicit array = prior of your choice. It also - support special values of 'asymmetric' and 'auto': the former uses a fixed - normalized asymmetric 1.0/topicno prior, the latter learns an asymmetric - prior directly from your data. - - `eta` can be a scalar for a symmetric prior over topic/word - distributions, or a matrix of shape num_topics x num_words, - which can be used to impose asymmetric priors over the word - distribution on a per-topic basis. This may be useful if you - want to seed certain topics with particular words by boosting - the priors for those words. - - Calculate and log perplexity estimate from the latest mini-batch once every - `eval_every` documents. Set to `None` to disable perplexity estimation (faster), - or to `0` to only evaluate perplexity once, at the end of each corpus pass. - - `decay` and `offset` parameters are the same as Kappa and Tau_0 in - Hoffman et al, respectively. - - `random_state` can be a numpy.random.RandomState object or the seed for one - - Example: - - >>> lda = LdaMulticore(corpus, id2word=id2word, num_topics=100) # train model - >>> print(lda[doc_bow]) # get topic probability distribution for a document - >>> lda.update(corpus2) # update the LDA model with additional documents - >>> print(lda[doc_bow]) + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + If not given, the model is left untrained (presumably because you want to call + :meth:`~gensim.models.ldamodel.LdaModel.update` manually). + num_topics : int, optional + The number of requested latent topics to be extracted from the training corpus. + id2word : {dict of (int, str), :class:`gensim.corpora.dictionary.Dictionary`} + Mapping from word IDs to words. It is used to determine the vocabulary size, as well as for + debugging and topic printing. + workers : int, optional + Number of workers processes to be used for parallelization. If None all available cores + (as estimated by `workers=cpu_count()-1` will be used. **Note** however that for + hyper-threaded CPUs, this estimation returns a too high number -- set `workers` + directly to the number of your **real** cores (not hyperthreads) minus one, for optimal performance. + chunksize : int, optional + Number of documents to be used in each training chunk. + passes : int, optional + Number of passes through the corpus during training. + alpha : {np.ndarray, str}, optional + Can be set to an 1D array of length equal to the number of expected topics that expresses + our a-priori belief for the each topics' probability. + Alternatively default prior selecting strategies can be employed by supplying a string: + + * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. + * 'default': Learns an assymetric prior from the corpus. + eta : {float, np.array, str}, optional + A-priori belief on word probability, this can be: + + * scalar for a symmetric prior over topic/word probability, + * vector of length num_words to denote an asymmetric user defined probability for each word, + * matrix of shape (num_topics, num_words) to assign a probability for each word-topic combination, + * the string 'auto' to learn the asymmetric prior from the data. + decay : float, optional + A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten + when each new document is examined. Corresponds to Kappa from + `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + offset : float, optional + Hyper-parameter that controls how much we will slow down the first steps the first few iterations. + Corresponds to Tau_0 from `Matthew D. Hoffman, David M. Blei, Francis Bach: + "Online Learning for Latent Dirichlet Allocation NIPS'10" `_. + eval_every : int, optional + Log perplexity is estimated every that many updates. Setting this to one slows down training by ~2x. + iterations : int, optional + Maximum number of iterations through the corpus when inferring the topic distribution of a corpus. + gamma_threshold : float, optional + Minimum change in the value of the gamma parameters to continue iterating. + minimum_probability : float, optional + Topics with a probability lower than this threshold will be filtered out. + random_state : {np.random.RandomState, int}, optional + Either a randomState object or a seed to generate one. Useful for reproducibility. + minimum_phi_value : float, optional + if `per_word_topics` is True, this represents a lower bound on the term probabilities. + per_word_topics : bool + If True, the model also computes a list of topics, sorted in descending order of most likely topics for + each word, along with their phi values multiplied by the feature length (i.e. word count). + dtype : {numpy.float16, numpy.float32, numpy.float64}, optional + Data-type to use during calculations inside model. All inputs are also converted. """ self.workers = max(1, cpu_count() - 1) if workers is None else workers @@ -154,13 +180,15 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, workers=None, ) def update(self, corpus, chunks_as_numpy=False): - """ - Train the model with new documents, by EM-iterating over `corpus` until - the topics converge (or until the maximum number of allowed iterations - is reached). `corpus` must be an iterable (repeatable stream of documents), + """Train the model with new documents, by EM-iterating over `corpus` until the topics converge + (or until the maximum number of allowed iterations is reached). - The E-step is distributed into the several processes. + Train the model with new documents, by EM-iterating over the corpus until the topics converge, or until + the maximum number of allowed iterations is reached. `corpus` must be an iterable. The E step is distributed + into the several processes. + Notes + ----- This update also supports updating an already trained model (`self`) with new documents from `corpus`; the two models are then merged in proportion to the number of old vs. new documents. This feature is still @@ -170,6 +198,16 @@ def update(self, corpus, chunks_as_numpy=False): this equals the online update of Hoffman et al. and is guaranteed to converge for any `decay` in (0.5, 1.0>. + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`) used to update the + model. + chunks_as_numpy : bool + Whether each chunk passed to the inference step should be a np.ndarray or not. Numpy can in some settings + turn the term IDs into floats, these will be converted back into integers in inference, which incurs a + performance hit. For distributed computing it may be desirable to keep the chunks as `numpy.ndarray`. + """ try: lencorpus = len(corpus) @@ -275,9 +313,15 @@ def process_result_queue(force=False): def worker_e_step(input_queue, result_queue): - """ - Perform E-step for each (chunk_no, chunk, model) 3-tuple from the - input queue, placing the resulting state into the result queue. + """Perform E-step for each job. + + Parameters + ---------- + input_queue : queue of (int, list of (int, float), :class:`~gensim.models.lda_worker.Worker`) + Each element is a job characterized by its ID, the corpus chunk to be processed in BOW format and the worker + responsible for processing it. + result_queue : queue of :class:`~gensim.models.ldamodel.LdaState` + After the worker finished the job, the state of the resulting (trained) worker model is appended to this queue. """ logger.debug("worker process entering E-step loop") diff --git a/gensim/models/ldaseqmodel.py b/gensim/models/ldaseqmodel.py index 467ab47c6c..3baae7aeca 100644 --- a/gensim/models/ldaseqmodel.py +++ b/gensim/models/ldaseqmodel.py @@ -4,23 +4,46 @@ # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html # Based on Copyright (C) 2016 Radim Rehurek +"""Lda Sequence model, inspired by `David M. Blei, John D. Lafferty: "Dynamic Topic Models" +`_ . +The original C/C++ implementation can be found on `blei-lab/dtm `. -""" -Inspired by the Blei's original DTM code and paper. -Original DTM C/C++ code: https://github.com/blei-lab/dtm -DTM Paper: https://www.cs.princeton.edu/~blei/papers/BleiLafferty2006a.pdf +TODO: The next steps to take this forward would be: + +#. Include DIM mode. Most of the infrastructure for this is in place. +#. See if LdaPost can be replaced by LdaModel completely without breaking anything. +#. Heavy lifting going on in the Sslm class - efforts can be made to cythonise mathematical methods, in particular, + update_obs and the optimization takes a lot time. +#. Try and make it distributed, especially around the E and M step. +#. Remove all C/C++ coding style/syntax. + +Examples +-------- + +Set up a model using have 30 documents, with 5 in the first time-slice, 10 in the second, and 15 in the third + +>>> from gensim.test.utils import common_corpus +>>> from gensim.models import LdaSeqModel +>>> +>>> ldaseq = LdaSeqModel(corpus=common_corpus, time_slice=[2, 4, 3], num_topics=2, chunksize=1) +Persist a model to disk and reload it later -TODO: -The next steps to take this forward would be: +>>> from gensim.test.utils import datapath +>>> +>>> temp_file = datapath("model") +>>> ldaseq.save(temp_file) +>>> +>>> # Load a potentially pre-trained model from disk. +>>> ldaseq = LdaSeqModel.load(temp_file) + +Access the document embeddings generated from the DTM + +>>> doc = common_corpus[1] +>>> +>>> embedding = ldaseq[doc] - 1) Include DIM mode. Most of the infrastructure for this is in place. - 2) See if LdaPost can be replaced by LdaModel completely without breaking anything. - 3) Heavy lifting going on in the sslm class - efforts can be made to cythonise mathematical methods. - - in particular, update_obs and the optimization takes a lot time. - 4) Try and make it distributed, especially around the E and M step. - 5) Remove all C/C++ coding style/syntax. """ from gensim import utils, matutils @@ -30,52 +53,62 @@ from scipy import optimize import logging -logger = logging.getLogger('gensim.models.ldaseqmodel') +logger = logging.getLogger(__name__) class LdaSeqModel(utils.SaveLoad): - """ - The constructor estimates Dynamic Topic Model parameters based - on a training corpus. - If we have 30 documents, with 5 in the first time-slice, 10 in the second, and 15 in the third, we would - set up our model like this: - - >>> ldaseq = LdaSeqModel(corpus=corpus, time_slice= [5, 10, 15], num_topics=5) - - Model persistency is achieved through inheriting utils.SaveLoad. - - >>> ldaseq.save("ldaseq") - - saves the model to disk. - """ - + """Estimate Dynamic Topic Model parameters based on a training corpus.""" def __init__(self, corpus=None, time_slice=None, id2word=None, alphas=0.01, num_topics=10, initialize='gensim', sstats=None, lda_model=None, obs_variance=0.5, chain_variance=0.005, passes=10, random_state=None, lda_inference_max_iter=25, em_min_iter=6, em_max_iter=20, chunksize=100): """ - `corpus` is any iterable gensim corpus - - `time_slice` as described above is a list which contains the number of documents in each time-slice - - `id2word` is a mapping from word ids (integers) to words (strings). - It is used to determine the vocabulary size and printing topics. - - `alphas` is a prior of your choice and should be a double or float value. default is 0.01 - - `num_topics` is the number of requested latent topics to be extracted from the training corpus. - `initalize` allows the user to decide how he wants to initialise the DTM model. Default is through gensim LDA. - You can use your own sstats of an LDA model previously trained as well by specifying 'own' - and passing a np matrix through sstats. - If you wish to just pass a previously used LDA model, pass it through `lda_model` - Shape of sstats is (vocab_len, num_topics) + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + If not given, the model is left untrained (presumably because you want to call + :meth:`~gensim.models.ldamodel.LdaSeqModel.update` manually). + time_slice : list of int, optional + Number of documents in each time-slice. Each time slice could for example represent a year's published + papers, in case the corpus comes from a journal publishing over multiple years. + It is asummed that `sum(time_slice) == num_topics`. + id2word : dict of (int, str), optional + Mapping from word IDs to words. It is used to determine the vocabulary size, as well as for + debugging and topic printing. + alphas : float, optional + The prior probability for the model. + num_topics : int, optional + The number of requested latent topics to be extracted from the training corpus. + initialize : {'gensim', 'own', 'ldamodel'}, optional + Controls the initialization of the DTM model. Supports three different modes: + * 'gensim': Uses gensim's LDA initialization. + * 'own': Uses your own initialization matrix of an LDA model that has been previously trained. + * 'lda_model': Use a previously used LDA model, passing it through the `lda_model` argument. + sstats : numpy.ndarray , optional + Sufficient statistics used for initializing the model if `initialize == 'own'`. Corresponds to matrix + beta in the linked paper for time slice 0, expected shape (`self.vocab_len`, `num_topics`). + lda_model : :class:`~gensim.models.ldamodel.LdaModel` + Model whose sufficient statistics will be used to initialize the current object if `initialize == 'gensim'`. + obs_variance : float, optional + Observed variance used to approximate the true and forward variance as shown in + `David M. Blei, John D. Lafferty: "Dynamic Topic Models" + `_. + chain_variance : float, optional + Gaussian parameter defined in the beta distribution to dictate how the beta values evolve over time. + passes : int, optional + Number of passes over the corpus for the initial :class:`~gensim.models.ldamodel.LdaModel` + random_state : {numpy.random.RandomState, int}, optional + Can be a np.random.RandomState object, or the seed to generate one. Used for reproducibility of results. + lda_inference_max_iter : int, optional + Maximum number of iterations in the inference step of the LDA training. + em_min_iter : int, optional + Minimum number of iterations until converge of the Expectation-Maximization algorithm + em_max_iter : int, optional + Maximum number of iterations until converge of the Expectation-Maximization algorithm. + chunksize : int, optional + Number of documents in the corpus do be processed in in a chunk. - `chain_variance` is a constant which dictates how the beta values evolve - it is a gaussian parameter - defined in the beta distribution. - - `passes` is the number of passes of the initial LdaModel. - - `random_state` can be a np.random.RandomState object or the seed for one, for the LdaModel. """ self.id2word = id2word if corpus is None and self.id2word is None: @@ -152,8 +185,21 @@ def __init__(self, corpus=None, time_slice=None, id2word=None, alphas=0.01, num_ self.fit_lda_seq(corpus, lda_inference_max_iter, em_min_iter, em_max_iter, chunksize) def init_ldaseq_ss(self, topic_chain_variance, topic_obs_variance, alpha, init_suffstats): - """ - Method to initialize State Space Language Model, topic wise. + """Initialize State Space Language Model, topic-wise. + + Parameters + ---------- + topic_chain_variance : float + Gaussian parameter defined in the beta distribution to dictate how the beta values evolve. + topic_obs_variance : float + Observed variance used to approximate the true and forward variance as shown in + `David M. Blei, John D. Lafferty: "Dynamic Topic Models" + `_. + alpha : float + The prior probability for the model. + init_suffstats : numpy.ndarray + Sufficient statistics used for initializing the model, expected shape (`self.vocab_len`, `num_topics`). + """ self.alphas = alpha for k, chain in enumerate(self.topic_chains): @@ -166,16 +212,30 @@ def init_ldaseq_ss(self, topic_chain_variance, topic_obs_variance, alpha, init_s # ldaseq.topic_chains[k].w_phi_sq = np.zeros((ldaseq.vocab_len, ldaseq.num_time_slices)) def fit_lda_seq(self, corpus, lda_inference_max_iter, em_min_iter, em_max_iter, chunksize): - """ - fit an lda sequence model: - for each time period: - set up lda model with E[log p(w|z)] and \alpha - - for each document: - perform posterior inference - update sufficient statistics/likelihood - - maximize topics + """Fit a LDA Sequence model (DTM). + + This method will iteratively setup LDA models and perform EM steps until the sufficient statistics convergence, + or until the maximum number of iterations is reached. Because the true posterior is intractable, an + appropriately tight lower bound must be used instead. This function will optimize this bound, by minimizing + its true Kullback-Liebler Divergence with the true posterior. + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc} + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + lda_inference_max_iter : int + Maximum number of iterations for the inference step of LDA. + em_min_iter : int + Minimum number of time slices to be inspected. + em_max_iter : int + Maximum number of time slices to be inspected. + chunksize : int + Number of documents to be processed in each chunk. + + Returns + ------- + float + The highest lower bound for the true posterior produced after all iterations. """ LDASQE_EM_THRESHOLD = 1e-4 @@ -243,10 +303,37 @@ def fit_lda_seq(self, corpus, lda_inference_max_iter, em_min_iter, em_max_iter, def lda_seq_infer(self, corpus, topic_suffstats, gammas, lhoods, iter_, lda_inference_max_iter, chunksize): - """ - Inference or E- Step. - This is used to set up the gensim LdaModel to be used for each time-slice. + """Inference (or E-step) for the lower bound EM optimization. + + This is used to set up the gensim :class:`~gensim.models.ldamodel.LdaModel` to be used for each time-slice. It also allows for Document Influence Model code to be written in. + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc} + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + topic_suffstats : numpy.ndarray + Sufficient statistics for time slice 0, used for initializing the model if `initialize == 'own'`, + expected shape (`self.vocab_len`, `num_topics`). + gammas : numpy.ndarray + Topic weight variational parameters for each document. If not supplied, it will be inferred from the model. + lhoods : list of float + The total log probability lower bound for each topic. Corresponds to the phi variational parameters in the + linked paper. + iter_ : int + Current iteration. + lda_inference_max_iter : int + Maximum number of iterations for the inference step of LDA. + chunksize : int + Number of documents to be processed in each chunk. + + Returns + ------- + (float, list of float) + The first value is the highest lower bound for the true posterior. + The second value is the list of optimized dirichlet variational parameters for the approximation of + the posterior. + """ num_topics = self.num_topics vocab_len = self.vocab_len @@ -273,10 +360,39 @@ def lda_seq_infer(self, corpus, topic_suffstats, gammas, lhoods, def inferDTMseq(self, corpus, topic_suffstats, gammas, lhoods, lda, ldapost, iter_, bound, lda_inference_max_iter, chunksize): - """ - Computes the likelihood of a sequential corpus under an LDA seq model, and return the likelihood bound. - Need to pass the LdaSeq model, corpus, sufficient stats, gammas and lhoods matrices previously created, - and LdaModel and LdaPost class objects. + """Compute the likelihood of a sequential corpus under an LDA seq model, and reports the likelihood bound. + + Parameters + ---------- + corpus : {iterable of list of (int, float), scipy.sparse.csc} + Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`). + topic_suffstats : numpy.ndarray + Sufficient statistics of the current model, expected shape (`self.vocab_len`, `num_topics`). + gammas : numpy.ndarray + Topic weight variational parameters for each document. If not supplied, it will be inferred from the model. + lhoods : list of float of length `self.num_topics` + The total log probability bound for each topic. Corresponds to phi from the linked paper. + lda : :class:`~gensim.models.ldamodel.LdaModel` + The trained LDA model of the previous iteration. + ldapost : :class:`~gensim.models.ldaseqmodel.LdaPost` + Posterior probability variables for the given LDA model. This will be used as the true (but intractable) + posterior. + iter_ : int + The current iteration. + bound : float + The LDA bound produced after all iterations. + lda_inference_max_iter : int + Maximum number of iterations for the inference step of LDA. + chunksize : int + Number of documents to be processed in each chunk. + + Returns + ------- + (float, list of float) + The first value is the highest lower bound for the true posterior. + The second value is the list of optimized dirichlet variational parameters for the approximation of + the posterior. + """ doc_index = 0 # overall doc_index in corpus time = 0 # current time-slice @@ -322,8 +438,21 @@ def inferDTMseq(self, corpus, topic_suffstats, gammas, lhoods, lda, return bound, gammas def make_lda_seq_slice(self, lda, time): - """ - set up the LDA model topic-word values with that of ldaseq. + """Update the LDA model topic-word values using time slices. + + Parameters + ---------- + + lda : :class:`~gensim.models.ldamodel.LdaModel` + The stationary model to be updated + time : int + The time slice assigned to the stationary model. + + Returns + ------- + lda : :class:`~gensim.models.ldamodel.LdaModel` + The stationary model updated to reflect the passed time slice. + """ for k in range(0, self.num_topics): lda.topics[:, k] = np.copy(self.topic_chains[k].e_log_prob[:, time]) @@ -332,8 +461,18 @@ def make_lda_seq_slice(self, lda, time): return lda def fit_lda_seq_topics(self, topic_suffstats): - """ - Fit lda sequence topic wise. + """Fit the sequential model topic-wise. + + Parameters + ---------- + topic_suffstats : numpy.ndarray + Sufficient statistics of the current model, expected shape (`self.vocab_len`, `num_topics`). + + Returns + ------- + float + The sum of the optimized lower bounds for all topics. + """ lhood = 0 @@ -345,8 +484,21 @@ def fit_lda_seq_topics(self, topic_suffstats): return lhood def print_topic_times(self, topic, top_terms=20): - """ - Prints one topic showing each time-slice. + """Get the most relevant words for a topic, for each timeslice. This can be used to inspect the evolution of a + topic through time. + + Parameters + ---------- + topic : int + The index of the topic. + top_terms : int, optional + Number of most relevant words associated with the topic to be returned. + + Returns + ------- + list of list of str + Top `top_terms` relevant terms for the topic for each time slice. + """ topics = [] for time in range(0, self.num_time_slices): @@ -355,19 +507,44 @@ def print_topic_times(self, topic, top_terms=20): return topics def print_topics(self, time=0, top_terms=20): + """Get the most relevant words for every topic. + + Parameters + ---------- + time : int, optional + The time slice in which we are interested in (since topics evolve over time, it is expected that the most + relevant words will also gradually change). + top_terms : int, optional + Number of most relevant words to be returned for each topic. + + Returns + ------- + list of list of (str, float) + Representation of all topics. Each of them is represented by a list of pairs of words and their assigned + probability. + """ - Prints all topics in a particular time-slice. - """ - topics = [] - for topic in range(0, self.num_topics): - topics.append(self.print_topic(topic, time, top_terms)) - return topics + return [self.print_topic(topic, time, top_terms) for topic in range(0, self.num_topics)] def print_topic(self, topic, time=0, top_terms=20): - """ - Topic is the topic number - Time is for a particular time_slice - top_terms is the number of terms to display + """Get the list of words most relevant to the given topic. + + Parameters + ---------- + topic : int + The index of the topic to be inspected. + time : int, optional + The time slice in which we are interested in (since topics evolve over time, it is expected that the most + relevant words will also gradually change). + top_terms : int, optional + Number of words associated with the topic to be returned. + + Returns + ------- + list of (str, float) + The representation of this topic. Each element in the list includes the word itself, along with the + probability assigned to it by the topic. + """ topic = self.topic_chains[topic].e_log_prob topic = np.transpose(topic) @@ -378,20 +555,52 @@ def print_topic(self, topic, time=0, top_terms=20): return beststr def doc_topics(self, doc_number): - """ - On passing the LdaSeqModel trained ldaseq object, the doc_number of your document in the corpus, - it returns the doc-topic probabilities of that document. + """Get the topic mixture for a document. + + Uses the priors for the dirichlet distribution that approximates the true posterior with the optimal + lower bound, and therefore requires the model to be already trained. + + + Parameters + ---------- + doc_number : int + Index of the document for which the mixture is returned. + + Returns + ------- + list of length `self.num_topics` + Probability for each topic in the mixture (essentially a point in the `self.num_topics - 1` simplex. + """ doc_topic = np.copy(self.gammas) doc_topic /= doc_topic.sum(axis=1)[:, np.newaxis] return doc_topic[doc_number] def dtm_vis(self, time, corpus): - """ - returns term_frequency, vocab, doc_lengths, topic-term distributions and doc_topic distributions, - specified by pyLDAvis format. - all of these are needed to visualise topics for DTM for a particular time-slice via pyLDAvis. - input parameter is the year to do the visualisation. + """Get the information needed to visualize the corpus model at a given time slice, using the pyLDAvis format. + + Parameters + ---------- + time : int + The time slice we are interested in. + corpus : {iterable of list of (int, float), scipy.sparse.csc}, optional + The corpus we want to visualize at the given time slice. + + Returns + ------- + doc_topics : list of length `self.num_topics` + Probability for each topic in the mixture (essentially a point in the `self.num_topics - 1` simplex. + topic_term : numpy.ndarray + The representation of each topic as a multinomial over words in the vocabulary, + expected shape (`num_topics`, vocabulary length). + doc_lengths : list of int + The number of words in each document. These could be fixed, or drawn from a Poisson distribution. + term_frequency : numpy.ndarray + The term frequency matrix (denoted as beta in the original Blei paper). This could also be the TF-IDF + representation of the corpus, expected shape (number of documents, length of vocabulary). + vocab : list of str + The set of unique terms existing in the cropuse's vocabulary. + """ doc_topic = np.copy(self.gammas) doc_topic /= doc_topic.sum(axis=1)[:, np.newaxis] @@ -409,14 +618,26 @@ def dtm_vis(self, time, corpus): term_frequency[pair[0]] += pair[1] vocab = [self.id2word[i] for i in range(0, len(self.id2word))] - # returns np arrays for doc_topic proportions, topic_term proportions, and document_lengths, term_frequency. - # these should be passed to the `pyLDAvis.prepare` method to visualise one time-slice of DTM topics. + return doc_topic, np.array(topic_term), doc_lengths, term_frequency, vocab def dtm_coherence(self, time): - """ - returns all topics of a particular time-slice without probabilitiy values for it to be used - for either "u_mass" or "c_v" coherence. + """Get the coherence for each topic. + + Can be used to measure the quality of the model, or to inspect the convergence through training via a callback. + + Parameters + ---------- + time : int + The time slice. + + Returns + ------- + list of list of str + The word representation for each topic, for each time slice. This can be used to check the time coherence + of topics as time evolves: If the most relevant words remain the same then the topic has somehow + converged or is relatively static, if they change rapidly the topic is evolving. + """ coherence_topics = [] for topics in self.print_topics(time): @@ -428,8 +649,18 @@ def dtm_coherence(self, time): return coherence_topics def __getitem__(self, doc): - """ - Similar to the LdaModel __getitem__ function, it returns topic proportions of a document passed. + """Get the topic mixture for the given document, using the inferred approximation of the true posterior. + + Parameters + ---------- + doc : list of (int, float) + The doc in BOW format. Can be an unseen document. + + Returns + ------- + list of float + Probabilities for each topic in the mixture. This is essentially a point in the `num_topics - 1` simplex. + """ lda_model = \ ldamodel.LdaModel(num_topics=self.num_topics, alpha=self.alphas, id2word=self.id2word, dtype=np.float64) @@ -448,14 +679,17 @@ def __getitem__(self, doc): class sslm(utils.SaveLoad): - """ - The sslm class is the State Space Language Model for DTM and contains the following information: - `obs` values contain the doc - topic ratios - `e_log_prob` contains topic - word ratios - `mean`, `fwd_mean` contains the mean values to be used for inference for each word for a time_slice - `variance`, `fwd_variance` contains the variance values to be used for inference for each word in a time_slice - `fwd_mean`, `fwd_variance` are the forward posterior values. - `zeta` is an extra variational parameter with a value for each time-slice + """Encapsulate the inner State Space Language Model for DTM. + + Some important attributes of this class: + + * `obs` is a matrix containing the document to topic ratios. + * `e_log_prob` is a matrix containing the topic to word ratios. + * `mean` contains the mean values to be used for inference for each word for a time slice. + * `variance` contains the variance values to be used for inference of word in a time slice. + * `fwd_mean` and`fwd_variance` are the forward posterior values for the mean and the variance. + * `zeta` is an extra variational parameter with a value for each time slice. + """ def __init__(self, vocab_len=None, num_time_slices=None, num_topics=None, obs_variance=0.5, chain_variance=0.005): @@ -485,36 +719,57 @@ def __init__(self, vocab_len=None, num_time_slices=None, num_topics=None, obs_va self.m_update_coeff_g = None def update_zeta(self): - """ - Updates the Zeta Variational Parameter. - Zeta is described in the appendix and is equal - to sum (exp(mean[word] + Variance[word] / 2)), over every time-slice. - It is the value of variational parameter zeta which maximizes the lower bound. + """Update the Zeta variational parameter. + + Zeta is described in the appendix and is equal to sum (exp(mean[word] + Variance[word] / 2)), + over every time-slice. It is the value of variational parameter zeta which maximizes the lower bound. + + Returns + ------- + list of float + The updated zeta values for each time slice. + """ for j, val in enumerate(self.zeta): self.zeta[j] = np.sum(np.exp(self.mean[:, j + 1] + self.variance[:, j + 1] / 2)) return self.zeta def compute_post_variance(self, word, chain_variance): - """ - Based on the Variational Kalman Filtering approach for Approximate Inference - [https://www.cs.princeton.edu/~blei/papers/BleiLafferty2006a.pdf] + """Get the variance, based on the `Variational Kalman Filtering approach for Approximate Inference (section 3.1) + `_. + This function accepts the word to compute variance for, along with the associated sslm class object, - and returns variance and fwd_variance - Computes Var[\beta_{t,w}] for t = 1:T + and returns the `variance` and the posterior approximation `fwd_variance`. - :math:: + Notes + ----- + This function essentially computes Var[\beta_{t,w}] for t = 1:T + + .. :math:: fwd\_variance[t] \equiv E((beta_{t,w}-mean_{t,w})^2 |beta_{t}\ for\ 1:t) = - (obs\_variance / fwd\_variance[t - 1] + chain\_variance + obs\_variance ) * - (fwd\_variance[t - 1] + obs\_variance) + (obs\_variance / fwd\_variance[t - 1] + chain\_variance + obs\_variance ) * + (fwd\_variance[t - 1] + obs\_variance) - :math:: + .. :math:: variance[t] \equiv E((beta_{t,w}-mean\_cap_{t,w})^2 |beta\_cap_{t}\ for\ 1:t) = fwd\_variance[t - 1] + (fwd\_variance[t - 1] / fwd\_variance[t - 1] + obs\_variance)^2 * (variance[t - 1] - (fwd\_variance[t-1] + obs\_variance)) + Parameters + ---------- + word: int + The word's ID. + chain_variance : float + Gaussian parameter defined in the beta distribution to dictate how the beta values evolve over time. + + Returns + ------- + (numpy.ndarray, numpy.ndarray) + The first returned value is the variance of each word in each time slice, the second value is the + inferred posterior variance for the same pairs. + """ INIT_VARIANCE_CONST = 1000 @@ -542,20 +797,37 @@ def compute_post_variance(self, word, chain_variance): return variance, fwd_variance def compute_post_mean(self, word, chain_variance): - """ - Based on the Variational Kalman Filtering approach for Approximate Inference - [https://www.cs.princeton.edu/~blei/papers/BleiLafferty2006a.pdf] - This function accepts the word to compute mean for, along with the associated sslm class object, - and returns mean and fwd_mean - Essentially a forward-backward to compute E[\beta_{t,w}] for t = 1:T. + """Get the mean, based on the `Variational Kalman Filtering approach for Approximate Inference (section 3.1) + `_. + + Notes + ----- + This function essentially computes E[\beta_{t,w}] for t = 1:T. + + .. :math:: + + Fwd_Mean(t) ≡ E(beta_{t,w} | beta_ˆ 1:t ) + = (obs_variance / fwd_variance[t - 1] + chain_variance + obs_variance ) * fwd_mean[t - 1] + + (1 - (obs_variance / fwd_variance[t - 1] + chain_variance + obs_variance)) * beta - Fwd_Mean(t) ≡ E(beta_{t,w} | beta_ˆ 1:t ) - = (obs_variance / fwd_variance[t - 1] + chain_variance + obs_variance ) * fwd_mean[t - 1] + - (1 - (obs_variance / fwd_variance[t - 1] + chain_variance + obs_variance)) * beta + .. :math:: - Mean(t) ≡ E(beta_{t,w} | beta_ˆ 1:T ) - = fwd_mean[t - 1] + (obs_variance / fwd_variance[t - 1] + obs_variance) + - (1 - obs_variance / fwd_variance[t - 1] + obs_variance)) * mean[t] + Mean(t) ≡ E(beta_{t,w} | beta_ˆ 1:T ) + = fwd_mean[t - 1] + (obs_variance / fwd_variance[t - 1] + obs_variance) + + (1 - obs_variance / fwd_variance[t - 1] + obs_variance)) * mean[t] + + Parameters + ---------- + word: int + The word's ID. + chain_variance : float + Gaussian parameter defined in the beta distribution to dictate how the beta values evolve over time. + + Returns + ------- + (numpy.ndarray, numpy.ndarray) + The first returned value is the mean of each word in each time slice, the second value is the + inferred posterior mean for the same pairs. """ T = self.num_time_slices @@ -581,21 +853,38 @@ def compute_post_mean(self, word, chain_variance): return mean, fwd_mean def compute_expected_log_prob(self): - """ - Compute the expected log probability given values of m. + """Compute the expected log probability given values of m. + The appendix describes the Expectation of log-probabilities in equation 5 of the DTM paper; - The below implementation is the result of solving the equation and is as implemented - in the original Blei DTM code. + The below implementation is the result of solving the equation and is implemented as in the original + Blei DTM code. + + Returns + ------- + numpy.ndarray of float + The expected value for the log probabilities for each word and time slice. + """ for (w, t), val in np.ndenumerate(self.e_log_prob): self.e_log_prob[w][t] = self.mean[w][t + 1] - np.log(self.zeta[t]) return self.e_log_prob def sslm_counts_init(self, obs_variance, chain_variance, sstats): - """ - Initialize State Space Language Model with LDA sufficient statistics. - Called for each topic-chain and initializes intial mean, variance and Topic-Word probabilities + """Initialize the State Space Language Model with LDA sufficient statistics. + + Called for each topic-chain and initializes initial mean, variance and Topic-Word probabilities for the first time-slice. + + Parameters + ---------- + obs_variance : float, optional + Observed variance used to approximate the true and forward variance. + chain_variance : float + Gaussian parameter defined in the beta distribution to dictate how the beta values evolve over time. + sstats : numpy.ndarray + Sufficient statistics of the LDA model. Corresponds to matrix beta in the linked paper for time slice 0, + expected shape (`self.vocab_len`, `num_topics`). + """ W = self.vocab_len T = self.num_time_slices @@ -621,11 +910,24 @@ def sslm_counts_init(self, obs_variance, chain_variance, sstats): self.e_log_prob = self.compute_expected_log_prob() def fit_sslm(self, sstats): - """ - Fits variational distribution. + """Fits variational distribution. + This is essentially the m-step. - Accepts the sstats for a particular topic for input and maximizes values for that topic. - Updates the values in the update_obs() and compute_expected_log_prob methods. + Maximizes the approximation of the true posterior for a particular topic using the provided sufficient + statistics. Updates the values using :meth:`~gensim.models.ldaseqmodel.sslm.update_obs` and + :meth:`~gensim.models.ldaseqmodel.sslm.compute_expected_log_prob`. + + Parameters + ---------- + sstats : numpy.ndarray + Sufficient statistics for a particular topic. Corresponds to matrix beta in the linked paper for the + current time slice, expected shape (`self.vocab_len`, `num_topics`). + + Returns + ------- + float + The lower bound for the true posterior achieved using the fitted approximate distribution. + """ W = self.vocab_len bound = 0 @@ -667,9 +969,23 @@ def fit_sslm(self, sstats): return bound def compute_bound(self, sstats, totals): - """ - Compute log probability bound. - Forumula is as described in appendix of DTM by Blei. (formula no. 5) + """Compute the maximized lower bound achieved for the log probability of the true posterior. + + Uses the formula presented in the appendix of the DTM paper (formula no. 5). + + Parameters + ---------- + sstats : numpy.ndarray + Sufficient statistics for a particular topic. Corresponds to matrix beta in the linked paper for the first + time slice, expected shape (`self.vocab_len`, `num_topics`). + totals : list of int of length `len(self.time_slice)` + The totals for each time slice. + + Returns + ------- + float + The maximized lower bound. + """ w = self.vocab_len t = self.num_time_slices @@ -703,7 +1019,7 @@ def compute_bound(self, sstats, totals): v = self.variance[w][t] - # w_phi_l is only used in Document Influence Model; the values are aleays zero in this case + # w_phi_l is only used in Document Influence Model; the values are always zero in this case # w_phi_l = sslm.w_phi_l[w][t - 1] # exp_i = np.exp(-prev_m) # term_1 += (np.power(m - prev_m - (w_phi_l * exp_i), 2) / (2 * chain_variance)) - @@ -720,12 +1036,25 @@ def compute_bound(self, sstats, totals): return val def update_obs(self, sstats, totals): - """ - Function to perform optimization of obs. Parameters are suff_stats set up in the fit_sslm method. + """Optimize the bound with respect to the observed variables. TODO: This is by far the slowest function in the whole algorithm. Replacing or improving the performance of this would greatly speed things up. + + Parameters + ---------- + sstats : numpy.ndarray + Sufficient statistics for a particular topic. Corresponds to matrix beta in the linked paper for the first + time slice, expected shape (`self.vocab_len`, `num_topics`). + totals : list of int of length `len(self.time_slice)` + The totals for each time slice. + + Returns + ------- + (numpy.ndarray of float, numpy.ndarray of float) + The updated optimized values for obs and the zeta variational parameter. + """ OBS_NORM_CUTOFF = 2 @@ -785,10 +1114,28 @@ def update_obs(self, sstats, totals): return self.obs, self.zeta def compute_mean_deriv(self, word, time, deriv): - """ - Used in helping find the optimum function. - computes derivative of E[\beta_{t,w}]/d obs_{s,w} for t = 1:T. - put the result in deriv, allocated T+1 vector + """Helper functions for optimizing a function. + + Compute the derivative of: + + .. :math:: + + E[\beta_{t,w}]/d obs_{s,w} for t = 1:T. + + Parameters + ---------- + word : int + The word's ID. + time : int + The time slice. + deriv : list of float + Derivative for each time slice. + + Returns + ------- + list of float + Mean derivative for each time slice. + """ T = self.num_time_slices @@ -817,8 +1164,26 @@ def compute_mean_deriv(self, word, time, deriv): return deriv def compute_obs_deriv(self, word, word_counts, totals, mean_deriv_mtx, deriv): - """ - Derivation of obs which is used in derivative function [df_obs] while optimizing. + """Derivation of obs which is used in derivative function `df_obs` while optimizing. + + Parameters + ---------- + word : int + The word's ID. + word_counts : list of int + Total word counts for each time slice. + totals : list of int of length `len(self.time_slice)` + The totals for each time slice. + mean_deriv_mtx : list of float + Mean derivative for each time slice. + deriv : list of float + Mean derivative for each time slice. + + Returns + ------- + list of float + Mean derivative for each time slice. + """ # flag @@ -869,19 +1234,36 @@ def compute_obs_deriv(self, word, word_counts, totals, mean_deriv_mtx, deriv): deriv[t] = term1 + term2 + term3 + term4 return deriv -# endclass sslm class LdaPost(utils.SaveLoad): + """Posterior values associated with each set of documents. - """ - Posterior values associated with each set of documents. TODO: use **Hoffman, Blei, Bach: Online Learning for Latent Dirichlet Allocation, NIPS 2010.** to update phi, gamma. End game would be to somehow replace LdaPost entirely with LdaModel. + """ def __init__(self, doc=None, lda=None, max_doc_len=None, num_topics=None, gamma=None, lhood=None): + """Initialize the posterior value structure for the given LDA model. + + Parameters + ---------- + doc : list of (int, int) + A BOW representation of the document. Each element in the list is a pair of a word's ID and its number + of occurences in the document. + lda : :class:`~gensim.models.ldamodel.LdaModel`, optional + The underlying LDA model. + max_doc_len : int, optional + The maximum number of words in a document. + num_topics : int, optional + Number of topics discovered by the LDA model. + gamma : numpy.ndarray, optional + Topic weight variational parameters for each document. If not supplied, it will be inferred from the model. + lhood : float, optional + The log likelihood lower bound. + """ self.doc = doc self.lda = lda self.gamma = gamma @@ -901,13 +1283,26 @@ def __init__(self, doc=None, lda=None, max_doc_len=None, num_topics=None, gamma= self.renormalized_doc_weight = None def update_phi(self, doc_number, time): - """ - Update variational multinomial parameters, based on a document and a time-slice. + """Update variational multinomial parameters, based on a document and a time-slice. + This is done based on the original Blei-LDA paper, where: log_phi := beta * exp(Ψ(gamma)), over every topic for every word. TODO: incorporate lee-sueng trick used in **Lee, Seung: Algorithms for non-negative matrix factorization, NIPS 2001**. + + Parameters + ---------- + doc_number : int + Document number. Unused. + time : int + Time slice. Unused. + + Returns + ------- + (list of float, list of float) + Multinomial parameters, and their logarithm, for each word in the document. + """ num_topics = self.lda.num_topics # digamma values @@ -939,9 +1334,16 @@ def update_phi(self, doc_number, time): return self.phi, self.log_phi def update_gamma(self): - """ - update variational dirichlet parameters as described in the original Blei LDA paper: + """Update variational dirichlet parameters. + + This operations is described in the original Blei LDA paper: gamma = alpha + sum(phi), over every topic for every word. + + Returns + ------- + list of float + The updated gamma parameters for each word in the document. + """ self.gamma = np.copy(self.lda.alpha) n = 0 # keep track of number of iterations for phi, log_phi @@ -954,9 +1356,7 @@ def update_gamma(self): return self.gamma def init_lda_post(self): - """ - Initialize variational posterior, does not return anything. - """ + """Initialize variational posterior. """ total = sum(count for word_id, count in self.doc) self.gamma.fill(self.lda.alpha[0] + float(total) / self.lda.num_topics) self.phi[:len(self.doc), :] = 1.0 / self.lda.num_topics @@ -964,8 +1364,13 @@ def init_lda_post(self): # ldapost.doc_weight = None def compute_lda_lhood(self): - """ - compute the likelihood bound + """Compute the log likelihood bound. + + Returns + ------- + float + The optimal lower bound for the true posterior using the approximate distribution. + """ num_topics = self.lda.num_topics gamma_sum = np.sum(self.gamma) @@ -1008,9 +1413,33 @@ def compute_lda_lhood(self): def fit_lda_post(self, doc_number, time, ldaseq, LDA_INFERENCE_CONVERGED=1e-8, lda_inference_max_iter=25, g=None, g3_matrix=None, g4_matrix=None, g5_matrix=None): - """ - Posterior inference for lda. - g, g3, g4 and g5 are matrices used in Document Influence Model and not used currently. + """Posterior inference for lda. + + Parameters + ---------- + doc_number : int + The documents number. + time : int + Time slice. + ldaseq : object + Unused. + LDA_INFERENCE_CONVERGED : float + Epsilon value used to check whether the inference step has sufficiently converged. + lda_inference_max_iter : int + Maximum number of iterations in the inference step. + g : object + Unused. Will be useful when the DIM model is implemented. + g3_matrix: object + Unused. Will be useful when the DIM model is implemented. + g4_matrix: object + Unused. Will be useful when the DIM model is implemented. + g5_matrix: object + Unused. Will be useful when the DIM model is implemented. + + Returns + ------- + float + The optimal lower bound for the true posterior using the approximate distribution. """ self.init_lda_post() @@ -1060,9 +1489,26 @@ def fit_lda_post(self, doc_number, time, ldaseq, LDA_INFERENCE_CONVERGED=1e-8, return lhood def update_lda_seq_ss(self, time, doc, topic_suffstats): - """ - Update lda sequence sufficient statistics from an lda posterior. - This is very similar to the update_gamma method and uses the same formula. + """Update lda sequence sufficient statistics from an lda posterior. + + This is very similar to the :meth:`~gensim.models.ldaseqmodel.LdaPost.update_gamma` method and uses + the same formula. + + Parameters + ---------- + time : int + The time slice. + doc : list of (int, float) + Unused but kept here for backwards compatibility. The document set in the constructor (`self.doc`) is used + instead. + topic_suffstats : list of float + Sufficient statistics for each topic. + + Returns + ------- + list of float + The updated sufficient statistics for each topic. + """ num_topics = self.lda.num_topics @@ -1077,10 +1523,32 @@ def update_lda_seq_ss(self, time, doc, topic_suffstats): return topic_suffstats -# the following functions are used in update_obs as the function to optimize +# the following functions are used in update_obs as the objective function. def f_obs(x, *args): - """ - Function which we are optimising for minimizing obs. + """Function which we are optimising for minimizing obs. + + Parameters + ---------- + x : list of float + The obs values for this word. + sslm : :class:`~gensim.models.ldaseqmodel.sslm` + The State Space Language Model for DTM. + word_counts : list of int + Total word counts for each time slice. + totals : list of int of length `len(self.time_slice)` + The totals for each time slice. + mean_deriv_mtx : list of float + Mean derivative for each time slice. + word : int + The word's ID. + deriv : list of float + Mean derivative for each time slice. + + Returns + ------- + list of float + The value of the objective function evaluated at point `x`. + """ sslm, word_counts, totals, mean_deriv_mtx, word, deriv = args # flag @@ -1131,8 +1599,30 @@ def f_obs(x, *args): def df_obs(x, *args): - """ - Derivative of function which optimises obs. + """Derivative of the objective function which optimises obs. + + Parameters + ---------- + x : list of float + The obs values for this word. + sslm : :class:`~gensim.models.ldaseqmodel.sslm` + The State Space Language Model for DTM. + word_counts : list of int + Total word counts for each time slice. + totals : list of int of length `len(self.time_slice)` + The totals for each time slice. + mean_deriv_mtx : list of float + Mean derivative for each time slice. + word : int + The word's ID. + deriv : list of float + Mean derivative for each time slice. + + Returns + ------- + list of float + The derivative of the objective function evaluated at point `x`. + """ sslm, word_counts, totals, mean_deriv_mtx, word, deriv = args diff --git a/gensim/models/lsimodel.py b/gensim/models/lsimodel.py index d17563af06..054cb3aa5b 100644 --- a/gensim/models/lsimodel.py +++ b/gensim/models/lsimodel.py @@ -113,7 +113,7 @@ def asfarray(a, name=''): a : numpy.ndarray Input array. name : str, optional - Array name, used for logging purposes. + Array name, used only for logging purposes. Returns ------- @@ -150,7 +150,7 @@ def ascarray(a, name=''): class Projection(utils.SaveLoad): - """Lower dimension projections of a Term-Passage matrix. + """Low dimensional projection of a term-document matrix. This is the class taking care of the 'core math': interfacing with corpora, splitting large corpora into chunks and merging them etc. This done through the higher-level :class:`~gensim.models.lsimodel.LsiModel` class. @@ -158,7 +158,7 @@ class Projection(utils.SaveLoad): Notes ----- The projection can be later updated by merging it with another :class:`~gensim.models.lsimodel.Projection` - via :meth:`~gensim.models.lsimodel.Projection.merge`. + via :meth:`~gensim.models.lsimodel.Projection.merge`. This is how incremental training actually happens. """ def __init__(self, m, k, docs=None, use_svdlibc=False, power_iters=P2_EXTRA_ITERS, @@ -321,7 +321,7 @@ class LsiModel(interfaces.TransformationABC, basemodel.BaseTopicModel): """Model for `Latent Semantic Indexing `_. - Algorithm of decomposition described in `"Fast and Faster: A Comparison of Two Streamed + The decomposition algorithm is described in `"Fast and Faster: A Comparison of Two Streamed Matrix Decomposition Algorithms" `_. Notes @@ -616,7 +616,7 @@ def get_topics(self): Notes ----- The number of topics can actually be smaller than `self.num_topics`, if there were not enough factors - (real rank of input matrix smaller than `self.num_topics`). + in the matrix (real rank of input matrix smaller than `self.num_topics`). Returns ------- @@ -636,8 +636,10 @@ def get_topics(self): def show_topic(self, topicno, topn=10): """Get the words that define a topic along with their contribution. - This is actually the left singular vector of the specified topic. The most important words in defining the topic - (in both directions) are included in the string, along with their contribution to the topic. + This is actually the left singular vector of the specified topic. + + The most important words in defining the topic (greatest absolute value) are included + in the output, along with their contribution to the topic. Parameters ---------- @@ -758,7 +760,7 @@ def load(cls, fname, *args, **kwargs): Notes ----- - Large arrays can be memmap'ed back as read-only (shared memory) by setting `mmap='r'`: + Large arrays can be memmap'ed back as read-only (shared memory) by setting the `mmap='r'` parameter. Parameters ---------- From 309da79584440b0ca87130393f8f85a261b38365 Mon Sep 17 00:00:00 2001 From: Stergiadis Manos Date: Wed, 20 Jun 2018 13:17:49 +0200 Subject: [PATCH 11/40] Allow pass empty dictionary to `gensim.corpora.WikiCorpus`. Fix #2052 (#2042) --- gensim/corpora/wikicorpus.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/gensim/corpora/wikicorpus.py b/gensim/corpora/wikicorpus.py index b7a18f02db..1c088b9416 100644 --- a/gensim/corpora/wikicorpus.py +++ b/gensim/corpora/wikicorpus.py @@ -558,7 +558,11 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction self.token_min_len = token_min_len self.token_max_len = token_max_len self.lower = lower - self.dictionary = dictionary or Dictionary(self.get_texts()) + + if dictionary is None: + self.dictionary = Dictionary(self.get_texts()) + else: + self.dictionary = dictionary def get_texts(self): """Iterate over the dump, yielding list of tokens for each article. From 76d194b3701ad176119d09913b321806c6aa3fc9 Mon Sep 17 00:00:00 2001 From: Fernando Camargo Date: Thu, 21 Jun 2018 22:02:10 -0300 Subject: [PATCH 12/40] Add `ns_exponent` parameter to control the negative sampling distribution for `*2vec` models. Fix #2090 (#2093) * Adding ns_exponent parameter to control the negative sampling distribution. * Fixed a code style problem. * Updated the documentation of the ns_exponent parameter. --- gensim/models/base_any2vec.py | 7 ++++++- gensim/models/doc2vec.py | 18 +++++++++++++++--- gensim/models/fasttext.py | 16 +++++++++++----- gensim/models/word2vec.py | 25 ++++++++++++++++--------- 4 files changed, 48 insertions(+), 18 deletions(-) diff --git a/gensim/models/base_any2vec.py b/gensim/models/base_any2vec.py index 3b6dabf95e..5cdb54930d 100644 --- a/gensim/models/base_any2vec.py +++ b/gensim/models/base_any2vec.py @@ -526,7 +526,7 @@ def _set_train_params(self, **kwargs): raise NotImplementedError() def __init__(self, sentences=None, workers=3, vector_size=100, epochs=5, callbacks=(), batch_words=10000, - trim_rule=None, sg=0, alpha=0.025, window=5, seed=1, hs=0, negative=5, cbow_mean=1, + trim_rule=None, sg=0, alpha=0.025, window=5, seed=1, hs=0, negative=5, ns_exponent=0.75, cbow_mean=1, min_alpha=0.0001, compute_loss=False, fast_version=0, **kwargs): """ @@ -603,6 +603,7 @@ def __init__(self, sentences=None, workers=3, vector_size=100, epochs=5, callbac self.min_alpha = float(min_alpha) self.hs = int(hs) self.negative = int(negative) + self.ns_exponent = ns_exponent self.cbow_mean = int(cbow_mean) self.compute_loss = bool(compute_loss) self.running_training_loss = 0 @@ -1098,6 +1099,10 @@ def load(cls, *args, **kwargs): """ model = super(BaseWordEmbeddingsModel, cls).load(*args, **kwargs) + if not hasattr(model, 'ns_exponent'): + model.ns_exponent = 0.75 + if not hasattr(model.vocabulary, 'ns_exponent'): + model.vocabulary.ns_exponent = 0.75 if model.negative and hasattr(model.wv, 'index2word'): model.vocabulary.make_cum_table(model.wv) # rebuild cum_table from vocabulary if not hasattr(model, 'corpus_count'): diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py index c2cfd1e16d..d73e6e777a 100644 --- a/gensim/models/doc2vec.py +++ b/gensim/models/doc2vec.py @@ -483,6 +483,12 @@ def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0 If > 0, negative sampling will be used, the int for negative specifies how many "noise words" should be drawn (usually between 5-20). If set to 0, no negative sampling is used. + ns_exponent : float, optional + The exponent used to shape the negative sampling distribution. A value of 1.0 samples exactly in proportion + to the frequencies, 0.0 samples all words equally, while a negative value samples low-frequency words more + than high-frequency words. The popular default value of 0.75 was chosen by the original Word2Vec paper. + More recently, in https://arxiv.org/abs/1804.04212, Caselles-Dupré, Lesaint, & Royo-Letelier suggest that + other values may perform better for recommendation applications. dm_mean : {1,0}, optional If 0 , use the sum of the context word vectors. If 1, use the mean. Only applies when `dm` is used in non-concatenative mode. @@ -546,7 +552,7 @@ def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0 self.dm_tag_count = int(dm_tag_count) kwargs['null_word'] = dm_concat - vocabulary_keys = ['max_vocab_size', 'min_count', 'sample', 'sorted_vocab', 'null_word'] + vocabulary_keys = ['max_vocab_size', 'min_count', 'sample', 'sorted_vocab', 'null_word', 'ns_exponent'] vocabulary_kwargs = dict((k, kwargs[k]) for k in vocabulary_keys if k in kwargs) self.vocabulary = Doc2VecVocab(**vocabulary_kwargs) @@ -1086,7 +1092,7 @@ class Doc2VecVocab(Word2VecVocab): This includes a mapping from words found in the corpus to their total frequency count. """ - def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0): + def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0, ns_exponent=0.75): """ Parameters @@ -1105,11 +1111,17 @@ def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=T null_word : {0, 1} If True, a null pseudo-word will be created for padding when using concatenative L1 (run-of-words). This word is only ever input – never predicted – so count, huffman-point, etc doesn't matter. + ns_exponent : float, optional + The exponent used to shape the negative sampling distribution. A value of 1.0 samples exactly in proportion + to the frequencies, 0.0 samples all words equally, while a negative value samples low-frequency words more + than high-frequency words. The popular default value of 0.75 was chosen by the original Word2Vec paper. + More recently, in https://arxiv.org/abs/1804.04212, Caselles-Dupré, Lesaint, & Royo-Letelier suggest that + other values may perform better for recommendation applications. """ super(Doc2VecVocab, self).__init__( max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, - sorted_vocab=sorted_vocab, null_word=null_word) + sorted_vocab=sorted_vocab, null_word=null_word, ns_exponent=ns_exponent) def scan_vocab(self, documents, docvecs, progress_per=10000, trim_rule=None): """Create the models Vocabulary: A mapping from unique words in the corpus to their frequency count. diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index e9c3dda239..20430eb1e8 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -243,8 +243,8 @@ class FastText(BaseWordEmbeddingsModel): """ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, word_ngrams=1, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, - negative=5, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, min_n=3, max_n=6, sorted_vocab=1, - bucket=2000000, trim_rule=None, batch_words=MAX_WORDS_IN_BATCH, callbacks=()): + negative=5, ns_exponent=0.75, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, min_n=3, max_n=6, + sorted_vocab=1, bucket=2000000, trim_rule=None, batch_words=MAX_WORDS_IN_BATCH, callbacks=()): """ Parameters @@ -290,6 +290,12 @@ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, If > 0, negative sampling will be used, the int for negative specifies how many "noise words" should be drawn (usually between 5-20). If set to 0, no negative sampling is used. + ns_exponent : float, optional + The exponent used to shape the negative sampling distribution. A value of 1.0 samples exactly in proportion + to the frequencies, 0.0 samples all words equally, while a negative value samples low-frequency words more + than high-frequency words. The popular default value of 0.75 was chosen by the original Word2Vec paper. + More recently, in https://arxiv.org/abs/1804.04212, Caselles-Dupré, Lesaint, & Royo-Letelier suggest that + other values may perform better for recommendation applications. cbow_mean : {1,0}, optional If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used. hashfxn : function, optional @@ -352,7 +358,7 @@ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, self.wv = FastTextKeyedVectors(size, min_n, max_n) self.vocabulary = FastTextVocab( max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, - sorted_vocab=bool(sorted_vocab), null_word=null_word) + sorted_vocab=bool(sorted_vocab), null_word=null_word, ns_exponent=ns_exponent) self.trainables = FastTextTrainables( vector_size=size, seed=seed, bucket=bucket, hashfxn=hashfxn) self.wv.bucket = self.bucket @@ -903,10 +909,10 @@ def accuracy(self, questions, restrict_vocab=30000, most_similar=None, case_inse class FastTextVocab(Word2VecVocab): """Vocabulary used by :class:`~gensim.models.fasttext.FastText`.""" - def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0): + def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0, ns_exponent=0.75): super(FastTextVocab, self).__init__( max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, - sorted_vocab=sorted_vocab, null_word=null_word) + sorted_vocab=sorted_vocab, null_word=null_word, ns_exponent=ns_exponent) def prepare_vocab(self, hs, negative, wv, update=False, keep_raw_vocab=False, trim_rule=None, min_count=None, sample=None, dry_run=False): diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py index 018a19c467..d163784c1c 100755 --- a/gensim/models/word2vec.py +++ b/gensim/models/word2vec.py @@ -628,7 +628,7 @@ class Word2Vec(BaseWordEmbeddingsModel): """ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, - sg=0, hs=0, negative=5, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, + sg=0, hs=0, negative=5, ns_exponent=0.75, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, trim_rule=None, sorted_vocab=1, batch_words=MAX_WORDS_IN_BATCH, compute_loss=False, callbacks=(), max_final_vocab=None): """ @@ -661,6 +661,12 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, If > 0, negative sampling will be used, the int for negative specifies how many "noise words" should be drawn (usually between 5-20). If set to 0, no negative sampling is used. + ns_exponent : float, optional + The exponent used to shape the negative sampling distribution. A value of 1.0 samples exactly in proportion + to the frequencies, 0.0 samples all words equally, while a negative value samples low-frequency words more + than high-frequency words. The popular default value of 0.75 was chosen by the original Word2Vec paper. + More recently, in https://arxiv.org/abs/1804.04212, Caselles-Dupré, Lesaint, & Royo-Letelier suggest that + other values may perform better for recommendation applications. cbow_mean : {0, 1}, optional If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used. alpha : float, optional @@ -731,8 +737,8 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, self.wv = Word2VecKeyedVectors(size) self.vocabulary = Word2VecVocab( - max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, - sorted_vocab=bool(sorted_vocab), null_word=null_word, max_final_vocab=max_final_vocab) + max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, sorted_vocab=bool(sorted_vocab), + null_word=null_word, max_final_vocab=max_final_vocab, ns_exponent=ns_exponent) self.trainables = Word2VecTrainables(seed=seed, vector_size=size, hashfxn=hashfxn) super(Word2Vec, self).__init__( @@ -1444,7 +1450,7 @@ class Word2VecVocab(utils.SaveLoad): """Vocabulary used by :class:`~gensim.models.word2vec.Word2Vec`.""" def __init__( self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=True, null_word=0, - max_final_vocab=None): + max_final_vocab=None, ns_exponent=0.75): self.max_vocab_size = max_vocab_size self.min_count = min_count self.sample = sample @@ -1453,6 +1459,7 @@ def __init__( self.cum_table = None # for negative sampling self.raw_vocab = None self.max_final_vocab = max_final_vocab + self.ns_exponent = ns_exponent def scan_vocab(self, sentences, progress_per=10000, trim_rule=None): """Do an initial scan of all words appearing in sentences.""" @@ -1698,9 +1705,9 @@ def create_binary_tree(self, wv): logger.info("built huffman tree with maximum node depth %i", max_depth) - def make_cum_table(self, wv, power=0.75, domain=2**31 - 1): - """Create a cumulative-distribution table using stored vocabulary word counts for drawing random words - in the negative-sampling training routines. + def make_cum_table(self, wv, domain=2**31 - 1): + """Create a cumulative-distribution table using stored vocabulary word counts for + drawing random words in the negative-sampling training routines. To draw a word index, choose a random integer up to the maximum value in the table (cum_table[-1]), then finding that integer's sorted insertion point (as if by `bisect_left` or `ndarray.searchsorted()`). @@ -1714,10 +1721,10 @@ def make_cum_table(self, wv, power=0.75, domain=2**31 - 1): # compute sum of all power (Z in paper) train_words_pow = 0.0 for word_index in xrange(vocab_size): - train_words_pow += wv.vocab[wv.index2word[word_index]].count**power + train_words_pow += wv.vocab[wv.index2word[word_index]].count**self.ns_exponent cumulative = 0.0 for word_index in xrange(vocab_size): - cumulative += wv.vocab[wv.index2word[word_index]].count**power + cumulative += wv.vocab[wv.index2word[word_index]].count**self.ns_exponent self.cum_table[word_index] = round(cumulative / train_words_pow * domain) if len(self.cum_table) > 0: assert self.cum_table[-1] == domain From cc441b7b8bf2f80b17cf44acbcb425d529876ff1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Fri, 22 Jun 2018 03:36:04 +0200 Subject: [PATCH 13/40] Fix documentation for various modules (#2096) * doc fixes * doc fixes to matutils * docsim doc fixes * doc fixes to interfaces module * doc fixes to Dictionary * doc fixes to MatrixMarket classes * doc fixes to WikiCorpus * minor code style changes in HashDictionary * fixing TfidfModel bugs + docs * fixes to phrases docs * fix PEP8 * fix documentation building * cleanup mmcorpus-related * cleanup dictionary * cleanup hashdictionary * cleanup wikicorpus * cleanup interfaces * cleanup matutils * rename smartirs signature * minor docs style fixes * regenerate *.c for mmreader (after last Radim fix) * fix bool parameters * regenerate _mmreader.c again * cleanup phrases * cleanup utils * Fix paper for phrases according to #2098, catch by @davidchall * cleanup docsim * - cleanup tfidfmodel - fix bug in smartirs_normalize (old version correct!) - remove persistence test & remove old models from repo (by rename reason) * typo fix * add back smartirs tests * retrying saved test files --- gensim/corpora/_mmreader.c | 2008 +++++++++++---------- gensim/corpora/_mmreader.pyx | 32 +- gensim/corpora/dictionary.py | 111 +- gensim/corpora/hashdictionary.py | 87 +- gensim/corpora/mmcorpus.py | 54 +- gensim/corpora/wikicorpus.py | 104 +- gensim/interfaces.py | 149 +- gensim/matutils.py | 293 +-- gensim/models/phrases.py | 104 +- gensim/models/tfidfmodel.py | 164 +- gensim/similarities/docsim.py | 193 +- gensim/sklearn_api/phrases.py | 11 +- gensim/test/test_data/tfidf_model.tst | Bin 1261 -> 909 bytes gensim/test/test_data/tfidf_model.tst.bz2 | Bin 822 -> 622 bytes gensim/utils.py | 426 +++-- 15 files changed, 1963 insertions(+), 1773 deletions(-) diff --git a/gensim/corpora/_mmreader.c b/gensim/corpora/_mmreader.c index a54b7d1d12..2adbf9d95d 100644 --- a/gensim/corpora/_mmreader.c +++ b/gensim/corpora/_mmreader.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.27.3 */ +/* Generated by Cython 0.28.3 */ #define PY_SSIZE_T_CLEAN #include "Python.h" @@ -7,7 +7,7 @@ #elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.6+ or Python 3.3+. #else -#define CYTHON_ABI "0_27_3" +#define CYTHON_ABI "0_28_3" #define CYTHON_FUTURE_DIVISION 0 #include #ifndef offsetof @@ -183,6 +183,103 @@ #undef BASE #undef MASK #endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) #define Py_OptimizeFlag 0 #endif @@ -211,12 +308,12 @@ #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif -#if PY_VERSION_HEX < 0x030700A0 || !defined(METH_FASTCALL) +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif - typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject **args, Py_ssize_t nargs); - typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject **args, + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast @@ -228,6 +325,18 @@ #else #define __Pyx_PyFastCFunction_Check(func) 0 #endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif #if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x03060000 @@ -237,6 +346,36 @@ #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; // PyThread_create_key reports success always +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif // TSS (Thread Specific Storage) API #if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else @@ -249,6 +388,11 @@ #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif #if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ @@ -293,18 +437,6 @@ #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif -#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) - #define PyObject_Malloc(s) PyMem_Malloc(s) - #define PyObject_Free(p) PyMem_Free(p) - #define PyObject_Realloc(p) PyMem_Realloc(p) -#endif -#if CYTHON_COMPILING_IN_PYSTON - #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) -#else - #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) -#endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 @@ -321,6 +453,7 @@ #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact + #define PyObject_Unicode PyObject_Str #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) @@ -332,7 +465,11 @@ #ifndef PySet_CheckExact #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) #endif -#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type @@ -367,16 +504,10 @@ #define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t #endif #if PY_MAJOR_VERSION >= 3 - #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func)) + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : (Py_INCREF(func), func)) #else #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) #endif -#ifndef __has_attribute - #define __has_attribute(x) 0 -#endif -#ifndef __has_cpp_attribute - #define __has_cpp_attribute(x) 0 -#endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods @@ -394,96 +525,6 @@ unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif -#ifndef CYTHON_RESTRICT - #if defined(__GNUC__) - #define CYTHON_RESTRICT __restrict__ - #elif defined(_MSC_VER) && _MSC_VER >= 1400 - #define CYTHON_RESTRICT __restrict - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_RESTRICT restrict - #else - #define CYTHON_RESTRICT - #endif -#endif -#ifndef CYTHON_UNUSED -# if defined(__GNUC__) -# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -#endif -#ifndef CYTHON_MAYBE_UNUSED_VAR -# if defined(__cplusplus) - template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } -# else -# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) -# endif -#endif -#ifndef CYTHON_NCP_UNUSED -# if CYTHON_COMPILING_IN_CPYTHON -# define CYTHON_NCP_UNUSED -# else -# define CYTHON_NCP_UNUSED CYTHON_UNUSED -# endif -#endif -#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) -#ifdef _MSC_VER - #ifndef _MSC_STDINT_H_ - #if _MSC_VER < 1300 - typedef unsigned char uint8_t; - typedef unsigned int uint32_t; - #else - typedef unsigned __int8 uint8_t; - typedef unsigned __int32 uint32_t; - #endif - #endif -#else - #include -#endif -#ifndef CYTHON_FALLTHROUGH - #if defined(__cplusplus) && __cplusplus >= 201103L - #if __has_cpp_attribute(fallthrough) - #define CYTHON_FALLTHROUGH [[fallthrough]] - #elif __has_cpp_attribute(clang::fallthrough) - #define CYTHON_FALLTHROUGH [[clang::fallthrough]] - #elif __has_cpp_attribute(gnu::fallthrough) - #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] - #endif - #endif - #ifndef CYTHON_FALLTHROUGH - #if __has_attribute(fallthrough) - #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) - #else - #define CYTHON_FALLTHROUGH - #endif - #endif - #if defined(__clang__ ) && defined(__apple_build_version__) - #if __apple_build_version__ < 7000000 - #undef CYTHON_FALLTHROUGH - #define CYTHON_FALLTHROUGH - #endif - #endif -#endif - -#ifndef CYTHON_INLINE - #if defined(__clang__) - #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) - #elif defined(__GNUC__) - #define CYTHON_INLINE __inline__ - #elif defined(_MSC_VER) - #define CYTHON_INLINE __inline - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_INLINE inline - #else - #define CYTHON_INLINE - #endif -#endif #if defined(WIN32) || defined(MS_WINDOWS) #define _USE_MATH_DEFINES @@ -520,6 +561,7 @@ static CYTHON_INLINE float __PYX_NAN() { #define __PYX_HAVE__gensim__corpora___mmreader #define __PYX_HAVE_API__gensim__corpora___mmreader +/* Early includes */ #include #include #ifdef _OPENMP @@ -606,7 +648,7 @@ static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) -#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False)) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ @@ -714,7 +756,7 @@ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } static PyObject *__pyx_m = NULL; static PyObject *__pyx_d; static PyObject *__pyx_b; -static PyObject *__pyx_cython_runtime; +static PyObject *__pyx_cython_runtime = NULL; static PyObject *__pyx_empty_tuple; static PyObject *__pyx_empty_bytes; static PyObject *__pyx_empty_unicode; @@ -725,7 +767,7 @@ static const char *__pyx_filename; static const char *__pyx_f[] = { - "_mmreader.pyx", + "gensim/corpora/_mmreader.pyx", "stringsource", }; @@ -735,11 +777,11 @@ struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__; struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr; struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__; -/* "gensim/corpora/_mmreader.pyx":19 +/* "gensim/corpora/_mmreader.pyx":21 * * * cdef class MmReader(object): # <<<<<<<<<<<<<< - * """Matrix market file reader (fast Cython version), used for :class:`~gensim.corpora.mmcorpus.MmCorpus`. + * """Matrix market file reader (fast Cython version), used internally in :class:`~gensim.corpora.mmcorpus.MmCorpus`. * */ struct __pyx_obj_6gensim_7corpora_9_mmreader_MmReader { @@ -752,7 +794,7 @@ struct __pyx_obj_6gensim_7corpora_9_mmreader_MmReader { }; -/* "gensim/corpora/_mmreader.pyx":45 +/* "gensim/corpora/_mmreader.pyx":47 * cdef public long long num_docs, num_terms, num_nnz * * def __init__(self, input, transposed=True): # <<<<<<<<<<<<<< @@ -765,7 +807,7 @@ struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__ { }; -/* "gensim/corpora/_mmreader.pyx":75 +/* "gensim/corpora/_mmreader.pyx":77 * line = utils.to_unicode(line) * if not line.startswith('%'): * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) # <<<<<<<<<<<<<< @@ -782,11 +824,11 @@ struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr { }; -/* "gensim/corpora/_mmreader.pyx":107 +/* "gensim/corpora/_mmreader.pyx":109 * break * * def __iter__(self): # <<<<<<<<<<<<<< - * """Iterate through corpus. + * """Iterate through all documents in the corpus. * */ struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__ { @@ -878,16 +920,7 @@ struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__ { /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_getattro)) - return tp->tp_getattro(obj, attr_name); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_getattr)) - return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); -#endif - return PyObject_GetAttr(obj, attr_name); -} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif @@ -1137,6 +1170,20 @@ static CYTHON_INLINE int __Pyx_HasAttr(PyObject *, PyObject *); /* IncludeStringH.proto */ #include +/* PyObject_GenericGetAttrNoDict.proto */ +#if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static CYTHON_INLINE PyObject* __Pyx_PyObject_GenericGetAttrNoDict(PyObject* obj, PyObject* attr_name); +#else +#define __Pyx_PyObject_GenericGetAttrNoDict PyObject_GenericGetAttr +#endif + +/* PyObject_GenericGetAttr.proto */ +#if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static PyObject* __Pyx_PyObject_GenericGetAttr(PyObject* obj, PyObject* attr_name); +#else +#define __Pyx_PyObject_GenericGetAttr PyObject_GenericGetAttr +#endif + /* SetupReduce.proto */ static int __Pyx_setup_reduce(PyObject* type_obj); @@ -1192,6 +1239,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) #define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) #endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) /* FetchCommonType.proto */ static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type); @@ -1223,14 +1271,15 @@ typedef struct { PyObject *gi_name; PyObject *gi_qualname; PyObject *gi_modulename; + PyObject *gi_code; int resume_label; char is_running; } __pyx_CoroutineObject; static __pyx_CoroutineObject *__Pyx__Coroutine_New( - PyTypeObject *type, __pyx_coroutine_body_t body, PyObject *closure, + PyTypeObject *type, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name); static __pyx_CoroutineObject *__Pyx__Coroutine_NewInit( - __pyx_CoroutineObject *gen, __pyx_coroutine_body_t body, PyObject *closure, + __pyx_CoroutineObject *gen, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name); static int __Pyx_Coroutine_clear(PyObject *self); static PyObject *__Pyx_Coroutine_Send(PyObject *self, PyObject *value); @@ -1264,8 +1313,8 @@ static int __Pyx_patch_abc(void); #define __Pyx_Generator_USED static PyTypeObject *__pyx_GeneratorType = 0; #define __Pyx_Generator_CheckExact(obj) (Py_TYPE(obj) == __pyx_GeneratorType) -#define __Pyx_Generator_New(body, closure, name, qualname, module_name)\ - __Pyx__Coroutine_New(__pyx_GeneratorType, body, closure, name, qualname, module_name) +#define __Pyx_Generator_New(body, code, closure, name, qualname, module_name)\ + __Pyx__Coroutine_New(__pyx_GeneratorType, body, code, closure, name, qualname, module_name) static PyObject *__Pyx_Generator_Next(PyObject *self); static int __pyx_Generator_init(void); @@ -1472,8 +1521,9 @@ static PyObject *__pyx_tuple__5; static PyObject *__pyx_tuple__6; static PyObject *__pyx_tuple__7; static PyObject *__pyx_codeobj__8; +/* Late includes */ -/* "gensim/corpora/_mmreader.pyx":45 +/* "gensim/corpora/_mmreader.pyx":47 * cdef public long long num_docs, num_terms, num_nnz * * def __init__(self, input, transposed=True): # <<<<<<<<<<<<<< @@ -1483,7 +1533,7 @@ static PyObject *__pyx_codeobj__8; /* Python wrapper */ static int __pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_1__init__(PyObject *__pyx_v_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ -static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader___init__[] = "\n\n Parameters\n ----------\n input : {str, file-like object}\n Path to input file in MM format or a file-like object that supports `seek()`\n (e.g. :class:`~gzip.GzipFile`, :class:`~bz2.BZ2File`).\n\n transposed : bool, optional\n if True, expects lines to represent doc_id, term_id, value. Else, expects term_id, doc_id, value.\n\n "; +static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader___init__[] = "\n\n Parameters\n ----------\n input : {str, file-like object}\n Path to the input file in MM format or a file-like object that supports `seek()`\n (e.g. smart_open objects).\n\n transposed : bool, optional\n Do lines represent `doc_id, term_id, value`, instead of `term_id, doc_id, value`?\n\n "; #if CYTHON_COMPILING_IN_CPYTHON struct wrapperbase __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__; #endif @@ -1511,17 +1561,17 @@ static int __pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_1__init__(PyObject *__ kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_input)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_input)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_transposed); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_transposed); if (value) { values[1] = value; kw_args--; } } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__init__") < 0)) __PYX_ERR(0, 45, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__init__") < 0)) __PYX_ERR(0, 47, __pyx_L3_error) } } else { switch (PyTuple_GET_SIZE(__pyx_args)) { @@ -1537,7 +1587,7 @@ static int __pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_1__init__(PyObject *__ } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("__init__", 0, 1, 2, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 45, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__init__", 0, 1, 2, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(0, 47, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("gensim.corpora._mmreader.MmReader.__init__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -1551,7 +1601,7 @@ static int __pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_1__init__(PyObject *__ } static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2generator1(__pyx_CoroutineObject *__pyx_generator, CYTHON_UNUSED PyThreadState *__pyx_tstate, PyObject *__pyx_sent_value); /* proto */ -/* "gensim/corpora/_mmreader.pyx":75 +/* "gensim/corpora/_mmreader.pyx":77 * line = utils.to_unicode(line) * if not line.startswith('%'): * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) # <<<<<<<<<<<<<< @@ -1568,7 +1618,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8__init___genexp if (unlikely(!__pyx_cur_scope)) { __pyx_cur_scope = ((struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr *)Py_None); __Pyx_INCREF(Py_None); - __PYX_ERR(0, 75, __pyx_L1_error) + __PYX_ERR(0, 77, __pyx_L1_error) } else { __Pyx_GOTREF(__pyx_cur_scope); } @@ -1576,7 +1626,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8__init___genexp __Pyx_INCREF(((PyObject *)__pyx_cur_scope->__pyx_outer_scope)); __Pyx_GIVEREF(__pyx_cur_scope->__pyx_outer_scope); { - __pyx_CoroutineObject *gen = __Pyx_Generator_New((__pyx_coroutine_body_t) __pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2generator1, (PyObject *) __pyx_cur_scope, __pyx_n_s_genexpr, __pyx_n_s_init___locals_genexpr, __pyx_n_s_gensim_corpora__mmreader); if (unlikely(!gen)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_CoroutineObject *gen = __Pyx_Generator_New((__pyx_coroutine_body_t) __pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2generator1, NULL, (PyObject *) __pyx_cur_scope, __pyx_n_s_genexpr, __pyx_n_s_init___locals_genexpr, __pyx_n_s_gensim_corpora__mmreader); if (unlikely(!gen)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_DECREF(__pyx_cur_scope); __Pyx_RefNannyFinishContext(); return (PyObject *) gen; @@ -1611,9 +1661,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener return NULL; } __pyx_L3_first_run:; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 75, __pyx_L1_error) - if (unlikely(!__pyx_cur_scope->__pyx_outer_scope->__pyx_v_line)) { __Pyx_RaiseClosureNameError("line"); __PYX_ERR(0, 75, __pyx_L1_error) } - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_cur_scope->__pyx_outer_scope->__pyx_v_line, __pyx_n_s_split); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 75, __pyx_L1_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 77, __pyx_L1_error) + if (unlikely(!__pyx_cur_scope->__pyx_outer_scope->__pyx_v_line)) { __Pyx_RaiseClosureNameError("line"); __PYX_ERR(0, 77, __pyx_L1_error) } + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_cur_scope->__pyx_outer_scope->__pyx_v_line, __pyx_n_s_split); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_2))) { @@ -1626,10 +1676,10 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener } } if (__pyx_t_3) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else { - __pyx_t_1 = __Pyx_PyObject_CallNoArg(__pyx_t_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_CallNoArg(__pyx_t_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 77, __pyx_L1_error) } __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; @@ -1637,9 +1687,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener __pyx_t_2 = __pyx_t_1; __Pyx_INCREF(__pyx_t_2); __pyx_t_4 = 0; __pyx_t_5 = NULL; } else { - __pyx_t_4 = -1; __pyx_t_2 = PyObject_GetIter(__pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_4 = -1; __pyx_t_2 = PyObject_GetIter(__pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_5 = Py_TYPE(__pyx_t_2)->tp_iternext; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_5 = Py_TYPE(__pyx_t_2)->tp_iternext; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 77, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; for (;;) { @@ -1647,17 +1697,17 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener if (likely(PyList_CheckExact(__pyx_t_2))) { if (__pyx_t_4 >= PyList_GET_SIZE(__pyx_t_2)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_4); __Pyx_INCREF(__pyx_t_1); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_4); __Pyx_INCREF(__pyx_t_1); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 77, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_4 >= PyTuple_GET_SIZE(__pyx_t_2)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_2, __pyx_t_4); __Pyx_INCREF(__pyx_t_1); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_2, __pyx_t_4); __Pyx_INCREF(__pyx_t_1); __pyx_t_4++; if (unlikely(0 < 0)) __PYX_ERR(0, 77, __pyx_L1_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_4); __pyx_t_4++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -1667,7 +1717,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 75, __pyx_L1_error) + else __PYX_ERR(0, 77, __pyx_L1_error) } break; } @@ -1677,7 +1727,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener __Pyx_XDECREF_SET(__pyx_cur_scope->__pyx_v_x, __pyx_t_1); __Pyx_GIVEREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyNumber_Int(__pyx_cur_scope->__pyx_v_x); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyNumber_Int(__pyx_cur_scope->__pyx_v_x); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; @@ -1697,7 +1747,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener __Pyx_XGOTREF(__pyx_t_2); __pyx_t_4 = __pyx_cur_scope->__pyx_t_1; __pyx_t_5 = __pyx_cur_scope->__pyx_t_2; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 75, __pyx_L1_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 77, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; CYTHON_MAYBE_UNUSED_VAR(__pyx_cur_scope); @@ -1719,7 +1769,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_8__init___2gener return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":45 +/* "gensim/corpora/_mmreader.pyx":47 * cdef public long long num_docs, num_terms, num_nnz * * def __init__(self, input, transposed=True): # <<<<<<<<<<<<<< @@ -1762,21 +1812,21 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ if (unlikely(!__pyx_cur_scope)) { __pyx_cur_scope = ((struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__ *)Py_None); __Pyx_INCREF(Py_None); - __PYX_ERR(0, 45, __pyx_L1_error) + __PYX_ERR(0, 47, __pyx_L1_error) } else { __Pyx_GOTREF(__pyx_cur_scope); } - /* "gensim/corpora/_mmreader.pyx":58 + /* "gensim/corpora/_mmreader.pyx":60 * * """ * logger.info("initializing cython corpus reader from %s", input) # <<<<<<<<<<<<<< * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: */ - __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_logger); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 58, __pyx_L1_error) + __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_logger); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_info); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 58, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_info); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 60, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = NULL; @@ -1794,7 +1844,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[3] = {__pyx_t_2, __pyx_kp_s_initializing_cython_corpus_reade, __pyx_v_input}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_4, 2+__pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 58, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_4, 2+__pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_GOTREF(__pyx_t_1); } else @@ -1802,13 +1852,13 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[3] = {__pyx_t_2, __pyx_kp_s_initializing_cython_corpus_reade, __pyx_v_input}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_4, 2+__pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 58, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_4, 2+__pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_GOTREF(__pyx_t_1); } else #endif { - __pyx_t_5 = PyTuple_New(2+__pyx_t_4); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 58, __pyx_L1_error) + __pyx_t_5 = PyTuple_New(2+__pyx_t_4); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 60, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); if (__pyx_t_2) { __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_2); __pyx_t_2 = NULL; @@ -1819,14 +1869,14 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_INCREF(__pyx_v_input); __Pyx_GIVEREF(__pyx_v_input); PyTuple_SET_ITEM(__pyx_t_5, 1+__pyx_t_4, __pyx_v_input); - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_5, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 58, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_5, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/corpora/_mmreader.pyx":59 + /* "gensim/corpora/_mmreader.pyx":61 * """ * logger.info("initializing cython corpus reader from %s", input) * self.input, self.transposed = input, transposed # <<<<<<<<<<<<<< @@ -1835,7 +1885,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ */ __pyx_t_1 = __pyx_v_input; __Pyx_INCREF(__pyx_t_1); - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_v_transposed); if (unlikely((__pyx_t_6 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 59, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_v_transposed); if (unlikely((__pyx_t_6 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 61, __pyx_L1_error) __Pyx_GIVEREF(__pyx_t_1); __Pyx_GOTREF(__pyx_v_self->input); __Pyx_DECREF(__pyx_v_self->input); @@ -1843,7 +1893,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_t_1 = 0; __pyx_v_self->transposed = __pyx_t_6; - /* "gensim/corpora/_mmreader.pyx":60 + /* "gensim/corpora/_mmreader.pyx":62 * logger.info("initializing cython corpus reader from %s", input) * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: # <<<<<<<<<<<<<< @@ -1851,9 +1901,9 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ * header = utils.to_unicode(next(lines)).strip() */ /*with:*/ { - __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_open_file); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_open_file); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = NULL; @@ -1867,13 +1917,13 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ } } if (!__pyx_t_3) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_v_self->input); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_v_self->input); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_3, __pyx_v_self->input}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_1); } else @@ -1881,27 +1931,27 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_3, __pyx_v_self->input}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_1); } else #endif { - __pyx_t_2 = PyTuple_New(1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_2 = PyTuple_New(1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_3); __pyx_t_3 = NULL; __Pyx_INCREF(__pyx_v_self->input); __Pyx_GIVEREF(__pyx_v_self->input); PyTuple_SET_ITEM(__pyx_t_2, 0+1, __pyx_v_self->input); - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_2, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_2, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } } __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __pyx_t_7 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_exit); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_exit); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); - __pyx_t_2 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_enter); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L3_error) + __pyx_t_2 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_enter); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 62, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_2))) { @@ -1914,10 +1964,10 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ } } if (__pyx_t_3) { - __pyx_t_5 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 60, __pyx_L3_error) + __pyx_t_5 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 62, __pyx_L3_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else { - __pyx_t_5 = __Pyx_PyObject_CallNoArg(__pyx_t_2); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 60, __pyx_L3_error) + __pyx_t_5 = __Pyx_PyObject_CallNoArg(__pyx_t_2); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 62, __pyx_L3_error) } __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; @@ -1936,7 +1986,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_v_lines = __pyx_t_2; __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":61 + /* "gensim/corpora/_mmreader.pyx":63 * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: * try: # <<<<<<<<<<<<<< @@ -1952,19 +2002,19 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_XGOTREF(__pyx_t_13); /*try:*/ { - /* "gensim/corpora/_mmreader.pyx":62 + /* "gensim/corpora/_mmreader.pyx":64 * with utils.open_file(self.input) as lines: * try: * header = utils.to_unicode(next(lines)).strip() # <<<<<<<<<<<<<< * if not header.lower().startswith('%%matrixmarket matrix coordinate real general'): * raise ValueError( */ - __pyx_t_5 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_5 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_5); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_5, __pyx_n_s_to_unicode); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_5, __pyx_n_s_to_unicode); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __pyx_t_5 = __Pyx_PyIter_Next(__pyx_v_lines); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_5 = __Pyx_PyIter_Next(__pyx_v_lines); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_14 = NULL; if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_3))) { @@ -1977,14 +2027,14 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ } } if (!__pyx_t_14) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_5); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_5); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_GOTREF(__pyx_t_1); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[2] = {__pyx_t_14, __pyx_t_5}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; @@ -1993,26 +2043,26 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[2] = {__pyx_t_14, __pyx_t_5}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } else #endif { - __pyx_t_15 = PyTuple_New(1+1); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_15 = PyTuple_New(1+1); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_15); __Pyx_GIVEREF(__pyx_t_14); PyTuple_SET_ITEM(__pyx_t_15, 0, __pyx_t_14); __pyx_t_14 = NULL; __Pyx_GIVEREF(__pyx_t_5); PyTuple_SET_ITEM(__pyx_t_15, 0+1, __pyx_t_5); __pyx_t_5 = 0; - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_15, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_15, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_15); __pyx_t_15 = 0; } } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_strip); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_strip); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_t_1 = NULL; @@ -2026,24 +2076,24 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ } } if (__pyx_t_1) { - __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 64, __pyx_L13_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } else { - __pyx_t_2 = __Pyx_PyObject_CallNoArg(__pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 62, __pyx_L13_error) + __pyx_t_2 = __Pyx_PyObject_CallNoArg(__pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 64, __pyx_L13_error) } __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_header = __pyx_t_2; __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":63 + /* "gensim/corpora/_mmreader.pyx":65 * try: * header = utils.to_unicode(next(lines)).strip() * if not header.lower().startswith('%%matrixmarket matrix coordinate real general'): # <<<<<<<<<<<<<< * raise ValueError( * "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" % */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_header, __pyx_n_s_lower); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 63, __pyx_L13_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_header, __pyx_n_s_lower); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 65, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_1 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_3))) { @@ -2056,32 +2106,32 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ } } if (__pyx_t_1) { - __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 63, __pyx_L13_error) + __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 65, __pyx_L13_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } else { - __pyx_t_2 = __Pyx_PyObject_CallNoArg(__pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 63, __pyx_L13_error) + __pyx_t_2 = __Pyx_PyObject_CallNoArg(__pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 65, __pyx_L13_error) } __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_startswith); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 63, __pyx_L13_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_startswith); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 65, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 63, __pyx_L13_error) + __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_tuple_, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 65, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_2); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 63, __pyx_L13_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_2); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 65, __pyx_L13_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_16 = ((!__pyx_t_6) != 0); - if (__pyx_t_16) { + if (unlikely(__pyx_t_16)) { - /* "gensim/corpora/_mmreader.pyx":66 + /* "gensim/corpora/_mmreader.pyx":68 * raise ValueError( * "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" % * (self.input, header) # <<<<<<<<<<<<<< * ) * except StopIteration: */ - __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 66, __pyx_L13_error) + __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 68, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_v_self->input); __Pyx_GIVEREF(__pyx_v_self->input); @@ -2090,37 +2140,32 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_GIVEREF(__pyx_v_header); PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_v_header); - /* "gensim/corpora/_mmreader.pyx":65 + /* "gensim/corpora/_mmreader.pyx":67 * if not header.lower().startswith('%%matrixmarket matrix coordinate real general'): * raise ValueError( * "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" % # <<<<<<<<<<<<<< * (self.input, header) * ) */ - __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_File_s_not_in_Matrix_Market_form, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 65, __pyx_L13_error) + __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_File_s_not_in_Matrix_Market_form, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 67, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":64 + /* "gensim/corpora/_mmreader.pyx":66 * header = utils.to_unicode(next(lines)).strip() * if not header.lower().startswith('%%matrixmarket matrix coordinate real general'): * raise ValueError( # <<<<<<<<<<<<<< * "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" % * (self.input, header) */ - __pyx_t_2 = PyTuple_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 64, __pyx_L13_error) + __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 66, __pyx_L13_error) __Pyx_GOTREF(__pyx_t_2); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 64, __pyx_L13_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(0, 64, __pyx_L13_error) + __Pyx_Raise(__pyx_t_2, 0, 0, 0); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __PYX_ERR(0, 66, __pyx_L13_error) - /* "gensim/corpora/_mmreader.pyx":63 + /* "gensim/corpora/_mmreader.pyx":65 * try: * header = utils.to_unicode(next(lines)).strip() * if not header.lower().startswith('%%matrixmarket matrix coordinate real general'): # <<<<<<<<<<<<<< @@ -2129,7 +2174,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ */ } - /* "gensim/corpora/_mmreader.pyx":61 + /* "gensim/corpora/_mmreader.pyx":63 * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: * try: # <<<<<<<<<<<<<< @@ -2146,10 +2191,10 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; - __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":68 + /* "gensim/corpora/_mmreader.pyx":70 * (self.input, header) * ) * except StopIteration: # <<<<<<<<<<<<<< @@ -2164,7 +2209,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ goto __pyx_L15_except_error; __pyx_L15_except_error:; - /* "gensim/corpora/_mmreader.pyx":61 + /* "gensim/corpora/_mmreader.pyx":63 * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: * try: # <<<<<<<<<<<<<< @@ -2184,7 +2229,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_L18_try_end:; } - /* "gensim/corpora/_mmreader.pyx":71 + /* "gensim/corpora/_mmreader.pyx":73 * pass * * self.num_docs = self.num_terms = self.num_nnz = 0 # <<<<<<<<<<<<<< @@ -2195,7 +2240,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_v_self->num_terms = 0; __pyx_v_self->num_nnz = 0; - /* "gensim/corpora/_mmreader.pyx":72 + /* "gensim/corpora/_mmreader.pyx":74 * * self.num_docs = self.num_terms = self.num_nnz = 0 * for lineno, line in enumerate(lines): # <<<<<<<<<<<<<< @@ -2203,41 +2248,41 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ * if not line.startswith('%'): */ __Pyx_INCREF(__pyx_int_0); - __pyx_t_3 = __pyx_int_0; + __pyx_t_2 = __pyx_int_0; if (likely(PyList_CheckExact(__pyx_v_lines)) || PyTuple_CheckExact(__pyx_v_lines)) { - __pyx_t_2 = __pyx_v_lines; __Pyx_INCREF(__pyx_t_2); __pyx_t_17 = 0; + __pyx_t_3 = __pyx_v_lines; __Pyx_INCREF(__pyx_t_3); __pyx_t_17 = 0; __pyx_t_18 = NULL; } else { - __pyx_t_17 = -1; __pyx_t_2 = PyObject_GetIter(__pyx_v_lines); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 72, __pyx_L7_error) - __Pyx_GOTREF(__pyx_t_2); - __pyx_t_18 = Py_TYPE(__pyx_t_2)->tp_iternext; if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 72, __pyx_L7_error) + __pyx_t_17 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_lines); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 74, __pyx_L7_error) + __Pyx_GOTREF(__pyx_t_3); + __pyx_t_18 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 74, __pyx_L7_error) } for (;;) { if (likely(!__pyx_t_18)) { - if (likely(PyList_CheckExact(__pyx_t_2))) { - if (__pyx_t_17 >= PyList_GET_SIZE(__pyx_t_2)) break; + if (likely(PyList_CheckExact(__pyx_t_3))) { + if (__pyx_t_17 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_17); __Pyx_INCREF(__pyx_t_1); __pyx_t_17++; if (unlikely(0 < 0)) __PYX_ERR(0, 72, __pyx_L7_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_17); __Pyx_INCREF(__pyx_t_1); __pyx_t_17++; if (unlikely(0 < 0)) __PYX_ERR(0, 74, __pyx_L7_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_17); __pyx_t_17++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 72, __pyx_L7_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_3, __pyx_t_17); __pyx_t_17++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 74, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { - if (__pyx_t_17 >= PyTuple_GET_SIZE(__pyx_t_2)) break; + if (__pyx_t_17 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_2, __pyx_t_17); __Pyx_INCREF(__pyx_t_1); __pyx_t_17++; if (unlikely(0 < 0)) __PYX_ERR(0, 72, __pyx_L7_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_17); __Pyx_INCREF(__pyx_t_1); __pyx_t_17++; if (unlikely(0 < 0)) __PYX_ERR(0, 74, __pyx_L7_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_17); __pyx_t_17++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 72, __pyx_L7_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_3, __pyx_t_17); __pyx_t_17++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 74, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); #endif } } else { - __pyx_t_1 = __pyx_t_18(__pyx_t_2); + __pyx_t_1 = __pyx_t_18(__pyx_t_3); if (unlikely(!__pyx_t_1)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 72, __pyx_L7_error) + else __PYX_ERR(0, 74, __pyx_L7_error) } break; } @@ -2247,24 +2292,24 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_XDECREF_SET(__pyx_cur_scope->__pyx_v_line, __pyx_t_1); __Pyx_GIVEREF(__pyx_t_1); __pyx_t_1 = 0; - __Pyx_INCREF(__pyx_t_3); - __Pyx_XDECREF_SET(__pyx_v_lineno, __pyx_t_3); - __pyx_t_1 = __Pyx_PyInt_AddObjC(__pyx_t_3, __pyx_int_1, 1, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 72, __pyx_L7_error) + __Pyx_INCREF(__pyx_t_2); + __Pyx_XDECREF_SET(__pyx_v_lineno, __pyx_t_2); + __pyx_t_1 = __Pyx_PyInt_AddObjC(__pyx_t_2, __pyx_int_1, 1, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 74, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); - __Pyx_DECREF(__pyx_t_3); - __pyx_t_3 = __pyx_t_1; + __Pyx_DECREF(__pyx_t_2); + __pyx_t_2 = __pyx_t_1; __pyx_t_1 = 0; - /* "gensim/corpora/_mmreader.pyx":73 + /* "gensim/corpora/_mmreader.pyx":75 * self.num_docs = self.num_terms = self.num_nnz = 0 * for lineno, line in enumerate(lines): * line = utils.to_unicode(line) # <<<<<<<<<<<<<< * if not line.startswith('%'): * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) */ - __pyx_t_15 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_15 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_15); - __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_15, __pyx_n_s_to_unicode); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_15, __pyx_n_s_to_unicode); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_15); __pyx_t_15 = 0; __pyx_t_15 = NULL; @@ -2278,13 +2323,13 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ } } if (!__pyx_t_15) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_cur_scope->__pyx_v_line); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_cur_scope->__pyx_v_line); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_15, __pyx_cur_scope->__pyx_v_line}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_GOTREF(__pyx_t_1); } else @@ -2292,19 +2337,19 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_15, __pyx_cur_scope->__pyx_v_line}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_GOTREF(__pyx_t_1); } else #endif { - __pyx_t_14 = PyTuple_New(1+1); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_14 = PyTuple_New(1+1); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_14); __Pyx_GIVEREF(__pyx_t_15); PyTuple_SET_ITEM(__pyx_t_14, 0, __pyx_t_15); __pyx_t_15 = NULL; __Pyx_INCREF(__pyx_cur_scope->__pyx_v_line); __Pyx_GIVEREF(__pyx_cur_scope->__pyx_v_line); PyTuple_SET_ITEM(__pyx_t_14, 0+1, __pyx_cur_scope->__pyx_v_line); - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_14, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 73, __pyx_L7_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_14, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; } @@ -2315,43 +2360,39 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_GIVEREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/corpora/_mmreader.pyx":74 + /* "gensim/corpora/_mmreader.pyx":76 * for lineno, line in enumerate(lines): * line = utils.to_unicode(line) * if not line.startswith('%'): # <<<<<<<<<<<<<< * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) * if not self.transposed: */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_cur_scope->__pyx_v_line, __pyx_n_s_startswith); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 74, __pyx_L7_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_cur_scope->__pyx_v_line, __pyx_n_s_startswith); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 76, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 74, __pyx_L7_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__3, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 76, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_16 = __Pyx_PyObject_IsTrue(__pyx_t_5); if (unlikely(__pyx_t_16 < 0)) __PYX_ERR(0, 74, __pyx_L7_error) + __pyx_t_16 = __Pyx_PyObject_IsTrue(__pyx_t_5); if (unlikely(__pyx_t_16 < 0)) __PYX_ERR(0, 76, __pyx_L7_error) __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __pyx_t_6 = ((!__pyx_t_16) != 0); if (__pyx_t_6) { - /* "gensim/corpora/_mmreader.pyx":75 + /* "gensim/corpora/_mmreader.pyx":77 * line = utils.to_unicode(line) * if not line.startswith('%'): * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) # <<<<<<<<<<<<<< * if not self.transposed: * self.num_docs, self.num_terms = self.num_terms, self.num_docs */ - __pyx_t_5 = __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8__init___genexpr(((PyObject*)__pyx_cur_scope)); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_5 = __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8__init___genexpr(((PyObject*)__pyx_cur_scope)); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_5); if ((likely(PyTuple_CheckExact(__pyx_t_5))) || (PyList_CheckExact(__pyx_t_5))) { PyObject* sequence = __pyx_t_5; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 3)) { if (size > 3) __Pyx_RaiseTooManyValuesError(3); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(0, 75, __pyx_L7_error) + __PYX_ERR(0, 77, __pyx_L7_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS if (likely(PyTuple_CheckExact(sequence))) { @@ -2367,17 +2408,17 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_INCREF(__pyx_t_14); __Pyx_INCREF(__pyx_t_15); #else - __pyx_t_1 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_1 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_14 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_14 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_14); - __pyx_t_15 = PySequence_ITEM(sequence, 2); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_15 = PySequence_ITEM(sequence, 2); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_15); #endif __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } else { Py_ssize_t index = -1; - __pyx_t_19 = PyObject_GetIter(__pyx_t_5); if (unlikely(!__pyx_t_19)) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_19 = PyObject_GetIter(__pyx_t_5); if (unlikely(!__pyx_t_19)) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_19); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __pyx_t_20 = Py_TYPE(__pyx_t_19)->tp_iternext; @@ -2387,7 +2428,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_GOTREF(__pyx_t_14); index = 2; __pyx_t_15 = __pyx_t_20(__pyx_t_19); if (unlikely(!__pyx_t_15)) goto __pyx_L23_unpacking_failed; __Pyx_GOTREF(__pyx_t_15); - if (__Pyx_IternextUnpackEndCheck(__pyx_t_20(__pyx_t_19), 3) < 0) __PYX_ERR(0, 75, __pyx_L7_error) + if (__Pyx_IternextUnpackEndCheck(__pyx_t_20(__pyx_t_19), 3) < 0) __PYX_ERR(0, 77, __pyx_L7_error) __pyx_t_20 = NULL; __Pyx_DECREF(__pyx_t_19); __pyx_t_19 = 0; goto __pyx_L24_unpacking_done; @@ -2395,20 +2436,20 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_DECREF(__pyx_t_19); __pyx_t_19 = 0; __pyx_t_20 = NULL; if (__Pyx_IterFinish() == 0) __Pyx_RaiseNeedMoreValuesError(index); - __PYX_ERR(0, 75, __pyx_L7_error) + __PYX_ERR(0, 77, __pyx_L7_error) __pyx_L24_unpacking_done:; } - __pyx_t_21 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_1); if (unlikely((__pyx_t_21 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_21 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_1); if (unlikely((__pyx_t_21 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_22 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_14); if (unlikely((__pyx_t_22 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_22 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_14); if (unlikely((__pyx_t_22 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; - __pyx_t_23 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_15); if (unlikely((__pyx_t_23 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 75, __pyx_L7_error) + __pyx_t_23 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_15); if (unlikely((__pyx_t_23 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 77, __pyx_L7_error) __Pyx_DECREF(__pyx_t_15); __pyx_t_15 = 0; __pyx_v_self->num_docs = __pyx_t_21; __pyx_v_self->num_terms = __pyx_t_22; __pyx_v_self->num_nnz = __pyx_t_23; - /* "gensim/corpora/_mmreader.pyx":76 + /* "gensim/corpora/_mmreader.pyx":78 * if not line.startswith('%'): * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) * if not self.transposed: # <<<<<<<<<<<<<< @@ -2418,7 +2459,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_t_6 = ((!(__pyx_v_self->transposed != 0)) != 0); if (__pyx_t_6) { - /* "gensim/corpora/_mmreader.pyx":77 + /* "gensim/corpora/_mmreader.pyx":79 * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) * if not self.transposed: * self.num_docs, self.num_terms = self.num_terms, self.num_docs # <<<<<<<<<<<<<< @@ -2430,7 +2471,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_v_self->num_docs = __pyx_t_23; __pyx_v_self->num_terms = __pyx_t_22; - /* "gensim/corpora/_mmreader.pyx":76 + /* "gensim/corpora/_mmreader.pyx":78 * if not line.startswith('%'): * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) * if not self.transposed: # <<<<<<<<<<<<<< @@ -2439,7 +2480,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ */ } - /* "gensim/corpora/_mmreader.pyx":78 + /* "gensim/corpora/_mmreader.pyx":80 * if not self.transposed: * self.num_docs, self.num_terms = self.num_terms, self.num_docs * break # <<<<<<<<<<<<<< @@ -2448,7 +2489,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ */ goto __pyx_L21_break; - /* "gensim/corpora/_mmreader.pyx":74 + /* "gensim/corpora/_mmreader.pyx":76 * for lineno, line in enumerate(lines): * line = utils.to_unicode(line) * if not line.startswith('%'): # <<<<<<<<<<<<<< @@ -2457,7 +2498,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ */ } - /* "gensim/corpora/_mmreader.pyx":72 + /* "gensim/corpora/_mmreader.pyx":74 * * self.num_docs = self.num_terms = self.num_nnz = 0 * for lineno, line in enumerate(lines): # <<<<<<<<<<<<<< @@ -2466,10 +2507,10 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ */ } __pyx_L21_break:; - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":60 + /* "gensim/corpora/_mmreader.pyx":62 * logger.info("initializing cython corpus reader from %s", input) * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: # <<<<<<<<<<<<<< @@ -2487,35 +2528,35 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_XDECREF(__pyx_t_14); __pyx_t_14 = 0; __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; - __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; /*except:*/ { __Pyx_AddTraceback("gensim.corpora._mmreader.MmReader.__init__", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_3, &__pyx_t_2, &__pyx_t_5) < 0) __PYX_ERR(0, 60, __pyx_L9_except_error) - __Pyx_GOTREF(__pyx_t_3); + if (__Pyx_GetException(&__pyx_t_2, &__pyx_t_3, &__pyx_t_5) < 0) __PYX_ERR(0, 62, __pyx_L9_except_error) __Pyx_GOTREF(__pyx_t_2); + __Pyx_GOTREF(__pyx_t_3); __Pyx_GOTREF(__pyx_t_5); - __pyx_t_15 = PyTuple_Pack(3, __pyx_t_3, __pyx_t_2, __pyx_t_5); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 60, __pyx_L9_except_error) + __pyx_t_15 = PyTuple_Pack(3, __pyx_t_2, __pyx_t_3, __pyx_t_5); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 62, __pyx_L9_except_error) __Pyx_GOTREF(__pyx_t_15); __pyx_t_13 = __Pyx_PyObject_Call(__pyx_t_7, __pyx_t_15, NULL); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __Pyx_DECREF(__pyx_t_15); __pyx_t_15 = 0; - if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 60, __pyx_L9_except_error) + if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 62, __pyx_L9_except_error) __Pyx_GOTREF(__pyx_t_13); __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_13); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; - if (__pyx_t_6 < 0) __PYX_ERR(0, 60, __pyx_L9_except_error) + if (__pyx_t_6 < 0) __PYX_ERR(0, 62, __pyx_L9_except_error) __pyx_t_16 = ((!(__pyx_t_6 != 0)) != 0); if (__pyx_t_16) { - __Pyx_GIVEREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_2); + __Pyx_GIVEREF(__pyx_t_3); __Pyx_XGIVEREF(__pyx_t_5); - __Pyx_ErrRestoreWithState(__pyx_t_3, __pyx_t_2, __pyx_t_5); - __pyx_t_3 = 0; __pyx_t_2 = 0; __pyx_t_5 = 0; - __PYX_ERR(0, 60, __pyx_L9_except_error) + __Pyx_ErrRestoreWithState(__pyx_t_2, __pyx_t_3, __pyx_t_5); + __pyx_t_2 = 0; __pyx_t_3 = 0; __pyx_t_5 = 0; + __PYX_ERR(0, 62, __pyx_L9_except_error) } - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; goto __pyx_L8_exception_handled; } @@ -2538,7 +2579,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ if (__pyx_t_7) { __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_7, __pyx_tuple__4, NULL); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 60, __pyx_L1_error) + if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; } @@ -2553,68 +2594,68 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __pyx_L29:; } - /* "gensim/corpora/_mmreader.pyx":80 + /* "gensim/corpora/_mmreader.pyx":82 * break * * logger.info( # <<<<<<<<<<<<<< * "accepted corpus with %i documents, %i features, %i non-zero entries", * self.num_docs, self.num_terms, self.num_nnz */ - __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_logger); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 80, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_info); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 80, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_logger); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_info); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 82, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/corpora/_mmreader.pyx":82 + /* "gensim/corpora/_mmreader.pyx":84 * logger.info( * "accepted corpus with %i documents, %i features, %i non-zero entries", * self.num_docs, self.num_terms, self.num_nnz # <<<<<<<<<<<<<< * ) * */ - __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_docs); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 82, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); - __pyx_t_15 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_terms); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 82, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_docs); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 84, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); + __pyx_t_15 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_terms); if (unlikely(!__pyx_t_15)) __PYX_ERR(0, 84, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_15); - __pyx_t_14 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_nnz); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 82, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_nnz); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 84, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_14); __pyx_t_1 = NULL; __pyx_t_4 = 0; - if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_3))) { - __pyx_t_1 = PyMethod_GET_SELF(__pyx_t_3); + if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_2))) { + __pyx_t_1 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_1)) { - PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); + PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_1); __Pyx_INCREF(function); - __Pyx_DECREF_SET(__pyx_t_3, function); + __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #if CYTHON_FAST_PYCALL - if (PyFunction_Check(__pyx_t_3)) { - PyObject *__pyx_temp[5] = {__pyx_t_1, __pyx_kp_s_accepted_corpus_with_i_documents, __pyx_t_2, __pyx_t_15, __pyx_t_14}; - __pyx_t_5 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_4, 4+__pyx_t_4); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 80, __pyx_L1_error) + if (PyFunction_Check(__pyx_t_2)) { + PyObject *__pyx_temp[5] = {__pyx_t_1, __pyx_kp_s_accepted_corpus_with_i_documents, __pyx_t_3, __pyx_t_15, __pyx_t_14}; + __pyx_t_5 = __Pyx_PyFunction_FastCall(__pyx_t_2, __pyx_temp+1-__pyx_t_4, 4+__pyx_t_4); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_GOTREF(__pyx_t_5); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; } else #endif #if CYTHON_FAST_PYCCALL - if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { - PyObject *__pyx_temp[5] = {__pyx_t_1, __pyx_kp_s_accepted_corpus_with_i_documents, __pyx_t_2, __pyx_t_15, __pyx_t_14}; - __pyx_t_5 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_4, 4+__pyx_t_4); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 80, __pyx_L1_error) + if (__Pyx_PyFastCFunction_Check(__pyx_t_2)) { + PyObject *__pyx_temp[5] = {__pyx_t_1, __pyx_kp_s_accepted_corpus_with_i_documents, __pyx_t_3, __pyx_t_15, __pyx_t_14}; + __pyx_t_5 = __Pyx_PyCFunction_FastCall(__pyx_t_2, __pyx_temp+1-__pyx_t_4, 4+__pyx_t_4); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_GOTREF(__pyx_t_5); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_DECREF(__pyx_t_14); __pyx_t_14 = 0; } else #endif { - __pyx_t_19 = PyTuple_New(4+__pyx_t_4); if (unlikely(!__pyx_t_19)) __PYX_ERR(0, 80, __pyx_L1_error) + __pyx_t_19 = PyTuple_New(4+__pyx_t_4); if (unlikely(!__pyx_t_19)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_19); if (__pyx_t_1) { __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_19, 0, __pyx_t_1); __pyx_t_1 = NULL; @@ -2622,23 +2663,23 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ __Pyx_INCREF(__pyx_kp_s_accepted_corpus_with_i_documents); __Pyx_GIVEREF(__pyx_kp_s_accepted_corpus_with_i_documents); PyTuple_SET_ITEM(__pyx_t_19, 0+__pyx_t_4, __pyx_kp_s_accepted_corpus_with_i_documents); - __Pyx_GIVEREF(__pyx_t_2); - PyTuple_SET_ITEM(__pyx_t_19, 1+__pyx_t_4, __pyx_t_2); + __Pyx_GIVEREF(__pyx_t_3); + PyTuple_SET_ITEM(__pyx_t_19, 1+__pyx_t_4, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_15); PyTuple_SET_ITEM(__pyx_t_19, 2+__pyx_t_4, __pyx_t_15); __Pyx_GIVEREF(__pyx_t_14); PyTuple_SET_ITEM(__pyx_t_19, 3+__pyx_t_4, __pyx_t_14); - __pyx_t_2 = 0; + __pyx_t_3 = 0; __pyx_t_15 = 0; __pyx_t_14 = 0; - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_19, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 80, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_19, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_19); __pyx_t_19 = 0; } - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - /* "gensim/corpora/_mmreader.pyx":45 + /* "gensim/corpora/_mmreader.pyx":47 * cdef public long long num_docs, num_terms, num_nnz * * def __init__(self, input, transposed=True): # <<<<<<<<<<<<<< @@ -2668,17 +2709,17 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader___init__(struct __pyx_ return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":85 +/* "gensim/corpora/_mmreader.pyx":87 * ) * * def __len__(self): # <<<<<<<<<<<<<< - * """Get size of corpus (number of documents).""" + * """Get the corpus size: total number of documents.""" * return self.num_docs */ /* Python wrapper */ static Py_ssize_t __pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_3__len__(PyObject *__pyx_v_self); /*proto*/ -static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_2__len__[] = "Get size of corpus (number of documents)."; +static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_2__len__[] = "Get the corpus size: total number of documents."; #if CYTHON_COMPILING_IN_CPYTHON struct wrapperbase __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__; #endif @@ -2698,9 +2739,9 @@ static Py_ssize_t __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_2__len__(struct __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__len__", 0); - /* "gensim/corpora/_mmreader.pyx":87 + /* "gensim/corpora/_mmreader.pyx":89 * def __len__(self): - * """Get size of corpus (number of documents).""" + * """Get the corpus size: total number of documents.""" * return self.num_docs # <<<<<<<<<<<<<< * * def __str__(self): @@ -2708,11 +2749,11 @@ static Py_ssize_t __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_2__len__(struct __pyx_r = __pyx_v_self->num_docs; goto __pyx_L0; - /* "gensim/corpora/_mmreader.pyx":85 + /* "gensim/corpora/_mmreader.pyx":87 * ) * * def __len__(self): # <<<<<<<<<<<<<< - * """Get size of corpus (number of documents).""" + * """Get the corpus size: total number of documents.""" * return self.num_docs */ @@ -2722,7 +2763,7 @@ static Py_ssize_t __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_2__len__(struct return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":89 +/* "gensim/corpora/_mmreader.pyx":91 * return self.num_docs * * def __str__(self): # <<<<<<<<<<<<<< @@ -2752,7 +2793,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_4__str__(struct PyObject *__pyx_t_4 = NULL; __Pyx_RefNannySetupContext("__str__", 0); - /* "gensim/corpora/_mmreader.pyx":90 + /* "gensim/corpora/_mmreader.pyx":92 * * def __str__(self): * return ("MmCorpus(%i documents, %i features, %i non-zero entries)" % # <<<<<<<<<<<<<< @@ -2761,20 +2802,20 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_4__str__(struct */ __Pyx_XDECREF(__pyx_r); - /* "gensim/corpora/_mmreader.pyx":91 + /* "gensim/corpora/_mmreader.pyx":93 * def __str__(self): * return ("MmCorpus(%i documents, %i features, %i non-zero entries)" % * (self.num_docs, self.num_terms, self.num_nnz)) # <<<<<<<<<<<<<< * * def skip_headers(self, input_file): */ - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_docs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 91, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_docs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 93, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_terms); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 91, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_terms); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 93, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_nnz); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 91, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_nnz); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 93, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyTuple_New(3); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 91, __pyx_L1_error) + __pyx_t_4 = PyTuple_New(3); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 93, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_1); @@ -2786,21 +2827,21 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_4__str__(struct __pyx_t_2 = 0; __pyx_t_3 = 0; - /* "gensim/corpora/_mmreader.pyx":90 + /* "gensim/corpora/_mmreader.pyx":92 * * def __str__(self): * return ("MmCorpus(%i documents, %i features, %i non-zero entries)" % # <<<<<<<<<<<<<< * (self.num_docs, self.num_terms, self.num_nnz)) * */ - __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_MmCorpus_i_documents_i_features, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 90, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_MmCorpus_i_documents_i_features, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 92, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; - /* "gensim/corpora/_mmreader.pyx":89 + /* "gensim/corpora/_mmreader.pyx":91 * return self.num_docs * * def __str__(self): # <<<<<<<<<<<<<< @@ -2822,7 +2863,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_4__str__(struct return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":93 +/* "gensim/corpora/_mmreader.pyx":95 * (self.num_docs, self.num_terms, self.num_nnz)) * * def skip_headers(self, input_file): # <<<<<<<<<<<<<< @@ -2856,7 +2897,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY int __pyx_t_6; __Pyx_RefNannySetupContext("skip_headers", 0); - /* "gensim/corpora/_mmreader.pyx":102 + /* "gensim/corpora/_mmreader.pyx":104 * * """ * for line in input_file: # <<<<<<<<<<<<<< @@ -2867,26 +2908,26 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY __pyx_t_1 = __pyx_v_input_file; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; __pyx_t_3 = NULL; } else { - __pyx_t_2 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_input_file); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 102, __pyx_L1_error) + __pyx_t_2 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_input_file); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 104, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 102, __pyx_L1_error) + __pyx_t_3 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 104, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_3)) { if (likely(PyList_CheckExact(__pyx_t_1))) { if (__pyx_t_2 >= PyList_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_4 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(0, 102, __pyx_L1_error) + __pyx_t_4 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(0, 104, __pyx_L1_error) #else - __pyx_t_4 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 102, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 104, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_4 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(0, 102, __pyx_L1_error) + __pyx_t_4 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(0, 104, __pyx_L1_error) #else - __pyx_t_4 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 102, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 104, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } @@ -2896,7 +2937,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 102, __pyx_L1_error) + else __PYX_ERR(0, 104, __pyx_L1_error) } break; } @@ -2905,23 +2946,23 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY __Pyx_XDECREF_SET(__pyx_v_line, __pyx_t_4); __pyx_t_4 = 0; - /* "gensim/corpora/_mmreader.pyx":103 + /* "gensim/corpora/_mmreader.pyx":105 * """ * for line in input_file: * if line.startswith(b'%'): # <<<<<<<<<<<<<< * continue * break */ - __pyx_t_4 = __Pyx_PyObject_GetAttrStr(__pyx_v_line, __pyx_n_s_startswith); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 103, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_GetAttrStr(__pyx_v_line, __pyx_n_s_startswith); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 103, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_tuple__5, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_5); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 103, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_5); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; if (__pyx_t_6) { - /* "gensim/corpora/_mmreader.pyx":104 + /* "gensim/corpora/_mmreader.pyx":106 * for line in input_file: * if line.startswith(b'%'): * continue # <<<<<<<<<<<<<< @@ -2930,7 +2971,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY */ goto __pyx_L3_continue; - /* "gensim/corpora/_mmreader.pyx":103 + /* "gensim/corpora/_mmreader.pyx":105 * """ * for line in input_file: * if line.startswith(b'%'): # <<<<<<<<<<<<<< @@ -2939,7 +2980,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY */ } - /* "gensim/corpora/_mmreader.pyx":105 + /* "gensim/corpora/_mmreader.pyx":107 * if line.startswith(b'%'): * continue * break # <<<<<<<<<<<<<< @@ -2948,7 +2989,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY */ goto __pyx_L4_break; - /* "gensim/corpora/_mmreader.pyx":102 + /* "gensim/corpora/_mmreader.pyx":104 * * """ * for line in input_file: # <<<<<<<<<<<<<< @@ -2960,7 +3001,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY __pyx_L4_break:; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/corpora/_mmreader.pyx":93 + /* "gensim/corpora/_mmreader.pyx":95 * (self.num_docs, self.num_terms, self.num_nnz)) * * def skip_headers(self, input_file): # <<<<<<<<<<<<<< @@ -2985,17 +3026,17 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_6skip_headers(CY } static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__pyx_CoroutineObject *__pyx_generator, CYTHON_UNUSED PyThreadState *__pyx_tstate, PyObject *__pyx_sent_value); /* proto */ -/* "gensim/corpora/_mmreader.pyx":107 +/* "gensim/corpora/_mmreader.pyx":109 * break * * def __iter__(self): # <<<<<<<<<<<<<< - * """Iterate through corpus. + * """Iterate through all documents in the corpus. * */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_9__iter__(PyObject *__pyx_v_self); /*proto*/ -static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_8__iter__[] = "Iterate through corpus.\n\n Notes\n ------\n Note that the total number of vectors returned is always equal to the number of rows specified\n in the header, empty documents are inserted and yielded where appropriate, even if they are not explicitly\n stored in the Matrix Market file.\n\n Yields\n ------\n (int, list of (int, number))\n Document id and Document in BoW format\n\n "; +static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_8__iter__[] = "Iterate through all documents in the corpus.\n\n Notes\n ------\n Note that the total number of vectors returned is always equal to the number of rows specified\n in the header: empty documents are inserted and yielded where appropriate, even if they are not explicitly\n stored in the Matrix Market file.\n\n Yields\n ------\n (int, list of (int, number))\n Document id and document in sparse bag-of-words format.\n\n "; #if CYTHON_COMPILING_IN_CPYTHON struct wrapperbase __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__; #endif @@ -3019,7 +3060,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8__iter__(struct if (unlikely(!__pyx_cur_scope)) { __pyx_cur_scope = ((struct __pyx_obj_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__ *)Py_None); __Pyx_INCREF(Py_None); - __PYX_ERR(0, 107, __pyx_L1_error) + __PYX_ERR(0, 109, __pyx_L1_error) } else { __Pyx_GOTREF(__pyx_cur_scope); } @@ -3027,7 +3068,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8__iter__(struct __Pyx_INCREF((PyObject *)__pyx_cur_scope->__pyx_v_self); __Pyx_GIVEREF((PyObject *)__pyx_cur_scope->__pyx_v_self); { - __pyx_CoroutineObject *gen = __Pyx_Generator_New((__pyx_coroutine_body_t) __pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator, (PyObject *) __pyx_cur_scope, __pyx_n_s_iter, __pyx_n_s_MmReader___iter, __pyx_n_s_gensim_corpora__mmreader); if (unlikely(!gen)) __PYX_ERR(0, 107, __pyx_L1_error) + __pyx_CoroutineObject *gen = __Pyx_Generator_New((__pyx_coroutine_body_t) __pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator, NULL, (PyObject *) __pyx_cur_scope, __pyx_n_s_iter, __pyx_n_s_MmReader___iter, __pyx_n_s_gensim_corpora__mmreader); if (unlikely(!gen)) __PYX_ERR(0, 109, __pyx_L1_error) __Pyx_DECREF(__pyx_cur_scope); __Pyx_RefNannyFinishContext(); return (PyObject *) gen; @@ -3083,9 +3124,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py return NULL; } __pyx_L3_first_run:; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 107, __pyx_L1_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 109, __pyx_L1_error) - /* "gensim/corpora/_mmreader.pyx":123 + /* "gensim/corpora/_mmreader.pyx":125 * """ * cdef long long docid, termid, previd * cdef double val = 0 # <<<<<<<<<<<<<< @@ -3094,7 +3135,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ __pyx_cur_scope->__pyx_v_val = 0.0; - /* "gensim/corpora/_mmreader.pyx":125 + /* "gensim/corpora/_mmreader.pyx":127 * cdef double val = 0 * * with utils.file_or_filename(self.input) as lines: # <<<<<<<<<<<<<< @@ -3102,9 +3143,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py * */ /*with:*/ { - __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_file_or_filename); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_file_or_filename); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = NULL; @@ -3118,13 +3159,13 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py } } if (!__pyx_t_2) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_cur_scope->__pyx_v_self->input); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_cur_scope->__pyx_v_self->input); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[2] = {__pyx_t_2, __pyx_cur_scope->__pyx_v_self->input}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_GOTREF(__pyx_t_1); } else @@ -3132,27 +3173,27 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[2] = {__pyx_t_2, __pyx_cur_scope->__pyx_v_self->input}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_GOTREF(__pyx_t_1); } else #endif { - __pyx_t_4 = PyTuple_New(1+1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_4 = PyTuple_New(1+1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_2); __pyx_t_2 = NULL; __Pyx_INCREF(__pyx_cur_scope->__pyx_v_self->input); __Pyx_GIVEREF(__pyx_cur_scope->__pyx_v_self->input); PyTuple_SET_ITEM(__pyx_t_4, 0+1, __pyx_cur_scope->__pyx_v_self->input); - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_4, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_4, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; } } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_5 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_exit); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_exit); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); - __pyx_t_4 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_enter); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 125, __pyx_L4_error) + __pyx_t_4 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_enter); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 127, __pyx_L4_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_2 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_4))) { @@ -3165,10 +3206,10 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py } } if (__pyx_t_2) { - __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_4, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 125, __pyx_L4_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_4, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 127, __pyx_L4_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } else { - __pyx_t_3 = __Pyx_PyObject_CallNoArg(__pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 125, __pyx_L4_error) + __pyx_t_3 = __Pyx_PyObject_CallNoArg(__pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 127, __pyx_L4_error) } __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; @@ -3186,14 +3227,14 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_cur_scope->__pyx_v_lines = __pyx_t_4; __pyx_t_4 = 0; - /* "gensim/corpora/_mmreader.pyx":126 + /* "gensim/corpora/_mmreader.pyx":128 * * with utils.file_or_filename(self.input) as lines: * self.skip_headers(lines) # <<<<<<<<<<<<<< * * previd = -1 */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_cur_scope->__pyx_v_self), __pyx_n_s_skip_headers); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 126, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_cur_scope->__pyx_v_self), __pyx_n_s_skip_headers); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 128, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_3 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_1))) { @@ -3206,13 +3247,13 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py } } if (!__pyx_t_3) { - __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_t_1, __pyx_cur_scope->__pyx_v_lines); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 126, __pyx_L8_error) + __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_t_1, __pyx_cur_scope->__pyx_v_lines); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 128, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_4); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_1)) { PyObject *__pyx_temp[2] = {__pyx_t_3, __pyx_cur_scope->__pyx_v_lines}; - __pyx_t_4 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 126, __pyx_L8_error) + __pyx_t_4 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 128, __pyx_L8_error) __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_4); } else @@ -3220,19 +3261,19 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_1)) { PyObject *__pyx_temp[2] = {__pyx_t_3, __pyx_cur_scope->__pyx_v_lines}; - __pyx_t_4 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 126, __pyx_L8_error) + __pyx_t_4 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 128, __pyx_L8_error) __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_4); } else #endif { - __pyx_t_2 = PyTuple_New(1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 126, __pyx_L8_error) + __pyx_t_2 = PyTuple_New(1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 128, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_3); __pyx_t_3 = NULL; __Pyx_INCREF(__pyx_cur_scope->__pyx_v_lines); __Pyx_GIVEREF(__pyx_cur_scope->__pyx_v_lines); PyTuple_SET_ITEM(__pyx_t_2, 0+1, __pyx_cur_scope->__pyx_v_lines); - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_2, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 126, __pyx_L8_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_2, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 128, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } @@ -3240,7 +3281,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - /* "gensim/corpora/_mmreader.pyx":128 + /* "gensim/corpora/_mmreader.pyx":130 * self.skip_headers(lines) * * previd = -1 # <<<<<<<<<<<<<< @@ -3249,7 +3290,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ __pyx_cur_scope->__pyx_v_previd = -1LL; - /* "gensim/corpora/_mmreader.pyx":129 + /* "gensim/corpora/_mmreader.pyx":131 * * previd = -1 * for line in lines: # <<<<<<<<<<<<<< @@ -3260,26 +3301,26 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_4 = __pyx_cur_scope->__pyx_v_lines; __Pyx_INCREF(__pyx_t_4); __pyx_t_9 = 0; __pyx_t_10 = NULL; } else { - __pyx_t_9 = -1; __pyx_t_4 = PyObject_GetIter(__pyx_cur_scope->__pyx_v_lines); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 129, __pyx_L8_error) + __pyx_t_9 = -1; __pyx_t_4 = PyObject_GetIter(__pyx_cur_scope->__pyx_v_lines); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 131, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_10 = Py_TYPE(__pyx_t_4)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 129, __pyx_L8_error) + __pyx_t_10 = Py_TYPE(__pyx_t_4)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 131, __pyx_L8_error) } for (;;) { if (likely(!__pyx_t_10)) { if (likely(PyList_CheckExact(__pyx_t_4))) { if (__pyx_t_9 >= PyList_GET_SIZE(__pyx_t_4)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyList_GET_ITEM(__pyx_t_4, __pyx_t_9); __Pyx_INCREF(__pyx_t_1); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 129, __pyx_L8_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_4, __pyx_t_9); __Pyx_INCREF(__pyx_t_1); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 131, __pyx_L8_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_4, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 129, __pyx_L8_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_4, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 131, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { if (__pyx_t_9 >= PyTuple_GET_SIZE(__pyx_t_4)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_4, __pyx_t_9); __Pyx_INCREF(__pyx_t_1); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 129, __pyx_L8_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_4, __pyx_t_9); __Pyx_INCREF(__pyx_t_1); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 131, __pyx_L8_error) #else - __pyx_t_1 = PySequence_ITEM(__pyx_t_4, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 129, __pyx_L8_error) + __pyx_t_1 = PySequence_ITEM(__pyx_t_4, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 131, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_1); #endif } @@ -3289,7 +3330,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 129, __pyx_L8_error) + else __PYX_ERR(0, 131, __pyx_L8_error) } break; } @@ -3300,25 +3341,25 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __Pyx_GIVEREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/corpora/_mmreader.pyx":131 + /* "gensim/corpora/_mmreader.pyx":133 * for line in lines: * * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): # <<<<<<<<<<<<<< * raise ValueError("unable to parse line: {}".format(line)) * */ - __pyx_t_11 = __Pyx_PyObject_AsString(__pyx_cur_scope->__pyx_v_line); if (unlikely((!__pyx_t_11) && PyErr_Occurred())) __PYX_ERR(0, 131, __pyx_L8_error) + __pyx_t_11 = __Pyx_PyObject_AsString(__pyx_cur_scope->__pyx_v_line); if (unlikely((!__pyx_t_11) && PyErr_Occurred())) __PYX_ERR(0, 133, __pyx_L8_error) __pyx_t_12 = ((sscanf(__pyx_t_11, ((char const *)"%lld %lld %lg"), (&__pyx_cur_scope->__pyx_v_docid), (&__pyx_cur_scope->__pyx_v_termid), (&__pyx_cur_scope->__pyx_v_val)) != 3) != 0); - if (__pyx_t_12) { + if (unlikely(__pyx_t_12)) { - /* "gensim/corpora/_mmreader.pyx":132 + /* "gensim/corpora/_mmreader.pyx":134 * * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): * raise ValueError("unable to parse line: {}".format(line)) # <<<<<<<<<<<<<< * * if not self.transposed: */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_kp_s_unable_to_parse_line, __pyx_n_s_format); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_kp_s_unable_to_parse_line, __pyx_n_s_format); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_2))) { @@ -3331,13 +3372,13 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py } } if (!__pyx_t_3) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_cur_scope->__pyx_v_line); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_2, __pyx_cur_scope->__pyx_v_line); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_1); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_2)) { PyObject *__pyx_temp[2] = {__pyx_t_3, __pyx_cur_scope->__pyx_v_line}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_2, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_2, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_1); } else @@ -3345,37 +3386,32 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_2)) { PyObject *__pyx_temp[2] = {__pyx_t_3, __pyx_cur_scope->__pyx_v_line}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_2, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_2, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_1); } else #endif { - __pyx_t_13 = PyTuple_New(1+1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_13 = PyTuple_New(1+1); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_13); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_13, 0, __pyx_t_3); __pyx_t_3 = NULL; __Pyx_INCREF(__pyx_cur_scope->__pyx_v_line); __Pyx_GIVEREF(__pyx_cur_scope->__pyx_v_line); PyTuple_SET_ITEM(__pyx_t_13, 0+1, __pyx_cur_scope->__pyx_v_line); - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_13, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_13, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; } } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = PyTuple_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 132, __pyx_L8_error) + __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 134, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_2); - __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_1); - __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_2, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 132, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __PYX_ERR(0, 132, __pyx_L8_error) + __Pyx_Raise(__pyx_t_2, 0, 0, 0); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __PYX_ERR(0, 134, __pyx_L8_error) - /* "gensim/corpora/_mmreader.pyx":131 + /* "gensim/corpora/_mmreader.pyx":133 * for line in lines: * * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): # <<<<<<<<<<<<<< @@ -3384,7 +3420,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ } - /* "gensim/corpora/_mmreader.pyx":134 + /* "gensim/corpora/_mmreader.pyx":136 * raise ValueError("unable to parse line: {}".format(line)) * * if not self.transposed: # <<<<<<<<<<<<<< @@ -3394,7 +3430,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_12 = ((!(__pyx_cur_scope->__pyx_v_self->transposed != 0)) != 0); if (__pyx_t_12) { - /* "gensim/corpora/_mmreader.pyx":135 + /* "gensim/corpora/_mmreader.pyx":137 * * if not self.transposed: * termid, docid = docid, termid # <<<<<<<<<<<<<< @@ -3406,7 +3442,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_cur_scope->__pyx_v_termid = __pyx_t_14; __pyx_cur_scope->__pyx_v_docid = __pyx_t_15; - /* "gensim/corpora/_mmreader.pyx":134 + /* "gensim/corpora/_mmreader.pyx":136 * raise ValueError("unable to parse line: {}".format(line)) * * if not self.transposed: # <<<<<<<<<<<<<< @@ -3415,7 +3451,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ } - /* "gensim/corpora/_mmreader.pyx":138 + /* "gensim/corpora/_mmreader.pyx":140 * * # -1 because matrix market indexes are 1-based => convert to 0-based * docid -= 1 # <<<<<<<<<<<<<< @@ -3424,7 +3460,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ __pyx_cur_scope->__pyx_v_docid = (__pyx_cur_scope->__pyx_v_docid - 1); - /* "gensim/corpora/_mmreader.pyx":139 + /* "gensim/corpora/_mmreader.pyx":141 * # -1 because matrix market indexes are 1-based => convert to 0-based * docid -= 1 * termid -= 1 # <<<<<<<<<<<<<< @@ -3433,7 +3469,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ __pyx_cur_scope->__pyx_v_termid = (__pyx_cur_scope->__pyx_v_termid - 1); - /* "gensim/corpora/_mmreader.pyx":141 + /* "gensim/corpora/_mmreader.pyx":143 * termid -= 1 * * assert previd <= docid, "matrix columns must come in ascending order" # <<<<<<<<<<<<<< @@ -3444,12 +3480,12 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py if (unlikely(!Py_OptimizeFlag)) { if (unlikely(!((__pyx_cur_scope->__pyx_v_previd <= __pyx_cur_scope->__pyx_v_docid) != 0))) { PyErr_SetObject(PyExc_AssertionError, __pyx_kp_s_matrix_columns_must_come_in_asce); - __PYX_ERR(0, 141, __pyx_L8_error) + __PYX_ERR(0, 143, __pyx_L8_error) } } #endif - /* "gensim/corpora/_mmreader.pyx":142 + /* "gensim/corpora/_mmreader.pyx":144 * * assert previd <= docid, "matrix columns must come in ascending order" * if docid != previd: # <<<<<<<<<<<<<< @@ -3459,7 +3495,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_12 = ((__pyx_cur_scope->__pyx_v_docid != __pyx_cur_scope->__pyx_v_previd) != 0); if (__pyx_t_12) { - /* "gensim/corpora/_mmreader.pyx":144 + /* "gensim/corpora/_mmreader.pyx":146 * if docid != previd: * # change of document: return the document read so far (its id is prevId) * if previd >= 0: # <<<<<<<<<<<<<< @@ -3469,26 +3505,26 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_12 = ((__pyx_cur_scope->__pyx_v_previd >= 0) != 0); if (__pyx_t_12) { - /* "gensim/corpora/_mmreader.pyx":145 + /* "gensim/corpora/_mmreader.pyx":147 * # change of document: return the document read so far (its id is prevId) * if previd >= 0: * yield previd, document # noqa:F821 # <<<<<<<<<<<<<< * * # return implicit (empty) documents between previous id and new id */ - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 145, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_1); - if (unlikely(!__pyx_cur_scope->__pyx_v_document)) { __Pyx_RaiseUnboundLocalError("document"); __PYX_ERR(0, 145, __pyx_L8_error) } - __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 145, __pyx_L8_error) + __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 147, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_2); - __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_1); + if (unlikely(!__pyx_cur_scope->__pyx_v_document)) { __Pyx_RaiseUnboundLocalError("document"); __PYX_ERR(0, 147, __pyx_L8_error) } + __pyx_t_1 = PyTuple_New(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 147, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_GIVEREF(__pyx_t_2); + PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_2); __Pyx_INCREF(__pyx_cur_scope->__pyx_v_document); __Pyx_GIVEREF(__pyx_cur_scope->__pyx_v_document); - PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_cur_scope->__pyx_v_document); - __pyx_t_1 = 0; - __pyx_r = __pyx_t_2; + PyTuple_SET_ITEM(__pyx_t_1, 1, __pyx_cur_scope->__pyx_v_document); __pyx_t_2 = 0; + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; __Pyx_XGIVEREF(__pyx_t_4); __pyx_cur_scope->__pyx_t_0 = __pyx_t_4; __Pyx_XGIVEREF(__pyx_t_5); @@ -3525,9 +3561,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __Pyx_XGOTREF(__pyx_t_8); __pyx_t_9 = __pyx_cur_scope->__pyx_t_5; __pyx_t_10 = __pyx_cur_scope->__pyx_t_6; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 145, __pyx_L8_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 147, __pyx_L8_error) - /* "gensim/corpora/_mmreader.pyx":144 + /* "gensim/corpora/_mmreader.pyx":146 * if docid != previd: * # change of document: return the document read so far (its id is prevId) * if previd >= 0: # <<<<<<<<<<<<<< @@ -3536,53 +3572,53 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ } - /* "gensim/corpora/_mmreader.pyx":149 + /* "gensim/corpora/_mmreader.pyx":151 * # return implicit (empty) documents between previous id and new id * # too, to keep consistent document numbering and corpus length * for previd in xrange(previd + 1, docid): # <<<<<<<<<<<<<< * yield previd, [] * */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_xrange); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 149, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_13 = __Pyx_PyInt_From_PY_LONG_LONG((__pyx_cur_scope->__pyx_v_previd + 1)); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_xrange); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 151, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_13 = __Pyx_PyInt_From_PY_LONG_LONG((__pyx_cur_scope->__pyx_v_previd + 1)); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 151, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_docid); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_docid); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 151, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_16 = NULL; __pyx_t_17 = 0; - if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_1))) { - __pyx_t_16 = PyMethod_GET_SELF(__pyx_t_1); + if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_2))) { + __pyx_t_16 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_16)) { - PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_1); + PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_16); __Pyx_INCREF(function); - __Pyx_DECREF_SET(__pyx_t_1, function); + __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_17 = 1; } } #if CYTHON_FAST_PYCALL - if (PyFunction_Check(__pyx_t_1)) { + if (PyFunction_Check(__pyx_t_2)) { PyObject *__pyx_temp[3] = {__pyx_t_16, __pyx_t_13, __pyx_t_3}; - __pyx_t_2 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_2, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 151, __pyx_L8_error) __Pyx_XDECREF(__pyx_t_16); __pyx_t_16 = 0; - __Pyx_GOTREF(__pyx_t_2); + __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else #endif #if CYTHON_FAST_PYCCALL - if (__Pyx_PyFastCFunction_Check(__pyx_t_1)) { + if (__Pyx_PyFastCFunction_Check(__pyx_t_2)) { PyObject *__pyx_temp[3] = {__pyx_t_16, __pyx_t_13, __pyx_t_3}; - __pyx_t_2 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_2, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 151, __pyx_L8_error) __Pyx_XDECREF(__pyx_t_16); __pyx_t_16 = 0; - __Pyx_GOTREF(__pyx_t_2); + __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else #endif { - __pyx_t_18 = PyTuple_New(2+__pyx_t_17); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_18 = PyTuple_New(2+__pyx_t_17); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 151, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_18); if (__pyx_t_16) { __Pyx_GIVEREF(__pyx_t_16); PyTuple_SET_ITEM(__pyx_t_18, 0, __pyx_t_16); __pyx_t_16 = NULL; @@ -3593,78 +3629,78 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py PyTuple_SET_ITEM(__pyx_t_18, 1+__pyx_t_17, __pyx_t_3); __pyx_t_13 = 0; __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_18, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 149, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_2); + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_18, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 151, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_18); __pyx_t_18 = 0; } - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (likely(PyList_CheckExact(__pyx_t_2)) || PyTuple_CheckExact(__pyx_t_2)) { - __pyx_t_1 = __pyx_t_2; __Pyx_INCREF(__pyx_t_1); __pyx_t_19 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + if (likely(PyList_CheckExact(__pyx_t_1)) || PyTuple_CheckExact(__pyx_t_1)) { + __pyx_t_2 = __pyx_t_1; __Pyx_INCREF(__pyx_t_2); __pyx_t_19 = 0; __pyx_t_20 = NULL; } else { - __pyx_t_19 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_t_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 149, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_20 = Py_TYPE(__pyx_t_1)->tp_iternext; if (unlikely(!__pyx_t_20)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_19 = -1; __pyx_t_2 = PyObject_GetIter(__pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 151, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_20 = Py_TYPE(__pyx_t_2)->tp_iternext; if (unlikely(!__pyx_t_20)) __PYX_ERR(0, 151, __pyx_L8_error) } - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; for (;;) { if (likely(!__pyx_t_20)) { - if (likely(PyList_CheckExact(__pyx_t_1))) { - if (__pyx_t_19 >= PyList_GET_SIZE(__pyx_t_1)) break; + if (likely(PyList_CheckExact(__pyx_t_2))) { + if (__pyx_t_19 >= PyList_GET_SIZE(__pyx_t_2)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_2 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_19); __Pyx_INCREF(__pyx_t_2); __pyx_t_19++; if (unlikely(0 < 0)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_1 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_19); __Pyx_INCREF(__pyx_t_1); __pyx_t_19++; if (unlikely(0 < 0)) __PYX_ERR(0, 151, __pyx_L8_error) #else - __pyx_t_2 = PySequence_ITEM(__pyx_t_1, __pyx_t_19); __pyx_t_19++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 149, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_2); + __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_19); __pyx_t_19++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 151, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_1); #endif } else { - if (__pyx_t_19 >= PyTuple_GET_SIZE(__pyx_t_1)) break; + if (__pyx_t_19 >= PyTuple_GET_SIZE(__pyx_t_2)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_19); __Pyx_INCREF(__pyx_t_2); __pyx_t_19++; if (unlikely(0 < 0)) __PYX_ERR(0, 149, __pyx_L8_error) + __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_2, __pyx_t_19); __Pyx_INCREF(__pyx_t_1); __pyx_t_19++; if (unlikely(0 < 0)) __PYX_ERR(0, 151, __pyx_L8_error) #else - __pyx_t_2 = PySequence_ITEM(__pyx_t_1, __pyx_t_19); __pyx_t_19++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 149, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_2); + __pyx_t_1 = PySequence_ITEM(__pyx_t_2, __pyx_t_19); __pyx_t_19++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 151, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_1); #endif } } else { - __pyx_t_2 = __pyx_t_20(__pyx_t_1); - if (unlikely(!__pyx_t_2)) { + __pyx_t_1 = __pyx_t_20(__pyx_t_2); + if (unlikely(!__pyx_t_1)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 149, __pyx_L8_error) + else __PYX_ERR(0, 151, __pyx_L8_error) } break; } - __Pyx_GOTREF(__pyx_t_2); + __Pyx_GOTREF(__pyx_t_1); } - __pyx_t_15 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_2); if (unlikely((__pyx_t_15 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 149, __pyx_L8_error) - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __pyx_t_15 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_1); if (unlikely((__pyx_t_15 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 151, __pyx_L8_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_cur_scope->__pyx_v_previd = __pyx_t_15; - /* "gensim/corpora/_mmreader.pyx":150 + /* "gensim/corpora/_mmreader.pyx":152 * # too, to keep consistent document numbering and corpus length * for previd in xrange(previd + 1, docid): * yield previd, [] # <<<<<<<<<<<<<< * * # from now on start adding fields to a new document, with a new id */ - __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 150, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_2); - __pyx_t_18 = PyList_New(0); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 150, __pyx_L8_error) + __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 152, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_t_18 = PyList_New(0); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 152, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_18); - __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 150, __pyx_L8_error) + __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 152, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_GIVEREF(__pyx_t_2); - PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_2); + __Pyx_GIVEREF(__pyx_t_1); + PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1); __Pyx_GIVEREF(__pyx_t_18); PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_t_18); - __pyx_t_2 = 0; + __pyx_t_1 = 0; __pyx_t_18 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; - __Pyx_XGIVEREF(__pyx_t_1); - __pyx_cur_scope->__pyx_t_0 = __pyx_t_1; + __Pyx_XGIVEREF(__pyx_t_2); + __pyx_cur_scope->__pyx_t_0 = __pyx_t_2; __Pyx_XGIVEREF(__pyx_t_4); __pyx_cur_scope->__pyx_t_1 = __pyx_t_4; __Pyx_XGIVEREF(__pyx_t_5); @@ -3686,9 +3722,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_generator->resume_label = 2; return __pyx_r; __pyx_L23_resume_from_yield:; - __pyx_t_1 = __pyx_cur_scope->__pyx_t_0; + __pyx_t_2 = __pyx_cur_scope->__pyx_t_0; __pyx_cur_scope->__pyx_t_0 = 0; - __Pyx_XGOTREF(__pyx_t_1); + __Pyx_XGOTREF(__pyx_t_2); __pyx_t_4 = __pyx_cur_scope->__pyx_t_1; __pyx_cur_scope->__pyx_t_1 = 0; __Pyx_XGOTREF(__pyx_t_4); @@ -3708,9 +3744,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_10 = __pyx_cur_scope->__pyx_t_6; __pyx_t_19 = __pyx_cur_scope->__pyx_t_8; __pyx_t_20 = __pyx_cur_scope->__pyx_t_9; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 150, __pyx_L8_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 152, __pyx_L8_error) - /* "gensim/corpora/_mmreader.pyx":149 + /* "gensim/corpora/_mmreader.pyx":151 * # return implicit (empty) documents between previous id and new id * # too, to keep consistent document numbering and corpus length * for previd in xrange(previd + 1, docid): # <<<<<<<<<<<<<< @@ -3718,9 +3754,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py * */ } - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":153 + /* "gensim/corpora/_mmreader.pyx":155 * * # from now on start adding fields to a new document, with a new id * previd = docid # <<<<<<<<<<<<<< @@ -3729,21 +3765,21 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ __pyx_cur_scope->__pyx_v_previd = __pyx_cur_scope->__pyx_v_docid; - /* "gensim/corpora/_mmreader.pyx":154 + /* "gensim/corpora/_mmreader.pyx":156 * # from now on start adding fields to a new document, with a new id * previd = docid * document = [] # <<<<<<<<<<<<<< * * document.append((termid, val,)) # add another field to the current document */ - __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 154, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_1); + __pyx_t_2 = PyList_New(0); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 156, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_2); __Pyx_XGOTREF(__pyx_cur_scope->__pyx_v_document); - __Pyx_XDECREF_SET(__pyx_cur_scope->__pyx_v_document, ((PyObject*)__pyx_t_1)); - __Pyx_GIVEREF(__pyx_t_1); - __pyx_t_1 = 0; + __Pyx_XDECREF_SET(__pyx_cur_scope->__pyx_v_document, ((PyObject*)__pyx_t_2)); + __Pyx_GIVEREF(__pyx_t_2); + __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":142 + /* "gensim/corpora/_mmreader.pyx":144 * * assert previd <= docid, "matrix columns must come in ascending order" * if docid != previd: # <<<<<<<<<<<<<< @@ -3752,30 +3788,30 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ } - /* "gensim/corpora/_mmreader.pyx":156 + /* "gensim/corpora/_mmreader.pyx":158 * document = [] * * document.append((termid, val,)) # add another field to the current document # <<<<<<<<<<<<<< * * # handle the last document, as a special case */ - if (unlikely(!__pyx_cur_scope->__pyx_v_document)) { __Pyx_RaiseUnboundLocalError("document"); __PYX_ERR(0, 156, __pyx_L8_error) } - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_termid); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 156, __pyx_L8_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = PyFloat_FromDouble(__pyx_cur_scope->__pyx_v_val); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 156, __pyx_L8_error) + if (unlikely(!__pyx_cur_scope->__pyx_v_document)) { __Pyx_RaiseUnboundLocalError("document"); __PYX_ERR(0, 158, __pyx_L8_error) } + __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_termid); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 158, __pyx_L8_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_3 = PyFloat_FromDouble(__pyx_cur_scope->__pyx_v_val); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 158, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_18 = PyTuple_New(2); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 156, __pyx_L8_error) + __pyx_t_18 = PyTuple_New(2); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 158, __pyx_L8_error) __Pyx_GOTREF(__pyx_t_18); - __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_18, 0, __pyx_t_1); + __Pyx_GIVEREF(__pyx_t_2); + PyTuple_SET_ITEM(__pyx_t_18, 0, __pyx_t_2); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_18, 1, __pyx_t_3); - __pyx_t_1 = 0; + __pyx_t_2 = 0; __pyx_t_3 = 0; - __pyx_t_21 = __Pyx_PyList_Append(__pyx_cur_scope->__pyx_v_document, __pyx_t_18); if (unlikely(__pyx_t_21 == ((int)-1))) __PYX_ERR(0, 156, __pyx_L8_error) + __pyx_t_21 = __Pyx_PyList_Append(__pyx_cur_scope->__pyx_v_document, __pyx_t_18); if (unlikely(__pyx_t_21 == ((int)-1))) __PYX_ERR(0, 158, __pyx_L8_error) __Pyx_DECREF(__pyx_t_18); __pyx_t_18 = 0; - /* "gensim/corpora/_mmreader.pyx":129 + /* "gensim/corpora/_mmreader.pyx":131 * * previd = -1 * for line in lines: # <<<<<<<<<<<<<< @@ -3785,7 +3821,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py } __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - /* "gensim/corpora/_mmreader.pyx":125 + /* "gensim/corpora/_mmreader.pyx":127 * cdef double val = 0 * * with utils.file_or_filename(self.input) as lines: # <<<<<<<<<<<<<< @@ -3800,27 +3836,27 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_L8_error:; __Pyx_XDECREF(__pyx_t_16); __pyx_t_16 = 0; __Pyx_XDECREF(__pyx_t_13); __pyx_t_13 = 0; - __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_t_18); __pyx_t_18 = 0; __Pyx_XDECREF(__pyx_t_4); __pyx_t_4 = 0; /*except:*/ { __Pyx_AddTraceback("gensim.corpora._mmreader.MmReader.__iter__", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_4, &__pyx_t_18, &__pyx_t_3) < 0) __PYX_ERR(0, 125, __pyx_L10_except_error) + if (__Pyx_GetException(&__pyx_t_4, &__pyx_t_18, &__pyx_t_3) < 0) __PYX_ERR(0, 127, __pyx_L10_except_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_GOTREF(__pyx_t_18); __Pyx_GOTREF(__pyx_t_3); - __pyx_t_1 = PyTuple_Pack(3, __pyx_t_4, __pyx_t_18, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 125, __pyx_L10_except_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_22 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_1, NULL); + __pyx_t_2 = PyTuple_Pack(3, __pyx_t_4, __pyx_t_18, __pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 127, __pyx_L10_except_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_22 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_2, NULL); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - if (unlikely(!__pyx_t_22)) __PYX_ERR(0, 125, __pyx_L10_except_error) + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + if (unlikely(!__pyx_t_22)) __PYX_ERR(0, 127, __pyx_L10_except_error) __Pyx_GOTREF(__pyx_t_22); __pyx_t_12 = __Pyx_PyObject_IsTrue(__pyx_t_22); __Pyx_DECREF(__pyx_t_22); __pyx_t_22 = 0; - if (__pyx_t_12 < 0) __PYX_ERR(0, 125, __pyx_L10_except_error) + if (__pyx_t_12 < 0) __PYX_ERR(0, 127, __pyx_L10_except_error) __pyx_t_23 = ((!(__pyx_t_12 != 0)) != 0); if (__pyx_t_23) { __Pyx_GIVEREF(__pyx_t_4); @@ -3828,7 +3864,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __Pyx_XGIVEREF(__pyx_t_3); __Pyx_ErrRestoreWithState(__pyx_t_4, __pyx_t_18, __pyx_t_3); __pyx_t_4 = 0; __pyx_t_18 = 0; __pyx_t_3 = 0; - __PYX_ERR(0, 125, __pyx_L10_except_error) + __PYX_ERR(0, 127, __pyx_L10_except_error) } __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_DECREF(__pyx_t_18); __pyx_t_18 = 0; @@ -3854,7 +3890,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py if (__pyx_t_5) { __pyx_t_8 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_tuple__6, NULL); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 125, __pyx_L1_error) + if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; } @@ -3869,7 +3905,7 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_L27:; } - /* "gensim/corpora/_mmreader.pyx":159 + /* "gensim/corpora/_mmreader.pyx":161 * * # handle the last document, as a special case * if previd >= 0: # <<<<<<<<<<<<<< @@ -3879,17 +3915,17 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_23 = ((__pyx_cur_scope->__pyx_v_previd >= 0) != 0); if (__pyx_t_23) { - /* "gensim/corpora/_mmreader.pyx":160 + /* "gensim/corpora/_mmreader.pyx":162 * # handle the last document, as a special case * if previd >= 0: * yield previd, document # <<<<<<<<<<<<<< * * # return empty documents between the last explicit document and the number */ - __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 160, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 162, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (unlikely(!__pyx_cur_scope->__pyx_v_document)) { __Pyx_RaiseUnboundLocalError("document"); __PYX_ERR(0, 160, __pyx_L1_error) } - __pyx_t_18 = PyTuple_New(2); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 160, __pyx_L1_error) + if (unlikely(!__pyx_cur_scope->__pyx_v_document)) { __Pyx_RaiseUnboundLocalError("document"); __PYX_ERR(0, 162, __pyx_L1_error) } + __pyx_t_18 = PyTuple_New(2); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 162, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_18); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_18, 0, __pyx_t_3); @@ -3906,9 +3942,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_generator->resume_label = 3; return __pyx_r; __pyx_L29_resume_from_yield:; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 160, __pyx_L1_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 162, __pyx_L1_error) - /* "gensim/corpora/_mmreader.pyx":159 + /* "gensim/corpora/_mmreader.pyx":161 * * # handle the last document, as a special case * if previd >= 0: # <<<<<<<<<<<<<< @@ -3917,26 +3953,26 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py */ } - /* "gensim/corpora/_mmreader.pyx":164 + /* "gensim/corpora/_mmreader.pyx":166 * # return empty documents between the last explicit document and the number * # of documents as specified in the header * for previd in xrange(previd + 1, self.num_docs): # <<<<<<<<<<<<<< * yield previd, [] * */ - __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_xrange); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_xrange); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = __Pyx_PyInt_From_PY_LONG_LONG((__pyx_cur_scope->__pyx_v_previd + 1)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_PY_LONG_LONG((__pyx_cur_scope->__pyx_v_previd + 1)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_self->num_docs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 164, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = NULL; + __pyx_t_2 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_self->num_docs); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 166, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_1 = NULL; __pyx_t_17 = 0; if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_3))) { - __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_3); - if (likely(__pyx_t_2)) { + __pyx_t_1 = PyMethod_GET_SELF(__pyx_t_3); + if (likely(__pyx_t_1)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); - __Pyx_INCREF(__pyx_t_2); + __Pyx_INCREF(__pyx_t_1); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_17 = 1; @@ -3944,37 +3980,37 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py } #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_3)) { - PyObject *__pyx_temp[3] = {__pyx_t_2, __pyx_t_4, __pyx_t_1}; - __pyx_t_18 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 164, __pyx_L1_error) - __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + PyObject *__pyx_temp[3] = {__pyx_t_1, __pyx_t_4, __pyx_t_2}; + __pyx_t_18 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 166, __pyx_L1_error) + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_GOTREF(__pyx_t_18); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } else #endif #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { - PyObject *__pyx_temp[3] = {__pyx_t_2, __pyx_t_4, __pyx_t_1}; - __pyx_t_18 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 164, __pyx_L1_error) - __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; + PyObject *__pyx_temp[3] = {__pyx_t_1, __pyx_t_4, __pyx_t_2}; + __pyx_t_18 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-__pyx_t_17, 2+__pyx_t_17); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 166, __pyx_L1_error) + __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_GOTREF(__pyx_t_18); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } else #endif { - __pyx_t_13 = PyTuple_New(2+__pyx_t_17); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_13 = PyTuple_New(2+__pyx_t_17); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - if (__pyx_t_2) { - __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_13, 0, __pyx_t_2); __pyx_t_2 = NULL; + if (__pyx_t_1) { + __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_13, 0, __pyx_t_1); __pyx_t_1 = NULL; } __Pyx_GIVEREF(__pyx_t_4); PyTuple_SET_ITEM(__pyx_t_13, 0+__pyx_t_17, __pyx_t_4); - __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_13, 1+__pyx_t_17, __pyx_t_1); + __Pyx_GIVEREF(__pyx_t_2); + PyTuple_SET_ITEM(__pyx_t_13, 1+__pyx_t_17, __pyx_t_2); __pyx_t_4 = 0; - __pyx_t_1 = 0; - __pyx_t_18 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_13, NULL); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_2 = 0; + __pyx_t_18 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_13, NULL); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_18); __Pyx_DECREF(__pyx_t_13); __pyx_t_13 = 0; } @@ -3983,9 +4019,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __pyx_t_3 = __pyx_t_18; __Pyx_INCREF(__pyx_t_3); __pyx_t_9 = 0; __pyx_t_10 = NULL; } else { - __pyx_t_9 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_18); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_9 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_18); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_10 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 166, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_18); __pyx_t_18 = 0; for (;;) { @@ -3993,17 +4029,17 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_9 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_18 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_9); __Pyx_INCREF(__pyx_t_18); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_18 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_9); __Pyx_INCREF(__pyx_t_18); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 166, __pyx_L1_error) #else - __pyx_t_18 = PySequence_ITEM(__pyx_t_3, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_18 = PySequence_ITEM(__pyx_t_3, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_18); #endif } else { if (__pyx_t_9 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_18 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_9); __Pyx_INCREF(__pyx_t_18); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_18 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_9); __Pyx_INCREF(__pyx_t_18); __pyx_t_9++; if (unlikely(0 < 0)) __PYX_ERR(0, 166, __pyx_L1_error) #else - __pyx_t_18 = PySequence_ITEM(__pyx_t_3, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_18 = PySequence_ITEM(__pyx_t_3, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_18); #endif } @@ -4013,37 +4049,37 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 164, __pyx_L1_error) + else __PYX_ERR(0, 166, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_18); } - __pyx_t_15 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_18); if (unlikely((__pyx_t_15 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_t_15 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_t_18); if (unlikely((__pyx_t_15 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 166, __pyx_L1_error) __Pyx_DECREF(__pyx_t_18); __pyx_t_18 = 0; __pyx_cur_scope->__pyx_v_previd = __pyx_t_15; - /* "gensim/corpora/_mmreader.pyx":165 + /* "gensim/corpora/_mmreader.pyx":167 * # of documents as specified in the header * for previd in xrange(previd + 1, self.num_docs): * yield previd, [] # <<<<<<<<<<<<<< * * def docbyoffset(self, offset): */ - __pyx_t_18 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 165, __pyx_L1_error) + __pyx_t_18 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_cur_scope->__pyx_v_previd); if (unlikely(!__pyx_t_18)) __PYX_ERR(0, 167, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_18); - __pyx_t_13 = PyList_New(0); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 165, __pyx_L1_error) + __pyx_t_13 = PyList_New(0); if (unlikely(!__pyx_t_13)) __PYX_ERR(0, 167, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_13); - __pyx_t_1 = PyTuple_New(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 165, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); + __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 167, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_18); - PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_18); + PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_18); __Pyx_GIVEREF(__pyx_t_13); - PyTuple_SET_ITEM(__pyx_t_1, 1, __pyx_t_13); + PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_t_13); __pyx_t_18 = 0; __pyx_t_13 = 0; - __pyx_r = __pyx_t_1; - __pyx_t_1 = 0; + __pyx_r = __pyx_t_2; + __pyx_t_2 = 0; __Pyx_XGIVEREF(__pyx_t_3); __pyx_cur_scope->__pyx_t_0 = __pyx_t_3; __pyx_cur_scope->__pyx_t_5 = __pyx_t_9; @@ -4060,9 +4096,9 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __Pyx_XGOTREF(__pyx_t_3); __pyx_t_9 = __pyx_cur_scope->__pyx_t_5; __pyx_t_10 = __pyx_cur_scope->__pyx_t_6; - if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 165, __pyx_L1_error) + if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 167, __pyx_L1_error) - /* "gensim/corpora/_mmreader.pyx":164 + /* "gensim/corpora/_mmreader.pyx":166 * # return empty documents between the last explicit document and the number * # of documents as specified in the header * for previd in xrange(previd + 1, self.num_docs): # <<<<<<<<<<<<<< @@ -4073,11 +4109,11 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; CYTHON_MAYBE_UNUSED_VAR(__pyx_cur_scope); - /* "gensim/corpora/_mmreader.pyx":107 + /* "gensim/corpora/_mmreader.pyx":109 * break * * def __iter__(self): # <<<<<<<<<<<<<< - * """Iterate through corpus. + * """Iterate through all documents in the corpus. * */ @@ -4102,17 +4138,17 @@ static PyObject *__pyx_gb_6gensim_7corpora_9_mmreader_8MmReader_10generator(__py return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":167 +/* "gensim/corpora/_mmreader.pyx":169 * yield previd, [] * * def docbyoffset(self, offset): # <<<<<<<<<<<<<< - * """Get document at file offset `offset` (in bytes). + * """Get the document at file offset `offset` (in bytes). * */ /* Python wrapper */ static PyObject *__pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_12docbyoffset(PyObject *__pyx_v_self, PyObject *__pyx_v_offset); /*proto*/ -static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset[] = "MmReader.docbyoffset(self, offset)\nGet document at file offset `offset` (in bytes).\n\n Parameters\n ----------\n offset : int\n Offset, in bytes, of desired document.\n\n Returns\n ------\n list of (int, str)\n Document in BoW format.\n\n "; +static char __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset[] = "MmReader.docbyoffset(self, offset)\nGet the document at file offset `offset` (in bytes).\n\n Parameters\n ----------\n offset : int\n File offset, in bytes, of the desired document.\n\n Returns\n ------\n list of (int, str)\n Document in sparse bag-of-words format.\n\n "; static PyObject *__pyx_pw_6gensim_7corpora_9_mmreader_8MmReader_12docbyoffset(PyObject *__pyx_v_self, PyObject *__pyx_v_offset) { PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations @@ -4150,20 +4186,20 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st int __pyx_t_13; __Pyx_RefNannySetupContext("docbyoffset", 0); - /* "gensim/corpora/_mmreader.pyx":186 + /* "gensim/corpora/_mmreader.pyx":188 * cdef double val * * if offset == -1: # <<<<<<<<<<<<<< * return [] * if isinstance(self.input, string_types): */ - __pyx_t_1 = __Pyx_PyInt_EqObjC(__pyx_v_offset, __pyx_int_neg_1, -1L, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 186, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_EqObjC(__pyx_v_offset, __pyx_int_neg_1, -1L, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 188, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_t_1); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(0, 186, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_t_1); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(0, 188, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; if (__pyx_t_2) { - /* "gensim/corpora/_mmreader.pyx":187 + /* "gensim/corpora/_mmreader.pyx":189 * * if offset == -1: * return [] # <<<<<<<<<<<<<< @@ -4171,13 +4207,13 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st * fin, close_fin = utils.smart_open(self.input), True */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 187, __pyx_L1_error) + __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 189, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "gensim/corpora/_mmreader.pyx":186 + /* "gensim/corpora/_mmreader.pyx":188 * cdef double val * * if offset == -1: # <<<<<<<<<<<<<< @@ -4186,7 +4222,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ } - /* "gensim/corpora/_mmreader.pyx":188 + /* "gensim/corpora/_mmreader.pyx":190 * if offset == -1: * return [] * if isinstance(self.input, string_types): # <<<<<<<<<<<<<< @@ -4195,24 +4231,24 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ __pyx_t_1 = __pyx_v_self->input; __Pyx_INCREF(__pyx_t_1); - __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_string_types); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 188, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_string_types); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 190, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = PyObject_IsInstance(__pyx_t_1, __pyx_t_3); if (unlikely(__pyx_t_2 == ((int)-1))) __PYX_ERR(0, 188, __pyx_L1_error) + __pyx_t_2 = PyObject_IsInstance(__pyx_t_1, __pyx_t_3); if (unlikely(__pyx_t_2 == ((int)-1))) __PYX_ERR(0, 190, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_4 = (__pyx_t_2 != 0); if (__pyx_t_4) { - /* "gensim/corpora/_mmreader.pyx":189 + /* "gensim/corpora/_mmreader.pyx":191 * return [] * if isinstance(self.input, string_types): * fin, close_fin = utils.smart_open(self.input), True # <<<<<<<<<<<<<< * else: * fin, close_fin = self.input, False */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_utils); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_smart_open); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_smart_open); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_t_1 = NULL; @@ -4226,13 +4262,13 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st } } if (!__pyx_t_1) { - __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_v_self->input); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_v_self->input); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_1, __pyx_v_self->input}; - __pyx_t_3 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_GOTREF(__pyx_t_3); } else @@ -4240,19 +4276,19 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_1, __pyx_v_self->input}; - __pyx_t_3 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_GOTREF(__pyx_t_3); } else #endif { - __pyx_t_6 = PyTuple_New(1+1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_6 = PyTuple_New(1+1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_6, 0, __pyx_t_1); __pyx_t_1 = NULL; __Pyx_INCREF(__pyx_v_self->input); __Pyx_GIVEREF(__pyx_v_self->input); PyTuple_SET_ITEM(__pyx_t_6, 0+1, __pyx_v_self->input); - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 189, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_6, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; } @@ -4263,7 +4299,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_t_3 = 0; __pyx_v_close_fin = __pyx_t_4; - /* "gensim/corpora/_mmreader.pyx":188 + /* "gensim/corpora/_mmreader.pyx":190 * if offset == -1: * return [] * if isinstance(self.input, string_types): # <<<<<<<<<<<<<< @@ -4273,7 +4309,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st goto __pyx_L4; } - /* "gensim/corpora/_mmreader.pyx":191 + /* "gensim/corpora/_mmreader.pyx":193 * fin, close_fin = utils.smart_open(self.input), True * else: * fin, close_fin = self.input, False # <<<<<<<<<<<<<< @@ -4290,14 +4326,14 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st } __pyx_L4:; - /* "gensim/corpora/_mmreader.pyx":193 + /* "gensim/corpora/_mmreader.pyx":195 * fin, close_fin = self.input, False * * fin.seek(offset) # works for gzip/bz2 input, too # <<<<<<<<<<<<<< * previd, document = -1, [] * for line in fin: */ - __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_v_fin, __pyx_n_s_seek); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 193, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_v_fin, __pyx_n_s_seek); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 195, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_6 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_5))) { @@ -4310,13 +4346,13 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st } } if (!__pyx_t_6) { - __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_v_offset); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 193, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_5, __pyx_v_offset); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 195, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_6, __pyx_v_offset}; - __pyx_t_3 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 193, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 195, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_6); __pyx_t_6 = 0; __Pyx_GOTREF(__pyx_t_3); } else @@ -4324,19 +4360,19 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[2] = {__pyx_t_6, __pyx_v_offset}; - __pyx_t_3 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 193, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 195, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_6); __pyx_t_6 = 0; __Pyx_GOTREF(__pyx_t_3); } else #endif { - __pyx_t_1 = PyTuple_New(1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 193, __pyx_L1_error) + __pyx_t_1 = PyTuple_New(1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 195, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_GIVEREF(__pyx_t_6); PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_6); __pyx_t_6 = NULL; __Pyx_INCREF(__pyx_v_offset); __Pyx_GIVEREF(__pyx_v_offset); PyTuple_SET_ITEM(__pyx_t_1, 0+1, __pyx_v_offset); - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_1, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 193, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_1, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 195, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } @@ -4344,7 +4380,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/corpora/_mmreader.pyx":194 + /* "gensim/corpora/_mmreader.pyx":196 * * fin.seek(offset) # works for gzip/bz2 input, too * previd, document = -1, [] # <<<<<<<<<<<<<< @@ -4352,13 +4388,13 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): */ __pyx_t_7 = -1LL; - __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 194, __pyx_L1_error) + __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 196, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_v_previd = __pyx_t_7; __pyx_v_document = ((PyObject*)__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/corpora/_mmreader.pyx":195 + /* "gensim/corpora/_mmreader.pyx":197 * fin.seek(offset) # works for gzip/bz2 input, too * previd, document = -1, [] * for line in fin: # <<<<<<<<<<<<<< @@ -4369,26 +4405,26 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_t_3 = __pyx_v_fin; __Pyx_INCREF(__pyx_t_3); __pyx_t_8 = 0; __pyx_t_9 = NULL; } else { - __pyx_t_8 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_fin); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 195, __pyx_L1_error) + __pyx_t_8 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_fin); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 197, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_9 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 195, __pyx_L1_error) + __pyx_t_9 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 197, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_9)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_8 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_5 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_8); __Pyx_INCREF(__pyx_t_5); __pyx_t_8++; if (unlikely(0 < 0)) __PYX_ERR(0, 195, __pyx_L1_error) + __pyx_t_5 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_8); __Pyx_INCREF(__pyx_t_5); __pyx_t_8++; if (unlikely(0 < 0)) __PYX_ERR(0, 197, __pyx_L1_error) #else - __pyx_t_5 = PySequence_ITEM(__pyx_t_3, __pyx_t_8); __pyx_t_8++; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 195, __pyx_L1_error) + __pyx_t_5 = PySequence_ITEM(__pyx_t_3, __pyx_t_8); __pyx_t_8++; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); #endif } else { if (__pyx_t_8 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_5 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_8); __Pyx_INCREF(__pyx_t_5); __pyx_t_8++; if (unlikely(0 < 0)) __PYX_ERR(0, 195, __pyx_L1_error) + __pyx_t_5 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_8); __Pyx_INCREF(__pyx_t_5); __pyx_t_8++; if (unlikely(0 < 0)) __PYX_ERR(0, 197, __pyx_L1_error) #else - __pyx_t_5 = PySequence_ITEM(__pyx_t_3, __pyx_t_8); __pyx_t_8++; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 195, __pyx_L1_error) + __pyx_t_5 = PySequence_ITEM(__pyx_t_3, __pyx_t_8); __pyx_t_8++; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); #endif } @@ -4398,7 +4434,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(0, 195, __pyx_L1_error) + else __PYX_ERR(0, 197, __pyx_L1_error) } break; } @@ -4407,25 +4443,25 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __Pyx_XDECREF_SET(__pyx_v_line, __pyx_t_5); __pyx_t_5 = 0; - /* "gensim/corpora/_mmreader.pyx":196 + /* "gensim/corpora/_mmreader.pyx":198 * previd, document = -1, [] * for line in fin: * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): # <<<<<<<<<<<<<< * raise ValueError("unable to parse line: {}".format(line)) * */ - __pyx_t_10 = __Pyx_PyObject_AsString(__pyx_v_line); if (unlikely((!__pyx_t_10) && PyErr_Occurred())) __PYX_ERR(0, 196, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_AsString(__pyx_v_line); if (unlikely((!__pyx_t_10) && PyErr_Occurred())) __PYX_ERR(0, 198, __pyx_L1_error) __pyx_t_4 = ((sscanf(__pyx_t_10, ((char const *)"%lld %lld %lg"), (&__pyx_v_docid), (&__pyx_v_termid), (&__pyx_v_val)) != 3) != 0); - if (__pyx_t_4) { + if (unlikely(__pyx_t_4)) { - /* "gensim/corpora/_mmreader.pyx":197 + /* "gensim/corpora/_mmreader.pyx":199 * for line in fin: * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): * raise ValueError("unable to parse line: {}".format(line)) # <<<<<<<<<<<<<< * * if not self.transposed: */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_kp_s_unable_to_parse_line, __pyx_n_s_format); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_kp_s_unable_to_parse_line, __pyx_n_s_format); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_6 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_1))) { @@ -4438,13 +4474,13 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st } } if (!__pyx_t_6) { - __pyx_t_5 = __Pyx_PyObject_CallOneArg(__pyx_t_1, __pyx_v_line); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_CallOneArg(__pyx_t_1, __pyx_v_line); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_1)) { PyObject *__pyx_temp[2] = {__pyx_t_6, __pyx_v_line}; - __pyx_t_5 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_6); __pyx_t_6 = 0; __Pyx_GOTREF(__pyx_t_5); } else @@ -4452,37 +4488,32 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_1)) { PyObject *__pyx_temp[2] = {__pyx_t_6, __pyx_v_line}; - __pyx_t_5 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyCFunction_FastCall(__pyx_t_1, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_6); __pyx_t_6 = 0; __Pyx_GOTREF(__pyx_t_5); } else #endif { - __pyx_t_11 = PyTuple_New(1+1); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_11 = PyTuple_New(1+1); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); __Pyx_GIVEREF(__pyx_t_6); PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_t_6); __pyx_t_6 = NULL; __Pyx_INCREF(__pyx_v_line); __Pyx_GIVEREF(__pyx_v_line); PyTuple_SET_ITEM(__pyx_t_11, 0+1, __pyx_v_line); - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_11, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_11, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; } } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 197, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_5); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 199, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __Pyx_GIVEREF(__pyx_t_5); - PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_t_5); - __pyx_t_5 = 0; - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_1, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 197, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_5); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __Pyx_Raise(__pyx_t_5, 0, 0, 0); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __PYX_ERR(0, 197, __pyx_L1_error) + __Pyx_Raise(__pyx_t_1, 0, 0, 0); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __PYX_ERR(0, 199, __pyx_L1_error) - /* "gensim/corpora/_mmreader.pyx":196 + /* "gensim/corpora/_mmreader.pyx":198 * previd, document = -1, [] * for line in fin: * if (sscanf(line, "%lld %lld %lg", &docid, &termid, &val) != 3): # <<<<<<<<<<<<<< @@ -4491,7 +4522,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ } - /* "gensim/corpora/_mmreader.pyx":199 + /* "gensim/corpora/_mmreader.pyx":201 * raise ValueError("unable to parse line: {}".format(line)) * * if not self.transposed: # <<<<<<<<<<<<<< @@ -4501,7 +4532,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_t_4 = ((!(__pyx_v_self->transposed != 0)) != 0); if (__pyx_t_4) { - /* "gensim/corpora/_mmreader.pyx":200 + /* "gensim/corpora/_mmreader.pyx":202 * * if not self.transposed: * termid, docid = docid, termid # <<<<<<<<<<<<<< @@ -4513,7 +4544,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_v_termid = __pyx_t_7; __pyx_v_docid = __pyx_t_12; - /* "gensim/corpora/_mmreader.pyx":199 + /* "gensim/corpora/_mmreader.pyx":201 * raise ValueError("unable to parse line: {}".format(line)) * * if not self.transposed: # <<<<<<<<<<<<<< @@ -4522,7 +4553,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ } - /* "gensim/corpora/_mmreader.pyx":203 + /* "gensim/corpora/_mmreader.pyx":205 * * # -1 because matrix market indexes are 1-based => convert to 0-based * docid -= 1 # <<<<<<<<<<<<<< @@ -4531,7 +4562,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ __pyx_v_docid = (__pyx_v_docid - 1); - /* "gensim/corpora/_mmreader.pyx":204 + /* "gensim/corpora/_mmreader.pyx":206 * # -1 because matrix market indexes are 1-based => convert to 0-based * docid -= 1 * termid -= 1 # <<<<<<<<<<<<<< @@ -4540,7 +4571,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ __pyx_v_termid = (__pyx_v_termid - 1); - /* "gensim/corpora/_mmreader.pyx":206 + /* "gensim/corpora/_mmreader.pyx":208 * termid -= 1 * * assert previd <= docid, "matrix columns must come in ascending order" # <<<<<<<<<<<<<< @@ -4551,12 +4582,12 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st if (unlikely(!Py_OptimizeFlag)) { if (unlikely(!((__pyx_v_previd <= __pyx_v_docid) != 0))) { PyErr_SetObject(PyExc_AssertionError, __pyx_kp_s_matrix_columns_must_come_in_asce); - __PYX_ERR(0, 206, __pyx_L1_error) + __PYX_ERR(0, 208, __pyx_L1_error) } } #endif - /* "gensim/corpora/_mmreader.pyx":207 + /* "gensim/corpora/_mmreader.pyx":209 * * assert previd <= docid, "matrix columns must come in ascending order" * if docid != previd: # <<<<<<<<<<<<<< @@ -4566,7 +4597,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_t_4 = ((__pyx_v_docid != __pyx_v_previd) != 0); if (__pyx_t_4) { - /* "gensim/corpora/_mmreader.pyx":208 + /* "gensim/corpora/_mmreader.pyx":210 * assert previd <= docid, "matrix columns must come in ascending order" * if docid != previd: * if previd >= 0: # <<<<<<<<<<<<<< @@ -4576,7 +4607,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_t_4 = ((__pyx_v_previd >= 0) != 0); if (__pyx_t_4) { - /* "gensim/corpora/_mmreader.pyx":209 + /* "gensim/corpora/_mmreader.pyx":211 * if docid != previd: * if previd >= 0: * break # <<<<<<<<<<<<<< @@ -4585,7 +4616,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ goto __pyx_L6_break; - /* "gensim/corpora/_mmreader.pyx":208 + /* "gensim/corpora/_mmreader.pyx":210 * assert previd <= docid, "matrix columns must come in ascending order" * if docid != previd: * if previd >= 0: # <<<<<<<<<<<<<< @@ -4594,7 +4625,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ } - /* "gensim/corpora/_mmreader.pyx":210 + /* "gensim/corpora/_mmreader.pyx":212 * if previd >= 0: * break * previd = docid # <<<<<<<<<<<<<< @@ -4603,7 +4634,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ __pyx_v_previd = __pyx_v_docid; - /* "gensim/corpora/_mmreader.pyx":207 + /* "gensim/corpora/_mmreader.pyx":209 * * assert previd <= docid, "matrix columns must come in ascending order" * if docid != previd: # <<<<<<<<<<<<<< @@ -4612,29 +4643,29 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ } - /* "gensim/corpora/_mmreader.pyx":212 + /* "gensim/corpora/_mmreader.pyx":214 * previd = docid * * document.append((termid, val,)) # add another field to the current document # <<<<<<<<<<<<<< * * if close_fin: */ - __pyx_t_5 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_termid); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 212, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_5); - __pyx_t_1 = PyFloat_FromDouble(__pyx_v_val); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 212, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_termid); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 214, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_11 = PyTuple_New(2); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 212, __pyx_L1_error) + __pyx_t_5 = PyFloat_FromDouble(__pyx_v_val); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 214, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_5); + __pyx_t_11 = PyTuple_New(2); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 214, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); - __Pyx_GIVEREF(__pyx_t_5); - PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_t_5); __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_11, 1, __pyx_t_1); - __pyx_t_5 = 0; + PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_t_1); + __Pyx_GIVEREF(__pyx_t_5); + PyTuple_SET_ITEM(__pyx_t_11, 1, __pyx_t_5); __pyx_t_1 = 0; - __pyx_t_13 = __Pyx_PyList_Append(__pyx_v_document, __pyx_t_11); if (unlikely(__pyx_t_13 == ((int)-1))) __PYX_ERR(0, 212, __pyx_L1_error) + __pyx_t_5 = 0; + __pyx_t_13 = __Pyx_PyList_Append(__pyx_v_document, __pyx_t_11); if (unlikely(__pyx_t_13 == ((int)-1))) __PYX_ERR(0, 214, __pyx_L1_error) __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - /* "gensim/corpora/_mmreader.pyx":195 + /* "gensim/corpora/_mmreader.pyx":197 * fin.seek(offset) # works for gzip/bz2 input, too * previd, document = -1, [] * for line in fin: # <<<<<<<<<<<<<< @@ -4645,7 +4676,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_L6_break:; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/corpora/_mmreader.pyx":214 + /* "gensim/corpora/_mmreader.pyx":216 * document.append((termid, val,)) # add another field to the current document * * if close_fin: # <<<<<<<<<<<<<< @@ -4655,35 +4686,35 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_t_4 = (__pyx_v_close_fin != 0); if (__pyx_t_4) { - /* "gensim/corpora/_mmreader.pyx":215 + /* "gensim/corpora/_mmreader.pyx":217 * * if close_fin: * fin.close() # <<<<<<<<<<<<<< * return document */ - __pyx_t_11 = __Pyx_PyObject_GetAttrStr(__pyx_v_fin, __pyx_n_s_close); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 215, __pyx_L1_error) + __pyx_t_11 = __Pyx_PyObject_GetAttrStr(__pyx_v_fin, __pyx_n_s_close); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 217, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); - __pyx_t_1 = NULL; + __pyx_t_5 = NULL; if (CYTHON_UNPACK_METHODS && likely(PyMethod_Check(__pyx_t_11))) { - __pyx_t_1 = PyMethod_GET_SELF(__pyx_t_11); - if (likely(__pyx_t_1)) { + __pyx_t_5 = PyMethod_GET_SELF(__pyx_t_11); + if (likely(__pyx_t_5)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_11); - __Pyx_INCREF(__pyx_t_1); + __Pyx_INCREF(__pyx_t_5); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_11, function); } } - if (__pyx_t_1) { - __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_11, __pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 215, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + if (__pyx_t_5) { + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_11, __pyx_t_5); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 217, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } else { - __pyx_t_3 = __Pyx_PyObject_CallNoArg(__pyx_t_11); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 215, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallNoArg(__pyx_t_11); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 217, __pyx_L1_error) } __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "gensim/corpora/_mmreader.pyx":214 + /* "gensim/corpora/_mmreader.pyx":216 * document.append((termid, val,)) # add another field to the current document * * if close_fin: # <<<<<<<<<<<<<< @@ -4692,7 +4723,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st */ } - /* "gensim/corpora/_mmreader.pyx":216 + /* "gensim/corpora/_mmreader.pyx":218 * if close_fin: * fin.close() * return document # <<<<<<<<<<<<<< @@ -4702,11 +4733,11 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st __pyx_r = __pyx_v_document; goto __pyx_L0; - /* "gensim/corpora/_mmreader.pyx":167 + /* "gensim/corpora/_mmreader.pyx":169 * yield previd, [] * * def docbyoffset(self, offset): # <<<<<<<<<<<<<< - * """Get document at file offset `offset` (in bytes). + * """Get the document at file offset `offset` (in bytes). * */ @@ -4728,7 +4759,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_11docbyoffset(st return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":41 +/* "gensim/corpora/_mmreader.pyx":43 * * """ * cdef public input # <<<<<<<<<<<<<< @@ -4823,7 +4854,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_5input_4__del__(struct return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":42 +/* "gensim/corpora/_mmreader.pyx":44 * """ * cdef public input * cdef public bint transposed # <<<<<<<<<<<<<< @@ -4850,7 +4881,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_10transposed___g PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_v_self->transposed); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 42, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_v_self->transposed); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 44, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; @@ -4885,7 +4916,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_10transposed_2__set__( __Pyx_RefNannyDeclarations int __pyx_t_1; __Pyx_RefNannySetupContext("__set__", 0); - __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_v_value); if (unlikely((__pyx_t_1 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 42, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_v_value); if (unlikely((__pyx_t_1 == (int)-1) && PyErr_Occurred())) __PYX_ERR(0, 44, __pyx_L1_error) __pyx_v_self->transposed = __pyx_t_1; /* function exit code */ @@ -4899,7 +4930,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_10transposed_2__set__( return __pyx_r; } -/* "gensim/corpora/_mmreader.pyx":43 +/* "gensim/corpora/_mmreader.pyx":45 * cdef public input * cdef public bint transposed * cdef public long long num_docs, num_terms, num_nnz # <<<<<<<<<<<<<< @@ -4926,7 +4957,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8num_docs___get_ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_docs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 43, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_docs); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 45, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; @@ -4961,7 +4992,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_8num_docs_2__set__(str __Pyx_RefNannyDeclarations PY_LONG_LONG __pyx_t_1; __Pyx_RefNannySetupContext("__set__", 0); - __pyx_t_1 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_v_value); if (unlikely((__pyx_t_1 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 43, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_v_value); if (unlikely((__pyx_t_1 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 45, __pyx_L1_error) __pyx_v_self->num_docs = __pyx_t_1; /* function exit code */ @@ -4994,7 +5025,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_9num_terms___get PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_terms); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 43, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_terms); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 45, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; @@ -5029,7 +5060,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_9num_terms_2__set__(st __Pyx_RefNannyDeclarations PY_LONG_LONG __pyx_t_1; __Pyx_RefNannySetupContext("__set__", 0); - __pyx_t_1 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_v_value); if (unlikely((__pyx_t_1 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 43, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_v_value); if (unlikely((__pyx_t_1 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 45, __pyx_L1_error) __pyx_v_self->num_terms = __pyx_t_1; /* function exit code */ @@ -5062,7 +5093,7 @@ static PyObject *__pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_7num_nnz___get__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_nnz); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 43, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_PY_LONG_LONG(__pyx_v_self->num_nnz); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 45, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; @@ -5097,7 +5128,7 @@ static int __pyx_pf_6gensim_7corpora_9_mmreader_8MmReader_7num_nnz_2__set__(stru __Pyx_RefNannyDeclarations PY_LONG_LONG __pyx_t_1; __Pyx_RefNannySetupContext("__set__", 0); - __pyx_t_1 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_v_value); if (unlikely((__pyx_t_1 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 43, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_As_PY_LONG_LONG(__pyx_v_value); if (unlikely((__pyx_t_1 == (PY_LONG_LONG)-1) && PyErr_Occurred())) __PYX_ERR(0, 45, __pyx_L1_error) __pyx_v_self->num_nnz = __pyx_t_1; /* function exit code */ @@ -5460,17 +5491,17 @@ static PyObject *__pyx_pw_6gensim_7corpora_9_mmreader_1__pyx_unpickle_MmReader(P kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_pyx_type)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_pyx_type)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_pyx_checksum)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_pyx_checksum)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_unpickle_MmReader", 1, 3, 3, 1); __PYX_ERR(1, 1, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_pyx_state)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_pyx_state)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_unpickle_MmReader", 1, 3, 3, 2); __PYX_ERR(1, 1, __pyx_L3_error) } @@ -6115,7 +6146,7 @@ static PyTypeObject __pyx_type_6gensim_7corpora_9_mmreader_MmReader = { 0, /*tp_setattro*/ 0, /*tp_as_buffer*/ Py_TPFLAGS_DEFAULT|Py_TPFLAGS_HAVE_VERSION_TAG|Py_TPFLAGS_CHECKTYPES|Py_TPFLAGS_HAVE_NEWBUFFER|Py_TPFLAGS_BASETYPE|Py_TPFLAGS_HAVE_GC, /*tp_flags*/ - "MmReader(input, transposed=True)\nMatrix market file reader (fast Cython version), used for :class:`~gensim.corpora.mmcorpus.MmCorpus`.\n\n Wrap a term-document matrix on disk (in matrix-market format), and present it\n as an object which supports iteration over the rows (~documents).\n\n Attributes\n ----------\n num_docs : int\n Number of documents in market matrix file.\n num_terms : int\n Number of terms.\n num_nnz : int\n Number of non-zero terms.\n\n Notes\n ----------\n Note that the file is read into memory one document at a time, not the whole\n matrix at once (unlike scipy.io.mmread). This allows us to process corpora\n which are larger than the available RAM.\n\n ", /*tp_doc*/ + "MmReader(input, transposed=True)\nMatrix market file reader (fast Cython version), used internally in :class:`~gensim.corpora.mmcorpus.MmCorpus`.\n\n Wrap a term-document matrix on disk (in matrix-market format), and present it\n as an object which supports iteration over the rows (~documents).\n\n Attributes\n ----------\n num_docs : int\n Number of documents in market matrix file.\n num_terms : int\n Number of terms.\n num_nnz : int\n Number of non-zero terms.\n\n Notes\n -----\n Note that the file is read into memory one document at a time, not the whole matrix at once\n (unlike e.g. `scipy.io.mmread` and other implementations).\n This allows us to process corpora which are larger than the available RAM.\n\n ", /*tp_doc*/ __pyx_tp_traverse_6gensim_7corpora_9_mmreader_MmReader, /*tp_traverse*/ __pyx_tp_clear_6gensim_7corpora_9_mmreader_MmReader, /*tp_clear*/ 0, /*tp_richcompare*/ @@ -6595,9 +6626,9 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {0, 0, 0, 0, 0, 0, 0} }; static int __Pyx_InitCachedBuiltins(void) { - __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(0, 64, __pyx_L1_error) - __pyx_builtin_StopIteration = __Pyx_GetBuiltinName(__pyx_n_s_StopIteration); if (!__pyx_builtin_StopIteration) __PYX_ERR(0, 68, __pyx_L1_error) - __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 72, __pyx_L1_error) + __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(0, 66, __pyx_L1_error) + __pyx_builtin_StopIteration = __Pyx_GetBuiltinName(__pyx_n_s_StopIteration); if (!__pyx_builtin_StopIteration) __PYX_ERR(0, 70, __pyx_L1_error) + __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(0, 74, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; @@ -6607,58 +6638,58 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0); - /* "gensim/corpora/_mmreader.pyx":63 + /* "gensim/corpora/_mmreader.pyx":65 * try: * header = utils.to_unicode(next(lines)).strip() * if not header.lower().startswith('%%matrixmarket matrix coordinate real general'): # <<<<<<<<<<<<<< * raise ValueError( * "File %s not in Matrix Market format with coordinate real general; instead found: \n%s" % */ - __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_s_matrixmarket_matrix_coordinate); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 63, __pyx_L1_error) + __pyx_tuple_ = PyTuple_Pack(1, __pyx_kp_s_matrixmarket_matrix_coordinate); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple_); __Pyx_GIVEREF(__pyx_tuple_); - /* "gensim/corpora/_mmreader.pyx":74 + /* "gensim/corpora/_mmreader.pyx":76 * for lineno, line in enumerate(lines): * line = utils.to_unicode(line) * if not line.startswith('%'): # <<<<<<<<<<<<<< * self.num_docs, self.num_terms, self.num_nnz = (int(x) for x in line.split()) * if not self.transposed: */ - __pyx_tuple__3 = PyTuple_Pack(1, __pyx_kp_s__2); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 74, __pyx_L1_error) + __pyx_tuple__3 = PyTuple_Pack(1, __pyx_kp_s__2); if (unlikely(!__pyx_tuple__3)) __PYX_ERR(0, 76, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__3); __Pyx_GIVEREF(__pyx_tuple__3); - /* "gensim/corpora/_mmreader.pyx":60 + /* "gensim/corpora/_mmreader.pyx":62 * logger.info("initializing cython corpus reader from %s", input) * self.input, self.transposed = input, transposed * with utils.open_file(self.input) as lines: # <<<<<<<<<<<<<< * try: * header = utils.to_unicode(next(lines)).strip() */ - __pyx_tuple__4 = PyTuple_Pack(3, Py_None, Py_None, Py_None); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 60, __pyx_L1_error) + __pyx_tuple__4 = PyTuple_Pack(3, Py_None, Py_None, Py_None); if (unlikely(!__pyx_tuple__4)) __PYX_ERR(0, 62, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__4); __Pyx_GIVEREF(__pyx_tuple__4); - /* "gensim/corpora/_mmreader.pyx":103 + /* "gensim/corpora/_mmreader.pyx":105 * """ * for line in input_file: * if line.startswith(b'%'): # <<<<<<<<<<<<<< * continue * break */ - __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_b__2); if (unlikely(!__pyx_tuple__5)) __PYX_ERR(0, 103, __pyx_L1_error) + __pyx_tuple__5 = PyTuple_Pack(1, __pyx_kp_b__2); if (unlikely(!__pyx_tuple__5)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__5); __Pyx_GIVEREF(__pyx_tuple__5); - /* "gensim/corpora/_mmreader.pyx":125 + /* "gensim/corpora/_mmreader.pyx":127 * cdef double val = 0 * * with utils.file_or_filename(self.input) as lines: # <<<<<<<<<<<<<< * self.skip_headers(lines) * */ - __pyx_tuple__6 = PyTuple_Pack(3, Py_None, Py_None, Py_None); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(0, 125, __pyx_L1_error) + __pyx_tuple__6 = PyTuple_Pack(3, Py_None, Py_None, Py_None); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__6); __Pyx_GIVEREF(__pyx_tuple__6); @@ -6689,12 +6720,160 @@ static int __Pyx_InitGlobals(void) { return -1; } +static int __Pyx_modinit_global_init_code(void); /*proto*/ +static int __Pyx_modinit_variable_export_code(void); /*proto*/ +static int __Pyx_modinit_function_export_code(void); /*proto*/ +static int __Pyx_modinit_type_init_code(void); /*proto*/ +static int __Pyx_modinit_type_import_code(void); /*proto*/ +static int __Pyx_modinit_variable_import_code(void); /*proto*/ +static int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader_MmReader) < 0) __PYX_ERR(0, 21, __pyx_L1_error) + __pyx_type_6gensim_7corpora_9_mmreader_MmReader.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type_6gensim_7corpora_9_mmreader_MmReader.tp_dictoffset && __pyx_type_6gensim_7corpora_9_mmreader_MmReader.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type_6gensim_7corpora_9_mmreader_MmReader.tp_getattro = __Pyx_PyObject_GenericGetAttr; + } + #if CYTHON_COMPILING_IN_CPYTHON + { + PyObject *wrapper = PyObject_GetAttrString((PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader, "__init__"); if (unlikely(!wrapper)) __PYX_ERR(0, 21, __pyx_L1_error) + if (Py_TYPE(wrapper) == &PyWrapperDescr_Type) { + __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__ = *((PyWrapperDescrObject *)wrapper)->d_base; + __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__.doc = __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader___init__; + ((PyWrapperDescrObject *)wrapper)->d_base = &__pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__; + } + } + #endif + #if CYTHON_COMPILING_IN_CPYTHON + { + PyObject *wrapper = PyObject_GetAttrString((PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader, "__len__"); if (unlikely(!wrapper)) __PYX_ERR(0, 21, __pyx_L1_error) + if (Py_TYPE(wrapper) == &PyWrapperDescr_Type) { + __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__ = *((PyWrapperDescrObject *)wrapper)->d_base; + __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__.doc = __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_2__len__; + ((PyWrapperDescrObject *)wrapper)->d_base = &__pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__; + } + } + #endif + #if CYTHON_COMPILING_IN_CPYTHON + { + PyObject *wrapper = PyObject_GetAttrString((PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader, "__iter__"); if (unlikely(!wrapper)) __PYX_ERR(0, 21, __pyx_L1_error) + if (Py_TYPE(wrapper) == &PyWrapperDescr_Type) { + __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__ = *((PyWrapperDescrObject *)wrapper)->d_base; + __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__.doc = __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_8__iter__; + ((PyWrapperDescrObject *)wrapper)->d_base = &__pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__; + } + } + #endif + if (PyObject_SetAttrString(__pyx_m, "MmReader", (PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader) < 0) __PYX_ERR(0, 21, __pyx_L1_error) + if (__Pyx_setup_reduce((PyObject*)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader) < 0) __PYX_ERR(0, 21, __pyx_L1_error) + __pyx_ptype_6gensim_7corpora_9_mmreader_MmReader = &__pyx_type_6gensim_7corpora_9_mmreader_MmReader; + if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__) < 0) __PYX_ERR(0, 47, __pyx_L1_error) + __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__.tp_dictoffset && __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__.tp_getattro = __Pyx_PyObject_GenericGetAttrNoDict; + } + __pyx_ptype_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__ = &__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__; + if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr) < 0) __PYX_ERR(0, 77, __pyx_L1_error) + __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr.tp_dictoffset && __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr.tp_getattro = __Pyx_PyObject_GenericGetAttrNoDict; + } + __pyx_ptype_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr = &__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr; + if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__) < 0) __PYX_ERR(0, 109, __pyx_L1_error) + __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__.tp_dictoffset && __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__.tp_getattro = __Pyx_PyObject_GenericGetAttrNoDict; + } + __pyx_ptype_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__ = &__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + + +#if PY_MAJOR_VERSION < 3 +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC void +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#else +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyObject * +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (!(defined(__cplusplus)) || (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ > 4))) + #define CYTHON_SMALL_CODE __attribute__((optimize("Os"))) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + + #if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC init_mmreader(void); /*proto*/ -PyMODINIT_FUNC init_mmreader(void) +__Pyx_PyMODINIT_FUNC init_mmreader(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC init_mmreader(void) #else -PyMODINIT_FUNC PyInit__mmreader(void); /*proto*/ -PyMODINIT_FUNC PyInit__mmreader(void) +__Pyx_PyMODINIT_FUNC PyInit__mmreader(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit__mmreader(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); @@ -6741,22 +6920,22 @@ static int __pyx_pymod_exec__mmreader(PyObject *__pyx_pyinit_module) PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; - PyObject *__pyx_t_4 = NULL; - PyObject *__pyx_t_5 = NULL; __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m && __pyx_m == __pyx_pyinit_module) return 0; + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif #if CYTHON_REFNANNY - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); - if (!__Pyx_RefNanny) { - PyErr_Clear(); - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); - if (!__Pyx_RefNanny) - Py_FatalError("failed to import 'refnanny' module"); - } - #endif - __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit__mmreader(void)", 0); +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit__mmreader(void)", 0); if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) @@ -6826,219 +7005,134 @@ static int __pyx_pymod_exec__mmreader(PyObject *__pyx_pyinit_module) if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) /*--- Constants init code ---*/ if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Global init code ---*/ - /*--- Variable export code ---*/ - /*--- Function export code ---*/ - /*--- Type init code ---*/ - if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader_MmReader) < 0) __PYX_ERR(0, 19, __pyx_L1_error) - __pyx_type_6gensim_7corpora_9_mmreader_MmReader.tp_print = 0; - #if CYTHON_COMPILING_IN_CPYTHON - { - PyObject *wrapper = PyObject_GetAttrString((PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader, "__init__"); if (unlikely(!wrapper)) __PYX_ERR(0, 19, __pyx_L1_error) - if (Py_TYPE(wrapper) == &PyWrapperDescr_Type) { - __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__ = *((PyWrapperDescrObject *)wrapper)->d_base; - __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__.doc = __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader___init__; - ((PyWrapperDescrObject *)wrapper)->d_base = &__pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader___init__; - } - } - #endif - #if CYTHON_COMPILING_IN_CPYTHON - { - PyObject *wrapper = PyObject_GetAttrString((PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader, "__len__"); if (unlikely(!wrapper)) __PYX_ERR(0, 19, __pyx_L1_error) - if (Py_TYPE(wrapper) == &PyWrapperDescr_Type) { - __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__ = *((PyWrapperDescrObject *)wrapper)->d_base; - __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__.doc = __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_2__len__; - ((PyWrapperDescrObject *)wrapper)->d_base = &__pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_2__len__; - } - } - #endif - #if CYTHON_COMPILING_IN_CPYTHON - { - PyObject *wrapper = PyObject_GetAttrString((PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader, "__iter__"); if (unlikely(!wrapper)) __PYX_ERR(0, 19, __pyx_L1_error) - if (Py_TYPE(wrapper) == &PyWrapperDescr_Type) { - __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__ = *((PyWrapperDescrObject *)wrapper)->d_base; - __pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__.doc = __pyx_doc_6gensim_7corpora_9_mmreader_8MmReader_8__iter__; - ((PyWrapperDescrObject *)wrapper)->d_base = &__pyx_wrapperbase_6gensim_7corpora_9_mmreader_8MmReader_8__iter__; - } - } - #endif - if (PyObject_SetAttrString(__pyx_m, "MmReader", (PyObject *)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader) < 0) __PYX_ERR(0, 19, __pyx_L1_error) - if (__Pyx_setup_reduce((PyObject*)&__pyx_type_6gensim_7corpora_9_mmreader_MmReader) < 0) __PYX_ERR(0, 19, __pyx_L1_error) - __pyx_ptype_6gensim_7corpora_9_mmreader_MmReader = &__pyx_type_6gensim_7corpora_9_mmreader_MmReader; - if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__) < 0) __PYX_ERR(0, 45, __pyx_L1_error) - __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__.tp_print = 0; - __pyx_ptype_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__ = &__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct____init__; - if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr) < 0) __PYX_ERR(0, 75, __pyx_L1_error) - __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr.tp_print = 0; - __pyx_ptype_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr = &__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_1_genexpr; - if (PyType_Ready(&__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__) < 0) __PYX_ERR(0, 107, __pyx_L1_error) - __pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__.tp_print = 0; - __pyx_ptype_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__ = &__pyx_type_6gensim_7corpora_9_mmreader___pyx_scope_struct_2___iter__; - /*--- Type import code ---*/ - /*--- Variable import code ---*/ - /*--- Function import code ---*/ + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + (void)__Pyx_modinit_variable_export_code(); + (void)__Pyx_modinit_function_export_code(); + if (unlikely(__Pyx_modinit_type_init_code() != 0)) goto __pyx_L1_error; + (void)__Pyx_modinit_type_import_code(); + (void)__Pyx_modinit_variable_import_code(); + (void)__Pyx_modinit_function_import_code(); /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif - /* "gensim/corpora/_mmreader.pyx":6 + /* "gensim/corpora/_mmreader.pyx":8 * from __future__ import with_statement * * from gensim import utils # <<<<<<<<<<<<<< * * from six import string_types */ - __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 6, __pyx_L1_error) + __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 8, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_n_s_utils); __Pyx_GIVEREF(__pyx_n_s_utils); PyList_SET_ITEM(__pyx_t_1, 0, __pyx_n_s_utils); - __pyx_t_2 = __Pyx_Import(__pyx_n_s_gensim, __pyx_t_1, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 6, __pyx_L1_error) + __pyx_t_2 = __Pyx_Import(__pyx_n_s_gensim, __pyx_t_1, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 8, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_utils); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 6, __pyx_L1_error) + __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_utils); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 8, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_utils, __pyx_t_1) < 0) __PYX_ERR(0, 6, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_utils, __pyx_t_1) < 0) __PYX_ERR(0, 8, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":8 + /* "gensim/corpora/_mmreader.pyx":10 * from gensim import utils * * from six import string_types # <<<<<<<<<<<<<< * from six.moves import xrange * import logging */ - __pyx_t_2 = PyList_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 8, __pyx_L1_error) + __pyx_t_2 = PyList_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 10, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_n_s_string_types); __Pyx_GIVEREF(__pyx_n_s_string_types); PyList_SET_ITEM(__pyx_t_2, 0, __pyx_n_s_string_types); - __pyx_t_1 = __Pyx_Import(__pyx_n_s_six, __pyx_t_2, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 8, __pyx_L1_error) + __pyx_t_1 = __Pyx_Import(__pyx_n_s_six, __pyx_t_2, -1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 10, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_1, __pyx_n_s_string_types); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 8, __pyx_L1_error) + __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_1, __pyx_n_s_string_types); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 10, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_string_types, __pyx_t_2) < 0) __PYX_ERR(0, 8, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_string_types, __pyx_t_2) < 0) __PYX_ERR(0, 10, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "gensim/corpora/_mmreader.pyx":9 + /* "gensim/corpora/_mmreader.pyx":11 * * from six import string_types * from six.moves import xrange # <<<<<<<<<<<<<< * import logging * */ - __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 9, __pyx_L1_error) + __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 11, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_n_s_xrange); __Pyx_GIVEREF(__pyx_n_s_xrange); PyList_SET_ITEM(__pyx_t_1, 0, __pyx_n_s_xrange); - __pyx_t_2 = __Pyx_Import(__pyx_n_s_six_moves, __pyx_t_1, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 9, __pyx_L1_error) + __pyx_t_2 = __Pyx_Import(__pyx_n_s_six_moves, __pyx_t_1, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 11, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_xrange); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 9, __pyx_L1_error) + __pyx_t_1 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_xrange); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 11, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_xrange, __pyx_t_1) < 0) __PYX_ERR(0, 9, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_xrange, __pyx_t_1) < 0) __PYX_ERR(0, 11, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":10 + /* "gensim/corpora/_mmreader.pyx":12 * from six import string_types * from six.moves import xrange * import logging # <<<<<<<<<<<<<< * * cimport cython */ - __pyx_t_2 = __Pyx_Import(__pyx_n_s_logging, 0, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 10, __pyx_L1_error) + __pyx_t_2 = __Pyx_Import(__pyx_n_s_logging, 0, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 12, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_logging, __pyx_t_2) < 0) __PYX_ERR(0, 10, __pyx_L1_error) + if (PyDict_SetItem(__pyx_d, __pyx_n_s_logging, __pyx_t_2) < 0) __PYX_ERR(0, 12, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "gensim/corpora/_mmreader.pyx":16 + /* "gensim/corpora/_mmreader.pyx":18 * * * logger = logging.getLogger(__name__) # <<<<<<<<<<<<<< * * */ - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_logging); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 16, __pyx_L1_error) + __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_logging); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 18, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_getLogger); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 18, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_getLogger); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 16, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_name); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 18, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_t_1, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 18, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_GetModuleGlobalName(__pyx_n_s_name); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 16, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_4 = NULL; - if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_3))) { - __pyx_t_4 = PyMethod_GET_SELF(__pyx_t_3); - if (likely(__pyx_t_4)) { - PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); - __Pyx_INCREF(__pyx_t_4); - __Pyx_INCREF(function); - __Pyx_DECREF_SET(__pyx_t_3, function); - } - } - if (!__pyx_t_4) { - __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 16, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __Pyx_GOTREF(__pyx_t_2); - } else { - #if CYTHON_FAST_PYCALL - if (PyFunction_Check(__pyx_t_3)) { - PyObject *__pyx_temp[2] = {__pyx_t_4, __pyx_t_1}; - __pyx_t_2 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 16, __pyx_L1_error) - __Pyx_XDECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_GOTREF(__pyx_t_2); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - } else - #endif - #if CYTHON_FAST_PYCCALL - if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { - PyObject *__pyx_temp[2] = {__pyx_t_4, __pyx_t_1}; - __pyx_t_2 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 16, __pyx_L1_error) - __Pyx_XDECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_GOTREF(__pyx_t_2); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - } else - #endif - { - __pyx_t_5 = PyTuple_New(1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 16, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_5); - __Pyx_GIVEREF(__pyx_t_4); PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_4); __pyx_t_4 = NULL; - __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_5, 0+1, __pyx_t_1); - __pyx_t_1 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_5, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 16, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); - __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - } - } - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (PyDict_SetItem(__pyx_d, __pyx_n_s_logger, __pyx_t_2) < 0) __PYX_ERR(0, 16, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + if (PyDict_SetItem(__pyx_d, __pyx_n_s_logger, __pyx_t_3) < 0) __PYX_ERR(0, 18, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "(tree fragment)":1 * def __pyx_unpickle_MmReader(__pyx_type, long __pyx_checksum, __pyx_state): # <<<<<<<<<<<<<< * if __pyx_checksum != 0xea5fe92: * from pickle import PickleError as __pyx_PickleError */ - __pyx_t_2 = PyCFunction_NewEx(&__pyx_mdef_6gensim_7corpora_9_mmreader_1__pyx_unpickle_MmReader, NULL, __pyx_n_s_gensim_corpora__mmreader); if (unlikely(!__pyx_t_2)) __PYX_ERR(1, 1, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_pyx_unpickle_MmReader, __pyx_t_2) < 0) __PYX_ERR(1, 1, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __pyx_t_3 = PyCFunction_NewEx(&__pyx_mdef_6gensim_7corpora_9_mmreader_1__pyx_unpickle_MmReader, NULL, __pyx_n_s_gensim_corpora__mmreader); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_pyx_unpickle_MmReader, __pyx_t_3) < 0) __PYX_ERR(1, 1, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "gensim/corpora/_mmreader.pyx":1 * # Copyright (C) 2018 Radim Rehurek # <<<<<<<<<<<<<< * # cython: embedsignature=True - * """Reader for corpus in the Matrix Market format.""" + * */ - __pyx_t_2 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); - if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_2) < 0) __PYX_ERR(0, 1, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __pyx_t_3 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); + if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_3) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /*--- Wrapped vars code ---*/ @@ -7047,8 +7141,6 @@ static int __pyx_pymod_exec__mmreader(PyObject *__pyx_pyinit_module) __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); - __Pyx_XDECREF(__pyx_t_4); - __Pyx_XDECREF(__pyx_t_5); if (__pyx_m) { if (__pyx_d) { __Pyx_AddTraceback("init gensim.corpora._mmreader", 0, __pyx_lineno, __pyx_filename); @@ -7086,6 +7178,20 @@ static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { } #endif +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); @@ -7495,10 +7601,19 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { PyObject *result; #if !CYTHON_AVOID_BORROWED_REFS +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 + result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); + if (likely(result)) { + Py_INCREF(result); + } else if (unlikely(PyErr_Occurred())) { + result = NULL; + } else { +#else result = PyDict_GetItem(__pyx_d, name); if (likely(result)) { Py_INCREF(result); } else { +#endif #else result = PyObject_GetItem(__pyx_d, name); if (!result) { @@ -7510,7 +7625,7 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { } /* PyErrFetchRestore */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { PyObject *tmp_type, *tmp_value, *tmp_tb; tmp_type = tstate->curexc_type; @@ -7534,18 +7649,16 @@ static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject #endif /* IterNext */ - static PyObject *__Pyx_PyIter_Next2Default(PyObject* defval) { + static PyObject *__Pyx_PyIter_Next2Default(PyObject* defval) { PyObject* exc_type; __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign exc_type = __Pyx_PyErr_Occurred(); if (unlikely(exc_type)) { - if (unlikely(!__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) + if (!defval || unlikely(!__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) return NULL; - if (defval) { - __Pyx_PyErr_Clear(); - Py_INCREF(defval); - } + __Pyx_PyErr_Clear(); + Py_INCREF(defval); return defval; } if (defval) { @@ -7576,15 +7689,22 @@ static CYTHON_INLINE PyObject *__Pyx_PyIter_Next2(PyObject* iterator, PyObject* if (likely(next)) return next; #endif - } else if (CYTHON_USE_TYPE_SLOTS || !PyIter_Check(iterator)) { + } else if (CYTHON_USE_TYPE_SLOTS || unlikely(!PyIter_Check(iterator))) { __Pyx_PyIter_Next_ErrorNoIterator(iterator); return NULL; } +#if !CYTHON_USE_TYPE_SLOTS + else { + next = PyIter_Next(iterator); + if (likely(next)) + return next; + } +#endif return __Pyx_PyIter_Next2Default(defval); } /* RaiseException */ - #if PY_MAJOR_VERSION < 3 + #if PY_MAJOR_VERSION < 3 static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, CYTHON_UNUSED PyObject *cause) { __Pyx_PyThreadState_declare @@ -7743,7 +7863,7 @@ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject #endif /* SaveResetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #if PY_VERSION_HEX >= 0x030700A2 *type = tstate->exc_state.exc_type; @@ -7782,7 +7902,7 @@ static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject #endif /* PyErrExceptionMatches */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx_PyErr_ExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(tuple); @@ -7807,7 +7927,7 @@ static CYTHON_INLINE int __Pyx_PyErr_ExceptionMatchesInState(PyThreadState* tsta #endif /* PyIntBinop */ - #if !CYTHON_COMPILING_IN_PYPY + #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED long intval, CYTHON_UNUSED int inplace) { #if PY_MAJOR_VERSION < 3 if (likely(PyInt_CheckExact(op1))) { @@ -7845,6 +7965,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -7855,6 +7976,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -7865,6 +7987,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -7875,6 +7998,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -7885,6 +8009,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -7895,6 +8020,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; default: return PyLong_Type.tp_as_number->nb_add(op1, op2); } } @@ -7923,20 +8049,20 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED #endif /* RaiseTooManyValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { + static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { PyErr_Format(PyExc_ValueError, "too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected); } /* RaiseNeedMoreValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { + static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { PyErr_Format(PyExc_ValueError, "need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack", index, (index == 1) ? "" : "s"); } /* IterFinish */ - static CYTHON_INLINE int __Pyx_IterFinish(void) { + static CYTHON_INLINE int __Pyx_IterFinish(void) { #if CYTHON_FAST_THREAD_STATE PyThreadState *tstate = __Pyx_PyThreadState_Current; PyObject* exc_type = tstate->curexc_type; @@ -7971,7 +8097,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* UnpackItemEndCheck */ - static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected) { + static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected) { if (unlikely(retval)) { Py_DECREF(retval); __Pyx_RaiseTooManyValuesError(expected); @@ -7983,7 +8109,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* GetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #else static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) { @@ -8053,12 +8179,12 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* None */ - static CYTHON_INLINE void __Pyx_RaiseUnboundLocalError(const char *varname) { + static CYTHON_INLINE void __Pyx_RaiseUnboundLocalError(const char *varname) { PyErr_Format(PyExc_UnboundLocalError, "local variable '%s' referenced before assignment", varname); } /* PyIntBinop */ - #if !CYTHON_COMPILING_IN_PYPY + #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED long intval, CYTHON_UNUSED int inplace) { if (op1 == op2) { Py_RETURN_TRUE; @@ -8090,31 +8216,37 @@ static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED a = -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; #if PyLong_SHIFT < 30 && PyLong_SHIFT != 15 default: return PyLong_Type.tp_richcompare(op1, op2, Py_EQ); #else @@ -8143,7 +8275,7 @@ static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED #endif /* GetAttr */ - static CYTHON_INLINE PyObject *__Pyx_GetAttr(PyObject *o, PyObject *n) { + static CYTHON_INLINE PyObject *__Pyx_GetAttr(PyObject *o, PyObject *n) { #if CYTHON_USE_TYPE_SLOTS #if PY_MAJOR_VERSION >= 3 if (likely(PyUnicode_Check(n))) @@ -8156,7 +8288,7 @@ static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* GetAttr3 */ - static PyObject *__Pyx_GetAttr3Default(PyObject *d) { + static PyObject *__Pyx_GetAttr3Default(PyObject *d) { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign if (unlikely(!__Pyx_PyErr_ExceptionMatches(PyExc_AttributeError))) @@ -8171,7 +8303,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetAttr3(PyObject *o, PyObject *n, PyObject } /* Import */ - static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { + static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { PyObject *empty_list = 0; PyObject *module = 0; PyObject *global_dict = 0; @@ -8236,7 +8368,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetAttr3(PyObject *o, PyObject *n, PyObject } /* ImportFrom */ - static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { + static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { PyObject* value = __Pyx_PyObject_GetAttrStr(module, name); if (unlikely(!value) && PyErr_ExceptionMatches(PyExc_AttributeError)) { PyErr_Format(PyExc_ImportError, @@ -8250,7 +8382,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetAttr3(PyObject *o, PyObject *n, PyObject } /* GetItemInt */ - static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { + static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { PyObject *r; if (!j) return NULL; r = PyObject_GetItem(o, j); @@ -8337,7 +8469,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, } /* HasAttr */ - static CYTHON_INLINE int __Pyx_HasAttr(PyObject *o, PyObject *n) { + static CYTHON_INLINE int __Pyx_HasAttr(PyObject *o, PyObject *n) { PyObject *r; if (unlikely(!__Pyx_PyBaseString_Check(n))) { PyErr_SetString(PyExc_TypeError, @@ -8354,8 +8486,58 @@ static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, } } +/* PyObject_GenericGetAttrNoDict */ + #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static PyObject *__Pyx_RaiseGenericGetAttributeError(PyTypeObject *tp, PyObject *attr_name) { + PyErr_Format(PyExc_AttributeError, +#if PY_MAJOR_VERSION >= 3 + "'%.50s' object has no attribute '%U'", + tp->tp_name, attr_name); +#else + "'%.50s' object has no attribute '%.400s'", + tp->tp_name, PyString_AS_STRING(attr_name)); +#endif + return NULL; +} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GenericGetAttrNoDict(PyObject* obj, PyObject* attr_name) { + PyObject *descr; + PyTypeObject *tp = Py_TYPE(obj); + if (unlikely(!PyString_Check(attr_name))) { + return PyObject_GenericGetAttr(obj, attr_name); + } + assert(!tp->tp_dictoffset); + descr = _PyType_Lookup(tp, attr_name); + if (unlikely(!descr)) { + return __Pyx_RaiseGenericGetAttributeError(tp, attr_name); + } + Py_INCREF(descr); + #if PY_MAJOR_VERSION < 3 + if (likely(PyType_HasFeature(Py_TYPE(descr), Py_TPFLAGS_HAVE_CLASS))) + #endif + { + descrgetfunc f = Py_TYPE(descr)->tp_descr_get; + if (unlikely(f)) { + PyObject *res = f(descr, obj, (PyObject *)tp); + Py_DECREF(descr); + return res; + } + } + return descr; +} +#endif + +/* PyObject_GenericGetAttr */ + #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static PyObject* __Pyx_PyObject_GenericGetAttr(PyObject* obj, PyObject* attr_name) { + if (unlikely(Py_TYPE(obj)->tp_dictoffset)) { + return PyObject_GenericGetAttr(obj, attr_name); + } + return __Pyx_PyObject_GenericGetAttrNoDict(obj, attr_name); +} +#endif + /* SetupReduce */ - static int __Pyx_setup_reduce_is_named(PyObject* meth, PyObject* name) { + static int __Pyx_setup_reduce_is_named(PyObject* meth, PyObject* name) { int ret; PyObject *name_attr; name_attr = __Pyx_PyObject_GetAttrStr(meth, __pyx_n_s_name); @@ -8431,18 +8613,21 @@ static int __Pyx_setup_reduce(PyObject* type_obj) { } /* CLineInTraceback */ - #ifndef CYTHON_CLINE_IN_TRACEBACK + #ifndef CYTHON_CLINE_IN_TRACEBACK static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_line) { PyObject *use_cline; PyObject *ptype, *pvalue, *ptraceback; #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { - use_cline = PyDict_GetItem(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); + use_cline = __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); } else #endif { @@ -8468,7 +8653,7 @@ static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_li #endif /* CodeObjectCache */ - static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { + static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { int start = 0, mid = 0, end = count - 1; if (end >= 0 && code_line > entries[end].code_line) { return count; @@ -8548,7 +8733,7 @@ static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { } /* AddTraceback */ - #include "compile.h" + #include "compile.h" #include "frameobject.h" #include "traceback.h" static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( @@ -8633,7 +8818,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_PY_LONG_LONG(PY_LONG_LONG value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_PY_LONG_LONG(PY_LONG_LONG value) { const PY_LONG_LONG neg_one = (PY_LONG_LONG) -1, const_zero = (PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -8664,7 +8849,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPyVerify */ - #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ + #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) #define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) @@ -8686,7 +8871,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -8717,7 +8902,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { + static CYTHON_INLINE PY_LONG_LONG __Pyx_PyInt_As_PY_LONG_LONG(PyObject *x) { const PY_LONG_LONG neg_one = (PY_LONG_LONG) -1, const_zero = (PY_LONG_LONG) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -8906,7 +9091,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { + static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -9095,7 +9280,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* CIntFromPy */ - static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { + static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -9284,7 +9469,7 @@ static void __Pyx_AddTraceback(const char *funcname, int c_line, } /* FastTypeChecks */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { while (a) { a = a->tp_base; @@ -9356,7 +9541,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj #endif /* FetchCommonType */ - static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type) { + static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type) { PyObject* fake_module; PyTypeObject* cached_type = NULL; fake_module = PyImport_AddModule((char*) "_cython_" CYTHON_ABI); @@ -9395,7 +9580,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* SwapException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSwap(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { PyObject *tmp_type, *tmp_value, *tmp_tb; #if PY_VERSION_HEX >= 0x030700A2 @@ -9429,7 +9614,7 @@ static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, #endif /* PyObjectCallMethod1 */ - static PyObject* __Pyx__PyObject_CallMethod1(PyObject* method, PyObject* arg) { + static PyObject* __Pyx__PyObject_CallMethod1(PyObject* method, PyObject* arg) { PyObject *result = NULL; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(method))) { @@ -9471,17 +9656,16 @@ static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, return result; } static PyObject* __Pyx_PyObject_CallMethod1(PyObject* obj, PyObject* method_name, PyObject* arg) { - PyObject *method, *result = NULL; + PyObject *method, *result; method = __Pyx_PyObject_GetAttrStr(obj, method_name); - if (unlikely(!method)) goto done; + if (unlikely(!method)) return NULL; result = __Pyx__PyObject_CallMethod1(method, arg); -done: - Py_XDECREF(method); + Py_DECREF(method); return result; } /* CoroutineBase */ - #include + #include #include #define __Pyx_Coroutine_Undelegate(gen) Py_CLEAR((gen)->yieldfrom) static int __Pyx_PyGen__FetchStopIterationValue(CYTHON_UNUSED PyThreadState *__pyx_tstate, PyObject **pvalue) { @@ -9580,7 +9764,7 @@ static void __Pyx__Coroutine_AlreadyRunningError(CYTHON_UNUSED __pyx_CoroutineOb const char *msg; if (0) { #ifdef __Pyx_Coroutine_USED - } else if (__Pyx_Coroutine_CheckExact((PyObject*)gen)) { + } else if (__Pyx_Coroutine_Check((PyObject*)gen)) { msg = "coroutine already executing"; #endif #ifdef __Pyx_AsyncGen_USED @@ -9597,7 +9781,7 @@ static void __Pyx__Coroutine_NotStartedError(CYTHON_UNUSED PyObject *gen) { const char *msg; if (0) { #ifdef __Pyx_Coroutine_USED - } else if (__Pyx_Coroutine_CheckExact(gen)) { + } else if (__Pyx_Coroutine_Check(gen)) { msg = "can't send non-None value to a just-started coroutine"; #endif #ifdef __Pyx_AsyncGen_USED @@ -9612,7 +9796,7 @@ static void __Pyx__Coroutine_NotStartedError(CYTHON_UNUSED PyObject *gen) { #define __Pyx_Coroutine_AlreadyTerminatedError(gen, value, closing) (__Pyx__Coroutine_AlreadyTerminatedError(gen, value, closing), (PyObject*)NULL) static void __Pyx__Coroutine_AlreadyTerminatedError(CYTHON_UNUSED PyObject *gen, PyObject *value, CYTHON_UNUSED int closing) { #ifdef __Pyx_Coroutine_USED - if (!closing && __Pyx_Coroutine_CheckExact(gen)) { + if (!closing && __Pyx_Coroutine_Check(gen)) { PyErr_SetString(PyExc_RuntimeError, "cannot reuse already awaited coroutine"); } else #endif @@ -9718,7 +9902,7 @@ static PyObject *__Pyx_Coroutine_Send(PyObject *self, PyObject *value) { } else #endif #ifdef __Pyx_Coroutine_USED - if (__Pyx_Coroutine_CheckExact(yf)) { + if (__Pyx_Coroutine_Check(yf)) { ret = __Pyx_Coroutine_Send(yf, value); } else #endif @@ -9764,7 +9948,7 @@ static int __Pyx_Coroutine_CloseIter(__pyx_CoroutineObject *gen, PyObject *yf) { } else #endif #ifdef __Pyx_Coroutine_USED - if (__Pyx_Coroutine_CheckExact(yf)) { + if (__Pyx_Coroutine_Check(yf)) { retval = __Pyx_Coroutine_Close(yf); if (!retval) return -1; @@ -9820,6 +10004,11 @@ static PyObject *__Pyx_Generator_Next(PyObject *self) { if (PyGen_CheckExact(yf)) { ret = _PyGen_Send((PyGenObject*)yf, NULL); } else + #endif + #ifdef __Pyx_Coroutine_USED + if (__Pyx_Coroutine_Check(yf)) { + ret = __Pyx_Coroutine_Send(yf, Py_None); + } else #endif ret = Py_TYPE(yf)->tp_iternext(yf); gen->is_running = 0; @@ -9851,7 +10040,7 @@ static PyObject *__Pyx_Coroutine_Close(PyObject *self) { Py_DECREF(retval); if ((0)) { #ifdef __Pyx_Coroutine_USED - } else if (__Pyx_Coroutine_CheckExact(self)) { + } else if (__Pyx_Coroutine_Check(self)) { msg = "coroutine ignored GeneratorExit"; #endif #ifdef __Pyx_AsyncGen_USED @@ -9899,7 +10088,7 @@ static PyObject *__Pyx__Coroutine_Throw(PyObject *self, PyObject *typ, PyObject || __Pyx_Generator_CheckExact(yf) #endif #ifdef __Pyx_Coroutine_USED - || __Pyx_Coroutine_CheckExact(yf) + || __Pyx_Coroutine_Check(yf) #endif ) { ret = __Pyx__Coroutine_Throw(yf, typ, val, tb, args, close_on_genexit); @@ -9968,6 +10157,7 @@ static int __Pyx_Coroutine_clear(PyObject *self) { Py_CLEAR(((__pyx_PyAsyncGenObject*)gen)->ag_finalizer); } #endif + Py_CLEAR(gen->gi_code); Py_CLEAR(gen->gi_name); Py_CLEAR(gen->gi_qualname); Py_CLEAR(gen->gi_modulename); @@ -10153,15 +10343,15 @@ __Pyx_Coroutine_set_qualname(__pyx_CoroutineObject *self, PyObject *value) return 0; } static __pyx_CoroutineObject *__Pyx__Coroutine_New( - PyTypeObject* type, __pyx_coroutine_body_t body, PyObject *closure, + PyTypeObject* type, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name) { __pyx_CoroutineObject *gen = PyObject_GC_New(__pyx_CoroutineObject, type); if (unlikely(!gen)) return NULL; - return __Pyx__Coroutine_NewInit(gen, body, closure, name, qualname, module_name); + return __Pyx__Coroutine_NewInit(gen, body, code, closure, name, qualname, module_name); } static __pyx_CoroutineObject *__Pyx__Coroutine_NewInit( - __pyx_CoroutineObject *gen, __pyx_coroutine_body_t body, PyObject *closure, + __pyx_CoroutineObject *gen, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name) { gen->body = body; gen->closure = closure; @@ -10180,12 +10370,14 @@ static __pyx_CoroutineObject *__Pyx__Coroutine_NewInit( gen->gi_name = name; Py_XINCREF(module_name); gen->gi_modulename = module_name; + Py_XINCREF(code); + gen->gi_code = code; PyObject_GC_Track(gen); return gen; } /* PatchModuleWithCoroutine */ - static PyObject* __Pyx_Coroutine_patch_module(PyObject* module, const char* py_code) { + static PyObject* __Pyx_Coroutine_patch_module(PyObject* module, const char* py_code) { #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) int result; PyObject *globals, *result_obj; @@ -10225,7 +10417,7 @@ static __pyx_CoroutineObject *__Pyx__Coroutine_NewInit( } /* PatchGeneratorABC */ - #ifndef CYTHON_REGISTER_ABCS + #ifndef CYTHON_REGISTER_ABCS #define CYTHON_REGISTER_ABCS 1 #endif #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) @@ -10282,7 +10474,7 @@ static int __Pyx_patch_abc(void) { } /* Generator */ - static PyMethodDef __pyx_Generator_methods[] = { + static PyMethodDef __pyx_Generator_methods[] = { {"send", (PyCFunction) __Pyx_Coroutine_Send, METH_O, (char*) PyDoc_STR("send(arg) -> send 'arg' into generator,\nreturn next yielded value or raise StopIteration.")}, {"throw", (PyCFunction) __Pyx_Coroutine_Throw, METH_VARARGS, @@ -10295,6 +10487,7 @@ static PyMemberDef __pyx_Generator_memberlist[] = { {(char *) "gi_running", T_BOOL, offsetof(__pyx_CoroutineObject, is_running), READONLY, NULL}, {(char*) "gi_yieldfrom", T_OBJECT, offsetof(__pyx_CoroutineObject, yieldfrom), READONLY, (char*) PyDoc_STR("object being iterated by 'yield from', or None")}, + {(char*) "gi_code", T_OBJECT, offsetof(__pyx_CoroutineObject, gi_code), READONLY, NULL}, {0, 0, 0, 0, 0} }; static PyGetSetDef __pyx_Generator_getsets[] = { @@ -10363,7 +10556,7 @@ static PyTypeObject __pyx_GeneratorType_type = { #endif }; static int __pyx_Generator_init(void) { - __pyx_GeneratorType_type.tp_getattro = PyObject_GenericGetAttr; + __pyx_GeneratorType_type.tp_getattro = __Pyx_PyObject_GenericGetAttrNoDict; __pyx_GeneratorType_type.tp_iter = PyObject_SelfIter; __pyx_GeneratorType = __Pyx_FetchCommonType(&__pyx_GeneratorType_type); if (unlikely(!__pyx_GeneratorType)) { @@ -10373,7 +10566,7 @@ static int __pyx_Generator_init(void) { } /* CheckBinaryVersion */ - static int __Pyx_check_binary_version(void) { + static int __Pyx_check_binary_version(void) { char ctversion[4], rtversion[4]; PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION); PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion()); @@ -10389,7 +10582,7 @@ static int __pyx_Generator_init(void) { } /* InitStrings */ - static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { + static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { while (t->p) { #if PY_MAJOR_VERSION < 3 if (t->is_unicode) { @@ -10415,7 +10608,7 @@ static int __pyx_Generator_init(void) { if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) - PyErr_Clear(); + return -1; ++t; } return 0; @@ -10629,6 +10822,9 @@ static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_DECREF(x); return ival; } +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } diff --git a/gensim/corpora/_mmreader.pyx b/gensim/corpora/_mmreader.pyx index 63b3d6cfd0..f4844127a3 100644 --- a/gensim/corpora/_mmreader.pyx +++ b/gensim/corpora/_mmreader.pyx @@ -1,6 +1,8 @@ # Copyright (C) 2018 Radim Rehurek # cython: embedsignature=True + """Reader for corpus in the Matrix Market format.""" + from __future__ import with_statement from gensim import utils @@ -17,7 +19,7 @@ logger = logging.getLogger(__name__) cdef class MmReader(object): - """Matrix market file reader (fast Cython version), used for :class:`~gensim.corpora.mmcorpus.MmCorpus`. + """Matrix market file reader (fast Cython version), used internally in :class:`~gensim.corpora.mmcorpus.MmCorpus`. Wrap a term-document matrix on disk (in matrix-market format), and present it as an object which supports iteration over the rows (~documents). @@ -32,10 +34,10 @@ cdef class MmReader(object): Number of non-zero terms. Notes - ---------- - Note that the file is read into memory one document at a time, not the whole - matrix at once (unlike scipy.io.mmread). This allows us to process corpora - which are larger than the available RAM. + ----- + Note that the file is read into memory one document at a time, not the whole matrix at once + (unlike e.g. `scipy.io.mmread` and other implementations). + This allows us to process corpora which are larger than the available RAM. """ cdef public input @@ -48,11 +50,11 @@ cdef class MmReader(object): Parameters ---------- input : {str, file-like object} - Path to input file in MM format or a file-like object that supports `seek()` - (e.g. :class:`~gzip.GzipFile`, :class:`~bz2.BZ2File`). + Path to the input file in MM format or a file-like object that supports `seek()` + (e.g. smart_open objects). transposed : bool, optional - if True, expects lines to represent doc_id, term_id, value. Else, expects term_id, doc_id, value. + Do lines represent `doc_id, term_id, value`, instead of `term_id, doc_id, value`? """ logger.info("initializing cython corpus reader from %s", input) @@ -83,7 +85,7 @@ cdef class MmReader(object): ) def __len__(self): - """Get size of corpus (number of documents).""" + """Get the corpus size: total number of documents.""" return self.num_docs def __str__(self): @@ -105,18 +107,18 @@ cdef class MmReader(object): break def __iter__(self): - """Iterate through corpus. + """Iterate through all documents in the corpus. Notes ------ Note that the total number of vectors returned is always equal to the number of rows specified - in the header, empty documents are inserted and yielded where appropriate, even if they are not explicitly + in the header: empty documents are inserted and yielded where appropriate, even if they are not explicitly stored in the Matrix Market file. Yields ------ (int, list of (int, number)) - Document id and Document in BoW format + Document id and document in sparse bag-of-words format. """ cdef long long docid, termid, previd @@ -165,17 +167,17 @@ cdef class MmReader(object): yield previd, [] def docbyoffset(self, offset): - """Get document at file offset `offset` (in bytes). + """Get the document at file offset `offset` (in bytes). Parameters ---------- offset : int - Offset, in bytes, of desired document. + File offset, in bytes, of the desired document. Returns ------ list of (int, str) - Document in BoW format. + Document in sparse bag-of-words format. """ # empty documents are not stored explicitly in MM format, so the index marks diff --git a/gensim/corpora/dictionary.py b/gensim/corpora/dictionary.py index 9a9edf24ed..84e2ed9945 100644 --- a/gensim/corpora/dictionary.py +++ b/gensim/corpora/dictionary.py @@ -4,8 +4,7 @@ # Copyright (C) 2010 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html - -"""This module implements the concept of Dictionary -- a mapping between words and their integer ids.""" +"""This module implements the concept of a Dictionary -- a mapping between words and their integer ids.""" from __future__ import with_statement @@ -30,20 +29,23 @@ class Dictionary(utils.SaveLoad, Mapping): """Dictionary encapsulates the mapping between normalized words and their integer ids. + Notable instance attributes: + Attributes - --------- + ---------- token2id : dict of (str, int) token -> tokenId. id2token : dict of (int, str) - Reverse mapping for token2id, initialized in lazy manner to save memory. + Reverse mapping for token2id, initialized in a lazy manner to save memory (not created until needed). dfs : dict of (int, int) - Document frequencies: token_id -> in how many documents contain this token. + Document frequencies: token_id -> how many documents contain this token. num_docs : int Number of documents processed. num_pos : int Total number of corpus positions (number of processed words). num_nnz : int - Total number of non-zeroes in the BOW matrix. + Total number of non-zeroes in the BOW matrix (sum of the number of unique + words per document over the entire corpus). """ def __init__(self, documents=None, prune_at=2000000): @@ -52,17 +54,17 @@ def __init__(self, documents=None, prune_at=2000000): Parameters ---------- documents : iterable of iterable of str, optional - Documents that used for initialization. + Documents to be used to initialize the mapping and collect corpus statistics. prune_at : int, optional - Total number of unique words. Dictionary will keep not more than `prune_at` words. + Dictionary will keep no more than `prune_at` words in its mapping, to limit its RAM footprint. Examples -------- >>> from gensim.corpora import Dictionary >>> >>> texts = [['human', 'interface', 'computer']] - >>> dct = Dictionary(texts) # fit dictionary - >>> dct.add_documents([["cat", "say", "meow"], ["dog"]]) # update dictionary with new documents + >>> dct = Dictionary(texts) # initialize a Dictionary + >>> dct.add_documents([["cat", "say", "meow"], ["dog"]]) # add more document (extend the vocabulary) >>> dct.doc2bow(["dog", "computer", "non_existent_word"]) [(0, 1), (6, 1)] @@ -79,12 +81,12 @@ def __init__(self, documents=None, prune_at=2000000): self.add_documents(documents, prune_at=prune_at) def __getitem__(self, tokenid): - """Get token by provided `tokenid`. + """Get the string token that corresponds to `tokenid`. Parameters ---------- tokenid : int - Id of token + Id of token. Returns ------- @@ -94,7 +96,7 @@ def __getitem__(self, tokenid): Raises ------ KeyError - If `tokenid` isn't contained in :class:`~gensim.corpora.dictionary.Dictionary`. + If this Dictionary doesn't contain such `tokenid`. """ if len(self.id2token) != len(self.token2id): @@ -104,7 +106,7 @@ def __getitem__(self, tokenid): return self.id2token[tokenid] # will throw for non-existent ids def __iter__(self): - """Iterate over tokens that stored.""" + """Iterate over all tokens.""" return iter(self.keys()) if PY3: @@ -145,7 +147,9 @@ def __str__(self): @staticmethod def from_documents(documents): - """Create :class:`~gensim.corpora.dictionary.Dictionary` based on `documents` + """Create :class:`~gensim.corpora.dictionary.Dictionary` from `documents`. + + Equivalent to `Dictionary(documents=documents)`. Parameters ---------- @@ -155,7 +159,7 @@ def from_documents(documents): Returns ------- :class:`~gensim.corpora.dictionary.Dictionary` - Dictionary filled by `documents`. + Dictionary initialized from `documents`. """ return Dictionary(documents=documents) @@ -168,18 +172,17 @@ def add_documents(self, documents, prune_at=2000000): documents : iterable of iterable of str Input corpus. All tokens should be already **tokenized and normalized**. prune_at : int, optional - Total number of unique words. Dictionary will keep not more than `prune_at` words. + Dictionary will keep no more than `prune_at` words in its mapping, to limit its RAM footprint. Examples -------- >>> from gensim.corpora import Dictionary >>> >>> corpus = ["máma mele maso".split(), "ema má máma".split()] - >>> dct = Dictionary(corpus) >>> len(dct) 5 - >>> dct.add_documents([["this","is","sparta"],["just","joking"]]) + >>> dct.add_documents([["this", "is", "sparta"], ["just", "joking"]]) >>> len(dct) 10 @@ -200,21 +203,21 @@ def add_documents(self, documents, prune_at=2000000): ) def doc2bow(self, document, allow_update=False, return_missing=False): - """Convert `document` into the bag-of-words (BoW) format = list of (token_id, token_count). + """Convert `document` into the bag-of-words (BoW) format = list of `(token_id, token_count)` tuples. Parameters ---------- - document : list of str + document : list of str Input document. allow_update : bool, optional - If True - update dictionary in the process (i.e. add new tokens and update frequencies). + Update self, by adding new tokens from `document` and updating internal corpus statistics. return_missing : bool, optional - Also return missing tokens (that doesn't contains in current dictionary). + Return missing tokens (tokens present in `document` but not in self) with frequencies? Return ------ list of (int, int) - BoW representation of `document` + BoW representation of `document`. list of (int, int), dict of (str, int) If `return_missing` is True, return BoW representation of `document` + dictionary with missing tokens and their frequencies. @@ -223,9 +226,9 @@ def doc2bow(self, document, allow_update=False, return_missing=False): -------- >>> from gensim.corpora import Dictionary >>> dct = Dictionary(["máma mele maso".split(), "ema má máma".split()]) - >>> dct.doc2bow(["this","is","máma"]) + >>> dct.doc2bow(["this", "is", "máma"]) [(2, 1)] - >>> dct.doc2bow(["this","is","máma"], return_missing=True) + >>> dct.doc2bow(["this", "is", "máma"], return_missing=True) ([(2, 1)], {u'this': 1, u'is': 1}) """ @@ -265,9 +268,6 @@ def doc2bow(self, document, allow_update=False, return_missing=False): def doc2idx(self, document, unknown_word_index=-1): """Convert `document` (a list of words) into a list of indexes = list of `token_id`. - - Notes - ----- Replace all unknown words i.e, words not in the dictionary with the index as set via `unknown_word_index`. Parameters @@ -280,7 +280,7 @@ def doc2idx(self, document, unknown_word_index=-1): Returns ------- list of int - Indexes in the dictionary for words in the `document` (preserving the order of words). + Token ids for tokens in `document`, in the same order. Examples -------- @@ -299,7 +299,7 @@ def doc2idx(self, document, unknown_word_index=-1): return [self.token2id.get(word, unknown_word_index) for word in document] def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000, keep_tokens=None): - """Filter tokens in dictionary by frequency. + """Filter out tokens in the dictionary by their frequency. Parameters ---------- @@ -315,15 +315,15 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000, keep_tokens=N Notes ----- - For tokens that appear in: - - #. Less than `no_below` documents (absolute number) or \n - #. More than `no_above` documents (fraction of total corpus size, **not absolute number**). - #. After (1) and (2), keep only the first `keep_n` most frequent tokens (or keep all if `None`). + This removes all tokens in the dictionary that are: + #. Less frequent than `no_below` documents (absolute number, e.g. `5`) or \n + #. More frequent than `no_above` documents (fraction of the total corpus size, e.g. `0.3`). + #. After (1) and (2), keep only the first `keep_n` most frequent tokens (or keep all if `keep_n=None`). - After the pruning, shrink resulting gaps in word ids. - Due to the gap shrinking, the same word may have a different word id before and after the call to this function! + After the pruning, resulting gaps in word ids are shrunk. + Due to this gap shrinking, **the same word may have a different word id before and after the call + to this function!** Examples -------- @@ -400,7 +400,8 @@ def filter_n_most_frequent(self, remove_n): def filter_tokens(self, bad_ids=None, good_ids=None): """Remove the selected `bad_ids` tokens from :class:`~gensim.corpora.dictionary.Dictionary`. - Alternative - keep selected `good_ids` in :class:`~gensim.corpora.dictionary.Dictionary` and remove the rest. + + Alternatively, keep selected `good_ids` in :class:`~gensim.corpora.dictionary.Dictionary` and remove the rest. Parameters ---------- @@ -438,7 +439,7 @@ def filter_tokens(self, bad_ids=None, good_ids=None): self.compactify() def compactify(self): - """Assign new word ids to all words, shrinking gaps.""" + """Assign new word ids to all words, shrinking any gaps.""" logger.debug("rebuilding dictionary, shrinking gaps") # build mapping from old id -> new id @@ -457,7 +458,7 @@ def save_as_text(self, fname, sort_by_word=True): fname : str Path to output file. sort_by_word : bool, optional - if True - sort by word in lexicographical order. + Sort words in lexicographical order before writing them out? Notes ----- @@ -469,14 +470,15 @@ def save_as_text(self, fname, sort_by_word=True): .... id_k[TAB]word_k[TAB]document_frequency_k[NEWLINE] - Warnings - -------- - Text format should be use for corpus inspection. Use :meth:`~gensim.corpora.dictionary.Dictionary.save` and - :meth:`~gensim.corpora.dictionary.Dictionary.load` to store in binary format (pickle) for better performance. + This text format is great for corpus inspection and debugging. As plaintext, it's also easily portable + to other tools and frameworks. For better performance and to store the entire object state, + including collected corpus statistics, use :meth:`~gensim.corpora.dictionary.Dictionary.save` and + :meth:`~gensim.corpora.dictionary.Dictionary.load` instead. See Also -------- :meth:`~gensim.corpora.dictionary.Dictionary.load_from_text` + Load :class:`~gensim.corpora.dictionary.Dictionary` from text file. Examples -------- @@ -489,7 +491,7 @@ def save_as_text(self, fname, sort_by_word=True): >>> dct = Dictionary(corpus) >>> dct.save_as_text(tmp_fname) >>> - >>> loaded_dct = Dictionary.load_from_text("testdata") + >>> loaded_dct = Dictionary.load_from_text(tmp_fname) >>> assert dct.token2id == loaded_dct.token2id """ @@ -507,23 +509,20 @@ def save_as_text(self, fname, sort_by_word=True): fout.write(utils.to_utf8(line)) def merge_with(self, other): - """Merge another dictionary into this dictionary, mapping same tokens to the same ids and new tokens to new ids. + """Merge another dictionary into this dictionary, mapping the same tokens to the same ids + and new tokens to new ids. Notes ----- The purpose is to merge two corpora created using two different dictionaries: `self` and `other`. `other` can be any id=>word mapping (a dict, a Dictionary object, ...). - Get a transformation object which, when accessed as `result[doc_from_other_corpus]`, will convert documents + Return a transformation object which, when accessed as `result[doc_from_other_corpus]`, will convert documents from a corpus built using the `other` dictionary into a document using the new, merged dictionary. - Warnings - -------- - This method will change `self` dictionary. - Parameters ---------- - other : :class:`~gensim.corpora.dictionary.Dictionary` + other : {dict, :class:`~gensim.corpora.dictionary.Dictionary`} Other dictionary. Return @@ -571,16 +570,18 @@ def merge_with(self, other): @staticmethod def load_from_text(fname): """Load a previously stored :class:`~gensim.corpora.dictionary.Dictionary` from a text file. + Mirror function to :meth:`~gensim.corpora.dictionary.Dictionary.save_as_text`. Parameters ---------- fname: str - Path to file produced by :meth:`~gensim.corpora.dictionary.Dictionary.save_as_text`. + Path to a file produced by :meth:`~gensim.corpora.dictionary.Dictionary.save_as_text`. See Also -------- :meth:`~gensim.corpora.dictionary.Dictionary.save_as_text` + Save :class:`~gensim.corpora.dictionary.Dictionary` to text file. Examples -------- @@ -593,7 +594,7 @@ def load_from_text(fname): >>> dct = Dictionary(corpus) >>> dct.save_as_text(tmp_fname) >>> - >>> loaded_dct = Dictionary.load_from_text("testdata") + >>> loaded_dct = Dictionary.load_from_text(tmp_fname) >>> assert dct.token2id == loaded_dct.token2id """ diff --git a/gensim/corpora/hashdictionary.py b/gensim/corpora/hashdictionary.py index a478c5e79f..85922d16c7 100644 --- a/gensim/corpora/hashdictionary.py +++ b/gensim/corpora/hashdictionary.py @@ -4,10 +4,8 @@ # Copyright (C) 2012 Homer Strong, Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html - -""" -This module implements the "hashing trick" [1]_ -- a mapping between words and their integer ids -using a fixed, static mapping (hash function). +"""Implements the `"hashing trick" `_ -- a mapping between words +and their integer ids using a fixed, static mapping (hash function). Notes ----- @@ -27,12 +25,6 @@ * Multiple words may map to the same id, causing hash collisions. The word <-> id mapping is no longer a bijection. - -References ----------- - -.. [1] http://en.wikipedia.org/wiki/Hashing-Trick - """ from __future__ import with_statement @@ -49,11 +41,7 @@ class HashDictionary(utils.SaveLoad, dict): - """ - Mapping between words and their integer ids, using a hashing function. - - Notes - ----- + """Mapping between words and their integer ids, using a hashing function. Unlike :class:`~gensim.corpora.dictionary.Dictionary`, building a :class:`~gensim.corpora.hashdictionary.HashDictionary` before using it **isn't a necessary step**. @@ -62,7 +50,6 @@ class HashDictionary(utils.SaveLoad, dict): Examples -------- - >>> from gensim.corpora import HashDictionary >>> >>> dct = HashDictionary(debug=False) # needs no training corpus! @@ -77,17 +64,16 @@ def __init__(self, documents=None, id_range=32000, myhash=zlib.adler32, debug=Tr Parameters ---------- - - documents : iterable of iterable of str + documents : iterable of iterable of str, optional Iterable of documents. If given, used to collect additional corpus statistics. :class:`~gensim.corpora.hashdictionary.HashDictionary` can work without these statistics (optional parameter). id_range : int, optional Number of hash-values in table, used as `id = myhash(key) %% id_range`. - myhash : function + myhash : function, optional Hash function, should support interface `myhash(str) -> int`, uses `zlib.adler32` by default. - debug : bool - If True - store which tokens have mapped to a given id. **Will use a lot of RAM**. + debug : bool, optional + Store which tokens have mapped to a given id? **Will use a lot of RAM**. If you find yourself running out of memory (or not sure that you really need raw tokens), keep `debug=False`. @@ -113,17 +99,18 @@ def __init__(self, documents=None, id_range=32000, myhash=zlib.adler32, debug=Tr def __getitem__(self, tokenid): """Get all words that have mapped to the given id so far, as a set. - Works only if you initialized your `HashDictionary` object with `debug=True`. + Warnings + -------- + Works only if you initialized your :class:`~gensim.corpora.hashdictionary.HashDictionary` object + with `debug=True`. Parameters ---------- - tokenid : int Token identifier (result of hashing). Return ------ - set of str Set of all words that have mapped to this id. @@ -136,13 +123,11 @@ def restricted_hash(self, token): Parameters ---------- - token : str Input token. Return ------ - int Hash value of `token`. @@ -169,17 +154,18 @@ def from_documents(*args, **kwargs): return HashDictionary(*args, **kwargs) def add_documents(self, documents): - """Collect corpus statistics from a corpus. Useful only if `debug=True`, to build - the reverse `id=>set(words)` mapping. + """Collect corpus statistics from a corpus. + + Warnings + -------- + Useful only if `debug=True`, to build the reverse `id=>set(words)` mapping. Notes ----- - This is only a convenience wrapper for calling `doc2bow` on each document with `allow_update=True`. Parameters ---------- - documents : iterable of list of str Collection of documents. @@ -208,8 +194,8 @@ def add_documents(self, documents): ) def doc2bow(self, document, allow_update=False, return_missing=False): - """Convert a sequence of words `document` into the bag-of-words format of - `[(word_id, word_count)]` (e.g. `[(1, 4), (150, 1), (2005, 2)]`). + """Convert a sequence of words `document` into the bag-of-words format of `[(word_id, word_count)]` + (e.g. `[(1, 4), (150, 1), (2005, 2)]`). Notes ----- @@ -225,8 +211,8 @@ def doc2bow(self, document, allow_update=False, return_missing=False): document : sequence of str A sequence of word tokens = **tokenized and normalized** strings. allow_update : bool, optional - If True - update corpus statistics and if `debug=True`, also the reverse id=>word mapping. - return_missing : bool + Update corpus statistics and if `debug=True`, also the reverse id=>word mapping? + return_missing : bool, optional Not used. Only here for compatibility with the Dictionary class. Return @@ -272,15 +258,18 @@ def doc2bow(self, document, allow_update=False, return_missing=False): return result def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): - """Filter tokens in the debug dictionary by their frequency. Only makes sense when `debug=True`. + """Filter tokens in the debug dictionary by their frequency. Since :class:`~gensim.corpora.hashdictionary.HashDictionary` id range is fixed and doesn't depend on the number - of tokens seen, this doesn't really "remove" anything. - It only clears some supplementary statistics, for easier debugging and a smaller RAM footprint. + of tokens seen, this doesn't really "remove" anything. It only clears some + internal corpus statistics, for easier debugging and a smaller RAM footprint. + + Warnings + -------- + Only makes sense when `debug=True`. Parameters ---------- - no_below : int, optional Keep tokens which are contained in at least `no_below` documents. no_above : float, optional @@ -291,25 +280,12 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): Notes ----- - For tokens that appear in: #. Less than `no_below` documents (absolute number) or \n #. More than `no_above` documents (fraction of total corpus size, **not absolute number**). #. After (1) and (2), keep only the first `keep_n` most frequent tokens (or keep all if `None`). - Examples - -------- - - >>> from gensim.corpora import HashDictionary - >>> - >>> dct = HashDictionary(debug=True) - >>> - >>> corpus = [["máma", "mele", "maso"], ["ema", "má", "máma"]] - >>> dct.filter_extremes(no_below=1, no_above=0.5, keep_n=1) - >>> print dct.token2id - {'maso': 15025} - """ no_above_abs = int(no_above * self.num_docs) # convert fractional threshold to absolute threshold ok = [item for item in iteritems(self.dfs_debug) if no_below <= item[1] <= no_above_abs] @@ -330,24 +306,25 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000): ) def save_as_text(self, fname): - """Save the debug token=>id mapping to a text file. Only makes sense when `debug=True`, for debugging. + """Save the debug token=>id mapping to a text file. + + Warnings + -------- + Only makes sense when `debug=True`, for debugging. Parameters ---------- - fname : str Path to output file. Notes ----- - The format is: `id[TAB]document frequency of this id[TAB]tab-separated set of words in UTF8 that map to this id[NEWLINE]`. Examples -------- - >>> from gensim.corpora import HashDictionary >>> from gensim.test.utils import get_tmpfile >>> diff --git a/gensim/corpora/mmcorpus.py b/gensim/corpora/mmcorpus.py index d7770607e8..92048bb67d 100644 --- a/gensim/corpora/mmcorpus.py +++ b/gensim/corpora/mmcorpus.py @@ -4,8 +4,7 @@ # Copyright (C) 2010 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html - -"""Corpus in the Matrix Market format.""" +"""Corpus in the `Matrix Market format `_.""" import logging @@ -17,24 +16,28 @@ class MmCorpus(matutils.MmReader, IndexedCorpus): - """Corpus in matrix market format. + """Corpus serialized using the `sparse coordinate Matrix Market format + `_. Wrap a term-document matrix on disk (in matrix-market format), and present it - as an object which supports iteration over the rows (~documents). + as an object which supports iteration over the matrix rows (~documents). + + Notable instance attributes: Attributes - ---------- + ------------------ num_docs : int - Number of documents in market matrix file. + Number of documents in the market matrix file. num_terms : int - Number of terms. + Number of features (terms, topics). num_nnz : int - Number of non-zero terms. + Number of non-zero elements in the sparse MM matrix. Notes - ---------- - Note that the file is read into memory one document at a time, not the whole matrix at once - (unlike :meth:`~scipy.io.mmread`). This allows us to process corpora which are larger than the available RAM. + ----- + The file is read into memory one document at a time, not the whole matrix at once, + unlike e.g. `scipy.io.mmread` and other implementations. This allows you to **process corpora which are larger + than the available RAM**, in a streamed manner. Example -------- @@ -47,7 +50,6 @@ class MmCorpus(matutils.MmReader, IndexedCorpus): ... pass """ - def __init__(self, fname): """ @@ -55,27 +57,26 @@ def __init__(self, fname): ---------- fname : {str, file-like object} Path to file in MM format or a file-like object that supports `seek()` - (e.g. :class:`gzip.GzipFile`, :class:`bz2.BZ2File`). + (e.g. a compressed file opened by `smart_open `_). """ - # avoid calling super(), too confusing IndexedCorpus.__init__(self, fname) matutils.MmReader.__init__(self, fname) def __iter__(self): - """Iterate through document. + """Iterate through all documents. Yields ------ - list of (int, str) - Document in BoW format. + list of (int, numeric) + Document in the `sparse Gensim bag-of-words format `__. Notes ------ The total number of vectors returned is always equal to the number of rows specified in the header. Empty documents are inserted and yielded where appropriate, even if they are not explicitly stored in the - Matrix Market file. + (sparse) Matrix Market file. """ for doc_id, doc in super(MmCorpus, self).__iter__(): @@ -83,7 +84,7 @@ def __iter__(self): @staticmethod def save_corpus(fname, corpus, id2word=None, progress_cnt=1000, metadata=False): - """Save a corpus in the Matrix Market format to disk. + """Save a corpus to disk in the sparse coordinate Matrix Market format. Parameters ---------- @@ -92,16 +93,17 @@ def save_corpus(fname, corpus, id2word=None, progress_cnt=1000, metadata=False): corpus : iterable of list of (int, number) Corpus in Bow format. id2word : dict of (int, str), optional - WordId -> Word. + Mapping between word_id -> word. Used to retrieve the total vocabulary size if provided. + Otherwise, the total vocabulary size is estimated based on the highest feature id encountered in `corpus`. progress_cnt : int, optional - Progress counter. + How often to report (log) progress. metadata : bool, optional - If true, writes out additional metadata. + Writes out additional metadata? - Notes - ----- - This function is automatically called by `MmCorpus.serialize`; don't - call it directly, call `serialize` instead. + Warnings + -------- + This function is automatically called by :class:`~gensim.corpora.mmcorpus.MmCorpus.serialize`, don't + call it directly, call :class:`~gensim.corpora.mmcorpus.MmCorpus.serialize` instead. Example ------- diff --git a/gensim/corpora/wikicorpus.py b/gensim/corpora/wikicorpus.py index 1c088b9416..966c5d7924 100644 --- a/gensim/corpora/wikicorpus.py +++ b/gensim/corpora/wikicorpus.py @@ -6,19 +6,16 @@ # Copyright (C) 2018 Emmanouil Stergiadis # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html - """Construct a corpus from a Wikipedia (or other MediaWiki-based) database dump. +Uses multiprocessing internally to parallelize the work and process the dump more quickly. + Notes ----- -If you have the `pattern` package installed, this module will use a fancy lemmatization to get a lemma -of each token (instead of plain alphabetic tokenizer). The package is available at [1]_ . - -See :mod:`~gensim.scripts.make_wiki` for a canned (example) script based on this module. +If you have the `pattern `_ package installed, +this module will use a fancy lemmatization to get a lemma of each token (instead of plain alphabetic tokenizer). -References ----------- -.. [1] https://github.com/clips/pattern +See :mod:`gensim.scripts.make_wiki` for a canned (example) command-line script based on this module. """ @@ -89,13 +86,7 @@ 'MediaWiki', 'User', 'Help', 'Book', 'Draft', 'WikiProject', 'Special', 'Talk' ] -"""MediaWiki namespaces [2]_ that ought to be ignored. - -References ----------- -.. [2] https://www.mediawiki.org/wiki/Manual:Namespace - -""" +"""`MediaWiki namespaces `_ that ought to be ignored.""" def find_interlinks(raw): @@ -110,6 +101,7 @@ def find_interlinks(raw): ------- dict Mapping from the linked article to the actual text found. + """ filtered = filter_wiki(raw, promote_remaining=False, simplify_links=False) interlinks_raw = re.findall(RE_P16, filtered) @@ -143,6 +135,7 @@ def filter_wiki(raw, promote_remaining=True, simplify_links=True): ------- str `raw` without markup. + """ # parsing of the wiki markup is not perfect, but sufficient for our purposes # contributions to improving this code are welcome :) @@ -221,18 +214,13 @@ def remove_template(s): Returns ------- str - Сopy of `s` with all the wikimedia markup template removed. See [4]_ for wikimedia templates details. + Сopy of `s` with all the `wikimedia markup template `_ removed. Notes ----- Since template can be nested, it is difficult remove them using regular expressions. - References - ---------- - .. [4] http://meta.wikimedia.org/wiki/Help:Template - """ - # Find the start and end position of each template by finding the opening # '{{' and closing '}}' n_open, n_close = 0, 0 @@ -271,11 +259,8 @@ def remove_file(s): Returns ------- str - Сopy of `s` with all the 'File:' and 'Image:' markup replaced by their corresponding captions. [3]_ - - References - ---------- - .. [3] http://www.mediawiki.org/wiki/Help:Images + Сopy of `s` with all the 'File:' and 'Image:' markup replaced by their `corresponding captions + `_. """ # The regex RE_P15 match a File: or Image: markup @@ -287,7 +272,7 @@ def remove_file(s): def tokenize(content, token_min_len=TOKEN_MIN_LEN, token_max_len=TOKEN_MAX_LEN, lower=True): - """Tokenize a piece of text from wikipedia. + """Tokenize a piece of text from Wikipedia. Set `token_min_len`, `token_max_len` as character length (not bytes!) thresholds for individual tokens. @@ -300,7 +285,7 @@ def tokenize(content, token_min_len=TOKEN_MIN_LEN, token_max_len=TOKEN_MAX_LEN, token_max_len : int Maximal token length. lower : bool - If True - convert `content` to lower case. + Convert `content` to lower case? Returns ------- @@ -398,12 +383,12 @@ def extract_pages(f, filter_namespaces=False): def process_article(args, tokenizer_func=tokenize, token_min_len=TOKEN_MIN_LEN, token_max_len=TOKEN_MAX_LEN, lower=True): - """Parse a wikipedia article, extract all tokens. + """Parse a Wikipedia article, extract all tokens. Notes ----- Set `tokenizer_func` (defaults is :func:`~gensim.corpora.wikicorpus.tokenize`) parameter for languages - like japanese or thai to perform better tokenization. + like Japanese or Thai to perform better tokenization. The `tokenizer_func` needs to take 4 parameters: (text: str, token_min_len: int, token_max_len: int, lower: bool). Parameters @@ -420,7 +405,7 @@ def process_article(args, tokenizer_func=tokenize, token_min_len=TOKEN_MIN_LEN, token_max_len : int Maximal token length. lower : bool - If True - convert article text to lower case. + Convert article text to lower case? Returns ------- @@ -478,7 +463,7 @@ def _process_article(args): class WikiCorpus(TextCorpus): - """Treat a wikipedia articles dump as a **read-only** corpus. + """Treat a Wikipedia articles dump as a read-only, streamed, memory-efficient corpus. Supported dump formats: @@ -489,7 +474,7 @@ class WikiCorpus(TextCorpus): Notes ----- - Dumps for English wikipedia can be founded `here `_. + Dumps for the English Wikipedia can be founded at https://dumps.wikimedia.org/enwiki/. Attributes ---------- @@ -503,39 +488,39 @@ class WikiCorpus(TextCorpus): Examples -------- + >>> from gensim.test.utils import datapath, get_tmpfile >>> from gensim.corpora import WikiCorpus, MmCorpus >>> - >>> wiki = WikiCorpus('enwiki-20100622-pages-articles.xml.bz2') # create word->word_id mapping, takes almost 8h - >>> MmCorpus.serialize('wiki_en_vocab200k.mm', wiki) # another 8h, creates a file in MatrixMarket format and mapping + >>> path_to_wiki_dump = datapath("enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2") + >>> corpus_path = get_tmpfile("wiki-corpus.mm") + >>> + >>> wiki = WikiCorpus(path_to_wiki_dump) # create word->word_id mapping, ~8h on full wiki + >>> MmCorpus.serialize(corpus_path, wiki) # another 8h, creates a file in MatrixMarket format and mapping """ - def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), dictionary=None, filter_namespaces=('0',), tokenizer_func=tokenize, article_min_tokens=ARTICLE_MIN_WORDS, token_min_len=TOKEN_MIN_LEN, token_max_len=TOKEN_MAX_LEN, lower=True): - """Initialize the corpus. - - Unless a dictionary is provided, this scans the corpus once, - to determine its vocabulary. + """ Parameters ---------- fname : str - Path to file with wikipedia dump. + Path to the Wikipedia dump file. processes : int, optional - Number of processes to run, defaults to **number of cpu - 1**. + Number of processes to run, defaults to `max(1, number of cpu - 1)`. lemmatize : bool - Whether to use lemmatization instead of simple regexp tokenization. - Defaults to `True` if *pattern* package installed. + Use lemmatization instead of simple regexp tokenization. + Defaults to `True` if you have the `pattern `_ package installed. dictionary : :class:`~gensim.corpora.dictionary.Dictionary`, optional Dictionary, if not provided, this scans the corpus once, to determine its vocabulary - (this needs **really long time**). - filter_namespaces : tuple of str + **IMPORTANT: this needs a really long time**. + filter_namespaces : tuple of str, optional Namespaces to consider. tokenizer_func : function, optional Function that will be used for tokenization. By default, use :func:`~gensim.corpora.wikicorpus.tokenize`. - Need to support interface: - tokenizer_func(text: str, token_min_len: int, token_max_len: int, lower: bool) -> list of str. + If you inject your own tokenizer, it must conform to this interface: + `tokenizer_func(text: str, token_min_len: int, token_max_len: int, lower: bool) -> list of str` article_min_tokens : int, optional Minimum tokens in article. Article will be ignored if number of tokens is less. token_min_len : int, optional @@ -543,7 +528,11 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction token_max_len : int, optional Maximal token length. lower : bool, optional - If True - convert all text to lower case. + Convert all text to lower case? + + Warnings + -------- + Unless a dictionary is provided, this scans the corpus once, to determine its vocabulary. """ self.fname = fname @@ -565,15 +554,25 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction self.dictionary = dictionary def get_texts(self): - """Iterate over the dump, yielding list of tokens for each article. + """Iterate over the dump, yielding a list of tokens for each article that passed + the length and namespace filtering. + + Uses multiprocessing internally to parallelize the work and process the dump more quickly. Notes ----- This iterates over the **texts**. If you want vectors, just use the standard corpus interface instead of this method: - >>> for vec in wiki_corpus: - >>> print(vec) + Examples + -------- + >>> from gensim.test.utils import datapath + >>> from gensim.corpora import WikiCorpus + >>> + >>> path_to_wiki_dump = datapath("enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2") + >>> + >>> for vec in WikiCorpus(path_to_wiki_dump): + ... pass Yields ------ @@ -583,7 +582,6 @@ def get_texts(self): List of tokens (extracted from the article), page id and article title otherwise. """ - articles, articles_all = 0, 0 positions, positions_all = 0, 0 diff --git a/gensim/interfaces.py b/gensim/interfaces.py index 0261c290f9..327dc9c960 100644 --- a/gensim/interfaces.py +++ b/gensim/interfaces.py @@ -4,11 +4,13 @@ # Copyright (C) 2010 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""This module contains implementations of basic interfaces used across the whole gensim package. -These interfaces usable for building corpus, transformation and similarity classes. +"""Basic interfaces used across the whole Gensim package. -All interfaces are realized as abstract base classes (i.e. some optional functionality is provided in the interface -itself, so that the interfaces should be inherited). +These interfaces are used for building corpora, model transformation and similarity queries. + +The interfaces are realized as abstract base classes. This means some functionality is already +provided in the interface itself, and subclasses should inherit from these interfaces +and implement the missing methods. """ @@ -68,16 +70,8 @@ class CorpusABC(utils.SaveLoad): Corpuses in different formats """ - def __iter__(self): - """Iterate over corpus, **should be overridden in inheritor class**. - - Raises - ------ - NotImplementedError - Since it's abstract class this iterator protocol should be overwritten in the inherited class. - - """ + """Iterate all over corpus.""" raise NotImplementedError('cannot instantiate abstract base class') def save(self, *args, **kwargs): @@ -85,51 +79,40 @@ def save(self, *args, **kwargs): Warnings -------- - This save only "state" of corpus class (not corpus-data at all), - for saving data please use :meth:`~gensim.interfaces.CorpusABC.save_corpus` instead`. + This save only the "state" of a corpus class, not the corpus data! - Parameters - ---------- - *args - Variable length argument list. - **kwargs - Arbitrary keyword arguments. + For saving data use the `serialize` method of the output format you'd like to use + (e.g. :meth:`gensim.corpora.mmcorpus.MmCorpus.serialize`). """ import warnings warnings.warn( - "corpus.save() stores only the (tiny) iteration object; " + "corpus.save() stores only the (tiny) iteration object in memory; " "to serialize the actual corpus content, use e.g. MmCorpus.serialize(corpus)" ) super(CorpusABC, self).save(*args, **kwargs) def __len__(self): - """Get size of the corpus (number of documents), **should be overridden in inheritor class**. - - Raises - ------ - NotImplementedError - Since it's abstract class this method should be reimplemented later. - - """ + """Get the corpus size = the total number of documents in it.""" raise NotImplementedError("must override __len__() before calling len(corpus)") @staticmethod def save_corpus(fname, corpus, id2word=None, metadata=False): - """Saves given `corpus` to disk, **should be overridden in inheritor class**. + """Save `corpus` to disk. Some formats support saving the dictionary (`feature_id -> word` mapping), which can be provided by the optional `id2word` parameter. Notes ----- - Some corpus also support an index of where each document begins, so that the documents on disk + Some corpora also support random access via document indexing, so that the documents on disk can be accessed in O(1) time (see the :class:`gensim.corpora.indexedcorpus.IndexedCorpus` base class). + In this case, :meth:`~gensim.interfaces.CorpusABC.save_corpus` is automatically called internally by :func:`serialize`, which does :meth:`~gensim.interfaces.CorpusABC.save_corpus` plus saves the index at the same time. - Calling :func:`serialize() is preferred to calling :meth:`~gensim.interfaces.CorpusABC.save_corpus`. + Calling :func:`serialize() is preferred to calling :meth:`gensim.interfaces.CorpusABC.save_corpus`. Parameters ---------- @@ -140,27 +123,26 @@ def save_corpus(fname, corpus, id2word=None, metadata=False): id2word : :class:`~gensim.corpora.Dictionary`, optional Dictionary of corpus. metadata : bool, optional - If True, will write some meta-information to `fname` too. + Write additional metadata to a separate too? """ raise NotImplementedError('cannot instantiate abstract base class') class TransformedCorpus(CorpusABC): - """Interface for corpus supports transformations.""" + """Interface for corpora that are the result of an online (streamed) transformation.""" def __init__(self, obj, corpus, chunksize=None, **kwargs): """ Parameters ---------- obj : object - Some corpus class from :mod:`gensim.corpora`. + A transformation :class:`~gensim.interfaces.TransformationABC` object that will be applied + to each document from `corpus` during iteration. corpus : iterable of list of (int, number) - Corpus in BoW format. + Corpus in bag-of-words format. chunksize : int, optional - If provided - more effective processing (by group of documents) will performed. - kwargs - Arbitrary keyword arguments. + If provided, a slightly more effective processing will be performed by grouping documents from `corpus`. """ self.obj, self.corpus, self.chunksize = obj, corpus, chunksize @@ -170,18 +152,18 @@ def __init__(self, obj, corpus, chunksize=None, **kwargs): self.metadata = False def __len__(self): - """Get size of the corpus.""" + """Get corpus size.""" return len(self.corpus) def __iter__(self): - """Iterate over the corpus. + """Iterate over the corpus, applying the selected transformation. - If `chunksize` is set, works in "batch-manner" (more efficient). + If `chunksize` was set in the constructor, works in "batch-manner" (more efficient). Yields ------ list of (int, number) - Document in BoW format + Documents in the sparse Gensim bag-of-words format. """ if self.chunksize: @@ -193,22 +175,26 @@ def __iter__(self): yield self.obj[doc] def __getitem__(self, docno): - """Get element from corpus index `docno`. + """Transform the document at position `docno` within `corpus` specified in the constructor. Parameters ---------- docno : int - Index of document in corpus. + Position of the document to transform. Document offset inside `self.corpus`. + + Notes + ----- + `self.corpus` must support random indexing. Returns ------- list of (int, number) - Document in BoW format + Transformed document in the sparse Gensim bag-of-words format. Raises ------ RuntimeError - If corpus doesn't support slicing (:meth`__getitem__` doesn't exists). + If corpus doesn't support index slicing (`__getitem__` doesn't exists). """ if hasattr(self.corpus, '__getitem__'): @@ -227,26 +213,17 @@ class TransformationABC(utils.SaveLoad): >>> from gensim.test.utils import common_dictionary, common_corpus >>> >>> model = LsiModel(common_corpus, id2word=common_dictionary) - >>> bow_vector = model[common_corpus[0]] # model applied through __getitem__ on document from corpus. - >>> bow_corpus = model[common_corpus] # also, we can apply model on full corpus - + >>> bow_vector = model[common_corpus[0]] # model applied through __getitem__ on one document from corpus. + >>> bow_corpus = model[common_corpus] # also, we can apply model on the full corpus """ - def __getitem__(self, vec): - """Get element of `transformations`, **should be overridden in inheritor class**. - - Transforms vector from one vector space into another **or** whole corpus into another. + """Transform a single document, or a whole corpus, from one vector space into another. Parameters ---------- - vec : object - Given vector. - - Raises - ------ - NotImplementedError - Since it's abstract class this method should be reimplemented later. + vec : {list of (int, number), iterable of list of (int, number)} + Document in bag-of-words, or streamed corpus. """ raise NotImplementedError('cannot instantiate abstract base class') @@ -257,11 +234,9 @@ def _apply(self, corpus, chunksize=None, **kwargs): Parameters ---------- corpus : iterable of list of (int, number) - Corpus in BoW format. + Corpus in sparse Gensim bag-of-words format. chunksize : int, optional - If provided - more effective processing (by group of documents) will performed. - kwargs - Arbitrary keyword arguments. + If provided, a more effective processing will performed. Returns ------- @@ -276,10 +251,9 @@ class SimilarityABC(utils.SaveLoad): """Interface for similarity search over a corpus. In all instances, there is a corpus against which we want to perform the similarity search. - For each similarity search, the input is a document and the output are its similarities + For each similarity search, the input is a document or a corpus, and the output are the similarities to individual corpus documents. - Examples -------- >>> from gensim.similarities import MatrixSimilarity @@ -296,56 +270,45 @@ class SimilarityABC(utils.SaveLoad): See Also -------- :mod:`gensim.similarities` - Provided different type of indexes for search. + Different index implementations of this interface. """ - def __init__(self, corpus): - """Initialization of object, **should be overridden in inheritor class**. + """ Parameters ---------- corpus : iterable of list of (int, number) - Corpus in BoW format. - - Raises - ------ - NotImplementedError - Since it's abstract class this method should be reimplemented later. + Corpus in sparse Gensim bag-of-words format. """ raise NotImplementedError("cannot instantiate Abstract Base Class") def get_similarities(self, doc): - """Get similarity measures of documents of corpus to given `doc`, **should be overridden in inheritor class**. + """Get similarities of the given document or corpus against this index. Parameters ---------- - doc : list of (int, number) - Document in BoW format. - - Raises - ------ - NotImplementedError - Since it's abstract class this method should be reimplemented later. + doc : {list of (int, number), iterable of list of (int, number)} + Document in the sparse Gensim bag-of-words format, or a streamed corpus of such documents. """ raise NotImplementedError("cannot instantiate Abstract Base Class") def __getitem__(self, query): - """Get access to similarities of document/corpus `query` to all documents in the corpus. - - Using :meth:`~gensim.interfaces.SimilarityABC.get_similarities` + """Get similarities of the given document or corpus against this index. + Uses :meth:`~gensim.interfaces.SimilarityABC.get_similarities` internally. Notes ----- - Passing corpus to `query` (instead of document) can be more efficient, because will processed in batching-way. + Passing an entire corpus as `query` can be more efficient than passing its documents one after another, + because it will issue queries in batches internally. Parameters ---------- - query : {list of (int, int), iterable of list of (int, int)} - Document or corpus in BoW format. + query : {list of (int, number), iterable of list of (int, number)} + Document in the sparse Gensim bag-of-words format, or a streamed corpus of such documents. Returns ------- @@ -383,12 +346,12 @@ def __getitem__(self, query): return matutils.full2sparse_clipped(result, self.num_best) def __iter__(self): - """Iterate over all documents, computes similarity against all other documents in the index. + """Iterate over all documents, compute similarity of each document against all other documents in the index. Yields ------ {`scipy.sparse.csr.csr_matrix`, list of (int, float)} - Similarity of current document and all documents of corpus. + Similarity of the current document and all documents in the corpus. """ # turn off query normalization (vectors in the index are assumed to be already normalized) diff --git a/gensim/matutils.py b/gensim/matutils.py index 80fd1e8c29..777de46817 100644 --- a/gensim/matutils.py +++ b/gensim/matutils.py @@ -4,7 +4,7 @@ # Copyright (C) 2011 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""This module contains math helper functions.""" +"""Math helper functions.""" from __future__ import with_statement @@ -31,41 +31,42 @@ def blas(name, ndarray): - """Helper for getting BLAS function, used :func:`scipy.linalg.get_blas_funcs`. + """Helper for getting the appropriate BLAS function, using :func:`scipy.linalg.get_blas_funcs`. Parameters ---------- name : str - Name(s) of BLAS functions without type prefix. + Name(s) of BLAS functions, without the type prefix. ndarray : numpy.ndarray Arrays can be given to determine optimal prefix of BLAS routines. Returns ------- - fortran object - Fortran function for needed operation. + object + BLAS function for the needed operation on the given data type. """ return scipy.linalg.get_blas_funcs((name,), (ndarray,))[0] def argsort(x, topn=None, reverse=False): - """Get indices of the `topn` smallest elements in array `x`. + """Efficiently calculate indices of the `topn` smallest elements in array `x`. Parameters ---------- x : array_like - Array to sort. + Array to get the smallest element indices from. topn : int, optional - Number of indices of the smallest(greatest) elements to be returned if given, - otherwise - indices of all elements will be returned in ascending(descending) order. + Number of indices of the smallest (greatest) elements to be returned. + If not given, indices of all elements will be returned in ascending (descending) order. reverse : bool, optional - If True - return the `topn` greatest elements, in descending order. + Return the `topn` greatest elements in descending order, + instead of smallest elements in ascending order? Returns ------- numpy.ndarray - Array of `topn` indices that.sort the array in the required order. + Array of `topn` indices that sort the array in the requested order. """ x = np.asarray(x) # unify code path for when `x` is not a np array (list, tuple...) @@ -83,38 +84,38 @@ def argsort(x, topn=None, reverse=False): def corpus2csc(corpus, num_terms=None, dtype=np.float64, num_docs=None, num_nnz=None, printprogress=0): - """Convert a streamed corpus in BoW format into a sparse matrix `scipy.sparse.csc_matrix`, + """Convert a streamed corpus in bag-of-words format into a sparse matrix `scipy.sparse.csc_matrix`, with documents as columns. Notes ----- If the number of terms, documents and non-zero elements is known, you can pass - them here as parameters and a more memory efficient code path will be taken. + them here as parameters and a (much) more memory efficient code path will be taken. Parameters ---------- corpus : iterable of iterable of (int, number) Input corpus in BoW format num_terms : int, optional - If provided, the `num_terms` attributes in the corpus will be ignored. + Number of terms in `corpus`. If provided, the `corpus.num_terms` attribute (if any) will be ignored. dtype : data-type, optional - Data type of output matrix. + Data type of output CSC matrix. num_docs : int, optional - If provided, the `num_docs` attributes in the corpus will be ignored. + Number of documents in `corpus`. If provided, the `corpus.num_docs` attribute (in any) will be ignored. num_nnz : int, optional - If provided, the `num_nnz` attributes in the corpus will be ignored. + Number of non-zero elements in `corpus`. If provided, the `corpus.num_nnz` attribute (if any) will be ignored. printprogress : int, optional - Print progress for every `printprogress` number of documents, - If 0 - nothing will be printed. + Log a progress message at INFO level once every `printprogress` documents. 0 to turn off progress logging. Returns ------- scipy.sparse.csc_matrix - Sparse matrix inferred based on `corpus`. + `corpus` converted into a sparse CSC matrix. See Also -------- :class:`~gensim.matutils.Sparse2Corpus` + Convert sparse format to Gensim corpus format. """ try: @@ -195,7 +196,7 @@ def pad(mat, padrow, padcol): def zeros_aligned(shape, dtype, order='C', align=128): - """Get array aligned at `align` byte boundary. + """Get array aligned at `align` byte boundary in memory. Parameters ---------- @@ -221,24 +222,24 @@ def zeros_aligned(shape, dtype, order='C', align=128): def ismatrix(m): - """Check does `m` numpy.ndarray or `scipy.sparse` matrix. + """Check whether `m` is a 2D `numpy.ndarray` or `scipy.sparse` matrix. Parameters ---------- m : object - Candidate for matrix + Object to check. Returns ------- bool - True if `m` is matrix, False otherwise. + Is `m` a 2D `numpy.ndarray` or `scipy.sparse` matrix. """ return isinstance(m, np.ndarray) and m.ndim == 2 or scipy.sparse.issparse(m) def any2sparse(vec, eps=1e-9): - """Convert a numpy.ndarray or `scipy.sparse` vector into gensim BoW format. + """Convert a numpy.ndarray or `scipy.sparse` vector into the Gensim bag-of-words format. Parameters ---------- @@ -261,16 +262,16 @@ def any2sparse(vec, eps=1e-9): def scipy2scipy_clipped(matrix, topn, eps=1e-9): - """Get a `scipy.sparse` vector / matrix consisting of 'topn' elements of the greatest magnitude (absolute value). + """Get the 'topn' elements of the greatest magnitude (absolute value) from a `scipy.sparse` vector or matrix. Parameters ---------- matrix : `scipy.sparse` - Input vector / matrix. + Input vector or matrix (1D or 2D sparse array). topn : int - Number of greatest (by module) elements, that will be in result. + Number of greatest elements, in absolute value, to return. eps : float - PARAMETER IGNORED. + Ignored. Returns ------- @@ -315,12 +316,12 @@ def scipy2scipy_clipped(matrix, topn, eps=1e-9): def scipy2sparse(vec, eps=1e-9): - """Convert a scipy.sparse vector BoW format. + """Convert a scipy.sparse vector into the Gensim bag-of-words format. Parameters ---------- vec : `scipy.sparse` - Sparse vector + Sparse vector. eps : float, optional Value used for threshold, all coordinates less than `eps` will not be presented in result. @@ -328,7 +329,7 @@ def scipy2sparse(vec, eps=1e-9): Returns ------- list of (int, float) - Vector in BoW format. + Vector in Gensim bag-of-words format. """ vec = vec.tocsr() @@ -337,14 +338,14 @@ def scipy2sparse(vec, eps=1e-9): class Scipy2Corpus(object): - """Convert a sequence of dense/sparse vectors into a streamed gensim corpus object. + """Convert a sequence of dense/sparse vectors into a streamed Gensim corpus object. See Also -------- :func:`~gensim.matutils.corpus2csc` + Convert corpus in Gensim format to `scipy.sparse.csc` matrix. """ - def __init__(self, vecs): """ @@ -368,23 +369,25 @@ def __len__(self): def sparse2full(doc, length): - """Convert a document in BoW format into dense numpy array. + """Convert a document in Gensim bag-of-words format into a dense numpy array. Parameters ---------- doc : list of (int, number) - Document in BoW format + Document in BoW format. length : int - Length of result vector + Vector dimensionality. This cannot be inferred from the BoW, and you must supply it explicitly. + This is typically the vocabulary size or number of topics, depending on how you created `doc`. Returns ------- numpy.ndarray - Dense variant of `doc` vector. + Dense numpy vector for `doc`. See Also -------- :func:`~gensim.matutils.full2sparse` + Convert dense array to gensim bag-of-words format. """ result = np.zeros(length, dtype=np.float32) # fill with zeroes (default value) @@ -398,23 +401,25 @@ def sparse2full(doc, length): def full2sparse(vec, eps=1e-9): - """Convert a dense array into the BoW format. + """Convert a dense numpy array into the Gensim bag-of-words format. Parameters ---------- vec : numpy.ndarray - Input dense vector + Dense input vector. eps : float - Threshold value, if coordinate in `vec` < eps, this will not be presented in result. + Feature weight threshold value. Features with `abs(weight) < eps` are considered sparse and + won't be included in the BOW result. Returns ------- list of (int, float) - BoW format of `vec`. + BoW format of `vec`, with near-zero values omitted (sparse vector). See Also -------- :func:`~gensim.matutils.sparse2full` + Convert a document in Gensim bag-of-words format into a dense numpy array. """ vec = np.asarray(vec, dtype=float) @@ -428,6 +433,9 @@ def full2sparse(vec, eps=1e-9): def full2sparse_clipped(vec, topn, eps=1e-9): """Like :func:`~gensim.matutils.full2sparse`, but only return the `topn` elements of the greatest magnitude (abs). + This is more efficient that sorting a vector and then taking the greatest values, especially + where `len(vec) >> topn`. + Parameters ---------- vec : numpy.ndarray @@ -445,6 +453,7 @@ def full2sparse_clipped(vec, topn, eps=1e-9): See Also -------- :func:`~gensim.matutils.full2sparse` + Convert dense array to gensim bag-of-words format. """ # use np.argpartition/argsort and only form tuples that are actually returned. @@ -458,27 +467,29 @@ def full2sparse_clipped(vec, topn, eps=1e-9): def corpus2dense(corpus, num_terms, num_docs=None, dtype=np.float32): - """Convert corpus into a dense numpy array (documents will be columns). + """Convert corpus into a dense numpy 2D array, with documents as columns. Parameters ---------- corpus : iterable of iterable of (int, number) - Input corpus in BoW format. + Input corpus in the Gensim bag-of-words format. num_terms : int - Number of terms in dictionary (will be used as size of output vector. + Number of terms in the dictionary. X-axis of the resulting matrix. num_docs : int, optional - Number of documents in corpus. + Number of documents in the corpus. If provided, a slightly more memory-efficient code path is taken. + Y-axis of the resulting matrix. dtype : data-type, optional - Data type of output matrix + Data type of the output matrix. Returns ------- numpy.ndarray - Dense array that present `corpus`. + Dense 2D array that presents `corpus`. See Also -------- :class:`~gensim.matutils.Dense2Corpus` + Convert dense matrix to Gensim corpus format. """ if num_docs is not None: @@ -493,16 +504,18 @@ def corpus2dense(corpus, num_terms, num_docs=None, dtype=np.float32): class Dense2Corpus(object): - """Treat dense numpy array as a streamed gensim corpus in BoW format. + """Treat dense numpy array as a streamed Gensim corpus in the bag-of-words format. Notes ----- - No data copy is made (changes to the underlying matrix imply changes in the corpus). + No data copy is made (changes to the underlying matrix imply changes in the streamed corpus). See Also -------- :func:`~gensim.matutils.corpus2dense` + Convert Gensim corpus to dense matrix. :class:`~gensim.matutils.Sparse2Corpus` + Convert sparse matrix to Gensim corpus format. """ def __init__(self, dense, documents_columns=True): @@ -513,7 +526,7 @@ def __init__(self, dense, documents_columns=True): dense : numpy.ndarray Corpus in dense format. documents_columns : bool, optional - If True - documents will be column, rows otherwise. + Documents in `dense` represented as columns, as opposed to rows? """ if documents_columns: @@ -522,7 +535,7 @@ def __init__(self, dense, documents_columns=True): self.dense = dense def __iter__(self): - """Iterate over corpus + """Iterate over the corpus. Yields ------ @@ -538,12 +551,14 @@ def __len__(self): class Sparse2Corpus(object): - """Convert a matrix in scipy.sparse format into a streaming gensim corpus. + """Convert a matrix in scipy.sparse format into a streaming Gensim corpus. See Also -------- :func:`~gensim.matutils.corpus2csc` + Convert gensim corpus format to `scipy.sparse.csc` matrix :class:`~gensim.matutils.Dense2Corpus` + Convert dense matrix to gensim corpus. """ def __init__(self, sparse, documents_columns=True): @@ -554,7 +569,7 @@ def __init__(self, sparse, documents_columns=True): sparse : `scipy.sparse` Corpus scipy sparse format documents_columns : bool, optional - If True - documents will be column, rows otherwise. + Documents will be column? """ if documents_columns: @@ -578,7 +593,7 @@ def __len__(self): return self.sparse.shape[1] def __getitem__(self, document_index): - """Get a single document in the corpus by its index. + """Retrieve a document vector from the corpus by its index. Parameters ---------- @@ -597,12 +612,12 @@ def __getitem__(self, document_index): def veclen(vec): - """Calculate length of vector + """Calculate L2 (euclidean) length of a vector. Parameters ---------- vec : list of (int, number) - Input vector in BoW format. + Input vector in sparse bag-of-words format. Returns ------- @@ -618,7 +633,7 @@ def veclen(vec): def ret_normalized_vec(vec, length): - """Normalize vector. + """Normalize a vector in L2 (Euclidean unit norm). Parameters ---------- @@ -630,7 +645,7 @@ def ret_normalized_vec(vec, length): Returns ------- list of (int, number) - Normalized vector in BoW format. + L2-normalized vector in BoW format. """ if length != 1.0: @@ -674,16 +689,16 @@ def unitvec(vec, norm='l2', return_norm=False): vec : {numpy.ndarray, scipy.sparse, list of (int, float)} Input vector in any format norm : {'l1', 'l2'}, optional - Normalization that will be used. + Metric to normalize in. return_norm : bool, optional - If True - returns the length of vector `vec`. + Return the length of vector `vec`, in addition to the normalized vector itself? Returns ------- numpy.ndarray, scipy.sparse, list of (int, float)} Normalized vector in same format as `vec`. float - Length of `vec` before normalization. + Length of `vec` before normalization, if `return_norm` is set. Notes ----- @@ -752,14 +767,15 @@ def unitvec(vec, norm='l2', return_norm=False): def cossim(vec1, vec2): """Get cosine similarity between two sparse vectors. - The similarity is a number between <-1.0, 1.0>, higher is more similar. + + Cosine similarity is a number between `<-1.0, 1.0>`, higher means more similar. Parameters ---------- vec1 : list of (int, float) - Vector in BoW format + Vector in BoW format. vec2 : list of (int, float) - Vector in BoW format + Vector in BoW format. Returns ------- @@ -784,9 +800,15 @@ def softcossim(vec1, vec2, similarity_matrix): """Get Soft Cosine Measure between two vectors given a term similarity matrix. Return Soft Cosine Measure between two sparse vectors given a sparse term similarity matrix - in the :class:`scipy.sparse.csc_matrix` format. The similarity is a number between <-1.0, 1.0>, + in the :class:`scipy.sparse.csc_matrix` format. The similarity is a number between `<-1.0, 1.0>`, higher is more similar. + Notes + ----- + Soft Cosine Measure was perhaps first defined by `Grigori Sidorov et al., + "Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model" + `_. + Parameters ---------- vec1 : list of (int, float) @@ -814,13 +836,6 @@ def softcossim(vec1, vec2, similarity_matrix): :class:`gensim.similarities.docsim.SoftCosineSimilarity` A class for performing corpus-based similarity queries with Soft Cosine Measure. - References - ---------- - Soft Cosine Measure was perhaps first defined by [sidorovetal14]_. - - .. [sidorovetal14] Grigori Sidorov et al., "Soft Similarity and Soft Cosine Measure: Similarity - of Features in Vector Space Model", 2014, http://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/2043/1921. - """ if not isinstance(similarity_matrix, scipy.sparse.csc_matrix): if isinstance(similarity_matrix, scipy.sparse.csr_matrix): @@ -852,17 +867,17 @@ def softcossim(vec1, vec2, similarity_matrix): def isbow(vec): - """Checks if vector passed is in BoW format. + """Checks if a vector is in the sparse Gensim bag-of-words format. Parameters ---------- vec : object - Input vector in any format + Object to check. Returns ------- bool - True if vector in BoW format, False otherwise. + Is `vec` in BoW format. """ if scipy.sparse.issparse(vec): @@ -877,24 +892,7 @@ def isbow(vec): return True -def convert_vec(vec1, vec2, num_features=None): - """Convert vectors to dense format - - Parameters - ---------- - vec1 : {scipy.sparse, list of (int, float)} - Input vector. - vec2 : {scipy.sparse, list of (int, float)} - Input vector. - num_features : int, optional - Number of features in vector. - - Returns - ------- - (numpy.ndarray, numpy.ndarray) - (`vec1`, `vec2`) in dense format. - - """ +def _convert_vec(vec1, vec2, num_features=None): if scipy.sparse.issparse(vec1): vec1 = vec1.toarray() if scipy.sparse.issparse(vec2): @@ -929,16 +927,16 @@ def kullback_leibler(vec1, vec2, num_features=None): vec2 : {scipy.sparse, numpy.ndarray, list of (int, float)} Distribution vector. num_features : int, optional - Number of features in vector. + Number of features in the vectors. Returns ------- float Kullback-Leibler distance between `vec1` and `vec2`. - Value in range [0, +∞) where values closer to 0 mean less distance (and a higher similarity). + Value in range [0, +∞) where values closer to 0 mean less distance (higher similarity). """ - vec1, vec2 = convert_vec(vec1, vec2, num_features=num_features) + vec1, vec2 = _convert_vec(vec1, vec2, num_features=num_features) return entropy(vec1, vec2) @@ -952,7 +950,7 @@ def jensen_shannon(vec1, vec2, num_features=None): vec2 : {scipy.sparse, numpy.ndarray, list of (int, float)} Distribution vector. num_features : int, optional - Number of features in vector. + Number of features in the vectors. Returns ------- @@ -961,10 +959,10 @@ def jensen_shannon(vec1, vec2, num_features=None): Notes ----- - This is symmetric and finite "version" of :func:`gensim.matutils.kullback_leibler`. + This is a symmetric and finite "version" of :func:`gensim.matutils.kullback_leibler`. """ - vec1, vec2 = convert_vec(vec1, vec2, num_features=num_features) + vec1, vec2 = _convert_vec(vec1, vec2, num_features=num_features) avg_vec = 0.5 * (vec1 + vec2) return 0.5 * (entropy(vec1, avg_vec) + entropy(vec2, avg_vec)) @@ -983,7 +981,7 @@ def hellinger(vec1, vec2): ------- float Hellinger distance between `vec1` and `vec2`. - Value in range [0, 1], where 0 is min distance (max similarity) and 1 is max distance (min similarity). + Value in range `[0, 1]`, where 0 is min distance (max similarity) and 1 is max distance (min similarity). """ if scipy.sparse.issparse(vec1): @@ -1004,7 +1002,7 @@ def hellinger(vec1, vec2): def jaccard(vec1, vec2): - """Calculate Jaccard distance between vectors. + """Calculate Jaccard distance between two vectors. Parameters ---------- @@ -1017,7 +1015,7 @@ def jaccard(vec1, vec2): ------- float Jaccard distance between `vec1` and `vec2`. - Value in range [0, 1], where 0 is min distance (max similarity) and 1 is max distance (min similarity). + Value in range `[0, 1]`, where 0 is min distance (max similarity) and 1 is max distance (min similarity). """ @@ -1050,7 +1048,7 @@ def jaccard(vec1, vec2): def jaccard_distance(set1, set2): - """Calculate Jaccard distance between two sets + """Calculate Jaccard distance between two sets. Parameters ---------- @@ -1063,7 +1061,7 @@ def jaccard_distance(set1, set2): ------- float Jaccard distance between `set1` and `set2`. - Value in range [0, 1], where 0 is min distance (max similarity) and 1 is max distance (min similarity). + Value in range `[0, 1]`, where 0 is min distance (max similarity) and 1 is max distance (min similarity). """ union_cardinality = len(set1 | set2) @@ -1093,7 +1091,7 @@ def logsumexp(x): Warnings -------- - By performance reasons, doesn't support NaNs or 1d, 3d, etc arrays like :func:`scipy.special.logsumexp`. + For performance reasons, doesn't support NaNs or 1d, 3d, etc arrays like :func:`scipy.special.logsumexp`. """ x_max = np.max(x) @@ -1144,20 +1142,25 @@ def dirichlet_expectation(alpha): def qr_destroy(la): """Get QR decomposition of `la[0]`. - Notes - ----- - Using this function should be less memory intense than calling `scipy.linalg.qr(la[0])`, - because the memory used in `la[0]` is reclaimed earlier. - + Parameters + ---------- + la : list of numpy.ndarray + Run QR decomposition on the first elements of `la`. Must not be empty. Returns ------- (numpy.ndarray, numpy.ndarray) Matrices :math:`Q` and :math:`R`. + Notes + ----- + Using this function is less memory intense than calling `scipy.linalg.qr(la[0])`, + because the memory used in `la[0]` is reclaimed earlier. This makes a difference when + decomposing very large arrays, where every memory copy counts. + Warnings -------- - Content of `la` gets destroyed in the process. + Content of `la` as well as `la[0]` gets destroyed in the process. Again, for memory-effiency reasons. """ a = np.asfortranarray(la[0]) @@ -1182,20 +1185,22 @@ def qr_destroy(la): class MmWriter(object): - """Store a corpus in Matrix Market format, used for :class:`~gensim.corpora.mmcorpus.MmCorpus`. + """Store a corpus in `Matrix Market format `_, + using :class:`~gensim.corpora.mmcorpus.MmCorpus`. Notes ----- - Output is written one document at a time, not the whole matrix at once (unlike `scipy.io.mmread`). - This allows us to process corpora which are larger than the available RAM. + The output is written one document at a time, not the whole matrix at once (unlike e.g. `scipy.io.mmread`). + This allows you to write corpora which are larger than the available RAM. The output file is created in a single pass through the input corpus, so that the input can be - a once-only stream (iterator). To achieve this, a fake MM header is written first, statistics are collected + a once-only stream (generator). + + To achieve this, a fake MM header is written first, corpus statistics are collected during the pass (shape of the matrix, number of non-zeroes), followed by a seek back to the beginning of the file, - rewriting the fake header with proper values. + rewriting the fake header with the final values. """ - HEADER_LINE = b'%%MatrixMarket matrix coordinate real general\n' # the only supported MM format def __init__(self, fname): @@ -1242,7 +1247,7 @@ def write_headers(self, num_docs, num_terms, num_nnz): self.headers_written = True def fake_headers(self, num_docs, num_terms, num_nnz): - """Write "fake" headers to file. + """Write "fake" headers to file, to be rewritten once we've scanned the entire corpus. Parameters ---------- @@ -1287,22 +1292,22 @@ def write_vector(self, docno, vector): @staticmethod def write_corpus(fname, corpus, progress_cnt=1000, index=False, num_terms=None, metadata=False): - """Save the corpus to disk in Matrix Market format. + """Save the corpus to disk in `Matrix Market format `_. Parameters ---------- fname : str Filename of the resulting file. corpus : iterable of list of (int, number) - Corpus in Bow format. + Corpus in streamed bag-of-words format. progress_cnt : int, optional Print progress for every `progress_cnt` number of documents. index : bool, optional - If True, the offsets will be return, otherwise return None. + Return offsets? num_terms : int, optional - If provided, the `num_terms` attributes in the corpus will be ignored. + Number of terms in the corpus. If provided, the `corpus.num_terms` attribute (if any) will be ignored. metadata : bool, optional - If True, a metadata file will be generated. + Generate a metadata file? Returns ------- @@ -1315,7 +1320,8 @@ def write_corpus(fname, corpus, progress_cnt=1000, index=False, num_terms=None, See Also -------- - :func:`~gensim.corpora.mmcorpus.MmCorpus.save_corpus` + :func:`gensim.corpora.mmcorpus.MmCorpus.save_corpus` + Save corpus to disk. """ mw = MmWriter(fname) @@ -1372,7 +1378,7 @@ def write_corpus(fname, corpus, progress_cnt=1000, index=False, num_terms=None, return offsets def __del__(self): - """Close `self.fout` file, alias for :meth:`~gensim.matutils.MmWriter.close`. + """Close `self.fout` file. Alias for :meth:`~gensim.matutils.MmWriter.close`. Warnings -------- @@ -1395,7 +1401,7 @@ def close(self): FAST_VERSION = -1 class MmReader(object): - """Matrix market file reader, used for :class:`~gensim.corpora.mmcorpus.MmCorpus`. + """Matrix market file reader, used internally in :class:`~gensim.corpora.mmcorpus.MmCorpus`. Wrap a term-document matrix on disk (in matrix-market format), and present it as an object which supports iteration over the rows (~documents). @@ -1403,30 +1409,29 @@ class MmReader(object): Attributes ---------- num_docs : int - number of documents in market matrix file + Number of documents in market matrix file. num_terms : int - number of terms + Number of terms. num_nnz : int - number of non-zero terms + Number of non-zero terms. Notes - ---------- + ----- Note that the file is read into memory one document at a time, not the whole matrix at once - (unlike :meth:`~scipy.io.mmread`). This allows us to process corpora which are larger than the available RAM. + (unlike e.g. `scipy.io.mmread` and other implementations). + This allows us to process corpora which are larger than the available RAM. """ - def __init__(self, input, transposed=True): """ Parameters ---------- input : {str, file-like object} - Path to input file in MM format or a file-like object that supports `seek()` - (e.g. :class:`~gzip.GzipFile`, :class:`~bz2.BZ2File`). - + Path to the input file in MM format or a file-like object that supports `seek()` + (e.g. smart_open objects). transposed : bool, optional - if True, expects lines to represent doc_id, term_id, value. Else, expects term_id, doc_id, value. + Do lines represent `doc_id, term_id, value`, instead of `term_id, doc_id, value`? """ logger.info("initializing corpus reader from %s", input) @@ -1457,7 +1462,7 @@ def __init__(self, input, transposed=True): ) def __len__(self): - """Get size of corpus (number of documents).""" + """Get the corpus size: total number of documents.""" return self.num_docs def __str__(self): @@ -1479,18 +1484,18 @@ def skip_headers(self, input_file): break def __iter__(self): - """Iterate through corpus. + """Iterate through all documents in the corpus. Notes ------ Note that the total number of vectors returned is always equal to the number of rows specified - in the header, empty documents are inserted and yielded where appropriate, even if they are not explicitly + in the header: empty documents are inserted and yielded where appropriate, even if they are not explicitly stored in the Matrix Market file. Yields ------ (int, list of (int, number)) - Document id and Document in BoW format + Document id and document in sparse bag-of-words format. """ with utils.file_or_filename(self.input) as lines: @@ -1530,17 +1535,17 @@ def __iter__(self): yield previd, [] def docbyoffset(self, offset): - """Get document at file offset `offset` (in bytes). + """Get the document at file offset `offset` (in bytes). Parameters ---------- offset : int - Offset, in bytes, of desired document. + File offset, in bytes, of the desired document. Returns ------ list of (int, str) - Document in BoW format. + Document in sparse bag-of-words format. """ # empty documents are not stored explicitly in MM format, so the index marks diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py index 5ff4e99051..ed6f4c44df 100644 --- a/gensim/models/phrases.py +++ b/gensim/models/phrases.py @@ -2,7 +2,15 @@ # -*- coding: utf-8 -*- # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""Automatically detect common phrases (multi-word expressions / bi-grams) from a stream of sentences. +"""Automatically detect common phrases -- multi-word expressions / word n-grams -- from a stream of sentences. + +Inspired by: + +* `Mikolov, et. al: "Distributed Representations of Words and Phrases and their Compositionality" + `_ +* `"Normalized (Pointwise) Mutual Information in Colocation Extraction" by Gerlof Bouma + `_ + Examples -------- @@ -25,6 +33,7 @@ ... pass """ + import sys import os import logging @@ -86,7 +95,6 @@ def _is_single(obj): class SentenceAnalyzer(object): """Base util class for :class:`~gensim.models.phrases.Phrases` and :class:`~gensim.models.phrases.Phraser`.""" - def score_item(self, worda, wordb, components, scorer): """Get bi-gram score statistics. @@ -119,16 +127,16 @@ def score_item(self, worda, wordb, components, scorer): return -1 def analyze_sentence(self, sentence, threshold, common_terms, scorer): - """Analyze a sentence. + """Analyze a sentence, detecting any bigrams that should be concatenated. Parameters ---------- - sentence : list of str - Token list representing the sentence to be analyzed. + sentence : iterable of str + Token sequence representing the sentence to be analyzed. threshold : float The minimum score for a bigram to be taken into account. common_terms : list of object - List of common terms, they have a special treatment. + List of common terms, they have special treatment. scorer : function Scorer function, as given to :class:`~gensim.models.phrases.Phrases`. See :func:`~gensim.models.phrases.npmi_scorer` and :func:`~gensim.models.phrases.original_scorer`. @@ -136,8 +144,8 @@ def analyze_sentence(self, sentence, threshold, common_terms, scorer): Yields ------ (str, score) - Tuple where first element is bi-gram, second is score (if bi-gram detected), - otherwise - first element is word and second is None. + If bi-gram detected, a tuple where the first element is a detect bigram, second its score. + Otherwise, the first tuple element is a single word and second is None. """ s = [utils.any2utf8(w) for w in sentence] @@ -265,21 +273,21 @@ def __init__(self, sentences=None, min_count=5, threshold=10.0, Notes ----- 'npmi' is more robust when dealing with common words that form part of common bigrams, and - ranges from -1 to 1, but is slower to calculate than the default. + ranges from -1 to 1, but is slower to calculate than the default. The default is the PMI-like scoring + as described by `Mikolov, et. al: "Distributed Representations of Words and Phrases and their Compositionality" + `_. - To use a custom scoring function, create a function with the following parameters and set the `scoring` - parameter to the custom function. You must use all the parameters in your function call, even if the - function does not require all the parameters. + To use a custom scoring function, pass in a function with the following signature: - * worda_count - number of occurrences in `sentences` of the first token in the phrase being scored - * wordb_count - number of occurrences in `sentences` of the second token in the phrase being scored - * bigram_count - number of occurrences in `sentences` of the phrase being scored + * worda_count - number of corpus occurrences in `sentences` of the first token in the bigram being scored + * wordb_count - number of corpus occurrences in `sentences` of the second token in the bigram being scored + * bigram_count - number of occurrences in `sentences` of the whole bigram * len_vocab - the number of unique tokens in `sentences` * min_count - the `min_count` setting of the Phrases class * corpus_word_count - the total number of tokens (non-unique) in `sentences` - A scoring function without any of these parameters (even if the parameters are not used) will - raise a ValueError on initialization of the Phrases class. The scoring function must be picklable. + The scoring function **must accept all these parameters**, even if it doesn't use them in its scoring. + The scoring function **must be pickleable**. """ if min_count <= 0: @@ -336,8 +344,8 @@ def __init__(self, sentences=None, min_count=5, threshold=10.0, @classmethod def load(cls, *args, **kwargs): - """Load a previously saved Phrases class. Handles backwards compatibility from older Phrases versions - which did not support pluggable scoring functions. + """Load a previously saved Phrases class. + Handles backwards compatibility from older Phrases versions which did not support pluggable scoring functions. Parameters ---------- @@ -493,21 +501,21 @@ def add_vocab(self, sentences): self.vocab = vocab def export_phrases(self, sentences, out_delimiter=b' ', as_tuples=False): - """Get all phrases from given 'sentences'. + """Get all phrases that appear in 'sentences' that pass the bigram threshold. Parameters ---------- sentences : iterable of list of str Text corpus. out_delimiter : str, optional - Delimiter that will be used for "glue" words to phrase. + Delimiter used to "glue" together words that form a bigram phrase. as_tuples : bool, optional - If True - yield (tuple(words), score), otherwise - (out_delimiter.join(words), score). + Yield `(tuple(words), score)` instead of `(out_delimiter.join(words), score)`? Yields ------ ((str, str), float) **or** (str, float) - Phrases given from `sentences`, type depends on `as_tuples` parameter. + Phrases detected in `sentences`. Return type depends on the `as_tuples` parameter. Example ------- @@ -544,7 +552,7 @@ def export_phrases(self, sentences, out_delimiter=b' ', as_tuples=False): yield (out_delimiter.join(words), score) def __getitem__(self, sentence): - """Convert the input tokens `sentence` into phrase tokens (where detected phrases are joined by delimiter). + """Convert the input tokens `sentence` into tokens where detected bigrams are joined by a selected delimiter. If `sentence` is an entire corpus (iterable of sentences rather than a single sentence), return an iterable that converts each of the corpus' sentences @@ -557,8 +565,9 @@ def __getitem__(self, sentence): Returns ------- - {list of str, :class:`gensim.iterfaces.TransformedCorpus`} - `sentences` with phrases, type depends on `sentence` type. + {list of str, :class:`gensim.interfaces.TransformedCorpus`} + `sentence` with detected phrase bigrams merged together, or a streamed corpus of such sentences + if the input was a corpus. Examples ---------- @@ -576,16 +585,13 @@ def __getitem__(self, sentence): >>> #Both of these tokens appear in corpus at least twice, and phrase score is higher, than treshold = 1: >>> print(phrases[sent]) [u'trees_graph', u'minors'] - - >>> from gensim.test.utils import datapath - >>> from gensim.models.word2vec import Text8Corpus - >>> from gensim.models.phrases import Phrases >>> >>> sentences = Text8Corpus(datapath('testcorpus.txt')) >>> phrases = Phrases(sentences, min_count=1, threshold=1) + >>> phraser = Phraser(phrases) # for speedup >>> >>> sent = [[u'trees', u'graph', u'minors'],[u'graph', u'minors']] - >>> for phrase in phrases[sent]: + >>> for phrase in phraser[sent]: ... pass """ @@ -621,8 +627,8 @@ def __getitem__(self, sentence): def original_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count, corpus_word_count): - """Calculation score, based on original `"Efficient Estimaton of Word Representations in Vector Space" by - Mikolov `_. + """Bigram scoring function, based on the original `Mikolov, et. al: "Distributed Representations + of Words and Phrases and their Compositionality" `_. Parameters ---------- @@ -635,13 +641,13 @@ def original_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count len_vocab : int Size of vocabulary. min_count: int - Minimal score threshold. + Minimum score threshold. corpus_word_count : int - NOT USED. + Not used in this particular scoring technique. Notes ----- - Formula: :math:`\\frac{(worda\_count - min\_count) * len\_vocab }{ (worda\_count * wordb\_count)}`. + Formula: :math:`\\frac{(bigram\_count - min\_count) * len\_vocab }{ (worda\_count * wordb\_count)}`. """ return (bigram_count - min_count) / worda_count / wordb_count * len_vocab @@ -660,11 +666,11 @@ def npmi_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count, co bigram_count : int Number of co-occurrences for phrase "worda_wordb". len_vocab : int - NOT USED. + Not used. min_count: int - NOT USED. + Not used. corpus_word_count : int - Number of words in corpus. + Total number of words in the corpus. Notes ----- @@ -679,7 +685,7 @@ def npmi_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count, co def pseudocorpus(source_vocab, sep, common_terms=frozenset()): - """Feeds source_vocab's compound keys back to it, to discover phrases. + """Feeds `source_vocab`'s compound keys back to it, to discover phrases. Parameters ---------- @@ -712,7 +718,14 @@ def pseudocorpus(source_vocab, sep, common_terms=frozenset()): class Phraser(SentenceAnalyzer, PhrasesTransformation): - """Minimal state & functionality to apply results of a :class:`~gensim.models.phrases.Phrases`.""" + """Minimal state & functionality exported from :class:`~gensim.models.phrases.Phrases`. + + The goal of this class is to cut down memory consumption of `Phrases`, by discarding model state + not strictly needed for the bigram detection task. + + Use this instead of `Phrases` if you do not need to update the bigram statistics with new documents any more. + + """ def __init__(self, phrases_model): """ @@ -777,7 +790,7 @@ def pseudocorpus(self, phrases_model): return pseudocorpus(phrases_model.vocab, phrases_model.delimiter, phrases_model.common_terms) def score_item(self, worda, wordb, components, scorer): - """Score bigram. + """Score a bigram. Parameters ---------- @@ -802,17 +815,18 @@ def score_item(self, worda, wordb, components, scorer): return -1 def __getitem__(self, sentence): - """Convert the input tokens `sentence` into phrase tokens. + """Convert the input sequence of tokens `sentence` into a sequence of tokens where adjacent + tokens are replaced by a single token if they form a bigram collocation. Parameters ---------- sentence : {list of str, iterable of list of str} - Input sentence or sentences. + Input sentence or a stream of sentences. Return ------ {list of str, iterable of list of str} - Sentence or sentences with phrase tokens that joined by delimiter-character. + Sentence or sentences with phrase tokens joined by `self.delimiter` character. Examples ---------- diff --git a/gensim/models/tfidfmodel.py b/gensim/models/tfidfmodel.py index 68e83d8e6f..ae24556835 100644 --- a/gensim/models/tfidfmodel.py +++ b/gensim/models/tfidfmodel.py @@ -5,6 +5,13 @@ # Copyright (C) 2017 Mohit Rathore # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html +"""This module implements functionality related to the `Term Frequency - Inverse Document Frequency +` vector space bag-of-words models. + +For a more in-depth exposition of TF-IDF and its various SMART variants (normalization, weighting schemes), +see the blog post at https://rare-technologies.com/pivoted-document-length-normalisation/ + +""" import logging from functools import partial @@ -18,7 +25,7 @@ def resolve_weights(smartirs): - """Checks for validity of `smartirs` parameter. + """Check the validity of `smartirs` parameters. Parameters ---------- @@ -32,20 +39,22 @@ def resolve_weights(smartirs): Returns ------- - w_tf : str - Term frequency weighing: + 3-tuple (local_letter, global_letter, normalization_letter) + + local_letter : str + Term frequency weighing, one of: * `n` - natural, * `l` - logarithm, * `a` - augmented, * `b` - boolean, * `L` - log average. - w_df : str - Document frequency weighting: + global_letter : str + Document frequency weighting, one of: * `n` - none, * `t` - idf, * `p` - prob idf. - w_n : str - Document normalization: + normalization_letter : str + Document normalization, one of: * `n` - none, * `c` - cosine. @@ -53,7 +62,7 @@ def resolve_weights(smartirs): ------ ValueError If `smartirs` is not a string of length 3 or one of the decomposed value - doesn't fit the list of permissible values + doesn't fit the list of permissible values. """ if not isinstance(smartirs, str) or len(smartirs) != 3: @@ -74,12 +83,12 @@ def resolve_weights(smartirs): def df2idf(docfreq, totaldocs, log_base=2.0, add=0.0): - """Compute default inverse-document-frequency for a term with document frequency: - :math:`idf = add + log_{log\_base} \\frac{totaldocs}{doc\_freq}` + """Compute inverse-document-frequency for a term with the given document frequency `docfreq`: + :math:`idf = add + log_{log\_base} \\frac{totaldocs}{docfreq}` Parameters ---------- - docfreq : float + docfreq : {int, float} Document frequency. totaldocs : int Total number of documents. @@ -103,16 +112,17 @@ def precompute_idfs(wglobal, dfs, total_docs): Parameters ---------- wglobal : function - Custom function for calculation idf, look at "universal" :func:`~gensim.models.tfidfmodel.updated_wglobal`. + Custom function for calculating the "global" weighting function. + See for example the SMART alternatives under :func:`~gensim.models.tfidfmodel.smartirs_wglobal`. dfs : dict - Dictionary with term_id and how many documents this token appeared. + Dictionary mapping `term_id` into how many documents did that term appear in. total_docs : int - Total number of document. + Total number of documents. Returns ------- - dict - Precomputed idfs in format {term_id_1: idfs_1, term_id_2: idfs_2, ...} + dict of (int, float) + Inverse document frequencies in the format `{term_id_1: idfs_1, term_id_2: idfs_2, ...}`. """ # not strictly necessary and could be computed on the fly in TfidfModel__getitem__. @@ -120,36 +130,36 @@ def precompute_idfs(wglobal, dfs, total_docs): return {termid: wglobal(df, total_docs) for termid, df in iteritems(dfs)} -def updated_wlocal(tf, n_tf): - """A scheme to transform `tf` or term frequency based on the value of `n_tf`. +def smartirs_wlocal(tf, local_scheme): + """Calculate local term weight for a term using the weighting scheme specified in `local_scheme`. Parameters ---------- tf : int Term frequency. - n_tf : {'n', 'l', 'a', 'b', 'L'} - Parameter to decide the current transformation scheme. + local : {'n', 'l', 'a', 'b', 'L'} + Local transformation scheme. Returns ------- float - Calculated wlocal. + Calculated local weight. """ - if n_tf == "n": + if local_scheme == "n": return tf - elif n_tf == "l": + elif local_scheme == "l": return 1 + np.log2(tf) - elif n_tf == "a": + elif local_scheme == "a": return 0.5 + (0.5 * tf / tf.max(axis=0)) - elif n_tf == "b": + elif local_scheme == "b": return tf.astype('bool').astype('int') - elif n_tf == "L": + elif local_scheme == "L": return (1 + np.log2(tf)) / (1 + np.log2(tf.mean(axis=0))) -def updated_wglobal(docfreq, totaldocs, n_df): - """A scheme to transform `docfreq` or document frequency based on the value of `n_df`. +def smartirs_wglobal(docfreq, totaldocs, global_scheme): + """Calculate global document weight based on the weighting scheme specified in `global_scheme`. Parameters ---------- @@ -157,56 +167,59 @@ def updated_wglobal(docfreq, totaldocs, n_df): Document frequency. totaldocs : int Total number of documents. - n_df : {'n', 't', 'p'} - Parameter to decide the current transformation scheme. + global_scheme : {'n', 't', 'p'} + Global transformation scheme. Returns ------- float - Calculated wglobal. + Calculated global weight. """ - if n_df == "n": + if global_scheme == "n": return 1. - elif n_df == "t": + elif global_scheme == "t": return np.log2(1.0 * totaldocs / docfreq) - elif n_df == "p": + elif global_scheme == "p": return max(0, np.log2((1.0 * totaldocs - docfreq) / docfreq)) -def updated_normalize(x, n_n, return_norm=False): - """Normalizes the final tf-idf value according to the value of `n_n`. +def smartirs_normalize(x, norm_scheme, return_norm=False): + """Normalize a vector using the normalization scheme specified in `norm_scheme`. Parameters ---------- x : numpy.ndarray Input array - n_n : {'n', 'c'} - Parameter that decides the normalizing function to be used. + norm_scheme : {'n', 'c'} + Normalizing function to use: + `n`: no normalization + `c`: unit L2 norm (scale `x` to unit euclidean length) return_norm : bool, optional - If True - returns the length of vector `x`. + Return the length of `x` as well? Returns ------- numpy.ndarray Normalized array. - float - Vector length. + float (only if return_norm is set) + L2 norm of `x`. """ - if n_n == "n": + if norm_scheme == "n": if return_norm: - return x, 1. + _, length = matutils.unitvec(x, return_norm=return_norm) + return x, length else: return x - elif n_n == "c": + elif norm_scheme == "c": return matutils.unitvec(x, return_norm=return_norm) class TfidfModel(interfaces.TransformationABC): """Objects of this class realize the transformation between word-document co-occurrence matrix (int) - into a locally/globally weighted TF_IDF matrix (positive floats). + into a locally/globally weighted TF-IDF matrix (positive floats). Examples -------- @@ -216,16 +229,15 @@ class TfidfModel(interfaces.TransformationABC): >>> >>> dataset = api.load("text8") >>> dct = Dictionary(dataset) # fit dictionary - >>> corpus = [dct.doc2bow(line) for line in dataset] # convert dataset to BoW format + >>> corpus = [dct.doc2bow(line) for line in dataset] # convert corpus to BoW format >>> >>> model = TfidfModel(corpus) # fit model - >>> vector = model[corpus[0]] # apply model + >>> vector = model[corpus[0]] # apply model to the first corpus document """ - def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.identity, wglobal=df2idf, normalize=True, smartirs=None, pivot=None, slope=0.65): - """Compute tf-idf by multiplying a local component (term frequency) with a global component + """Compute TF-IDF by multiplying a local component (term frequency) with a global component (inverse document frequency), and normalizing the resulting documents to unit length. Formula for non-normalized weight of term :math:`i` in document :math:`j` in a corpus of :math:`D` documents @@ -252,9 +264,7 @@ def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.iden wglobal : function, optional Function for global weighting, default is :func:`~gensim.models.tfidfmodel.df2idf`. normalize : bool, optional - It dictates how the final transformed vectors will be normalized. `normalize=True` means set to unit length - (default); `False` means don't normalize. You can also set `normalize` to your own function that accepts - and returns a sparse vector. + Normalize document vectors to unit euclidean length? You can also inject your own function into `normalize`. smartirs : str, optional SMART (System for the Mechanical Analysis and Retrieval of Text) Information Retrieval System, a mnemonic scheme for denoting tf-idf weighting variants in the vector space model. @@ -280,19 +290,21 @@ def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.iden For more information visit `SMART Information Retrieval System `_. pivot : float, optional - It is the point around which the regular normalization curve is `tilted` to get the new pivoted + See the blog post at https://rare-technologies.com/pivoted-document-length-normalisation/. + + Pivot is the point around which the regular normalization curve is `tilted` to get the new pivoted normalization curve. In the paper `Amit Singhal, Chris Buckley, Mandar Mitra: "Pivoted Document Length Normalization" `_ it is the point where the retrieval and relevance curves intersect. - This parameter along with slope is used for pivoted document length normalization. - Only when `pivot` is not None pivoted document length normalization will be applied else regular TfIdf - is used. + + This parameter along with `slope` is used for pivoted document length normalization. + Only when `pivot` is not None will pivoted document length normalization be applied. + Otherwise, regular TfIdf is used. slope : float, optional - It is the parameter required by pivoted document length normalization which determines the slope to which - the `old normalization` can be tilted. This parameter only works when pivot is defined by user and is not - None. - """ + Parameter required by pivoted document length normalization which determines the slope to which + the `old normalization` can be tilted. This parameter only works when pivot is defined. + """ self.id2word = id2word self.wlocal, self.wglobal, self.normalize = wlocal, wglobal, normalize self.num_docs, self.num_nnz, self.idfs = None, None, None @@ -304,13 +316,13 @@ def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.iden # If smartirs is not None, override wlocal, wglobal and normalize if smartirs is not None: n_tf, n_df, n_n = resolve_weights(smartirs) - self.wlocal = partial(updated_wlocal, n_tf=n_tf) - self.wglobal = partial(updated_wglobal, n_df=n_df) + self.wlocal = partial(smartirs_wlocal, local_scheme=n_tf) + self.wglobal = partial(smartirs_wglobal, global_scheme=n_df) # also return norm factor if pivot is not none if self.pivot is None: - self.normalize = partial(updated_normalize, n_n=n_n) + self.normalize = partial(smartirs_normalize, norm_scheme=n_n) else: - self.normalize = partial(updated_normalize, n_n=n_n, return_norm=True) + self.normalize = partial(smartirs_normalize, norm_scheme=n_n, return_norm=True) if dictionary is not None: # user supplied a Dictionary object, which already contains all the @@ -334,19 +346,19 @@ def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.iden @classmethod def load(cls, *args, **kwargs): - """ - Load a previously saved TfidfModel class. Handles backwards compatibility from - older TfidfModel versions which did not use pivoted document normalization. + """Load a previously saved TfidfModel class. Handles backwards compatibility from + older TfidfModel versions which did not use pivoted document normalization. + """ model = super(TfidfModel, cls).load(*args, **kwargs) if not hasattr(model, 'pivot'): - logger.info('older version of %s loaded without pivot arg', cls.__name__) - logger.info('Setting pivot to None.') model.pivot = None + logger.info('older version of %s loaded without pivot arg', cls.__name__) + logger.info('Setting pivot to %s.', model.pivot) if not hasattr(model, 'slope'): - logger.info('older version of %s loaded without slope arg', cls.__name__) - logger.info('Setting slope to 0.65.') model.slope = 0.65 + logger.info('older version of %s loaded without slope arg', cls.__name__) + logger.info('Setting slope to %s.', model.slope) return model def __str__(self): @@ -384,19 +396,21 @@ def initialize(self, corpus): self.idfs = precompute_idfs(self.wglobal, self.dfs, self.num_docs) def __getitem__(self, bow, eps=1e-12): - """Get tf-idf representation of the input vector and/or corpus. + """Get the tf-idf representation of an input vector and/or corpus. bow : {list of (int, int), iterable of iterable of (int, int)} - Input document or copus in BoW format. + Input document in the `sparse Gensim bag-of-words format + `_, + or a streamed corpus of such documents. eps : float Threshold value, will remove all position that have tfidf-value less than `eps`. Returns ------- vector : list of (int, float) - TfIdf vector, if `bow` is document **OR** + TfIdf vector, if `bow` is a single document :class:`~gensim.interfaces.TransformedCorpus` - TfIdf corpus, if `bow` is corpus. + TfIdf corpus, if `bow` is a corpus. """ self.eps = eps diff --git a/gensim/similarities/docsim.py b/gensim/similarities/docsim.py index 5dedc50b67..4e036d720e 100755 --- a/gensim/similarities/docsim.py +++ b/gensim/similarities/docsim.py @@ -4,9 +4,10 @@ # Copyright (C) 2013 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""Computing similarities across a collection of documents in the Vector Space Model. +"""Compute similarities across a collection of documents in the Vector Space Model. The main class is :class:`~gensim.similarities.docsim.Similarity`, which builds an index for a given set of documents. + Once the index is built, you can perform efficient queries like "Tell me how similar is this query document to each document in the index?". The result is a vector of numbers as large as the size of the initial set of documents, that is, one float for each index document. Alternatively, you can also request only the top-N most @@ -16,12 +17,13 @@ How It Works ------------ The :class:`~gensim.similarities.docsim.Similarity` class splits the index into several smaller sub-indexes ("shards"), -which are disk-based. If your entire index fits in memory (~hundreds of thousands documents for 1GB of RAM), +which are disk-based. If your entire index fits in memory (~one million documents per 1GB of RAM), you can also use the :class:`~gensim.similarities.docsim.MatrixSimilarity` or :class:`~gensim.similarities.docsim.SparseMatrixSimilarity` classes directly. -These are more simple but do not scale as well (they keep the entire index in RAM, no sharding). +These are more simple but do not scale as well: they keep the entire index in RAM, no sharding. They also do not +support adding new document to the index dynamically. -Once the index has been initialized, you can query for document similarity simply by: +Once the index has been initialized, you can query for document similarity simply by >>> from gensim.test.utils import common_corpus, common_dictionary, get_tmpfile >>> @@ -31,7 +33,7 @@ >>> index = Similarity(index_tmpfile, common_corpus, num_features=len(common_dictionary)) # build the index >>> similarities = index[query] # get similarities between the query and all index documents -If you have more query documents, you can submit them all at once, in a batch: +If you have more query documents, you can submit them all at once, in a batch >>> from gensim.test.utils import common_corpus, common_dictionary, get_tmpfile >>> @@ -42,12 +44,12 @@ >>> for similarities in index[batch_of_documents]: # the batch is simply an iterable of documents, aka gensim corpus. ... pass -The benefit of this batch (aka "chunked") querying is much better performance. +The benefit of this batch (aka "chunked") querying is a much better performance. To see the speed-up on your machine, run ``python -m gensim.test.simspeed`` (compare to my results `here `_). There is also a special syntax for when you need similarity of documents in the index -to the index itself (i.e. queries=indexed documents themselves). This special syntax +to the index itself (i.e. queries = the indexed documents themselves). This special syntax uses the faster, batch queries internally and **is ideal for all-vs-all pairwise similarities**: >>> from gensim.test.utils import common_corpus, common_dictionary, get_tmpfile @@ -59,6 +61,7 @@ ... pass """ + import logging import itertools import os @@ -89,9 +92,9 @@ class Shard(utils.SaveLoad): :class:`~gensim.similarities.docsim.SparseMatrixSimilarity`, etc, so that it mmaps from disk on request (query). """ - def __init__(self, fname, index): """ + Parameters ---------- fname : str @@ -212,10 +215,8 @@ def query_shard(args): Returns ------- - :class:`numpy.ndarray` - Similarities of document/corpus if index is :class:`~gensim.similarities.docsim.MatrixSimilarity` **or** - :class:`scipy.sparse.csr_matrix` - for case if index is :class:`~gensim.similarities.docsim.SparseMatrixSimilarity`. + :class:`numpy.ndarray` or :class:`scipy.sparse.csr_matrix` + Similarities of the query against documents indexed in this shard. """ query, shard = args # simulate starmap (not part of multiprocessing in older Pythons) @@ -226,15 +227,15 @@ def query_shard(args): class Similarity(interfaces.SimilarityABC): - """Compute cosine similarity of a dynamic query against a static corpus of documents ('the index'). + """Compute cosine similarity of a dynamic query against a corpus of documents ('the index'). + + The index supports adding new documents dynamically. Notes ----- Scalability is achieved by sharding the index into smaller pieces, each of which fits into core memory The shards themselves are simply stored as files to disk and mmap'ed back as needed. - - Examples -------- >>> from gensim.corpora.textcorpus import TextCorpus @@ -276,31 +277,34 @@ def __init__(self, output_prefix, corpus, num_features, num_best=None, chunksize Parameters ---------- output_prefix : str - Prefix for shard filename. If None - random filename in temp will be used. + Prefix for shard filename. If None, a random filename in temp will be used. corpus : iterable of list of (int, number) - Corpus in BoW format. + Corpus in streamed Gensim bag-of-words format. num_features : int Size of the dictionary (number of features). num_best : int, optional If set, return only the `num_best` most similar documents, always leaving out documents with similarity = 0. Otherwise, return a full vector with one float for every document in the index. chunksize : int, optional - Size of block. + Size of query chunks. Used internally when the query is an entire corpus. shardsize : int, optional - Size of shards should be chosen so that a `shardsize x chunksize` matrix of floats fits comfortably - into memory. + Maximum shard size, in documents. Choose a value so that a `shardsize x chunksize` matrix of floats fits + comfortably into your RAM. norm : {'l1', 'l2'}, optional Normalization to use. Notes - ------------ - Documents are split (internally, transparently) into shards of `shardsize` documents each, converted to matrix, - for faster BLAS calls. Each shard is stored to disk under `output_prefix.shard_number`. + ----- + Documents are split (internally, transparently) into shards of `shardsize` documents each, and each shard + converted to a matrix, for faster BLAS calls. Each shard is stored to disk under `output_prefix.shard_number`. + If you don't specify an output prefix, a random filename in temp will be used. - If your entire index fits in memory (~hundreds of thousands - documents for 1GB of RAM), you can also use the :class:`~gensim.similarities.docsim.MatrixSimilarity` - or :class:`~gensim.similarities.docsim.SparseMatrixSimilarity` classes directly. These are more simple - but do not scale as well (they keep the entire index in RAM, no sharding). + + If your entire index fits in memory (~1 million documents per 1GB of RAM), you can also use the + :class:`~gensim.similarities.docsim.MatrixSimilarity` or + :class:`~gensim.similarities.docsim.SparseMatrixSimilarity` classes directly. + These are more simple but do not scale as well (they keep the entire index in RAM, no sharding). + They also do not support adding new document dynamically. """ if output_prefix is None: @@ -427,7 +431,7 @@ def close_shard(self): self.fresh_docs, self.fresh_nnz = [], 0 def reopen_shard(self): - """Reopen incomplete shard.""" + """Reopen an incomplete shard.""" assert self.shards if self.fresh_docs: raise ValueError("cannot reopen a shard with fresh documents in index") @@ -441,18 +445,17 @@ def reopen_shard(self): logger.debug("reopen complete") def query_shards(self, query): - """Applying shard[query] for each shard in `self.shards`, as a sequence. + """Apply shard[query] to each shard in `self.shards`. Used internally. Parameters ---------- query : {iterable of list of (int, number) , list of (int, number))} Document in BoW format or corpus of documents. - Returns ------- - (None, list of ...) - Result of search. + (None, list of individual shard query results) + Query results. """ args = zip([query] * len(self.shards), self.shards) @@ -467,19 +470,17 @@ def query_shards(self, query): return pool, result def __getitem__(self, query): - """Get similarities of document (or corpus) `query` to all documents in the corpus. + """Get similarities of the document (or corpus) `query` to all documents in the corpus. Parameters ---------- query : {iterable of list of (int, number) , list of (int, number))} - Corpus or document of corpus. + A single document in bag-of-words format, or a corpus (iterable) of such documents. Return ------ - :class:`numpy.ndarray` - Similarities of document/corpus if index is :class:`~gensim.similarities.docsim.MatrixSimilarity` **or** - :class:`scipy.sparse.csr_matrix` - for case if index is :class:`~gensim.similarities.docsim.SparseMatrixSimilarity`. + :class:`numpy.ndarray` or :class:`scipy.sparse.csr_matrix` + Similarities of the query against this index. Notes ----- @@ -496,7 +497,7 @@ def __getitem__(self, query): >>> >>> corpus = TextCorpus(datapath('testcorpus.txt')) >>> index = Similarity('temp', corpus, num_features=400) - >>> result = index[corpus] # similarities matrix + >>> result = index[corpus] # pairwise similarities of each document against each document """ self.close_shard() # no-op if no documents added to index since last query @@ -547,7 +548,7 @@ def convert(shard_no, doc): return result def vector_by_id(self, docpos): - """Get indexed vector corresponding to the document at position `docpos`. + """Get the indexed vector corresponding to the document at position `docpos`. Parameters ---------- @@ -557,7 +558,7 @@ def vector_by_id(self, docpos): Return ------ :class:`scipy.sparse.csr_matrix` - Indexed vector, internal type depends on underlying index. + Indexed vector. Examples -------- @@ -584,19 +585,17 @@ def vector_by_id(self, docpos): return result def similarity_by_id(self, docpos): - """Get similarity of the given document only by `docpos`. + """Get similarity of a document specified by its index position `docpos`. Parameters ---------- docpos : int - Document position in index + Document position in the index. Return ------ - :class:`numpy.ndarray` - Similarities of document/corpus if index is :class:`~gensim.similarities.docsim.MatrixSimilarity` **or** - :class:`scipy.sparse.csr_matrix` - for case if index is :class:`~gensim.similarities.docsim.SparseMatrixSimilarity`. + :class:`numpy.ndarray` or :class:`scipy.sparse.csr_matrix` + Similarities of the given document against this index. Examples -------- @@ -617,14 +616,12 @@ def similarity_by_id(self, docpos): def __iter__(self): """For each index document in index, compute cosine similarity against all other documents in the index. - Using :meth:`~gensim.similarities.docsim.Similarity.iter_chunks`. + Uses :meth:`~gensim.similarities.docsim.Similarity.iter_chunks` internally. Yields ------ - :class:`numpy.ndarray` - Similarities of document if index is :class:`~gensim.similarities.docsim.MatrixSimilarity` **or** - :class:`scipy.sparse.csr_matrix` - for case if index is :class:`~gensim.similarities.docsim.SparseMatrixSimilarity`. + :class:`numpy.ndarray` or :class:`scipy.sparse.csr_matrix` + Similarities of each document in turn against the index. """ # turn off query normalization (vectors in the index are already normalized, save some CPU) @@ -640,24 +637,18 @@ def __iter__(self): self.norm = norm # restore normalization def iter_chunks(self, chunksize=None): - """Iteratively yield the index as chunks of documents, each of size <= chunksize. + """Iteratively yield the index as chunks of document vectors, each of size <= chunksize. Parameters ---------- chunksize : int, optional Size of chunk,, if None - `self.chunksize` will be used. - Notes - ----- - The chunk is returned in its raw form. - The size of the chunk may be smaller than requested; it is up to the caller to check the result for real length. - Yields ------ - :class:`numpy.ndarray` - Similarities of document if index is :class:`~gensim.similarities.docsim.MatrixSimilarity` **or** - :class:`scipy.sparse.csr_matrix` - for case if index is :class:`~gensim.similarities.docsim.SparseMatrixSimilarity`. + :class:`numpy.ndarray` or :class:`scipy.sparse.csr_matrix` + Chunks of the index as 2D arrays. The arrays are either dense or sparse, depending on + whether the shard was storing dense or sparse vectors. """ self.close_shard() @@ -677,26 +668,27 @@ def iter_chunks(self, chunksize=None): yield chunk def check_moved(self): - """Update shard locations (for case if the server directory has moved on filesystem).""" + """Update shard locations, for case where the server prefix location changed on the filesystem.""" dirname = os.path.dirname(self.output_prefix) for shard in self.shards: shard.dirname = dirname def save(self, fname=None, *args, **kwargs): - """Save the object via pickling (also see load) under filename specified in the constructor. + """Save the index object via pickling under `fname`. See also :meth:`~gensim.docsim.Similarity.load()`. Parameters ---------- fname : str, optional Path for save index, if not provided - will be saved to `self.output_prefix`. *args : object - Arguments, look at :meth:`gensim.interfaces.SimilarityABC.save`. + Arguments, see :meth:`gensim.utils.SaveLoad.save`. **kwargs : object - Keyword arguments, look at :meth:`gensim.interfaces.SimilarityABC.save`. + Keyword arguments, see :meth:`gensim.utils.SaveLoad.save`. Notes ----- - Call :meth:`~gensim.similarities.Similarity.close_shard` internally to spill unfinished shards to disk first. + Will call :meth:`~gensim.similarities.Similarity.close_shard` internally to spill + any unfinished shards to disk first. Examples -------- @@ -708,7 +700,7 @@ def save(self, fname=None, *args, **kwargs): >>> output_fname = get_tmpfile("saved_index") >>> >>> corpus = TextCorpus(datapath('testcorpus.txt')) - >>> index = Similarity(temp_fname, corpus, num_features=400) + >>> index = Similarity(output_fname, corpus, num_features=400) >>> >>> index.save(output_fname) >>> loaded_index = index.load(output_fname) @@ -720,7 +712,7 @@ def save(self, fname=None, *args, **kwargs): super(Similarity, self).save(fname, *args, **kwargs) def destroy(self): - """Delete all files under self.output_prefix, object is not usable after calling this method anymore.""" + """Delete all files under self.output_prefix Index is not usable anymore after calling this method.""" import glob for fname in glob.glob(self.output_prefix + '*'): logger.info("deleting %s", fname) @@ -748,18 +740,18 @@ def __init__(self, corpus, num_best=None, dtype=numpy.float32, num_features=None Parameters ---------- corpus : iterable of list of (int, number) - Corpus in BoW format. + Corpus in streamed Gensim bag-of-words format. num_best : int, optional If set, return only the `num_best` most similar documents, always leaving out documents with similarity = 0. Otherwise, return a full vector with one float for every document in the index. - dtype : numpy.dtype - Datatype of internal matrix - num_features : int, optional - Size of the dictionary. - chunksize : int, optional - Size of chunk. + num_features : int + Size of the dictionary (number of features). corpus_len : int, optional - Size of `corpus`, if not specified - will scan corpus to determine size. + Number of documents in `corpus`. If not specified, will scan the corpus to determine the matrix size. + chunksize : int, optional + Size of query chunks. Used internally when the query is an entire corpus. + dtype : numpy.dtype, optional + Datatype to store the internal matrix in. """ if num_features is None: @@ -804,7 +796,7 @@ def __len__(self): return self.index.shape[0] def get_similarities(self, query): - """Get similarity between `query` and current index instance. + """Get similarity between `query` and this index. Warnings -------- @@ -914,11 +906,11 @@ def __len__(self): return len(self.corpus) def get_similarities(self, query): - """Get similarity between `query` and current index instance. + """Get similarity between `query` and this index. Warnings -------- - Do not use this function directly; use the self[query] syntax instead. + Do not use this function directly; use the `self[query]` syntax instead. Parameters ---------- @@ -964,16 +956,18 @@ def __str__(self): class WmdSimilarity(interfaces.SimilarityABC): """Compute negative WMD similarity against a corpus of documents by storing the index matrix in memory. - See :class:`~gensim.models.keyedvectors.WordEmbeddingsKeyedVectors` for more information. Also, tutorial `notebook `_ for more examples. When using this code, please consider citing the following papers: - `Ofir Pele and Michael Werman, "A linear time histogram metric for improved SIFT matching" - `_, `Ofir Pele and Michael Werman, "Fast and robust earth - mover's distances" `_, `"Matt Kusner et al. "From Word - Embeddings To Document Distances" `_. + + * `Ofir Pele and Michael Werman, "A linear time histogram metric for improved SIFT matching" + `_ + * `Ofir Pele and Michael Werman, "Fast and robust earth mover's distances" + `_ + * `Matt Kusner et al. "From Word Embeddings To Document Distances" + `_ Example ------- @@ -992,7 +986,6 @@ class WmdSimilarity(interfaces.SimilarityABC): >>> sims = index[query] """ - def __init__(self, corpus, w2v_model, num_best=None, normalize_w2v_and_replace=True, chunksize=256): """ @@ -1030,11 +1023,11 @@ def __len__(self): return len(self.corpus) def get_similarities(self, query): - """Get similarity between `query` and current index instance. + """Get similarity between `query` and this index. Warnings -------- - Do not use this function directly; use the self[query] syntax instead. + Do not use this function directly; use the `self[query]` syntax instead. Parameters ---------- @@ -1082,7 +1075,7 @@ class SparseMatrixSimilarity(interfaces.SimilarityABC): Notes ----- - Use this if your input corpus contains sparse vectors (such as documents in bag-of-words format) and fits into RAM. + Use this if your input corpus contains sparse vectors (such as TF-IDF documents) and fits into RAM. The matrix is internally stored as a :class:`scipy.sparse.csr_matrix` matrix. Unless the entire matrix fits into main memory, use :class:`~gensim.similarities.docsim.Similarity` instead. @@ -1099,35 +1092,33 @@ class SparseMatrixSimilarity(interfaces.SimilarityABC): Index similarity (dense with cosine distance). """ - def __init__(self, corpus, num_features=None, num_terms=None, num_docs=None, num_nnz=None, num_best=None, chunksize=500, dtype=numpy.float32, maintain_sparsity=False): """ + Parameters ---------- corpus: iterable of list of (int, float) A list of documents in the BoW format. num_features : int, optional - Size of the dictionary. + Size of the dictionary. Must be either specified, or present in `corpus.num_terms`. num_terms : int, optional - Number of terms, **must be specified**. + Alias for `num_features`, you can use either. num_docs : int, optional - Number of documents in `corpus`. + Number of documents in `corpus`. Will be calculated if not provided. num_nnz : int, optional - Number of non-zero terms. + Number of non-zero elements in `corpus`. Will be calculated if not provided. num_best : int, optional If set, return only the `num_best` most similar documents, always leaving out documents with similarity = 0. Otherwise, return a full vector with one float for every document in the index. chunksize : int, optional - Size of chunk. + Size of query chunks. Used internally when the query is an entire corpus. dtype : numpy.dtype, optional - Data type of internal matrix. + Data type of the internal matrix. maintain_sparsity : bool, optional - if True - will return sparse arr from - :meth:`~gensim.similarities.docsim.SparseMatrixSimilarity.get_similarities`. + Return sparse arrays from :meth:`~gensim.similarities.docsim.SparseMatrixSimilarity.get_similarities`? """ - self.num_best = num_best self.normalize = True self.chunksize = chunksize @@ -1168,11 +1159,11 @@ def __len__(self): return self.index.shape[0] def get_similarities(self, query): - """Get similarity between `query` and current index instance. + """Get similarity between `query` and this index. Warnings -------- - Do not use this function directly; use the self[query] syntax instead. + Do not use this function directly; use the `self[query]` syntax instead. Parameters ---------- diff --git a/gensim/sklearn_api/phrases.py b/gensim/sklearn_api/phrases.py index 7579a09cc9..8c32ab4dd0 100644 --- a/gensim/sklearn_api/phrases.py +++ b/gensim/sklearn_api/phrases.py @@ -35,9 +35,10 @@ class PhrasesTransformer(TransformerMixin, BaseEstimator): """Base Phrases module, wraps :class:`~gensim.models.phrases.Phrases`. - For more information, please have a look to `Mikolov, et. al: "Efficient Estimation of Word Representations in - Vector Space" `_ and `Gerlof Bouma: "Normalized (Pointwise) Mutual Information - in Collocation Extraction" `_. + For more information, please have a look to `Mikolov, et. al: "Distributed Representations + of Words and Phrases and their Compositionality" `_ and + `Gerlof Bouma: "Normalized (Pointwise) Mutual Information in Collocation Extraction" + `_. """ def __init__(self, min_count=5, threshold=10.0, max_vocab_size=40000000, @@ -63,8 +64,8 @@ def __init__(self, min_count=5, threshold=10.0, max_vocab_size=40000000, or with a function with the expected parameter names. Two built-in scoring functions are available by setting `scoring` to a string: - * 'default': Explained in `Mikolov, et. al: "Efficient Estimation of Word Representations - in Vector Space" `_. + * 'default': `Mikolov, et. al: "Distributed Representations of Words and Phrases + and their Compositionality" `_. * 'npmi': Explained in `Gerlof Bouma: "Normalized (Pointwise) Mutual Information in Collocation Extraction" `_. diff --git a/gensim/test/test_data/tfidf_model.tst b/gensim/test/test_data/tfidf_model.tst index 8d3c60c73ed35f9d341a1a9e65fd490301539739..b6448f0e388e9f0e1410d6c4b718631b65b7f9fe 100644 GIT binary patch literal 909 zcma))%Wl&^6o%tCiJeJXTA*CZ{pJ8Q&=m_%*;QhM7ZtN>WI5wWY{|Fdu@j|IB)R|| z0kLAibMOZ67OZ#!R&YEe$S6Xpt>ZKP=J!7%&;O>$$0CtoY{#iDB54<+&>yKWd0h=( zRhWR*KZ52Qbc=P9G>^R~JQUF4qcY(|nnsdjUS5PAD%<}zlyN1>rTf={Kl-s&H!0(6CZRWAE!?Gql{u_hw80g( zd72A5E+gDho_jMQxfgjkfwkj#;uo__5IDt}qo=e%wfFn5Zc&|S&m6~j`3o=gpbcE! z48DB&tQ}}C-tEH%)q=HP{U3IkHka5LsxPs#w6(-GX}ivT?&2EfXs6E9y634;XG(X0 znsugh7iqW7lsT$UHjX;j4eTcNE_Q;| zqs@{L*A2%Q0)f`I2FwWkooSl;aNA+#B0X@2=}E!iE^BAuBrV{c!;I-TN{3zqR&bL1 z{ZSL>WBTq}K_AoifUO>TEb{k|X@$yPXBwrLAJ{&bw-OVu(fW}U*l7Kjtthx~e!{dw QIb)6`533yS49cPX8!<~ZasU7T literal 1261 zcma)++fvg&7{`00ZHfm}JRlxXDJoU)gbIR3l$EM0YE)`WleCGXN&ndt24RWi_OX%*>ah!27!)7+S+5PQz-n>m24a;Lrv)uGe%Vp)T?wEBsSLVcY zRxB$>4822g6{(V%OC%CryQz8J3eu!sP4jQF&X8F}wnP#nMUuRWC(V0?_bi`v@iE88 zJRb{uRCq6vR9nsR<1J^=57AXo75<@VPQ&v9%Vfw^kyi^spC2@J*IBVpFzRj32z}pW zN=pwyN9V>V@jkR$rXE_R_E&;};u^Xswv_DR&?>e{`#sIWHZ{pL8Q9J$A$n@kPsbcx z@&gk)DiX6=3_GVM@ZsaT;a@#!ue3I>jCR1BMN4D)qUHKJH+)wWy=q==^H8;x8Fp8( zN3Mv_nZCiWmlULqrH1R*bQk;VO}Np474)rPKSh7Z?&D4zP%|P(npwv|=|zY`!i&Q- zxxur@aAXxnd3p?KPubuBE;rjQk6#ez%L+4eR}T~nZ0sv$xZJW798*(VaD5ENd190A zae`v7MAA~nI7*dDW#%_;@z~#?C+Cw>IHh*+ z6;}@(Zv>|!3{#XNoS`^NlJgupyGIY14z0~&}wqyhBQFhLAJl8P#*O$h|hf?-G^7{Z82 zcemlS@CS8rgM!BnOOSytq%g@1U4knK#s!x;_6H%;r(<(UoY&D++iu{MEIkx3w{i7+ z;2eMqD&Fm8K}+Hw@dICjT4x&0=WQ*c2a(+a(Su18(aMgFbgp(PN!Sfl?%y^i900^M zU`DXhJJ)L+so2Z`EE1A`-w2@^g7hwttAW6hBQNnOh zqT`LNN>Y^Fb~1pBz)h)2Xdyg<@5HiP1_D4$B@~e{bf!uiYdo>uzX7NW2VrBmwKS!8 zgbR){ietshigCzcu&#E{WzBC|6v(>#AGg02dXD$Duk^uI#5zmM^EBvXY6 I4AExr0H;F`zyJUM literal 822 zcmV-61IheCT4*^jL0KkKS?3V!e*gkE|NZ~}|NsC0|NsC0|NsC0|FUC%0HBBf03sL$ z1P}lKzyg0iguRHi~%x zA?h?~p^>#T$)GeeXaE2MLn8zLWMmp-4Ff_df0U{Enw!-F)Mx+z0004?0000001W^% zGy$LiibXU44FDPd27mwn00000001-q02vN9)ipFWKm-7iISr==DeZtoswe^=J%_3~ z0RS^3l!ka3U4JX`ly^4FHH~1{4^;n1ulaz#yUm2to+vQ`CO>VQBO|C{`Rn zq9aWt13)4lAQ*^k7SSvuAQ2(WHCu9SoxE++w~_6_5)ed%=@kG3Twol|0PI~Tj-*5$ zlMmPoWXJ&nODMo6Fv5Zi(NhK|2g$uk8Y|o;qx2&$j#+4HolcJ6e|@L> zEci%H0Fs%3jsPh@EGcs@R|P;?sw=X(QioL0LLqT)Zt(DlvtElFONUOqFB#Q<%9R{; zc~@lSWmc(IF<(m(H7mx2T$n@_LGDDT+fw~sVY+CNk)Z_`4blQb&p_qoS&#=16rmCi zF-pIG%^>Zq#F%MFkdunWtVw-f@;v07l7RP>5jon!nCQG=of}JuSFP+^e>m2|?WGZYN zcQ9L36s5KTHcYg29Jm>r(Ba-|HnR|(nMqn>o>M$}tU5*-Bg5ix#);VdCLVr%lTXo7 zsio?>SF-nC3*~((H#1* # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -"""This module contains various general utility functions.""" +"""Various general utility functions.""" from __future__ import with_statement from contextlib import contextmanager @@ -73,11 +73,8 @@ def get_random_state(seed): Notes ----- - Method originally from [1]_ and written by @joshloyal. - - References - ---------- - .. [1] https://github.com/maciejkula/glove-python + Method originally from `maciejkula/glove-python `_ + and written by `@joshloyal `_. """ if seed is None or seed is np.random: @@ -94,11 +91,7 @@ def synchronous(tlockname): Notes ----- - Adapted from [2]_ - - References - ---------- - .. [2] http://code.activestate.com/recipes/577105-synchronization-decorator-for-class-methods/ + Adapted from http://code.activestate.com/recipes/577105-synchronization-decorator-for-class-methods/. """ def _synched(func): @@ -117,7 +110,7 @@ def _synchronizer(self, *args, **kwargs): def file_or_filename(input): - """Open file with `smart_open`. + """Open a filename for reading with `smart_open`, or seek to the beginning if `input` is an already open file. Parameters ---------- @@ -126,8 +119,8 @@ def file_or_filename(input): Returns ------- - input : file-like object - Opened file OR seek out to 0 byte if `input` is already file-like object. + file-like object + An open file, positioned at the beginning. """ if isinstance(input, string_types): @@ -141,7 +134,7 @@ def file_or_filename(input): @contextmanager def open_file(input): - """Provide "with-like" behaviour except closing the file object. + """Provide "with-like" behaviour without closing the file object. Parameters ---------- @@ -170,7 +163,7 @@ def open_file(input): def deaccent(text): - """Remove accentuation from the given string. + """Remove letter accents from the given string. Parameters ---------- @@ -180,7 +173,7 @@ def deaccent(text): Returns ------- str - Unicode string without accentuation. + Unicode string without accents. Examples -------- @@ -221,25 +214,24 @@ def copytree_hardlink(source, dest): def tokenize(text, lowercase=False, deacc=False, encoding='utf8', errors="strict", to_lower=False, lower=False): - """Iteratively yield tokens as unicode strings, removing accent marks and optionally lowercasing string - if any from `lowercase`, `to_lower`, `lower` set to True. + """Iteratively yield tokens as unicode strings, optionally removing accent marks and lowercasing it. Parameters ---------- - text : str + text : str or bytes Input string. - lowercase : bool, optional - If True - lowercase input string. deacc : bool, optional - If True - remove accentuation from string by :func:`~gensim.utils.deaccent`. + Remove accentuation using :func:`~gensim.utils.deaccent`? encoding : str, optional Encoding of input string, used as parameter for :func:`~gensim.utils.to_unicode`. errors : str, optional Error handling behaviour, used as parameter for :func:`~gensim.utils.to_unicode`. + lowercase : bool, optional + Lowercase the input string? to_lower : bool, optional - Same as `lowercase`. + Same as `lowercase`. Convenience alias. lower : bool, optional - Same as `lowercase`. + Same as `lowercase`. Convenience alias. Yields ------ @@ -281,19 +273,20 @@ def simple_tokenize(text): def simple_preprocess(doc, deacc=False, min_len=2, max_len=15): - """Convert a document into a list of tokens (also with lowercase and optional de-accents), - used :func:`~gensim.utils.tokenize`. + """Convert a document into a list of lowercase tokens, ignoring tokens that are too short or too long. + + Uses :func:`~gensim.utils.tokenize` internally. Parameters ---------- doc : str Input document. deacc : bool, optional - If True - remove accentuation from string by :func:`~gensim.utils.deaccent`. + Remove accent marks from tokens using :func:`~gensim.utils.deaccent`? min_len : int, optional - Minimal length of token in result (inclusive). + Minimum length of token (inclusive). Shorter tokens are discarded. max_len : int, optional - Maximal length of token in result (inclusive). + Maximum length of token in result (inclusive). Longer tokens are discarded. Returns ------- @@ -309,16 +302,16 @@ def simple_preprocess(doc, deacc=False, min_len=2, max_len=15): def any2utf8(text, errors='strict', encoding='utf8'): - """Convert `text` to bytestring in utf8. + """Convert a unicode or bytes string in the given encoding into a utf8 bytestring. Parameters ---------- text : str Input text. errors : str, optional - Error handling behaviour, used as parameter for `unicode` function (python2 only). + Error handling behaviour if `text` is a bytestring. encoding : str, optional - Encoding of `text` for `unicode` function (python2 only). + Encoding of `text` if it is a bytestring. Returns ------- @@ -337,16 +330,16 @@ def any2utf8(text, errors='strict', encoding='utf8'): def any2unicode(text, encoding='utf8', errors='strict'): - """Convert `text` to unicode. + """Convert `text` (bytestring in given encoding or unicode) to unicode. Parameters ---------- text : str Input text. errors : str, optional - Error handling behaviour, used as parameter for `unicode` function (python2 only). + Error handling behaviour if `text` is a bytestring. encoding : str, optional - Encoding of `text` for `unicode` function (python2 only). + Encoding of `text` if it is a bytestring. Returns ------- @@ -363,7 +356,7 @@ def any2unicode(text, encoding='utf8', errors='strict'): def call_on_class_only(*args, **kwargs): - """Helper for raise `AttributeError` if method should be called from instance. + """Helper to raise `AttributeError` if a class method is called on an instance. Used internally. Parameters ---------- @@ -375,24 +368,24 @@ def call_on_class_only(*args, **kwargs): Raises ------ AttributeError - If `load` method are called on instance. + If a class method is called on an instance. """ raise AttributeError('This method should be called on a class object.') class SaveLoad(object): - """Class which inherit from this class have save/load functions, which un/pickle them to disk. + """Serialize/deserialize object from disk, by equipping objects with the save()/load() methods. Warnings -------- - This uses pickle for de/serializing, so objects must not contain unpicklable attributes, + This uses pickle internally (among other techniques), so objects must not contain unpicklable attributes such as lambda functions etc. """ @classmethod def load(cls, fname, mmap=None): - """Load a previously saved object (using :meth:`~gensim.utils.SaveLoad.save`) from file. + """Load an object previously saved using :meth:`~gensim.utils.SaveLoad.save` from a file. Parameters ---------- @@ -406,6 +399,7 @@ def load(cls, fname, mmap=None): See Also -------- :meth:`~gensim.utils.SaveLoad.save` + Save object to file. Returns ------- @@ -414,8 +408,8 @@ def load(cls, fname, mmap=None): Raises ------ - IOError - When methods are called on instance (should be called from class). + AttributeError + When called on an object instance instead of class (this is a class method). """ logger.info("loading %s object from %s", cls.__name__, fname) @@ -428,20 +422,20 @@ def load(cls, fname, mmap=None): return obj def _load_specials(self, fname, mmap, compress, subname): - """Loads any attributes that were stored specially, and gives the same opportunity - to recursively included :class:`~gensim.utils.SaveLoad` instances. + """Load attributes that were stored separately, and give them the same opportunity + to recursively load using the :class:`~gensim.utils.SaveLoad` interface. Parameters ---------- fname : str - Path to file that contains needed object. - mmap : str - Memory-map option. + Input file path. + mmap : {None, ‘r+’, ‘r’, ‘w+’, ‘c’} + Memory-map options. See `numpy.load(mmap_mode) + `_. compress : bool - Set to True if file is compressed. + Is the input file compressed? subname : str - ... - + Attribute name. Set automatically during recursive processing. """ def mmap_error(obj, filename): @@ -492,7 +486,7 @@ def mmap_error(obj, filename): @staticmethod def _adapt_by_suffix(fname): - """Give appropriate compress setting and filename formula. + """Get compress setting and filename for numpy file compression. Parameters ---------- @@ -509,7 +503,7 @@ def _adapt_by_suffix(fname): return compress, lambda *args: '.'.join(args + (suffix,)) def _smart_save(self, fname, separately=None, sep_limit=10 * 1024**2, ignore=frozenset(), pickle_protocol=2): - """Save the object to file. + """Save the object to a file. Used internally by :meth:`gensim.utils.SaveLoad.save()`. Parameters ---------- @@ -526,18 +520,12 @@ def _smart_save(self, fname, separately=None, sep_limit=10 * 1024**2, ignore=fro Notes ----- - If `separately` is None, automatically detect large - numpy/scipy.sparse arrays in the object being stored, and store - them into separate files. This avoids pickle memory errors and - allows mmap'ing large arrays back on load efficiently. - - You can also set `separately` manually, in which case it must be - a list of attribute names to be stored in separate files. The - automatic check is not performed in this case. + If `separately` is None, automatically detect large numpy/scipy.sparse arrays in the object being stored, + and store them into separate files. This avoids pickle memory errors and allows mmap'ing large arrays back + on load efficiently. - See Also - -------- - :meth:`~gensim.utils.SaveLoad.load` + You can also set `separately` manually, in which case it must be a list of attribute names to be stored + in separate files. The automatic check is not performed in this case. """ logger.info("saving %s object under %s, separately %s", self.__class__.__name__, fname, separately) @@ -564,11 +552,11 @@ def _save_specials(self, fname, separately, sep_limit, ignore, pickle_protocol, fname : str Output filename. separately : list or None - Iterable of attributes than need to store distinctly + List of attributes to store separately. sep_limit : int - Limit for separation. + Don't store arrays smaller than this separately. In bytes. ignore : iterable of str - Attributes that shouldn't be store. + Attributes that shouldn't be stored at all. pickle_protocol : int Protocol number for pickle. compress : bool @@ -659,7 +647,7 @@ def _save_specials(self, fname, separately, sep_limit, ignore, pickle_protocol, return restores + [(self, asides)] def save(self, fname_or_handle, separately=None, sep_limit=10 * 1024**2, ignore=frozenset(), pickle_protocol=2): - """Save the object to file. + """Save the object to a file. Parameters ---------- @@ -667,21 +655,24 @@ def save(self, fname_or_handle, separately=None, sep_limit=10 * 1024**2, ignore= Path to output file or already opened file-like object. If the object is a file handle, no special array handling will be performed, all attributes will be saved to the same file. separately : list of str or None, optional - If None - automatically detect large numpy/scipy.sparse arrays in the object being stored, and store - them into separate files. This avoids pickle memory errors and allows mmap'ing large arrays - back on load efficiently. - If list of str - this attributes will be stored in separate files, the automatic check + If None, automatically detect large numpy/scipy.sparse arrays in the object being stored, and store + them into separate files. This prevent memory errors for large objects, and also allows + `memory-mapping `_ the large arrays for efficient + loading and sharing the large arrays in RAM between multiple processes. + + If list of str: store these attributes into separate files. The automated size check is not performed in this case. - sep_limit : int - Limit for automatic separation. - ignore : frozenset of str - Attributes that shouldn't be serialize/store. - pickle_protocol : int + sep_limit : int, optional + Don't store arrays smaller than this separately. In bytes. + ignore : frozenset of str, optional + Attributes that shouldn't be stored at all. + pickle_protocol : int, optional Protocol number for pickle. See Also -------- :meth:`~gensim.utils.SaveLoad.load` + Load object from file. """ try: @@ -713,7 +704,7 @@ def get_max_id(corpus): Parameters ---------- - corpus : iterable of iterable of (int, int) + corpus : iterable of iterable of (int, numeric) Collection of texts in BoW format. Returns @@ -739,7 +730,6 @@ class FakeDict(object): This is meant to avoid allocating real dictionaries when `num_terms` is huge, which is a waste of memory. """ - def __init__(self, num_terms): """ @@ -781,8 +771,8 @@ def keys(self): list of int Highest id, packed in list. - Warnings - -------- + Notes + ----- To avoid materializing the whole `range(0, self.num_terms)`, this returns the highest id = `[self.num_terms - 1]` only. @@ -804,7 +794,7 @@ def dict_from_corpus(corpus): Parameters ---------- - corpus : iterable of iterable of (int, int) + corpus : iterable of iterable of (int, numeric) Collection of texts in BoW format. Returns @@ -825,17 +815,25 @@ def dict_from_corpus(corpus): def is_corpus(obj): - """Check whether `obj` is a corpus. + """Check whether `obj` is a corpus, by peeking at its first element. Works even on streamed generators. + The peeked element is put back into a object returned by this function, so always use + that returned object instead of the original `obj`. Parameters ---------- obj : object - Something `iterable of iterable` that contains (int, int). + An `iterable of iterable` that contains (int, numeric). - Return - ------ + Returns + ------- (bool, object) - Pair of (is_corpus, `obj`), is_corpus True if `obj` is corpus. + Pair of (is `obj` a corpus, `obj` with peeked element restored) + + Examples + -------- + >>> from gensim.utils import is_corpus + >>> corpus = [[(1, 1.0)], [(2, -0.3), (3, 0.12)]] + >>> corpus_or_not, corpus = is_corpus(corpus) Warnings -------- @@ -918,13 +916,12 @@ class RepeatCorpus(SaveLoad): [[(1, 2)], [], [(1, 2)], [], [(1, 2)]] """ - def __init__(self, corpus, reps): """ Parameters ---------- - corpus : iterable of iterable of (int, int) + corpus : iterable of iterable of (int, numeric) Input corpus. reps : int Number of repeats for documents from corpus. @@ -949,13 +946,12 @@ class RepeatCorpusNTimes(SaveLoad): [[(1, 0.5)], [], [(1, 0.5)], [], [(1, 0.5)], []] """ - def __init__(self, corpus, n): """ Parameters ---------- - corpus : iterable of iterable of (int, int) + corpus : iterable of iterable of (int, numeric) Input corpus. n : int Number of repeats for corpus. @@ -971,17 +967,16 @@ def __iter__(self): class ClippedCorpus(SaveLoad): - """Wrap a `corpus` and return `max_doc` element from it""" - + """Wrap a `corpus` and return `max_doc` element from it.""" def __init__(self, corpus, max_docs=None): """ Parameters ---------- - corpus : iterable of iterable of (int, int) + corpus : iterable of iterable of (int, numeric) Input corpus. max_docs : int - Maximal number of documents in result corpus. + Maximum number of documents in the wrapped corpus. Warnings -------- @@ -1000,17 +995,16 @@ def __len__(self): class SlicedCorpus(SaveLoad): - """Wrap `corpus` and return the slice of it""" - + """Wrap `corpus` and return a slice of it.""" def __init__(self, corpus, slice_): """ Parameters ---------- - corpus : iterable of iterable of (int, int) + corpus : iterable of iterable of (int, numeric) Input corpus. slice_ : slice or iterable - Slice for `corpus` + Slice for `corpus`. Notes ----- @@ -1046,7 +1040,8 @@ def __len__(self): def safe_unichr(intval): - """ + """Create a unicode character from its integer value. In case `unichr` fails, render the character + as an escaped `\\U<8-byte hex value of intval>` string. Parameters ---------- @@ -1069,13 +1064,14 @@ def safe_unichr(intval): def decode_htmlentities(text): - """Decode HTML entities in text, coded as hex, decimal or named. - This function from [3]_. + """Decode all HTML entities in text that are encoded as hex, decimal or named entities. + Adapted from `python-twitter-ircbot/html_decode.py + `_. Parameters ---------- text : str - Input html text. + Input HTML. Examples -------- @@ -1089,10 +1085,6 @@ def decode_htmlentities(text): >>> print(decode_htmlentities("foo < bar")) foo < bar - References - ---------- - .. [3] http://github.com/sku/python-twitter-ircbot/blob/321d94e0e40d0acc92f5bf57d126b57369da70de/html_decode.py - """ def substitute_entity(match): try: @@ -1120,22 +1112,23 @@ def substitute_entity(match): def chunkize_serial(iterable, chunksize, as_numpy=False, dtype=np.float32): - """Give elements from the iterable in `chunksize`-ed lists. - The last returned element may be smaller (if length of collection is not divisible by `chunksize`). + """Yield elements from `iterable` in "chunksize"-ed groups. + + The last returned element may be smaller if the length of collection is not divisible by `chunksize`. Parameters ---------- iterable : iterable of object - Any iterable. + An iterable. chunksize : int - Size of chunk from result. + Split iterable into chunks of this size. as_numpy : bool, optional - If True - yield `np.ndarray`, otherwise - list + Yield chunks as `np.ndarray` instead of lists. Yields ------ - list of object OR np.ndarray - Groups based on `iterable` + list OR np.ndarray + "chunksize"-ed chunks of elements from `iterable`. Examples -------- @@ -1161,7 +1154,26 @@ def chunkize_serial(iterable, chunksize, as_numpy=False, dtype=np.float32): class InputQueue(multiprocessing.Process): + """Populate a queue of input chunks from a streamed corpus. + + Useful for reading and chunking corpora in the background, in a separate process, + so that workers that use the queue are not starved for input chunks. + + """ def __init__(self, q, corpus, chunksize, maxsize, as_numpy): + """ + Parameters + ---------- + q : multiprocessing.Queue + Enqueue chunks into this queue. + corpus : iterable of iterable of (int, numeric) + Corpus to read and split into "chunksize"-ed groups + chunksize : int + Split `corpus` into chunks of this size. + as_numpy : bool, optional + Enqueue chunks as `numpy.ndarray` instead of lists. + + """ super(InputQueue, self).__init__() self.q = q self.maxsize = maxsize @@ -1197,50 +1209,56 @@ def run(self): warnings.warn("detected Windows; aliasing chunkize to chunkize_serial") def chunkize(corpus, chunksize, maxsize=0, as_numpy=False): - """Split `corpus` into smaller chunks, used :func:`~gensim.utils.chunkize_serial`. + """Split `corpus` into fixed-sized chunks, using :func:`~gensim.utils.chunkize_serial`. Parameters ---------- corpus : iterable of object - Any iterable object. + An iterable. chunksize : int - Size of chunk from result. + Split `corpus` into chunks of this size. maxsize : int, optional - THIS PARAMETER IGNORED. + Ignored. For interface compatibility only. as_numpy : bool, optional - If True - yield `np.ndarray`, otherwise - list + Yield chunks as `np.ndarray`s instead of lists? Yields ------ - list of object OR np.ndarray - Groups based on `iterable` + list OR np.ndarray + "chunksize"-ed chunks of elements from `corpus`. """ for chunk in chunkize_serial(corpus, chunksize, as_numpy=as_numpy): yield chunk else: def chunkize(corpus, chunksize, maxsize=0, as_numpy=False): - """Split `corpus` into smaller chunks, used :func:`~gensim.utils.chunkize_serial`. + """Split `corpus` into fixed-sized chunks, using :func:`~gensim.utils.chunkize_serial`. Parameters ---------- corpus : iterable of object - Any iterable object. + An iterable. chunksize : int - Size of chunk from result. + Split `corpus` into chunks of this size. maxsize : int, optional - THIS PARAMETER IGNORED. + If > 0, prepare chunks in a background process, filling a chunk queue of size at most `maxsize`. as_numpy : bool, optional - If True - yield `np.ndarray`, otherwise - list + Yield chunks as `np.ndarray` instead of lists? + + Yields + ------ + list OR np.ndarray + "chunksize"-ed chunks of elements from `corpus`. Notes ----- Each chunk is of length `chunksize`, except the last one which may be smaller. A once-only input stream (`corpus` from a generator) is ok, chunking is done efficiently via itertools. - If `maxsize > 1`, don't wait idly in between successive chunk `yields`, but rather keep filling a short queue + If `maxsize > 0`, don't wait idly in between successive chunk `yields`, but rather keep filling a short queue (of size at most `maxsize`) with forthcoming chunks in advance. This is realized by starting a separate process, - and is meant to reduce I/O delays, which can be significant when `corpus` comes from a slow medium (like HDD). + and is meant to reduce I/O delays, which can be significant when `corpus` comes from a slow medium + like HDD, database or network. If `maxsize == 0`, don't fool around with parallelism and simply yield the chunksize via :func:`~gensim.utils.chunkize_serial` (no I/O optimizations). @@ -1269,19 +1287,27 @@ def chunkize(corpus, chunksize, maxsize=0, as_numpy=False): def smart_extension(fname, ext): - """Generate filename with `ext`. + """Append a file extension `ext` to `fname`, while keeping compressed extensions like `.bz2` or + `.gz` (if any) at the end. Parameters ---------- fname : str - Path to file. + Filename or full path. ext : str - File extension. + Extension to append before any compression extensions. Returns ------- str - New path to file with `ext`. + New path to file with `ext` appended. + + Examples + -------- + + >>> from gensim.utils import smart_extension + >>> smart_extension("my_file.pkl.gz", ".vectors") + 'my_file.pkl.vectors.gz' """ fname, oext = os.path.splitext(fname) @@ -1296,7 +1322,7 @@ def smart_extension(fname, ext): def pickle(obj, fname, protocol=2): - """Pickle object `obj` to file `fname`. + """Pickle object `obj` to file `fname`, using smart_open so that `fname` can be on S3, HDFS, compressed etc. Parameters ---------- @@ -1305,7 +1331,7 @@ def pickle(obj, fname, protocol=2): fname : str Path to pickle file. protocol : int, optional - Pickle protocol number, default is 2 to support compatible across python 2.x and 3.x. + Pickle protocol number. Default is 2 in order to support compatibility across python 2.x and 3.x. """ with smart_open(fname, 'wb') as fout: # 'b' for binary, needed on Windows @@ -1313,7 +1339,7 @@ def pickle(obj, fname, protocol=2): def unpickle(fname): - """Load object from `fname`. + """Load object from `fname`, using smart_open so that `fname` can be on S3, HDFS, compressed etc. Parameters ---------- @@ -1363,7 +1389,10 @@ def revdict(d): def deprecated(reason): - """Decorator which can be used to mark functions as deprecated. + """Decorator to mark functions as deprecated. + + Calling a decorated function will result in a warning being emitted, using warnings.warn. + Adapted from https://stackoverflow.com/a/40301488/8001386. Parameters ---------- @@ -1375,14 +1404,6 @@ def deprecated(reason): function Decorated function - Notes - ----- - It will result in a warning being emitted when the function is used, base code from [4]_. - - References - ---------- - .. [4] https://stackoverflow.com/a/40301488/8001386 - """ if isinstance(reason, string_types): def decorator(func): @@ -1420,19 +1441,18 @@ def new_func2(*args, **kwargs): @deprecated("Function will be removed in 4.0.0") def toptexts(query, texts, index, n=10): - """ - Debug fnc to help inspect the top `n` most similar documents (according to a - similarity index `index`), to see if they are actually related to the query. + """Debug fnc to help inspect the top `n` most similar documents (according to a similarity index `index`), + to see if they are actually related to the query. Parameters ---------- - query : list + query : {list of (int, number), numpy.ndarray} vector OR BoW (list of tuples) texts : str object that can return something insightful for each document via `texts[docid]`, such as its fulltext or snippet. index : any - a class from gensim.similarity.docsim + A instance from from :mod:`gensim.similarity.docsim`. Return ------ @@ -1447,7 +1467,7 @@ def toptexts(query, texts, index, n=10): def randfname(prefix='gensim'): - """Generate path with random filename/ + """Generate a random filename in temp. Parameters ---------- @@ -1457,7 +1477,7 @@ def randfname(prefix='gensim'): Returns ------- str - Full path with random filename (in temporary folder). + Full path in the in system's temporary folder, ending in a random filename. """ randpart = hex(random.randint(0, 0xffffff))[2:] @@ -1467,11 +1487,13 @@ def randfname(prefix='gensim'): @deprecated("Function will be removed in 4.0.0") def upload_chunked(server, docs, chunksize=1000, preprocess=None): """Memory-friendly upload of documents to a SimServer (or Pyro SimServer proxy). + Notes ----- Use this function to train or index large collections -- avoid sending the entire corpus over the wire as a single Pyro in-memory object. The documents will be sent in smaller chunks, of `chunksize` documents each. + """ start = 0 for chunk in grouper(docs, chunksize): @@ -1494,18 +1516,18 @@ def getNS(host=None, port=None, broadcast=True, hmac_key=None): Parameters ---------- host : str, optional - Hostname of ns. + Name server hostname. port : int, optional - Port of ns. + Name server port. broadcast : bool, optional - If True - use broadcast mechanism (i.e. all Pyro nodes in local network), not otherwise. + Use broadcast mechanism? (i.e. reach out to all Pyro nodes in the network) hmac_key : str, optional Private key. Raises ------ RuntimeError - when Pyro name server is not found + When Pyro name server is not found. Returns ------- @@ -1521,9 +1543,10 @@ def getNS(host=None, port=None, broadcast=True, hmac_key=None): def pyro_daemon(name, obj, random_suffix=False, ip=None, port=None, ns_conf=None): - """Register object with name server (starting the name server if not running - yet) and block until the daemon is terminated. The object is registered under - `name`, or `name`+ some random suffix if `random_suffix` is set. + """Register an object with the Pyro name server. + + Start the name server if not running yet and block until the daemon is terminated. + The object is registered under `name`, or `name`+ some random suffix if `random_suffix` is set. """ if ns_conf is None: @@ -1543,16 +1566,12 @@ def pyro_daemon(name, obj, random_suffix=False, ip=None, port=None, ns_conf=None def has_pattern(): - """Check that `pattern` [5]_ package already installed. + """Check whether the `pattern `_ package is installed. Returns ------- bool - True if `pattern` installed, False otherwise. - - References - ---------- - .. [5] https://github.com/clips/pattern + Is `pattern` installed? """ try: @@ -1564,8 +1583,9 @@ def has_pattern(): def lemmatize(content, allowed_tags=re.compile(r'(NN|VB|JJ|RB)'), light=False, stopwords=frozenset(), min_length=2, max_length=15): - """Use the English lemmatizer from `pattern` [5]_ to extract UTF8-encoded tokens in - their base form=lemma, e.g. "are, is, being" -> "be" etc. + """Use the English lemmatizer from `pattern `_ to extract UTF8-encoded tokens in + their base form aka lemma, e.g. "are, is, being" becomes "be" etc. + This is a smarter version of stemming, taking word context into account. Parameters @@ -1577,29 +1597,38 @@ def lemmatize(content, allowed_tags=re.compile(r'(NN|VB|JJ|RB)'), light=False, Only considers nouns, verbs, adjectives and adverbs by default (=all other lemmas are discarded). light : bool, optional DEPRECATED FLAG, DOESN'T SUPPORT BY `pattern`. - stopwords : frozenset + stopwords : frozenset, optional Set of words that will be removed from output. - min_length : int + min_length : int, optional Minimal token length in output (inclusive). - max_length : int + max_length : int, optional Maximal token length in output (inclusive). Returns ------- list of str - List with tokens with POS tag. + List with tokens with POS tags. Warnings -------- - This function is only available when the optional 'pattern' package is installed. + This function is only available when the optional `pattern `_ is installed. + + Raises + ------ + ImportError + If `pattern `_ not installed. Examples -------- >>> from gensim.utils import lemmatize >>> lemmatize('Hello World! How is it going?! Nonexistentword, 21') ['world/NN', 'be/VB', 'go/VB', 'nonexistentword/NN'] + + Note the context-dependent part-of-speech tags between these two examples: + >>> lemmatize('The study ranks high.') ['study/NN', 'rank/VB', 'high/JJ'] + >>> lemmatize('The ranks study hard.') ['rank/NN', 'study/VB', 'hard/RB'] @@ -1632,16 +1661,16 @@ def lemmatize(content, allowed_tags=re.compile(r'(NN|VB|JJ|RB)'), light=False, def mock_data_row(dim=1000, prob_nnz=0.5, lam=1.0): - """Create a random gensim BoW vector. + """Create a random gensim BoW vector, with the feature counts following the Poisson distribution. Parameters ---------- dim : int, optional Dimension of vector. prob_nnz : float, optional - Probability of each coordinate will be nonzero, will be drawn from Poisson distribution. + Probability of each coordinate will be nonzero, will be drawn from the Poisson distribution. lam : float, optional - Parameter for Poisson distribution. + Lambda parameter for the Poisson distribution. Returns ------- @@ -1654,7 +1683,7 @@ def mock_data_row(dim=1000, prob_nnz=0.5, lam=1.0): def mock_data(n_items=1000, dim=1000, prob_nnz=0.5, lam=1.0): - """Create a random gensim-style corpus (BoW), used :func:`~gensim.utils.mock_data_row`. + """Create a random Gensim-style corpus (BoW), using :func:`~gensim.utils.mock_data_row`. Parameters ---------- @@ -1681,6 +1710,7 @@ def prune_vocab(vocab, min_reduce, trim_rule=None): """Remove all entries from the `vocab` dictionary with count smaller than `min_reduce`. Modifies `vocab` in place, returns the sum of all counts that were pruned. + Parameters ---------- vocab : dict @@ -1736,18 +1766,19 @@ def qsize(queue): def keep_vocab_item(word, count, min_count, trim_rule=None): - """Check that should we keep `word` in vocab or remove. + """Should we keep `word` in the vocab or remove it? Parameters ---------- word : str Input word. count : int - Number of times that word contains in corpus. + Number of times that word appeared in a corpus. min_count : int - Frequency threshold for `word`. + Discard words with frequency smaller than this. trim_rule : function, optional - Function for trimming entities from vocab, default behaviour is `vocab[w] <= min_reduce`. + Custom function to decide whether to keep or discard this word. + If a custom `trim_rule` is not specified, the default behaviour is simply `count >= min_count`. Returns ------- @@ -1770,11 +1801,10 @@ def keep_vocab_item(word, count, min_count, trim_rule=None): def check_output(stdout=subprocess.PIPE, *popenargs, **kwargs): - r"""Run command with arguments and return its output as a byte string. - Backported from Python 2.7 as it's implemented as pure python on stdlib + small modification. - Widely used for :mod:`gensim.models.wrappers`. + r"""Run OS command with the given arguments and return its output as a byte string. - Very similar with [6]_ + Backported from Python 2.7 with a few minor modifications. Widely used for :mod:`gensim.models.wrappers`. + Behaves very similar to https://docs.python.org/2/library/subprocess.html#subprocess.check_output. Examples -------- @@ -1787,10 +1817,6 @@ def check_output(stdout=subprocess.PIPE, *popenargs, **kwargs): KeyboardInterrupt If Ctrl+C pressed. - References - ---------- - .. [6] https://docs.python.org/2/library/subprocess.html#subprocess.check_output - """ try: logger.debug("COMMAND: %s %s", popenargs, kwargs) @@ -1811,21 +1837,21 @@ def check_output(stdout=subprocess.PIPE, *popenargs, **kwargs): def sample_dict(d, n=10, use_random=True): - """Pick `n` items from dictionary `d`. + """Selected `n` (possibly random) items from the dictionary `d`. Parameters ---------- d : dict Input dictionary. n : int, optional - Number of items that will be picked. + Number of items to select. use_random : bool, optional - If True - pick items randomly, otherwise - according to natural dict iteration. + Select items randomly (without replacement), instead of by the natural dict iteration order? Returns ------- list of (object, object) - Picked items from dictionary, represented as list. + Selected items from dictionary, as a list. """ selected_keys = random.sample(list(d), min(len(d), n)) if use_random else itertools.islice(iterkeys(d), n) @@ -1880,10 +1906,10 @@ def strided_windows(ndarray, window_size): def iter_windows(texts, window_size, copy=False, ignore_below_size=True, include_doc_num=False): """Produce a generator over the given texts using a sliding window of `window_size`. + The windows produced are views of some subsequence of a text. To use deep copies instead, pass `copy=True`. - Parameters ---------- texts : list of str @@ -1891,11 +1917,11 @@ def iter_windows(texts, window_size, copy=False, ignore_below_size=True, include window_size : int Size of sliding window. copy : bool, optional - If True - produce deep copies. + Produce deep copies. ignore_below_size : bool, optional - If True - ignore documents that are not at least `window_size` in length. + Ignore documents that are not at least `window_size` in length? include_doc_num : bool, optional - If True - will be yield doc_num too. + Yield the text position with `texts` along with each window? """ for doc_num, document in enumerate(texts): @@ -1917,18 +1943,18 @@ def _iter_windows(document, window_size, copy=False, ignore_below_size=True): def flatten(nested_list): - """Recursively flatten out a nested list. + """Recursively flatten a nested sequence of elements. Parameters ---------- - nested_list : list - Possibly nested list. + nested_list : iterable + Possibly nested sequence of elements to flatten. Returns ------- list - Flattened version of input, where any list elements have been unpacked into the top-level list - in a recursive fashion. + Flattened version of `nested_list` where any elements that are an iterable (`collections.Iterable`) + have been unpacked into the top-level list, in a recursive fashion. """ return list(lazy_flatten(nested_list)) From fd6f6eb71996cd36a6236070f33efdfb37dde342 Mon Sep 17 00:00:00 2001 From: bohea Date: Fri, 22 Jun 2018 11:45:58 +0800 Subject: [PATCH 14/40] Fix bug in `Similarity.query_shards` in multiprocessing case (#2044) --- gensim/similarities/docsim.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/similarities/docsim.py b/gensim/similarities/docsim.py index 4e036d720e..4f7782a402 100755 --- a/gensim/similarities/docsim.py +++ b/gensim/similarities/docsim.py @@ -462,7 +462,7 @@ def query_shards(self, query): if PARALLEL_SHARDS and PARALLEL_SHARDS > 1: logger.debug("spawning %i query processes", PARALLEL_SHARDS) pool = multiprocessing.Pool(PARALLEL_SHARDS) - result = pool.imap(query_shard, args, chunksize=1 + len(args) / PARALLEL_SHARDS) + result = pool.imap(query_shard, args, chunksize=1 + len(list(args)) / PARALLEL_SHARDS) else: # serial processing, one shard after another pool = None From 43c01a239101e0817d1b1b65fce132999cb8337b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Wed, 27 Jun 2018 07:11:06 +0200 Subject: [PATCH 15/40] Update non-API docs (about, intro, etc) (#2101) * update non-API docs * Ivan's review comments * remove algo links (broken) * remove "local testing" section from install.rst * add links into intro page * add other channels to support * fix install page (correct dependencies, badges for all CI, drop useless parts) * fix distributed * minor doc fixes * update twitter account * Add description for each CI service * expand glossary * drop caps * fix documentation building --- docs/src/about.rst | 46 +++++----- docs/src/distributed.rst | 12 +-- docs/src/gensim_theme/layout.html | 2 +- docs/src/install.rst | 127 +++++++------------------ docs/src/intro.rst | 148 ++++++++++++++++-------------- docs/src/models/doc2vec.rst | 6 +- docs/src/models/word2vec.rst | 6 +- docs/src/support.rst | 27 +++--- 8 files changed, 165 insertions(+), 209 deletions(-) diff --git a/docs/src/about.rst b/docs/src/about.rst index 64a65bd333..25194b9404 100644 --- a/docs/src/about.rst +++ b/docs/src/about.rst @@ -2,12 +2,12 @@ .. _about: -============ +===== About -============ +===== History --------- +------- Gensim started off as a collection of various Python scripts for the Czech Digital Mathematics Library `dml.cz `_ in 2008, where it served to generate a short list of the most similar articles to a given article (**gensim = "generate similar"**). @@ -15,19 +15,18 @@ I also wanted to try these fancy "Latent Semantic Methods", but the libraries th realized the necessary computation were `not much fun to work with `_. Naturally, I set out to reinvent the wheel. Our `2010 LREC publication `_ -describes the initial design decisions behind gensim (clarity, efficiency and scalability) -and is fairly representative of how gensim works even today. +describes the initial design decisions behind Gensim: clarity, efficiency and scalability. It is fairly representative of how Gensim works even today. Later versions of gensim improved this efficiency and scalability tremendously. In fact, I made algorithmic scalability of distributional semantics the topic of my `PhD thesis `_. -By now, gensim is---to my knowledge---the most robust, efficient and hassle-free piece +By now, Gensim is---to my knowledge---the most robust, efficient and hassle-free piece of software to realize unsupervised semantic modelling from plain text. It stands in contrast to brittle homework-assignment-implementations that do not scale on one hand, and robust java-esque projects that take forever just to run "hello world". In 2011, I started using `Github `_ for source code hosting -and the gensim website moved to its present domain. In 2013, gensim got its current logo and website design. +and the Gensim website moved to its present domain. In 2013, Gensim got its current logo and website design. Licensing @@ -35,39 +34,40 @@ Licensing Gensim is licensed under the OSI-approved `GNU LGPLv2.1 license `_. This means that it's free for both personal and commercial use, but if you make any -modification to gensim that you distribute to other people, you have to disclose +modification to Gensim that you distribute to other people, you have to disclose the source code of these modifications. -Apart from that, you are free to redistribute gensim in any way you like, though you're +Apart from that, you are free to redistribute Gensim in any way you like, though you're not allowed to modify its license (doh!). -My intent here is, of course, to **get more help and community involvement** with the development of gensim. +My intent here is to **get more help and community involvement** with the development of Gensim. The legalese is therefore less important to me than your input and contributions. -Contact me if LGPL doesn't fit your bill but you'd still like to use gensim -- we'll work something out. + +`Contact me `_ if LGPL doesn't fit your bill and you'd like the open source restrictions lifted. .. seealso:: - I also host a document similarity package `gensim.simserver`. This is a high-level - interface to `gensim` functionality, and offers transactional remote (web-based) - document similarity queries and indexing. It uses gensim to do the heavy lifting: - you don't need the `simserver` to use gensim, but you do need gensim to use the `simserver`. - Note that unlike gensim, `gensim.simserver` is licensed under `Affero GPL `_, - which is much more restrictive for inclusion in commercial projects. + We also built a high performance commercial server for NLP, document analysis, indexing, search and clustering: https://scaletext.ai. ScaleText is available both on-prem and as SaaS. + + Reach out at info@scaletext.com if you need an industry-grade NLP tool with professional support. + Contributors --------------- +------------ -Credit goes to all the people who contributed to gensim, be it in `discussions `_, +Credit goes to the many people who contributed to Gensim, be it in `discussions `_, ideas, `code contributions `_ or `bug reports `_. + It's really useful and motivating to get feedback, in any shape or form, so big thanks to you all! Some honorable mentions are included in the `CHANGELOG.txt `_. Academic citing ----------------- +--------------- -Gensim has been used in `many students' final theses as well as research papers `_. When citing gensim, -please use `this BibTeX entry `_:: +Gensim has been used in `over a thousand research paper and student theses `_. + +When citing Gensim, please use `this BibTeX entry `_:: @inproceedings{rehurek_lrec, title = {{Software Framework for Topic Modelling with Large Corpora}}, @@ -83,5 +83,3 @@ please use `this BibTeX entry `_:: note={\url{http://is.muni.cz/publication/884893/en}}, language={English} } - - diff --git a/docs/src/distributed.rst b/docs/src/distributed.rst index 38f243222f..8b27fedc4f 100644 --- a/docs/src/distributed.rst +++ b/docs/src/distributed.rst @@ -1,7 +1,7 @@ .. _distributed: Distributed Computing -=================================== +===================== Why distributed computing? --------------------------- @@ -37,20 +37,20 @@ Prerequisites For communication between nodes, `gensim` uses `Pyro (PYthon Remote Objects) `_, version >= 4.27. This is a library for low-level socket communication -and remote procedure calls (RPC) in Python. `Pyro` is a pure-Python library, so its +and remote procedure calls (RPC) in Python. `Pyro4` is a pure-Python library, so its installation is quite painless and only involves copying its `*.py` files somewhere onto your Python's import path:: - sudo easy_install Pyro4 + pip install Pyro4 -You don't have to install `Pyro` to run `gensim`, but if you don't, you won't be able +You don't have to install Pyro to run Gensim, but if you don't, you won't be able to access the distributed features (i.e., everything will always run in serial mode, the examples on this page don't apply). Core concepts ------------------------------------ +------------- -As always, `gensim` strives for a clear and straightforward API (see :ref:`design`). +As always, Gensim strives for a clear and straightforward API (see :ref:`design`). To this end, *you do not need to make any changes in your code at all* in order to run it over a cluster of computers! diff --git a/docs/src/gensim_theme/layout.html b/docs/src/gensim_theme/layout.html index feac733791..4b4bd9fc43 100644 --- a/docs/src/gensim_theme/layout.html +++ b/docs/src/gensim_theme/layout.html @@ -174,7 +174,7 @@

Get Expert Help From The Gensim Authors

- Tweet @RadimRehurek + Tweet @Gensim_py
diff --git a/docs/src/install.rst b/docs/src/install.rst index 69d101e430..61039cb1d8 100644 --- a/docs/src/install.rst +++ b/docs/src/install.rst @@ -7,120 +7,59 @@ Installation Quick install -------------- -Run in your terminal:: - - easy_install -U gensim - -or, alternatively:: +Run in your terminal (recommended):: pip install --upgrade gensim -In case that fails, make sure you're installing into a writeable location (or use `sudo`), or read on. - ------ - -Dependencies -------------- -Gensim is known to run on Linux, Windows and Mac OS X and should run on any other -platform that supports Python 2.6+ and NumPy. Gensim depends on the following software: - -* `Python `_ >= 2.6. Tested with versions 2.6, 2.7, 3.3, 3.4 and 3.5. Support for Python 2.5 was discontinued starting gensim 0.10.0; if you *must* use Python 2.5, install gensim 0.9.1. -* `NumPy `_ >= 1.3. Tested with version 1.9.0, 1.7.1, 1.7.0, 1.6.2, 1.6.1rc2, 1.5.0rc1, 1.4.0, 1.3.0, 1.3.0rc2. -* `SciPy `_ >= 0.7. Tested with version 0.14.0, 0.12.0, 0.11.0, 0.10.1, 0.9.0, 0.8.0, 0.8.0b1, 0.7.1, 0.7.0. - -**Windows users** are well advised to try the `Enthought distribution `_, -which conveniently includes Python & NumPy & SciPy in a single bundle, and is free for academic use. - - -Install Python and `easy_install` ---------------------------------- - -Check what version of Python you have with:: - - python --version - -You can download Python from http://python.org/download. - -.. note:: Gensim requires Python 2.6 / 3.3 or greater, and will not run under earlier versions. - -Next, install the `easy_install utility `_, -which will make installing other Python programs easier. - -Install SciPy & NumPy ----------------------- - -These are quite popular Python packages, so chances are there are pre-built binary -distributions available for your platform. You can try installing from source using easy_install:: +or, alternatively for `conda` environments:: - easy_install numpy - easy_install scipy - -If that doesn't work or if you'd rather install using a binary package, consult -http://www.scipy.org/Download. - -Install `gensim` ------------------ - -You can now install (or upgrade) `gensim` with:: - - easy_install --upgrade gensim + conda install -c conda-forge gensim That's it! Congratulations, you can proceed to the :doc:`tutorials `. ------ - -If you also want to run the algorithms over a cluster -of computers, in :doc:`distributed`, you should install with:: - - easy_install gensim[distributed] - -The optional `distributed` feature installs `Pyro (PYthon Remote Objects) `_. -If you don't know what distributed computing means, you can ignore it: -`gensim` will work fine for you anyway. -This optional extension can also be installed separately later with:: - - easy_install Pyro4 +In case that failed, make sure you're installing into a writeable location (or use `sudo`). ----- -There are also alternative routes to install: - -1. If you have downloaded and unzipped the `tar.gz source `_ - for `gensim` (or you're installing `gensim` from `github `_), - you can run:: - - python setup.py install - - to install `gensim` into your ``site-packages`` folder. -2. If you wish to make local changes to the `gensim` code (`gensim` is, after all, a - package which targets research prototyping and modifications), a preferred - way may be installing with:: +Code dependencies +----------------- - python setup.py develop +Gensim runs on Linux, Windows and Mac OS X, and should run on any other +platform that supports Python 2.7+ and NumPy. Gensim depends on the following software: - This will only place a symlink into your ``site-packages`` directory. The actual - files will stay wherever you unpacked them. -3. If you don't have root priviledges (or just don't want to put the package into - your ``site-packages``), simply unpack the source package somewhere and that's it! No - compilation or installation needed. Just don't forget to set your PYTHONPATH - (or modify ``sys.path``), so that Python can find the unpacked package when importing. +* `Python `_ >= 2.7 (tested with versions 2.7, 3.5 and 3.6) +* `NumPy `_ >= 1.11.3 +* `SciPy `_ >= 0.18.1 +* `Six `_ >= 1.5.0 +* `smart_open `_ >= 1.2.1 +Testing Gensim +-------------- -Testing `gensim` ----------------- +Gensim uses continuous integration, automatically running a full test suite on each pull request with -To test the package, unzip the `tar.gz source `_ and run:: ++------------+-----------------------------------------------------------------------------------------+--------------+ +| CI service | Task | Build badge | ++============+=========================================================================================+==============+ +| Travis | Run tests on Linux and check `code-style `_ | |Travis|_ | ++------------+-----------------------------------------------------------------------------------------+--------------+ +| AppVeyor | Run tests on Windows | |AppVeyor|_ | ++------------+-----------------------------------------------------------------------------------------+--------------+ +| CircleCI | Build documentation | |CircleCI|_ | ++------------+-----------------------------------------------------------------------------------------+--------------+ - python setup.py test +.. |Travis| image:: https://travis-ci.org/RaRe-Technologies/gensim.svg?branch=develop +.. _Travis: https://travis-ci.org/RaRe-Technologies/gensim -Gensim uses Travis CI for continuous integration: |Travis|_ +.. |CircleCI| image:: https://circleci.com/gh/RaRe-Technologies/gensim/tree/develop.svg?style=shield +.. _CircleCI: https://circleci.com/gh/RaRe-Technologies/gensim -.. |Travis| image:: https://api.travis-ci.org/piskvorky/gensim.png?branch=develop -.. _Travis: https://travis-ci.org/piskvorky/gensim +.. |AppVeyor| image:: https://ci.appveyor.com/api/projects/status/r2au32ucpn8gr0tl/branch/develop?svg=true +.. _AppVeyor: https://ci.appveyor.com/api/projects/status/r2au32ucpn8gr0tl/branch/develop?svg=true Problems? --------- -Use the `gensim discussion group `_ for -questions and troubleshooting. See the :doc:`support page `. +Use the `Gensim discussion group `_ for +questions and troubleshooting. See the :doc:`support page ` for commercial support. diff --git a/docs/src/intro.rst b/docs/src/intro.rst index 3ffc724267..bcb60efa27 100644 --- a/docs/src/intro.rst +++ b/docs/src/intro.rst @@ -7,16 +7,15 @@ Introduction Gensim is a :ref:`free ` Python library designed to automatically extract semantic topics from documents, as efficiently (computer-wise) and painlessly (human-wise) as possible. - Gensim is designed to process raw, unstructured digital texts ("*plain text*"). -The algorithms in `gensim`, such as **Latent Semantic Analysis**, **Latent Dirichlet Allocation** and **Random Projections** -discover semantic structure of documents by examining statistical -co-occurrence patterns of the words within a corpus of training documents. -These algorithms are unsupervised, which means no human input is necessary -- you only need a corpus of plain text documents. -Once these statistical patterns are found, any plain text documents can be succinctly -expressed in the new, semantic representation and queried for topical similarity -against other documents. +The algorithms in Gensim, such as :class:`~gensim.models.word2vec.Word2Vec`, :class:`~gensim.models.fasttext.FastText`, +Latent Semantic Analysis (LSI, LSA, see :class:`~gensim.models.lsimodel.LsiModel`), Latent Dirichlet +Allocation (LDA, see :class:`~gensim.models.ldamodel.LdaModel`) etc, automatically discover the semantic structure of documents by examining statistical +co-occurrence patterns within a corpus of training documents. These algorithms are **unsupervised**, +which means no human input is necessary -- you only need a corpus of plain text documents. + +Once these statistical patterns are found, any plain text documents (sentence, phrase, word…) can be succinctly expressed in the new, semantic representation and queried for topical similarity against other documents (words, phrases…). .. note:: If the previous paragraphs left you confused, you can read more about the `Vector @@ -27,69 +26,71 @@ against other documents. .. _design: Features ------------------- +-------- * **Memory independence** -- there is no need for the whole training corpus to reside fully in RAM at any one time (can process large, web-scale corpora). +* **Memory sharing** -- trained models can be persisted to disk and loaded back via mmap. Multiple processes can share the same data, cutting down RAM footprint. * Efficient implementations for several popular vector space algorithms, - including **Tf-Idf**, distributed incremental **Latent Semantic Analysis**, - distributed incremental **Latent Dirichlet Allocation (LDA)** or **Random Projection**; adding new ones is easy (really!). -* I/O wrappers and converters around **several popular data formats**. -* **Similarity queries** for documents in their semantic representation. - -The creation of `gensim` was motivated by a perceived lack of available, scalable software -frameworks that realize topic modelling, and/or their overwhelming internal complexity (hail Java!). -You can read more about the motivation in our `LREC 2010 workshop paper `_. -If you want to cite `gensim` in your own work, please refer to that article (`BibTeX `_). + including :class:`~gensim.models.word2vec.Word2Vec`, :class:`~gensim.models.doc2vec.Doc2Vec`, :class:`~gensim.models.fasttext.FastText`, + TF-IDF, Latent Semantic Analysis (LSI, LSA, see :class:`~gensim.models.lsimodel.LsiModel`), + Latent Dirichlet Allocation (LDA, see :class:`~gensim.models.ldamodel.LdaModel`) or Random Projection (see :class:`~gensim.models.rpmodel.RpModel`). +* I/O wrappers and readers from several popular data formats. +* Fast similarity queries for documents in their semantic representation. -You're welcome to share your results and experiments on the `mailing list `_. +The **principal design objectives** behind Gensim are: -The **principal design objectives** behind `gensim` are: - -1. Straightforward interfaces and low API learning curve for developers. Good - for prototyping. +1. Straightforward interfaces and low API learning curve for developers. Good for prototyping. 2. Memory independence with respect to the size of the input corpus; all intermediate steps and algorithms operate in a streaming fashion, accessing one document at a time. .. seealso:: - If you're interested in document indexing/similarity retrieval, I also maintain a higher-level package - of `document similarity server `_. It uses `gensim` internally. + We also built a high performance commercial server for NLP, document analysis, indexing, search and clustering: https://scaletext.ai. ScaleText is available both on-prem and as SaaS. + + Reach out at info@scaletext.com if you need an industry-grade NLP tool with professional support. + .. _availability: Availability ------------ -Gensim is licensed under the OSI-approved `GNU LGPLv2.1 license `_ -and can be downloaded either from its `github repository `_ +Gensim is licensed under the OSI-approved `GNU LGPLv2.1 license `_ and can be downloaded either from its `Github repository `_ or from the `Python Package Index `_. .. seealso:: - See the :doc:`install ` page for more info on `gensim` deployment. + See the :doc:`install ` page for more info on Gensim deployment. Core concepts ------------- -The whole `gensim` package revolves around the concepts of :term:`corpus`, :term:`vector` and -:term:`model`. - .. glossary:: Corpus - A collection of digital documents. This collection is used to automatically - infer the structure of the documents, their topics, etc. For - this reason, the collection is also called a *training corpus*. This inferred - latent structure can be later used to assign topics to new documents, which did - not appear in the training corpus. - No human intervention (such as tagging the documents by hand, or creating - other metadata) is required. - - Vector - In the Vector Space Model (VSM), each document is represented by an + A collection of digital documents. Corpora serve two roles in Gensim: + + 1. Input for model training + The corpus is used to automatically train a machine learning model, such as + :class:`~gensim.models.lsimodel.LsiModel` or :class:`~gensim.models.ldamodel.LdaModel`. + + The models use this *training corpus* to look for common themes and topics, initializing + their internal model parameters. + + Gensim in unique in its focus on *unsupervised* models so that no human intervention, + such as costly annotations or tagging documents by hand, is required. + + 2. Documents to organize. + After training, a topic model can be used to extract topics from new documents (documents + not seen in the training corpus). + + Such corpora can be :doc:`indexed `, queried by semantic similarity, clustered etc. + + Vector space model + In a Vector Space Model (VSM), each document is represented by an array of features. For example, a single feature may be thought of as a question-answer pair: @@ -100,10 +101,13 @@ The whole `gensim` package revolves around the concepts of :term:`corpus`, :term The question is usually represented only by its integer id (such as `1`, `2` and `3` here), so that the representation of this document becomes a series of pairs like ``(1, 0.0), (2, 2.0), (3, 5.0)``. + If we know all the questions in advance, we may leave them implicit and simply write ``(0.0, 2.0, 5.0)``. - This sequence of answers can be thought of as a *vector* (in this case a 3-dimensional vector). For practical purposes, only questions to which the answer is (or - can be converted to) a single real number are allowed. + + This sequence of answers can be thought of as a **vector** (in this case a 3-dimensional dense vector). + For practical purposes, only questions to which the answer is (or + can be converted to) a *single floating point number* are allowed in Gensim. The questions are the same for each document, so that looking at two vectors (representing two documents), we will hopefully be able to make @@ -111,36 +115,46 @@ The whole `gensim` package revolves around the concepts of :term:`corpus`, :term therefore the original documents must be similar, too". Of course, whether such conclusions correspond to reality depends on how well we picked our questions. - Sparse Vector - Typically, the answer to most questions will be ``0.0``. To save space, - we omit them from the document's representation, and write only ``(2, 2.0), - (3, 5.0)`` (note the missing ``(1, 0.0)``). - Since the set of all questions is known in advance, all the missing features - in a sparse representation of a document can be unambiguously resolved to zero, ``0.0``. + Gensim sparse vector, Bag-of-words vector + To save space, in Gensim we omit all vector elements with value 0.0. For example, instead of the + 3-dimensional dense vector ``(0.0, 2.0, 5.0)``, we write only ``[(2, 2.0), (3, 5.0)]`` (note the missing ``(1, 0.0)``). Each vector element is a pair (2-tuple) of ``(feature_id, feature_value)``. The values of all missing features in this sparse representation can be unambiguously resolved to zero, ``0.0``. + + Documents in Gensim are represented by such sparse vectors (sometimes called bag-of-words vectors). + + Gensim streamed corpus + Gensim does not prescribe any specific corpus format. A corpus is simply a sequence + of sparse vector (see above). + + For example, ``[ [(2, 2.0), (3, 5.0)], [(3, 1.0)] ]`` + is a simple corpus of two documents = two sparse vectors: the first with two non-zero elements, + the second with one non-zero element. This particular corpus is represented as a plain Python ``list``. + + However, the full power of Gensim comes from the fact that a corpus doesn't have to be a ``list``, + or a ``NumPy`` array, or a ``Pandas`` dataframe, or whatever. Gensim *accepts any object that, + when iterated over, successively yields these sparse bag-of-word vectors*. + + This flexibility allows you to create your own corpus classes that stream the sparse vectors directly from disk, network, database, dataframes…. The models in Gensim are implemented such that they don't require all vectors to reside in RAM at once. You can even create the sparse vectors on the fly! - Gensim does not prescribe any specific corpus format; - a corpus is anything that, when iterated over, successively yields these sparse vectors. - For example, `set((((2, 2.0), (3, 5.0)), ((0, 1.0), (3, 1.0))))` is a trivial - corpus of two documents, each with two non-zero `feature-answer` pairs. + See our `tutorial on streamed data processing in Python `_. + For a built-in example of an efficient corpus format streamed directly from disk, see + the Matrix Market format in :mod:`~gensim.corpora.mmcorpus`. For a minimal blueprint example on + how to create your own streamed corpora, check out the `source code of CSV corpus `_. + Model, Transformation + Gensim uses **model** to refer to the code and associated data (model parameters) + required to transform one document representation to another. - Model - We use **model** as an abstract term referring to a transformation from - one document representation to another. In `gensim` documents are - represented as vectors so a model can be thought of as a transformation - between two vector spaces. The details of this transformation are - learned from the training corpus. + In Gensim, documents are represented as vectors (see above) so a model can be thought of as a transformation + from one vector space to another. The parameters of this transformation are learned from the training corpus. + Trained models (the data parameters) can be persisted to disk and later loaded back, either to continue + training on new training documents or to transform new documents. - For example, consider a transformation that takes a raw count of word - occurrences and weights them so that common words are discounted and - rare words are promoted. The exact amount that any particular word is - weighted by is determined by the relative frequency of that word in the - training corpus. When we apply this model we transform from one vector - space (containing the raw word counts) to another (containing the - weighted counts). + Gensim implements multiple models, such as :class:`~gensim.models.word2vec.Word2Vec`, + :class:`~gensim.models.lsimodel.LsiModel`, :class:`~gensim.models.ldamodel.LdaModel`, + :class:`~gensim.models.fasttext.FastText` etc. See the :doc:`API reference ` for a full list. .. seealso:: - For some examples on how this works out in code, go to :doc:`tutorials `. + For some examples on how all this works out in code, go to :doc:`Tutorials `. diff --git a/docs/src/models/doc2vec.rst b/docs/src/models/doc2vec.rst index f2da8bb722..b5d2e290b5 100644 --- a/docs/src/models/doc2vec.rst +++ b/docs/src/models/doc2vec.rst @@ -1,8 +1,8 @@ -:mod:`models.doc2vec` -- Deep learning with paragraph2vec -========================================================= +:mod:`models.doc2vec` -- Doc2vec paragraph embeddings +===================================================== .. automodule:: gensim.models.doc2vec - :synopsis: Deep learning with doc2vec + :synopsis: Doc2vec paragraph embeddings :members: :inherited-members: :undoc-members: diff --git a/docs/src/models/word2vec.rst b/docs/src/models/word2vec.rst index 1679429e22..62117c1a6b 100644 --- a/docs/src/models/word2vec.rst +++ b/docs/src/models/word2vec.rst @@ -1,8 +1,8 @@ -:mod:`models.word2vec` -- Deep learning with word2vec -====================================================== +:mod:`models.word2vec` -- Word2vec embeddings +============================================= .. automodule:: gensim.models.word2vec - :synopsis: Deep learning with word2vec + :synopsis: Word2vec embeddings :members: :inherited-members: :undoc-members: diff --git a/docs/src/support.rst b/docs/src/support.rst index a9f83e1380..44b213b865 100644 --- a/docs/src/support.rst +++ b/docs/src/support.rst @@ -1,18 +1,21 @@ .. _support: -============= +======= Support -============= +======= Open source support --------------------- +------------------- + +The main communication channel is the `Gensim mailing list `_. + +Additional channels are `twitter @gensim_py `_ and `Gitter piskvorky/gensim `_. -The main communication channel is the `gensim mailing list `_. This is the preferred way to **ask for help**, **report problems** and **share insights** with the community. Newbie questions are perfectly fine, just make sure you've read the :doc:`tutorials `. -I discourage sending private emails, because the mailing list serves as a knowledge base for all gensim users, cutting maintenance efforts needed for support. If you feel your problem is too special, data too sensitive, technical scope too demanding, **see the "business" section below**. +I discourage sending private emails, because the mailing list serves as a knowledge base for all Gensim users, cutting maintenance efforts needed for support. If you feel your problem is too special, data too sensitive, technical scope too demanding, **see the "business" section below**. -When posting on the mailing list, try to include all relevant information, such as what it is you are trying to achieve, what went wrong, relevant gensim logs, package versions etc. +When posting on the mailing list, try to include all relevant information, such as what it is you are trying to achieve, what went wrong, relevant Gensim logs, package versions etc. **FAQ** and some useful **snippets of code** are maintained on GitHub: https://github.com/piskvorky/gensim/wiki/Recipes-&-FAQ. @@ -20,14 +23,16 @@ You can also try asking on StackOverflow, using the `gensim tag `_. +We run a consulting R&D company focused on data mining and unstructured text processing, https://rare-technologies.com. + +If you need commercial support, design validation, technical training or custom system development, `get in touch `_ for a quote. -In case you need commercial support, design validation, technical training or custom system development, `get in touch `_ for a quote. Developer support ------------------ -Developers who `tweak gensim internals `_ are encouraged to report issues at the `GitHub issue tracker `_. -Note that this is not a medium for discussions or asking open-ended questions; please use the mailing list for that. +Developers who `tweak Gensim internals `_ are encouraged to report issues at the `GitHub issue tracker `_. + +Note that Github is not a medium for discussions or asking open-ended questions; please use the `mailing list `_ for that. From 37e49971efa74310b300468a5b3cf531319c6536 Mon Sep 17 00:00:00 2001 From: Ivan Menshikh Date: Wed, 27 Jun 2018 13:37:16 +0500 Subject: [PATCH 16/40] Disable google-style docstring support. Fix #1663 (#2106) --- docs/src/conf.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/src/conf.py b/docs/src/conf.py index 31d512262c..71eb9a9014 100644 --- a/docs/src/conf.py +++ b/docs/src/conf.py @@ -28,6 +28,8 @@ extensions = ['sphinx.ext.autodoc', 'sphinxcontrib.napoleon', 'sphinx.ext.imgmath', 'sphinxcontrib.programoutput'] autoclass_content = "both" +napoleon_google_docstring = False # Disable support for google-style docstring + # Add any paths that contain templates here, relative to this directory. templates_path = ['_templates'] From 875b028ccd009fe2fa7665e177b8ab0b5e2dc40d Mon Sep 17 00:00:00 2001 From: Gordon Mohr Date: Thu, 5 Jul 2018 08:53:09 -0700 Subject: [PATCH 17/40] Fix `Doc2Vec.infer_vector`, notebook cleanup (#2103) * inherit inference defaults/param-names from model * corrections, fresh execution w/ current code * improve wordings * simplify, optimize notebook; fresh runthrough * fresh execution cells; remove stray cell * py3 fixes; fresh execution cells * restore 1st cell timing * attempt to fix tests on `python27` --- docs/notebooks/doc2vec-IMDB.ipynb | 928 ++++++++++++++++-------------- docs/notebooks/doc2vec-lee.ipynb | 123 ++-- gensim/models/doc2vec.py | 25 +- gensim/test/test_doc2vec.py | 12 +- setup.py | 2 +- 5 files changed, 594 insertions(+), 496 deletions(-) diff --git a/docs/notebooks/doc2vec-IMDB.ipynb b/docs/notebooks/doc2vec-IMDB.ipynb index 5b680eddad..61e83a9459 100644 --- a/docs/notebooks/doc2vec-IMDB.ipynb +++ b/docs/notebooks/doc2vec-IMDB.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Gensim Doc2vec Tutorial on the IMDB Sentiment Dataset" + "# Gensim `Doc2Vec` Tutorial on the IMDB Sentiment Dataset" ] }, { @@ -16,7 +16,7 @@ "In this tutorial, we will learn how to apply Doc2vec using gensim by recreating the results of Le and Mikolov 2014. \n", "\n", "### Bag-of-words Model\n", - "Previous state-of-the-art document representations were based on the bag-of-words model, which represent input documents as a fixed-length vector. For example, borrowing from the Wikipedia article, the two documents \n", + "Early state-of-the-art document representations were based on the bag-of-words model, which represent input documents as a fixed-length vector. For example, borrowing from the Wikipedia article, the two documents \n", "(1) `John likes to watch movies. Mary likes movies too.` \n", "(2) `John also likes to watch football games.` \n", "are used to construct a length 10 list of words \n", @@ -26,24 +26,29 @@ "(2) `[1, 1, 1, 1, 0, 0, 0, 1, 1, 1]` \n", "Bag-of-words models are surprisingly effective but still lose information about word order. Bag of n-grams models consider word phrases of length n to represent documents as fixed-length vectors to capture local word order but suffer from data sparsity and high dimensionality.\n", "\n", - "### Word2vec Model\n", - "Word2vec is a more recent model that embeds words in a high-dimensional vector space using a shallow neural network. The result is a set of word vectors where vectors close together in vector space have similar meanings based on context, and word vectors distant to each other have differing meanings. For example, `strong` and `powerful` would be close together and `strong` and `Paris` would be relatively far. There are two versions of this model based on skip-grams and continuous bag of words.\n", + "### `Word2Vec`\n", + "`Word2Vec` is a more recent model that embeds words in a lower-dimensional vector space using a shallow neural network. The result is a set of word-vectors where vectors close together in vector space have similar meanings based on context, and word-vectors distant to each other have differing meanings. For example, `strong` and `powerful` would be close together and `strong` and `Paris` would be relatively far. There are two versions of this model based on skip-grams (SG) and continuous-bag-of-words (CBOW), both implemented by the gensim `Word2Vec` class.\n", "\n", "\n", - "#### Word2vec - Skip-gram Model\n", - "The skip-gram word2vec model, for example, takes in pairs (word1, word2) generated by moving a window across text data, and trains a 1-hidden-layer neural network based on the fake task of given an input word, giving us a predicted probability distribution of nearby words to the input. The hidden-to-output weights in the neural network give us the word embeddings. So if the hidden layer has 300 neurons, this network will give us 300-dimensional word embeddings. We use one-hot encoding for the words.\n", + "#### `Word2Vec` - Skip-gram Model\n", + "The skip-gram word2vec model, for example, takes in pairs (word1, word2) generated by moving a window across text data, and trains a 1-hidden-layer neural network based on the synthetic task of given an input word, giving us a predicted probability distribution of nearby words to the input. A virtual one-hot encoding of words goes through a 'projection layer' to the hidden layer; these projection weights are later interpreted as the word embeddings. So if the hidden layer has 300 neurons, this network will give us 300-dimensional word embeddings.\n", "\n", - "#### Word2vec - Continuous-bag-of-words Model\n", - "Continuous-bag-of-words Word2vec is very similar to the skip-gram model. It is also a 1-hidden-layer neural network. The fake task is based on the input context words in a window around a center word, predict the center word. Again, the hidden-to-output weights give us the word embeddings and we use one-hot encoding.\n", + "#### `Word2Vec` - Continuous-bag-of-words Model\n", + "Continuous-bag-of-words Word2vec is very similar to the skip-gram model. It is also a 1-hidden-layer neural network. The synthetic training task now uses the average of multiple input context words, rather than a single word as in skip-gram, to predict the center word. Again, the projection weights that turn one-hot words into averageable vectors, of the same width as the hidden layer, are interpreted as the word embeddings. \n", "\n", - "### Paragraph Vector\n", - "Le and Mikolov 2014 introduces the Paragraph Vector, which outperforms more naïve representations of documents such as averaging the Word2vec word vectors of a document. The idea is straightforward: we act as if a paragraph (or document) is just another vector like a word vector, but we will call it a paragraph vector. We determine the embedding of the paragraph in vector space in the same way as words. Our paragraph vector model considers local word order like bag of n-grams, but gives us a denser representation in vector space compared to a sparse, high-dimensional representation.\n", + "But, Word2Vec doesn't yet get us fixed-size vectors for longer texts.\n", + "\n", + "\n", + "### Paragraph Vector, aka gensim `Doc2Vec`\n", + "The straightforward approach of averaging each of a text's words' word-vectors creates a quick and crude document-vector that can often be useful. However, Le and Mikolov in 2014 introduced the Paragraph Vector, which usually outperforms such simple-averaging.\n", + "\n", + "The basic idea is: act as if a document has another floating word-like vector, which contributes to all training predictions, and is updated like other word-vectors, but we will call it a doc-vector. Gensim's `Doc2Vec` class implements this algorithm. \n", "\n", "#### Paragraph Vector - Distributed Memory (PV-DM)\n", - "This is the Paragraph Vector model analogous to Continuous-bag-of-words Word2vec. The paragraph vectors are obtained by training a neural network on the fake task of inferring a center word based on context words and a context paragraph. A paragraph is a context for all words in the paragraph, and a word in a paragraph can have that paragraph as a context. \n", + "This is the Paragraph Vector model analogous to Word2Vec CBOW. The doc-vectors are obtained by training a neural network on the synthetic task of predicting a center word based an average of both context word-vectors and the full document's doc-vector.\n", "\n", "#### Paragraph Vector - Distributed Bag of Words (PV-DBOW)\n", - "This is the Paragraph Vector model analogous to Skip-gram Word2vec. The paragraph vectors are obtained by training a neural network on the fake task of predicting a probability distribution of words in a paragraph given a randomly-sampled word from the paragraph.\n", + "This is the Paragraph Vector model analogous to Word2Vec SG. The doc-vectors are obtained by training a neural network on the synthetic task of predicting a target word just from the full document's doc-vector. (It is also common to combine this with skip-gram testing, using both the doc-vector and nearby word-vectors to predict a single target word, but only one at a time.)\n", "\n", "### Requirements\n", "The following python modules are dependencies for this tutorial:\n", @@ -63,7 +68,9 @@ "metadata": {}, "source": [ "Let's download the IMDB archive if it is not already downloaded (84 MB). This will be our text data for this tutorial. \n", - "The data can be found here: http://ai.stanford.edu/~amaas/data/sentiment/" + "The data can be found here: http://ai.stanford.edu/~amaas/data/sentiment/\n", + "\n", + "This cell will only reattempt steps (such as downloading the compressed data) if their output isn't already present, so it is safe to re-run until it completes successfully. " ] }, { @@ -75,11 +82,22 @@ "name": "stdout", "output_type": "stream", "text": [ - "Total running time: 0.00035199999999990794\n" + "IMDB archive directory already available without download.\n", + "Cleaning up dataset...\n", + " train/pos: 12500 files\n", + " train/neg: 12500 files\n", + " test/pos: 12500 files\n", + " test/neg: 12500 files\n", + " train/unsup: 50000 files\n", + "Success, alldata-id.txt is available for next steps.\n", + "CPU times: user 17.3 s, sys: 14.1 s, total: 31.3 s\n", + "Wall time: 1min 2s\n" ] } ], "source": [ + "%%time \n", + "\n", "import locale\n", "import glob\n", "import os.path\n", @@ -87,11 +105,13 @@ "import tarfile\n", "import sys\n", "import codecs\n", - "import smart_open\n", + "from smart_open import smart_open\n", + "import re\n", "\n", "dirname = 'aclImdb'\n", "filename = 'aclImdb_v1.tar.gz'\n", "locale.setlocale(locale.LC_ALL, 'C')\n", + "all_lines = []\n", "\n", "if sys.version > '3':\n", " control_chars = [chr(0x85)]\n", @@ -104,14 +124,9 @@ " # Replace breaks with spaces\n", " norm_text = norm_text.replace('
', ' ')\n", " # Pad punctuation with spaces on both sides\n", - " for char in ['.', '\"', ',', '(', ')', '!', '?', ';', ':']:\n", - " norm_text = norm_text.replace(char, ' ' + char + ' ')\n", + " norm_text = re.sub(r\"([\\.\\\",\\(\\)!\\?;:])\", \" \\\\1 \", norm_text)\n", " return norm_text\n", "\n", - "import time\n", - "import smart_open\n", - "start = time.clock()\n", - "\n", "if not os.path.isfile('aclImdb/alldata-id.txt'):\n", " if not os.path.isdir(dirname):\n", " if not os.path.isfile(filename):\n", @@ -119,52 +134,44 @@ " print(\"Downloading IMDB archive...\")\n", " url = u'http://ai.stanford.edu/~amaas/data/sentiment/' + filename\n", " r = requests.get(url)\n", - " with smart_open.smart_open(filename, 'wb') as f:\n", + " with smart_open(filename, 'wb') as f:\n", " f.write(r.content)\n", + " # if error here, try `tar xfz aclImdb_v1.tar.gz` outside notebook, then re-run this cell\n", " tar = tarfile.open(filename, mode='r')\n", " tar.extractall()\n", " tar.close()\n", + " else:\n", + " print(\"IMDB archive directory already available without download.\")\n", "\n", - " # Concatenate and normalize test/train data\n", + " # Collect & normalize test/train data\n", " print(\"Cleaning up dataset...\")\n", " folders = ['train/pos', 'train/neg', 'test/pos', 'test/neg', 'train/unsup']\n", - " alldata = u''\n", " for fol in folders:\n", " temp = u''\n", + " newline = \"\\n\".encode(\"utf-8\")\n", " output = fol.replace('/', '-') + '.txt'\n", " # Is there a better pattern to use?\n", " txt_files = glob.glob(os.path.join(dirname, fol, '*.txt'))\n", - " for txt in txt_files:\n", - " with smart_open.smart_open(txt, \"rb\") as t:\n", - " t_clean = t.read().decode(\"utf-8\")\n", - " for c in control_chars:\n", - " t_clean = t_clean.replace(c, ' ')\n", - " temp += t_clean\n", - " temp += \"\\n\"\n", - " temp_norm = normalize_text(temp)\n", - " with smart_open.smart_open(os.path.join(dirname, output), \"wb\") as n:\n", - " n.write(temp_norm.encode(\"utf-8\"))\n", - " alldata += temp_norm\n", + " print(\" %s: %i files\" % (fol, len(txt_files)))\n", + " with smart_open(os.path.join(dirname, output), \"wb\") as n:\n", + " for i, txt in enumerate(txt_files):\n", + " with smart_open(txt, \"rb\") as t:\n", + " one_text = t.read().decode(\"utf-8\")\n", + " for c in control_chars:\n", + " one_text = one_text.replace(c, ' ')\n", + " one_text = normalize_text(one_text)\n", + " all_lines.append(one_text)\n", + " n.write(one_text.encode(\"utf-8\"))\n", + " n.write(newline)\n", "\n", - " with smart_open.smart_open(os.path.join(dirname, 'alldata-id.txt'), 'wb') as f:\n", - " for idx, line in enumerate(alldata.splitlines()):\n", + " # Save to disk for instant re-use on any future runs\n", + " with smart_open(os.path.join(dirname, 'alldata-id.txt'), 'wb') as f:\n", + " for idx, line in enumerate(all_lines):\n", " num_line = u\"_*{0} {1}\\n\".format(idx, line)\n", " f.write(num_line.encode(\"utf-8\"))\n", "\n", - "end = time.clock()\n", - "print (\"Total running time: \", end-start)" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "import os.path\n", - "assert os.path.isfile(\"aclImdb/alldata-id.txt\"), \"alldata-id.txt unavailable\"" + "assert os.path.isfile(\"aclImdb/alldata-id.txt\"), \"alldata-id.txt unavailable\"\n", + "print(\"Success, alldata-id.txt is available for next steps.\")" ] }, { @@ -176,28 +183,32 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "100000 docs: 25000 train-sentiment, 25000 test-sentiment\n" + "100000 docs: 25000 train-sentiment, 25000 test-sentiment\n", + "CPU times: user 5.3 s, sys: 1.25 s, total: 6.55 s\n", + "Wall time: 6.74 s\n" ] } ], "source": [ + "%%time\n", + "\n", "import gensim\n", "from gensim.models.doc2vec import TaggedDocument\n", "from collections import namedtuple\n", - "from smart_open import smart_open\n", "\n", + "# this data object class suffices as a `TaggedDocument` (with `words` and `tags`) \n", + "# plus adds other state helpful for our later evaluation/reporting\n", "SentimentDocument = namedtuple('SentimentDocument', 'words tags split sentiment')\n", "\n", - "alldocs = [] # Will hold all docs in original order\n", - "with smart_open('aclImdb/alldata-id.txt', 'rb') as alldata:\n", - " alldata = alldata.read().decode('utf-8')\n", + "alldocs = []\n", + "with smart_open('aclImdb/alldata-id.txt', 'rb', encoding='utf-8') as alldata:\n", " for line_no, line in enumerate(alldata):\n", " tokens = gensim.utils.to_unicode(line).split()\n", " words = tokens[1:]\n", @@ -208,9 +219,26 @@ "\n", "train_docs = [doc for doc in alldocs if doc.split == 'train']\n", "test_docs = [doc for doc in alldocs if doc.split == 'test']\n", - "doc_list = alldocs[:] # For reshuffling per pass\n", "\n", - "print('%d docs: %d train-sentiment, %d test-sentiment' % (len(doc_list), len(train_docs), len(test_docs)))" + "print('%d docs: %d train-sentiment, %d test-sentiment' % (len(alldocs), len(train_docs), len(test_docs)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Because the native document-order has similar-sentiment documents in large clumps – which is suboptimal for training – we work with once-shuffled copy of the training set." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "from random import shuffle\n", + "doc_list = alldocs[:] \n", + "shuffle(doc_list)" ] }, { @@ -229,7 +257,7 @@ "`./word2vec -train ../alldata-id.txt -output vectors.txt -cbow 0 -size 100 -window 10 -negative 5 -hs 0 -sample 1e-4 -threads 40 -binary 0 -iter 20 -min-count 1 -sentence-vectors 1`\n", "\n", "We vary the following parameter choices:\n", - "* 100-dimensional vectors, as the 400-d vectors of the paper don't seem to offer much benefit on this task\n", + "* 100-dimensional vectors, as the 400-d vectors of the paper take a lot of memory and, in our tests of this task, don't seem to offer much benefit\n", "* Similarly, frequent word subsampling seems to decrease sentiment-prediction accuracy, so it's left out\n", "* `cbow=0` means skip-gram which is equivalent to the paper's 'PV-DBOW' mode, matched in gensim with `dm=0`\n", "* Added to that DBOW model are two DM models, one which averages context vectors (`dm_mean`) and one which concatenates them (`dm_concat`, resulting in a much larger, slower, more data-hungry model)\n", @@ -245,13 +273,16 @@ "name": "stdout", "output_type": "stream", "text": [ - "Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)\n", - "Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)\n", - "Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)\n" + "Doc2Vec(dbow,d100,n5,mc2,t4) vocabulary scanned & state initialized\n", + "Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4) vocabulary scanned & state initialized\n", + "Doc2Vec(dm/c,d100,n5,w5,mc2,t4) vocabulary scanned & state initialized\n", + "CPU times: user 28.7 s, sys: 414 ms, total: 29.1 s\n", + "Wall time: 29.1 s\n" ] } ], "source": [ + "%%time\n", "from gensim.models import Doc2Vec\n", "import gensim.models.doc2vec\n", "from collections import OrderedDict\n", @@ -261,20 +292,21 @@ "assert gensim.models.doc2vec.FAST_VERSION > -1, \"This will be painfully slow otherwise\"\n", "\n", "simple_models = [\n", - " # PV-DM w/ concatenation - window=5 (both sides) approximates paper's 10-word total window size\n", - " Doc2Vec(dm=1, dm_concat=1, size=100, window=5, negative=5, hs=0, min_count=2, workers=cores),\n", - " # PV-DBOW \n", - " Doc2Vec(dm=0, size=100, negative=5, hs=0, min_count=2, workers=cores),\n", - " # PV-DM w/ average\n", - " Doc2Vec(dm=1, dm_mean=1, size=100, window=10, negative=5, hs=0, min_count=2, workers=cores),\n", + " # PV-DBOW plain\n", + " Doc2Vec(dm=0, vector_size=100, negative=5, hs=0, min_count=2, sample=0, \n", + " epochs=20, workers=cores),\n", + " # PV-DM w/ default averaging; a higher starting alpha may improve CBOW/PV-DM modes\n", + " Doc2Vec(dm=1, vector_size=100, window=10, negative=5, hs=0, min_count=2, sample=0, \n", + " epochs=20, workers=cores, alpha=0.05, comment='alpha=0.05'),\n", + " # PV-DM w/ concatenation - big, slow, experimental mode\n", + " # window=5 (both sides) approximates paper's apparent 10-word total window size\n", + " Doc2Vec(dm=1, dm_concat=1, vector_size=100, window=5, negative=5, hs=0, min_count=2, sample=0, \n", + " epochs=20, workers=cores),\n", "]\n", "\n", - "# Speed up setup by sharing results of the 1st model's vocabulary scan\n", - "simple_models[0].build_vocab(alldocs) # PV-DM w/ concat requires one special NULL word so it serves as template\n", - "print(simple_models[0])\n", - "for model in simple_models[1:]:\n", - " model.reset_from(simple_models[0])\n", - " print(model)\n", + "for model in simple_models:\n", + " model.build_vocab(alldocs)\n", + " print(\"%s vocabulary scanned & state initialized\" % model)\n", "\n", "models_by_name = OrderedDict((str(model), model) for model in simple_models)" ] @@ -283,20 +315,18 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Le and Mikolov notes that combining a paragraph vector from Distributed Bag of Words (DBOW) and Distributed Memory (DM) improves performance. We will follow, pairing the models together for evaluation. Here, we concatenate the paragraph vectors obtained from each model." + "Le and Mikolov notes that combining a paragraph vector from Distributed Bag of Words (DBOW) and Distributed Memory (DM) improves performance. We will follow, pairing the models together for evaluation. Here, we concatenate the paragraph vectors obtained from each model with the help of a thin wrapper class included in a gensim test module. (Note that this a separate, later concatenation of output-vectors than the kind of input-window-concatenation enabled by the `dm_concat=1` mode above.)" ] }, { "cell_type": "code", "execution_count": 5, - "metadata": { - "collapsed": true - }, + "metadata": {}, "outputs": [], "source": [ "from gensim.test.test_doc2vec import ConcatenatedDoc2Vec\n", - "models_by_name['dbow+dmm'] = ConcatenatedDoc2Vec([simple_models[1], simple_models[2]])\n", - "models_by_name['dbow+dmc'] = ConcatenatedDoc2Vec([simple_models[1], simple_models[0]])" + "models_by_name['dbow+dmm'] = ConcatenatedDoc2Vec([simple_models[0], simple_models[1]])\n", + "models_by_name['dbow+dmc'] = ConcatenatedDoc2Vec([simple_models[0], simple_models[2]])" ] }, { @@ -317,49 +347,34 @@ "cell_type": "code", "execution_count": 6, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/daniel/miniconda3/envs/gensim/lib/python3.6/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n", - " from pandas.core import datetools\n" - ] - } - ], + "outputs": [], "source": [ "import numpy as np\n", "import statsmodels.api as sm\n", "from random import sample\n", - "\n", - "# For timing\n", - "from contextlib import contextmanager\n", - "from timeit import default_timer\n", - "import time \n", - "\n", - "@contextmanager\n", - "def elapsed_timer():\n", - " start = default_timer()\n", - " elapser = lambda: default_timer() - start\n", - " yield lambda: elapser()\n", - " end = default_timer()\n", - " elapser = lambda: end-start\n", " \n", "def logistic_predictor_from_data(train_targets, train_regressors):\n", + " \"\"\"Fit a statsmodel logistic predictor on supplied data\"\"\"\n", " logit = sm.Logit(train_targets, train_regressors)\n", " predictor = logit.fit(disp=0)\n", " # print(predictor.summary())\n", " return predictor\n", "\n", - "def error_rate_for_model(test_model, train_set, test_set, infer=False, infer_steps=3, infer_alpha=0.1, infer_subsample=0.1):\n", + "def error_rate_for_model(test_model, train_set, test_set, \n", + " reinfer_train=False, reinfer_test=False, \n", + " infer_steps=None, infer_alpha=None, infer_subsample=0.2):\n", " \"\"\"Report error rate on test_doc sentiments, using supplied model and train_docs\"\"\"\n", "\n", - " train_targets, train_regressors = zip(*[(doc.sentiment, test_model.docvecs[doc.tags[0]]) for doc in train_set])\n", + " train_targets = [doc.sentiment for doc in train_set]\n", + " if reinfer_train:\n", + " train_regressors = [test_model.infer_vector(doc.words, steps=infer_steps, alpha=infer_alpha) for doc in train_set]\n", + " else:\n", + " train_regressors = [test_model.docvecs[doc.tags[0]] for doc in train_set]\n", " train_regressors = sm.add_constant(train_regressors)\n", " predictor = logistic_predictor_from_data(train_targets, train_regressors)\n", "\n", " test_data = test_set\n", - " if infer:\n", + " if reinfer_test:\n", " if infer_subsample < 1.0:\n", " test_data = sample(test_data, int(infer_subsample * len(test_data)))\n", " test_regressors = [test_model.infer_vector(doc.words, steps=infer_steps, alpha=infer_alpha) for doc in test_data]\n", @@ -379,18 +394,16 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Bulk Training" + "## Bulk Training & Per-Model Evaluation" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "We use an explicit multiple-pass, alpha-reduction approach as sketched in this [gensim doc2vec blog post](http://radimrehurek.com/2014/12/doc2vec-tutorial/) with added shuffling of corpus on each pass.\n", - "\n", - "Note that vector training is occurring on *all* documents of the dataset, which includes all TRAIN/TEST/DEV docs.\n", + "Note that doc-vector training is occurring on *all* documents of the dataset, which includes all TRAIN/TEST/DEV docs.\n", "\n", - "We evaluate each model's sentiment predictive power based on error rate, and the evaluation is repeated after each pass so we can see the rates of relative improvement. The base numbers reuse the TRAIN and TEST vectors stored in the models for the logistic regression, while the _inferred_ results use newly-inferred TEST vectors. \n", + "We evaluate each model's sentiment predictive power based on error rate, and the evaluation is done for each model. \n", "\n", "(On a 4-core 2.6Ghz Intel Core i7, these 20 passes training and evaluating 3 main models takes about an hour.)" ] @@ -398,13 +411,11 @@ { "cell_type": "code", "execution_count": 7, - "metadata": { - "collapsed": true - }, + "metadata": {}, "outputs": [], "source": [ "from collections import defaultdict\n", - "best_error = defaultdict(lambda: 1.0) # To selectively print only best errors achieved" + "error_rates = defaultdict(lambda: 1.0) # To selectively print only best errors achieved" ] }, { @@ -416,208 +427,82 @@ "name": "stdout", "output_type": "stream", "text": [ - "START 2017-07-08 17:48:01.470463\n", - "*0.404640 : 1 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 80.4s 2.3s\n", - "*0.361200 : 1 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)_inferred 80.4s 10.9s\n", - "*0.247520 : 1 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.0s 1.1s\n", - "*0.201200 : 1 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)_inferred 31.0s 3.5s\n", - "*0.264120 : 1 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 38.5s 0.7s\n", - "*0.203600 : 1 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)_inferred 38.5s 4.7s\n", - "*0.216600 : 1 passes : dbow+dmm 0.0s 1.7s\n", - "*0.199600 : 1 passes : dbow+dmm_inferred 0.0s 10.6s\n", - "*0.244800 : 1 passes : dbow+dmc 0.0s 2.0s\n", - "*0.219600 : 1 passes : dbow+dmc_inferred 0.0s 15.0s\n", - "Completed pass 1 at alpha 0.025000\n", - "*0.349560 : 2 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 52.7s 0.6s\n", - "*0.147400 : 2 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 20.3s 0.5s\n", - "*0.209200 : 2 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 28.3s 0.5s\n", - "*0.140280 : 2 passes : dbow+dmm 0.0s 1.4s\n", - "*0.149360 : 2 passes : dbow+dmc 0.0s 2.2s\n", - "Completed pass 2 at alpha 0.023800\n", - "*0.308760 : 3 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 50.4s 0.6s\n", - "*0.126880 : 3 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 19.5s 0.5s\n", - "*0.192560 : 3 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 37.8s 0.7s\n", - "*0.124440 : 3 passes : dbow+dmm 0.0s 1.8s\n", - "*0.126280 : 3 passes : dbow+dmc 0.0s 1.7s\n", - "Completed pass 3 at alpha 0.022600\n", - "*0.277160 : 4 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 75.2s 0.7s\n", - "*0.119120 : 4 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.0s 2.6s\n", - "*0.177960 : 4 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 48.3s 0.8s\n", - "*0.118000 : 4 passes : dbow+dmm 0.0s 2.2s\n", - "*0.119400 : 4 passes : dbow+dmc 0.0s 2.0s\n", - "Completed pass 4 at alpha 0.021400\n", - "*0.256040 : 5 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 75.2s 0.8s\n", - "*0.256800 : 5 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)_inferred 75.2s 9.0s\n", - "*0.115120 : 5 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 34.0s 1.6s\n", - "*0.115200 : 5 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)_inferred 34.0s 3.5s\n", - "*0.171840 : 5 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 42.5s 0.9s\n", - "*0.202400 : 5 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)_inferred 42.5s 6.2s\n", - "*0.111920 : 5 passes : dbow+dmm 0.0s 2.0s\n", - "*0.118000 : 5 passes : dbow+dmm_inferred 0.0s 11.6s\n", - "*0.113040 : 5 passes : dbow+dmc 0.0s 2.2s\n", - "*0.115600 : 5 passes : dbow+dmc_inferred 0.0s 17.3s\n", - "Completed pass 5 at alpha 0.020200\n", - "*0.236880 : 6 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 70.1s 2.0s\n", - "*0.109720 : 6 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 32.2s 0.9s\n", - "*0.166320 : 6 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 44.8s 0.9s\n", - "*0.108720 : 6 passes : dbow+dmm 0.0s 2.1s\n", - "*0.108480 : 6 passes : dbow+dmc 0.0s 2.0s\n", - "Completed pass 6 at alpha 0.019000\n", - "*0.221640 : 7 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 84.7s 0.9s\n", - "*0.107120 : 7 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.3s 1.9s\n", - "*0.164000 : 7 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 43.0s 0.9s\n", - "*0.106160 : 7 passes : dbow+dmm 0.0s 2.0s\n", - "*0.106680 : 7 passes : dbow+dmc 0.0s 2.0s\n", - "Completed pass 7 at alpha 0.017800\n", - "*0.209360 : 8 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 64.0s 0.8s\n", - "*0.106200 : 8 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.2s 0.8s\n", - "*0.161360 : 8 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 43.0s 0.9s\n", - "*0.104480 : 8 passes : dbow+dmm 0.0s 3.0s\n", - "*0.105640 : 8 passes : dbow+dmc 0.0s 2.0s\n", - "Completed pass 8 at alpha 0.016600\n", - "*0.203520 : 9 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 66.6s 1.0s\n", - "*0.105120 : 9 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 39.1s 1.1s\n", - "*0.160960 : 9 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 43.7s 0.7s\n", - " 0.104840 : 9 passes : dbow+dmm 0.0s 2.0s\n", - "*0.104240 : 9 passes : dbow+dmc 0.0s 2.0s\n", - "Completed pass 9 at alpha 0.015400\n", - "*0.195840 : 10 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 66.5s 1.7s\n", - "*0.197600 : 10 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)_inferred 66.5s 10.1s\n", - "*0.104280 : 10 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.3s 0.8s\n", - " 0.115200 : 10 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)_inferred 31.3s 4.7s\n", - "*0.158800 : 10 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 44.5s 0.9s\n", - "*0.182800 : 10 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)_inferred 44.5s 6.3s\n", - "*0.102760 : 10 passes : dbow+dmm 0.0s 3.1s\n", - "*0.110000 : 10 passes : dbow+dmm_inferred 0.0s 11.3s\n", - "*0.103920 : 10 passes : dbow+dmc 0.0s 2.2s\n", - "*0.109200 : 10 passes : dbow+dmc_inferred 0.0s 16.4s\n", - "Completed pass 10 at alpha 0.014200\n", - "*0.190800 : 11 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 71.3s 1.0s\n", - "*0.103840 : 11 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 33.8s 0.8s\n", - "*0.157440 : 11 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 44.5s 0.9s\n", - " 0.103240 : 11 passes : dbow+dmm 0.0s 3.0s\n", - " 0.104360 : 11 passes : dbow+dmc 0.0s 2.1s\n", - "Completed pass 11 at alpha 0.013000\n", - "*0.188520 : 12 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 65.4s 0.8s\n", - " 0.104600 : 12 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 33.3s 1.0s\n", - "*0.157240 : 12 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 53.5s 1.7s\n", - " 0.103880 : 12 passes : dbow+dmm 0.0s 2.8s\n", - " 0.104640 : 12 passes : dbow+dmc 0.0s 2.6s\n", - "Completed pass 12 at alpha 0.011800\n", - "*0.185760 : 13 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 71.8s 1.7s\n", - " 0.104040 : 13 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.9s 1.0s\n", - "*0.155960 : 13 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 45.7s 0.8s\n", - "*0.102720 : 13 passes : dbow+dmm 0.0s 2.0s\n", - " 0.104120 : 13 passes : dbow+dmc 0.0s 1.9s\n", - "Completed pass 13 at alpha 0.010600\n", - "*0.181960 : 14 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 80.3s 0.8s\n", - "*0.103680 : 14 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 23.1s 0.7s\n", - "*0.155040 : 14 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 31.4s 1.5s\n", - "*0.102440 : 14 passes : dbow+dmm 0.0s 1.6s\n", - "*0.103680 : 14 passes : dbow+dmc 0.0s 1.7s\n", - "Completed pass 14 at alpha 0.009400\n", - "*0.180680 : 15 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 48.5s 0.7s\n", - "*0.186000 : 15 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)_inferred 48.5s 12.0s\n", - " 0.104840 : 15 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 23.4s 0.7s\n", - "*0.101600 : 15 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)_inferred 23.4s 4.3s\n", - "*0.154000 : 15 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 53.2s 2.0s\n", - " 0.191600 : 15 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)_inferred 53.2s 4.8s\n", - " 0.102960 : 15 passes : dbow+dmm 0.0s 3.1s\n", - "*0.108400 : 15 passes : dbow+dmm_inferred 0.0s 11.4s\n", - " 0.104280 : 15 passes : dbow+dmc 0.0s 1.7s\n", - "*0.098400 : 15 passes : dbow+dmc_inferred 0.0s 14.1s\n", - "Completed pass 15 at alpha 0.008200\n", - "*0.180320 : 16 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 68.3s 1.0s\n", - "*0.103600 : 16 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 28.5s 2.1s\n", - " 0.154640 : 16 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 43.4s 0.7s\n", - " 0.102520 : 16 passes : dbow+dmm 0.0s 1.9s\n", - "*0.102480 : 16 passes : dbow+dmc 0.0s 2.9s\n", - "Completed pass 16 at alpha 0.007000\n", - "*0.178160 : 17 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 63.4s 2.0s\n", - "*0.103360 : 17 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 31.5s 0.8s\n", - " 0.154160 : 17 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 40.9s 1.0s\n", - "*0.102320 : 17 passes : dbow+dmm 0.0s 3.0s\n", - " 0.102680 : 17 passes : dbow+dmc 0.0s 2.0s\n", - "Completed pass 17 at alpha 0.005800\n", - "*0.177520 : 18 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 55.1s 0.8s\n", - "*0.103120 : 18 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 24.8s 0.7s\n", - "*0.153040 : 18 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 32.9s 0.8s\n", - " 0.102440 : 18 passes : dbow+dmm 0.0s 1.7s\n", - "*0.102480 : 18 passes : dbow+dmc 0.0s 2.6s\n", - "Completed pass 18 at alpha 0.004600\n", - "*0.177240 : 19 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 57.2s 1.5s\n", - "*0.103080 : 19 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 20.6s 1.8s\n", - "*0.152680 : 19 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 43.8s 0.8s\n", - " 0.102800 : 19 passes : dbow+dmm 0.0s 1.8s\n", - " 0.102600 : 19 passes : dbow+dmc 0.0s 1.7s\n", - "Completed pass 19 at alpha 0.003400\n", - "*0.176080 : 20 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4) 50.2s 0.6s\n", - " 0.188000 : 20 passes : Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)_inferred 50.2s 8.5s\n", - " 0.103400 : 20 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4) 19.7s 0.7s\n", - " 0.111600 : 20 passes : Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)_inferred 19.7s 4.1s\n", - "*0.152680 : 20 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4) 30.5s 0.6s\n" + "Training Doc2Vec(dbow,d100,n5,mc2,t4)\n", + "CPU times: user 18min 41s, sys: 59.7 s, total: 19min 41s\n", + "Wall time: 6min 49s\n", + "\n", + "Evaluating Doc2Vec(dbow,d100,n5,mc2,t4)\n", + "CPU times: user 1.85 s, sys: 226 ms, total: 2.07 s\n", + "Wall time: 673 ms\n", + "\n", + "0.102600 Doc2Vec(dbow,d100,n5,mc2,t4)\n", + "\n", + "Training Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "CPU times: user 28min 21s, sys: 1min 30s, total: 29min 52s\n", + "Wall time: 9min 22s\n", + "\n", + "Evaluating Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "CPU times: user 1.71 s, sys: 175 ms, total: 1.88 s\n", + "Wall time: 605 ms\n", + "\n", + "0.154280 Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "\n", + "Training Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "CPU times: user 55min 8s, sys: 36.5 s, total: 55min 44s\n", + "Wall time: 14min 43s\n", + "\n", + "Evaluating Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "CPU times: user 1.47 s, sys: 110 ms, total: 1.58 s\n", + "Wall time: 533 ms\n", + "\n", + "0.225760 Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "\n" ] - }, + } + ], + "source": [ + "for model in simple_models: \n", + " print(\"Training %s\" % model)\n", + " %time model.train(doc_list, total_examples=len(doc_list), epochs=model.epochs)\n", + " \n", + " print(\"\\nEvaluating %s\" % model)\n", + " %time err_rate, err_count, test_count, predictor = error_rate_for_model(model, train_docs, test_docs)\n", + " error_rates[str(model)] = err_rate\n", + " print(\"\\n%f %s\\n\" % (err_rate, model))" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - " 0.182800 : 20 passes : Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)_inferred 30.5s 4.7s\n", - " 0.102600 : 20 passes : dbow+dmm 0.0s 1.6s\n", - " 0.112800 : 20 passes : dbow+dmm_inferred 0.0s 8.8s\n", - "*0.102440 : 20 passes : dbow+dmc 0.0s 2.1s\n", - " 0.103600 : 20 passes : dbow+dmc_inferred 0.0s 12.4s\n", - "Completed pass 20 at alpha 0.002200\n", - "END 2017-07-08 18:39:42.878219\n" + "\n", + "Evaluating Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "CPU times: user 4.13 s, sys: 459 ms, total: 4.59 s\n", + "Wall time: 1.72 s\n", + "\n", + "0.103360 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "\n", + "\n", + "Evaluating Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "CPU times: user 4.03 s, sys: 351 ms, total: 4.38 s\n", + "Wall time: 1.38 s\n", + "\n", + "0.105080 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "\n" ] } ], "source": [ - "from random import shuffle\n", - "import datetime\n", - "\n", - "alpha, min_alpha, passes = (0.025, 0.001, 20)\n", - "alpha_delta = (alpha - min_alpha) / passes\n", - "\n", - "print(\"START %s\" % datetime.datetime.now())\n", - "\n", - "for epoch in range(passes):\n", - " shuffle(doc_list) # Shuffling gets best results\n", - " \n", - " for name, train_model in models_by_name.items():\n", - " # Train\n", - " duration = 'na'\n", - " train_model.alpha, train_model.min_alpha = alpha, alpha\n", - " with elapsed_timer() as elapsed:\n", - " train_model.train(doc_list, total_examples=len(doc_list), epochs=1)\n", - " duration = '%.1f' % elapsed()\n", - " \n", - " # Evaluate\n", - " eval_duration = ''\n", - " with elapsed_timer() as eval_elapsed:\n", - " err, err_count, test_count, predictor = error_rate_for_model(train_model, train_docs, test_docs)\n", - " eval_duration = '%.1f' % eval_elapsed()\n", - " best_indicator = ' '\n", - " if err <= best_error[name]:\n", - " best_error[name] = err\n", - " best_indicator = '*' \n", - " print(\"%s%f : %i passes : %s %ss %ss\" % (best_indicator, err, epoch + 1, name, duration, eval_duration))\n", - "\n", - " if ((epoch + 1) % 5) == 0 or epoch == 0:\n", - " eval_duration = ''\n", - " with elapsed_timer() as eval_elapsed:\n", - " infer_err, err_count, test_count, predictor = error_rate_for_model(train_model, train_docs, test_docs, infer=True)\n", - " eval_duration = '%.1f' % eval_elapsed()\n", - " best_indicator = ' '\n", - " if infer_err < best_error[name + '_inferred']:\n", - " best_error[name + '_inferred'] = infer_err\n", - " best_indicator = '*'\n", - " print(\"%s%f : %i passes : %s %ss %ss\" % (best_indicator, infer_err, epoch + 1, name + '_inferred', duration, eval_duration))\n", - "\n", - " print('Completed pass %i at alpha %f' % (epoch + 1, alpha))\n", - " alpha -= alpha_delta\n", - " \n", - "print(\"END %s\" % str(datetime.datetime.now()))" + "for model in [models_by_name['dbow+dmm'], models_by_name['dbow+dmc']]: \n", + " print(\"\\nEvaluating %s\" % model)\n", + " %time err_rate, err_count, test_count, predictor = error_rate_for_model(model, train_docs, test_docs)\n", + " error_rates[str(model)] = err_rate\n", + " print(\"\\n%f %s\\n\" % (err_rate, model))" ] }, { @@ -629,31 +514,26 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Err rate Model\n", - "0.098400 dbow+dmc_inferred\n", - "0.101600 Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)_inferred\n", - "0.102320 dbow+dmm\n", - "0.102440 dbow+dmc\n", - "0.103080 Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)\n", - "0.108400 dbow+dmm_inferred\n", - "0.152680 Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)\n", - "0.176080 Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)\n", - "0.182800 Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)_inferred\n", - "0.186000 Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)_inferred\n" + "Err_rate Model\n", + "0.102600 Doc2Vec(dbow,d100,n5,mc2,t4)\n", + "0.103360 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "0.105080 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "0.154280 Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "0.225760 Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n" ] } ], "source": [ - "# Print best error rates achieved\n", - "print(\"Err rate Model\")\n", - "for rate, name in sorted((rate, name) for name, rate in best_error.items()):\n", + "# Compare error rates achieved, best-to-worst\n", + "print(\"Err_rate Model\")\n", + "for rate, name in sorted((rate, name) for name, rate in error_rates.items()):\n", " print(\"%f %s\" % (rate, name))" ] }, @@ -661,7 +541,11 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "In our testing, contrary to the results of the paper, PV-DBOW performs best. Concatenating vectors from different models only offers a small predictive improvement over averaging vectors. There best results reproduced are just under 10% error rate, still a long way from the paper's reported 7.42% error rate." + "In our testing, contrary to the results of the paper, on this problem, PV-DBOW alone performs as good as anything else. Concatenating vectors from different models only sometimes offers a tiny predictive improvement – and stays generally close to the best-performing solo model included. \n", + "\n", + "The best results achieved here are just around 10% error rate, still a long way from the paper's reported 7.42% error rate. \n", + "\n", + "(Other trials not shown, with larger vectors and other changes, also don't come close to the paper's reported value. Others around the net have reported a similar inability to reproduce the paper's best numbers. The PV-DM/C mode improves a bit with many more training epochs – but doesn't reach parity with PV-DBOW.)" ] }, { @@ -680,20 +564,34 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "for doc 73872...\n", - "Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4):\n", - " [(73872, 0.7427197694778442), (43744, 0.42404329776763916), (75113, 0.41938722133636475)]\n", - "Doc2Vec(dbow,d100,n5,mc2,s0.001,t4):\n", - " [(73872, 0.9305995106697083), (64147, 0.6267511248588562), (80042, 0.6207213401794434)]\n", - "Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4):\n", - " [(73872, 0.7893393039703369), (67773, 0.7167356014251709), (32802, 0.6937947273254395)]\n" + "for doc 66229...\n", + "Doc2Vec(dbow,d100,n5,mc2,t4):\n", + " [(66229, 0.9756568670272827), (66223, 0.5901858806610107), (81851, 0.5678753852844238)]\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/neuscratch/Dev/gensim/gensim/matutils.py:737: FutureWarning: Conversion of the second argument of issubdtype from `int` to `np.signedinteger` is deprecated. In future, it will be treated as `np.int64 == np.dtype(int).type`.\n", + " if np.issubdtype(vec.dtype, np.int):\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4):\n", + " [(66229, 0.9355567097663879), (71883, 0.49743932485580444), (74232, 0.49549904465675354)]\n", + "Doc2Vec(dm/c,d100,n5,w5,mc2,t4):\n", + " [(66229, 0.9248996376991272), (97306, 0.4372865557670593), (99824, 0.40370166301727295)]\n" ] } ], @@ -709,7 +607,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "(Yes, here the stored vector from 20 epochs of training is usually one of the closest to a freshly-inferred vector for the same words. Note the defaults for inference are very abbreviated – just 3 steps starting at a high alpha – and likely need tuning for other applications.)" + "(Yes, here the stored vector from 20 epochs of training is usually one of the closest to a freshly-inferred vector for the same words. Defaults for inference may benefit from tuning for each dataset or model parameters.)" ] }, { @@ -721,22 +619,32 @@ }, { "cell_type": "code", - "execution_count": 11, - "metadata": {}, + "execution_count": 18, + "metadata": { + "scrolled": false + }, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/neuscratch/Dev/gensim/gensim/matutils.py:737: FutureWarning: Conversion of the second argument of issubdtype from `int` to `np.signedinteger` is deprecated. In future, it will be treated as `np.int64 == np.dtype(int).type`.\n", + " if np.issubdtype(vec.dtype, np.int):\n" + ] + }, { "name": "stdout", "output_type": "stream", "text": [ - "TARGET (71919): «tweety is perched in his cage on the ledge and sylvester is across the street at the \" bird watching society \" building on about the same level . both are looking through binoculars , and they spot each other . tweety then utters his famous phrase , \" i taught i taw a puddy cat . \" ( thought i saw a pussy cat . ) sylvester scampers over to grab the bird . tweety flies out of his cage and granny comes to the rescue , bashing the cat and driving it away . the rest of the animated short shows a series of attempts by sylvester to grab tweetie - a familiar theme - and how either bad luck or granny thwarts him every time . the cat dons disguises and tries a number of clever schemes . . . all of which are funny and very entertaining . in all , a good cartoon and fun to watch .»\n", + "TARGET (34105): «even a decade after \" frontline \" aired on the abc , near as i can tell , \" current affairs \" programmes are still using the same tricks over and over . time after time , \" today tonight \" and \" a current affair \" are seen to be hiding behind the facade of journalistic professionalism , and yet they feed us nothing but tired stories about weight-loss and dodgy tradesmen , shameless network promotions and pointless celebrity puff-pieces . having often been subjected to that entertainment-less void between 'the simpsons' at 6 : 00 pm and 'sale of the century' ( or 'temptation' ) at 7 : 00 pm , i was all too aware of the little tricks that these shows would use to attract ratings . fortunately , four rising comedians – rob sitch , jane kennedy , santo cilauro and tom gleisner – were also all too aware of all this , and they crafted their frustrations into one of the most wickedly-hilarious media satires you'll ever see on television . the four entertainers had already met with comedic success , their previous most memorable television stint being on 'the late show , ' the brilliant saturday night variety show which ran for two seasons from 1992-1993 , and also featured fellow comedians mick molloy , tony martin , jason stephens and judith lucy . \" frontline \" boasts an ensemble of colourful characters , each with their own distinct and quirky personality . the current-affairs show is headed by nicely-groomed mike moore ( rob sitch ) , an ambitious , pretentious , dim-witted narcissist . mike works under the delusion that the show is serving a vital role for society – he is always adamant that they \" maintain their journalistic integrity \" – and his executive producers have excelled into getting him to believe just that . mike is basically a puppet to bring the news to the people ; occasionally he gets the inkling that he is being led along by the nose , but usually this thought is stamped out via appeals to his vanity or promises of a promotion . brooke vandenberg ( jane kennedy ) is the senior female reporter on the show . she is constantly concerned about her looks and public profile , and , if the rumours are to be believed , she has had a romantic liaison with just about every male celebrity in existence . another equally amoral reporter , marty di stasio , is portrayed by tiriel mora , who memorably played inept solicitor dennis denuto in the australian comedy classic , 'the castle . ' emma ward ( alison whyte ) is the line producer on the show , and the single shining beacon of morality on the \" frontline \" set . then there's the highly-amusing weatherman , geoffrey salter ( santo cilauro ) , mike's best friend and confidant . geoff makes a living out of always agreeing with mike's opinion , and of laughing uproariously at his jokes before admitting that he doesn't get them . for each of the shows three seasons , we are treated to a different ep , executive producer . brian thompson ( bruno lawrence ) , who unfortunately passed away in 1995 , runs the programme during season 1 . he has a decent set of morals , and is always civil to his employees , and yet is more-than-willing to cast these aside in favour of high ratings . sam murphy ( kevin j . wilson ) arrives on set in season 2 , a hard-nosed , smooth-talking producer who knows exactly how to string mike along ; the last episode of the second season , when mike finally gets the better of him , is a classic moment . graeme \" prowsey \" prowse ( steve bisley ) , ep for the third season , is crude , unpleasant and unashamedly sexist . it's , therefore , remarkable that you eventually come to like him . with its cast of distinctive , exaggerated characters , \" frontline \" has a lot of fun satirising current-affairs programmes and their dubious methods for winning ratings . many of the episodes were shot quickly and cheaply , often implementing many plot ideas from recent real-life situations , but this never really detracts from the show's topicality ten years on . celebrity cameos come in abundance , with some of the most memorable appearances including pauline hanson , don burke and jon english . watch out for harry shearer's hilarious appearance in the season 2 episode \" changing the face of current affairs , \" playing larry hadges , an american hired by the network to reform the show . particularly in the third season , i noticed that \" frontline \" boasted an extremely gritty form of black humour , uncharacteristic for such a light-hearted comedy show . genuinely funny moments are born from brooke being surreptitiously bribed into having an abortion , murder by a crazed gunman and mike treacherously betraying his best friend's hopes and dreams , only to be told that he is a good friend . the series' final minute – minus an added-scene during the credits , which was probably added just in case a fourth season was to be produced – was probably the greatest , blackest ending to a comedy series that i've yet seen . below is listed a very tentative list of my top five favourite \" frontline \" episodes , but , make no mistake , every single half-hour is absolutely hilarious and hard-hitting satire . 1 ) \" the siege \" ( season 1 ) 2 ) \" give 'em enough rope \" ( season 2 ) 3 ) \" addicted to fame \" ( season 3 ) 4 ) \" basic instincts \" ( season 2 ) 5 ) \" add sex and stir \" ( season 1 )»\n", "\n", - "SIMILAR/DISSIMILAR DOCS PER MODEL Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4):\n", + "SIMILAR/DISSIMILAR DOCS PER MODEL Doc2Vec(dbow,d100,n5,mc2,t4):\n", "\n", - "MOST (30440, 0.752430260181427): «in tweety's s . o . s , sylvester goes from picking garbage cans to being a stowaway on a cruise ship that happens to carry a certain canary bird-and granny , his owner . uh-oh ! once again , tweety and granny provide many obstacles to the cat's attempts to get the bird . sylvester also gets seasick quite a few times , too . and the second time the red-nosed feline goes to the place on the ship that has something that cures his ailments , tweety replaces it with nitroglycerin . so now sylvester can blow fire ! i'll stop here and say this is another excellent cartoon directed by friz freling starring the popular cat-and-bird duo . tweety's s . o . s is most highly recommended .»\n", + "MOST (34106, 0.6284705996513367): «the sad thing about frontline is that once you watch three or four episodes of it you really begin to understand that it is not far away from what happens in real life . what is really sad is that it also makes extremely funny . the frontline team in series one consists of brian thompson ( bruno lawrence ) - a man who truly lives and dies merely by the ratings his show gets . occasionally his stunts to achieve these ratings see him run in with his line producer emma thompson ( alison whyte ) ; a woman who hasn't lost all her journalistic integrity and is prepared to defend moral scruples on occasions . the same cannot be said of reporter brooke vandenberg ( jane kennedy ) - a reporter who has had all the substance sucked out of her- so much so that when interviewing ben elton she needs to be instructed to laugh . her reports usually consist of interviewing celebrities ( with whom she has or hasn't 'crossed paths' with before ) or scandalous unethical reports that usually backfire . martin de stasio ( tiriel mora ) is the reporter with whom the team relies on for gravitas and dignity , as he has the smarts of 21 years of journalism behind him . his doesn't have principles so much as a nous of what makes a good journalistic story , though he does draw the occasional line . parading over this chaos ( in name ) is mike moore ( rob sitch ) an egotistical , naive reporter who can't see that he's only a pretty face for the grubby journalism . he often finds his morals being compromised simply because brian appeals to his vanity and allows his stupidity to do the rest . frontline is the sort of show that there needs to be more of , because it shows that while in modern times happiness , safety and deep political insight are interesting things ; it's much easier to rate with scandal , fear and tabloid celebrities .»\n", "\n", - "MEDIAN (32141, 0.3800385594367981): «my entire family enjoyed this film , including 2 small children . great values without sex , violence , drugs , nudity , or profanity . also no zillion dollar special effects were added to try to misdirect viewers from a poorly written storyline . a simple little family fun movie . we especially like the songs in the movie . but we only got to hear a portion of the songs . . . mostly during the end credits . . . would love to buy a sound track cd from this movie . this is my 4th bill hillman movie and they all have the same guidelines as mentioned above . with all the movies out there that you don't want your kids to watch , this hillman fella has a no risk rating . we love his movies .»\n", + "MEDIAN (35245, 0.2309201955795288): «\" hell to pay \" bills itself as the rebirth of the classic western . . . it succeeds as a western genre movie that the entire family could see and not unlike the films baby-boomers experienced decades ago . the good guys are good and the bad guys are really bad ! . bo svenson , stella stevens , lee majors , andrew prine ( excellent in this film ) tim thomerson and james drury are all great and it's fun to see them again . james drury really shines in this one , maybe even better than his days as \" the virginian . \" in a way , \" hell to pay \" reminds me of those movies in the 60's where actors you know from so many shows make an appearance . if you're of a certain age , buck taylor , peter brown and denny miller and william smith provide a \" wow \" factor because we seldom get to see these icons these days . \" hell to pay \" features screen legends along with newer names in hollywood . most notable in the cast of \" newbies \" is rachel kimsey ( rebekah ) , who i've seen lately on \" the young and the restless \" and kevin kazakoff , who plays the angst-ridden kirby , a war-weary man who's torn between wanting to live and let live or stepping in to \" do the right thing . \" william gregory lee is excellent as chance , kirby's mischievous and womanizing brother . katie keane plays rachel , rebekah's sister , a woman who did what was necessary to stay alive but giving up her pride in the process . in a small but memorable role , jeff davis plays mean joe , a former confederate with a rather nasty mean streak . i think we'll be seeing more of these fine actors in the future . \" hell to pay \" is a fun movie with a great story to tell grab the popcorn , we're headin' west ! .»\n", "\n", - "LEAST (57712, -0.051298510283231735): «in a recent biography of burt lancaster , go tell the spartans is described as the best vietnam war film that nobody ever saw . hopefully with television and video products that will be corrected . i prefer to think of it as a prequel to platoon . this film is set in 1964 when america's participation was limited to advisers by this time raised to about 20 , 000 of them by president kennedy . whether if kennedy had lived and won a second term he would have increased our commitment to a half a million men as lyndon johnson did is open to much historical speculation . major burt lancaster heads such an advisory team with his number two captain marc singer . they get some replacements and a new assignment to build a fortress where the french tried years ago and failed . the replacements are a really mixed bag , a sergeant who lancaster has served with before and respects highly in jonathan goldsmith , a very green and eager second lieutenant in joe unger , a demolitions man who is a draftee and at that time vietnam service was a strictly volunteer thing in craig wasson , and a medic who is also a junkie in dennis howard . for one reason or another all of these get sent forward to build that outpost in a place that suddenly has acquired military significance . i said before this could be a prequel to platoon . platoon is set in the time a few years later when the usa was fully militarily committed in vietnam . platoon raises the same issues about the futility of that war , but i think go tell the spartans does a much better job . hard to bring your best effort into the fight since who and what you're fighting and fighting for seems to change weekly . originally this project was for william holden and i'm surprised holden passed on it . maybe for the better because lancaster strikes just the right note as the professional soldier in what was a backwater assignment who politics has passed over for promotion . knowing all that you will understand why lancaster makes the final decision he does . two others of note are evan kim who is the head of the south vietnamese regulars and interpreter who lancaster and company are training . he epitomizes the brutality of the struggle for us in a way that we can't appreciate from the other side because we never meet any of the viet cong by name . dolph sweet plays the general in charge of the american vietnam commitment , a general harnitz . he is closest to a real character because the general in charge their before johnson raised the troop levels and put in william westmoreland was paul harkins . joe unger is who i think gives the best performance as the shavetail lieutenant with all the conventional ideas of war and believes we have got to be with the good guys since we are americans . he learns fast that you issue uniforms for a reason and wars against people who don't have them are the most difficult . i think one could get a deep understanding of just what america faced in 1964 in vietnam by watching go tell the spartans .»\n", + "LEAST (261, -0.09666291624307632): «an unusual film from ringo lam and one that's strangely under-appreciated . the mix of fantasy kung-fu with a more realistic depiction of swords and spears being driven thru bodies is startling especially during the first ten minutes . a horseback rider get chopped in two and his waist and legs keep riding the horse . several horses get chopped up . it's very unexpected . the story is very simple , fong and his shaolin brothers are captured by a crazed maniac general and imprisoned in the red lotus temple which seems to be more of a torture chamber then a temple . the general has a similarity to kurtz in apocalypse now as he spouts warped philosophy and makes frightening paintings with human blood . the production is very impressive and the setting is bleak . blood is everywhere . the action is very well done and mostly coherent unlike many hk action scenes from the time . sometimes the movie veers into absurdity or the effects are cheesy but it's never bad enough to ruin the film . find this one , it's one of the best hk kung fu films from the early nineties . just remember it's not child friendly .»\n", "\n" ] } @@ -757,7 +665,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "(Somewhat, in terms of reviewer tone, movie genre, etc... the MOST cosine-similar docs usually seem more like the TARGET than the MEDIAN or LEAST.)" + "Somewhat, in terms of reviewer tone, movie genre, etc... the MOST cosine-similar docs usually seem more like the TARGET than the MEDIAN or LEAST... especially if the MOST has a cosine-similarity > 0.5. Re-run the cell to try another random target document." ] }, { @@ -769,10 +677,8 @@ }, { "cell_type": "code", - "execution_count": 12, - "metadata": { - "collapsed": true - }, + "execution_count": 13, + "metadata": {}, "outputs": [], "source": [ "word_models = simple_models[:]" @@ -780,83 +686,91 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "most similar words for 'thrilled' (276 occurences)\n" + "most similar words for 'spoilt' (97 occurences)\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/neuscratch/Dev/gensim/gensim/matutils.py:737: FutureWarning: Conversion of the second argument of issubdtype from `int` to `np.signedinteger` is deprecated. In future, it will be treated as `np.int64 == np.dtype(int).type`.\n", + " if np.issubdtype(vec.dtype, np.int):\n" ] }, { "data": { "text/html": [ - "
Doc2Vec(dm/c,d100,n5,w5,mc2,s0.001,t4)Doc2Vec(dbow,d100,n5,mc2,s0.001,t4)Doc2Vec(dm/m,d100,n5,w10,mc2,s0.001,t4)
[('pleased', 0.8135600090026855),
\n", - "('excited', 0.7601636648178101),
\n", - "('surprised', 0.7497514486312866),
\n", - "('delighted', 0.740871012210846),
\n", - "('impressed', 0.7300887107849121),
\n", - "('disappointed', 0.715817391872406),
\n", - "('shocked', 0.7109759449958801),
\n", - "('intrigued', 0.7000594139099121),
\n", - "('amazed', 0.6994709968566895),
\n", - "('fascinated', 0.6952326893806458),
\n", - "('saddened', 0.68060702085495),
\n", - "('satisfied', 0.674963116645813),
\n", - "('apprehensive', 0.6572576761245728),
\n", - "('entertained', 0.654381275177002),
\n", - "('disgusted', 0.6502282023429871),
\n", - "('overjoyed', 0.6485082507133484),
\n", - "('stunned', 0.6478738784790039),
\n", - "('entranced', 0.6438385844230652),
\n", - "('amused', 0.6437265872955322),
\n", - "('dissappointed', 0.6427538394927979)]		[(\"ifans'\", 0.44280144572257996),
\n", - "('shay', 0.4335209131240845),
\n", - "('crappers', 0.4007232189178467),
\n", - "('overflow', 0.40028804540634155),
\n", - "('yum', 0.3929170072078705),
\n", - "(\"monkey'\", 0.38661277294158936),
\n", - "('kholi', 0.38401469588279724),
\n", - "('fun-bloodbath', 0.38145124912261963),
\n", - "('breathed', 0.373812735080719),
\n", - "(\"eszterhas'\", 0.3729144334793091),
\n", - "('nob', 0.3723628520965576),
\n", - "(\"meatloaf's\", 0.3720172643661499),
\n", - "('ruegger', 0.3683895468711853),
\n", - "(\"haynes'\", 0.36665791273117065),
\n", - "('feigning', 0.36445197463035583),
\n", - "('torches', 0.35865518450737),
\n", - "('sirens', 0.3581739068031311),
\n", - "('insides', 0.35690629482269287),
\n", - "('swackhamer', 0.35603001713752747),
\n", - "('trolls', 0.3526684641838074)]		[('pleased', 0.7576382160186768),
\n", - "('excited', 0.7351139187812805),
\n", - "('delighted', 0.7220871448516846),
\n", - "('intrigued', 0.6748061180114746),
\n", - "('surprised', 0.6552557945251465),
\n", - "('shocked', 0.6505781412124634),
\n", - "('disappointed', 0.6428648233413696),
\n", - "('impressed', 0.6426182389259338),
\n", - "('overjoyed', 0.6259098052978516),
\n", - "('saddened', 0.6148285865783691),
\n", - "('anxious', 0.6140503883361816),
\n", - "('fascinated', 0.6126223802566528),
\n", - "('skeptical', 0.6025052070617676),
\n", - "('suprised', 0.5986943244934082),
\n", - "('upset', 0.596437931060791),
\n", - "('relieved', 0.593376874923706),
\n", - "('psyched', 0.5923721790313721),
\n", - "('captivated', 0.5753644704818726),
\n", - "('astonished', 0.574415922164917),
\n", - "('horrified', 0.5716636180877686)]
" + "
Doc2Vec(dbow,d100,n5,mc2,t4)Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)Doc2Vec(dm/c,d100,n5,w5,mc2,t4)
[(\"wives'\", 0.4262964725494385),
\n", + "('horrificaly', 0.4177134335041046),
\n", + "(\"snit'\", 0.4037289619445801),
\n", + "('improf', 0.40169233083724976),
\n", + "('humiliatingly', 0.3946930170059204),
\n", + "('heart-pounding', 0.3938479423522949),
\n", + "(\"'jo'\", 0.38460421562194824),
\n", + "('kieron', 0.37991276383399963),
\n", + "('linguistic', 0.3727714419364929),
\n", + "('rothery', 0.3719364404678345),
\n", + "('zellwegger', 0.370682954788208),
\n", + "('never-released', 0.36564797163009644),
\n", + "('coffeeshop', 0.36534833908081055),
\n", + "('slater--these', 0.3643302917480469),
\n", + "('over-plotted', 0.36348140239715576),
\n", + "('synchronism', 0.36320072412490845),
\n", + "('exploitations', 0.3631579875946045),
\n", + "(\"donor's\", 0.36226314306259155),
\n", + "('neend', 0.3619685769081116),
\n", + "('renaud', 0.3611547350883484)]		[('spoiled', 0.6693772077560425),
\n", + "('ruined', 0.5701743960380554),
\n", + "('dominated', 0.554553747177124),
\n", + "('marred', 0.5456377267837524),
\n", + "('undermined', 0.5353708267211914),
\n", + "('unencumbered', 0.5345744490623474),
\n", + "('dwarfed', 0.5331343412399292),
\n", + "('followed', 0.5186703205108643),
\n", + "('entranced', 0.513541042804718),
\n", + "('emboldened', 0.5100494623184204),
\n", + "('shunned', 0.5044804215431213),
\n", + "('disgusted', 0.5000460743904114),
\n", + "('overestimated', 0.49955034255981445),
\n", + "('bolstered', 0.4971669018268585),
\n", + "('replaced', 0.4966174364089966),
\n", + "('bookended', 0.49495506286621094),
\n", + "('blowout', 0.49287083745002747),
\n", + "('overshadowed', 0.48964253067970276),
\n", + "('played', 0.48709338903427124),
\n", + "('accompanied', 0.47834640741348267)]		[('spoiled', 0.6672338247299194),
\n", + "('troubled', 0.520033597946167),
\n", + "('bankrupted', 0.509053647518158),
\n", + "('ruined', 0.4965386986732483),
\n", + "('misguided', 0.4900725483894348),
\n", + "('devoured', 0.48988765478134155),
\n", + "('ravaged', 0.4861036539077759),
\n", + "('frustrated', 0.4841104745864868),
\n", + "('suffocated', 0.4828023314476013),
\n", + "('investigated', 0.47958582639694214),
\n", + "('tormented', 0.4791877865791321),
\n", + "('traumatized', 0.4785040616989136),
\n", + "('shaken', 0.4784379005432129),
\n", + "('persecuted', 0.4774147868156433),
\n", + "('crippled', 0.4771782457828522),
\n", + "('torpedoed', 0.4764551818370819),
\n", + "('plagued', 0.47006863355636597),
\n", + "('drowned', 0.4688340723514557),
\n", + "('prompted', 0.4678872525691986),
\n", + "('abandoned', 0.4652657210826874)]
" ], "text/plain": [ "" ] }, - "execution_count": 13, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } @@ -871,7 +785,7 @@ " break\n", "# or uncomment below line, to just pick a word from the relevant domain:\n", "#word = 'comedy/drama'\n", - "similars_per_model = [str(model.most_similar(word, topn=20)).replace('), ','),
\\n') for model in word_models]\n", + "similars_per_model = [str(model.wv.most_similar(word, topn=20)).replace('), ','),
\\n') for model in word_models]\n", "similar_table = (\"
\" +\n", " \"\".join([str(model) for model in word_models]) + \n", " \"
\" +\n", @@ -885,9 +799,9 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Do the DBOW words look meaningless? That's because the gensim DBOW model doesn't train word vectors – they remain at their random initialized values – unless you ask with the `dbow_words=1` initialization parameter. Concurrent word-training slows DBOW mode significantly, and offers little improvement (and sometimes a little worsening) of the error rate on this IMDB sentiment-prediction task. \n", + "Do the DBOW words look meaningless? That's because the gensim DBOW model doesn't train word vectors – they remain at their random initialized values – unless you ask with the `dbow_words=1` initialization parameter. Concurrent word-training slows DBOW mode significantly, and offers little improvement (and sometimes a little worsening) of the error rate on this IMDB sentiment-prediction task, but may be appropriate on other tasks, or if you also need word-vectors. \n", "\n", - "Words from DM models tend to show meaningfully similar words when there are many examples in the training data (as with 'plot' or 'actor'). (All DM modes inherently involve word vector training concurrent with doc vector training.)" + "Words from DM models tend to show meaningfully similar words when there are many examples in the training data (as with 'plot' or 'actor'). (All DM modes inherently involve word-vector training concurrent with doc-vector training.)" ] }, { @@ -899,27 +813,67 @@ }, { "cell_type": "code", - "execution_count": 14, - "metadata": { - "collapsed": true - }, - "outputs": [], + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Success, questions-words.txt is available for next steps.\n" + ] + } + ], + "source": [ + "# grab the file if not already local\n", + "questions_filename = 'questions-words.txt'\n", + "if not os.path.isfile(questions_filename):\n", + " # Download IMDB archive\n", + " print(\"Downloading analogy questions file...\")\n", + " url = u'https://raw.githubusercontent.com/tmikolov/word2vec/master/questions-words.txt'\n", + " r = requests.get(url)\n", + " with smart_open(questions_filename, 'wb') as f:\n", + " f.write(r.content)\n", + "assert os.path.isfile(questions_filename), \"questions-words.txt unavailable\"\n", + "print(\"Success, questions-words.txt is available for next steps.\")" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/neuscratch/Dev/gensim/gensim/matutils.py:737: FutureWarning: Conversion of the second argument of issubdtype from `int` to `np.signedinteger` is deprecated. In future, it will be treated as `np.int64 == np.dtype(int).type`.\n", + " if np.issubdtype(vec.dtype, np.int):\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Doc2Vec(dbow,d100,n5,mc2,t4): 0.00% correct (0 of 14657)\n", + "Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4): 17.37% correct (2546 of 14657)\n", + "Doc2Vec(dm/c,d100,n5,w5,mc2,t4): 19.20% correct (2814 of 14657)\n" + ] + } + ], "source": [ - "# Download this file: https://github.com/nicholas-leonard/word2vec/blob/master/questions-words.txt\n", - "# and place it in the local directory\n", - "# Note: this takes many minutes\n", - "if os.path.isfile('questions-words.txt'):\n", - " for model in word_models:\n", - " sections = model.accuracy('questions-words.txt')\n", - " correct, incorrect = len(sections[-1]['correct']), len(sections[-1]['incorrect'])\n", - " print('%s: %0.2f%% correct (%d of %d)' % (model, float(correct*100)/(correct+incorrect), correct, correct+incorrect))" + "# Note: this analysis takes many minutes\n", + "for model in word_models:\n", + " score, sections = model.wv.evaluate_word_analogies('questions-words.txt')\n", + " correct, incorrect = len(sections[-1]['correct']), len(sections[-1]['incorrect'])\n", + " print('%s: %0.2f%% correct (%d of %d)' % (model, float(correct*100)/(correct+incorrect), correct, correct+incorrect))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "Even though this is a tiny, domain-specific dataset, it shows some meager capability on the general word analogies – at least for the DM/concat and DM/mean models which actually train word vectors. (The untrained random-initialized words of the DBOW model of course fail miserably.)" + "Even though this is a tiny, domain-specific dataset, it shows some meager capability on the general word analogies – at least for the DM/mean and DM/concat models which actually train word vectors. (The untrained random-initialized words of the DBOW model of course fail miserably.)" ] }, { @@ -931,7 +885,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -942,36 +896,119 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "To mix the Google dataset (if locally available) into the word tests..." + "### Advanced technique: re-inferring doc-vectors" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Because the bulk-trained vectors had much of their training early, when the model itself was still settling, it is *sometimes* the case that rather than using the bulk-trained vectors, new vectors re-inferred from the final state of the model serve better as the input/test data for downstream tasks. \n", + "\n", + "Our `error_rate_for_model()` function already had a non-default option to re-infer vectors before training/testing the classifier, so here we test that option. (This takes as long or longer than initial bulk training, as inference is only single-threaded.)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Evaluating Doc2Vec(dbow,d100,n5,mc2,t4) re-inferred\n", + "CPU times: user 7min 9s, sys: 1.55 s, total: 7min 11s\n", + "Wall time: 7min 10s\n", + "\n", + "0.102240 Doc2Vec(dbow,d100,n5,mc2,t4)_reinferred\n", + "\n", + "Evaluating Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4) re-inferred\n", + "CPU times: user 9min 48s, sys: 1.53 s, total: 9min 49s\n", + "Wall time: 9min 48s\n", + "\n", + "0.146200 Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)_reinferred\n", + "\n", + "Evaluating Doc2Vec(dm/c,d100,n5,w5,mc2,t4) re-inferred\n", + "CPU times: user 16min 13s, sys: 1.32 s, total: 16min 14s\n", + "Wall time: 16min 13s\n", + "\n", + "0.218120 Doc2Vec(dm/c,d100,n5,w5,mc2,t4)_reinferred\n", + "\n", + "Evaluating Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4) re-inferred\n", + "CPU times: user 15min 50s, sys: 1.63 s, total: 15min 52s\n", + "Wall time: 15min 49s\n", + "\n", + "0.102120 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)_reinferred\n", + "\n", + "Evaluating Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4) re-inferred\n", + "CPU times: user 22min 53s, sys: 1.81 s, total: 22min 55s\n", + "Wall time: 22min 52s\n", + "\n", + "0.104320 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4)_reinferred\n", + "\n" + ] + } + ], + "source": [ + "for model in simple_models + [models_by_name['dbow+dmm'], models_by_name['dbow+dmc']]: \n", + " print(\"Evaluating %s re-inferred\" % str(model))\n", + " pseudomodel_name = str(model)+\"_reinferred\"\n", + " %time err_rate, err_count, test_count, predictor = error_rate_for_model(model, train_docs, test_docs, reinfer_train=True, reinfer_test=True, infer_subsample=1.0)\n", + " error_rates[pseudomodel_name] = err_rate\n", + " print(\"\\n%f %s\\n\" % (err_rate, pseudomodel_name))" + ] + }, + { + "cell_type": "code", + "execution_count": 25, "metadata": { - "collapsed": true + "scrolled": true }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Err_rate Model\n", + "0.102120 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)_reinferred\n", + "0.102240 Doc2Vec(dbow,d100,n5,mc2,t4)_reinferred\n", + "0.102600 Doc2Vec(dbow,d100,n5,mc2,t4)\n", + "0.103360 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "0.104320 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4)_reinferred\n", + "0.105080 Doc2Vec(dbow,d100,n5,mc2,t4)+Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n", + "0.146200 Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)_reinferred\n", + "0.154280 Doc2Vec(\"alpha=0.05\",dm/m,d100,n5,w10,mc2,t4)\n", + "0.218120 Doc2Vec(dm/c,d100,n5,w5,mc2,t4)_reinferred\n", + "0.225760 Doc2Vec(dm/c,d100,n5,w5,mc2,t4)\n" + ] + } + ], + "source": [ + "# Compare error rates achieved, best-to-worst\n", + "print(\"Err_rate Model\")\n", + "for rate, name in sorted((rate, name) for name, rate in error_rates.items()):\n", + " print(\"%f %s\" % (rate, name))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, "source": [ - "from gensim.models import KeyedVectors\n", - "w2v_g100b = KeyedVectors.load_word2vec_format('GoogleNews-vectors-negative300.bin.gz', binary=True)\n", - "w2v_g100b.compact_name = 'w2v_g100b'\n", - "word_models.append(w2v_g100b)" + "Here, we do *not* see much benefit of re-inference. It's more likely to help if the initial training used fewer epochs (10 is also a common value in the literature for larger datasets), or perhaps in larger datasets. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "To get copious logging output from above steps..." + "### To get copious logging output from above steps..." ] }, { "cell_type": "code", "execution_count": null, - "metadata": { - "collapsed": true - }, + "metadata": {}, "outputs": [], "source": [ "import logging\n", @@ -984,25 +1021,30 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "To auto-reload python code while developing..." + "### To auto-reload python code while developing..." ] }, { "cell_type": "code", "execution_count": null, - "metadata": { - "collapsed": true - }, + "metadata": {}, "outputs": [], "source": [ "%load_ext autoreload\n", "%autoreload 2" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { "kernelspec": { - "display_name": "Python [default]", + "display_name": "Python 3", "language": "python", "name": "python3" }, @@ -1016,7 +1058,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.1" + "version": "3.6.6" } }, "nbformat": 4, diff --git a/docs/notebooks/doc2vec-lee.ipynb b/docs/notebooks/doc2vec-lee.ipynb index 9865096cdc..371f879f15 100644 --- a/docs/notebooks/doc2vec-lee.ipynb +++ b/docs/notebooks/doc2vec-lee.ipynb @@ -190,16 +190,18 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Now, we'll instantiate a Doc2Vec model with a vector size with 50 words and iterating over the training corpus 55 times. We set the minimum word count to 2 in order to give higher frequency words more weighting. Model accuracy can be improved by increasing the number of iterations but this generally increases the training time. Small datasets with short documents, like this one, can benefit from more training passes." + "Now, we'll instantiate a Doc2Vec model with a vector size with 50 words and iterating over the training corpus 40 times. We set the minimum word count to 2 in order to discard words with very few occurrences. (Without a variety of representative examples, retaining such infrequent words can often make a model worse!) Typical iteration counts in published 'Paragraph Vectors' results, using 10s-of-thousands to millions of docs, are 10-20. More iterations take more time and eventually reach a point of diminishing returns.\n", + "\n", + "However, this is a very very small dataset (300 documents) with shortish documents (a few hundred words). Adding training passes can sometimes help with such small datasets." ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ - "model = gensim.models.doc2vec.Doc2Vec(vector_size=50, min_count=2, epochs=55)" + "model = gensim.models.doc2vec.Doc2Vec(vector_size=50, min_count=2, epochs=40)" ] }, { @@ -211,7 +213,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -237,15 +239,15 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "CPU times: user 4.5 s, sys: 247 ms, total: 4.75 s\n", - "Wall time: 2.04 s\n" + "CPU times: user 4.61 s, sys: 814 ms, total: 5.43 s\n", + "Wall time: 2.68 s\n" ] } ], @@ -269,26 +271,26 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "array([ 0.03101196, 0.08118944, 0.10724881, -0.16268663, -0.12030419,\n", - " 0.07530276, -0.05967962, 0.01093007, 0.01722554, -0.16849394,\n", - " -0.09248347, 0.00667514, 0.05426382, -0.0725852 , 0.09535281,\n", - " -0.12534387, 0.08636193, -0.1029434 , -0.07632427, -0.24741814,\n", - " -0.1277334 , -0.09834807, -0.12880586, -0.07720284, -0.12248702,\n", - " -0.15788661, 0.17826575, -0.12920539, 0.02845461, -0.12751418,\n", - " 0.06129557, -0.02319777, 0.11814108, -0.08767211, -0.04094559,\n", - " -0.00681656, 0.00937355, 0.02168806, -0.03686712, 0.14234844,\n", - " -0.01192134, 0.06787674, -0.25467244, -0.22923732, -0.03031967,\n", - " -0.2362234 , 0.1105942 , 0.01180398, 0.01921744, -0.07667527],\n", + "array([ 0.24116205, 0.07339828, -0.27019867, -0.19452883, 0.126193 ,\n", + " 0.22654183, 0.26595142, 0.21971616, -0.03823646, -0.14102826,\n", + " 0.30460876, 0.0068176 , -0.1742173 , 0.05304497, 0.16511315,\n", + " -0.15094836, 0.14354771, 0.01259909, -0.17909774, 0.07656667,\n", + " 0.15878952, -0.18826678, 0.03750297, -0.3339148 , -0.09979844,\n", + " -0.05963492, 0.00099474, -0.18307815, -0.00851006, -0.02054437,\n", + " 0.0683636 , -0.13510053, -0.05586798, -0.07510707, 0.13390398,\n", + " -0.08525871, -0.03863541, 0.03461651, -0.1619014 , 0.12662718,\n", + " 0.23388451, 0.11462782, -0.02873337, 0.16269833, -0.01474206,\n", + " 0.09754166, 0.12638392, -0.09281237, -0.04791372, 0.15747668],\n", " dtype=float32)" ] }, - "execution_count": 12, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -297,6 +299,15 @@ "model.infer_vector(['only', 'you', 'can', 'prevent', 'forest', 'fires'])" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Note that `infer_vector()` does *not* take a string, but rather a list of string tokens, which should have already been tokenized the same way as the `words` property of original training document objects. \n", + "\n", + "Also note that because the underlying training/inference algorithms are an iterative approximation problem that makes use of internal randomization, repeated inferences of the same text will return slightly different vectors." + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -313,9 +324,18 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/neuscratch/Dev/gensim/gensim/matutils.py:737: FutureWarning: Conversion of the second argument of issubdtype from `int` to `np.signedinteger` is deprecated. In future, it will be treated as `np.int64 == np.dtype(int).type`.\n", + " if np.issubdtype(vec.dtype, np.int):\n" + ] + } + ], "source": [ "ranks = []\n", "second_ranks = []\n", @@ -337,7 +357,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 12, "metadata": { "scrolled": true }, @@ -345,16 +365,16 @@ { "data": { "text/plain": [ - "Counter({0: 284, 1: 13, 2: 2, 4: 1})" + "Counter({0: 292, 1: 8})" ] }, - "execution_count": 14, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "collections.Counter(ranks) # Results vary due to random seeding and very small corpus" + "collections.Counter(ranks) # Results vary between runs due to random seeding and very small corpus" ] }, { @@ -368,7 +388,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -379,11 +399,13 @@ "\n", "SIMILAR/DISSIMILAR DOCS PER MODEL Doc2Vec(dm/m,d50,n5,w5,mc2,s0.001,t3):\n", "\n", - "MOST (299, 0.8637137413024902): «australia will take on france in the doubles rubber of the davis cup tennis final today with the tie levelled at wayne arthurs and todd woodbridge are scheduled to lead australia in the doubles against cedric pioline and fabrice santoro however changes can be made to the line up up to an hour before the match and australian team captain john fitzgerald suggested he might do just that we ll make team appraisal of the whole situation go over the pros and cons and make decision french team captain guy forget says he will not make changes but does not know what to expect from australia todd is the best doubles player in the world right now so expect him to play he said would probably use wayne arthurs but don know what to expect really pat rafter salvaged australia davis cup campaign yesterday with win in the second singles match rafter overcame an arm injury to defeat french number one sebastien grosjean in three sets the australian says he is happy with his form it not very pretty tennis there isn too many consistent bounces you are playing like said bit of classic old grass court rafter said rafter levelled the score after lleyton hewitt shock five set loss to nicholas escude in the first singles rubber but rafter says he felt no added pressure after hewitt defeat knew had good team to back me up even if we were down he said knew could win on the last day know the boys can win doubles so even if we were down still feel we are good enough team to win and vice versa they are good enough team to beat us as well»\n", + "MOST (299, 0.93604576587677): «australia will take on france in the doubles rubber of the davis cup tennis final today with the tie levelled at wayne arthurs and todd woodbridge are scheduled to lead australia in the doubles against cedric pioline and fabrice santoro however changes can be made to the line up up to an hour before the match and australian team captain john fitzgerald suggested he might do just that we ll make team appraisal of the whole situation go over the pros and cons and make decision french team captain guy forget says he will not make changes but does not know what to expect from australia todd is the best doubles player in the world right now so expect him to play he said would probably use wayne arthurs but don know what to expect really pat rafter salvaged australia davis cup campaign yesterday with win in the second singles match rafter overcame an arm injury to defeat french number one sebastien grosjean in three sets the australian says he is happy with his form it not very pretty tennis there isn too many consistent bounces you are playing like said bit of classic old grass court rafter said rafter levelled the score after lleyton hewitt shock five set loss to nicholas escude in the first singles rubber but rafter says he felt no added pressure after hewitt defeat knew had good team to back me up even if we were down he said knew could win on the last day know the boys can win doubles so even if we were down still feel we are good enough team to win and vice versa they are good enough team to beat us as well»\n", + "\n", + "SECOND-MOST (112, 0.8006965517997742): «australian cricket captain steve waugh has supported fast bowler brett lee after criticism of his intimidatory bowling to the south african tailenders in the first test in adelaide earlier this month lee was fined for giving new zealand tailender shane bond an unsportsmanlike send off during the third test in perth waugh says tailenders should not be protected from short pitched bowling these days you re earning big money you ve got responsibility to learn how to bat he said mean there no times like years ago when it was not professional and sort of bowlers code these days you re professional our batsmen work very hard at their batting and expect other tailenders to do likewise meanwhile waugh says his side will need to guard against complacency after convincingly winning the first test by runs waugh says despite the dominance of his side in the first test south africa can never be taken lightly it only one test match out of three or six whichever way you want to look at it so there lot of work to go he said but it nice to win the first battle definitely it gives us lot of confidence going into melbourne you know the big crowd there we love playing in front of the boxing day crowd so that will be to our advantage as well south africa begins four day match against new south wales in sydney on thursday in the lead up to the boxing day test veteran fast bowler allan donald will play in the warm up match and is likely to take his place in the team for the second test south african captain shaun pollock expects much better performance from his side in the melbourne test we still believe that we didn play to our full potential so if we can improve on our aspects the output we put out on the field will be lot better and we still believe we have side that is good enough to beat australia on our day he said»\n", "\n", - "MEDIAN (178, 0.2800390124320984): «year old middle eastern woman is said to be responding well to treatment after being diagnosed with typhoid in temporary holding centre on remote christmas island it could be hours before tests can confirm whether the disease has spread further two of the woman three children boy aged and year old girl have been quarantined with their mother in the christmas island hospital third child remains at the island sports hall where locals say conditions are crowded and hot all detainees on christmas island are being monitored by health team for signs of fever or abdominal pains the key symptoms of typhoid which is spread by contact with contaminated food or water hygiene measures have also been stepped up the western australian health department is briefing medical staff on infection control procedures but locals have expressed concern the disease could spread to the wider community»\n", + "MEDIAN (119, 0.26439014077186584): «australia is continuing to negotiate with the united states government in an effort to interview the australian david hicks who was captured fighting alongside taliban forces in afghanistan mr hicks is being held by the united states on board ship in the afghanistan region where the australian federal police and australian security intelligence organisation asio officials are trying to gain access foreign affairs minister alexander downer has also confirmed that the australian government is investigating reports that another australian has been fighting for taliban forces in afghanistan we often get reports of people going to different parts of the world and asking us to investigate them he said we always investigate sometimes it is impossible to find out we just don know in this case but it is not to say that we think there are lot of australians in afghanistan the only case we know is hicks mr downer says it is unclear when mr hicks will be back on australian soil but he is hopeful the americans will facilitate australian authorities interviewing him»\n", "\n", - "LEAST (11, 0.01867116428911686): «peru has entered two days of official mourning for the more than people killed in fire that destroyed part of downtown lima police say the fire began when fireworks cache exploded in shop just four blocks from peru congress in heritage listed area famed for its spanish colonial era architecture early evening crowds buying traditional fireworks for new year eve celebrations were trapped by the flames as they raced through surrounding markets and four storey apartment buildings local residents blame vendors of illegal fireworks and say the death toll was exacerbated by poor traffic control in the adjoining narrow street where cars themselves engulfed by fire trapped fleeing victims hospitals have urged the public to donate medicine for the hundreds of burns victims peru president alejandro toledo has cut short his beach holiday to oversee an inquiry»\n", + "LEAST (243, -0.12885713577270508): «four afghan factions have reached agreement on an interim cabinet during talks in germany the united nations says the administration which will take over from december will be headed by the royalist anti taliban commander hamed karzai it concludes more than week of negotiations outside bonn and is aimed at restoring peace and stability to the war ravaged country the year old former deputy foreign minister who is currently battling the taliban around the southern city of kandahar is an ally of the exiled afghan king mohammed zahir shah he will serve as chairman of an interim authority that will govern afghanistan for six month period before loya jirga or grand traditional assembly of elders in turn appoints an month transitional government meanwhile united states marines are now reported to have been deployed in eastern afghanistan where opposition forces are closing in on al qaeda soldiers reports from the area say there has been gun battle between the opposition and al qaeda close to the tora bora cave complex where osama bin laden is thought to be hiding in the south of the country american marines are taking part in patrols around the air base they have secured near kandahar but are unlikely to take part in any assault on the city however the chairman of the joint chiefs of staff general richard myers says they are prepared for anything they are prepared for engagements they re robust fighting force and they re absolutely ready to engage if that required he said»\n", "\n" ] } @@ -391,7 +413,7 @@ "source": [ "print('Document ({}): «{}»\\n'.format(doc_id, ' '.join(train_corpus[doc_id].words)))\n", "print(u'SIMILAR/DISSIMILAR DOCS PER MODEL %s:\\n' % model)\n", - "for label, index in [('MOST', 0), ('MEDIAN', len(sims)//2), ('LEAST', len(sims) - 1)]:\n", + "for label, index in [('MOST', 0), ('SECOND-MOST', 1), ('MEDIAN', len(sims)//2), ('LEAST', len(sims) - 1)]:\n", " print(u'%s %s: «%s»\\n' % (label, sims[index], ' '.join(train_corpus[sims[index][0]].words)))" ] }, @@ -399,30 +421,32 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Notice above that the most similar document is has a similarity score of ~80% (or higher). However, the similarity score for the second ranked documents should be significantly lower (assuming the documents are in fact different) and the reasoning becomes obvious when we examine the text itself" + "Notice above that the most similar document (usually the same text) is has a similarity score approaching 1.0. However, the similarity score for the second-ranked documents should be significantly lower (assuming the documents are in fact different) and the reasoning becomes obvious when we examine the text itself.\n", + "\n", + "We can run the next cell repeatedly to see a sampling other target-document comparisons. " ] }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Train Document (186): «united nationals secretary general kofi annan has accepted the nobel peace prize in the norwegian capital oslo declaring that to save one life is to save humanity itself mr annan told gala audience the world must respect the individual whose fundamental rights he says have been sacrificed too often for the good of the state the year old un chief native of ghana shares this year th nobel peace prize with the united nations as whole his award was for bringing new life to the world body in his fight for human rights and against aids and terrorism»\n", + "Train Document (289): «there is renewed attempt to move the debate over choosing an australian head of state forward after conference in southern new south wales at the weekend in corowa delegates adopted proposal which recommended plebiscite to direct another constitutional convention and referendum on republic and australian head of state committee will meet in about four weeks to work on the next step in the campaign one of the proposal developers historian walter phillips hopes there is vote on an australian head of state in about five years think that in five or six years we should be pretty near if we can get this process going and carried forward now we have to persuade our political leaders that it is something they should take up that going to be one of the problems mr phillips said»\n", "\n", - "Similar Document (207, 0.6752535104751587): «geoff huegill has continued his record breaking ways at the world cup short course swimming in melbourne bettering the australian record in the metres butterfly huegill beat fellow australian michael klim backing up after last night setting world record in the metres butterfly»\n", + "Similar Document (298, 0.7201520204544067): «university of canberra academic proposal for republic will be one of five discussed at an historic conference starting in corowa today the conference is part of centenary of federation celebrations and recognises the corowa conference of which began the process towards the federation of australia in university of canberra law lecturer bedeharris is proposing three referenda to determine the republic issue they would decide on whether the monarchy should be replaced the codification powers for head of state and the choice of republic model doctor harris says any constitutional change must involve all australians think it is very important that the people of australia be given the opporunity to choose or be consulted at every stage of the process»\n", "\n" ] } ], "source": [ - "# Pick a random document from the test corpus and infer a vector from the model\n", + "# Pick a random document from the corpus and infer a vector from the model\n", "doc_id = random.randint(0, len(train_corpus) - 1)\n", "\n", - "# Compare and print the most/median/least similar documents from the train corpus\n", + "# Compare and print the second-most-similar document\n", "print('Train Document ({}): «{}»\\n'.format(doc_id, ' '.join(train_corpus[doc_id].words)))\n", "sim_id = second_ranks[doc_id]\n", "print('Similar Document {}: «{}»\\n'.format(sim_id, ' '.join(train_corpus[sim_id[0]].words)))" @@ -444,24 +468,32 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Test Document (23): «china said sunday it issued new regulations controlling the export of missile technology taking steps to ease concerns about transferring sensitive equipment to middle east countries particularly iran however the new rules apparently do not ban outright the transfer of specific items something washington long has urged beijing to do»\n", + "Test Document (6): «senior members of the saudi royal family paid at least million to osama bin laden terror group and the taliban for an agreement his forces would not attack targets in saudi arabia according to court documents the papers filed in us billion billion lawsuit in the us allege the deal was made after two secret meetings between saudi royals and leaders of al qa ida including bin laden the money enabled al qa ida to fund training camps in afghanistan later attended by the september hijackers the disclosures will increase tensions between the us and saudi arabia»\n", "\n", "SIMILAR/DISSIMILAR DOCS PER MODEL Doc2Vec(dm/m,d50,n5,w5,mc2,s0.001,t3):\n", "\n", - "MOST (265, 0.42007705569267273): «the federal government is under fire from unions over new departmental report which recommends australia outsource information technology it to india the document says india has low cost skilled workforce the minister for foreign affairs and trade alexander downer has given his support to the document from his department entitled india new economy old economy the report says sectors like it finance and offer attractive direct investment opportunities it also says australian firms could become more competitive by outsourcing to the indian it sector the community and public sector union wendy caird says the government seems to be encouraging local companies to export jobs to india think that quite alarming obviously labour is great deal cheaper in india and that assisted by the indian government removing labour laws and bankruptcy laws ms caird said the union says while the initiative may create jobs in india it will not help australia rising unemployment»\n", + "MOST (261, 0.6407690048217773): «afghan opposition leaders meeting in germany have reached an agreement after seven days of talks on the structure of an interim post taliban government for afghanistan the agreement calls for the immediate assembly of temporary group of multi national peacekeepers in kabul and possibly other areas the four afghan factions have approved plan for member ruling council composed of chairman five deputy chairmen and other members the council would govern afghanistan for six months at which time traditional afghan assembly called loya jirga would be convened to decide on more permanent structure the agreement calls for elections within two years»\n", "\n", - "MEDIAN (257, 0.11956833302974701): «hundreds of fans stood vigil today for the immersion of george harrison ashes into the ganges river at the hindu holy city of benares but officials and sect leaders remained tightlipped on when or where last rites for the former beatle long time devotee of the hindu hare krishna sect would take place he was closely attached to benares where devout hindus come to scatter the ashes of their dead relatives in the ganges in ritual symbolising the journey of the soul towards eternal salvation the beatles former lead guitarist died on thursday of cancer aged amid chants and prayers of hare krishna devotees who were at his bedside according to details of the ceremony released by members of the hare krishna movement yesterday harrison widow olivia accompanied by son dhani were to scatter some of the ashes early this morning in discreet ceremony at hinduism holy river some of harrison ashes could also be immersed in the ganges at allahabad another holy spot for devout hindus about kilometres upstream from benares spokesman for the hare krishna group said tomorrow harrison family members were supposed to take part in special prayer meeting in vrindavan the birthplace of lord krishna km north of the indian capital the news brought hundreds of journalists fans and curious onlookers to benares odd ghats platforms or steps from which the ashes are strewn into the river this morning but as the day wore on local administration officials and hare krishna devotees in benares refused to confirm when and where along the ganges the ceremony would take place»\n", + "MEDIAN (103, 0.13398753106594086): «the hih royal commission has heard evidence that there were doubts about the company ability to pay all of its creditors three months before its collapse partner for accountancy firm ernst and young john gibbons says he and his colleague kim smith attended meeting with hih on november mr gibbons has told the commission hih chairman ray williams and finance director dominic federa were at that meeting mr gibbons said mr smith noted that if hih was wound up on that date there would be clear shortage of assets to pay creditors he says the directors were told it was highly likely all creditors would not receive per cent returns the commission has also heard that the accountancy firm told the directors that even with hih restructuring plans there was potential for insolvency»\n", "\n", - "LEAST (267, -0.22617124021053314): «israeli prime minister ariel sharon has opened an emergency security cabinet meeting after placing blame for recent suicide attacks squarely on palestinian leader yasser arafat called an urgent meeting of the heads of all the security systems and very shortly the government will hold special session the government will meet in order to make decisions about how to deal further with terrorism he said in national address on public television the government was to discuss its policy on the palestinian authority which mr sharon implied was the enemy of the jewish state and should bear the consequences those who rise up against us to kill us are responsible for their own destruction he said in statement interpreted by palestinian official as call for war arafat has made his strategic choices strategy of terrorism in choosing to try to win political accomplishments through murder and in choosing to allow the ruthless killing of civilians arafat has chosen the path of terrorism mr sharon said the government represents practically the whole of the israel public and we have the paramount goal and need for unity in order to cope with all the brutalities facing us he added tonight we heard declaration of war said chief palestinian negotiator saeb erakat on cnn television sharon has chosen the path of darkness even before his address israeli helicopters and warplanes attacked targets in the west bank and gaza strip including arafat offices and police headquarters in jenin and the palestinian leader three helicopters in gaza city the air strikes were launched on palestinian targets in the wake of weekend suicide attacks by the islamic militant group hamas which left israelis dead meanwhile hamas has defied the palestinian state of emergency and called for more suicide attacks against israel at the funeral of gunman who killed settler more than supporters of the hardline group gathered to bury year old muslim al aarage one of two palestinians who shot the settler dead on sunday in the north of the gaza strip before being killed by israeli soldiers the suicide operations will continue as long as the enemy continues its occupation of palestinian lands in the gaza strip and west bank militant from the group told crowd with loudspeaker when sharon kills women and children our people have the right to defend ourselves then they call us terrorists he said every religion and law in the world gives us the right to defend ourselves he said shortly before the air strikes began security services have arrested some militants from hamas and its smaller rival islamic jihad in the crackdown since sunday human rights group amnesty international has condemned deliberate attacks by the palestinian suicide bombers at the weekend these attacks are horrifying and tragic amnesty said in statement we call on armed groups to end immediately the direct targeting of civilians which contravenes the most fundamental principles of humanity the organisation called on the israeli government and the palestinian authority to remember that no abuses of human rights by armed groups can excuse violations of fundamental human rights and humanitarian law»\n", + "LEAST (264, -0.35531237721443176): «widespread damage from yesterday violent storms in new south wales has forced the government to declare more areas of the state natural disaster zones up to volunteers and fire fighters are continuing the big mop up state emergency services ses volunteers are still clearing some of thehuge trees that came crashing down on homes in sydney north martin walker was sitting on his back deck when the storm struck it sounded like freight train was about to hit our house you could hear it coming with such ferocity and as it hit all the trees just seemed to bend and there was stuff hitting the back of our house mr walker said pitwater bankstown sutherland hurstville and liverpool in sydney and gunnedah and tamworth in the state north west have been added to the list of natural disaster areas new south wales premier bob carr has inspected one of the worst hit parts wahroonga in sydney north struck by the of this storm damage we ve had storms before but never winds of this force and it was uneven and unpredictable in its impact mr carr said the final damage bill is expected to be more than million»\n", "\n" ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/neuscratch/Dev/gensim/gensim/matutils.py:737: FutureWarning: Conversion of the second argument of issubdtype from `int` to `np.signedinteger` is deprecated. In future, it will be treated as `np.int64 == np.dtype(int).type`.\n", + " if np.issubdtype(vec.dtype, np.int):\n" + ] } ], "source": [ @@ -485,6 +517,13 @@ "\n", "That's it! Doc2Vec is a great way to explore relationships between documents." ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -503,7 +542,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.2" + "version": "3.6.6" } }, "nbformat": 4, diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py index d73e6e777a..bf1eac8264 100644 --- a/gensim/models/doc2vec.py +++ b/gensim/models/doc2vec.py @@ -743,7 +743,7 @@ def estimated_lookup_memory(self): """ return 60 * len(self.docvecs.offset2doctag) + 140 * len(self.docvecs.doctags) - def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): + def infer_vector(self, doc_words, alpha=None, min_alpha=None, epochs=None, steps=None): """Infer a vector for given post-bulk training document. Notes @@ -756,12 +756,17 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): doc_words : list of str A document for which the vector representation will be inferred. alpha : float, optional - The initial learning rate. + The initial learning rate. If unspecified, value from model initialization will be reused. min_alpha : float, optional - Learning rate will linearly drop to `min_alpha` as training progresses. - steps : int, optional - Number of times to train the new document. A higher value may slow down training, but it will result in more - stable representations. + Learning rate will linearly drop to `min_alpha` over all inference epochs. If unspecified, + value from model initialization will be reused. + epochs : int, optional + Number of times to train the new document. Larger values take more time, but may improve + quality and run-to-run stability of inferred vectors. If unspecified, the `epochs` value + from model initialization will be reused. + steps : int, optional, deprecated + Previous name for `epochs`, still available for now for backward compatibility: if + `epochs` is unspecified but `steps` is, the `steps` value will be used. Returns ------- @@ -769,15 +774,19 @@ def infer_vector(self, doc_words, alpha=0.1, min_alpha=0.0001, steps=5): The inferred paragraph vector for the new document. """ + alpha = alpha or self.alpha + min_alpha = min_alpha or self.min_alpha + epochs = epochs or steps or self.epochs + doctag_vectors, doctag_locks = self.trainables.get_doctag_trainables(doc_words, self.docvecs.vector_size) doctag_indexes = [0] work = zeros(self.trainables.layer1_size, dtype=REAL) if not self.sg: neu1 = matutils.zeros_aligned(self.trainables.layer1_size, dtype=REAL) - alpha_delta = (alpha - min_alpha) / (steps - 1) + alpha_delta = (alpha - min_alpha) / max(epochs - 1, 1) - for i in range(steps): + for i in range(epochs): if self.sg: train_document_dbow( self, doc_words, doctag_indexes, alpha, work, diff --git a/gensim/test/test_doc2vec.py b/gensim/test/test_doc2vec.py index 559e166d4f..b80588c55e 100644 --- a/gensim/test/test_doc2vec.py +++ b/gensim/test/test_doc2vec.py @@ -513,8 +513,16 @@ def __init__(self, models): def __getitem__(self, token): return np.concatenate([model[token] for model in self.models]) - def infer_vector(self, document, alpha=0.1, min_alpha=0.0001, steps=5): - return np.concatenate([model.infer_vector(document, alpha, min_alpha, steps) for model in self.models]) + def __str__(self): + """Abbreviated name, built from submodels' names""" + return "+".join([str(model) for model in self.models]) + + @property + def epochs(self): + return self.models[0].epochs + + def infer_vector(self, document, alpha=None, min_alpha=None, epochs=None, steps=None): + return np.concatenate([model.infer_vector(document, alpha, min_alpha, epochs, steps) for model in self.models]) def train(self, *ignore_args, **ignore_kwargs): pass # train subcomponents individually diff --git a/setup.py b/setup.py index 132eb925c5..71c0f044f7 100644 --- a/setup.py +++ b/setup.py @@ -308,7 +308,7 @@ def finalize_options(self): 'numpy >= 1.11.3', 'scipy >= 0.18.1', 'six >= 1.5.0', - 'smart_open >= 1.2.1', + 'smart_open >= 1.2.1, < 1.6.0', ], tests_require=linux_testenv, extras_require={ From 49527af805288fdaeb09a21a24a6890fc39297c2 Mon Sep 17 00:00:00 2001 From: ivan Date: Fri, 6 Jul 2018 07:45:53 +0500 Subject: [PATCH 18/40] apply fixes for distributed mode lda/lsi from @piskvorky #2102 --- gensim/models/lda_dispatcher.py | 29 +++++++++++--------------- gensim/models/lda_worker.py | 18 +++++++--------- gensim/models/lsi_dispatcher.py | 37 ++++++++++++++------------------- gensim/models/lsi_worker.py | 29 +++++++++++--------------- 4 files changed, 47 insertions(+), 66 deletions(-) diff --git a/gensim/models/lda_dispatcher.py b/gensim/models/lda_dispatcher.py index c6865981ab..3e83bf7b3f 100755 --- a/gensim/models/lda_dispatcher.py +++ b/gensim/models/lda_dispatcher.py @@ -4,24 +4,19 @@ # Copyright (C) 2010 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -""":class:`~gensim.models.lda_dispatcher.Dispatcher` process which orchestrates -distributed :class:`~gensim.models.ldamodel.LdaModel` computations. -Run this script only once, on the master node in your cluster. +"""Dispatcher process which orchestrates distributed Latent Dirichlet Allocation +(LDA, :class:`~gensim.models.ldamodel.LdaModel`) computations. +Run this script only once, on any node in your cluster. Notes ----- -The dispatches expects to find worker scripts already running. Make sure you run as many workers as you like on -your machines **before** launching the dispatcher. - -Warnings --------- -Requires installed `Pyro4 `_. +The dispatcher expects to find worker scripts already running. Make sure you run as many workers as you like on +your machines **before** launching the dispatcher. How to use distributed :class:`~gensim.models.ldamodel.LdaModel` ---------------------------------------------------------------- - #. Install needed dependencies (Pyro4) :: pip install gensim[distributed] @@ -59,7 +54,6 @@ """ - from __future__ import with_statement import argparse import os @@ -126,7 +120,7 @@ def __init__(self, maxsize=MAX_JOBS_QUEUE, ns_conf=None): @Pyro4.expose def initialize(self, **model_params): - """Fully initializes the dispatcher and all its workers. + """Fully initialize the dispatcher and all its workers. Parameters ---------- @@ -176,7 +170,7 @@ def getworkers(self): @Pyro4.expose def getjob(self, worker_id): - """Atomically pops a job from the queue. + """Atomically pop a job from the queue. Parameters ---------- @@ -242,7 +236,7 @@ def getstate(self): @Pyro4.expose def reset(self, state): - """Reinitializes all workers for a new EM iteration. + """Reinitialize all workers for a new EM iteration. Parameters ---------- @@ -261,7 +255,9 @@ def reset(self, state): @Pyro4.oneway @utils.synchronous('lock_update') def jobdone(self, workerid): - """Callback used by workers to notify when their job is done. + """A worker has finished its job. Log this event and then asynchronously transfer control back to the worker. + + Callback used by workers to notify when their job is done. The job done event is logged and then control is asynchronously transfered back to the worker (who can then request another job). In this way, control flow basically oscillates between @@ -290,7 +286,7 @@ def jobsdone(self): @Pyro4.oneway def exit(self): - """Terminate all workers and then the dispatcher.""" + """Terminate all registered workers and then the dispatcher.""" for workerid, worker in iteritems(self.workers): logger.info("terminating worker %s", workerid) worker.exit() @@ -299,7 +295,6 @@ def exit(self): def main(): - """Set up argument parser,logger and launches pyro daemon.""" parser = argparse.ArgumentParser(description=__doc__[:-135], formatter_class=argparse.RawTextHelpFormatter) parser.add_argument( "--maxsize", diff --git a/gensim/models/lda_worker.py b/gensim/models/lda_worker.py index 56314e8388..83aa7ec462 100755 --- a/gensim/models/lda_worker.py +++ b/gensim/models/lda_worker.py @@ -4,21 +4,16 @@ # Copyright (C) 2011 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -""":class:`~gensim.models.lda_worker.Worker` ("slave") process used in computing -distributed :class:`~gensim.models.ldamodel.LdaModel`. +"""Worker ("slave") process used in computing distributed Latent Dirichlet Allocation +(LDA, :class:`~gensim.models.ldamodel.LdaModel`). Run this script on every node in your cluster. If you wish, you may even run it multiple times on a single machine, to make better use of multiple cores (just beware that memory footprint increases accordingly). -Warnings --------- -Requires installed `Pyro4 `_. - How to use distributed :class:`~gensim.models.ldamodel.LdaModel` ---------------------------------------------------------------- - #. Install needed dependencies (Pyro4) :: pip install gensim[distributed] @@ -55,6 +50,7 @@ :ellipsis: 0, -7 """ + from __future__ import with_statement import os import sys @@ -88,12 +84,12 @@ class Worker(object): """ def __init__(self): - """Partly initializes the model.""" + """Partly initialize the model.""" self.model = None @Pyro4.expose def initialize(self, myid, dispatcher, **model_params): - """Fully initializes the worker. + """Fully initialize the worker. Parameters ---------- @@ -117,7 +113,7 @@ def initialize(self, myid, dispatcher, **model_params): @Pyro4.expose @Pyro4.oneway def requestjob(self): - """Request jobs from the dispatcher, in a perpetual loop until :meth:`~gensim.models.lda_worker.Worker.getstate` + """Request jobs from the dispatcher, in a perpetual loop until :meth:`gensim.models.lda_worker.Worker.getstate` is called. Raises @@ -145,7 +141,7 @@ def requestjob(self): @utils.synchronous('lock_update') def processjob(self, job): - """Incrementally processes the job and potentially logs progress. + """Incrementally process the job and potentially logs progress. Parameters ---------- diff --git a/gensim/models/lsi_dispatcher.py b/gensim/models/lsi_dispatcher.py index af435999e2..0d033d580c 100755 --- a/gensim/models/lsi_dispatcher.py +++ b/gensim/models/lsi_dispatcher.py @@ -4,24 +4,17 @@ # Copyright (C) 2010 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -""":class:`~gensim.models.lsi_dispatcher.Dispatcher` process which orchestrates -distributed :class:`~gensim.models.lsimodel.LsiModel` computations. -Run this script only once, on the master node in your cluster. +"""Dispatcher process which orchestrates distributed :class:`~gensim.models.lsimodel.LsiModel` computations. +Run this script only once, on any node in your cluster. Notes ----- -The dispatches expects to find worker scripts already running. Make sure you run as many workers as you like on +The dispatcher expects to find worker scripts already running. Make sure you run as many workers as you like on your machines **before** launching the dispatcher. -Warnings --------- -Requires installed `Pyro4 `_. -Distributed version works only in local network. - - -How to use distributed :class:`~gensim.models.lsimodel.LsiModel` ----------------------------------------------------------------- +How to use distributed LSI +-------------------------- #. Install needed dependencies (Pyro4) :: @@ -51,7 +44,6 @@ >>> >>> model = LsiModel(common_corpus, id2word=common_dictionary, distributed=True) - Command line arguments ---------------------- @@ -60,7 +52,6 @@ """ - from __future__ import with_statement import os import sys @@ -100,7 +91,7 @@ class Dispatcher(object): """ def __init__(self, maxsize=0): - """Partly initializes the dispatcher. + """Partly initialize the dispatcher. A full initialization (including initialization of the workers) requires a call to :meth:`~gensim.models.lsi_dispatcher.Dispatcher.initialize` @@ -117,12 +108,14 @@ def __init__(self, maxsize=0): @Pyro4.expose def initialize(self, **model_params): - """Fully initializes the dispatcher and all its workers. + """Fully initialize the dispatcher and all its workers. Parameters ---------- **model_params - Keyword parameters used to initialize individual workers, see :class:`~gensim.models.lsimodel.LsiModel`. + Keyword parameters used to initialize individual workers + (gets handed all the way down to :meth:`gensim.models.lsi_worker.Worker.initialize`). + See :class:`~gensim.models.lsimodel.LsiModel`. Raises ------ @@ -148,7 +141,7 @@ def initialize(self, **model_params): worker.initialize(workerid, dispatcher=self.callback, **model_params) self.workers[workerid] = worker except Pyro4.errors.PyroError: - logger.exception("unresponsive worker at %s, deleting it from the name server" % uri) + logger.exception("unresponsive worker at %s, deleting it from the name server", uri) ns.remove(name) if not self.workers: @@ -168,7 +161,7 @@ def getworkers(self): @Pyro4.expose def getjob(self, worker_id): - """Atomically pops a job from the queue. + """Atomically pop a job from the queue. Parameters ---------- @@ -242,7 +235,9 @@ def reset(self): @Pyro4.oneway @utils.synchronous('lock_update') def jobdone(self, workerid): - """Callback used by workers to notify when their job is done. + """A worker has finished its job. Log this event and then asynchronously transfer control back to the worker. + + Callback used by workers to notify when their job is done. The job done event is logged and then control is asynchronously transfered back to the worker (who can then request another job). In this way, control flow basically oscillates between @@ -272,7 +267,7 @@ def jobsdone(self): @Pyro4.oneway def exit(self): - """Terminate all workers and then the dispatcher.""" + """Terminate all registered workers and then the dispatcher.""" for workerid, worker in iteritems(self.workers): logger.info("terminating worker %s", workerid) worker.exit() diff --git a/gensim/models/lsi_worker.py b/gensim/models/lsi_worker.py index 2a4a66bb9e..fddcdf6bcb 100755 --- a/gensim/models/lsi_worker.py +++ b/gensim/models/lsi_worker.py @@ -4,21 +4,15 @@ # Copyright (C) 2010 Radim Rehurek # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html -""":class:`~gensim.models.lsi_worker.Worker` ("slave") process used in computing -distributed :class:`~gensim.models.lsimodel.LsiModel`. +"""Worker ("slave") process used in computing distributed Latent Semantic Indexing (LSI, +:class:`~gensim.models.lsimodel.LsiModel`) models. Run this script on every node in your cluster. If you wish, you may even run it multiple times on a single machine, -to make better use of multiple cores (just beware that memory footprint increases accordingly). +to make better use of multiple cores (just beware that memory footprint increases linearly). -Warnings --------- -Requires installed `Pyro4 `_. -Distributed version works only in local network. - - -How to use distributed :class:`~gensim.models.lsimodel.LsiModel` ----------------------------------------------------------------- +How to use distributed LSI +-------------------------- #. Install needed dependencies (Pyro4) :: @@ -56,6 +50,7 @@ :ellipsis: 0, -3 """ + from __future__ import with_statement import os import sys @@ -79,7 +74,7 @@ class Worker(object): def __init__(self): - """Partly initializes the model. + """Partly initialize the model. A full initialization requires a call to :meth:`~gensim.models.lsi_worker.Worker.initialize`. @@ -88,7 +83,7 @@ def __init__(self): @Pyro4.expose def initialize(self, myid, dispatcher, **model_params): - """Fully initializes the worker. + """Fully initialize the worker. Parameters ---------- @@ -118,7 +113,7 @@ def requestjob(self): Raises ------ RuntimeError - If `self.model` is None (i.e. worker non initialized). + If `self.model` is None (i.e. worker not initialized). """ if self.model is None: @@ -140,7 +135,7 @@ def requestjob(self): @utils.synchronous('lock_update') def processjob(self, job): - """Incrementally processes the job and potentially logs progress. + """Incrementally process the job and potentially logs progress. Parameters ---------- @@ -173,14 +168,14 @@ def getstate(self): @Pyro4.expose @utils.synchronous('lock_update') def reset(self): - """Resets the worker by deleting its current projection.""" + """Reset the worker by deleting its current projection.""" logger.info("resetting worker #%i", self.myid) self.model.projection = self.model.projection.empty_like() self.finished = False @Pyro4.oneway def exit(self): - """Terminates the worker.""" + """Terminate the worker.""" logger.info("terminating worker #%i", self.myid) os._exit(0) From abd76dbe1ebad18afebab12e13783cc633a06374 Mon Sep 17 00:00:00 2001 From: ivan Date: Fri, 6 Jul 2018 12:31:24 +0500 Subject: [PATCH 19/40] remove smart_open limitation from setup.py, replace smart_open -> open until https://github.com/RaRe-Technologies/smart_open/issues/207 will be fixed --- gensim/models/deprecated/fasttext_wrapper.py | 2 +- gensim/models/fasttext.py | 4 +++- setup.py | 2 +- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/gensim/models/deprecated/fasttext_wrapper.py b/gensim/models/deprecated/fasttext_wrapper.py index e48a96072f..be5330db05 100644 --- a/gensim/models/deprecated/fasttext_wrapper.py +++ b/gensim/models/deprecated/fasttext_wrapper.py @@ -291,7 +291,7 @@ def delete_training_files(cls, model_file): def load_binary_data(self, encoding='utf8'): """Loads data from the output binary file created by FastText training""" - with utils.smart_open(self.file_name, 'rb') as f: + with open(self.file_name, 'rb') as f: self.load_model_params(f) self.load_dict(f, encoding=encoding) self.load_vectors(f) diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index 20430eb1e8..803b9899c4 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -708,7 +708,9 @@ def load_binary_data(self, encoding='utf8'): Specifies the encoding. """ - with utils.smart_open(self.file_name, 'rb') as f: + + ### TODO use smart_open again when https://github.com/RaRe-Technologies/smart_open/issues/207 will be fixed + with open(self.file_name, 'rb') as f: self._load_model_params(f) self._load_dict(f, encoding=encoding) self._load_vectors(f) diff --git a/setup.py b/setup.py index 71c0f044f7..132eb925c5 100644 --- a/setup.py +++ b/setup.py @@ -308,7 +308,7 @@ def finalize_options(self): 'numpy >= 1.11.3', 'scipy >= 0.18.1', 'six >= 1.5.0', - 'smart_open >= 1.2.1, < 1.6.0', + 'smart_open >= 1.2.1', ], tests_require=linux_testenv, extras_require={ From 398a00d28bb6da4493a275ae7d6cc690e1436d09 Mon Sep 17 00:00:00 2001 From: ivan Date: Fri, 6 Jul 2018 12:37:37 +0500 Subject: [PATCH 20/40] fix PEP8 issues --- gensim/models/deprecated/fasttext_wrapper.py | 2 ++ gensim/models/fasttext.py | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/gensim/models/deprecated/fasttext_wrapper.py b/gensim/models/deprecated/fasttext_wrapper.py index be5330db05..930f2c1308 100644 --- a/gensim/models/deprecated/fasttext_wrapper.py +++ b/gensim/models/deprecated/fasttext_wrapper.py @@ -291,6 +291,8 @@ def delete_training_files(cls, model_file): def load_binary_data(self, encoding='utf8'): """Loads data from the output binary file created by FastText training""" + + # TODO use smart_open again when https://github.com/RaRe-Technologies/smart_open/issues/207 will be fixed with open(self.file_name, 'rb') as f: self.load_model_params(f) self.load_dict(f, encoding=encoding) diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index 803b9899c4..0b69ddcc8b 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -86,7 +86,6 @@ from gensim.models.utils_any2vec import _compute_ngrams, _ft_hash from gensim.utils import deprecated, call_on_class_only -from gensim import utils logger = logging.getLogger(__name__) @@ -709,7 +708,7 @@ def load_binary_data(self, encoding='utf8'): """ - ### TODO use smart_open again when https://github.com/RaRe-Technologies/smart_open/issues/207 will be fixed + # TODO use smart_open again when https://github.com/RaRe-Technologies/smart_open/issues/207 will be fixed with open(self.file_name, 'rb') as f: self._load_model_params(f) self._load_dict(f, encoding=encoding) From d172a25f50a04a5f09799e2a05113b67370030af Mon Sep 17 00:00:00 2001 From: ivan Date: Fri, 6 Jul 2018 12:50:48 +0500 Subject: [PATCH 21/40] bump version to 3.5.0 --- docs/src/conf.py | 4 ++-- gensim/__init__.py | 2 +- setup.py | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/src/conf.py b/docs/src/conf.py index 71eb9a9014..d05558c540 100644 --- a/docs/src/conf.py +++ b/docs/src/conf.py @@ -55,9 +55,9 @@ # built documents. # # The short X.Y version. -version = '3.4' +version = '3.5' # The full version, including alpha/beta/rc tags. -release = '3.4.0' +release = '3.5.0' # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. diff --git a/gensim/__init__.py b/gensim/__init__.py index 96e956fffd..f70ef0f412 100644 --- a/gensim/__init__.py +++ b/gensim/__init__.py @@ -5,7 +5,7 @@ from gensim import parsing, corpora, matutils, interfaces, models, similarities, summarization, utils # noqa:F401 import logging -__version__ = '3.4.0' +__version__ = '3.5.0' class NullHandler(logging.Handler): diff --git a/setup.py b/setup.py index 132eb925c5..555ccc44fd 100644 --- a/setup.py +++ b/setup.py @@ -244,7 +244,7 @@ def finalize_options(self): setup( name='gensim', - version='3.4.0', + version='3.5.0', description='Python framework for fast Vector Space Modelling', long_description=LONG_DESCRIPTION, From a46f98f93bc5bf2f54e442003b6da8c16e6af81d Mon Sep 17 00:00:00 2001 From: ivan Date: Fri, 6 Jul 2018 12:55:10 +0500 Subject: [PATCH 22/40] bump changelos to 3.5.0 + add missing changelog for 3.4.0 --- CHANGELOG.md | 202 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 202 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 0c695cf0f5..7dd69eb6de 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,207 @@ Changes =========== +## 3.5.0, 2018-07-06 + +This release comprises a glorious 38 pull requests from 28 contributors. Most of the effort went into improving the documentation—hence the release code name "Docs 💬"! + +Apart from the **massive overhaul of all Gensim documentation** (including docstring style and examples—[you asked for it](https://rare-technologies.com/gensim-survey-2018/)), we also managed to sneak in some new functionality and a number of bug fixes. As usual, see the notes below for a complete list, with links to pull requests for more details. + +**Huge thanks to all contributors!** Nobody loves working on documentation. 3.5.0 is a result of several months of laborious, unglamorous, and sometimes invisible work. Enjoy! + + +### :books: Documentation improvements + +* Overhaul documentation for `*2vec` models (__[@steremma](https://github.com/steremma)__ & __[@piskvorky](https://github.com/piskvorky)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1944](https://github.com/RaRe-Technologies/gensim/pull/1944), [#2087](https://github.com/RaRe-Technologies/gensim/pull/2087)) +* Fix documentation for LDA-related models (__[@steremma](https://github.com/steremma)__ & __[@piskvorky](https://github.com/piskvorky)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#2026](https://github.com/RaRe-Technologies/gensim/pull/2026)) +* Fix documentation for utils, corpora, inferfaces (__[@piskvorky](https://github.com/piskvorky)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#2096](https://github.com/RaRe-Technologies/gensim/pull/2096)) +* Update non-API docs (about, intro, license etc) (__[@piskvorky](https://github.com/piskvorky)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#2101](https://github.com/RaRe-Technologies/gensim/pull/2101)) +* Refactor documentation for `gensim.models.phrases` (__[@CLearERR](https://github.com/CLearERR)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1950](https://github.com/RaRe-Technologies/gensim/pull/1950)) +* Fix HashDictionary documentation (__[@piskvorky](https://github.com/piskvorky)__, [#2073](https://github.com/RaRe-Technologies/gensim/pull/2073)) +* Fix docstrings for `gensim.models.AuthorTopicModel` (__[@souravsingh](https://github.com/souravsingh)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1907](https://github.com/RaRe-Technologies/gensim/pull/1907)) +* Fix docstrings for HdpModel, lda_worker & lda_dispatcher (__[@gyanesh-m](https://github.com/gyanesh-m)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1912](https://github.com/RaRe-Technologies/gensim/pull/1912)) +* Fix format & links for `gensim.similarities.docsim` (__[@CLearERR](https://github.com/CLearERR)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#2030](https://github.com/RaRe-Technologies/gensim/pull/2030)) +* Remove duplication of class documentation for `IndexedCorpus` (__[@darindf](https://github.com/darindf)__, [#2033](https://github.com/RaRe-Technologies/gensim/pull/2033)) +* Refactor documentation for `gensim.models.coherencemodel` (__[@CLearERR](https://github.com/CLearERR)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1933](https://github.com/RaRe-Technologies/gensim/pull/1933)) +* Fix docstrings for `gensim.sklearn_api` (__[@steremma](https://github.com/steremma)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1895](https://github.com/RaRe-Technologies/gensim/pull/1895)) +* Disable google-style docstring support (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#2106](https://github.com/RaRe-Technologies/gensim/pull/2106)) +* Fix docstring of `gensim.models.KeyedVectors.similarity_matrix` (__[@Witiko](https://github.com/Witiko)__, [#1971](https://github.com/RaRe-Technologies/gensim/pull/1971)) +* Consistently use `smart_open()` instead of `open()` in notebooks (__[@sharanry](https://github.com/sharanry)__, [#1812](https://github.com/RaRe-Technologies/gensim/pull/1812)) + + +### :star2: New features: + +* Add `add_entity` method to `KeyedVectors` to allow adding word vectors manually (__[@persiyanov](https://github.com/persiyanov)__, [#1957](https://github.com/RaRe-Technologies/gensim/pull/1957)) +* Add inference for new unseen author to `AuthorTopicModel` (__[@Stamenov](https://github.com/Stamenov)__, [#1766](https://github.com/RaRe-Technologies/gensim/pull/1766)) +* Add `evaluate_word_analogies` (will replace `accuracy`) method to `KeyedVectors` (__[@akutuzov](https://github.com/akutuzov)__, [#1935](https://github.com/RaRe-Technologies/gensim/pull/1935)) +* Add Pivot Normalization to `TfidfModel` (__[@markroxor](https://github.com/markroxor)__, [#1780](https://github.com/RaRe-Technologies/gensim/pull/1780)) + + + +### :+1: Improvements + +* Allow initialization with `max_final_vocab` in lieu of `min_count` in `Word2Vec`(__[@aneesh-joshi](https://github.com/aneesh-joshi)__, [#1915](https://github.com/RaRe-Technologies/gensim/pull/1915)) +* Add `dtype` argument for `chunkize_serial` in `LdaModel` (__[@darindf](https://github.com/darindf)__, [#2027](https://github.com/RaRe-Technologies/gensim/pull/2027)) +* Increase performance in `Phrases.analyze_sentence` (__[@JonathanHourany](https://github.com/JonathanHourany)__, [#2070](https://github.com/RaRe-Technologies/gensim/pull/2070)) +* Add `ns_exponent` parameter to control the negative sampling distribution for `*2vec` models (__[@fernandocamargoti](https://github.com/fernandocamargoti)__, [#2093](https://github.com/RaRe-Technologies/gensim/pull/2093)) + + +### :red_circle: Bug fixes: + + +* Fix `Doc2Vec.infer_vector` + notebook cleanup (__[@gojomo](https://github.com/gojomo)__, [#2103](https://github.com/RaRe-Technologies/gensim/pull/2103)) +* Fix linear decay for learning rate in `Doc2Vec.infer_vector` (__[@umangv](https://github.com/umangv)__, [#2063](https://github.com/RaRe-Technologies/gensim/pull/2063)) +* Fix negative sampling floating-point error for `gensim.models.Poincare (__[@jayantj](https://github.com/jayantj)__, [#1959](https://github.com/RaRe-Technologies/gensim/pull/1959)) +* Fix loading `word2vec` and `doc2vec` models saved using old Gensim versions (__[@manneshiva](https://github.com/manneshiva)__, [#2012](https://github.com/RaRe-Technologies/gensim/pull/2012)) +* Fix `SoftCosineSimilarity.get_similarities` on corpora ssues/1955) (__[@Witiko](https://github.com/Witiko)__, [#1972](https://github.com/RaRe-Technologies/gensim/pull/1972)) +* Fix return dtype for `matutils.unitvec` according to input dtype (__[@o-P-o](https://github.com/o-P-o)__, [#1992](https://github.com/RaRe-Technologies/gensim/pull/1992)) +* Fix passing empty dictionary to `gensim.corpora.WikiCorpus` (__[@steremma](https://github.com/steremma)__, [#2042](https://github.com/RaRe-Technologies/gensim/pull/2042)) +* Fix bug in `Similarity.query_shards` in multiprocessing case (__[@bohea](https://github.com/bohea)__, [#2044](https://github.com/RaRe-Technologies/gensim/pull/2044)) +* Fix SMART from TfidfModel for case when `df == "n"` (__[@PeteBleackley](https://github.com/PeteBleackley)__, [#2021](https://github.com/RaRe-Technologies/gensim/pull/2021)) +* Fix OverflowError when loading a large term-document matrix in compiled MatrixMarket format (__[@arlenk](https://github.com/arlenk)__, [#2001](https://github.com/RaRe-Technologies/gensim/pull/2001)) +* Update rules for removing table markup from Wikipedia dumps (__[@chaitaliSaini](https://github.com/chaitaliSaini)__, [#1954](https://github.com/RaRe-Technologies/gensim/pull/1954)) +* Fix `_is_single` from `Phrases` for case when corpus is a NumPy array (__[@rmalouf](https://github.com/rmalouf)__, [#1987](https://github.com/RaRe-Technologies/gensim/pull/1987)) +* Fix tests for `EuclideanKeyedVectors.similarity_matrix` (__[@Witiko](https://github.com/Witiko)__, [#1984](https://github.com/RaRe-Technologies/gensim/pull/1984)) +* Fix deprecated parameters in `D2VTransformer` and `W2VTransformer`(__[@MritunjayMohitesh](https://github.com/MritunjayMohitesh)__, [#1945](https://github.com/RaRe-Technologies/gensim/pull/1945)) +* Fix `Doc2Vec.infer_vector` after loading old `Doc2Vec` (`gensim<=3.2`)(__[@manneshiva](https://github.com/manneshiva)__, [#1974](https://github.com/RaRe-Technologies/gensim/pull/1974)) +* Fix inheritance chain for `load_word2vec_format` (__[@DennisChen0307](https://github.com/DennisChen0307)__, [#1968](https://github.com/RaRe-Technologies/gensim/pull/1968)) +* Update Keras version (avoid bug from `keras==2.1.5`) (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1963](https://github.com/RaRe-Technologies/gensim/pull/1963)) + + + +### :warning: Deprecations (will be removed in the next major release) +* Remove + - `gensim.models.wrappers.fasttext` (obsoleted by the new native `gensim.models.fasttext` implementation) + - `gensim.examples` + - `gensim.nosy` + - `gensim.scripts.word2vec_standalone` + - `gensim.scripts.make_wiki_lemma` + - `gensim.scripts.make_wiki_online` + - `gensim.scripts.make_wiki_online_lemma` + - `gensim.scripts.make_wiki_online_nodebug` + - `gensim.scripts.make_wiki` (all of these obsoleted by the new native `gensim.scripts.segment_wiki` implementation) + - "deprecated" functions and attributes + +* Move + - `gensim.scripts.make_wikicorpus` ➡ `gensim.scripts.make_wiki.py` + - `gensim.summarization` ➡ `gensim.models.summarization` + - `gensim.topic_coherence` ➡ `gensim.models._coherence` + - `gensim.utils` ➡ `gensim.utils.utils` (old imports will continue to work) + - `gensim.parsing.*` ➡ `gensim.utils.text_utils` + + +## 3.4.0, 2018-03-01 + +### :star2: New features: +* Massive optimizations of `gensim.models.LdaModel`: much faster training, using Cython. (__[@arlenk](https://github.com/arlenk)__, [#1767](https://github.com/RaRe-Technologies/gensim/pull/1767)) + - Training benchmark :boom: + + | dataset | old LDA [sec] | optimized LDA [sec] | speed up | + |---------|---------------|---------------------|---------| + | nytimes | 3473 | **1975** | **1.76x** | + | enron | 774 | **437** | **1.77x** | + + - This change **affects all models that depend on `LdaModel`**, such as `LdaMulticore`, `LdaSeqModel`, `AuthorTopicModel`. +* Huge speed-ups to corpus I/O with `MmCorpus` (Cython) (__[@arlenk](https://github.com/arlenk)__, [#1825](https://github.com/RaRe-Technologies/gensim/pull/1825)) + - File reading benchmark + + | dataset | file compressed? | old MmReader [sec] | optimized MmReader [sec] | speed up | + |---------------|:-----------:|:------------:|:------------------:|:-------------:| + | enron | no | 22.3 | **2.6** | **8.7x** | + | | yes | 37.3 | **14.4** | **2.6x** | + | nytimes | no | 419.3 | **49.2** | **8.5x** | + | | yes | 686.2 | **275.1** | **2.5x** | + | text8 | no | 25.4 | **2.5** | **10.1x** | + | | yes | 41.9 | **17.0** | **2.5x** | + + - Overall, a **2.5x** speedup for compressed `.mm.gz` input and **8.5x** :fire::fire::fire: for uncompressed plaintext `.mm`. + +* Performance and memory optimization to `gensim.models.FastText` :rocket: (__[@jbaiter](https://github.com/jbaiter)__, [#1916](https://github.com/RaRe-Technologies/gensim/pull/1916)) + - Benchmark (first 500,000 articles from English Wikipedia) + + | Metric | old FastText | optimized FastText | improvement | + | -----------------------| -----------------| -------------------|-------------| + | Training time (1 epoch) | 4823.4s (80.38 minutes) | **1873.6s (31.22 minutes)** | **2.57x** | + | Training time (full) | 1h 26min 13s | **36min 43s** | **2.35x** | + | Training words/sec | 72,781 | **187,366** | **2.57x** | + | Training peak memory | 5.2 GB | **3.7 GB** | **1.4x** | + + - Overall, a **2.5x** speedup & memory usage reduced by **30%**. + +* Implemented [Soft Cosine Measure](https://en.wikipedia.org/wiki/Cosine_similarity#Soft_cosine_measure) (__[@Witiko](https://github.com/Witiko)__, [#1827](https://github.com/RaRe-Technologies/gensim/pull/1827)) + - New method for assessing document similarity, a nice faster alternative to [WMD, Word Mover's Distance](http://proceedings.mlr.press/v37/kusnerb15.pdf) + - Benchmark + + | Technique | MAP score | Duration | + |-----------|-----------|--------------| + | softcossim| **45.99** | **1.24 sec** | + | wmd-relax | 44.48 | 12.22 sec | + | cossim | 44.22 | 4.39 sec | + | wmd-gensim| 44.08 | 98.29 sec | + + - [Soft Cosine notebook with detailed description, examples & benchmarks](https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/soft_cosine_tutorial.ipynb) + - Related papers: + - [Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model](http://www.scielo.org.mx/pdf/cys/v18n3/v18n3a7.pdf) + - [SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering](http://www.aclweb.org/anthology/S17-2051) + - [Vector Space Representations in IR](https://github.com/witiko-masters-thesis/thesis/blob/master/main.pdf) + + +### :+1: Improvements: +* New method to show the Gensim installation parameters: `python -m gensim.scripts.package_info --info`. Use this when reporting problems, for easier debugging. Fix #1902 (__[@sharanry](https://github.com/sharanry)__, [#1903](https://github.com/RaRe-Technologies/gensim/pull/1903)) +* Added a flag to optionally skip network-related tests, to help maintainers avoid network issues with CI services (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1930](https://github.com/RaRe-Technologies/gensim/pull/1930)) +* Added `license` field to `setup.py`, allowing the use of tools like `pip-licenses` (__[@nils-werner](https://github.com/nils-werner)__, [#1909](https://github.com/RaRe-Technologies/gensim/pull/1909)) + +### :red_circle: Bug fixes: +* Fix Python 3 compatibility for `gensim.corpora.UciCorpus.save_corpus` (__[@darindf](https://github.com/darindf)__, [#1875](https://github.com/RaRe-Technologies/gensim/pull/1875)) +* Add `wv` property to KeyedVectors for backward compatibility. Fix #1882 (__[@manneshiva](https://github.com/manneshiva)__, [#1884](https://github.com/RaRe-Technologies/gensim/pull/1884)) +* Fix deprecation warning from `inspect.getargspec`. Fix #1878 (__[@aneesh-joshi](https://github.com/aneesh-joshi)__, [#1887](https://github.com/RaRe-Technologies/gensim/pull/1887)) +* Add `LabeledSentence` to `gensim.models.doc2vec` for backward compatibility. Fix #1886 (__[@manneshiva](https://github.com/manneshiva)__, [#1891](https://github.com/RaRe-Technologies/gensim/pull/1891)) +* Fix empty output bug in `Phrases` (when using `model[tokens]` twice). Fix #1401 (__[@sj29-innovate](https://github.com/sj29-innovate)__, [#1853](https://github.com/RaRe-Technologies/gensim/pull/1853)) +* Fix type problems for `D2VTransformer.fit_transform`. Fix #1834 (__[@Utkarsh-Mishra-CIC](https://github.com/Utkarsh-Mishra-CIC)__, [#1845](https://github.com/RaRe-Technologies/gensim/pull/1845)) +* Fix `datatype` parameter for `KeyedVectors.load_word2vec_format`. Fix #1682 (__[@pushpankar](https://github.com/pushpankar)__, [#1819](https://github.com/RaRe-Technologies/gensim/pull/1819)) +* Fix deprecated parameters in `doc2vec-lee` notebook (__[@TheFlash10](https://github.com/TheFlash10)__, [#1918](https://github.com/RaRe-Technologies/gensim/pull/1918)) +* Fix file-like closing bug in `gensim.corpora.MmCorpus`. Fix #1869 (__[@sj29-innovate](https://github.com/sj29-innovate)__, [#1911](https://github.com/RaRe-Technologies/gensim/pull/1911)) +* Fix precision problem in `test_similarities.py`, no more FP fails. (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1928](https://github.com/RaRe-Technologies/gensim/pull/1928)) +* Fix encoding in Lee corpus reader. (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1931](https://github.com/RaRe-Technologies/gensim/pull/1931)) +* Fix OOV pairs counter in `WordEmbeddingsKeyedVectors.evaluate_word_pairs`. (__[@akutuzov](https://github.com/akutuzov)__, [#1934](https://github.com/RaRe-Technologies/gensim/pull/1934)) + + +### :books: Tutorial and doc improvements: +* Fix example block for `gensim.models.Word2Vec` (__[@nzw0301](https://github.com/nzw0301)__, [#1870](https://github.com/RaRe-Technologies/gensim/pull/1876)) +* Fix `doc2vec-lee` notebook (__[@numericlee](https://github.com/numericlee)__, [#1870](https://github.com/RaRe-Technologies/gensim/pull/1870)) +* Store images from `README.md` directly in repository. Fix #1849 (__[@ibrahimsharaf](https://github.com/ibrahimsharaf)__, [#1861](https://github.com/RaRe-Technologies/gensim/pull/1861)) +* Add windows venv activate command to `CONTRIBUTING.md` (__[@aneesh-joshi](https://github.com/aneesh-joshi)__, [#1880](https://github.com/RaRe-Technologies/gensim/pull/1880)) +* Add anaconda-cloud badge. Partial fix #1901 (__[@sharanry](https://github.com/sharanry)__, [#1905](https://github.com/RaRe-Technologies/gensim/pull/1905)) +* Fix docstrings for lsi-related code (__[@steremma](https://github.com/steremma)__, [#1892](https://github.com/RaRe-Technologies/gensim/pull/1892)) +* Fix parameter description of `sg` parameter for `gensim.models.word2vec` (__[@mdcclv](https://github.com/mdcclv)__, [#1919](https://github.com/RaRe-Technologies/gensim/pull/1919)) +* Refactor documentation for `gensim.similarities.docsim` and `MmCorpus-related`. (__[@CLearERR](https://github.com/CLearERR)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1910](https://github.com/RaRe-Technologies/gensim/pull/1910)) +* Fix docstrings for `gensim.test.utils` (__[@yurkai](https://github.com/yurkai)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1904](https://github.com/RaRe-Technologies/gensim/pull/1904)) +* Refactor docstrings for `gensim.scripts`. Partial fix #1665 (__[@yurkai](https://github.com/yurkai)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1792](https://github.com/RaRe-Technologies/gensim/pull/1792)) +* Refactor API reference `gensim.corpora`. Partial fix #1671 (__[@CLearERR](https://github.com/CLearERR)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1835](https://github.com/RaRe-Technologies/gensim/pull/1835)) +* Fix documentation for `gensim.models.wrappers` (__[@kakshay21](https://github.com/kakshay21)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1859](https://github.com/RaRe-Technologies/gensim/pull/1859)) +* Fix docstrings for `gensim.interfaces` (__[@yurkai](https://github.com/yurkai)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1913](https://github.com/RaRe-Technologies/gensim/pull/1913)) + + +### :warning: Deprecations (will be removed in the next major release) +* Remove + - `gensim.models.wrappers.fasttext` (obsoleted by the new native `gensim.models.fasttext` implementation) + - `gensim.examples` + - `gensim.nosy` + - `gensim.scripts.word2vec_standalone` + - `gensim.scripts.make_wiki_lemma` + - `gensim.scripts.make_wiki_online` + - `gensim.scripts.make_wiki_online_lemma` + - `gensim.scripts.make_wiki_online_nodebug` + - `gensim.scripts.make_wiki` (all of these obsoleted by the new native `gensim.scripts.segment_wiki` implementation) + - "deprecated" functions and attributes + +* Move + - `gensim.scripts.make_wikicorpus` ➡ `gensim.scripts.make_wiki.py` + - `gensim.summarization` ➡ `gensim.models.summarization` + - `gensim.topic_coherence` ➡ `gensim.models._coherence` + - `gensim.utils` ➡ `gensim.utils.utils` (old imports will continue to work) + - `gensim.parsing.*` ➡ `gensim.utils.text_utils` + + ## 3.3.0, 2018-01-02 :star2: New features: From 6ecd261ebac4a716b14b6d33f69323df06f88270 Mon Sep 17 00:00:00 2001 From: ivan Date: Fri, 6 Jul 2018 12:57:13 +0500 Subject: [PATCH 23/40] regenerated C files with Cython --- gensim/_matutils.c | 5815 +++++++++++++++++++++++--------------------- 1 file changed, 3067 insertions(+), 2748 deletions(-) diff --git a/gensim/_matutils.c b/gensim/_matutils.c index e71c89895f..90afbdcd72 100644 --- a/gensim/_matutils.c +++ b/gensim/_matutils.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.27.3 */ +/* Generated by Cython 0.28.3 */ #define PY_SSIZE_T_CLEAN #include "Python.h" @@ -7,7 +7,7 @@ #elif PY_VERSION_HEX < 0x02060000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.6+ or Python 3.3+. #else -#define CYTHON_ABI "0_27_3" +#define CYTHON_ABI "0_28_3" #define CYTHON_FUTURE_DIVISION 1 #include #ifndef offsetof @@ -183,6 +183,103 @@ #undef BASE #undef MASK #endif +#ifndef __has_attribute + #define __has_attribute(x) 0 +#endif +#ifndef __has_cpp_attribute + #define __has_cpp_attribute(x) 0 +#endif +#ifndef CYTHON_RESTRICT + #if defined(__GNUC__) + #define CYTHON_RESTRICT __restrict__ + #elif defined(_MSC_VER) && _MSC_VER >= 1400 + #define CYTHON_RESTRICT __restrict + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_RESTRICT restrict + #else + #define CYTHON_RESTRICT + #endif +#endif +#ifndef CYTHON_UNUSED +# if defined(__GNUC__) +# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) +# define CYTHON_UNUSED __attribute__ ((__unused__)) +# else +# define CYTHON_UNUSED +# endif +#endif +#ifndef CYTHON_MAYBE_UNUSED_VAR +# if defined(__cplusplus) + template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } +# else +# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) +# endif +#endif +#ifndef CYTHON_NCP_UNUSED +# if CYTHON_COMPILING_IN_CPYTHON +# define CYTHON_NCP_UNUSED +# else +# define CYTHON_NCP_UNUSED CYTHON_UNUSED +# endif +#endif +#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) +#ifdef _MSC_VER + #ifndef _MSC_STDINT_H_ + #if _MSC_VER < 1300 + typedef unsigned char uint8_t; + typedef unsigned int uint32_t; + #else + typedef unsigned __int8 uint8_t; + typedef unsigned __int32 uint32_t; + #endif + #endif +#else + #include +#endif +#ifndef CYTHON_FALLTHROUGH + #if defined(__cplusplus) && __cplusplus >= 201103L + #if __has_cpp_attribute(fallthrough) + #define CYTHON_FALLTHROUGH [[fallthrough]] + #elif __has_cpp_attribute(clang::fallthrough) + #define CYTHON_FALLTHROUGH [[clang::fallthrough]] + #elif __has_cpp_attribute(gnu::fallthrough) + #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] + #endif + #endif + #ifndef CYTHON_FALLTHROUGH + #if __has_attribute(fallthrough) + #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) + #else + #define CYTHON_FALLTHROUGH + #endif + #endif + #if defined(__clang__ ) && defined(__apple_build_version__) + #if __apple_build_version__ < 7000000 + #undef CYTHON_FALLTHROUGH + #define CYTHON_FALLTHROUGH + #endif + #endif +#endif + +#ifndef CYTHON_INLINE + #if defined(__clang__) + #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) + #elif defined(__GNUC__) + #define CYTHON_INLINE __inline__ + #elif defined(_MSC_VER) + #define CYTHON_INLINE __inline + #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + #define CYTHON_INLINE inline + #else + #define CYTHON_INLINE + #endif +#endif + #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX < 0x02070600 && !defined(Py_OptimizeFlag) #define Py_OptimizeFlag 0 #endif @@ -211,12 +308,12 @@ #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif -#if PY_VERSION_HEX < 0x030700A0 || !defined(METH_FASTCALL) +#if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif - typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject **args, Py_ssize_t nargs); - typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject **args, + typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); + typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast @@ -228,6 +325,18 @@ #else #define __Pyx_PyFastCFunction_Check(func) 0 #endif +#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) + #define PyObject_Malloc(s) PyMem_Malloc(s) + #define PyObject_Free(p) PyMem_Free(p) + #define PyObject_Realloc(p) PyMem_Realloc(p) +#endif +#if CYTHON_COMPILING_IN_PYSTON + #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) +#else + #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) + #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) +#endif #if !CYTHON_FAST_THREAD_STATE || PY_VERSION_HEX < 0x02070000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x03060000 @@ -237,6 +346,36 @@ #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif +#if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) +#include "pythread.h" +#define Py_tss_NEEDS_INIT 0 +typedef int Py_tss_t; +static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { + *key = PyThread_create_key(); + return 0; // PyThread_create_key reports success always +} +static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { + Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); + *key = Py_tss_NEEDS_INIT; + return key; +} +static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { + PyObject_Free(key); +} +static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { + return *key != Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { + PyThread_delete_key(*key); + *key = Py_tss_NEEDS_INIT; +} +static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { + return PyThread_set_key_value(*key, value); +} +static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { + return PyThread_get_key_value(*key); +} +#endif // TSS (Thread Specific Storage) API #if CYTHON_COMPILING_IN_CPYTHON || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else @@ -249,6 +388,11 @@ #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && CYTHON_USE_UNICODE_INTERNALS +#define __Pyx_PyDict_GetItemStr(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) +#else +#define __Pyx_PyDict_GetItemStr(dict, name) PyDict_GetItem(dict, name) +#endif #if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ @@ -293,18 +437,6 @@ #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif -#if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) - #define PyObject_Malloc(s) PyMem_Malloc(s) - #define PyObject_Free(p) PyMem_Free(p) - #define PyObject_Realloc(p) PyMem_Realloc(p) -#endif -#if CYTHON_COMPILING_IN_PYSTON - #define __Pyx_PyCode_HasFreeVars(co) PyCode_HasFreeVars(co) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) PyFrame_SetLineNumber(frame, lineno) -#else - #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) - #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) -#endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 @@ -321,6 +453,7 @@ #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact + #define PyObject_Unicode PyObject_Str #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) @@ -332,7 +465,11 @@ #ifndef PySet_CheckExact #define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type) #endif -#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) +#if CYTHON_ASSUME_SAFE_MACROS + #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) +#else + #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) +#endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type @@ -367,16 +504,10 @@ #define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t #endif #if PY_MAJOR_VERSION >= 3 - #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func)) + #define __Pyx_PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : (Py_INCREF(func), func)) #else #define __Pyx_PyMethod_New(func, self, klass) PyMethod_New(func, self, klass) #endif -#ifndef __has_attribute - #define __has_attribute(x) 0 -#endif -#ifndef __has_cpp_attribute - #define __has_cpp_attribute(x) 0 -#endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods @@ -394,96 +525,6 @@ unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif -#ifndef CYTHON_RESTRICT - #if defined(__GNUC__) - #define CYTHON_RESTRICT __restrict__ - #elif defined(_MSC_VER) && _MSC_VER >= 1400 - #define CYTHON_RESTRICT __restrict - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_RESTRICT restrict - #else - #define CYTHON_RESTRICT - #endif -#endif -#ifndef CYTHON_UNUSED -# if defined(__GNUC__) -# if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -# elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) -# define CYTHON_UNUSED __attribute__ ((__unused__)) -# else -# define CYTHON_UNUSED -# endif -#endif -#ifndef CYTHON_MAYBE_UNUSED_VAR -# if defined(__cplusplus) - template void CYTHON_MAYBE_UNUSED_VAR( const T& ) { } -# else -# define CYTHON_MAYBE_UNUSED_VAR(x) (void)(x) -# endif -#endif -#ifndef CYTHON_NCP_UNUSED -# if CYTHON_COMPILING_IN_CPYTHON -# define CYTHON_NCP_UNUSED -# else -# define CYTHON_NCP_UNUSED CYTHON_UNUSED -# endif -#endif -#define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) -#ifdef _MSC_VER - #ifndef _MSC_STDINT_H_ - #if _MSC_VER < 1300 - typedef unsigned char uint8_t; - typedef unsigned int uint32_t; - #else - typedef unsigned __int8 uint8_t; - typedef unsigned __int32 uint32_t; - #endif - #endif -#else - #include -#endif -#ifndef CYTHON_FALLTHROUGH - #if defined(__cplusplus) && __cplusplus >= 201103L - #if __has_cpp_attribute(fallthrough) - #define CYTHON_FALLTHROUGH [[fallthrough]] - #elif __has_cpp_attribute(clang::fallthrough) - #define CYTHON_FALLTHROUGH [[clang::fallthrough]] - #elif __has_cpp_attribute(gnu::fallthrough) - #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] - #endif - #endif - #ifndef CYTHON_FALLTHROUGH - #if __has_attribute(fallthrough) - #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) - #else - #define CYTHON_FALLTHROUGH - #endif - #endif - #if defined(__clang__ ) && defined(__apple_build_version__) - #if __apple_build_version__ < 7000000 - #undef CYTHON_FALLTHROUGH - #define CYTHON_FALLTHROUGH - #endif - #endif -#endif - -#ifndef CYTHON_INLINE - #if defined(__clang__) - #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) - #elif defined(__GNUC__) - #define CYTHON_INLINE __inline__ - #elif defined(_MSC_VER) - #define CYTHON_INLINE __inline - #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L - #define CYTHON_INLINE inline - #else - #define CYTHON_INLINE - #endif -#endif #if defined(WIN32) || defined(MS_WINDOWS) #define _USE_MATH_DEFINES @@ -520,6 +561,7 @@ static CYTHON_INLINE float __PYX_NAN() { #define __PYX_HAVE__gensim___matutils #define __PYX_HAVE_API__gensim___matutils +/* Early includes */ #include #include #include "numpy/arrayobject.h" @@ -612,7 +654,7 @@ static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) -#define __Pyx_PyBool_FromLong(b) ((b) ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False)) +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ @@ -720,7 +762,7 @@ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } static PyObject *__pyx_m = NULL; static PyObject *__pyx_d; static PyObject *__pyx_b; -static PyObject *__pyx_cython_runtime; +static PyObject *__pyx_cython_runtime = NULL; static PyObject *__pyx_empty_tuple; static PyObject *__pyx_empty_bytes; static PyObject *__pyx_empty_unicode; @@ -867,7 +909,7 @@ typedef struct { } __Pyx_BufFmt_Context; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":743 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":730 * # in Cython to enable them only on the right systems. * * ctypedef npy_int8 int8_t # <<<<<<<<<<<<<< @@ -876,7 +918,7 @@ typedef struct { */ typedef npy_int8 __pyx_t_5numpy_int8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":731 * * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t # <<<<<<<<<<<<<< @@ -885,7 +927,7 @@ typedef npy_int8 __pyx_t_5numpy_int8_t; */ typedef npy_int16 __pyx_t_5numpy_int16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":732 * ctypedef npy_int8 int8_t * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t # <<<<<<<<<<<<<< @@ -894,7 +936,7 @@ typedef npy_int16 __pyx_t_5numpy_int16_t; */ typedef npy_int32 __pyx_t_5numpy_int32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":746 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":733 * ctypedef npy_int16 int16_t * ctypedef npy_int32 int32_t * ctypedef npy_int64 int64_t # <<<<<<<<<<<<<< @@ -903,7 +945,7 @@ typedef npy_int32 __pyx_t_5numpy_int32_t; */ typedef npy_int64 __pyx_t_5numpy_int64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":750 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":737 * #ctypedef npy_int128 int128_t * * ctypedef npy_uint8 uint8_t # <<<<<<<<<<<<<< @@ -912,7 +954,7 @@ typedef npy_int64 __pyx_t_5numpy_int64_t; */ typedef npy_uint8 __pyx_t_5numpy_uint8_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":751 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":738 * * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t # <<<<<<<<<<<<<< @@ -921,7 +963,7 @@ typedef npy_uint8 __pyx_t_5numpy_uint8_t; */ typedef npy_uint16 __pyx_t_5numpy_uint16_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":752 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":739 * ctypedef npy_uint8 uint8_t * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t # <<<<<<<<<<<<<< @@ -930,7 +972,7 @@ typedef npy_uint16 __pyx_t_5numpy_uint16_t; */ typedef npy_uint32 __pyx_t_5numpy_uint32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":753 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":740 * ctypedef npy_uint16 uint16_t * ctypedef npy_uint32 uint32_t * ctypedef npy_uint64 uint64_t # <<<<<<<<<<<<<< @@ -939,7 +981,7 @@ typedef npy_uint32 __pyx_t_5numpy_uint32_t; */ typedef npy_uint64 __pyx_t_5numpy_uint64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":757 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":744 * #ctypedef npy_uint128 uint128_t * * ctypedef npy_float32 float32_t # <<<<<<<<<<<<<< @@ -948,7 +990,7 @@ typedef npy_uint64 __pyx_t_5numpy_uint64_t; */ typedef npy_float32 __pyx_t_5numpy_float32_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":745 * * ctypedef npy_float32 float32_t * ctypedef npy_float64 float64_t # <<<<<<<<<<<<<< @@ -957,7 +999,7 @@ typedef npy_float32 __pyx_t_5numpy_float32_t; */ typedef npy_float64 __pyx_t_5numpy_float64_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":754 * # The int types are mapped a bit surprising -- * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t # <<<<<<<<<<<<<< @@ -966,7 +1008,7 @@ typedef npy_float64 __pyx_t_5numpy_float64_t; */ typedef npy_long __pyx_t_5numpy_int_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":768 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":755 * # numpy.int corresponds to 'l' and numpy.long to 'q' * ctypedef npy_long int_t * ctypedef npy_longlong long_t # <<<<<<<<<<<<<< @@ -975,7 +1017,7 @@ typedef npy_long __pyx_t_5numpy_int_t; */ typedef npy_longlong __pyx_t_5numpy_long_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":756 * ctypedef npy_long int_t * ctypedef npy_longlong long_t * ctypedef npy_longlong longlong_t # <<<<<<<<<<<<<< @@ -984,7 +1026,7 @@ typedef npy_longlong __pyx_t_5numpy_long_t; */ typedef npy_longlong __pyx_t_5numpy_longlong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":758 * ctypedef npy_longlong longlong_t * * ctypedef npy_ulong uint_t # <<<<<<<<<<<<<< @@ -993,7 +1035,7 @@ typedef npy_longlong __pyx_t_5numpy_longlong_t; */ typedef npy_ulong __pyx_t_5numpy_uint_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":772 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":759 * * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t # <<<<<<<<<<<<<< @@ -1002,7 +1044,7 @@ typedef npy_ulong __pyx_t_5numpy_uint_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":760 * ctypedef npy_ulong uint_t * ctypedef npy_ulonglong ulong_t * ctypedef npy_ulonglong ulonglong_t # <<<<<<<<<<<<<< @@ -1011,7 +1053,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulong_t; */ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":762 * ctypedef npy_ulonglong ulonglong_t * * ctypedef npy_intp intp_t # <<<<<<<<<<<<<< @@ -1020,7 +1062,7 @@ typedef npy_ulonglong __pyx_t_5numpy_ulonglong_t; */ typedef npy_intp __pyx_t_5numpy_intp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":763 * * ctypedef npy_intp intp_t * ctypedef npy_uintp uintp_t # <<<<<<<<<<<<<< @@ -1029,7 +1071,7 @@ typedef npy_intp __pyx_t_5numpy_intp_t; */ typedef npy_uintp __pyx_t_5numpy_uintp_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":765 * ctypedef npy_uintp uintp_t * * ctypedef npy_double float_t # <<<<<<<<<<<<<< @@ -1038,7 +1080,7 @@ typedef npy_uintp __pyx_t_5numpy_uintp_t; */ typedef npy_double __pyx_t_5numpy_float_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":766 * * ctypedef npy_double float_t * ctypedef npy_double double_t # <<<<<<<<<<<<<< @@ -1047,7 +1089,7 @@ typedef npy_double __pyx_t_5numpy_float_t; */ typedef npy_double __pyx_t_5numpy_double_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":780 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":767 * ctypedef npy_double float_t * ctypedef npy_double double_t * ctypedef npy_longdouble longdouble_t # <<<<<<<<<<<<<< @@ -1086,7 +1128,7 @@ struct __pyx_MemviewEnum_obj; struct __pyx_memoryview_obj; struct __pyx_memoryviewslice_obj; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":769 * ctypedef npy_longdouble longdouble_t * * ctypedef npy_cfloat cfloat_t # <<<<<<<<<<<<<< @@ -1095,7 +1137,7 @@ struct __pyx_memoryviewslice_obj; */ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":783 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":770 * * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t # <<<<<<<<<<<<<< @@ -1104,7 +1146,7 @@ typedef npy_cfloat __pyx_t_5numpy_cfloat_t; */ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":771 * ctypedef npy_cfloat cfloat_t * ctypedef npy_cdouble cdouble_t * ctypedef npy_clongdouble clongdouble_t # <<<<<<<<<<<<<< @@ -1113,7 +1155,7 @@ typedef npy_cdouble __pyx_t_5numpy_cdouble_t; */ typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t; -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":786 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":773 * ctypedef npy_clongdouble clongdouble_t * * ctypedef npy_cdouble complex_t # <<<<<<<<<<<<<< @@ -1122,7 +1164,7 @@ typedef npy_clongdouble __pyx_t_5numpy_clongdouble_t; */ typedef npy_cdouble __pyx_t_5numpy_complex_t; -/* "View.MemoryView":103 +/* "View.MemoryView":104 * * @cname("__pyx_array") * cdef class array: # <<<<<<<<<<<<<< @@ -1147,7 +1189,7 @@ struct __pyx_array_obj { }; -/* "View.MemoryView":277 +/* "View.MemoryView":278 * * @cname('__pyx_MemviewEnum') * cdef class Enum(object): # <<<<<<<<<<<<<< @@ -1160,7 +1202,7 @@ struct __pyx_MemviewEnum_obj { }; -/* "View.MemoryView":328 +/* "View.MemoryView":329 * * @cname('__pyx_memoryview') * cdef class memoryview(object): # <<<<<<<<<<<<<< @@ -1183,7 +1225,7 @@ struct __pyx_memoryview_obj { }; -/* "View.MemoryView":953 +/* "View.MemoryView":960 * * @cname('__pyx_memoryviewslice') * cdef class _memoryviewslice(memoryview): # <<<<<<<<<<<<<< @@ -1200,7 +1242,7 @@ struct __pyx_memoryviewslice_obj { -/* "View.MemoryView":103 +/* "View.MemoryView":104 * * @cname("__pyx_array") * cdef class array: # <<<<<<<<<<<<<< @@ -1214,7 +1256,7 @@ struct __pyx_vtabstruct_array { static struct __pyx_vtabstruct_array *__pyx_vtabptr_array; -/* "View.MemoryView":328 +/* "View.MemoryView":329 * * @cname('__pyx_memoryview') * cdef class memoryview(object): # <<<<<<<<<<<<<< @@ -1234,7 +1276,7 @@ struct __pyx_vtabstruct_memoryview { static struct __pyx_vtabstruct_memoryview *__pyx_vtabptr_memoryview; -/* "View.MemoryView":953 +/* "View.MemoryView":960 * * @cname('__pyx_memoryviewslice') * cdef class _memoryviewslice(memoryview): # <<<<<<<<<<<<<< @@ -1313,16 +1355,7 @@ static struct __pyx_vtabstruct__memoryviewslice *__pyx_vtabptr__memoryviewslice; /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS -static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { - PyTypeObject* tp = Py_TYPE(obj); - if (likely(tp->tp_getattro)) - return tp->tp_getattro(obj, attr_name); -#if PY_MAJOR_VERSION < 3 - if (likely(tp->tp_getattr)) - return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); -#endif - return PyObject_GetAttr(obj, attr_name); -} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif @@ -1484,23 +1517,13 @@ static CYTHON_INLINE int __Pyx_PyDict_ContainsTF(PyObject* item, PyObject* dict, /* DictGetItem.proto */ #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY -static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { - PyObject *value; - value = PyDict_GetItemWithError(d, key); - if (unlikely(!value)) { - if (!PyErr_Occurred()) { - PyObject* args = PyTuple_Pack(1, key); - if (likely(args)) - PyErr_SetObject(PyExc_KeyError, args); - Py_XDECREF(args); - } - return NULL; - } - Py_INCREF(value); - return value; -} +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key); +#define __Pyx_PyObject_Dict_GetItem(obj, name)\ + (likely(PyDict_CheckExact(obj)) ?\ + __Pyx_PyDict_GetItem(obj, name) : PyObject_GetItem(obj, name)) #else - #define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) +#define __Pyx_PyObject_Dict_GetItem(obj, name) PyObject_GetItem(obj, name) #endif /* SetItemInt.proto */ @@ -1640,6 +1663,13 @@ static PyObject *__pyx_array_get_memview(struct __pyx_array_obj *); /*proto*/ /* GetAttr.proto */ static CYTHON_INLINE PyObject *__Pyx_GetAttr(PyObject *, PyObject *); +/* ObjectGetItem.proto */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key); +#else +#define __Pyx_PyObject_GetItem(obj, key) PyObject_GetItem(obj, key) +#endif + /* decode_c_string_utf16.proto */ static CYTHON_INLINE PyObject *__Pyx_PyUnicode_DecodeUTF16(const char *s, Py_ssize_t size, const char *errors) { int byteorder = 0; @@ -1674,6 +1704,19 @@ static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, /* Import.proto */ static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level); +/* FastTypeChecks.proto */ +#if CYTHON_COMPILING_IN_CPYTHON +#define __Pyx_TypeCheck(obj, type) __Pyx_IsSubtype(Py_TYPE(obj), (PyTypeObject *)type) +static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b); +static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches(PyObject *err, PyObject *type); +static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObject *type1, PyObject *type2); +#else +#define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type) +#define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) +#define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) +#endif +#define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) + static CYTHON_UNUSED int __pyx_memoryview_getbuffer(PyObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags); /*proto*/ /* ListCompAppend.proto */ #if CYTHON_USE_PYLIST_INTERNALS && CYTHON_ASSUME_SAFE_MACROS @@ -1727,6 +1770,20 @@ static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name); /* HasAttr.proto */ static CYTHON_INLINE int __Pyx_HasAttr(PyObject *, PyObject *); +/* PyObject_GenericGetAttrNoDict.proto */ +#if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static CYTHON_INLINE PyObject* __Pyx_PyObject_GenericGetAttrNoDict(PyObject* obj, PyObject* attr_name); +#else +#define __Pyx_PyObject_GenericGetAttrNoDict PyObject_GenericGetAttr +#endif + +/* PyObject_GenericGetAttr.proto */ +#if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static PyObject* __Pyx_PyObject_GenericGetAttr(PyObject* obj, PyObject* attr_name); +#else +#define __Pyx_PyObject_GenericGetAttr PyObject_GenericGetAttr +#endif + /* SetVTable.proto */ static int __Pyx_SetVtable(PyObject *dict, void *vtable); @@ -1738,7 +1795,6 @@ static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type); /* CythonFunction.proto */ #define __Pyx_CyFunction_USED 1 -#include #define __Pyx_CYFUNCTION_STATICMETHOD 0x01 #define __Pyx_CYFUNCTION_CLASSMETHOD 0x02 #define __Pyx_CYFUNCTION_CCLASS 0x04 @@ -1999,18 +2055,6 @@ static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *); /* CIntFromPy.proto */ static CYTHON_INLINE char __Pyx_PyInt_As_char(PyObject *); -/* FastTypeChecks.proto */ -#if CYTHON_COMPILING_IN_CPYTHON -#define __Pyx_TypeCheck(obj, type) __Pyx_IsSubtype(Py_TYPE(obj), (PyTypeObject *)type) -static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b); -static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches(PyObject *err, PyObject *type); -static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObject *type1, PyObject *type2); -#else -#define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type) -#define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) -#define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) -#endif - /* IsLittleEndian.proto */ static CYTHON_INLINE int __Pyx_Is_Little_Endian(void); @@ -2035,16 +2079,16 @@ static int __Pyx_ValidateAndInit_memviewslice( PyObject *original_obj); /* ObjectToMemviewSlice.proto */ -static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_double(PyObject *); +static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_double(PyObject *, int writable_flag); /* ObjectToMemviewSlice.proto */ -static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_float(PyObject *); +static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_float(PyObject *, int writable_flag); /* ObjectToMemviewSlice.proto */ -static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_double(PyObject *); +static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_double(PyObject *, int writable_flag); /* ObjectToMemviewSlice.proto */ -static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_float(PyObject *); +static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_float(PyObject *, int writable_flag); /* CheckBinaryVersion.proto */ static int __Pyx_check_binary_version(void); @@ -2297,6 +2341,8 @@ static const char __pyx_k_numpy_core_multiarray_failed_to[] = "numpy.core.multia static const char __pyx_k_unknown_dtype_code_in_numpy_pxd[] = "unknown dtype code in numpy.pxd (%d)"; static const char __pyx_k_Buffer_view_does_not_expose_stri[] = "Buffer view does not expose strides"; static const char __pyx_k_Can_only_create_a_buffer_that_is[] = "Can only create a buffer that is contiguous in memory."; +static const char __pyx_k_Cannot_assign_to_read_only_memor[] = "Cannot assign to read-only memoryview"; +static const char __pyx_k_Cannot_create_writable_memory_vi[] = "Cannot create writable memory view from read-only memoryview"; static const char __pyx_k_Empty_shape_tuple_for_cython_arr[] = "Empty shape tuple for cython.array"; static const char __pyx_k_Expected_at_least_d_argument_s_g[] = "Expected at least %d argument%s, got %d"; static const char __pyx_k_Format_string_allocated_too_shor[] = "Format string allocated too short, see comment in numpy.pxd"; @@ -2316,6 +2362,8 @@ static const char __pyx_k_Format_string_allocated_too_shor_2[] = "Format string static PyObject *__pyx_n_s_ASCII; static PyObject *__pyx_kp_s_Buffer_view_does_not_expose_stri; static PyObject *__pyx_kp_s_Can_only_create_a_buffer_that_is; +static PyObject *__pyx_kp_s_Cannot_assign_to_read_only_memor; +static PyObject *__pyx_kp_s_Cannot_create_writable_memory_vi; static PyObject *__pyx_kp_s_Cannot_index_with_type_s; static PyObject *__pyx_n_s_Ellipsis; static PyObject *__pyx_kp_s_Empty_shape_tuple_for_cython_arr; @@ -2510,9 +2558,9 @@ static PyObject *__pyx_tuple__6; static PyObject *__pyx_tuple__7; static PyObject *__pyx_tuple__8; static PyObject *__pyx_tuple__9; -static PyObject *__pyx_slice__31; -static PyObject *__pyx_slice__32; static PyObject *__pyx_slice__33; +static PyObject *__pyx_slice__34; +static PyObject *__pyx_slice__35; static PyObject *__pyx_tuple__10; static PyObject *__pyx_tuple__11; static PyObject *__pyx_tuple__12; @@ -2534,28 +2582,31 @@ static PyObject *__pyx_tuple__27; static PyObject *__pyx_tuple__28; static PyObject *__pyx_tuple__29; static PyObject *__pyx_tuple__30; -static PyObject *__pyx_tuple__34; -static PyObject *__pyx_tuple__35; +static PyObject *__pyx_tuple__31; +static PyObject *__pyx_tuple__32; static PyObject *__pyx_tuple__36; static PyObject *__pyx_tuple__37; +static PyObject *__pyx_tuple__38; static PyObject *__pyx_tuple__39; static PyObject *__pyx_tuple__41; static PyObject *__pyx_tuple__43; static PyObject *__pyx_tuple__45; static PyObject *__pyx_tuple__47; static PyObject *__pyx_tuple__49; -static PyObject *__pyx_tuple__50; static PyObject *__pyx_tuple__51; static PyObject *__pyx_tuple__52; static PyObject *__pyx_tuple__53; static PyObject *__pyx_tuple__54; -static PyObject *__pyx_codeobj__38; +static PyObject *__pyx_tuple__55; +static PyObject *__pyx_tuple__56; static PyObject *__pyx_codeobj__40; static PyObject *__pyx_codeobj__42; static PyObject *__pyx_codeobj__44; static PyObject *__pyx_codeobj__46; static PyObject *__pyx_codeobj__48; -static PyObject *__pyx_codeobj__55; +static PyObject *__pyx_codeobj__50; +static PyObject *__pyx_codeobj__57; +/* Late includes */ /* "gensim/_matutils.pyx":14 * @@ -2592,11 +2643,11 @@ static PyObject *__pyx_pw_6gensim_9_matutils_1mean_absolute_difference(PyObject kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_a)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_a)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_b)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_b)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("mean_absolute_difference", 1, 2, 2, 1); __PYX_ERR(0, 14, __pyx_L3_error) } @@ -2659,7 +2710,7 @@ static PyObject *__pyx_pf_6gensim_9_matutils_mean_absolute_difference(CYTHON_UNU __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(0, 30, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (__pyx_t_4) { + if (unlikely(__pyx_t_4)) { /* "gensim/_matutils.pyx":31 * """ @@ -2712,10 +2763,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_mean_absolute_difference(CYTHON_UNU * return _mean_absolute_difference[float](a, b) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_5 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_a); - if (unlikely(!__pyx_t_5.memview)) __PYX_ERR(0, 34, __pyx_L1_error) - __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_b); - if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 34, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_a, PyBUF_WRITABLE); if (unlikely(!__pyx_t_5.memview)) __PYX_ERR(0, 34, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_b, PyBUF_WRITABLE); if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 34, __pyx_L1_error) __pyx_t_2 = PyFloat_FromDouble(__pyx_fuse_1__pyx_f_6gensim_9_matutils__mean_absolute_difference(__pyx_t_5, __pyx_t_6)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 34, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __PYX_XDEC_MEMVIEW(&__pyx_t_5, 1); @@ -2766,10 +2815,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_mean_absolute_difference(CYTHON_UNU * return _mean_absolute_difference[float](a.astype(np.float32), b.astype(np.float32)) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_a); - if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 36, __pyx_L1_error) - __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_b); - if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 36, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_a, PyBUF_WRITABLE); if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 36, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_b, PyBUF_WRITABLE); if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 36, __pyx_L1_error) __pyx_t_1 = PyFloat_FromDouble(__pyx_fuse_0__pyx_f_6gensim_9_matutils__mean_absolute_difference(__pyx_t_7, __pyx_t_8)); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __PYX_XDEC_MEMVIEW(&__pyx_t_7, 1); @@ -2873,8 +2920,7 @@ static PyObject *__pyx_pf_6gensim_9_matutils_mean_absolute_difference(CYTHON_UNU } } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_t_3); - if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 38, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_t_3, PyBUF_WRITABLE); if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_b, __pyx_n_s_astype); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); @@ -2929,8 +2975,7 @@ static PyObject *__pyx_pf_6gensim_9_matutils_mean_absolute_difference(CYTHON_UNU } } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_t_3); - if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 38, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_t_3, PyBUF_WRITABLE); if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = PyFloat_FromDouble(__pyx_fuse_0__pyx_f_6gensim_9_matutils__mean_absolute_difference(__pyx_t_8, __pyx_t_7)); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); @@ -3000,6 +3045,7 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__mean_absolute_difference(__ size_t __pyx_t_2; size_t __pyx_t_3; size_t __pyx_t_4; + size_t __pyx_t_5; /* "gensim/_matutils.pyx":61 * """ @@ -3036,8 +3082,9 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__mean_absolute_difference(__ * result /= N */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":69 * @@ -3046,9 +3093,9 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__mean_absolute_difference(__ * result /= N * */ - __pyx_t_3 = __pyx_v_i; __pyx_t_4 = __pyx_v_i; - __pyx_v_result = (__pyx_v_result + fabs(((*((float *) ( /* dim=0 */ (__pyx_v_a.data + __pyx_t_3 * __pyx_v_a.strides[0]) ))) - (*((float *) ( /* dim=0 */ (__pyx_v_b.data + __pyx_t_4 * __pyx_v_b.strides[0]) )))))); + __pyx_t_5 = __pyx_v_i; + __pyx_v_result = (__pyx_v_result + fabs(((*((float *) ( /* dim=0 */ (__pyx_v_a.data + __pyx_t_4 * __pyx_v_a.strides[0]) ))) - (*((float *) ( /* dim=0 */ (__pyx_v_b.data + __pyx_t_5 * __pyx_v_b.strides[0]) )))))); } /* "gensim/_matutils.pyx":70 @@ -3093,6 +3140,7 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__mean_absolute_difference(_ size_t __pyx_t_2; size_t __pyx_t_3; size_t __pyx_t_4; + size_t __pyx_t_5; /* "gensim/_matutils.pyx":61 * """ @@ -3129,8 +3177,9 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__mean_absolute_difference(_ * result /= N */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":69 * @@ -3139,9 +3188,9 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__mean_absolute_difference(_ * result /= N * */ - __pyx_t_3 = __pyx_v_i; __pyx_t_4 = __pyx_v_i; - __pyx_v_result = (__pyx_v_result + fabs(((*((double *) ( /* dim=0 */ (__pyx_v_a.data + __pyx_t_3 * __pyx_v_a.strides[0]) ))) - (*((double *) ( /* dim=0 */ (__pyx_v_b.data + __pyx_t_4 * __pyx_v_b.strides[0]) )))))); + __pyx_t_5 = __pyx_v_i; + __pyx_v_result = (__pyx_v_result + fabs(((*((double *) ( /* dim=0 */ (__pyx_v_a.data + __pyx_t_4 * __pyx_v_a.strides[0]) ))) - (*((double *) ( /* dim=0 */ (__pyx_v_b.data + __pyx_t_5 * __pyx_v_b.strides[0]) )))))); } /* "gensim/_matutils.pyx":70 @@ -3241,8 +3290,7 @@ static PyObject *__pyx_pf_6gensim_9_matutils_2logsumexp(CYTHON_UNUSED PyObject * * return _logsumexp_2d[float](x) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_5 = __Pyx_PyObject_to_MemoryviewSlice_dsds_double(__pyx_v_x); - if (unlikely(!__pyx_t_5.memview)) __PYX_ERR(0, 95, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_to_MemoryviewSlice_dsds_double(__pyx_v_x, PyBUF_WRITABLE); if (unlikely(!__pyx_t_5.memview)) __PYX_ERR(0, 95, __pyx_L1_error) __pyx_t_2 = PyFloat_FromDouble(__pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__pyx_t_5)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 95, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __PYX_XDEC_MEMVIEW(&__pyx_t_5, 1); @@ -3290,8 +3338,7 @@ static PyObject *__pyx_pf_6gensim_9_matutils_2logsumexp(CYTHON_UNUSED PyObject * * return _logsumexp_2d[float](x.astype(np.float32)) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_x); - if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 97, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_x, PyBUF_WRITABLE); if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 97, __pyx_L1_error) __pyx_t_3 = PyFloat_FromDouble(__pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__pyx_t_6)); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 97, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __PYX_XDEC_MEMVIEW(&__pyx_t_6, 1); @@ -3392,8 +3439,7 @@ static PyObject *__pyx_pf_6gensim_9_matutils_2logsumexp(CYTHON_UNUSED PyObject * } } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_t_1); - if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 99, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_t_1, PyBUF_WRITABLE); if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 99, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_t_1 = PyFloat_FromDouble(__pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__pyx_t_6)); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 99, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); @@ -3464,11 +3510,13 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews size_t __pyx_t_6; size_t __pyx_t_7; size_t __pyx_t_8; - int __pyx_t_9; + size_t __pyx_t_9; size_t __pyx_t_10; - size_t __pyx_t_11; + int __pyx_t_11; size_t __pyx_t_12; size_t __pyx_t_13; + size_t __pyx_t_14; + size_t __pyx_t_15; /* "gensim/_matutils.pyx":120 * """ @@ -3516,8 +3564,9 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * if data[i, j] > max_val: */ __pyx_t_3 = __pyx_v_I; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_i = __pyx_t_4; + __pyx_t_4 = __pyx_t_3; + for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { + __pyx_v_i = __pyx_t_5; /* "gensim/_matutils.pyx":129 * @@ -3526,9 +3575,10 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * if data[i, j] > max_val: * max_val = data[i, j] */ - __pyx_t_5 = __pyx_v_J; - for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { - __pyx_v_j = __pyx_t_6; + __pyx_t_6 = __pyx_v_J; + __pyx_t_7 = __pyx_t_6; + for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_7; __pyx_t_8+=1) { + __pyx_v_j = __pyx_t_8; /* "gensim/_matutils.pyx":130 * for i in range(I): @@ -3537,10 +3587,10 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * max_val = data[i, j] * */ - __pyx_t_7 = __pyx_v_i; - __pyx_t_8 = __pyx_v_j; - __pyx_t_9 = (((*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_7 * __pyx_v_data.strides[0]) ) + __pyx_t_8 * __pyx_v_data.strides[1]) ))) > __pyx_v_max_val) != 0); - if (__pyx_t_9) { + __pyx_t_9 = __pyx_v_i; + __pyx_t_10 = __pyx_v_j; + __pyx_t_11 = (((*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_9 * __pyx_v_data.strides[0]) ) + __pyx_t_10 * __pyx_v_data.strides[1]) ))) > __pyx_v_max_val) != 0); + if (__pyx_t_11) { /* "gensim/_matutils.pyx":131 * for j in range(J): @@ -3549,9 +3599,9 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * * for i in range(I): */ - __pyx_t_10 = __pyx_v_i; - __pyx_t_11 = __pyx_v_j; - __pyx_v_max_val = (*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_10 * __pyx_v_data.strides[0]) ) + __pyx_t_11 * __pyx_v_data.strides[1]) ))); + __pyx_t_12 = __pyx_v_i; + __pyx_t_13 = __pyx_v_j; + __pyx_v_max_val = (*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_12 * __pyx_v_data.strides[0]) ) + __pyx_t_13 * __pyx_v_data.strides[1]) ))); /* "gensim/_matutils.pyx":130 * for i in range(I): @@ -3572,8 +3622,9 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * result += exp(data[i, j] - max_val) */ __pyx_t_3 = __pyx_v_I; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_i = __pyx_t_4; + __pyx_t_4 = __pyx_t_3; + for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { + __pyx_v_i = __pyx_t_5; /* "gensim/_matutils.pyx":134 * @@ -3582,9 +3633,10 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * result += exp(data[i, j] - max_val) * */ - __pyx_t_5 = __pyx_v_J; - for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { - __pyx_v_j = __pyx_t_6; + __pyx_t_6 = __pyx_v_J; + __pyx_t_7 = __pyx_t_6; + for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_7; __pyx_t_8+=1) { + __pyx_v_j = __pyx_t_8; /* "gensim/_matutils.pyx":135 * for i in range(I): @@ -3593,9 +3645,9 @@ static float __pyx_fuse_0__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memviews * * result = log(result) + max_val */ - __pyx_t_12 = __pyx_v_i; - __pyx_t_13 = __pyx_v_j; - __pyx_v_result = (__pyx_v_result + exp(((*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_12 * __pyx_v_data.strides[0]) ) + __pyx_t_13 * __pyx_v_data.strides[1]) ))) - __pyx_v_max_val))); + __pyx_t_14 = __pyx_v_i; + __pyx_t_15 = __pyx_v_j; + __pyx_v_result = (__pyx_v_result + exp(((*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_14 * __pyx_v_data.strides[0]) ) + __pyx_t_15 * __pyx_v_data.strides[1]) ))) - __pyx_v_max_val))); } } @@ -3647,11 +3699,13 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview size_t __pyx_t_6; size_t __pyx_t_7; size_t __pyx_t_8; - int __pyx_t_9; + size_t __pyx_t_9; size_t __pyx_t_10; - size_t __pyx_t_11; + int __pyx_t_11; size_t __pyx_t_12; size_t __pyx_t_13; + size_t __pyx_t_14; + size_t __pyx_t_15; /* "gensim/_matutils.pyx":120 * """ @@ -3699,8 +3753,9 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * if data[i, j] > max_val: */ __pyx_t_3 = __pyx_v_I; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_i = __pyx_t_4; + __pyx_t_4 = __pyx_t_3; + for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { + __pyx_v_i = __pyx_t_5; /* "gensim/_matutils.pyx":129 * @@ -3709,9 +3764,10 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * if data[i, j] > max_val: * max_val = data[i, j] */ - __pyx_t_5 = __pyx_v_J; - for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { - __pyx_v_j = __pyx_t_6; + __pyx_t_6 = __pyx_v_J; + __pyx_t_7 = __pyx_t_6; + for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_7; __pyx_t_8+=1) { + __pyx_v_j = __pyx_t_8; /* "gensim/_matutils.pyx":130 * for i in range(I): @@ -3720,10 +3776,10 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * max_val = data[i, j] * */ - __pyx_t_7 = __pyx_v_i; - __pyx_t_8 = __pyx_v_j; - __pyx_t_9 = (((*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_7 * __pyx_v_data.strides[0]) ) + __pyx_t_8 * __pyx_v_data.strides[1]) ))) > __pyx_v_max_val) != 0); - if (__pyx_t_9) { + __pyx_t_9 = __pyx_v_i; + __pyx_t_10 = __pyx_v_j; + __pyx_t_11 = (((*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_9 * __pyx_v_data.strides[0]) ) + __pyx_t_10 * __pyx_v_data.strides[1]) ))) > __pyx_v_max_val) != 0); + if (__pyx_t_11) { /* "gensim/_matutils.pyx":131 * for j in range(J): @@ -3732,9 +3788,9 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * * for i in range(I): */ - __pyx_t_10 = __pyx_v_i; - __pyx_t_11 = __pyx_v_j; - __pyx_v_max_val = (*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_10 * __pyx_v_data.strides[0]) ) + __pyx_t_11 * __pyx_v_data.strides[1]) ))); + __pyx_t_12 = __pyx_v_i; + __pyx_t_13 = __pyx_v_j; + __pyx_v_max_val = (*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_12 * __pyx_v_data.strides[0]) ) + __pyx_t_13 * __pyx_v_data.strides[1]) ))); /* "gensim/_matutils.pyx":130 * for i in range(I): @@ -3755,8 +3811,9 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * result += exp(data[i, j] - max_val) */ __pyx_t_3 = __pyx_v_I; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_i = __pyx_t_4; + __pyx_t_4 = __pyx_t_3; + for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { + __pyx_v_i = __pyx_t_5; /* "gensim/_matutils.pyx":134 * @@ -3765,9 +3822,10 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * result += exp(data[i, j] - max_val) * */ - __pyx_t_5 = __pyx_v_J; - for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { - __pyx_v_j = __pyx_t_6; + __pyx_t_6 = __pyx_v_J; + __pyx_t_7 = __pyx_t_6; + for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_7; __pyx_t_8+=1) { + __pyx_v_j = __pyx_t_8; /* "gensim/_matutils.pyx":135 * for i in range(I): @@ -3776,9 +3834,9 @@ static double __pyx_fuse_1__pyx_f_6gensim_9_matutils__logsumexp_2d(__Pyx_memview * * result = log(result) + max_val */ - __pyx_t_12 = __pyx_v_i; - __pyx_t_13 = __pyx_v_j; - __pyx_v_result = (__pyx_v_result + exp(((*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_12 * __pyx_v_data.strides[0]) ) + __pyx_t_13 * __pyx_v_data.strides[1]) ))) - __pyx_v_max_val))); + __pyx_t_14 = __pyx_v_i; + __pyx_t_15 = __pyx_v_j; + __pyx_v_result = (__pyx_v_result + exp(((*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_data.data + __pyx_t_14 * __pyx_v_data.strides[0]) ) + __pyx_t_15 * __pyx_v_data.strides[1]) ))) - __pyx_v_max_val))); } } @@ -4110,10 +4168,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_6dirichlet_expectation_2d(CYTHON_UN * elif alpha.dtype == np.float32: * out = np.zeros(alpha.shape, dtype=alpha.dtype) */ - __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_dsds_double(__pyx_v_alpha); - if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 182, __pyx_L1_error) - __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_dsds_double(__pyx_v_out); - if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 182, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_dsds_double(__pyx_v_alpha, PyBUF_WRITABLE); if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 182, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_dsds_double(__pyx_v_out, PyBUF_WRITABLE); if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 182, __pyx_L1_error) __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__pyx_t_6, __pyx_t_7); __PYX_XDEC_MEMVIEW(&__pyx_t_6, 1); __pyx_t_6.memview = NULL; @@ -4193,10 +4249,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_6dirichlet_expectation_2d(CYTHON_UN * elif alpha.dtype == np.float16: * out = np.zeros(alpha.shape, dtype=np.float32) */ - __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_alpha); - if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 185, __pyx_L1_error) - __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_out); - if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 185, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_alpha, PyBUF_WRITABLE); if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 185, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_out, PyBUF_WRITABLE); if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 185, __pyx_L1_error) __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__pyx_t_8, __pyx_t_9); __PYX_XDEC_MEMVIEW(&__pyx_t_8, 1); __pyx_t_8.memview = NULL; @@ -4332,11 +4386,9 @@ static PyObject *__pyx_pf_6gensim_9_matutils_6dirichlet_expectation_2d(CYTHON_UN } } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_t_10); - if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 188, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_t_10, PyBUF_WRITABLE); if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 188, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_out); - if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 188, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_dsds_float(__pyx_v_out, PyBUF_WRITABLE); if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 188, __pyx_L1_error) __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__pyx_t_9, __pyx_t_8); __PYX_XDEC_MEMVIEW(&__pyx_t_9, 1); __pyx_t_9.memview = NULL; @@ -4559,10 +4611,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_8dirichlet_expectation_1d(CYTHON_UN * elif alpha.dtype == np.float32: * out = np.zeros(alpha.shape, dtype=alpha.dtype) */ - __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_alpha); - if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 211, __pyx_L1_error) - __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_out); - if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 211, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_alpha, PyBUF_WRITABLE); if (unlikely(!__pyx_t_6.memview)) __PYX_ERR(0, 211, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyObject_to_MemoryviewSlice_ds_double(__pyx_v_out, PyBUF_WRITABLE); if (unlikely(!__pyx_t_7.memview)) __PYX_ERR(0, 211, __pyx_L1_error) __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__pyx_t_6, __pyx_t_7); __PYX_XDEC_MEMVIEW(&__pyx_t_6, 1); __pyx_t_6.memview = NULL; @@ -4642,10 +4692,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_8dirichlet_expectation_1d(CYTHON_UN * elif alpha.dtype == np.float16: * out = np.zeros(alpha.shape, dtype=np.float32) */ - __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_alpha); - if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 214, __pyx_L1_error) - __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_out); - if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 214, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_alpha, PyBUF_WRITABLE); if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 214, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_out, PyBUF_WRITABLE); if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 214, __pyx_L1_error) __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__pyx_t_8, __pyx_t_9); __PYX_XDEC_MEMVIEW(&__pyx_t_8, 1); __pyx_t_8.memview = NULL; @@ -4781,11 +4829,9 @@ static PyObject *__pyx_pf_6gensim_9_matutils_8dirichlet_expectation_1d(CYTHON_UN } } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_t_10); - if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 217, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_t_10, PyBUF_WRITABLE); if (unlikely(!__pyx_t_9.memview)) __PYX_ERR(0, 217, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_out); - if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 217, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_to_MemoryviewSlice_ds_float(__pyx_v_out, PyBUF_WRITABLE); if (unlikely(!__pyx_t_8.memview)) __PYX_ERR(0, 217, __pyx_L1_error) __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__pyx_t_9, __pyx_t_8); __PYX_XDEC_MEMVIEW(&__pyx_t_9, 1); __pyx_t_9.memview = NULL; @@ -4926,6 +4972,7 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P size_t __pyx_t_3; size_t __pyx_t_4; size_t __pyx_t_5; + size_t __pyx_t_6; /* "gensim/_matutils.pyx":237 * @@ -4962,8 +5009,9 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":243 * @@ -4972,8 +5020,8 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * * psi_sum_alpha = _digamma(sum_alpha) */ - __pyx_t_3 = __pyx_v_i; - __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((float *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_3 * __pyx_v_alpha.strides[0]) )))); + __pyx_t_4 = __pyx_v_i; + __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((float *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_4 * __pyx_v_alpha.strides[0]) )))); } /* "gensim/_matutils.pyx":245 @@ -4993,8 +5041,9 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":248 * @@ -5003,9 +5052,9 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * * */ - __pyx_t_4 = __pyx_v_i; __pyx_t_5 = __pyx_v_i; - *((float *) ( /* dim=0 */ (__pyx_v_out.data + __pyx_t_5 * __pyx_v_out.strides[0]) )) = (__pyx_fuse_0__pyx_f_6gensim_9_matutils__digamma((*((float *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_4 * __pyx_v_alpha.strides[0]) )))) - __pyx_v_psi_sum_alpha); + __pyx_t_6 = __pyx_v_i; + *((float *) ( /* dim=0 */ (__pyx_v_out.data + __pyx_t_6 * __pyx_v_out.strides[0]) )) = (__pyx_fuse_0__pyx_f_6gensim_9_matutils__digamma((*((float *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_5 * __pyx_v_alpha.strides[0]) )))) - __pyx_v_psi_sum_alpha); } /* "gensim/_matutils.pyx":225 @@ -5029,6 +5078,7 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P size_t __pyx_t_3; size_t __pyx_t_4; size_t __pyx_t_5; + size_t __pyx_t_6; /* "gensim/_matutils.pyx":237 * @@ -5065,8 +5115,9 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":243 * @@ -5075,8 +5126,8 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * * psi_sum_alpha = _digamma(sum_alpha) */ - __pyx_t_3 = __pyx_v_i; - __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((double *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_3 * __pyx_v_alpha.strides[0]) )))); + __pyx_t_4 = __pyx_v_i; + __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((double *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_4 * __pyx_v_alpha.strides[0]) )))); } /* "gensim/_matutils.pyx":245 @@ -5096,8 +5147,9 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":248 * @@ -5106,9 +5158,9 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_1d(__P * * */ - __pyx_t_4 = __pyx_v_i; __pyx_t_5 = __pyx_v_i; - *((double *) ( /* dim=0 */ (__pyx_v_out.data + __pyx_t_5 * __pyx_v_out.strides[0]) )) = (__pyx_fuse_1__pyx_f_6gensim_9_matutils__digamma((*((double *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_4 * __pyx_v_alpha.strides[0]) )))) - __pyx_v_psi_sum_alpha); + __pyx_t_6 = __pyx_v_i; + *((double *) ( /* dim=0 */ (__pyx_v_out.data + __pyx_t_6 * __pyx_v_out.strides[0]) )) = (__pyx_fuse_1__pyx_f_6gensim_9_matutils__digamma((*((double *) ( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_5 * __pyx_v_alpha.strides[0]) )))) - __pyx_v_psi_sum_alpha); } /* "gensim/_matutils.pyx":225 @@ -5147,6 +5199,8 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P size_t __pyx_t_8; size_t __pyx_t_9; size_t __pyx_t_10; + size_t __pyx_t_11; + size_t __pyx_t_12; /* "gensim/_matutils.pyx":265 * @@ -5192,8 +5246,9 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * for j in range(J): */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":272 * @@ -5211,9 +5266,10 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * sum_alpha += alpha[i, j] * */ - __pyx_t_3 = __pyx_v_J; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_j = __pyx_t_4; + __pyx_t_4 = __pyx_v_J; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_j = __pyx_t_6; /* "gensim/_matutils.pyx":274 * sum_alpha = 0.0 @@ -5222,9 +5278,9 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * * psi_sum_alpha = _digamma(sum_alpha) */ - __pyx_t_5 = __pyx_v_i; - __pyx_t_6 = __pyx_v_j; - __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_5 * __pyx_v_alpha.strides[0]) ) + __pyx_t_6 * __pyx_v_alpha.strides[1]) )))); + __pyx_t_7 = __pyx_v_i; + __pyx_t_8 = __pyx_v_j; + __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_7 * __pyx_v_alpha.strides[0]) ) + __pyx_t_8 * __pyx_v_alpha.strides[1]) )))); } /* "gensim/_matutils.pyx":276 @@ -5243,9 +5299,10 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * out[i, j] = _digamma(alpha[i, j]) - psi_sum_alpha * */ - __pyx_t_3 = __pyx_v_J; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_j = __pyx_t_4; + __pyx_t_4 = __pyx_v_J; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_j = __pyx_t_6; /* "gensim/_matutils.pyx":279 * @@ -5254,11 +5311,11 @@ static void __pyx_fuse_0__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * * */ - __pyx_t_7 = __pyx_v_i; - __pyx_t_8 = __pyx_v_j; __pyx_t_9 = __pyx_v_i; __pyx_t_10 = __pyx_v_j; - *((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_out.data + __pyx_t_9 * __pyx_v_out.strides[0]) ) + __pyx_t_10 * __pyx_v_out.strides[1]) )) = (__pyx_fuse_0__pyx_f_6gensim_9_matutils__digamma((*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_7 * __pyx_v_alpha.strides[0]) ) + __pyx_t_8 * __pyx_v_alpha.strides[1]) )))) - __pyx_v_psi_sum_alpha); + __pyx_t_11 = __pyx_v_i; + __pyx_t_12 = __pyx_v_j; + *((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_out.data + __pyx_t_11 * __pyx_v_out.strides[0]) ) + __pyx_t_12 * __pyx_v_out.strides[1]) )) = (__pyx_fuse_0__pyx_f_6gensim_9_matutils__digamma((*((float *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_9 * __pyx_v_alpha.strides[0]) ) + __pyx_t_10 * __pyx_v_alpha.strides[1]) )))) - __pyx_v_psi_sum_alpha); } } @@ -5290,6 +5347,8 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P size_t __pyx_t_8; size_t __pyx_t_9; size_t __pyx_t_10; + size_t __pyx_t_11; + size_t __pyx_t_12; /* "gensim/_matutils.pyx":265 * @@ -5335,8 +5394,9 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * for j in range(J): */ __pyx_t_1 = __pyx_v_I; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; /* "gensim/_matutils.pyx":272 * @@ -5354,9 +5414,10 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * sum_alpha += alpha[i, j] * */ - __pyx_t_3 = __pyx_v_J; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_j = __pyx_t_4; + __pyx_t_4 = __pyx_v_J; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_j = __pyx_t_6; /* "gensim/_matutils.pyx":274 * sum_alpha = 0.0 @@ -5365,9 +5426,9 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * * psi_sum_alpha = _digamma(sum_alpha) */ - __pyx_t_5 = __pyx_v_i; - __pyx_t_6 = __pyx_v_j; - __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_5 * __pyx_v_alpha.strides[0]) ) + __pyx_t_6 * __pyx_v_alpha.strides[1]) )))); + __pyx_t_7 = __pyx_v_i; + __pyx_t_8 = __pyx_v_j; + __pyx_v_sum_alpha = (__pyx_v_sum_alpha + (*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_7 * __pyx_v_alpha.strides[0]) ) + __pyx_t_8 * __pyx_v_alpha.strides[1]) )))); } /* "gensim/_matutils.pyx":276 @@ -5386,9 +5447,10 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * out[i, j] = _digamma(alpha[i, j]) - psi_sum_alpha * */ - __pyx_t_3 = __pyx_v_J; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_j = __pyx_t_4; + __pyx_t_4 = __pyx_v_J; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_j = __pyx_t_6; /* "gensim/_matutils.pyx":279 * @@ -5397,11 +5459,11 @@ static void __pyx_fuse_1__pyx_f_6gensim_9_matutils__dirichlet_expectation_2d(__P * * */ - __pyx_t_7 = __pyx_v_i; - __pyx_t_8 = __pyx_v_j; __pyx_t_9 = __pyx_v_i; __pyx_t_10 = __pyx_v_j; - *((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_out.data + __pyx_t_9 * __pyx_v_out.strides[0]) ) + __pyx_t_10 * __pyx_v_out.strides[1]) )) = (__pyx_fuse_1__pyx_f_6gensim_9_matutils__digamma((*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_7 * __pyx_v_alpha.strides[0]) ) + __pyx_t_8 * __pyx_v_alpha.strides[1]) )))) - __pyx_v_psi_sum_alpha); + __pyx_t_11 = __pyx_v_i; + __pyx_t_12 = __pyx_v_j; + *((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_out.data + __pyx_t_11 * __pyx_v_out.strides[0]) ) + __pyx_t_12 * __pyx_v_out.strides[1]) )) = (__pyx_fuse_1__pyx_f_6gensim_9_matutils__digamma((*((double *) ( /* dim=1 */ (( /* dim=0 */ (__pyx_v_alpha.data + __pyx_t_9 * __pyx_v_alpha.strides[0]) ) + __pyx_t_10 * __pyx_v_alpha.strides[1]) )))) - __pyx_v_psi_sum_alpha); } } @@ -5457,23 +5519,23 @@ static PyObject *__pyx_pw_6gensim_9_matutils_11digamma(PyObject *__pyx_self, PyO kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_signatures)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_signatures)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_args)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_args)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_fused_cpdef", 1, 4, 4, 1); __PYX_ERR(0, 282, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_kwargs)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_kwargs)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_fused_cpdef", 1, 4, 4, 2); __PYX_ERR(0, 282, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: - if (likely((values[3] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_defaults)) != 0)) kw_args--; + if (likely((values[3] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_defaults)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_fused_cpdef", 1, 4, 4, 3); __PYX_ERR(0, 282, __pyx_L3_error) } @@ -5514,7 +5576,6 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ Py_ssize_t __pyx_v_i; CYTHON_UNUSED PyTypeObject *__pyx_v_ndarray = 0; CYTHON_UNUSED Py_ssize_t __pyx_v_itemsize; - CYTHON_UNUSED int __pyx_v_arg_is_pythran_compatible; PyObject *__pyx_v_arg = NULL; PyObject *__pyx_v_candidates = NULL; PyObject *__pyx_v_sig = NULL; @@ -5535,7 +5596,8 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ PyObject *__pyx_t_10 = NULL; Py_ssize_t __pyx_t_11; Py_ssize_t __pyx_t_12; - int __pyx_t_13; + Py_ssize_t __pyx_t_13; + int __pyx_t_14; __Pyx_RefNannySetupContext("digamma", 0); __Pyx_INCREF(__pyx_v_kwargs); __pyx_t_1 = PyList_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) @@ -5565,7 +5627,6 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ __pyx_v_ndarray = ((PyTypeObject*)__pyx_t_1); __pyx_t_1 = 0; __pyx_v_itemsize = -1L; - __pyx_v_arg_is_pythran_compatible = 0; if (unlikely(__pyx_v_args == Py_None)) { PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()"); __PYX_ERR(0, 282, __pyx_L1_error) @@ -5631,16 +5692,11 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ __pyx_t_1 = __Pyx_PyString_Format(__pyx_kp_s_Expected_at_least_d_argument_s_g, __pyx_t_6); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __pyx_t_6 = PyTuple_New(1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_CallOneArg(__pyx_builtin_TypeError, __pyx_t_1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_6, 0, __pyx_t_1); - __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_t_6, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_Raise(__pyx_t_6, 0, 0, 0); + __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; __PYX_ERR(0, 282, __pyx_L1_error) } __pyx_L6:; @@ -5655,44 +5711,45 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ goto __pyx_L10_break; } __pyx_L10_break:; - __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_v_candidates = ((PyObject*)__pyx_t_1); - __pyx_t_1 = 0; + __pyx_t_6 = PyList_New(0); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_6); + __pyx_v_candidates = ((PyObject*)__pyx_t_6); + __pyx_t_6 = 0; __pyx_t_5 = 0; if (unlikely(__pyx_v_signatures == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); __PYX_ERR(0, 282, __pyx_L1_error) } - __pyx_t_6 = __Pyx_dict_iterator(((PyObject*)__pyx_v_signatures), 1, ((PyObject *)NULL), (&__pyx_t_7), (&__pyx_t_8)); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); - __Pyx_XDECREF(__pyx_t_1); - __pyx_t_1 = __pyx_t_6; - __pyx_t_6 = 0; + __pyx_t_1 = __Pyx_dict_iterator(((PyObject*)__pyx_v_signatures), 1, ((PyObject *)NULL), (&__pyx_t_7), (&__pyx_t_8)); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_XDECREF(__pyx_t_6); + __pyx_t_6 = __pyx_t_1; + __pyx_t_1 = 0; while (1) { - __pyx_t_9 = __Pyx_dict_iter_next(__pyx_t_1, __pyx_t_7, &__pyx_t_5, &__pyx_t_6, NULL, NULL, __pyx_t_8); + __pyx_t_9 = __Pyx_dict_iter_next(__pyx_t_6, __pyx_t_7, &__pyx_t_5, &__pyx_t_1, NULL, NULL, __pyx_t_8); if (unlikely(__pyx_t_9 == 0)) break; if (unlikely(__pyx_t_9 == -1)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); - __Pyx_XDECREF_SET(__pyx_v_sig, __pyx_t_6); - __pyx_t_6 = 0; + __Pyx_GOTREF(__pyx_t_1); + __Pyx_XDECREF_SET(__pyx_v_sig, __pyx_t_1); + __pyx_t_1 = 0; __pyx_v_match_found = 0; - __pyx_t_6 = __Pyx_PyObject_GetAttrStr(__pyx_v_sig, __pyx_n_s_strip); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); - __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_6, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_sig, __pyx_n_s_strip); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__4, NULL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __pyx_t_6 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_split); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_10, __pyx_n_s_split); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_6, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_tuple__6, NULL); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_XDECREF_SET(__pyx_v_src_sig, __pyx_t_10); __pyx_t_10 = 0; __pyx_t_11 = PyList_GET_SIZE(__pyx_v_dest_sig); if (unlikely(__pyx_t_11 == ((Py_ssize_t)-1))) __PYX_ERR(0, 282, __pyx_L1_error) - for (__pyx_t_12 = 0; __pyx_t_12 < __pyx_t_11; __pyx_t_12+=1) { - __pyx_v_i = __pyx_t_12; + __pyx_t_12 = __pyx_t_11; + for (__pyx_t_13 = 0; __pyx_t_13 < __pyx_t_12; __pyx_t_13+=1) { + __pyx_v_i = __pyx_t_13; __pyx_t_10 = __Pyx_GetItemInt_List(__pyx_v_dest_sig, __pyx_v_i, Py_ssize_t, 1, PyInt_FromSsize_t, 1, 1, 1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_XDECREF_SET(__pyx_v_dst_type, __pyx_t_10); @@ -5702,10 +5759,10 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ if (__pyx_t_2) { __pyx_t_10 = __Pyx_GetItemInt(__pyx_v_src_sig, __pyx_v_i, Py_ssize_t, 1, PyInt_FromSsize_t, 0, 1, 1); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __pyx_t_6 = PyObject_RichCompare(__pyx_t_10, __pyx_v_dst_type, Py_EQ); __Pyx_XGOTREF(__pyx_t_6); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_1 = PyObject_RichCompare(__pyx_t_10, __pyx_v_dst_type, Py_EQ); __Pyx_XGOTREF(__pyx_t_1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_t_6); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; + __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_t_1); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; if (__pyx_t_2) { __pyx_v_match_found = 1; goto __pyx_L17; @@ -5720,26 +5777,26 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ __pyx_L15_break:; __pyx_t_2 = (__pyx_v_match_found != 0); if (__pyx_t_2) { - __pyx_t_13 = __Pyx_PyList_Append(__pyx_v_candidates, __pyx_v_sig); if (unlikely(__pyx_t_13 == ((int)-1))) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_14 = __Pyx_PyList_Append(__pyx_v_candidates, __pyx_v_sig); if (unlikely(__pyx_t_14 == ((int)-1))) __PYX_ERR(0, 282, __pyx_L1_error) } } - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_2 = (__pyx_v_candidates != Py_None) && (PyList_GET_SIZE(__pyx_v_candidates) != 0); + __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; + __pyx_t_2 = (PyList_GET_SIZE(__pyx_v_candidates) != 0); __pyx_t_3 = ((!__pyx_t_2) != 0); if (__pyx_t_3) { - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_Raise(__pyx_t_1, 0, 0, 0); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__7, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_6); + __Pyx_Raise(__pyx_t_6, 0, 0, 0); + __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; __PYX_ERR(0, 282, __pyx_L1_error) } __pyx_t_7 = PyList_GET_SIZE(__pyx_v_candidates); if (unlikely(__pyx_t_7 == ((Py_ssize_t)-1))) __PYX_ERR(0, 282, __pyx_L1_error) __pyx_t_3 = ((__pyx_t_7 > 1) != 0); if (__pyx_t_3) { - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_Raise(__pyx_t_1, 0, 0, 0); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__8, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_6); + __Pyx_Raise(__pyx_t_6, 0, 0, 0); + __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; __PYX_ERR(0, 282, __pyx_L1_error) } /*else*/ { @@ -5748,13 +5805,13 @@ static PyObject *__pyx_pf_6gensim_9_matutils_10digamma(CYTHON_UNUSED PyObject *_ PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); __PYX_ERR(0, 282, __pyx_L1_error) } - __pyx_t_1 = __Pyx_GetItemInt_List(__pyx_v_candidates, 0, long, 1, __Pyx_PyInt_From_long, 1, 0, 1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_6 = __Pyx_PyDict_GetItem(((PyObject*)__pyx_v_signatures), __pyx_t_1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_6 = __Pyx_GetItemInt_List(__pyx_v_candidates, 0, long, 1, __Pyx_PyInt_From_long, 1, 0, 1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_r = __pyx_t_6; - __pyx_t_6 = 0; + __pyx_t_1 = __Pyx_PyDict_GetItem(((PyObject*)__pyx_v_signatures), __pyx_t_6); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_1); + __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; + __pyx_r = __pyx_t_1; + __pyx_t_1 = 0; goto __pyx_L0; } @@ -6253,12 +6310,12 @@ static CYTHON_INLINE double __pyx_fuse_1__pyx_f_6gensim_9_matutils__digamma(doub return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* Python wrapper */ @@ -6275,7 +6332,6 @@ static CYTHON_UNUSED int __pyx_pw_5numpy_7ndarray_1__getbuffer__(PyObject *__pyx } static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, Py_buffer *__pyx_v_info, int __pyx_v_flags) { - int __pyx_v_copy_shape; int __pyx_v_i; int __pyx_v_ndim; int __pyx_v_endian_detector; @@ -6284,7 +6340,6 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P char *__pyx_v_f; PyArray_Descr *__pyx_v_descr = 0; int __pyx_v_offset; - int __pyx_v_hasfields; int __pyx_r; __Pyx_RefNannyDeclarations int __pyx_t_1; @@ -6292,38 +6347,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P PyObject *__pyx_t_3 = NULL; int __pyx_t_4; int __pyx_t_5; - PyObject *__pyx_t_6 = NULL; - char *__pyx_t_7; - __Pyx_RefNannySetupContext("__getbuffer__", 0); - if (__pyx_v_info != NULL) { - __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(__pyx_v_info->obj); - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":220 - * # of flags - * - * if info == NULL: return # <<<<<<<<<<<<<< - * - * cdef int copy_shape, i, ndim - */ - __pyx_t_1 = ((__pyx_v_info == NULL) != 0); - if (__pyx_t_1) { - __pyx_r = 0; - goto __pyx_L0; + int __pyx_t_6; + PyObject *__pyx_t_7 = NULL; + char *__pyx_t_8; + if (__pyx_v_info == NULL) { + PyErr_SetString(PyExc_BufferError, "PyObject_GetBuffer: view==NULL argument is obsolete"); + return -1; } + __Pyx_RefNannySetupContext("__getbuffer__", 0); + __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); + __Pyx_GIVEREF(__pyx_v_info->obj); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":222 * - * cdef int copy_shape, i, ndim + * cdef int i, ndim * cdef int endian_detector = 1 # <<<<<<<<<<<<<< * cdef bint little_endian = ((&endian_detector)[0] != 0) * */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":224 - * cdef int copy_shape, i, ndim + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":223 + * cdef int i, ndim * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< * @@ -6331,59 +6376,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":226 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":225 * cdef bint little_endian = ((&endian_detector)[0] != 0) * * ndim = PyArray_NDIM(self) # <<<<<<<<<<<<<< * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): + * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) */ __pyx_v_ndim = PyArray_NDIM(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 - * ndim = PyArray_NDIM(self) - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 - * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): - * copy_shape = 1 # <<<<<<<<<<<<<< - * else: - * copy_shape = 0 - */ - __pyx_v_copy_shape = 1; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 * ndim = PyArray_NDIM(self) * - * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< - * copy_shape = 1 - * else: - */ - goto __pyx_L4; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 - * copy_shape = 1 - * else: - * copy_shape = 0 # <<<<<<<<<<<<<< - * - * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) - */ - /*else*/ { - __pyx_v_copy_shape = 0; - } - __pyx_L4:; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 - * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") @@ -6392,10 +6396,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L6_bool_binop_done; + goto __pyx_L4_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":234 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":228 * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -6404,32 +6408,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_C_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L6_bool_binop_done:; + __pyx_L4_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__9, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 235, __pyx_L1_error) + __PYX_ERR(1, 229, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 - * copy_shape = 0 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":227 + * ndim = PyArray_NDIM(self) * * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): @@ -6437,7 +6441,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -6448,10 +6452,10 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L9_bool_binop_done; + goto __pyx_L7_bool_binop_done; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":238 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":232 * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): # <<<<<<<<<<<<<< @@ -6460,31 +6464,31 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((!(PyArray_CHKFLAGS(__pyx_v_self, NPY_F_CONTIGUOUS) != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L9_bool_binop_done:; + __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__10, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 239, __pyx_L1_error) + __PYX_ERR(1, 233, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":231 * raise ValueError(u"ndarray is not C contiguous") * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) # <<<<<<<<<<<<<< @@ -6493,35 +6497,35 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 * raise ValueError(u"ndarray is not Fortran contiguous") * * info.buf = PyArray_DATA(self) # <<<<<<<<<<<<<< * info.ndim = ndim - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): */ __pyx_v_info->buf = PyArray_DATA(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":236 * * info.buf = PyArray_DATA(self) * info.ndim = ndim # <<<<<<<<<<<<<< - * if copy_shape: + * if sizeof(npy_intp) != sizeof(Py_ssize_t): * # Allocate new buffer for strides and shape info. */ __pyx_v_info->ndim = __pyx_v_ndim; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - __pyx_t_1 = (__pyx_v_copy_shape != 0); + __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":240 * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) # <<<<<<<<<<<<<< @@ -6530,7 +6534,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->strides = ((Py_ssize_t *)PyObject_Malloc((((sizeof(Py_ssize_t)) * 2) * ((size_t)__pyx_v_ndim)))); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":241 * # This is allocated as one block, strides first. * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim # <<<<<<<<<<<<<< @@ -6539,7 +6543,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = (__pyx_v_info->strides + __pyx_v_ndim); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":242 * info.strides = PyObject_Malloc(sizeof(Py_ssize_t) * 2 * ndim) * info.shape = info.strides + ndim * for i in range(ndim): # <<<<<<<<<<<<<< @@ -6547,10 +6551,11 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P * info.shape[i] = PyArray_DIMS(self)[i] */ __pyx_t_4 = __pyx_v_ndim; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 * info.shape = info.strides + ndim * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] # <<<<<<<<<<<<<< @@ -6559,7 +6564,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->strides[__pyx_v_i]) = (PyArray_STRIDES(__pyx_v_self)[__pyx_v_i]); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":244 * for i in range(ndim): * info.strides[i] = PyArray_STRIDES(self)[i] * info.shape[i] = PyArray_DIMS(self)[i] # <<<<<<<<<<<<<< @@ -6569,17 +6574,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_info->shape[__pyx_v_i]) = (PyArray_DIMS(__pyx_v_self)[__pyx_v_i]); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":243 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":237 * info.buf = PyArray_DATA(self) * info.ndim = ndim - * if copy_shape: # <<<<<<<<<<<<<< + * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< * # Allocate new buffer for strides and shape info. * # This is allocated as one block, strides first. */ - goto __pyx_L11; + goto __pyx_L9; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":252 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":246 * info.shape[i] = PyArray_DIMS(self)[i] * else: * info.strides = PyArray_STRIDES(self) # <<<<<<<<<<<<<< @@ -6589,7 +6594,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->strides = ((Py_ssize_t *)PyArray_STRIDES(__pyx_v_self)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":247 * else: * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) # <<<<<<<<<<<<<< @@ -6598,9 +6603,9 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->shape = ((Py_ssize_t *)PyArray_DIMS(__pyx_v_self)); } - __pyx_L11:; + __pyx_L9:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":248 * info.strides = PyArray_STRIDES(self) * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL # <<<<<<<<<<<<<< @@ -6609,7 +6614,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->suboffsets = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":255 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":249 * info.shape = PyArray_DIMS(self) * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) # <<<<<<<<<<<<<< @@ -6618,7 +6623,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->itemsize = PyArray_ITEMSIZE(__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":256 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":250 * info.suboffsets = NULL * info.itemsize = PyArray_ITEMSIZE(self) * info.readonly = not PyArray_ISWRITEABLE(self) # <<<<<<<<<<<<<< @@ -6627,7 +6632,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->readonly = (!(PyArray_ISWRITEABLE(__pyx_v_self) != 0)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":253 * * cdef int t * cdef char* f = NULL # <<<<<<<<<<<<<< @@ -6636,7 +6641,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_f = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":254 * cdef int t * cdef char* f = NULL * cdef dtype descr = self.descr # <<<<<<<<<<<<<< @@ -6648,85 +6653,32 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_descr = ((PyArray_Descr *)__pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":257 * cdef int offset * - * cdef bint hasfields = PyDataType_HASFIELDS(descr) # <<<<<<<<<<<<<< + * info.obj = self # <<<<<<<<<<<<<< * - * if not hasfields and not copy_shape: + * if not PyDataType_HASFIELDS(descr): */ - __pyx_v_hasfields = PyDataType_HASFIELDS(__pyx_v_descr); + __Pyx_INCREF(((PyObject *)__pyx_v_self)); + __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); + __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< + * t = descr.type_num + * if ((descr.byteorder == c'>' and little_endian) or */ - __pyx_t_2 = ((!(__pyx_v_hasfields != 0)) != 0); - if (__pyx_t_2) { - } else { - __pyx_t_1 = __pyx_t_2; - goto __pyx_L15_bool_binop_done; - } - __pyx_t_2 = ((!(__pyx_v_copy_shape != 0)) != 0); - __pyx_t_1 = __pyx_t_2; - __pyx_L15_bool_binop_done:; + __pyx_t_1 = ((!(PyDataType_HASFIELDS(__pyx_v_descr) != 0)) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 - * if not hasfields and not copy_shape: - * # do not call releasebuffer - * info.obj = None # <<<<<<<<<<<<<< - * else: - * # need to call releasebuffer - */ - __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(Py_None); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = Py_None; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 - * cdef bint hasfields = PyDataType_HASFIELDS(descr) + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":260 * - * if not hasfields and not copy_shape: # <<<<<<<<<<<<<< - * # do not call releasebuffer - * info.obj = None - */ - goto __pyx_L14; - } - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 - * else: - * # need to call releasebuffer - * info.obj = self # <<<<<<<<<<<<<< - * - * if not hasfields: - */ - /*else*/ { - __Pyx_INCREF(((PyObject *)__pyx_v_self)); - __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); - __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); - __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - } - __pyx_L14:; - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self - * - * if not hasfields: # <<<<<<<<<<<<<< - * t = descr.type_num - * if ((descr.byteorder == c'>' and little_endian) or - */ - __pyx_t_1 = ((!(__pyx_v_hasfields != 0)) != 0); - if (__pyx_t_1) { - - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 - * - * if not hasfields: + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num # <<<<<<<<<<<<<< * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): @@ -6734,8 +6686,8 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_t_4 = __pyx_v_descr->type_num; __pyx_v_t = __pyx_t_4; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -6743,18 +6695,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_t_2 = ((__pyx_v_descr->byteorder == '>') != 0); if (!__pyx_t_2) { - goto __pyx_L20_next_or; + goto __pyx_L15_next_or; } else { } __pyx_t_2 = (__pyx_v_little_endian != 0); if (!__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } - __pyx_L20_next_or:; + __pyx_L15_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":262 * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -6765,36 +6717,36 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P if (__pyx_t_2) { } else { __pyx_t_1 = __pyx_t_2; - goto __pyx_L19_bool_binop_done; + goto __pyx_L14_bool_binop_done; } __pyx_t_2 = ((!(__pyx_v_little_endian != 0)) != 0); __pyx_t_1 = __pyx_t_2; - __pyx_L19_bool_binop_done:; + __pyx_L14_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__11, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 276, __pyx_L1_error) + __PYX_ERR(1, 263, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 - * if not hasfields: + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":261 + * if not PyDataType_HASFIELDS(descr): * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (descr.byteorder == c'<' and not little_endian)): @@ -6802,7 +6754,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":264 * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" # <<<<<<<<<<<<<< @@ -6814,7 +6766,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"b"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":265 * raise ValueError(u"Non-native byte order not supported") * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" # <<<<<<<<<<<<<< @@ -6825,7 +6777,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"B"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":266 * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" # <<<<<<<<<<<<<< @@ -6836,7 +6788,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"h"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":267 * elif t == NPY_UBYTE: f = "B" * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" # <<<<<<<<<<<<<< @@ -6847,7 +6799,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"H"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":281 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":268 * elif t == NPY_SHORT: f = "h" * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" # <<<<<<<<<<<<<< @@ -6858,7 +6810,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"i"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":269 * elif t == NPY_USHORT: f = "H" * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" # <<<<<<<<<<<<<< @@ -6869,7 +6821,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"I"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":270 * elif t == NPY_INT: f = "i" * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" # <<<<<<<<<<<<<< @@ -6880,7 +6832,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"l"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":271 * elif t == NPY_UINT: f = "I" * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" # <<<<<<<<<<<<<< @@ -6891,7 +6843,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"L"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":285 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 * elif t == NPY_LONG: f = "l" * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" # <<<<<<<<<<<<<< @@ -6902,7 +6854,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":273 * elif t == NPY_ULONG: f = "L" * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" # <<<<<<<<<<<<<< @@ -6913,7 +6865,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Q"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":274 * elif t == NPY_LONGLONG: f = "q" * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" # <<<<<<<<<<<<<< @@ -6924,7 +6876,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"f"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":275 * elif t == NPY_ULONGLONG: f = "Q" * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" # <<<<<<<<<<<<<< @@ -6935,7 +6887,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"d"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 * elif t == NPY_FLOAT: f = "f" * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" # <<<<<<<<<<<<<< @@ -6946,7 +6898,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"g"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":290 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":277 * elif t == NPY_DOUBLE: f = "d" * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" # <<<<<<<<<<<<<< @@ -6957,7 +6909,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zf"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":291 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":278 * elif t == NPY_LONGDOUBLE: f = "g" * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" # <<<<<<<<<<<<<< @@ -6968,7 +6920,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zd"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":279 * elif t == NPY_CFLOAT: f = "Zf" * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" # <<<<<<<<<<<<<< @@ -6979,7 +6931,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_v_f = ((char *)"Zg"); break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":293 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":280 * elif t == NPY_CDOUBLE: f = "Zd" * elif t == NPY_CLONGDOUBLE: f = "Zg" * elif t == NPY_OBJECT: f = "O" # <<<<<<<<<<<<<< @@ -6991,33 +6943,28 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P break; default: - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":282 * elif t == NPY_OBJECT: f = "O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< * info.format = f * return */ - __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_6 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __pyx_t_7 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_t_3); if (unlikely(!__pyx_t_7)) __PYX_ERR(1, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 295, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_7); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_GIVEREF(__pyx_t_6); - PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_6); - __pyx_t_6 = 0; - __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_3, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(1, 295, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_6); + __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; + __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_Raise(__pyx_t_6, 0, 0, 0); - __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __PYX_ERR(1, 295, __pyx_L1_error) + __PYX_ERR(1, 282, __pyx_L1_error) break; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":283 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f # <<<<<<<<<<<<<< @@ -7026,7 +6973,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_info->format = __pyx_v_f; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":284 * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * info.format = f * return # <<<<<<<<<<<<<< @@ -7036,16 +6983,16 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P __pyx_r = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":272 - * info.obj = self + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":259 + * info.obj = self * - * if not hasfields: # <<<<<<<<<<<<<< + * if not PyDataType_HASFIELDS(descr): # <<<<<<<<<<<<<< * t = descr.type_num * if ((descr.byteorder == c'>' and little_endian) or */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":299 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":286 * return * else: * info.format = PyObject_Malloc(_buffer_format_string_len) # <<<<<<<<<<<<<< @@ -7055,7 +7002,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P /*else*/ { __pyx_v_info->format = ((char *)PyObject_Malloc(0xFF)); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":300 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":287 * else: * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment # <<<<<<<<<<<<<< @@ -7064,7 +7011,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ (__pyx_v_info->format[0]) = '^'; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":301 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":288 * info.format = PyObject_Malloc(_buffer_format_string_len) * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 # <<<<<<<<<<<<<< @@ -7073,17 +7020,17 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P */ __pyx_v_offset = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":302 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":289 * info.format[0] = c'^' # Native data types, manual alignment * offset = 0 * f = _util_dtypestring(descr, info.format + 1, # <<<<<<<<<<<<<< * info.format + _buffer_format_string_len, * &offset) */ - __pyx_t_7 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_7 == ((char *)NULL))) __PYX_ERR(1, 302, __pyx_L1_error) - __pyx_v_f = __pyx_t_7; + __pyx_t_8 = __pyx_f_5numpy__util_dtypestring(__pyx_v_descr, (__pyx_v_info->format + 1), (__pyx_v_info->format + 0xFF), (&__pyx_v_offset)); if (unlikely(__pyx_t_8 == ((char *)NULL))) __PYX_ERR(1, 289, __pyx_L1_error) + __pyx_v_f = __pyx_t_8; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":305 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":292 * info.format + _buffer_format_string_len, * &offset) * f[0] = c'\0' # Terminate format string # <<<<<<<<<<<<<< @@ -7093,12 +7040,12 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P (__pyx_v_f[0]) = '\x00'; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":214 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":215 * # experimental exception made for __getbuffer__ and __releasebuffer__ * # -- the details of this may change. * def __getbuffer__(ndarray self, Py_buffer* info, int flags): # <<<<<<<<<<<<<< * # This implementation of getbuffer is geared towards Cython - * # requirements, and does not yet fullfill the PEP. + * # requirements, and does not yet fulfill the PEP. */ /* function exit code */ @@ -7106,18 +7053,18 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_3); - __Pyx_XDECREF(__pyx_t_6); + __Pyx_XDECREF(__pyx_t_7); __Pyx_AddTraceback("numpy.ndarray.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; - if (__pyx_v_info != NULL && __pyx_v_info->obj != NULL) { + if (__pyx_v_info->obj != NULL) { __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = NULL; + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } goto __pyx_L2; __pyx_L0:; - if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) { - __Pyx_GOTREF(Py_None); - __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL; + if (__pyx_v_info->obj == Py_None) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } __pyx_L2:; __Pyx_XDECREF((PyObject *)__pyx_v_descr); @@ -7125,7 +7072,7 @@ static int __pyx_pf_5numpy_7ndarray___getbuffer__(PyArrayObject *__pyx_v_self, P return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -7149,7 +7096,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s int __pyx_t_1; __Pyx_RefNannySetupContext("__releasebuffer__", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -7159,7 +7106,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (PyArray_HASFIELDS(__pyx_v_self) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":309 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":296 * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) # <<<<<<<<<<<<<< @@ -7168,7 +7115,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->format); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":308 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":295 * * def __releasebuffer__(ndarray self, Py_buffer* info): * if PyArray_HASFIELDS(self): # <<<<<<<<<<<<<< @@ -7177,7 +7124,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -7187,7 +7134,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __pyx_t_1 = (((sizeof(npy_intp)) != (sizeof(Py_ssize_t))) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":311 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":298 * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): * PyObject_Free(info.strides) # <<<<<<<<<<<<<< @@ -7196,7 +7143,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ PyObject_Free(__pyx_v_info->strides); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":310 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":297 * if PyArray_HASFIELDS(self): * PyObject_Free(info.format) * if sizeof(npy_intp) != sizeof(Py_ssize_t): # <<<<<<<<<<<<<< @@ -7205,7 +7152,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":307 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":294 * f[0] = c'\0' # Terminate format string * * def __releasebuffer__(ndarray self, Py_buffer* info): # <<<<<<<<<<<<<< @@ -7217,7 +7164,7 @@ static void __pyx_pf_5numpy_7ndarray_2__releasebuffer__(PyArrayObject *__pyx_v_s __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -7231,7 +7178,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew1", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":789 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":776 * * cdef inline object PyArray_MultiIterNew1(a): * return PyArray_MultiIterNew(1, a) # <<<<<<<<<<<<<< @@ -7239,13 +7186,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ * cdef inline object PyArray_MultiIterNew2(a, b): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 789, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(1, ((void *)__pyx_v_a)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 776, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":775 * ctypedef npy_cdouble complex_t * * cdef inline object PyArray_MultiIterNew1(a): # <<<<<<<<<<<<<< @@ -7264,7 +7211,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew1(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -7278,7 +7225,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew2", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":779 * * cdef inline object PyArray_MultiIterNew2(a, b): * return PyArray_MultiIterNew(2, a, b) # <<<<<<<<<<<<<< @@ -7286,13 +7233,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ * cdef inline object PyArray_MultiIterNew3(a, b, c): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 792, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(2, ((void *)__pyx_v_a), ((void *)__pyx_v_b)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 779, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":778 * return PyArray_MultiIterNew(1, a) * * cdef inline object PyArray_MultiIterNew2(a, b): # <<<<<<<<<<<<<< @@ -7311,7 +7258,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew2(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -7325,7 +7272,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew3", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":795 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":782 * * cdef inline object PyArray_MultiIterNew3(a, b, c): * return PyArray_MultiIterNew(3, a, b, c) # <<<<<<<<<<<<<< @@ -7333,13 +7280,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ * cdef inline object PyArray_MultiIterNew4(a, b, c, d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 795, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(3, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 782, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":781 * return PyArray_MultiIterNew(2, a, b) * * cdef inline object PyArray_MultiIterNew3(a, b, c): # <<<<<<<<<<<<<< @@ -7358,7 +7305,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew3(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -7372,7 +7319,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew4", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":798 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":785 * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): * return PyArray_MultiIterNew(4, a, b, c, d) # <<<<<<<<<<<<<< @@ -7380,13 +7327,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 798, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(4, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 785, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":797 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":784 * return PyArray_MultiIterNew(3, a, b, c) * * cdef inline object PyArray_MultiIterNew4(a, b, c, d): # <<<<<<<<<<<<<< @@ -7405,7 +7352,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew4(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -7419,7 +7366,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("PyArray_MultiIterNew5", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":788 * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): * return PyArray_MultiIterNew(5, a, b, c, d, e) # <<<<<<<<<<<<<< @@ -7427,13 +7374,13 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ * cdef inline tuple PyDataType_SHAPE(dtype d): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 801, __pyx_L1_error) + __pyx_t_1 = PyArray_MultiIterNew(5, ((void *)__pyx_v_a), ((void *)__pyx_v_b), ((void *)__pyx_v_c), ((void *)__pyx_v_d), ((void *)__pyx_v_e)); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 788, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":800 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":787 * return PyArray_MultiIterNew(4, a, b, c, d) * * cdef inline object PyArray_MultiIterNew5(a, b, c, d, e): # <<<<<<<<<<<<<< @@ -7452,7 +7399,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyArray_MultiIterNew5(PyObject *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -7466,7 +7413,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ int __pyx_t_1; __Pyx_RefNannySetupContext("PyDataType_SHAPE", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -7476,7 +7423,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_t_1 = (PyDataType_HASSUBARRAY(__pyx_v_d) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":792 * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): * return d.subarray.shape # <<<<<<<<<<<<<< @@ -7488,7 +7435,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ __pyx_r = ((PyObject*)__pyx_v_d->subarray->shape); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":804 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":791 * * cdef inline tuple PyDataType_SHAPE(dtype d): * if PyDataType_HASSUBARRAY(d): # <<<<<<<<<<<<<< @@ -7497,7 +7444,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":794 * return d.subarray.shape * else: * return () # <<<<<<<<<<<<<< @@ -7511,7 +7458,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":803 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":790 * return PyArray_MultiIterNew(5, a, b, c, d, e) * * cdef inline tuple PyDataType_SHAPE(dtype d): # <<<<<<<<<<<<<< @@ -7526,7 +7473,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_PyDataType_SHAPE(PyArray_Descr *__ return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -7555,7 +7502,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx char *__pyx_t_9; __Pyx_RefNannySetupContext("_util_dtypestring", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":801 * * cdef dtype child * cdef int endian_detector = 1 # <<<<<<<<<<<<<< @@ -7564,7 +7511,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_endian_detector = 1; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":815 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":802 * cdef dtype child * cdef int endian_detector = 1 * cdef bint little_endian = ((&endian_detector)[0] != 0) # <<<<<<<<<<<<<< @@ -7573,7 +7520,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_little_endian = ((((char *)(&__pyx_v_endian_detector))[0]) != 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -7582,21 +7529,21 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->names == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); - __PYX_ERR(1, 818, __pyx_L1_error) + __PYX_ERR(1, 805, __pyx_L1_error) } __pyx_t_1 = __pyx_v_descr->names; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; for (;;) { if (__pyx_t_2 >= PyTuple_GET_SIZE(__pyx_t_1)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_3); __pyx_t_2++; if (unlikely(0 < 0)) __PYX_ERR(1, 805, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 818, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 805, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif __Pyx_XDECREF_SET(__pyx_v_childname, __pyx_t_3); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":819 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":806 * * for childname in descr.names: * fields = descr.fields[childname] # <<<<<<<<<<<<<< @@ -7605,15 +7552,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (unlikely(__pyx_v_descr->fields == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); - __PYX_ERR(1, 819, __pyx_L1_error) + __PYX_ERR(1, 806, __pyx_L1_error) } - __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 819, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_GetItem(__pyx_v_descr->fields, __pyx_v_childname); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 819, __pyx_L1_error) + if (!(likely(PyTuple_CheckExact(__pyx_t_3))||((__pyx_t_3) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "tuple", Py_TYPE(__pyx_t_3)->tp_name), 0))) __PYX_ERR(1, 806, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_fields, ((PyObject*)__pyx_t_3)); __pyx_t_3 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":820 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":807 * for childname in descr.names: * fields = descr.fields[childname] * child, new_offset = fields # <<<<<<<<<<<<<< @@ -7622,15 +7569,11 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ if (likely(__pyx_v_fields != Py_None)) { PyObject* sequence = __pyx_v_fields; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(1, 820, __pyx_L1_error) + __PYX_ERR(1, 807, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyTuple_GET_ITEM(sequence, 0); @@ -7638,51 +7581,51 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(__pyx_t_4); #else - __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 820, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { - __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 820, __pyx_L1_error) + __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(1, 807, __pyx_L1_error) } - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 820, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_ptype_5numpy_dtype))))) __PYX_ERR(1, 807, __pyx_L1_error) __Pyx_XDECREF_SET(__pyx_v_child, ((PyArray_Descr *)__pyx_t_3)); __pyx_t_3 = 0; __Pyx_XDECREF_SET(__pyx_v_new_offset, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * */ - __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_3 = PyNumber_Subtract(__pyx_v_new_offset, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 822, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyInt_As_int(__pyx_t_3); if (unlikely((__pyx_t_5 == (int)-1) && PyErr_Occurred())) __PYX_ERR(1, 809, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_6 = ((((__pyx_v_end - __pyx_v_f) - ((int)__pyx_t_5)) < 15) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__12, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 823, __pyx_L1_error) + __PYX_ERR(1, 810, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":822 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 * child, new_offset = fields * * if (end - f) - (new_offset - offset[0]) < 15: # <<<<<<<<<<<<<< @@ -7691,7 +7634,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -7711,7 +7654,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __pyx_L8_next_or:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":813 * * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): # <<<<<<<<<<<<<< @@ -7728,29 +7671,29 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = __pyx_t_7; __pyx_L7_bool_binop_done:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") */ - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__13, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 827, __pyx_L1_error) + __PYX_ERR(1, 814, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":812 * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") * * if ((child.byteorder == c'>' and little_endian) or # <<<<<<<<<<<<<< @@ -7759,7 +7702,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":824 * * # Output padding bytes * while offset[0] < new_offset: # <<<<<<<<<<<<<< @@ -7767,15 +7710,15 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * f += 1 */ while (1) { - __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int((__pyx_v_offset[0])); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_t_3, __pyx_v_new_offset, Py_LT); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 824, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (!__pyx_t_6) break; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":825 * # Output padding bytes * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte # <<<<<<<<<<<<<< @@ -7784,7 +7727,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ (__pyx_v_f[0]) = 0x78; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":826 * while offset[0] < new_offset: * f[0] = 120 # "x"; pad byte * f += 1 # <<<<<<<<<<<<<< @@ -7793,7 +7736,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 * f[0] = 120 # "x"; pad byte * f += 1 * offset[0] += 1 # <<<<<<<<<<<<<< @@ -7804,7 +7747,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + 1); } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":829 * offset[0] += 1 * * offset[0] += child.itemsize # <<<<<<<<<<<<<< @@ -7814,7 +7757,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_8 = 0; (__pyx_v_offset[__pyx_t_8]) = ((__pyx_v_offset[__pyx_t_8]) + __pyx_v_child->elsize); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -7824,19 +7767,19 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_t_6 = ((!(PyDataType_HASFIELDS(__pyx_v_child) != 0)) != 0); if (__pyx_t_6) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":832 * * if not PyDataType_HASFIELDS(child): * t = child.type_num # <<<<<<<<<<<<<< * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") */ - __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_int(__pyx_v_child->type_num); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 832, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_XDECREF_SET(__pyx_v_t, __pyx_t_4); __pyx_t_4 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -7844,22 +7787,22 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ __pyx_t_6 = (((__pyx_v_end - __pyx_v_f) < 5) != 0); - if (__pyx_t_6) { + if (unlikely(__pyx_t_6)) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__14, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_RuntimeError, __pyx_tuple__14, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_Raise(__pyx_t_4, 0, 0, 0); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __PYX_ERR(1, 847, __pyx_L1_error) + __PYX_ERR(1, 834, __pyx_L1_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":833 * if not PyDataType_HASFIELDS(child): * t = child.type_num * if end - f < 5: # <<<<<<<<<<<<<< @@ -7868,252 +7811,252 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":837 * * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" # <<<<<<<<<<<<<< * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_BYTE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 837, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 98; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":838 * # Until ticket #99 is fixed, use integers to avoid warnings * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" # <<<<<<<<<<<<<< * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UBYTE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 838, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":839 * if t == NPY_BYTE: f[0] = 98 #"b" * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" # <<<<<<<<<<<<<< * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_SHORT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 839, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x68; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":840 * elif t == NPY_UBYTE: f[0] = 66 #"B" * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" # <<<<<<<<<<<<<< * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_USHORT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 840, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 72; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":854 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":841 * elif t == NPY_SHORT: f[0] = 104 #"h" * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" # <<<<<<<<<<<<<< * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_INT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 854, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 841, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x69; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":842 * elif t == NPY_USHORT: f[0] = 72 #"H" * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" # <<<<<<<<<<<<<< * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_UINT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 855, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 842, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 73; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":843 * elif t == NPY_INT: f[0] = 105 #"i" * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" # <<<<<<<<<<<<<< * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 856, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 843, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x6C; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":857 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 * elif t == NPY_UINT: f[0] = 73 #"I" * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" # <<<<<<<<<<<<<< * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 857, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 844, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 76; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":858 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":845 * elif t == NPY_LONG: f[0] = 108 #"l" * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" # <<<<<<<<<<<<<< * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGLONG); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 858, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 845, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x71; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":859 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":846 * elif t == NPY_ULONG: f[0] = 76 #"L" * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" # <<<<<<<<<<<<<< * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_ULONGLONG); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 859, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 846, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 81; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 * elif t == NPY_LONGLONG: f[0] = 113 #"q" * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" # <<<<<<<<<<<<<< * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_FLOAT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 860, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 847, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x66; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":848 * elif t == NPY_ULONGLONG: f[0] = 81 #"Q" * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" # <<<<<<<<<<<<<< * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_DOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 861, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 848, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x64; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":862 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":849 * elif t == NPY_FLOAT: f[0] = 102 #"f" * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" # <<<<<<<<<<<<<< * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_LONGDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 862, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 849, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 0x67; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":863 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":850 * elif t == NPY_DOUBLE: f[0] = 100 #"d" * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf # <<<<<<<<<<<<<< * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CFLOAT); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 863, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 850, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -8122,18 +8065,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":864 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":851 * elif t == NPY_LONGDOUBLE: f[0] = 103 #"g" * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd # <<<<<<<<<<<<<< * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CDOUBLE); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 864, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 851, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -8142,18 +8085,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":865 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":852 * elif t == NPY_CFLOAT: f[0] = 90; f[1] = 102; f += 1 # Zf * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg # <<<<<<<<<<<<<< * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: */ - __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_CLONGDOUBLE); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_4 = PyObject_RichCompare(__pyx_v_t, __pyx_t_3, Py_EQ); __Pyx_XGOTREF(__pyx_t_4); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 865, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_4); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 852, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__pyx_t_6) { (__pyx_v_f[0]) = 90; @@ -8162,25 +8105,25 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":866 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":853 * elif t == NPY_CDOUBLE: f[0] = 90; f[1] = 100; f += 1 # Zd * elif t == NPY_CLONGDOUBLE: f[0] = 90; f[1] = 103; f += 1 # Zg * elif t == NPY_OBJECT: f[0] = 79 #"O" # <<<<<<<<<<<<<< * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) */ - __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyInt_From_enum__NPY_TYPES(NPY_OBJECT); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_3 = PyObject_RichCompare(__pyx_v_t, __pyx_t_4, Py_EQ); __Pyx_XGOTREF(__pyx_t_3); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 866, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely(__pyx_t_6 < 0)) __PYX_ERR(1, 853, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - if (__pyx_t_6) { + if (likely(__pyx_t_6)) { (__pyx_v_f[0]) = 79; goto __pyx_L15; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":868 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":855 * elif t == NPY_OBJECT: f[0] = 79 #"O" * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) # <<<<<<<<<<<<<< @@ -8188,23 +8131,18 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * else: */ /*else*/ { - __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_3 = PyUnicode_Format(__pyx_kp_u_unknown_dtype_code_in_numpy_pxd, __pyx_v_t); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 868, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 855, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 868, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(1, 868, __pyx_L1_error) + __Pyx_Raise(__pyx_t_4, 0, 0, 0); + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __PYX_ERR(1, 855, __pyx_L1_error) } __pyx_L15:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":869 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":856 * else: * raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t) * f += 1 # <<<<<<<<<<<<<< @@ -8213,7 +8151,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx */ __pyx_v_f = (__pyx_v_f + 1); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":844 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":831 * offset[0] += child.itemsize * * if not PyDataType_HASFIELDS(child): # <<<<<<<<<<<<<< @@ -8223,7 +8161,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx goto __pyx_L13; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":873 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":860 * # Cython ignores struct boundary information ("T{...}"), * # so don't output it * f = _util_dtypestring(child, f, end, offset) # <<<<<<<<<<<<<< @@ -8231,12 +8169,12 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx * */ /*else*/ { - __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 873, __pyx_L1_error) + __pyx_t_9 = __pyx_f_5numpy__util_dtypestring(__pyx_v_child, __pyx_v_f, __pyx_v_end, __pyx_v_offset); if (unlikely(__pyx_t_9 == ((char *)NULL))) __PYX_ERR(1, 860, __pyx_L1_error) __pyx_v_f = __pyx_t_9; } __pyx_L13:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":818 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":805 * cdef tuple fields * * for childname in descr.names: # <<<<<<<<<<<<<< @@ -8246,7 +8184,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":874 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":861 * # so don't output it * f = _util_dtypestring(child, f, end, offset) * return f # <<<<<<<<<<<<<< @@ -8256,7 +8194,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx __pyx_r = __pyx_v_f; goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":809 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":796 * return () * * cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL: # <<<<<<<<<<<<<< @@ -8281,7 +8219,7 @@ static CYTHON_INLINE char *__pyx_f_5numpy__util_dtypestring(PyArray_Descr *__pyx return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -8296,7 +8234,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a int __pyx_t_2; __Pyx_RefNannySetupContext("set_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -8307,7 +8245,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":993 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":980 * cdef PyObject* baseptr * if base is None: * baseptr = NULL # <<<<<<<<<<<<<< @@ -8316,7 +8254,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_baseptr = NULL; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":992 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":979 * cdef inline void set_array_base(ndarray arr, object base): * cdef PyObject* baseptr * if base is None: # <<<<<<<<<<<<<< @@ -8326,7 +8264,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a goto __pyx_L3; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":995 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":982 * baseptr = NULL * else: * Py_INCREF(base) # important to do this before decref below! # <<<<<<<<<<<<<< @@ -8336,7 +8274,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a /*else*/ { Py_INCREF(__pyx_v_base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":983 * else: * Py_INCREF(base) # important to do this before decref below! * baseptr = base # <<<<<<<<<<<<<< @@ -8347,7 +8285,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a } __pyx_L3:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":984 * Py_INCREF(base) # important to do this before decref below! * baseptr = base * Py_XDECREF(arr.base) # <<<<<<<<<<<<<< @@ -8356,7 +8294,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ Py_XDECREF(__pyx_v_arr->base); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":985 * baseptr = base * Py_XDECREF(arr.base) * arr.base = baseptr # <<<<<<<<<<<<<< @@ -8365,7 +8303,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a */ __pyx_v_arr->base = __pyx_v_baseptr; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":990 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":977 * * * cdef inline void set_array_base(ndarray arr, object base): # <<<<<<<<<<<<<< @@ -8377,7 +8315,7 @@ static CYTHON_INLINE void __pyx_f_5numpy_set_array_base(PyArrayObject *__pyx_v_a __Pyx_RefNannyFinishContext(); } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -8391,7 +8329,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py int __pyx_t_1; __Pyx_RefNannySetupContext("get_array_base", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -8401,7 +8339,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py __pyx_t_1 = ((__pyx_v_arr->base == NULL) != 0); if (__pyx_t_1) { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":989 * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: * return None # <<<<<<<<<<<<<< @@ -8409,11 +8347,10 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py * return arr.base */ __Pyx_XDECREF(__pyx_r); - __Pyx_INCREF(Py_None); - __pyx_r = Py_None; + __pyx_r = Py_None; __Pyx_INCREF(Py_None); goto __pyx_L0; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1001 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":988 * * cdef inline object get_array_base(ndarray arr): * if arr.base is NULL: # <<<<<<<<<<<<<< @@ -8422,7 +8359,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py */ } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":991 * return None * else: * return arr.base # <<<<<<<<<<<<<< @@ -8436,7 +8373,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py goto __pyx_L0; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":987 * arr.base = baseptr * * cdef inline object get_array_base(ndarray arr): # <<<<<<<<<<<<<< @@ -8451,7 +8388,7 @@ static CYTHON_INLINE PyObject *__pyx_f_5numpy_get_array_base(PyArrayObject *__py return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -8472,7 +8409,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_array", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -8488,16 +8425,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":998 * cdef inline int import_array() except -1: * try: * _import_array() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.multiarray failed to import") */ - __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1011, __pyx_L3_error) + __pyx_t_4 = _import_array(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 998, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -8511,7 +8448,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":999 * try: * _import_array() * except Exception: # <<<<<<<<<<<<<< @@ -8521,28 +8458,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_array", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1012, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 999, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__15, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1013, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__15, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1000, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1013, __pyx_L5_except_error) + __PYX_ERR(1, 1000, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":997 * # Cython code. * cdef inline int import_array() except -1: * try: # <<<<<<<<<<<<<< @@ -8557,7 +8494,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":996 * # Versions of the import_* functions which are more suitable for * # Cython code. * cdef inline int import_array() except -1: # <<<<<<<<<<<<<< @@ -8580,7 +8517,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_array(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -8601,7 +8538,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_umath", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -8617,16 +8554,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1017 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1004 * cdef inline int import_umath() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1017, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1004, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -8640,7 +8577,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1018 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1005 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -8650,28 +8587,28 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_umath", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1018, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1005, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__16, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1019, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__16, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1006, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1019, __pyx_L5_except_error) + __PYX_ERR(1, 1006, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1016 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1003 * * cdef inline int import_umath() except -1: * try: # <<<<<<<<<<<<<< @@ -8686,7 +8623,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1015 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1002 * raise ImportError("numpy.core.multiarray failed to import") * * cdef inline int import_umath() except -1: # <<<<<<<<<<<<<< @@ -8709,7 +8646,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_umath(void) { return __pyx_r; } -/* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 +/* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -8730,7 +8667,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { PyObject *__pyx_t_8 = NULL; __Pyx_RefNannySetupContext("import_ufunc", 0); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -8746,16 +8683,16 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __Pyx_XGOTREF(__pyx_t_3); /*try:*/ { - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1023 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1010 * cdef inline int import_ufunc() except -1: * try: * _import_umath() # <<<<<<<<<<<<<< * except Exception: * raise ImportError("numpy.core.umath failed to import") */ - __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1023, __pyx_L3_error) + __pyx_t_4 = _import_umath(); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(1, 1010, __pyx_L3_error) - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -8769,7 +8706,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { goto __pyx_L8_try_end; __pyx_L3_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1024 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1011 * try: * _import_umath() * except Exception: # <<<<<<<<<<<<<< @@ -8778,26 +8715,26 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_t_4 = __Pyx_PyErr_ExceptionMatches(((PyObject *)(&((PyTypeObject*)PyExc_Exception)[0]))); if (__pyx_t_4) { __Pyx_AddTraceback("numpy.import_ufunc", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1024, __pyx_L5_except_error) + if (__Pyx_GetException(&__pyx_t_5, &__pyx_t_6, &__pyx_t_7) < 0) __PYX_ERR(1, 1011, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GOTREF(__pyx_t_6); __Pyx_GOTREF(__pyx_t_7); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__17, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1025, __pyx_L5_except_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_builtin_ImportError, __pyx_tuple__17, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(1, 1012, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_Raise(__pyx_t_8, 0, 0, 0); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; - __PYX_ERR(1, 1025, __pyx_L5_except_error) + __PYX_ERR(1, 1012, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1022 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1009 * * cdef inline int import_ufunc() except -1: * try: # <<<<<<<<<<<<<< @@ -8812,7 +8749,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { __pyx_L8_try_end:; } - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1021 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1008 * raise ImportError("numpy.core.umath failed to import") * * cdef inline int import_ufunc() except -1: # <<<<<<<<<<<<<< @@ -8835,7 +8772,7 @@ static CYTHON_INLINE int __pyx_f_5numpy_import_ufunc(void) { return __pyx_r; } -/* "View.MemoryView":120 +/* "View.MemoryView":121 * cdef bint dtype_is_object * * def __cinit__(array self, tuple shape, Py_ssize_t itemsize, format not None, # <<<<<<<<<<<<<< @@ -8878,35 +8815,35 @@ static int __pyx_array___cinit__(PyObject *__pyx_v_self, PyObject *__pyx_args, P kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_shape)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_shape)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_itemsize)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_itemsize)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 3, 5, 1); __PYX_ERR(2, 120, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 3, 5, 1); __PYX_ERR(2, 121, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_format)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_format)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 3, 5, 2); __PYX_ERR(2, 120, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 3, 5, 2); __PYX_ERR(2, 121, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 3: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_mode); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_mode); if (value) { values[3] = value; kw_args--; } } CYTHON_FALLTHROUGH; case 4: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_allocate_buffer); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_allocate_buffer); if (value) { values[4] = value; kw_args--; } } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__cinit__") < 0)) __PYX_ERR(2, 120, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__cinit__") < 0)) __PYX_ERR(2, 121, __pyx_L3_error) } } else { switch (PyTuple_GET_SIZE(__pyx_args)) { @@ -8922,14 +8859,14 @@ static int __pyx_array___cinit__(PyObject *__pyx_v_self, PyObject *__pyx_args, P } } __pyx_v_shape = ((PyObject*)values[0]); - __pyx_v_itemsize = __Pyx_PyIndex_AsSsize_t(values[1]); if (unlikely((__pyx_v_itemsize == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 120, __pyx_L3_error) + __pyx_v_itemsize = __Pyx_PyIndex_AsSsize_t(values[1]); if (unlikely((__pyx_v_itemsize == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 121, __pyx_L3_error) __pyx_v_format = values[2]; __pyx_v_mode = values[3]; if (values[4]) { - __pyx_v_allocate_buffer = __Pyx_PyObject_IsTrue(values[4]); if (unlikely((__pyx_v_allocate_buffer == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 121, __pyx_L3_error) + __pyx_v_allocate_buffer = __Pyx_PyObject_IsTrue(values[4]); if (unlikely((__pyx_v_allocate_buffer == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 122, __pyx_L3_error) } else { - /* "View.MemoryView":121 + /* "View.MemoryView":122 * * def __cinit__(array self, tuple shape, Py_ssize_t itemsize, format not None, * mode="c", bint allocate_buffer=True): # <<<<<<<<<<<<<< @@ -8941,19 +8878,19 @@ static int __pyx_array___cinit__(PyObject *__pyx_v_self, PyObject *__pyx_args, P } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 3, 5, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(2, 120, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 3, 5, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(2, 121, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("View.MemoryView.array.__cinit__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return -1; __pyx_L4_argument_unpacking_done:; - if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_shape), (&PyTuple_Type), 1, "shape", 1))) __PYX_ERR(2, 120, __pyx_L1_error) + if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_shape), (&PyTuple_Type), 1, "shape", 1))) __PYX_ERR(2, 121, __pyx_L1_error) if (unlikely(((PyObject *)__pyx_v_format) == Py_None)) { - PyErr_Format(PyExc_TypeError, "Argument '%.200s' must not be None", "format"); __PYX_ERR(2, 120, __pyx_L1_error) + PyErr_Format(PyExc_TypeError, "Argument '%.200s' must not be None", "format"); __PYX_ERR(2, 121, __pyx_L1_error) } __pyx_r = __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(((struct __pyx_array_obj *)__pyx_v_self), __pyx_v_shape, __pyx_v_itemsize, __pyx_v_format, __pyx_v_mode, __pyx_v_allocate_buffer); - /* "View.MemoryView":120 + /* "View.MemoryView":121 * cdef bint dtype_is_object * * def __cinit__(array self, tuple shape, Py_ssize_t itemsize, format not None, # <<<<<<<<<<<<<< @@ -8988,10 +8925,11 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ Py_ssize_t __pyx_t_8; PyObject *__pyx_t_9 = NULL; PyObject *__pyx_t_10 = NULL; + Py_ssize_t __pyx_t_11; __Pyx_RefNannySetupContext("__cinit__", 0); __Pyx_INCREF(__pyx_v_format); - /* "View.MemoryView":127 + /* "View.MemoryView":128 * cdef PyObject **p * * self.ndim = len(shape) # <<<<<<<<<<<<<< @@ -9000,12 +8938,12 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ if (unlikely(__pyx_v_shape == Py_None)) { PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()"); - __PYX_ERR(2, 127, __pyx_L1_error) + __PYX_ERR(2, 128, __pyx_L1_error) } - __pyx_t_1 = PyTuple_GET_SIZE(__pyx_v_shape); if (unlikely(__pyx_t_1 == ((Py_ssize_t)-1))) __PYX_ERR(2, 127, __pyx_L1_error) + __pyx_t_1 = PyTuple_GET_SIZE(__pyx_v_shape); if (unlikely(__pyx_t_1 == ((Py_ssize_t)-1))) __PYX_ERR(2, 128, __pyx_L1_error) __pyx_v_self->ndim = ((int)__pyx_t_1); - /* "View.MemoryView":128 + /* "View.MemoryView":129 * * self.ndim = len(shape) * self.itemsize = itemsize # <<<<<<<<<<<<<< @@ -9014,7 +8952,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_self->itemsize = __pyx_v_itemsize; - /* "View.MemoryView":130 + /* "View.MemoryView":131 * self.itemsize = itemsize * * if not self.ndim: # <<<<<<<<<<<<<< @@ -9022,22 +8960,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ * */ __pyx_t_2 = ((!(__pyx_v_self->ndim != 0)) != 0); - if (__pyx_t_2) { + if (unlikely(__pyx_t_2)) { - /* "View.MemoryView":131 + /* "View.MemoryView":132 * * if not self.ndim: * raise ValueError("Empty shape tuple for cython.array") # <<<<<<<<<<<<<< * * if itemsize <= 0: */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__18, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 131, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__18, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 132, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(2, 131, __pyx_L1_error) + __PYX_ERR(2, 132, __pyx_L1_error) - /* "View.MemoryView":130 + /* "View.MemoryView":131 * self.itemsize = itemsize * * if not self.ndim: # <<<<<<<<<<<<<< @@ -9046,7 +8984,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":133 + /* "View.MemoryView":134 * raise ValueError("Empty shape tuple for cython.array") * * if itemsize <= 0: # <<<<<<<<<<<<<< @@ -9054,22 +8992,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ * */ __pyx_t_2 = ((__pyx_v_itemsize <= 0) != 0); - if (__pyx_t_2) { + if (unlikely(__pyx_t_2)) { - /* "View.MemoryView":134 + /* "View.MemoryView":135 * * if itemsize <= 0: * raise ValueError("itemsize <= 0 for cython.array") # <<<<<<<<<<<<<< * * if not isinstance(format, bytes): */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__19, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 134, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__19, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 135, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(2, 134, __pyx_L1_error) + __PYX_ERR(2, 135, __pyx_L1_error) - /* "View.MemoryView":133 + /* "View.MemoryView":134 * raise ValueError("Empty shape tuple for cython.array") * * if itemsize <= 0: # <<<<<<<<<<<<<< @@ -9078,7 +9016,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":136 + /* "View.MemoryView":137 * raise ValueError("itemsize <= 0 for cython.array") * * if not isinstance(format, bytes): # <<<<<<<<<<<<<< @@ -9089,22 +9027,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ __pyx_t_4 = ((!(__pyx_t_2 != 0)) != 0); if (__pyx_t_4) { - /* "View.MemoryView":137 + /* "View.MemoryView":138 * * if not isinstance(format, bytes): * format = format.encode('ASCII') # <<<<<<<<<<<<<< * self._format = format # keep a reference to the byte string * self.format = self._format */ - __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_format, __pyx_n_s_encode); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 137, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_format, __pyx_n_s_encode); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_tuple__20, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 137, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_tuple__20, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF_SET(__pyx_v_format, __pyx_t_5); __pyx_t_5 = 0; - /* "View.MemoryView":136 + /* "View.MemoryView":137 * raise ValueError("itemsize <= 0 for cython.array") * * if not isinstance(format, bytes): # <<<<<<<<<<<<<< @@ -9113,14 +9051,14 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":138 + /* "View.MemoryView":139 * if not isinstance(format, bytes): * format = format.encode('ASCII') * self._format = format # keep a reference to the byte string # <<<<<<<<<<<<<< * self.format = self._format * */ - if (!(likely(PyBytes_CheckExact(__pyx_v_format))||((__pyx_v_format) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "bytes", Py_TYPE(__pyx_v_format)->tp_name), 0))) __PYX_ERR(2, 138, __pyx_L1_error) + if (!(likely(PyBytes_CheckExact(__pyx_v_format))||((__pyx_v_format) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "bytes", Py_TYPE(__pyx_v_format)->tp_name), 0))) __PYX_ERR(2, 139, __pyx_L1_error) __pyx_t_5 = __pyx_v_format; __Pyx_INCREF(__pyx_t_5); __Pyx_GIVEREF(__pyx_t_5); @@ -9129,7 +9067,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ __pyx_v_self->_format = ((PyObject*)__pyx_t_5); __pyx_t_5 = 0; - /* "View.MemoryView":139 + /* "View.MemoryView":140 * format = format.encode('ASCII') * self._format = format # keep a reference to the byte string * self.format = self._format # <<<<<<<<<<<<<< @@ -9138,12 +9076,12 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ if (unlikely(__pyx_v_self->_format == Py_None)) { PyErr_SetString(PyExc_TypeError, "expected bytes, NoneType found"); - __PYX_ERR(2, 139, __pyx_L1_error) + __PYX_ERR(2, 140, __pyx_L1_error) } - __pyx_t_6 = __Pyx_PyBytes_AsWritableString(__pyx_v_self->_format); if (unlikely((!__pyx_t_6) && PyErr_Occurred())) __PYX_ERR(2, 139, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyBytes_AsWritableString(__pyx_v_self->_format); if (unlikely((!__pyx_t_6) && PyErr_Occurred())) __PYX_ERR(2, 140, __pyx_L1_error) __pyx_v_self->format = __pyx_t_6; - /* "View.MemoryView":142 + /* "View.MemoryView":143 * * * self._shape = PyObject_Malloc(sizeof(Py_ssize_t)*self.ndim*2) # <<<<<<<<<<<<<< @@ -9152,7 +9090,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_self->_shape = ((Py_ssize_t *)PyObject_Malloc((((sizeof(Py_ssize_t)) * __pyx_v_self->ndim) * 2))); - /* "View.MemoryView":143 + /* "View.MemoryView":144 * * self._shape = PyObject_Malloc(sizeof(Py_ssize_t)*self.ndim*2) * self._strides = self._shape + self.ndim # <<<<<<<<<<<<<< @@ -9161,7 +9099,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_self->_strides = (__pyx_v_self->_shape + __pyx_v_self->ndim); - /* "View.MemoryView":145 + /* "View.MemoryView":146 * self._strides = self._shape + self.ndim * * if not self._shape: # <<<<<<<<<<<<<< @@ -9169,22 +9107,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ * */ __pyx_t_4 = ((!(__pyx_v_self->_shape != 0)) != 0); - if (__pyx_t_4) { + if (unlikely(__pyx_t_4)) { - /* "View.MemoryView":146 + /* "View.MemoryView":147 * * if not self._shape: * raise MemoryError("unable to allocate shape and strides.") # <<<<<<<<<<<<<< * * */ - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_MemoryError, __pyx_tuple__21, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 146, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_MemoryError, __pyx_tuple__21, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 147, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_Raise(__pyx_t_5, 0, 0, 0); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __PYX_ERR(2, 146, __pyx_L1_error) + __PYX_ERR(2, 147, __pyx_L1_error) - /* "View.MemoryView":145 + /* "View.MemoryView":146 * self._strides = self._shape + self.ndim * * if not self._shape: # <<<<<<<<<<<<<< @@ -9193,7 +9131,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":149 + /* "View.MemoryView":150 * * * for idx, dim in enumerate(shape): # <<<<<<<<<<<<<< @@ -9205,18 +9143,18 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ for (;;) { if (__pyx_t_1 >= PyTuple_GET_SIZE(__pyx_t_5)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_5, __pyx_t_1); __Pyx_INCREF(__pyx_t_3); __pyx_t_1++; if (unlikely(0 < 0)) __PYX_ERR(2, 149, __pyx_L1_error) + __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_5, __pyx_t_1); __Pyx_INCREF(__pyx_t_3); __pyx_t_1++; if (unlikely(0 < 0)) __PYX_ERR(2, 150, __pyx_L1_error) #else - __pyx_t_3 = PySequence_ITEM(__pyx_t_5, __pyx_t_1); __pyx_t_1++; if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 149, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(__pyx_t_5, __pyx_t_1); __pyx_t_1++; if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 150, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif - __pyx_t_8 = __Pyx_PyIndex_AsSsize_t(__pyx_t_3); if (unlikely((__pyx_t_8 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 149, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyIndex_AsSsize_t(__pyx_t_3); if (unlikely((__pyx_t_8 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 150, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_dim = __pyx_t_8; __pyx_v_idx = __pyx_t_7; __pyx_t_7 = (__pyx_t_7 + 1); - /* "View.MemoryView":150 + /* "View.MemoryView":151 * * for idx, dim in enumerate(shape): * if dim <= 0: # <<<<<<<<<<<<<< @@ -9224,20 +9162,20 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ * self._shape[idx] = dim */ __pyx_t_4 = ((__pyx_v_dim <= 0) != 0); - if (__pyx_t_4) { + if (unlikely(__pyx_t_4)) { - /* "View.MemoryView":151 + /* "View.MemoryView":152 * for idx, dim in enumerate(shape): * if dim <= 0: * raise ValueError("Invalid shape in axis %d: %d." % (idx, dim)) # <<<<<<<<<<<<<< * self._shape[idx] = dim * */ - __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_idx); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 151, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_idx); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 152, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_9 = PyInt_FromSsize_t(__pyx_v_dim); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 151, __pyx_L1_error) + __pyx_t_9 = PyInt_FromSsize_t(__pyx_v_dim); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 152, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); - __pyx_t_10 = PyTuple_New(2); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 151, __pyx_L1_error) + __pyx_t_10 = PyTuple_New(2); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 152, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_10, 0, __pyx_t_3); @@ -9245,22 +9183,17 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ PyTuple_SET_ITEM(__pyx_t_10, 1, __pyx_t_9); __pyx_t_3 = 0; __pyx_t_9 = 0; - __pyx_t_9 = __Pyx_PyString_Format(__pyx_kp_s_Invalid_shape_in_axis_d_d, __pyx_t_10); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 151, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyString_Format(__pyx_kp_s_Invalid_shape_in_axis_d_d, __pyx_t_10); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 152, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __pyx_t_10 = PyTuple_New(1); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 151, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_9); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 152, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); - __Pyx_GIVEREF(__pyx_t_9); - PyTuple_SET_ITEM(__pyx_t_10, 0, __pyx_t_9); - __pyx_t_9 = 0; - __pyx_t_9 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_10, NULL); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 151, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_9); - __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - __Pyx_Raise(__pyx_t_9, 0, 0, 0); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; - __PYX_ERR(2, 151, __pyx_L1_error) + __Pyx_Raise(__pyx_t_10, 0, 0, 0); + __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; + __PYX_ERR(2, 152, __pyx_L1_error) - /* "View.MemoryView":150 + /* "View.MemoryView":151 * * for idx, dim in enumerate(shape): * if dim <= 0: # <<<<<<<<<<<<<< @@ -9269,7 +9202,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":152 + /* "View.MemoryView":153 * if dim <= 0: * raise ValueError("Invalid shape in axis %d: %d." % (idx, dim)) * self._shape[idx] = dim # <<<<<<<<<<<<<< @@ -9278,7 +9211,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ (__pyx_v_self->_shape[__pyx_v_idx]) = __pyx_v_dim; - /* "View.MemoryView":149 + /* "View.MemoryView":150 * * * for idx, dim in enumerate(shape): # <<<<<<<<<<<<<< @@ -9288,17 +9221,17 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ } __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - /* "View.MemoryView":155 + /* "View.MemoryView":156 * * cdef char order * if mode == 'fortran': # <<<<<<<<<<<<<< * order = b'F' * self.mode = u'fortran' */ - __pyx_t_4 = (__Pyx_PyString_Equals(__pyx_v_mode, __pyx_n_s_fortran, Py_EQ)); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(2, 155, __pyx_L1_error) + __pyx_t_4 = (__Pyx_PyString_Equals(__pyx_v_mode, __pyx_n_s_fortran, Py_EQ)); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(2, 156, __pyx_L1_error) if (__pyx_t_4) { - /* "View.MemoryView":156 + /* "View.MemoryView":157 * cdef char order * if mode == 'fortran': * order = b'F' # <<<<<<<<<<<<<< @@ -9307,7 +9240,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_order = 'F'; - /* "View.MemoryView":157 + /* "View.MemoryView":158 * if mode == 'fortran': * order = b'F' * self.mode = u'fortran' # <<<<<<<<<<<<<< @@ -9320,7 +9253,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ __Pyx_DECREF(__pyx_v_self->mode); __pyx_v_self->mode = __pyx_n_u_fortran; - /* "View.MemoryView":155 + /* "View.MemoryView":156 * * cdef char order * if mode == 'fortran': # <<<<<<<<<<<<<< @@ -9330,17 +9263,17 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ goto __pyx_L10; } - /* "View.MemoryView":158 + /* "View.MemoryView":159 * order = b'F' * self.mode = u'fortran' * elif mode == 'c': # <<<<<<<<<<<<<< * order = b'C' * self.mode = u'c' */ - __pyx_t_4 = (__Pyx_PyString_Equals(__pyx_v_mode, __pyx_n_s_c, Py_EQ)); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(2, 158, __pyx_L1_error) - if (__pyx_t_4) { + __pyx_t_4 = (__Pyx_PyString_Equals(__pyx_v_mode, __pyx_n_s_c, Py_EQ)); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(2, 159, __pyx_L1_error) + if (likely(__pyx_t_4)) { - /* "View.MemoryView":159 + /* "View.MemoryView":160 * self.mode = u'fortran' * elif mode == 'c': * order = b'C' # <<<<<<<<<<<<<< @@ -9349,7 +9282,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_order = 'C'; - /* "View.MemoryView":160 + /* "View.MemoryView":161 * elif mode == 'c': * order = b'C' * self.mode = u'c' # <<<<<<<<<<<<<< @@ -9362,7 +9295,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ __Pyx_DECREF(__pyx_v_self->mode); __pyx_v_self->mode = __pyx_n_u_c; - /* "View.MemoryView":158 + /* "View.MemoryView":159 * order = b'F' * self.mode = u'fortran' * elif mode == 'c': # <<<<<<<<<<<<<< @@ -9372,7 +9305,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ goto __pyx_L10; } - /* "View.MemoryView":162 + /* "View.MemoryView":163 * self.mode = u'c' * else: * raise ValueError("Invalid mode, expected 'c' or 'fortran', got %s" % mode) # <<<<<<<<<<<<<< @@ -9380,23 +9313,18 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ * self.len = fill_contig_strides_array(self._shape, self._strides, */ /*else*/ { - __pyx_t_5 = __Pyx_PyString_Format(__pyx_kp_s_Invalid_mode_expected_c_or_fortr, __pyx_v_mode); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 162, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_5); - __pyx_t_9 = PyTuple_New(1); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 162, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_9); - __Pyx_GIVEREF(__pyx_t_5); - PyTuple_SET_ITEM(__pyx_t_9, 0, __pyx_t_5); - __pyx_t_5 = 0; - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_9, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 162, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyString_Format(__pyx_kp_s_Invalid_mode_expected_c_or_fortr, __pyx_v_mode); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 163, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); - __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; - __Pyx_Raise(__pyx_t_5, 0, 0, 0); + __pyx_t_10 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_5); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 163, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __PYX_ERR(2, 162, __pyx_L1_error) + __Pyx_Raise(__pyx_t_10, 0, 0, 0); + __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; + __PYX_ERR(2, 163, __pyx_L1_error) } __pyx_L10:; - /* "View.MemoryView":164 + /* "View.MemoryView":165 * raise ValueError("Invalid mode, expected 'c' or 'fortran', got %s" % mode) * * self.len = fill_contig_strides_array(self._shape, self._strides, # <<<<<<<<<<<<<< @@ -9405,7 +9333,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_self->len = __pyx_fill_contig_strides_array(__pyx_v_self->_shape, __pyx_v_self->_strides, __pyx_v_itemsize, __pyx_v_self->ndim, __pyx_v_order); - /* "View.MemoryView":167 + /* "View.MemoryView":168 * itemsize, self.ndim, order) * * self.free_data = allocate_buffer # <<<<<<<<<<<<<< @@ -9414,19 +9342,19 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_self->free_data = __pyx_v_allocate_buffer; - /* "View.MemoryView":168 + /* "View.MemoryView":169 * * self.free_data = allocate_buffer * self.dtype_is_object = format == b'O' # <<<<<<<<<<<<<< * if allocate_buffer: * */ - __pyx_t_5 = PyObject_RichCompare(__pyx_v_format, __pyx_n_b_O, Py_EQ); __Pyx_XGOTREF(__pyx_t_5); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 168, __pyx_L1_error) - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_t_5); if (unlikely((__pyx_t_4 == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 168, __pyx_L1_error) - __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; + __pyx_t_10 = PyObject_RichCompare(__pyx_v_format, __pyx_n_b_O, Py_EQ); __Pyx_XGOTREF(__pyx_t_10); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 169, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_t_10); if (unlikely((__pyx_t_4 == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 169, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __pyx_v_self->dtype_is_object = __pyx_t_4; - /* "View.MemoryView":169 + /* "View.MemoryView":170 * self.free_data = allocate_buffer * self.dtype_is_object = format == b'O' * if allocate_buffer: # <<<<<<<<<<<<<< @@ -9436,7 +9364,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ __pyx_t_4 = (__pyx_v_allocate_buffer != 0); if (__pyx_t_4) { - /* "View.MemoryView":172 + /* "View.MemoryView":173 * * * self.data = malloc(self.len) # <<<<<<<<<<<<<< @@ -9445,7 +9373,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_self->data = ((char *)malloc(__pyx_v_self->len)); - /* "View.MemoryView":173 + /* "View.MemoryView":174 * * self.data = malloc(self.len) * if not self.data: # <<<<<<<<<<<<<< @@ -9453,22 +9381,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ * */ __pyx_t_4 = ((!(__pyx_v_self->data != 0)) != 0); - if (__pyx_t_4) { + if (unlikely(__pyx_t_4)) { - /* "View.MemoryView":174 + /* "View.MemoryView":175 * self.data = malloc(self.len) * if not self.data: * raise MemoryError("unable to allocate array data.") # <<<<<<<<<<<<<< * * if self.dtype_is_object: */ - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_MemoryError, __pyx_tuple__22, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 174, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_5); - __Pyx_Raise(__pyx_t_5, 0, 0, 0); - __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __PYX_ERR(2, 174, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyObject_Call(__pyx_builtin_MemoryError, __pyx_tuple__22, NULL); if (unlikely(!__pyx_t_10)) __PYX_ERR(2, 175, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_10); + __Pyx_Raise(__pyx_t_10, 0, 0, 0); + __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; + __PYX_ERR(2, 175, __pyx_L1_error) - /* "View.MemoryView":173 + /* "View.MemoryView":174 * * self.data = malloc(self.len) * if not self.data: # <<<<<<<<<<<<<< @@ -9477,7 +9405,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":176 + /* "View.MemoryView":177 * raise MemoryError("unable to allocate array data.") * * if self.dtype_is_object: # <<<<<<<<<<<<<< @@ -9487,7 +9415,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ __pyx_t_4 = (__pyx_v_self->dtype_is_object != 0); if (__pyx_t_4) { - /* "View.MemoryView":177 + /* "View.MemoryView":178 * * if self.dtype_is_object: * p = self.data # <<<<<<<<<<<<<< @@ -9496,7 +9424,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ __pyx_v_p = ((PyObject **)__pyx_v_self->data); - /* "View.MemoryView":178 + /* "View.MemoryView":179 * if self.dtype_is_object: * p = self.data * for i in range(self.len / itemsize): # <<<<<<<<<<<<<< @@ -9505,17 +9433,18 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ if (unlikely(__pyx_v_itemsize == 0)) { PyErr_SetString(PyExc_ZeroDivisionError, "integer division or modulo by zero"); - __PYX_ERR(2, 178, __pyx_L1_error) + __PYX_ERR(2, 179, __pyx_L1_error) } else if (sizeof(Py_ssize_t) == sizeof(long) && (!(((Py_ssize_t)-1) > 0)) && unlikely(__pyx_v_itemsize == (Py_ssize_t)-1) && unlikely(UNARY_NEG_WOULD_OVERFLOW(__pyx_v_self->len))) { PyErr_SetString(PyExc_OverflowError, "value too large to perform division"); - __PYX_ERR(2, 178, __pyx_L1_error) + __PYX_ERR(2, 179, __pyx_L1_error) } __pyx_t_1 = __Pyx_div_Py_ssize_t(__pyx_v_self->len, __pyx_v_itemsize); - for (__pyx_t_8 = 0; __pyx_t_8 < __pyx_t_1; __pyx_t_8+=1) { - __pyx_v_i = __pyx_t_8; + __pyx_t_8 = __pyx_t_1; + for (__pyx_t_11 = 0; __pyx_t_11 < __pyx_t_8; __pyx_t_11+=1) { + __pyx_v_i = __pyx_t_11; - /* "View.MemoryView":179 + /* "View.MemoryView":180 * p = self.data * for i in range(self.len / itemsize): * p[i] = Py_None # <<<<<<<<<<<<<< @@ -9524,7 +9453,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ (__pyx_v_p[__pyx_v_i]) = Py_None; - /* "View.MemoryView":180 + /* "View.MemoryView":181 * for i in range(self.len / itemsize): * p[i] = Py_None * Py_INCREF(Py_None) # <<<<<<<<<<<<<< @@ -9534,7 +9463,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ Py_INCREF(Py_None); } - /* "View.MemoryView":176 + /* "View.MemoryView":177 * raise MemoryError("unable to allocate array data.") * * if self.dtype_is_object: # <<<<<<<<<<<<<< @@ -9543,7 +9472,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":169 + /* "View.MemoryView":170 * self.free_data = allocate_buffer * self.dtype_is_object = format == b'O' * if allocate_buffer: # <<<<<<<<<<<<<< @@ -9552,7 +9481,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ */ } - /* "View.MemoryView":120 + /* "View.MemoryView":121 * cdef bint dtype_is_object * * def __cinit__(array self, tuple shape, Py_ssize_t itemsize, format not None, # <<<<<<<<<<<<<< @@ -9576,7 +9505,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array___cinit__(struct __ return __pyx_r; } -/* "View.MemoryView":183 +/* "View.MemoryView":184 * * @cname('getbuffer') * def __getbuffer__(self, Py_buffer *info, int flags): # <<<<<<<<<<<<<< @@ -9608,13 +9537,15 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru Py_ssize_t __pyx_t_5; int __pyx_t_6; Py_ssize_t *__pyx_t_7; - __Pyx_RefNannySetupContext("__getbuffer__", 0); - if (__pyx_v_info != NULL) { - __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(__pyx_v_info->obj); + if (__pyx_v_info == NULL) { + PyErr_SetString(PyExc_BufferError, "PyObject_GetBuffer: view==NULL argument is obsolete"); + return -1; } + __Pyx_RefNannySetupContext("__getbuffer__", 0); + __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); + __Pyx_GIVEREF(__pyx_v_info->obj); - /* "View.MemoryView":184 + /* "View.MemoryView":185 * @cname('getbuffer') * def __getbuffer__(self, Py_buffer *info, int flags): * cdef int bufmode = -1 # <<<<<<<<<<<<<< @@ -9623,18 +9554,18 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru */ __pyx_v_bufmode = -1; - /* "View.MemoryView":185 + /* "View.MemoryView":186 * def __getbuffer__(self, Py_buffer *info, int flags): * cdef int bufmode = -1 * if self.mode == u"c": # <<<<<<<<<<<<<< * bufmode = PyBUF_C_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * elif self.mode == u"fortran": */ - __pyx_t_1 = (__Pyx_PyUnicode_Equals(__pyx_v_self->mode, __pyx_n_u_c, Py_EQ)); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 185, __pyx_L1_error) + __pyx_t_1 = (__Pyx_PyUnicode_Equals(__pyx_v_self->mode, __pyx_n_u_c, Py_EQ)); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 186, __pyx_L1_error) __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":186 + /* "View.MemoryView":187 * cdef int bufmode = -1 * if self.mode == u"c": * bufmode = PyBUF_C_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS # <<<<<<<<<<<<<< @@ -9643,7 +9574,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru */ __pyx_v_bufmode = (PyBUF_C_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS); - /* "View.MemoryView":185 + /* "View.MemoryView":186 * def __getbuffer__(self, Py_buffer *info, int flags): * cdef int bufmode = -1 * if self.mode == u"c": # <<<<<<<<<<<<<< @@ -9653,18 +9584,18 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru goto __pyx_L3; } - /* "View.MemoryView":187 + /* "View.MemoryView":188 * if self.mode == u"c": * bufmode = PyBUF_C_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * elif self.mode == u"fortran": # <<<<<<<<<<<<<< * bufmode = PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * if not (flags & bufmode): */ - __pyx_t_2 = (__Pyx_PyUnicode_Equals(__pyx_v_self->mode, __pyx_n_u_fortran, Py_EQ)); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(2, 187, __pyx_L1_error) + __pyx_t_2 = (__Pyx_PyUnicode_Equals(__pyx_v_self->mode, __pyx_n_u_fortran, Py_EQ)); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(2, 188, __pyx_L1_error) __pyx_t_1 = (__pyx_t_2 != 0); if (__pyx_t_1) { - /* "View.MemoryView":188 + /* "View.MemoryView":189 * bufmode = PyBUF_C_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * elif self.mode == u"fortran": * bufmode = PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS # <<<<<<<<<<<<<< @@ -9673,7 +9604,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru */ __pyx_v_bufmode = (PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS); - /* "View.MemoryView":187 + /* "View.MemoryView":188 * if self.mode == u"c": * bufmode = PyBUF_C_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * elif self.mode == u"fortran": # <<<<<<<<<<<<<< @@ -9683,7 +9614,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru } __pyx_L3:; - /* "View.MemoryView":189 + /* "View.MemoryView":190 * elif self.mode == u"fortran": * bufmode = PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * if not (flags & bufmode): # <<<<<<<<<<<<<< @@ -9691,22 +9622,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru * info.buf = self.data */ __pyx_t_1 = ((!((__pyx_v_flags & __pyx_v_bufmode) != 0)) != 0); - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "View.MemoryView":190 + /* "View.MemoryView":191 * bufmode = PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * if not (flags & bufmode): * raise ValueError("Can only create a buffer that is contiguous in memory.") # <<<<<<<<<<<<<< * info.buf = self.data * info.len = self.len */ - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__23, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 190, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__23, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(2, 190, __pyx_L1_error) + __PYX_ERR(2, 191, __pyx_L1_error) - /* "View.MemoryView":189 + /* "View.MemoryView":190 * elif self.mode == u"fortran": * bufmode = PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * if not (flags & bufmode): # <<<<<<<<<<<<<< @@ -9715,7 +9646,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru */ } - /* "View.MemoryView":191 + /* "View.MemoryView":192 * if not (flags & bufmode): * raise ValueError("Can only create a buffer that is contiguous in memory.") * info.buf = self.data # <<<<<<<<<<<<<< @@ -9725,7 +9656,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_4 = __pyx_v_self->data; __pyx_v_info->buf = __pyx_t_4; - /* "View.MemoryView":192 + /* "View.MemoryView":193 * raise ValueError("Can only create a buffer that is contiguous in memory.") * info.buf = self.data * info.len = self.len # <<<<<<<<<<<<<< @@ -9735,7 +9666,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_5 = __pyx_v_self->len; __pyx_v_info->len = __pyx_t_5; - /* "View.MemoryView":193 + /* "View.MemoryView":194 * info.buf = self.data * info.len = self.len * info.ndim = self.ndim # <<<<<<<<<<<<<< @@ -9745,7 +9676,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_6 = __pyx_v_self->ndim; __pyx_v_info->ndim = __pyx_t_6; - /* "View.MemoryView":194 + /* "View.MemoryView":195 * info.len = self.len * info.ndim = self.ndim * info.shape = self._shape # <<<<<<<<<<<<<< @@ -9755,7 +9686,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_7 = __pyx_v_self->_shape; __pyx_v_info->shape = __pyx_t_7; - /* "View.MemoryView":195 + /* "View.MemoryView":196 * info.ndim = self.ndim * info.shape = self._shape * info.strides = self._strides # <<<<<<<<<<<<<< @@ -9765,7 +9696,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_7 = __pyx_v_self->_strides; __pyx_v_info->strides = __pyx_t_7; - /* "View.MemoryView":196 + /* "View.MemoryView":197 * info.shape = self._shape * info.strides = self._strides * info.suboffsets = NULL # <<<<<<<<<<<<<< @@ -9774,7 +9705,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru */ __pyx_v_info->suboffsets = NULL; - /* "View.MemoryView":197 + /* "View.MemoryView":198 * info.strides = self._strides * info.suboffsets = NULL * info.itemsize = self.itemsize # <<<<<<<<<<<<<< @@ -9784,7 +9715,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_5 = __pyx_v_self->itemsize; __pyx_v_info->itemsize = __pyx_t_5; - /* "View.MemoryView":198 + /* "View.MemoryView":199 * info.suboffsets = NULL * info.itemsize = self.itemsize * info.readonly = 0 # <<<<<<<<<<<<<< @@ -9793,7 +9724,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru */ __pyx_v_info->readonly = 0; - /* "View.MemoryView":200 + /* "View.MemoryView":201 * info.readonly = 0 * * if flags & PyBUF_FORMAT: # <<<<<<<<<<<<<< @@ -9803,7 +9734,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_1 = ((__pyx_v_flags & PyBUF_FORMAT) != 0); if (__pyx_t_1) { - /* "View.MemoryView":201 + /* "View.MemoryView":202 * * if flags & PyBUF_FORMAT: * info.format = self.format # <<<<<<<<<<<<<< @@ -9813,7 +9744,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __pyx_t_4 = __pyx_v_self->format; __pyx_v_info->format = __pyx_t_4; - /* "View.MemoryView":200 + /* "View.MemoryView":201 * info.readonly = 0 * * if flags & PyBUF_FORMAT: # <<<<<<<<<<<<<< @@ -9823,7 +9754,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru goto __pyx_L5; } - /* "View.MemoryView":203 + /* "View.MemoryView":204 * info.format = self.format * else: * info.format = NULL # <<<<<<<<<<<<<< @@ -9835,7 +9766,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru } __pyx_L5:; - /* "View.MemoryView":205 + /* "View.MemoryView":206 * info.format = NULL * * info.obj = self # <<<<<<<<<<<<<< @@ -9848,7 +9779,7 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - /* "View.MemoryView":183 + /* "View.MemoryView":184 * * @cname('getbuffer') * def __getbuffer__(self, Py_buffer *info, int flags): # <<<<<<<<<<<<<< @@ -9863,22 +9794,22 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_2__getbuffer__(stru __Pyx_XDECREF(__pyx_t_3); __Pyx_AddTraceback("View.MemoryView.array.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; - if (__pyx_v_info != NULL && __pyx_v_info->obj != NULL) { + if (__pyx_v_info->obj != NULL) { __Pyx_GOTREF(__pyx_v_info->obj); - __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = NULL; + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } goto __pyx_L2; __pyx_L0:; - if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) { - __Pyx_GOTREF(Py_None); - __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL; + if (__pyx_v_info->obj == Py_None) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } __pyx_L2:; __Pyx_RefNannyFinishContext(); return __pyx_r; } -/* "View.MemoryView":209 +/* "View.MemoryView":210 * __pyx_getbuffer = capsule( &__pyx_array_getbuffer, "getbuffer(obj, view, flags)") * * def __dealloc__(array self): # <<<<<<<<<<<<<< @@ -9902,7 +9833,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc int __pyx_t_1; __Pyx_RefNannySetupContext("__dealloc__", 0); - /* "View.MemoryView":210 + /* "View.MemoryView":211 * * def __dealloc__(array self): * if self.callback_free_data != NULL: # <<<<<<<<<<<<<< @@ -9912,7 +9843,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc __pyx_t_1 = ((__pyx_v_self->callback_free_data != NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":211 + /* "View.MemoryView":212 * def __dealloc__(array self): * if self.callback_free_data != NULL: * self.callback_free_data(self.data) # <<<<<<<<<<<<<< @@ -9921,7 +9852,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc */ __pyx_v_self->callback_free_data(__pyx_v_self->data); - /* "View.MemoryView":210 + /* "View.MemoryView":211 * * def __dealloc__(array self): * if self.callback_free_data != NULL: # <<<<<<<<<<<<<< @@ -9931,7 +9862,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc goto __pyx_L3; } - /* "View.MemoryView":212 + /* "View.MemoryView":213 * if self.callback_free_data != NULL: * self.callback_free_data(self.data) * elif self.free_data: # <<<<<<<<<<<<<< @@ -9941,7 +9872,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc __pyx_t_1 = (__pyx_v_self->free_data != 0); if (__pyx_t_1) { - /* "View.MemoryView":213 + /* "View.MemoryView":214 * self.callback_free_data(self.data) * elif self.free_data: * if self.dtype_is_object: # <<<<<<<<<<<<<< @@ -9951,7 +9882,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc __pyx_t_1 = (__pyx_v_self->dtype_is_object != 0); if (__pyx_t_1) { - /* "View.MemoryView":214 + /* "View.MemoryView":215 * elif self.free_data: * if self.dtype_is_object: * refcount_objects_in_slice(self.data, self._shape, # <<<<<<<<<<<<<< @@ -9960,7 +9891,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc */ __pyx_memoryview_refcount_objects_in_slice(__pyx_v_self->data, __pyx_v_self->_shape, __pyx_v_self->_strides, __pyx_v_self->ndim, 0); - /* "View.MemoryView":213 + /* "View.MemoryView":214 * self.callback_free_data(self.data) * elif self.free_data: * if self.dtype_is_object: # <<<<<<<<<<<<<< @@ -9969,7 +9900,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc */ } - /* "View.MemoryView":216 + /* "View.MemoryView":217 * refcount_objects_in_slice(self.data, self._shape, * self._strides, self.ndim, False) * free(self.data) # <<<<<<<<<<<<<< @@ -9978,7 +9909,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc */ free(__pyx_v_self->data); - /* "View.MemoryView":212 + /* "View.MemoryView":213 * if self.callback_free_data != NULL: * self.callback_free_data(self.data) * elif self.free_data: # <<<<<<<<<<<<<< @@ -9988,7 +9919,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc } __pyx_L3:; - /* "View.MemoryView":217 + /* "View.MemoryView":218 * self._strides, self.ndim, False) * free(self.data) * PyObject_Free(self._shape) # <<<<<<<<<<<<<< @@ -9997,7 +9928,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc */ PyObject_Free(__pyx_v_self->_shape); - /* "View.MemoryView":209 + /* "View.MemoryView":210 * __pyx_getbuffer = capsule( &__pyx_array_getbuffer, "getbuffer(obj, view, flags)") * * def __dealloc__(array self): # <<<<<<<<<<<<<< @@ -10009,7 +9940,7 @@ static void __pyx_array___pyx_pf_15View_dot_MemoryView_5array_4__dealloc__(struc __Pyx_RefNannyFinishContext(); } -/* "View.MemoryView":220 +/* "View.MemoryView":221 * * @property * def memview(self): # <<<<<<<<<<<<<< @@ -10036,7 +9967,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_5array_7memview___get__(struct _ PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":221 + /* "View.MemoryView":222 * @property * def memview(self): * return self.get_memview() # <<<<<<<<<<<<<< @@ -10044,13 +9975,13 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_5array_7memview___get__(struct _ * @cname('get_memview') */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = ((struct __pyx_vtabstruct_array *)__pyx_v_self->__pyx_vtab)->get_memview(__pyx_v_self); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 221, __pyx_L1_error) + __pyx_t_1 = ((struct __pyx_vtabstruct_array *)__pyx_v_self->__pyx_vtab)->get_memview(__pyx_v_self); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 222, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":220 + /* "View.MemoryView":221 * * @property * def memview(self): # <<<<<<<<<<<<<< @@ -10069,7 +10000,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_5array_7memview___get__(struct _ return __pyx_r; } -/* "View.MemoryView":224 +/* "View.MemoryView":225 * * @cname('get_memview') * cdef get_memview(self): # <<<<<<<<<<<<<< @@ -10086,7 +10017,7 @@ static PyObject *__pyx_array_get_memview(struct __pyx_array_obj *__pyx_v_self) { PyObject *__pyx_t_3 = NULL; __Pyx_RefNannySetupContext("get_memview", 0); - /* "View.MemoryView":225 + /* "View.MemoryView":226 * @cname('get_memview') * cdef get_memview(self): * flags = PyBUF_ANY_CONTIGUOUS|PyBUF_FORMAT|PyBUF_WRITABLE # <<<<<<<<<<<<<< @@ -10095,7 +10026,7 @@ static PyObject *__pyx_array_get_memview(struct __pyx_array_obj *__pyx_v_self) { */ __pyx_v_flags = ((PyBUF_ANY_CONTIGUOUS | PyBUF_FORMAT) | PyBUF_WRITABLE); - /* "View.MemoryView":226 + /* "View.MemoryView":227 * cdef get_memview(self): * flags = PyBUF_ANY_CONTIGUOUS|PyBUF_FORMAT|PyBUF_WRITABLE * return memoryview(self, flags, self.dtype_is_object) # <<<<<<<<<<<<<< @@ -10103,11 +10034,11 @@ static PyObject *__pyx_array_get_memview(struct __pyx_array_obj *__pyx_v_self) { * def __len__(self): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_flags); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 226, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_flags); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 227, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyBool_FromLong(__pyx_v_self->dtype_is_object); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 226, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyBool_FromLong(__pyx_v_self->dtype_is_object); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 227, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyTuple_New(3); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 226, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(3); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 227, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(((PyObject *)__pyx_v_self)); __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); @@ -10118,14 +10049,14 @@ static PyObject *__pyx_array_get_memview(struct __pyx_array_obj *__pyx_v_self) { PyTuple_SET_ITEM(__pyx_t_3, 2, __pyx_t_2); __pyx_t_1 = 0; __pyx_t_2 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryview_type), __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 226, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryview_type), __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 227, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":224 + /* "View.MemoryView":225 * * @cname('get_memview') * cdef get_memview(self): # <<<<<<<<<<<<<< @@ -10146,7 +10077,7 @@ static PyObject *__pyx_array_get_memview(struct __pyx_array_obj *__pyx_v_self) { return __pyx_r; } -/* "View.MemoryView":228 +/* "View.MemoryView":229 * return memoryview(self, flags, self.dtype_is_object) * * def __len__(self): # <<<<<<<<<<<<<< @@ -10172,7 +10103,7 @@ static Py_ssize_t __pyx_array___pyx_pf_15View_dot_MemoryView_5array_6__len__(str __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__len__", 0); - /* "View.MemoryView":229 + /* "View.MemoryView":230 * * def __len__(self): * return self._shape[0] # <<<<<<<<<<<<<< @@ -10182,7 +10113,7 @@ static Py_ssize_t __pyx_array___pyx_pf_15View_dot_MemoryView_5array_6__len__(str __pyx_r = (__pyx_v_self->_shape[0]); goto __pyx_L0; - /* "View.MemoryView":228 + /* "View.MemoryView":229 * return memoryview(self, flags, self.dtype_is_object) * * def __len__(self): # <<<<<<<<<<<<<< @@ -10196,7 +10127,7 @@ static Py_ssize_t __pyx_array___pyx_pf_15View_dot_MemoryView_5array_6__len__(str return __pyx_r; } -/* "View.MemoryView":231 +/* "View.MemoryView":232 * return self._shape[0] * * def __getattr__(self, attr): # <<<<<<<<<<<<<< @@ -10224,7 +10155,7 @@ static PyObject *__pyx_array___pyx_pf_15View_dot_MemoryView_5array_8__getattr__( PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("__getattr__", 0); - /* "View.MemoryView":232 + /* "View.MemoryView":233 * * def __getattr__(self, attr): * return getattr(self.memview, attr) # <<<<<<<<<<<<<< @@ -10232,16 +10163,16 @@ static PyObject *__pyx_array___pyx_pf_15View_dot_MemoryView_5array_8__getattr__( * def __getitem__(self, item): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_memview); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 232, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_memview); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_GetAttr(__pyx_t_1, __pyx_v_attr); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 232, __pyx_L1_error) + __pyx_t_2 = __Pyx_GetAttr(__pyx_t_1, __pyx_v_attr); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":231 + /* "View.MemoryView":232 * return self._shape[0] * * def __getattr__(self, attr): # <<<<<<<<<<<<<< @@ -10261,7 +10192,7 @@ static PyObject *__pyx_array___pyx_pf_15View_dot_MemoryView_5array_8__getattr__( return __pyx_r; } -/* "View.MemoryView":234 +/* "View.MemoryView":235 * return getattr(self.memview, attr) * * def __getitem__(self, item): # <<<<<<<<<<<<<< @@ -10289,7 +10220,7 @@ static PyObject *__pyx_array___pyx_pf_15View_dot_MemoryView_5array_10__getitem__ PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("__getitem__", 0); - /* "View.MemoryView":235 + /* "View.MemoryView":236 * * def __getitem__(self, item): * return self.memview[item] # <<<<<<<<<<<<<< @@ -10297,16 +10228,16 @@ static PyObject *__pyx_array___pyx_pf_15View_dot_MemoryView_5array_10__getitem__ * def __setitem__(self, item, value): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_memview); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 235, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_memview); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 236, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = PyObject_GetItem(__pyx_t_1, __pyx_v_item); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 235, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetItem(__pyx_t_1, __pyx_v_item); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 236, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":234 + /* "View.MemoryView":235 * return getattr(self.memview, attr) * * def __getitem__(self, item): # <<<<<<<<<<<<<< @@ -10326,7 +10257,7 @@ static PyObject *__pyx_array___pyx_pf_15View_dot_MemoryView_5array_10__getitem__ return __pyx_r; } -/* "View.MemoryView":237 +/* "View.MemoryView":238 * return self.memview[item] * * def __setitem__(self, item, value): # <<<<<<<<<<<<<< @@ -10353,19 +10284,19 @@ static int __pyx_array___pyx_pf_15View_dot_MemoryView_5array_12__setitem__(struc PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__setitem__", 0); - /* "View.MemoryView":238 + /* "View.MemoryView":239 * * def __setitem__(self, item, value): * self.memview[item] = value # <<<<<<<<<<<<<< * * */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_memview); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 238, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_memview); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 239, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (unlikely(PyObject_SetItem(__pyx_t_1, __pyx_v_item, __pyx_v_value) < 0)) __PYX_ERR(2, 238, __pyx_L1_error) + if (unlikely(PyObject_SetItem(__pyx_t_1, __pyx_v_item, __pyx_v_value) < 0)) __PYX_ERR(2, 239, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "View.MemoryView":237 + /* "View.MemoryView":238 * return self.memview[item] * * def __setitem__(self, item, value): # <<<<<<<<<<<<<< @@ -10492,7 +10423,7 @@ static PyObject *__pyx_pf___pyx_array_2__setstate_cython__(CYTHON_UNUSED struct return __pyx_r; } -/* "View.MemoryView":242 +/* "View.MemoryView":243 * * @cname("__pyx_array_new") * cdef array array_cwrapper(tuple shape, Py_ssize_t itemsize, char *format, # <<<<<<<<<<<<<< @@ -10511,7 +10442,7 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize PyObject *__pyx_t_5 = NULL; __Pyx_RefNannySetupContext("array_cwrapper", 0); - /* "View.MemoryView":246 + /* "View.MemoryView":247 * cdef array result * * if buf == NULL: # <<<<<<<<<<<<<< @@ -10521,20 +10452,20 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize __pyx_t_1 = ((__pyx_v_buf == NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":247 + /* "View.MemoryView":248 * * if buf == NULL: * result = array(shape, itemsize, format, mode.decode('ASCII')) # <<<<<<<<<<<<<< * else: * result = array(shape, itemsize, format, mode.decode('ASCII'), */ - __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_itemsize); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 247, __pyx_L1_error) + __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_itemsize); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 248, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyBytes_FromString(__pyx_v_format); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 247, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyBytes_FromString(__pyx_v_format); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 248, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = __Pyx_decode_c_string(__pyx_v_mode, 0, strlen(__pyx_v_mode), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 247, __pyx_L1_error) + __pyx_t_4 = __Pyx_decode_c_string(__pyx_v_mode, 0, strlen(__pyx_v_mode), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 248, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_5 = PyTuple_New(4); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 247, __pyx_L1_error) + __pyx_t_5 = PyTuple_New(4); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 248, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_INCREF(__pyx_v_shape); __Pyx_GIVEREF(__pyx_v_shape); @@ -10548,13 +10479,13 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize __pyx_t_2 = 0; __pyx_t_3 = 0; __pyx_t_4 = 0; - __pyx_t_4 = __Pyx_PyObject_Call(((PyObject *)__pyx_array_type), __pyx_t_5, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 247, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(((PyObject *)__pyx_array_type), __pyx_t_5, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 248, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __pyx_v_result = ((struct __pyx_array_obj *)__pyx_t_4); __pyx_t_4 = 0; - /* "View.MemoryView":246 + /* "View.MemoryView":247 * cdef array result * * if buf == NULL: # <<<<<<<<<<<<<< @@ -10564,7 +10495,7 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize goto __pyx_L3; } - /* "View.MemoryView":249 + /* "View.MemoryView":250 * result = array(shape, itemsize, format, mode.decode('ASCII')) * else: * result = array(shape, itemsize, format, mode.decode('ASCII'), # <<<<<<<<<<<<<< @@ -10572,13 +10503,13 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize * result.data = buf */ /*else*/ { - __pyx_t_4 = PyInt_FromSsize_t(__pyx_v_itemsize); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 249, __pyx_L1_error) + __pyx_t_4 = PyInt_FromSsize_t(__pyx_v_itemsize); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_5 = __Pyx_PyBytes_FromString(__pyx_v_format); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 249, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyBytes_FromString(__pyx_v_format); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); - __pyx_t_3 = __Pyx_decode_c_string(__pyx_v_mode, 0, strlen(__pyx_v_mode), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 249, __pyx_L1_error) + __pyx_t_3 = __Pyx_decode_c_string(__pyx_v_mode, 0, strlen(__pyx_v_mode), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = PyTuple_New(4); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 249, __pyx_L1_error) + __pyx_t_2 = PyTuple_New(4); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_v_shape); __Pyx_GIVEREF(__pyx_v_shape); @@ -10593,32 +10524,32 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize __pyx_t_5 = 0; __pyx_t_3 = 0; - /* "View.MemoryView":250 + /* "View.MemoryView":251 * else: * result = array(shape, itemsize, format, mode.decode('ASCII'), * allocate_buffer=False) # <<<<<<<<<<<<<< * result.data = buf * */ - __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 250, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 251, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_allocate_buffer, Py_False) < 0) __PYX_ERR(2, 250, __pyx_L1_error) + if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_allocate_buffer, Py_False) < 0) __PYX_ERR(2, 251, __pyx_L1_error) - /* "View.MemoryView":249 + /* "View.MemoryView":250 * result = array(shape, itemsize, format, mode.decode('ASCII')) * else: * result = array(shape, itemsize, format, mode.decode('ASCII'), # <<<<<<<<<<<<<< * allocate_buffer=False) * result.data = buf */ - __pyx_t_5 = __Pyx_PyObject_Call(((PyObject *)__pyx_array_type), __pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 249, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(((PyObject *)__pyx_array_type), __pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_result = ((struct __pyx_array_obj *)__pyx_t_5); __pyx_t_5 = 0; - /* "View.MemoryView":251 + /* "View.MemoryView":252 * result = array(shape, itemsize, format, mode.decode('ASCII'), * allocate_buffer=False) * result.data = buf # <<<<<<<<<<<<<< @@ -10629,7 +10560,7 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize } __pyx_L3:; - /* "View.MemoryView":253 + /* "View.MemoryView":254 * result.data = buf * * return result # <<<<<<<<<<<<<< @@ -10641,7 +10572,7 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize __pyx_r = __pyx_v_result; goto __pyx_L0; - /* "View.MemoryView":242 + /* "View.MemoryView":243 * * @cname("__pyx_array_new") * cdef array array_cwrapper(tuple shape, Py_ssize_t itemsize, char *format, # <<<<<<<<<<<<<< @@ -10664,7 +10595,7 @@ static struct __pyx_array_obj *__pyx_array_new(PyObject *__pyx_v_shape, Py_ssize return __pyx_r; } -/* "View.MemoryView":279 +/* "View.MemoryView":280 * cdef class Enum(object): * cdef object name * def __init__(self, name): # <<<<<<<<<<<<<< @@ -10694,11 +10625,11 @@ static int __pyx_MemviewEnum___init__(PyObject *__pyx_v_self, PyObject *__pyx_ar kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_name)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_name)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__init__") < 0)) __PYX_ERR(2, 279, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__init__") < 0)) __PYX_ERR(2, 280, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 1) { goto __pyx_L5_argtuple_error; @@ -10709,7 +10640,7 @@ static int __pyx_MemviewEnum___init__(PyObject *__pyx_v_self, PyObject *__pyx_ar } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("__init__", 1, 1, 1, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(2, 279, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__init__", 1, 1, 1, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(2, 280, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("View.MemoryView.Enum.__init__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -10727,7 +10658,7 @@ static int __pyx_MemviewEnum___pyx_pf_15View_dot_MemoryView_4Enum___init__(struc __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__init__", 0); - /* "View.MemoryView":280 + /* "View.MemoryView":281 * cdef object name * def __init__(self, name): * self.name = name # <<<<<<<<<<<<<< @@ -10740,7 +10671,7 @@ static int __pyx_MemviewEnum___pyx_pf_15View_dot_MemoryView_4Enum___init__(struc __Pyx_DECREF(__pyx_v_self->name); __pyx_v_self->name = __pyx_v_name; - /* "View.MemoryView":279 + /* "View.MemoryView":280 * cdef class Enum(object): * cdef object name * def __init__(self, name): # <<<<<<<<<<<<<< @@ -10754,7 +10685,7 @@ static int __pyx_MemviewEnum___pyx_pf_15View_dot_MemoryView_4Enum___init__(struc return __pyx_r; } -/* "View.MemoryView":281 +/* "View.MemoryView":282 * def __init__(self, name): * self.name = name * def __repr__(self): # <<<<<<<<<<<<<< @@ -10780,7 +10711,7 @@ static PyObject *__pyx_MemviewEnum___pyx_pf_15View_dot_MemoryView_4Enum_2__repr_ __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__repr__", 0); - /* "View.MemoryView":282 + /* "View.MemoryView":283 * self.name = name * def __repr__(self): * return self.name # <<<<<<<<<<<<<< @@ -10792,7 +10723,7 @@ static PyObject *__pyx_MemviewEnum___pyx_pf_15View_dot_MemoryView_4Enum_2__repr_ __pyx_r = __pyx_v_self->name; goto __pyx_L0; - /* "View.MemoryView":281 + /* "View.MemoryView":282 * def __init__(self, name): * self.name = name * def __repr__(self): # <<<<<<<<<<<<<< @@ -11094,7 +11025,7 @@ static PyObject *__pyx_pf___pyx_MemviewEnum_2__setstate_cython__(struct __pyx_Me return __pyx_r; } -/* "View.MemoryView":296 +/* "View.MemoryView":297 * * @cname('__pyx_align_pointer') * cdef void *align_pointer(void *memory, size_t alignment) nogil: # <<<<<<<<<<<<<< @@ -11108,7 +11039,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) void *__pyx_r; int __pyx_t_1; - /* "View.MemoryView":298 + /* "View.MemoryView":299 * cdef void *align_pointer(void *memory, size_t alignment) nogil: * "Align pointer memory on a given boundary" * cdef Py_intptr_t aligned_p = memory # <<<<<<<<<<<<<< @@ -11117,7 +11048,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) */ __pyx_v_aligned_p = ((Py_intptr_t)__pyx_v_memory); - /* "View.MemoryView":302 + /* "View.MemoryView":303 * * with cython.cdivision(True): * offset = aligned_p % alignment # <<<<<<<<<<<<<< @@ -11126,7 +11057,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) */ __pyx_v_offset = (__pyx_v_aligned_p % __pyx_v_alignment); - /* "View.MemoryView":304 + /* "View.MemoryView":305 * offset = aligned_p % alignment * * if offset > 0: # <<<<<<<<<<<<<< @@ -11136,7 +11067,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) __pyx_t_1 = ((__pyx_v_offset > 0) != 0); if (__pyx_t_1) { - /* "View.MemoryView":305 + /* "View.MemoryView":306 * * if offset > 0: * aligned_p += alignment - offset # <<<<<<<<<<<<<< @@ -11145,7 +11076,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) */ __pyx_v_aligned_p = (__pyx_v_aligned_p + (__pyx_v_alignment - __pyx_v_offset)); - /* "View.MemoryView":304 + /* "View.MemoryView":305 * offset = aligned_p % alignment * * if offset > 0: # <<<<<<<<<<<<<< @@ -11154,7 +11085,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) */ } - /* "View.MemoryView":307 + /* "View.MemoryView":308 * aligned_p += alignment - offset * * return aligned_p # <<<<<<<<<<<<<< @@ -11164,7 +11095,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) __pyx_r = ((void *)__pyx_v_aligned_p); goto __pyx_L0; - /* "View.MemoryView":296 + /* "View.MemoryView":297 * * @cname('__pyx_align_pointer') * cdef void *align_pointer(void *memory, size_t alignment) nogil: # <<<<<<<<<<<<<< @@ -11177,7 +11108,7 @@ static void *__pyx_align_pointer(void *__pyx_v_memory, size_t __pyx_v_alignment) return __pyx_r; } -/* "View.MemoryView":343 +/* "View.MemoryView":344 * cdef __Pyx_TypeInfo *typeinfo * * def __cinit__(memoryview self, object obj, int flags, bint dtype_is_object=False): # <<<<<<<<<<<<<< @@ -11213,23 +11144,23 @@ static int __pyx_memoryview___cinit__(PyObject *__pyx_v_self, PyObject *__pyx_ar kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_obj)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_obj)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_flags)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_flags)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 2, 3, 1); __PYX_ERR(2, 343, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 2, 3, 1); __PYX_ERR(2, 344, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: if (kw_args > 0) { - PyObject* value = PyDict_GetItem(__pyx_kwds, __pyx_n_s_dtype_is_object); + PyObject* value = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_dtype_is_object); if (value) { values[2] = value; kw_args--; } } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__cinit__") < 0)) __PYX_ERR(2, 343, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__cinit__") < 0)) __PYX_ERR(2, 344, __pyx_L3_error) } } else { switch (PyTuple_GET_SIZE(__pyx_args)) { @@ -11242,16 +11173,16 @@ static int __pyx_memoryview___cinit__(PyObject *__pyx_v_self, PyObject *__pyx_ar } } __pyx_v_obj = values[0]; - __pyx_v_flags = __Pyx_PyInt_As_int(values[1]); if (unlikely((__pyx_v_flags == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 343, __pyx_L3_error) + __pyx_v_flags = __Pyx_PyInt_As_int(values[1]); if (unlikely((__pyx_v_flags == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 344, __pyx_L3_error) if (values[2]) { - __pyx_v_dtype_is_object = __Pyx_PyObject_IsTrue(values[2]); if (unlikely((__pyx_v_dtype_is_object == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 343, __pyx_L3_error) + __pyx_v_dtype_is_object = __Pyx_PyObject_IsTrue(values[2]); if (unlikely((__pyx_v_dtype_is_object == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 344, __pyx_L3_error) } else { __pyx_v_dtype_is_object = ((int)0); } } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 2, 3, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(2, 343, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 0, 2, 3, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(2, 344, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("View.MemoryView.memoryview.__cinit__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -11273,7 +11204,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ int __pyx_t_4; __Pyx_RefNannySetupContext("__cinit__", 0); - /* "View.MemoryView":344 + /* "View.MemoryView":345 * * def __cinit__(memoryview self, object obj, int flags, bint dtype_is_object=False): * self.obj = obj # <<<<<<<<<<<<<< @@ -11286,7 +11217,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __Pyx_DECREF(__pyx_v_self->obj); __pyx_v_self->obj = __pyx_v_obj; - /* "View.MemoryView":345 + /* "View.MemoryView":346 * def __cinit__(memoryview self, object obj, int flags, bint dtype_is_object=False): * self.obj = obj * self.flags = flags # <<<<<<<<<<<<<< @@ -11295,7 +11226,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ __pyx_v_self->flags = __pyx_v_flags; - /* "View.MemoryView":346 + /* "View.MemoryView":347 * self.obj = obj * self.flags = flags * if type(self) is memoryview or obj is not None: # <<<<<<<<<<<<<< @@ -11315,16 +11246,16 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __pyx_L4_bool_binop_done:; if (__pyx_t_1) { - /* "View.MemoryView":347 + /* "View.MemoryView":348 * self.flags = flags * if type(self) is memoryview or obj is not None: * __Pyx_GetBuffer(obj, &self.view, flags) # <<<<<<<<<<<<<< * if self.view.obj == NULL: * (<__pyx_buffer *> &self.view).obj = Py_None */ - __pyx_t_4 = __Pyx_GetBuffer(__pyx_v_obj, (&__pyx_v_self->view), __pyx_v_flags); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(2, 347, __pyx_L1_error) + __pyx_t_4 = __Pyx_GetBuffer(__pyx_v_obj, (&__pyx_v_self->view), __pyx_v_flags); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(2, 348, __pyx_L1_error) - /* "View.MemoryView":348 + /* "View.MemoryView":349 * if type(self) is memoryview or obj is not None: * __Pyx_GetBuffer(obj, &self.view, flags) * if self.view.obj == NULL: # <<<<<<<<<<<<<< @@ -11334,7 +11265,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __pyx_t_1 = ((((PyObject *)__pyx_v_self->view.obj) == NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":349 + /* "View.MemoryView":350 * __Pyx_GetBuffer(obj, &self.view, flags) * if self.view.obj == NULL: * (<__pyx_buffer *> &self.view).obj = Py_None # <<<<<<<<<<<<<< @@ -11343,7 +11274,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ ((Py_buffer *)(&__pyx_v_self->view))->obj = Py_None; - /* "View.MemoryView":350 + /* "View.MemoryView":351 * if self.view.obj == NULL: * (<__pyx_buffer *> &self.view).obj = Py_None * Py_INCREF(Py_None) # <<<<<<<<<<<<<< @@ -11352,7 +11283,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ Py_INCREF(Py_None); - /* "View.MemoryView":348 + /* "View.MemoryView":349 * if type(self) is memoryview or obj is not None: * __Pyx_GetBuffer(obj, &self.view, flags) * if self.view.obj == NULL: # <<<<<<<<<<<<<< @@ -11361,7 +11292,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ } - /* "View.MemoryView":346 + /* "View.MemoryView":347 * self.obj = obj * self.flags = flags * if type(self) is memoryview or obj is not None: # <<<<<<<<<<<<<< @@ -11370,7 +11301,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ } - /* "View.MemoryView":353 + /* "View.MemoryView":354 * * global __pyx_memoryview_thread_locks_used * if __pyx_memoryview_thread_locks_used < THREAD_LOCKS_PREALLOCATED: # <<<<<<<<<<<<<< @@ -11380,7 +11311,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __pyx_t_1 = ((__pyx_memoryview_thread_locks_used < 8) != 0); if (__pyx_t_1) { - /* "View.MemoryView":354 + /* "View.MemoryView":355 * global __pyx_memoryview_thread_locks_used * if __pyx_memoryview_thread_locks_used < THREAD_LOCKS_PREALLOCATED: * self.lock = __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] # <<<<<<<<<<<<<< @@ -11389,7 +11320,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ __pyx_v_self->lock = (__pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used]); - /* "View.MemoryView":355 + /* "View.MemoryView":356 * if __pyx_memoryview_thread_locks_used < THREAD_LOCKS_PREALLOCATED: * self.lock = __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] * __pyx_memoryview_thread_locks_used += 1 # <<<<<<<<<<<<<< @@ -11398,7 +11329,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ __pyx_memoryview_thread_locks_used = (__pyx_memoryview_thread_locks_used + 1); - /* "View.MemoryView":353 + /* "View.MemoryView":354 * * global __pyx_memoryview_thread_locks_used * if __pyx_memoryview_thread_locks_used < THREAD_LOCKS_PREALLOCATED: # <<<<<<<<<<<<<< @@ -11407,7 +11338,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ } - /* "View.MemoryView":356 + /* "View.MemoryView":357 * self.lock = __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] * __pyx_memoryview_thread_locks_used += 1 * if self.lock is NULL: # <<<<<<<<<<<<<< @@ -11417,7 +11348,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __pyx_t_1 = ((__pyx_v_self->lock == NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":357 + /* "View.MemoryView":358 * __pyx_memoryview_thread_locks_used += 1 * if self.lock is NULL: * self.lock = PyThread_allocate_lock() # <<<<<<<<<<<<<< @@ -11426,7 +11357,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ __pyx_v_self->lock = PyThread_allocate_lock(); - /* "View.MemoryView":358 + /* "View.MemoryView":359 * if self.lock is NULL: * self.lock = PyThread_allocate_lock() * if self.lock is NULL: # <<<<<<<<<<<<<< @@ -11434,18 +11365,18 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ * */ __pyx_t_1 = ((__pyx_v_self->lock == NULL) != 0); - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "View.MemoryView":359 + /* "View.MemoryView":360 * self.lock = PyThread_allocate_lock() * if self.lock is NULL: * raise MemoryError # <<<<<<<<<<<<<< * * if flags & PyBUF_FORMAT: */ - PyErr_NoMemory(); __PYX_ERR(2, 359, __pyx_L1_error) + PyErr_NoMemory(); __PYX_ERR(2, 360, __pyx_L1_error) - /* "View.MemoryView":358 + /* "View.MemoryView":359 * if self.lock is NULL: * self.lock = PyThread_allocate_lock() * if self.lock is NULL: # <<<<<<<<<<<<<< @@ -11454,7 +11385,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ } - /* "View.MemoryView":356 + /* "View.MemoryView":357 * self.lock = __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] * __pyx_memoryview_thread_locks_used += 1 * if self.lock is NULL: # <<<<<<<<<<<<<< @@ -11463,7 +11394,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ } - /* "View.MemoryView":361 + /* "View.MemoryView":362 * raise MemoryError * * if flags & PyBUF_FORMAT: # <<<<<<<<<<<<<< @@ -11473,7 +11404,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __pyx_t_1 = ((__pyx_v_flags & PyBUF_FORMAT) != 0); if (__pyx_t_1) { - /* "View.MemoryView":362 + /* "View.MemoryView":363 * * if flags & PyBUF_FORMAT: * self.dtype_is_object = (self.view.format[0] == b'O' and self.view.format[1] == b'\0') # <<<<<<<<<<<<<< @@ -11491,7 +11422,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ __pyx_L11_bool_binop_done:; __pyx_v_self->dtype_is_object = __pyx_t_1; - /* "View.MemoryView":361 + /* "View.MemoryView":362 * raise MemoryError * * if flags & PyBUF_FORMAT: # <<<<<<<<<<<<<< @@ -11501,7 +11432,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ goto __pyx_L10; } - /* "View.MemoryView":364 + /* "View.MemoryView":365 * self.dtype_is_object = (self.view.format[0] == b'O' and self.view.format[1] == b'\0') * else: * self.dtype_is_object = dtype_is_object # <<<<<<<<<<<<<< @@ -11513,7 +11444,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ } __pyx_L10:; - /* "View.MemoryView":366 + /* "View.MemoryView":367 * self.dtype_is_object = dtype_is_object * * self.acquisition_count_aligned_p = <__pyx_atomic_int *> align_pointer( # <<<<<<<<<<<<<< @@ -11522,7 +11453,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ __pyx_v_self->acquisition_count_aligned_p = ((__pyx_atomic_int *)__pyx_align_pointer(((void *)(&(__pyx_v_self->acquisition_count[0]))), (sizeof(__pyx_atomic_int)))); - /* "View.MemoryView":368 + /* "View.MemoryView":369 * self.acquisition_count_aligned_p = <__pyx_atomic_int *> align_pointer( * &self.acquisition_count[0], sizeof(__pyx_atomic_int)) * self.typeinfo = NULL # <<<<<<<<<<<<<< @@ -11531,7 +11462,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ */ __pyx_v_self->typeinfo = NULL; - /* "View.MemoryView":343 + /* "View.MemoryView":344 * cdef __Pyx_TypeInfo *typeinfo * * def __cinit__(memoryview self, object obj, int flags, bint dtype_is_object=False): # <<<<<<<<<<<<<< @@ -11550,7 +11481,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview___cinit_ return __pyx_r; } -/* "View.MemoryView":370 +/* "View.MemoryView":371 * self.typeinfo = NULL * * def __dealloc__(memoryview self): # <<<<<<<<<<<<<< @@ -11576,11 +11507,12 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal int __pyx_t_2; int __pyx_t_3; int __pyx_t_4; - PyThread_type_lock __pyx_t_5; + int __pyx_t_5; PyThread_type_lock __pyx_t_6; + PyThread_type_lock __pyx_t_7; __Pyx_RefNannySetupContext("__dealloc__", 0); - /* "View.MemoryView":371 + /* "View.MemoryView":372 * * def __dealloc__(memoryview self): * if self.obj is not None: # <<<<<<<<<<<<<< @@ -11591,7 +11523,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":372 + /* "View.MemoryView":373 * def __dealloc__(memoryview self): * if self.obj is not None: * __Pyx_ReleaseBuffer(&self.view) # <<<<<<<<<<<<<< @@ -11600,7 +11532,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal */ __Pyx_ReleaseBuffer((&__pyx_v_self->view)); - /* "View.MemoryView":371 + /* "View.MemoryView":372 * * def __dealloc__(memoryview self): * if self.obj is not None: # <<<<<<<<<<<<<< @@ -11609,7 +11541,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal */ } - /* "View.MemoryView":376 + /* "View.MemoryView":377 * cdef int i * global __pyx_memoryview_thread_locks_used * if self.lock != NULL: # <<<<<<<<<<<<<< @@ -11619,7 +11551,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal __pyx_t_2 = ((__pyx_v_self->lock != NULL) != 0); if (__pyx_t_2) { - /* "View.MemoryView":377 + /* "View.MemoryView":378 * global __pyx_memoryview_thread_locks_used * if self.lock != NULL: * for i in range(__pyx_memoryview_thread_locks_used): # <<<<<<<<<<<<<< @@ -11627,10 +11559,11 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal * __pyx_memoryview_thread_locks_used -= 1 */ __pyx_t_3 = __pyx_memoryview_thread_locks_used; - for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { - __pyx_v_i = __pyx_t_4; + __pyx_t_4 = __pyx_t_3; + for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { + __pyx_v_i = __pyx_t_5; - /* "View.MemoryView":378 + /* "View.MemoryView":379 * if self.lock != NULL: * for i in range(__pyx_memoryview_thread_locks_used): * if __pyx_memoryview_thread_locks[i] is self.lock: # <<<<<<<<<<<<<< @@ -11640,7 +11573,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal __pyx_t_2 = (((__pyx_memoryview_thread_locks[__pyx_v_i]) == __pyx_v_self->lock) != 0); if (__pyx_t_2) { - /* "View.MemoryView":379 + /* "View.MemoryView":380 * for i in range(__pyx_memoryview_thread_locks_used): * if __pyx_memoryview_thread_locks[i] is self.lock: * __pyx_memoryview_thread_locks_used -= 1 # <<<<<<<<<<<<<< @@ -11649,7 +11582,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal */ __pyx_memoryview_thread_locks_used = (__pyx_memoryview_thread_locks_used - 1); - /* "View.MemoryView":380 + /* "View.MemoryView":381 * if __pyx_memoryview_thread_locks[i] is self.lock: * __pyx_memoryview_thread_locks_used -= 1 * if i != __pyx_memoryview_thread_locks_used: # <<<<<<<<<<<<<< @@ -11659,27 +11592,27 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal __pyx_t_2 = ((__pyx_v_i != __pyx_memoryview_thread_locks_used) != 0); if (__pyx_t_2) { - /* "View.MemoryView":382 + /* "View.MemoryView":383 * if i != __pyx_memoryview_thread_locks_used: * __pyx_memoryview_thread_locks[i], __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] = ( * __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used], __pyx_memoryview_thread_locks[i]) # <<<<<<<<<<<<<< * break * else: */ - __pyx_t_5 = (__pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used]); - __pyx_t_6 = (__pyx_memoryview_thread_locks[__pyx_v_i]); + __pyx_t_6 = (__pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used]); + __pyx_t_7 = (__pyx_memoryview_thread_locks[__pyx_v_i]); - /* "View.MemoryView":381 + /* "View.MemoryView":382 * __pyx_memoryview_thread_locks_used -= 1 * if i != __pyx_memoryview_thread_locks_used: * __pyx_memoryview_thread_locks[i], __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] = ( # <<<<<<<<<<<<<< * __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used], __pyx_memoryview_thread_locks[i]) * break */ - (__pyx_memoryview_thread_locks[__pyx_v_i]) = __pyx_t_5; - (__pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used]) = __pyx_t_6; + (__pyx_memoryview_thread_locks[__pyx_v_i]) = __pyx_t_6; + (__pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used]) = __pyx_t_7; - /* "View.MemoryView":380 + /* "View.MemoryView":381 * if __pyx_memoryview_thread_locks[i] is self.lock: * __pyx_memoryview_thread_locks_used -= 1 * if i != __pyx_memoryview_thread_locks_used: # <<<<<<<<<<<<<< @@ -11688,7 +11621,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal */ } - /* "View.MemoryView":383 + /* "View.MemoryView":384 * __pyx_memoryview_thread_locks[i], __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used] = ( * __pyx_memoryview_thread_locks[__pyx_memoryview_thread_locks_used], __pyx_memoryview_thread_locks[i]) * break # <<<<<<<<<<<<<< @@ -11697,7 +11630,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal */ goto __pyx_L6_break; - /* "View.MemoryView":378 + /* "View.MemoryView":379 * if self.lock != NULL: * for i in range(__pyx_memoryview_thread_locks_used): * if __pyx_memoryview_thread_locks[i] is self.lock: # <<<<<<<<<<<<<< @@ -11708,7 +11641,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal } /*else*/ { - /* "View.MemoryView":385 + /* "View.MemoryView":386 * break * else: * PyThread_free_lock(self.lock) # <<<<<<<<<<<<<< @@ -11719,7 +11652,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal } __pyx_L6_break:; - /* "View.MemoryView":376 + /* "View.MemoryView":377 * cdef int i * global __pyx_memoryview_thread_locks_used * if self.lock != NULL: # <<<<<<<<<<<<<< @@ -11728,7 +11661,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal */ } - /* "View.MemoryView":370 + /* "View.MemoryView":371 * self.typeinfo = NULL * * def __dealloc__(memoryview self): # <<<<<<<<<<<<<< @@ -11740,7 +11673,7 @@ static void __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_2__deal __Pyx_RefNannyFinishContext(); } -/* "View.MemoryView":387 +/* "View.MemoryView":388 * PyThread_free_lock(self.lock) * * cdef char *get_item_pointer(memoryview self, object index) except NULL: # <<<<<<<<<<<<<< @@ -11763,7 +11696,7 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py char *__pyx_t_7; __Pyx_RefNannySetupContext("get_item_pointer", 0); - /* "View.MemoryView":389 + /* "View.MemoryView":390 * cdef char *get_item_pointer(memoryview self, object index) except NULL: * cdef Py_ssize_t dim * cdef char *itemp = self.view.buf # <<<<<<<<<<<<<< @@ -11772,7 +11705,7 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py */ __pyx_v_itemp = ((char *)__pyx_v_self->view.buf); - /* "View.MemoryView":391 + /* "View.MemoryView":392 * cdef char *itemp = self.view.buf * * for dim, idx in enumerate(index): # <<<<<<<<<<<<<< @@ -11784,26 +11717,26 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py __pyx_t_2 = __pyx_v_index; __Pyx_INCREF(__pyx_t_2); __pyx_t_3 = 0; __pyx_t_4 = NULL; } else { - __pyx_t_3 = -1; __pyx_t_2 = PyObject_GetIter(__pyx_v_index); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 391, __pyx_L1_error) + __pyx_t_3 = -1; __pyx_t_2 = PyObject_GetIter(__pyx_v_index); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 392, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_4 = Py_TYPE(__pyx_t_2)->tp_iternext; if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 391, __pyx_L1_error) + __pyx_t_4 = Py_TYPE(__pyx_t_2)->tp_iternext; if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 392, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_4)) { if (likely(PyList_CheckExact(__pyx_t_2))) { if (__pyx_t_3 >= PyList_GET_SIZE(__pyx_t_2)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_5 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_3); __Pyx_INCREF(__pyx_t_5); __pyx_t_3++; if (unlikely(0 < 0)) __PYX_ERR(2, 391, __pyx_L1_error) + __pyx_t_5 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_3); __Pyx_INCREF(__pyx_t_5); __pyx_t_3++; if (unlikely(0 < 0)) __PYX_ERR(2, 392, __pyx_L1_error) #else - __pyx_t_5 = PySequence_ITEM(__pyx_t_2, __pyx_t_3); __pyx_t_3++; if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 391, __pyx_L1_error) + __pyx_t_5 = PySequence_ITEM(__pyx_t_2, __pyx_t_3); __pyx_t_3++; if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 392, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); #endif } else { if (__pyx_t_3 >= PyTuple_GET_SIZE(__pyx_t_2)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_5 = PyTuple_GET_ITEM(__pyx_t_2, __pyx_t_3); __Pyx_INCREF(__pyx_t_5); __pyx_t_3++; if (unlikely(0 < 0)) __PYX_ERR(2, 391, __pyx_L1_error) + __pyx_t_5 = PyTuple_GET_ITEM(__pyx_t_2, __pyx_t_3); __Pyx_INCREF(__pyx_t_5); __pyx_t_3++; if (unlikely(0 < 0)) __PYX_ERR(2, 392, __pyx_L1_error) #else - __pyx_t_5 = PySequence_ITEM(__pyx_t_2, __pyx_t_3); __pyx_t_3++; if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 391, __pyx_L1_error) + __pyx_t_5 = PySequence_ITEM(__pyx_t_2, __pyx_t_3); __pyx_t_3++; if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 392, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); #endif } @@ -11813,7 +11746,7 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(2, 391, __pyx_L1_error) + else __PYX_ERR(2, 392, __pyx_L1_error) } break; } @@ -11824,18 +11757,18 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py __pyx_v_dim = __pyx_t_1; __pyx_t_1 = (__pyx_t_1 + 1); - /* "View.MemoryView":392 + /* "View.MemoryView":393 * * for dim, idx in enumerate(index): * itemp = pybuffer_index(&self.view, itemp, idx, dim) # <<<<<<<<<<<<<< * * return itemp */ - __pyx_t_6 = __Pyx_PyIndex_AsSsize_t(__pyx_v_idx); if (unlikely((__pyx_t_6 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 392, __pyx_L1_error) - __pyx_t_7 = __pyx_pybuffer_index((&__pyx_v_self->view), __pyx_v_itemp, __pyx_t_6, __pyx_v_dim); if (unlikely(__pyx_t_7 == ((char *)NULL))) __PYX_ERR(2, 392, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyIndex_AsSsize_t(__pyx_v_idx); if (unlikely((__pyx_t_6 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 393, __pyx_L1_error) + __pyx_t_7 = __pyx_pybuffer_index((&__pyx_v_self->view), __pyx_v_itemp, __pyx_t_6, __pyx_v_dim); if (unlikely(__pyx_t_7 == ((char *)NULL))) __PYX_ERR(2, 393, __pyx_L1_error) __pyx_v_itemp = __pyx_t_7; - /* "View.MemoryView":391 + /* "View.MemoryView":392 * cdef char *itemp = self.view.buf * * for dim, idx in enumerate(index): # <<<<<<<<<<<<<< @@ -11845,7 +11778,7 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":394 + /* "View.MemoryView":395 * itemp = pybuffer_index(&self.view, itemp, idx, dim) * * return itemp # <<<<<<<<<<<<<< @@ -11855,7 +11788,7 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py __pyx_r = __pyx_v_itemp; goto __pyx_L0; - /* "View.MemoryView":387 + /* "View.MemoryView":388 * PyThread_free_lock(self.lock) * * cdef char *get_item_pointer(memoryview self, object index) except NULL: # <<<<<<<<<<<<<< @@ -11875,7 +11808,7 @@ static char *__pyx_memoryview_get_item_pointer(struct __pyx_memoryview_obj *__py return __pyx_r; } -/* "View.MemoryView":397 +/* "View.MemoryView":398 * * * def __getitem__(memoryview self, object index): # <<<<<<<<<<<<<< @@ -11910,7 +11843,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ char *__pyx_t_6; __Pyx_RefNannySetupContext("__getitem__", 0); - /* "View.MemoryView":398 + /* "View.MemoryView":399 * * def __getitem__(memoryview self, object index): * if index is Ellipsis: # <<<<<<<<<<<<<< @@ -11921,7 +11854,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":399 + /* "View.MemoryView":400 * def __getitem__(memoryview self, object index): * if index is Ellipsis: * return self # <<<<<<<<<<<<<< @@ -11933,7 +11866,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ __pyx_r = ((PyObject *)__pyx_v_self); goto __pyx_L0; - /* "View.MemoryView":398 + /* "View.MemoryView":399 * * def __getitem__(memoryview self, object index): * if index is Ellipsis: # <<<<<<<<<<<<<< @@ -11942,26 +11875,22 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ */ } - /* "View.MemoryView":401 + /* "View.MemoryView":402 * return self * * have_slices, indices = _unellipsify(index, self.view.ndim) # <<<<<<<<<<<<<< * * cdef char *itemp */ - __pyx_t_3 = _unellipsify(__pyx_v_index, __pyx_v_self->view.ndim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 401, __pyx_L1_error) + __pyx_t_3 = _unellipsify(__pyx_v_index, __pyx_v_self->view.ndim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 402, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); if (likely(__pyx_t_3 != Py_None)) { PyObject* sequence = __pyx_t_3; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(2, 401, __pyx_L1_error) + __PYX_ERR(2, 402, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_4 = PyTuple_GET_ITEM(sequence, 0); @@ -11969,31 +11898,31 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ __Pyx_INCREF(__pyx_t_4); __Pyx_INCREF(__pyx_t_5); #else - __pyx_t_4 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 401, __pyx_L1_error) + __pyx_t_4 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 402, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_5 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 401, __pyx_L1_error) + __pyx_t_5 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 402, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); #endif __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else { - __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(2, 401, __pyx_L1_error) + __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(2, 402, __pyx_L1_error) } __pyx_v_have_slices = __pyx_t_4; __pyx_t_4 = 0; __pyx_v_indices = __pyx_t_5; __pyx_t_5 = 0; - /* "View.MemoryView":404 + /* "View.MemoryView":405 * * cdef char *itemp * if have_slices: # <<<<<<<<<<<<<< * return memview_slice(self, indices) * else: */ - __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_v_have_slices); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(2, 404, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_v_have_slices); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(2, 405, __pyx_L1_error) if (__pyx_t_2) { - /* "View.MemoryView":405 + /* "View.MemoryView":406 * cdef char *itemp * if have_slices: * return memview_slice(self, indices) # <<<<<<<<<<<<<< @@ -12001,13 +11930,13 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ * itemp = self.get_item_pointer(indices) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_3 = ((PyObject *)__pyx_memview_slice(__pyx_v_self, __pyx_v_indices)); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 405, __pyx_L1_error) + __pyx_t_3 = ((PyObject *)__pyx_memview_slice(__pyx_v_self, __pyx_v_indices)); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 406, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; - /* "View.MemoryView":404 + /* "View.MemoryView":405 * * cdef char *itemp * if have_slices: # <<<<<<<<<<<<<< @@ -12016,7 +11945,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ */ } - /* "View.MemoryView":407 + /* "View.MemoryView":408 * return memview_slice(self, indices) * else: * itemp = self.get_item_pointer(indices) # <<<<<<<<<<<<<< @@ -12024,10 +11953,10 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ * */ /*else*/ { - __pyx_t_6 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->get_item_pointer(__pyx_v_self, __pyx_v_indices); if (unlikely(__pyx_t_6 == ((char *)NULL))) __PYX_ERR(2, 407, __pyx_L1_error) + __pyx_t_6 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->get_item_pointer(__pyx_v_self, __pyx_v_indices); if (unlikely(__pyx_t_6 == ((char *)NULL))) __PYX_ERR(2, 408, __pyx_L1_error) __pyx_v_itemp = __pyx_t_6; - /* "View.MemoryView":408 + /* "View.MemoryView":409 * else: * itemp = self.get_item_pointer(indices) * return self.convert_item_to_object(itemp) # <<<<<<<<<<<<<< @@ -12035,14 +11964,14 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ * def __setitem__(memoryview self, object index, object value): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_3 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->convert_item_to_object(__pyx_v_self, __pyx_v_itemp); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 408, __pyx_L1_error) + __pyx_t_3 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->convert_item_to_object(__pyx_v_self, __pyx_v_itemp); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 409, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; } - /* "View.MemoryView":397 + /* "View.MemoryView":398 * * * def __getitem__(memoryview self, object index): # <<<<<<<<<<<<<< @@ -12065,12 +11994,12 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_4_ return __pyx_r; } -/* "View.MemoryView":410 +/* "View.MemoryView":411 * return self.convert_item_to_object(itemp) * * def __setitem__(memoryview self, object index, object value): # <<<<<<<<<<<<<< - * have_slices, index = _unellipsify(index, self.view.ndim) - * + * if self.view.readonly: + * raise TypeError("Cannot assign to read-only memoryview") */ /* Python wrapper */ @@ -12091,111 +12020,139 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_6__setit PyObject *__pyx_v_obj = NULL; int __pyx_r; __Pyx_RefNannyDeclarations - PyObject *__pyx_t_1 = NULL; + int __pyx_t_1; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; - int __pyx_t_4; + PyObject *__pyx_t_4 = NULL; __Pyx_RefNannySetupContext("__setitem__", 0); __Pyx_INCREF(__pyx_v_index); - /* "View.MemoryView":411 + /* "View.MemoryView":412 * * def __setitem__(memoryview self, object index, object value): + * if self.view.readonly: # <<<<<<<<<<<<<< + * raise TypeError("Cannot assign to read-only memoryview") + * + */ + __pyx_t_1 = (__pyx_v_self->view.readonly != 0); + if (unlikely(__pyx_t_1)) { + + /* "View.MemoryView":413 + * def __setitem__(memoryview self, object index, object value): + * if self.view.readonly: + * raise TypeError("Cannot assign to read-only memoryview") # <<<<<<<<<<<<<< + * + * have_slices, index = _unellipsify(index, self.view.ndim) + */ + __pyx_t_2 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__26, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 413, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_Raise(__pyx_t_2, 0, 0, 0); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __PYX_ERR(2, 413, __pyx_L1_error) + + /* "View.MemoryView":412 + * + * def __setitem__(memoryview self, object index, object value): + * if self.view.readonly: # <<<<<<<<<<<<<< + * raise TypeError("Cannot assign to read-only memoryview") + * + */ + } + + /* "View.MemoryView":415 + * raise TypeError("Cannot assign to read-only memoryview") + * * have_slices, index = _unellipsify(index, self.view.ndim) # <<<<<<<<<<<<<< * * if have_slices: */ - __pyx_t_1 = _unellipsify(__pyx_v_index, __pyx_v_self->view.ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 411, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - if (likely(__pyx_t_1 != Py_None)) { - PyObject* sequence = __pyx_t_1; - #if !CYTHON_COMPILING_IN_PYPY - Py_ssize_t size = Py_SIZE(sequence); - #else - Py_ssize_t size = PySequence_Size(sequence); - #endif + __pyx_t_2 = _unellipsify(__pyx_v_index, __pyx_v_self->view.ndim); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 415, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + if (likely(__pyx_t_2 != Py_None)) { + PyObject* sequence = __pyx_t_2; + Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); - __PYX_ERR(2, 411, __pyx_L1_error) + __PYX_ERR(2, 415, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_2 = PyTuple_GET_ITEM(sequence, 0); - __pyx_t_3 = PyTuple_GET_ITEM(sequence, 1); - __Pyx_INCREF(__pyx_t_2); + __pyx_t_3 = PyTuple_GET_ITEM(sequence, 0); + __pyx_t_4 = PyTuple_GET_ITEM(sequence, 1); __Pyx_INCREF(__pyx_t_3); + __Pyx_INCREF(__pyx_t_4); #else - __pyx_t_2 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 411, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 411, __pyx_L1_error) + __pyx_t_3 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 415, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); + __pyx_t_4 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 415, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_4); #endif - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } else { - __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(2, 411, __pyx_L1_error) + __Pyx_RaiseNoneNotIterableError(); __PYX_ERR(2, 415, __pyx_L1_error) } - __pyx_v_have_slices = __pyx_t_2; - __pyx_t_2 = 0; - __Pyx_DECREF_SET(__pyx_v_index, __pyx_t_3); + __pyx_v_have_slices = __pyx_t_3; __pyx_t_3 = 0; + __Pyx_DECREF_SET(__pyx_v_index, __pyx_t_4); + __pyx_t_4 = 0; - /* "View.MemoryView":413 + /* "View.MemoryView":417 * have_slices, index = _unellipsify(index, self.view.ndim) * * if have_slices: # <<<<<<<<<<<<<< * obj = self.is_slice(value) * if obj: */ - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_have_slices); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(2, 413, __pyx_L1_error) - if (__pyx_t_4) { + __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_v_have_slices); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 417, __pyx_L1_error) + if (__pyx_t_1) { - /* "View.MemoryView":414 + /* "View.MemoryView":418 * * if have_slices: * obj = self.is_slice(value) # <<<<<<<<<<<<<< * if obj: * self.setitem_slice_assignment(self[index], obj) */ - __pyx_t_1 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->is_slice(__pyx_v_self, __pyx_v_value); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 414, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_v_obj = __pyx_t_1; - __pyx_t_1 = 0; + __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->is_slice(__pyx_v_self, __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 418, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_v_obj = __pyx_t_2; + __pyx_t_2 = 0; - /* "View.MemoryView":415 + /* "View.MemoryView":419 * if have_slices: * obj = self.is_slice(value) * if obj: # <<<<<<<<<<<<<< * self.setitem_slice_assignment(self[index], obj) * else: */ - __pyx_t_4 = __Pyx_PyObject_IsTrue(__pyx_v_obj); if (unlikely(__pyx_t_4 < 0)) __PYX_ERR(2, 415, __pyx_L1_error) - if (__pyx_t_4) { + __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_v_obj); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 419, __pyx_L1_error) + if (__pyx_t_1) { - /* "View.MemoryView":416 + /* "View.MemoryView":420 * obj = self.is_slice(value) * if obj: * self.setitem_slice_assignment(self[index], obj) # <<<<<<<<<<<<<< * else: * self.setitem_slice_assign_scalar(self[index], value) */ - __pyx_t_1 = PyObject_GetItem(((PyObject *)__pyx_v_self), __pyx_v_index); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 416, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->setitem_slice_assignment(__pyx_v_self, __pyx_t_1, __pyx_v_obj); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 416, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_2 = __Pyx_PyObject_GetItem(((PyObject *)__pyx_v_self), __pyx_v_index); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 420, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __pyx_t_4 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->setitem_slice_assignment(__pyx_v_self, __pyx_t_2, __pyx_v_obj); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 420, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_4); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - /* "View.MemoryView":415 + /* "View.MemoryView":419 * if have_slices: * obj = self.is_slice(value) * if obj: # <<<<<<<<<<<<<< * self.setitem_slice_assignment(self[index], obj) * else: */ - goto __pyx_L4; + goto __pyx_L5; } - /* "View.MemoryView":418 + /* "View.MemoryView":422 * self.setitem_slice_assignment(self[index], obj) * else: * self.setitem_slice_assign_scalar(self[index], value) # <<<<<<<<<<<<<< @@ -12203,27 +12160,27 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_6__setit * self.setitem_indexed(index, value) */ /*else*/ { - __pyx_t_3 = PyObject_GetItem(((PyObject *)__pyx_v_self), __pyx_v_index); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 418, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_memoryview_type))))) __PYX_ERR(2, 418, __pyx_L1_error) - __pyx_t_1 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->setitem_slice_assign_scalar(__pyx_v_self, ((struct __pyx_memoryview_obj *)__pyx_t_3), __pyx_v_value); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 418, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_4 = __Pyx_PyObject_GetItem(((PyObject *)__pyx_v_self), __pyx_v_index); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 422, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_4); + if (!(likely(((__pyx_t_4) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_4, __pyx_memoryview_type))))) __PYX_ERR(2, 422, __pyx_L1_error) + __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->setitem_slice_assign_scalar(__pyx_v_self, ((struct __pyx_memoryview_obj *)__pyx_t_4), __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 422, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } - __pyx_L4:; + __pyx_L5:; - /* "View.MemoryView":413 + /* "View.MemoryView":417 * have_slices, index = _unellipsify(index, self.view.ndim) * * if have_slices: # <<<<<<<<<<<<<< * obj = self.is_slice(value) * if obj: */ - goto __pyx_L3; + goto __pyx_L4; } - /* "View.MemoryView":420 + /* "View.MemoryView":424 * self.setitem_slice_assign_scalar(self[index], value) * else: * self.setitem_indexed(index, value) # <<<<<<<<<<<<<< @@ -12231,27 +12188,27 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_6__setit * cdef is_slice(self, obj): */ /*else*/ { - __pyx_t_1 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->setitem_indexed(__pyx_v_self, __pyx_v_index, __pyx_v_value); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 420, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->setitem_indexed(__pyx_v_self, __pyx_v_index, __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 424, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } - __pyx_L3:; + __pyx_L4:; - /* "View.MemoryView":410 + /* "View.MemoryView":411 * return self.convert_item_to_object(itemp) * * def __setitem__(memoryview self, object index, object value): # <<<<<<<<<<<<<< - * have_slices, index = _unellipsify(index, self.view.ndim) - * + * if self.view.readonly: + * raise TypeError("Cannot assign to read-only memoryview") */ /* function exit code */ __pyx_r = 0; goto __pyx_L0; __pyx_L1_error:; - __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); + __Pyx_XDECREF(__pyx_t_4); __Pyx_AddTraceback("View.MemoryView.memoryview.__setitem__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; __pyx_L0:; @@ -12262,7 +12219,7 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_6__setit return __pyx_r; } -/* "View.MemoryView":422 +/* "View.MemoryView":426 * self.setitem_indexed(index, value) * * cdef is_slice(self, obj): # <<<<<<<<<<<<<< @@ -12285,7 +12242,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __Pyx_RefNannySetupContext("is_slice", 0); __Pyx_INCREF(__pyx_v_obj); - /* "View.MemoryView":423 + /* "View.MemoryView":427 * * cdef is_slice(self, obj): * if not isinstance(obj, memoryview): # <<<<<<<<<<<<<< @@ -12296,7 +12253,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __pyx_t_2 = ((!(__pyx_t_1 != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":424 + /* "View.MemoryView":428 * cdef is_slice(self, obj): * if not isinstance(obj, memoryview): * try: # <<<<<<<<<<<<<< @@ -12312,34 +12269,34 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __Pyx_XGOTREF(__pyx_t_5); /*try:*/ { - /* "View.MemoryView":425 + /* "View.MemoryView":429 * if not isinstance(obj, memoryview): * try: * obj = memoryview(obj, self.flags|PyBUF_ANY_CONTIGUOUS, # <<<<<<<<<<<<<< * self.dtype_is_object) * except TypeError: */ - __pyx_t_6 = __Pyx_PyInt_From_int((__pyx_v_self->flags | PyBUF_ANY_CONTIGUOUS)); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 425, __pyx_L4_error) + __pyx_t_6 = __Pyx_PyInt_From_int((__pyx_v_self->flags | PyBUF_ANY_CONTIGUOUS)); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 429, __pyx_L4_error) __Pyx_GOTREF(__pyx_t_6); - /* "View.MemoryView":426 + /* "View.MemoryView":430 * try: * obj = memoryview(obj, self.flags|PyBUF_ANY_CONTIGUOUS, * self.dtype_is_object) # <<<<<<<<<<<<<< * except TypeError: * return None */ - __pyx_t_7 = __Pyx_PyBool_FromLong(__pyx_v_self->dtype_is_object); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 426, __pyx_L4_error) + __pyx_t_7 = __Pyx_PyBool_FromLong(__pyx_v_self->dtype_is_object); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 430, __pyx_L4_error) __Pyx_GOTREF(__pyx_t_7); - /* "View.MemoryView":425 + /* "View.MemoryView":429 * if not isinstance(obj, memoryview): * try: * obj = memoryview(obj, self.flags|PyBUF_ANY_CONTIGUOUS, # <<<<<<<<<<<<<< * self.dtype_is_object) * except TypeError: */ - __pyx_t_8 = PyTuple_New(3); if (unlikely(!__pyx_t_8)) __PYX_ERR(2, 425, __pyx_L4_error) + __pyx_t_8 = PyTuple_New(3); if (unlikely(!__pyx_t_8)) __PYX_ERR(2, 429, __pyx_L4_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_INCREF(__pyx_v_obj); __Pyx_GIVEREF(__pyx_v_obj); @@ -12350,13 +12307,13 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ PyTuple_SET_ITEM(__pyx_t_8, 2, __pyx_t_7); __pyx_t_6 = 0; __pyx_t_7 = 0; - __pyx_t_7 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryview_type), __pyx_t_8, NULL); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 425, __pyx_L4_error) + __pyx_t_7 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryview_type), __pyx_t_8, NULL); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 429, __pyx_L4_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_DECREF_SET(__pyx_v_obj, __pyx_t_7); __pyx_t_7 = 0; - /* "View.MemoryView":424 + /* "View.MemoryView":428 * cdef is_slice(self, obj): * if not isinstance(obj, memoryview): * try: # <<<<<<<<<<<<<< @@ -12373,7 +12330,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "View.MemoryView":427 + /* "View.MemoryView":431 * obj = memoryview(obj, self.flags|PyBUF_ANY_CONTIGUOUS, * self.dtype_is_object) * except TypeError: # <<<<<<<<<<<<<< @@ -12383,12 +12340,12 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __pyx_t_9 = __Pyx_PyErr_ExceptionMatches(__pyx_builtin_TypeError); if (__pyx_t_9) { __Pyx_AddTraceback("View.MemoryView.memoryview.is_slice", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_7, &__pyx_t_8, &__pyx_t_6) < 0) __PYX_ERR(2, 427, __pyx_L6_except_error) + if (__Pyx_GetException(&__pyx_t_7, &__pyx_t_8, &__pyx_t_6) < 0) __PYX_ERR(2, 431, __pyx_L6_except_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_GOTREF(__pyx_t_8); __Pyx_GOTREF(__pyx_t_6); - /* "View.MemoryView":428 + /* "View.MemoryView":432 * self.dtype_is_object) * except TypeError: * return None # <<<<<<<<<<<<<< @@ -12396,8 +12353,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ * return obj */ __Pyx_XDECREF(__pyx_r); - __Pyx_INCREF(Py_None); - __pyx_r = Py_None; + __pyx_r = Py_None; __Pyx_INCREF(Py_None); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; @@ -12406,7 +12362,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ goto __pyx_L6_except_error; __pyx_L6_except_error:; - /* "View.MemoryView":424 + /* "View.MemoryView":428 * cdef is_slice(self, obj): * if not isinstance(obj, memoryview): * try: # <<<<<<<<<<<<<< @@ -12427,7 +12383,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __pyx_L9_try_end:; } - /* "View.MemoryView":423 + /* "View.MemoryView":427 * * cdef is_slice(self, obj): * if not isinstance(obj, memoryview): # <<<<<<<<<<<<<< @@ -12436,7 +12392,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ */ } - /* "View.MemoryView":430 + /* "View.MemoryView":434 * return None * * return obj # <<<<<<<<<<<<<< @@ -12448,7 +12404,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ __pyx_r = __pyx_v_obj; goto __pyx_L0; - /* "View.MemoryView":422 + /* "View.MemoryView":426 * self.setitem_indexed(index, value) * * cdef is_slice(self, obj): # <<<<<<<<<<<<<< @@ -12470,7 +12426,7 @@ static PyObject *__pyx_memoryview_is_slice(struct __pyx_memoryview_obj *__pyx_v_ return __pyx_r; } -/* "View.MemoryView":432 +/* "View.MemoryView":436 * return obj * * cdef setitem_slice_assignment(self, dst, src): # <<<<<<<<<<<<<< @@ -12489,50 +12445,50 @@ static PyObject *__pyx_memoryview_setitem_slice_assignment(struct __pyx_memoryvi int __pyx_t_4; __Pyx_RefNannySetupContext("setitem_slice_assignment", 0); - /* "View.MemoryView":436 + /* "View.MemoryView":440 * cdef __Pyx_memviewslice src_slice * * memoryview_copy_contents(get_slice_from_memview(src, &src_slice)[0], # <<<<<<<<<<<<<< * get_slice_from_memview(dst, &dst_slice)[0], * src.ndim, dst.ndim, self.dtype_is_object) */ - if (!(likely(((__pyx_v_src) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_src, __pyx_memoryview_type))))) __PYX_ERR(2, 436, __pyx_L1_error) + if (!(likely(((__pyx_v_src) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_src, __pyx_memoryview_type))))) __PYX_ERR(2, 440, __pyx_L1_error) - /* "View.MemoryView":437 + /* "View.MemoryView":441 * * memoryview_copy_contents(get_slice_from_memview(src, &src_slice)[0], * get_slice_from_memview(dst, &dst_slice)[0], # <<<<<<<<<<<<<< * src.ndim, dst.ndim, self.dtype_is_object) * */ - if (!(likely(((__pyx_v_dst) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_dst, __pyx_memoryview_type))))) __PYX_ERR(2, 437, __pyx_L1_error) + if (!(likely(((__pyx_v_dst) == Py_None) || likely(__Pyx_TypeTest(__pyx_v_dst, __pyx_memoryview_type))))) __PYX_ERR(2, 441, __pyx_L1_error) - /* "View.MemoryView":438 + /* "View.MemoryView":442 * memoryview_copy_contents(get_slice_from_memview(src, &src_slice)[0], * get_slice_from_memview(dst, &dst_slice)[0], * src.ndim, dst.ndim, self.dtype_is_object) # <<<<<<<<<<<<<< * * cdef setitem_slice_assign_scalar(self, memoryview dst, value): */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_src, __pyx_n_s_ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 438, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_src, __pyx_n_s_ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 442, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 438, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_2 == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 442, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_dst, __pyx_n_s_ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 438, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_dst, __pyx_n_s_ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 442, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_3 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_3 == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 438, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_As_int(__pyx_t_1); if (unlikely((__pyx_t_3 == (int)-1) && PyErr_Occurred())) __PYX_ERR(2, 442, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "View.MemoryView":436 + /* "View.MemoryView":440 * cdef __Pyx_memviewslice src_slice * * memoryview_copy_contents(get_slice_from_memview(src, &src_slice)[0], # <<<<<<<<<<<<<< * get_slice_from_memview(dst, &dst_slice)[0], * src.ndim, dst.ndim, self.dtype_is_object) */ - __pyx_t_4 = __pyx_memoryview_copy_contents((__pyx_memoryview_get_slice_from_memoryview(((struct __pyx_memoryview_obj *)__pyx_v_src), (&__pyx_v_src_slice))[0]), (__pyx_memoryview_get_slice_from_memoryview(((struct __pyx_memoryview_obj *)__pyx_v_dst), (&__pyx_v_dst_slice))[0]), __pyx_t_2, __pyx_t_3, __pyx_v_self->dtype_is_object); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(2, 436, __pyx_L1_error) + __pyx_t_4 = __pyx_memoryview_copy_contents((__pyx_memoryview_get_slice_from_memoryview(((struct __pyx_memoryview_obj *)__pyx_v_src), (&__pyx_v_src_slice))[0]), (__pyx_memoryview_get_slice_from_memoryview(((struct __pyx_memoryview_obj *)__pyx_v_dst), (&__pyx_v_dst_slice))[0]), __pyx_t_2, __pyx_t_3, __pyx_v_self->dtype_is_object); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(2, 440, __pyx_L1_error) - /* "View.MemoryView":432 + /* "View.MemoryView":436 * return obj * * cdef setitem_slice_assignment(self, dst, src): # <<<<<<<<<<<<<< @@ -12553,7 +12509,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assignment(struct __pyx_memoryvi return __pyx_r; } -/* "View.MemoryView":440 +/* "View.MemoryView":444 * src.ndim, dst.ndim, self.dtype_is_object) * * cdef setitem_slice_assign_scalar(self, memoryview dst, value): # <<<<<<<<<<<<<< @@ -12582,7 +12538,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor PyObject *__pyx_t_11 = NULL; __Pyx_RefNannySetupContext("setitem_slice_assign_scalar", 0); - /* "View.MemoryView":442 + /* "View.MemoryView":446 * cdef setitem_slice_assign_scalar(self, memoryview dst, value): * cdef int array[128] * cdef void *tmp = NULL # <<<<<<<<<<<<<< @@ -12591,7 +12547,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ __pyx_v_tmp = NULL; - /* "View.MemoryView":447 + /* "View.MemoryView":451 * cdef __Pyx_memviewslice *dst_slice * cdef __Pyx_memviewslice tmp_slice * dst_slice = get_slice_from_memview(dst, &tmp_slice) # <<<<<<<<<<<<<< @@ -12600,7 +12556,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ __pyx_v_dst_slice = __pyx_memoryview_get_slice_from_memoryview(__pyx_v_dst, (&__pyx_v_tmp_slice)); - /* "View.MemoryView":449 + /* "View.MemoryView":453 * dst_slice = get_slice_from_memview(dst, &tmp_slice) * * if self.view.itemsize > sizeof(array): # <<<<<<<<<<<<<< @@ -12610,7 +12566,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor __pyx_t_1 = ((((size_t)__pyx_v_self->view.itemsize) > (sizeof(__pyx_v_array))) != 0); if (__pyx_t_1) { - /* "View.MemoryView":450 + /* "View.MemoryView":454 * * if self.view.itemsize > sizeof(array): * tmp = PyMem_Malloc(self.view.itemsize) # <<<<<<<<<<<<<< @@ -12619,7 +12575,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ __pyx_v_tmp = PyMem_Malloc(__pyx_v_self->view.itemsize); - /* "View.MemoryView":451 + /* "View.MemoryView":455 * if self.view.itemsize > sizeof(array): * tmp = PyMem_Malloc(self.view.itemsize) * if tmp == NULL: # <<<<<<<<<<<<<< @@ -12627,18 +12583,18 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor * item = tmp */ __pyx_t_1 = ((__pyx_v_tmp == NULL) != 0); - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "View.MemoryView":452 + /* "View.MemoryView":456 * tmp = PyMem_Malloc(self.view.itemsize) * if tmp == NULL: * raise MemoryError # <<<<<<<<<<<<<< * item = tmp * else: */ - PyErr_NoMemory(); __PYX_ERR(2, 452, __pyx_L1_error) + PyErr_NoMemory(); __PYX_ERR(2, 456, __pyx_L1_error) - /* "View.MemoryView":451 + /* "View.MemoryView":455 * if self.view.itemsize > sizeof(array): * tmp = PyMem_Malloc(self.view.itemsize) * if tmp == NULL: # <<<<<<<<<<<<<< @@ -12647,7 +12603,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ } - /* "View.MemoryView":453 + /* "View.MemoryView":457 * if tmp == NULL: * raise MemoryError * item = tmp # <<<<<<<<<<<<<< @@ -12656,7 +12612,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ __pyx_v_item = __pyx_v_tmp; - /* "View.MemoryView":449 + /* "View.MemoryView":453 * dst_slice = get_slice_from_memview(dst, &tmp_slice) * * if self.view.itemsize > sizeof(array): # <<<<<<<<<<<<<< @@ -12666,7 +12622,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor goto __pyx_L3; } - /* "View.MemoryView":455 + /* "View.MemoryView":459 * item = tmp * else: * item = array # <<<<<<<<<<<<<< @@ -12678,7 +12634,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor } __pyx_L3:; - /* "View.MemoryView":457 + /* "View.MemoryView":461 * item = array * * try: # <<<<<<<<<<<<<< @@ -12687,7 +12643,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ /*try:*/ { - /* "View.MemoryView":458 + /* "View.MemoryView":462 * * try: * if self.dtype_is_object: # <<<<<<<<<<<<<< @@ -12697,7 +12653,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor __pyx_t_1 = (__pyx_v_self->dtype_is_object != 0); if (__pyx_t_1) { - /* "View.MemoryView":459 + /* "View.MemoryView":463 * try: * if self.dtype_is_object: * ( item)[0] = value # <<<<<<<<<<<<<< @@ -12706,7 +12662,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ (((PyObject **)__pyx_v_item)[0]) = ((PyObject *)__pyx_v_value); - /* "View.MemoryView":458 + /* "View.MemoryView":462 * * try: * if self.dtype_is_object: # <<<<<<<<<<<<<< @@ -12716,7 +12672,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor goto __pyx_L8; } - /* "View.MemoryView":461 + /* "View.MemoryView":465 * ( item)[0] = value * else: * self.assign_item_from_object( item, value) # <<<<<<<<<<<<<< @@ -12724,13 +12680,13 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor * */ /*else*/ { - __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->assign_item_from_object(__pyx_v_self, ((char *)__pyx_v_item), __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 461, __pyx_L6_error) + __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->assign_item_from_object(__pyx_v_self, ((char *)__pyx_v_item), __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 465, __pyx_L6_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_L8:; - /* "View.MemoryView":465 + /* "View.MemoryView":469 * * * if self.view.suboffsets != NULL: # <<<<<<<<<<<<<< @@ -12740,18 +12696,18 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor __pyx_t_1 = ((__pyx_v_self->view.suboffsets != NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":466 + /* "View.MemoryView":470 * * if self.view.suboffsets != NULL: * assert_direct_dimensions(self.view.suboffsets, self.view.ndim) # <<<<<<<<<<<<<< * slice_assign_scalar(dst_slice, dst.view.ndim, self.view.itemsize, * item, self.dtype_is_object) */ - __pyx_t_2 = assert_direct_dimensions(__pyx_v_self->view.suboffsets, __pyx_v_self->view.ndim); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 466, __pyx_L6_error) + __pyx_t_2 = assert_direct_dimensions(__pyx_v_self->view.suboffsets, __pyx_v_self->view.ndim); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 470, __pyx_L6_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":465 + /* "View.MemoryView":469 * * * if self.view.suboffsets != NULL: # <<<<<<<<<<<<<< @@ -12760,7 +12716,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor */ } - /* "View.MemoryView":467 + /* "View.MemoryView":471 * if self.view.suboffsets != NULL: * assert_direct_dimensions(self.view.suboffsets, self.view.ndim) * slice_assign_scalar(dst_slice, dst.view.ndim, self.view.itemsize, # <<<<<<<<<<<<<< @@ -12770,7 +12726,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor __pyx_memoryview_slice_assign_scalar(__pyx_v_dst_slice, __pyx_v_dst->view.ndim, __pyx_v_self->view.itemsize, __pyx_v_item, __pyx_v_self->dtype_is_object); } - /* "View.MemoryView":470 + /* "View.MemoryView":474 * item, self.dtype_is_object) * finally: * PyMem_Free(tmp) # <<<<<<<<<<<<<< @@ -12817,7 +12773,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor __pyx_L7:; } - /* "View.MemoryView":440 + /* "View.MemoryView":444 * src.ndim, dst.ndim, self.dtype_is_object) * * cdef setitem_slice_assign_scalar(self, memoryview dst, value): # <<<<<<<<<<<<<< @@ -12838,7 +12794,7 @@ static PyObject *__pyx_memoryview_setitem_slice_assign_scalar(struct __pyx_memor return __pyx_r; } -/* "View.MemoryView":472 +/* "View.MemoryView":476 * PyMem_Free(tmp) * * cdef setitem_indexed(self, index, value): # <<<<<<<<<<<<<< @@ -12854,28 +12810,28 @@ static PyObject *__pyx_memoryview_setitem_indexed(struct __pyx_memoryview_obj *_ PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("setitem_indexed", 0); - /* "View.MemoryView":473 + /* "View.MemoryView":477 * * cdef setitem_indexed(self, index, value): * cdef char *itemp = self.get_item_pointer(index) # <<<<<<<<<<<<<< * self.assign_item_from_object(itemp, value) * */ - __pyx_t_1 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->get_item_pointer(__pyx_v_self, __pyx_v_index); if (unlikely(__pyx_t_1 == ((char *)NULL))) __PYX_ERR(2, 473, __pyx_L1_error) + __pyx_t_1 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->get_item_pointer(__pyx_v_self, __pyx_v_index); if (unlikely(__pyx_t_1 == ((char *)NULL))) __PYX_ERR(2, 477, __pyx_L1_error) __pyx_v_itemp = __pyx_t_1; - /* "View.MemoryView":474 + /* "View.MemoryView":478 * cdef setitem_indexed(self, index, value): * cdef char *itemp = self.get_item_pointer(index) * self.assign_item_from_object(itemp, value) # <<<<<<<<<<<<<< * * cdef convert_item_to_object(self, char *itemp): */ - __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->assign_item_from_object(__pyx_v_self, __pyx_v_itemp, __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 474, __pyx_L1_error) + __pyx_t_2 = ((struct __pyx_vtabstruct_memoryview *)__pyx_v_self->__pyx_vtab)->assign_item_from_object(__pyx_v_self, __pyx_v_itemp, __pyx_v_value); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 478, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":472 + /* "View.MemoryView":476 * PyMem_Free(tmp) * * cdef setitem_indexed(self, index, value): # <<<<<<<<<<<<<< @@ -12896,7 +12852,7 @@ static PyObject *__pyx_memoryview_setitem_indexed(struct __pyx_memoryview_obj *_ return __pyx_r; } -/* "View.MemoryView":476 +/* "View.MemoryView":480 * self.assign_item_from_object(itemp, value) * * cdef convert_item_to_object(self, char *itemp): # <<<<<<<<<<<<<< @@ -12923,31 +12879,31 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview int __pyx_t_11; __Pyx_RefNannySetupContext("convert_item_to_object", 0); - /* "View.MemoryView":479 + /* "View.MemoryView":483 * """Only used if instantiated manually by the user, or if Cython doesn't * know how to convert the type""" * import struct # <<<<<<<<<<<<<< * cdef bytes bytesitem * */ - __pyx_t_1 = __Pyx_Import(__pyx_n_s_struct, 0, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 479, __pyx_L1_error) + __pyx_t_1 = __Pyx_Import(__pyx_n_s_struct, 0, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 483, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_v_struct = __pyx_t_1; __pyx_t_1 = 0; - /* "View.MemoryView":482 + /* "View.MemoryView":486 * cdef bytes bytesitem * * bytesitem = itemp[:self.view.itemsize] # <<<<<<<<<<<<<< * try: * result = struct.unpack(self.view.format, bytesitem) */ - __pyx_t_1 = __Pyx_PyBytes_FromStringAndSize(__pyx_v_itemp + 0, __pyx_v_self->view.itemsize - 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 482, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyBytes_FromStringAndSize(__pyx_v_itemp + 0, __pyx_v_self->view.itemsize - 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 486, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_v_bytesitem = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; - /* "View.MemoryView":483 + /* "View.MemoryView":487 * * bytesitem = itemp[:self.view.itemsize] * try: # <<<<<<<<<<<<<< @@ -12963,16 +12919,16 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview __Pyx_XGOTREF(__pyx_t_4); /*try:*/ { - /* "View.MemoryView":484 + /* "View.MemoryView":488 * bytesitem = itemp[:self.view.itemsize] * try: * result = struct.unpack(self.view.format, bytesitem) # <<<<<<<<<<<<<< * except struct.error: * raise ValueError("Unable to convert item to object") */ - __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_unpack); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 484, __pyx_L3_error) + __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_unpack); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 488, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_5); - __pyx_t_6 = __Pyx_PyBytes_FromString(__pyx_v_self->view.format); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 484, __pyx_L3_error) + __pyx_t_6 = __Pyx_PyBytes_FromString(__pyx_v_self->view.format); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 488, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_6); __pyx_t_7 = NULL; __pyx_t_8 = 0; @@ -12989,7 +12945,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[3] = {__pyx_t_7, __pyx_t_6, __pyx_v_bytesitem}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-__pyx_t_8, 2+__pyx_t_8); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 484, __pyx_L3_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_5, __pyx_temp+1-__pyx_t_8, 2+__pyx_t_8); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 488, __pyx_L3_error) __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; @@ -12998,14 +12954,14 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_5)) { PyObject *__pyx_temp[3] = {__pyx_t_7, __pyx_t_6, __pyx_v_bytesitem}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-__pyx_t_8, 2+__pyx_t_8); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 484, __pyx_L3_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_5, __pyx_temp+1-__pyx_t_8, 2+__pyx_t_8); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 488, __pyx_L3_error) __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; } else #endif { - __pyx_t_9 = PyTuple_New(2+__pyx_t_8); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 484, __pyx_L3_error) + __pyx_t_9 = PyTuple_New(2+__pyx_t_8); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 488, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_9); if (__pyx_t_7) { __Pyx_GIVEREF(__pyx_t_7); PyTuple_SET_ITEM(__pyx_t_9, 0, __pyx_t_7); __pyx_t_7 = NULL; @@ -13016,7 +12972,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview __Pyx_GIVEREF(__pyx_v_bytesitem); PyTuple_SET_ITEM(__pyx_t_9, 1+__pyx_t_8, __pyx_v_bytesitem); __pyx_t_6 = 0; - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_9, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 484, __pyx_L3_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_5, __pyx_t_9, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 488, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } @@ -13024,7 +12980,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview __pyx_v_result = __pyx_t_1; __pyx_t_1 = 0; - /* "View.MemoryView":483 + /* "View.MemoryView":487 * * bytesitem = itemp[:self.view.itemsize] * try: # <<<<<<<<<<<<<< @@ -13033,7 +12989,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview */ } - /* "View.MemoryView":488 + /* "View.MemoryView":492 * raise ValueError("Unable to convert item to object") * else: * if len(self.view.format) == 1: # <<<<<<<<<<<<<< @@ -13045,7 +13001,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview __pyx_t_11 = ((__pyx_t_10 == 1) != 0); if (__pyx_t_11) { - /* "View.MemoryView":489 + /* "View.MemoryView":493 * else: * if len(self.view.format) == 1: * return result[0] # <<<<<<<<<<<<<< @@ -13053,13 +13009,13 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_GetItemInt(__pyx_v_result, 0, long, 1, __Pyx_PyInt_From_long, 0, 0, 1); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 489, __pyx_L5_except_error) + __pyx_t_1 = __Pyx_GetItemInt(__pyx_v_result, 0, long, 1, __Pyx_PyInt_From_long, 0, 0, 1); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 493, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L6_except_return; - /* "View.MemoryView":488 + /* "View.MemoryView":492 * raise ValueError("Unable to convert item to object") * else: * if len(self.view.format) == 1: # <<<<<<<<<<<<<< @@ -13068,7 +13024,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview */ } - /* "View.MemoryView":490 + /* "View.MemoryView":494 * if len(self.view.format) == 1: * return result[0] * return result # <<<<<<<<<<<<<< @@ -13087,41 +13043,44 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; - /* "View.MemoryView":485 + /* "View.MemoryView":489 * try: * result = struct.unpack(self.view.format, bytesitem) * except struct.error: # <<<<<<<<<<<<<< * raise ValueError("Unable to convert item to object") * else: */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_error); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 485, __pyx_L5_except_error) - __Pyx_GOTREF(__pyx_t_1); - __pyx_t_8 = __Pyx_PyErr_ExceptionMatches(__pyx_t_1); - __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; + __Pyx_ErrFetch(&__pyx_t_1, &__pyx_t_5, &__pyx_t_9); + __pyx_t_6 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_error); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 489, __pyx_L5_except_error) + __Pyx_GOTREF(__pyx_t_6); + __pyx_t_8 = __Pyx_PyErr_GivenExceptionMatches(__pyx_t_1, __pyx_t_6); + __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; + __Pyx_ErrRestore(__pyx_t_1, __pyx_t_5, __pyx_t_9); + __pyx_t_1 = 0; __pyx_t_5 = 0; __pyx_t_9 = 0; if (__pyx_t_8) { __Pyx_AddTraceback("View.MemoryView.memoryview.convert_item_to_object", __pyx_clineno, __pyx_lineno, __pyx_filename); - if (__Pyx_GetException(&__pyx_t_1, &__pyx_t_5, &__pyx_t_9) < 0) __PYX_ERR(2, 485, __pyx_L5_except_error) - __Pyx_GOTREF(__pyx_t_1); - __Pyx_GOTREF(__pyx_t_5); + if (__Pyx_GetException(&__pyx_t_9, &__pyx_t_5, &__pyx_t_1) < 0) __PYX_ERR(2, 489, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_9); + __Pyx_GOTREF(__pyx_t_5); + __Pyx_GOTREF(__pyx_t_1); - /* "View.MemoryView":486 + /* "View.MemoryView":490 * result = struct.unpack(self.view.format, bytesitem) * except struct.error: * raise ValueError("Unable to convert item to object") # <<<<<<<<<<<<<< * else: * if len(self.view.format) == 1: */ - __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__26, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 486, __pyx_L5_except_error) + __pyx_t_6 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__27, NULL); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 490, __pyx_L5_except_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_Raise(__pyx_t_6, 0, 0, 0); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - __PYX_ERR(2, 486, __pyx_L5_except_error) + __PYX_ERR(2, 490, __pyx_L5_except_error) } goto __pyx_L5_except_error; __pyx_L5_except_error:; - /* "View.MemoryView":483 + /* "View.MemoryView":487 * * bytesitem = itemp[:self.view.itemsize] * try: # <<<<<<<<<<<<<< @@ -13141,7 +13100,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview goto __pyx_L0; } - /* "View.MemoryView":476 + /* "View.MemoryView":480 * self.assign_item_from_object(itemp, value) * * cdef convert_item_to_object(self, char *itemp): # <<<<<<<<<<<<<< @@ -13167,7 +13126,7 @@ static PyObject *__pyx_memoryview_convert_item_to_object(struct __pyx_memoryview return __pyx_r; } -/* "View.MemoryView":492 +/* "View.MemoryView":496 * return result * * cdef assign_item_from_object(self, char *itemp, object value): # <<<<<<<<<<<<<< @@ -13198,19 +13157,19 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie char *__pyx_t_14; __Pyx_RefNannySetupContext("assign_item_from_object", 0); - /* "View.MemoryView":495 + /* "View.MemoryView":499 * """Only used if instantiated manually by the user, or if Cython doesn't * know how to convert the type""" * import struct # <<<<<<<<<<<<<< * cdef char c * cdef bytes bytesvalue */ - __pyx_t_1 = __Pyx_Import(__pyx_n_s_struct, 0, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 495, __pyx_L1_error) + __pyx_t_1 = __Pyx_Import(__pyx_n_s_struct, 0, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 499, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_v_struct = __pyx_t_1; __pyx_t_1 = 0; - /* "View.MemoryView":500 + /* "View.MemoryView":504 * cdef Py_ssize_t i * * if isinstance(value, tuple): # <<<<<<<<<<<<<< @@ -13221,37 +13180,37 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie __pyx_t_3 = (__pyx_t_2 != 0); if (__pyx_t_3) { - /* "View.MemoryView":501 + /* "View.MemoryView":505 * * if isinstance(value, tuple): * bytesvalue = struct.pack(self.view.format, *value) # <<<<<<<<<<<<<< * else: * bytesvalue = struct.pack(self.view.format, value) */ - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_pack); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 501, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_pack); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_4 = __Pyx_PyBytes_FromString(__pyx_v_self->view.format); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 501, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyBytes_FromString(__pyx_v_self->view.format); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_5 = PyTuple_New(1); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 501, __pyx_L1_error) + __pyx_t_5 = PyTuple_New(1); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GIVEREF(__pyx_t_4); PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_4); __pyx_t_4 = 0; - __pyx_t_4 = __Pyx_PySequence_Tuple(__pyx_v_value); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 501, __pyx_L1_error) + __pyx_t_4 = __Pyx_PySequence_Tuple(__pyx_v_value); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_6 = PyNumber_Add(__pyx_t_5, __pyx_t_4); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 501, __pyx_L1_error) + __pyx_t_6 = PyNumber_Add(__pyx_t_5, __pyx_t_4); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_6, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 501, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_1, __pyx_t_6, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 505, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - if (!(likely(PyBytes_CheckExact(__pyx_t_4))||((__pyx_t_4) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "bytes", Py_TYPE(__pyx_t_4)->tp_name), 0))) __PYX_ERR(2, 501, __pyx_L1_error) + if (!(likely(PyBytes_CheckExact(__pyx_t_4))||((__pyx_t_4) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "bytes", Py_TYPE(__pyx_t_4)->tp_name), 0))) __PYX_ERR(2, 505, __pyx_L1_error) __pyx_v_bytesvalue = ((PyObject*)__pyx_t_4); __pyx_t_4 = 0; - /* "View.MemoryView":500 + /* "View.MemoryView":504 * cdef Py_ssize_t i * * if isinstance(value, tuple): # <<<<<<<<<<<<<< @@ -13261,7 +13220,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie goto __pyx_L3; } - /* "View.MemoryView":503 + /* "View.MemoryView":507 * bytesvalue = struct.pack(self.view.format, *value) * else: * bytesvalue = struct.pack(self.view.format, value) # <<<<<<<<<<<<<< @@ -13269,9 +13228,9 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie * for i, c in enumerate(bytesvalue): */ /*else*/ { - __pyx_t_6 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_pack); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 503, __pyx_L1_error) + __pyx_t_6 = __Pyx_PyObject_GetAttrStr(__pyx_v_struct, __pyx_n_s_pack); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - __pyx_t_1 = __Pyx_PyBytes_FromString(__pyx_v_self->view.format); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 503, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyBytes_FromString(__pyx_v_self->view.format); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_5 = NULL; __pyx_t_7 = 0; @@ -13288,7 +13247,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_6)) { PyObject *__pyx_temp[3] = {__pyx_t_5, __pyx_t_1, __pyx_v_value}; - __pyx_t_4 = __Pyx_PyFunction_FastCall(__pyx_t_6, __pyx_temp+1-__pyx_t_7, 2+__pyx_t_7); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 503, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyFunction_FastCall(__pyx_t_6, __pyx_temp+1-__pyx_t_7, 2+__pyx_t_7); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 507, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -13297,14 +13256,14 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_6)) { PyObject *__pyx_temp[3] = {__pyx_t_5, __pyx_t_1, __pyx_v_value}; - __pyx_t_4 = __Pyx_PyCFunction_FastCall(__pyx_t_6, __pyx_temp+1-__pyx_t_7, 2+__pyx_t_7); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 503, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyCFunction_FastCall(__pyx_t_6, __pyx_temp+1-__pyx_t_7, 2+__pyx_t_7); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 507, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } else #endif { - __pyx_t_8 = PyTuple_New(2+__pyx_t_7); if (unlikely(!__pyx_t_8)) __PYX_ERR(2, 503, __pyx_L1_error) + __pyx_t_8 = PyTuple_New(2+__pyx_t_7); if (unlikely(!__pyx_t_8)) __PYX_ERR(2, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); if (__pyx_t_5) { __Pyx_GIVEREF(__pyx_t_5); PyTuple_SET_ITEM(__pyx_t_8, 0, __pyx_t_5); __pyx_t_5 = NULL; @@ -13315,18 +13274,18 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie __Pyx_GIVEREF(__pyx_v_value); PyTuple_SET_ITEM(__pyx_t_8, 1+__pyx_t_7, __pyx_v_value); __pyx_t_1 = 0; - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_6, __pyx_t_8, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 503, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_Call(__pyx_t_6, __pyx_t_8, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 507, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; } __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; - if (!(likely(PyBytes_CheckExact(__pyx_t_4))||((__pyx_t_4) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "bytes", Py_TYPE(__pyx_t_4)->tp_name), 0))) __PYX_ERR(2, 503, __pyx_L1_error) + if (!(likely(PyBytes_CheckExact(__pyx_t_4))||((__pyx_t_4) == Py_None)||(PyErr_Format(PyExc_TypeError, "Expected %.16s, got %.200s", "bytes", Py_TYPE(__pyx_t_4)->tp_name), 0))) __PYX_ERR(2, 507, __pyx_L1_error) __pyx_v_bytesvalue = ((PyObject*)__pyx_t_4); __pyx_t_4 = 0; } __pyx_L3:; - /* "View.MemoryView":505 + /* "View.MemoryView":509 * bytesvalue = struct.pack(self.view.format, value) * * for i, c in enumerate(bytesvalue): # <<<<<<<<<<<<<< @@ -13336,7 +13295,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie __pyx_t_9 = 0; if (unlikely(__pyx_v_bytesvalue == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' is not iterable"); - __PYX_ERR(2, 505, __pyx_L1_error) + __PYX_ERR(2, 509, __pyx_L1_error) } __Pyx_INCREF(__pyx_v_bytesvalue); __pyx_t_10 = __pyx_v_bytesvalue; @@ -13346,7 +13305,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie __pyx_t_11 = __pyx_t_14; __pyx_v_c = (__pyx_t_11[0]); - /* "View.MemoryView":506 + /* "View.MemoryView":510 * * for i, c in enumerate(bytesvalue): * itemp[i] = c # <<<<<<<<<<<<<< @@ -13355,7 +13314,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie */ __pyx_v_i = __pyx_t_9; - /* "View.MemoryView":505 + /* "View.MemoryView":509 * bytesvalue = struct.pack(self.view.format, value) * * for i, c in enumerate(bytesvalue): # <<<<<<<<<<<<<< @@ -13364,7 +13323,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie */ __pyx_t_9 = (__pyx_t_9 + 1); - /* "View.MemoryView":506 + /* "View.MemoryView":510 * * for i, c in enumerate(bytesvalue): * itemp[i] = c # <<<<<<<<<<<<<< @@ -13375,7 +13334,7 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie } __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; - /* "View.MemoryView":492 + /* "View.MemoryView":496 * return result * * cdef assign_item_from_object(self, char *itemp, object value): # <<<<<<<<<<<<<< @@ -13403,12 +13362,12 @@ static PyObject *__pyx_memoryview_assign_item_from_object(struct __pyx_memoryvie return __pyx_r; } -/* "View.MemoryView":509 +/* "View.MemoryView":513 * * @cname('getbuffer') * def __getbuffer__(self, Py_buffer *info, int flags): # <<<<<<<<<<<<<< - * if flags & PyBUF_STRIDES: - * info.shape = self.view.shape + * if flags & PyBUF_WRITABLE and self.view.readonly: + * raise ValueError("Cannot create writable memory view from read-only memoryview") */ /* Python wrapper */ @@ -13428,20 +13387,64 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu int __pyx_r; __Pyx_RefNannyDeclarations int __pyx_t_1; - Py_ssize_t *__pyx_t_2; - char *__pyx_t_3; - void *__pyx_t_4; - int __pyx_t_5; - Py_ssize_t __pyx_t_6; + int __pyx_t_2; + PyObject *__pyx_t_3 = NULL; + Py_ssize_t *__pyx_t_4; + char *__pyx_t_5; + void *__pyx_t_6; + int __pyx_t_7; + Py_ssize_t __pyx_t_8; + if (__pyx_v_info == NULL) { + PyErr_SetString(PyExc_BufferError, "PyObject_GetBuffer: view==NULL argument is obsolete"); + return -1; + } __Pyx_RefNannySetupContext("__getbuffer__", 0); - if (__pyx_v_info != NULL) { - __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); - __Pyx_GIVEREF(__pyx_v_info->obj); + __pyx_v_info->obj = Py_None; __Pyx_INCREF(Py_None); + __Pyx_GIVEREF(__pyx_v_info->obj); + + /* "View.MemoryView":514 + * @cname('getbuffer') + * def __getbuffer__(self, Py_buffer *info, int flags): + * if flags & PyBUF_WRITABLE and self.view.readonly: # <<<<<<<<<<<<<< + * raise ValueError("Cannot create writable memory view from read-only memoryview") + * + */ + __pyx_t_2 = ((__pyx_v_flags & PyBUF_WRITABLE) != 0); + if (__pyx_t_2) { + } else { + __pyx_t_1 = __pyx_t_2; + goto __pyx_L4_bool_binop_done; } + __pyx_t_2 = (__pyx_v_self->view.readonly != 0); + __pyx_t_1 = __pyx_t_2; + __pyx_L4_bool_binop_done:; + if (unlikely(__pyx_t_1)) { + + /* "View.MemoryView":515 + * def __getbuffer__(self, Py_buffer *info, int flags): + * if flags & PyBUF_WRITABLE and self.view.readonly: + * raise ValueError("Cannot create writable memory view from read-only memoryview") # <<<<<<<<<<<<<< + * + * if flags & PyBUF_STRIDES: + */ + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__28, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 515, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); + __Pyx_Raise(__pyx_t_3, 0, 0, 0); + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __PYX_ERR(2, 515, __pyx_L1_error) - /* "View.MemoryView":510 + /* "View.MemoryView":514 * @cname('getbuffer') * def __getbuffer__(self, Py_buffer *info, int flags): + * if flags & PyBUF_WRITABLE and self.view.readonly: # <<<<<<<<<<<<<< + * raise ValueError("Cannot create writable memory view from read-only memoryview") + * + */ + } + + /* "View.MemoryView":517 + * raise ValueError("Cannot create writable memory view from read-only memoryview") + * * if flags & PyBUF_STRIDES: # <<<<<<<<<<<<<< * info.shape = self.view.shape * else: @@ -13449,27 +13452,27 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu __pyx_t_1 = ((__pyx_v_flags & PyBUF_STRIDES) != 0); if (__pyx_t_1) { - /* "View.MemoryView":511 - * def __getbuffer__(self, Py_buffer *info, int flags): + /* "View.MemoryView":518 + * * if flags & PyBUF_STRIDES: * info.shape = self.view.shape # <<<<<<<<<<<<<< * else: * info.shape = NULL */ - __pyx_t_2 = __pyx_v_self->view.shape; - __pyx_v_info->shape = __pyx_t_2; + __pyx_t_4 = __pyx_v_self->view.shape; + __pyx_v_info->shape = __pyx_t_4; - /* "View.MemoryView":510 - * @cname('getbuffer') - * def __getbuffer__(self, Py_buffer *info, int flags): + /* "View.MemoryView":517 + * raise ValueError("Cannot create writable memory view from read-only memoryview") + * * if flags & PyBUF_STRIDES: # <<<<<<<<<<<<<< * info.shape = self.view.shape * else: */ - goto __pyx_L3; + goto __pyx_L6; } - /* "View.MemoryView":513 + /* "View.MemoryView":520 * info.shape = self.view.shape * else: * info.shape = NULL # <<<<<<<<<<<<<< @@ -13479,9 +13482,9 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu /*else*/ { __pyx_v_info->shape = NULL; } - __pyx_L3:; + __pyx_L6:; - /* "View.MemoryView":515 + /* "View.MemoryView":522 * info.shape = NULL * * if flags & PyBUF_STRIDES: # <<<<<<<<<<<<<< @@ -13491,27 +13494,27 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu __pyx_t_1 = ((__pyx_v_flags & PyBUF_STRIDES) != 0); if (__pyx_t_1) { - /* "View.MemoryView":516 + /* "View.MemoryView":523 * * if flags & PyBUF_STRIDES: * info.strides = self.view.strides # <<<<<<<<<<<<<< * else: * info.strides = NULL */ - __pyx_t_2 = __pyx_v_self->view.strides; - __pyx_v_info->strides = __pyx_t_2; + __pyx_t_4 = __pyx_v_self->view.strides; + __pyx_v_info->strides = __pyx_t_4; - /* "View.MemoryView":515 + /* "View.MemoryView":522 * info.shape = NULL * * if flags & PyBUF_STRIDES: # <<<<<<<<<<<<<< * info.strides = self.view.strides * else: */ - goto __pyx_L4; + goto __pyx_L7; } - /* "View.MemoryView":518 + /* "View.MemoryView":525 * info.strides = self.view.strides * else: * info.strides = NULL # <<<<<<<<<<<<<< @@ -13521,9 +13524,9 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu /*else*/ { __pyx_v_info->strides = NULL; } - __pyx_L4:; + __pyx_L7:; - /* "View.MemoryView":520 + /* "View.MemoryView":527 * info.strides = NULL * * if flags & PyBUF_INDIRECT: # <<<<<<<<<<<<<< @@ -13533,27 +13536,27 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu __pyx_t_1 = ((__pyx_v_flags & PyBUF_INDIRECT) != 0); if (__pyx_t_1) { - /* "View.MemoryView":521 + /* "View.MemoryView":528 * * if flags & PyBUF_INDIRECT: * info.suboffsets = self.view.suboffsets # <<<<<<<<<<<<<< * else: * info.suboffsets = NULL */ - __pyx_t_2 = __pyx_v_self->view.suboffsets; - __pyx_v_info->suboffsets = __pyx_t_2; + __pyx_t_4 = __pyx_v_self->view.suboffsets; + __pyx_v_info->suboffsets = __pyx_t_4; - /* "View.MemoryView":520 + /* "View.MemoryView":527 * info.strides = NULL * * if flags & PyBUF_INDIRECT: # <<<<<<<<<<<<<< * info.suboffsets = self.view.suboffsets * else: */ - goto __pyx_L5; + goto __pyx_L8; } - /* "View.MemoryView":523 + /* "View.MemoryView":530 * info.suboffsets = self.view.suboffsets * else: * info.suboffsets = NULL # <<<<<<<<<<<<<< @@ -13563,9 +13566,9 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu /*else*/ { __pyx_v_info->suboffsets = NULL; } - __pyx_L5:; + __pyx_L8:; - /* "View.MemoryView":525 + /* "View.MemoryView":532 * info.suboffsets = NULL * * if flags & PyBUF_FORMAT: # <<<<<<<<<<<<<< @@ -13575,27 +13578,27 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu __pyx_t_1 = ((__pyx_v_flags & PyBUF_FORMAT) != 0); if (__pyx_t_1) { - /* "View.MemoryView":526 + /* "View.MemoryView":533 * * if flags & PyBUF_FORMAT: * info.format = self.view.format # <<<<<<<<<<<<<< * else: * info.format = NULL */ - __pyx_t_3 = __pyx_v_self->view.format; - __pyx_v_info->format = __pyx_t_3; + __pyx_t_5 = __pyx_v_self->view.format; + __pyx_v_info->format = __pyx_t_5; - /* "View.MemoryView":525 + /* "View.MemoryView":532 * info.suboffsets = NULL * * if flags & PyBUF_FORMAT: # <<<<<<<<<<<<<< * info.format = self.view.format * else: */ - goto __pyx_L6; + goto __pyx_L9; } - /* "View.MemoryView":528 + /* "View.MemoryView":535 * info.format = self.view.format * else: * info.format = NULL # <<<<<<<<<<<<<< @@ -13605,60 +13608,61 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu /*else*/ { __pyx_v_info->format = NULL; } - __pyx_L6:; + __pyx_L9:; - /* "View.MemoryView":530 + /* "View.MemoryView":537 * info.format = NULL * * info.buf = self.view.buf # <<<<<<<<<<<<<< * info.ndim = self.view.ndim * info.itemsize = self.view.itemsize */ - __pyx_t_4 = __pyx_v_self->view.buf; - __pyx_v_info->buf = __pyx_t_4; + __pyx_t_6 = __pyx_v_self->view.buf; + __pyx_v_info->buf = __pyx_t_6; - /* "View.MemoryView":531 + /* "View.MemoryView":538 * * info.buf = self.view.buf * info.ndim = self.view.ndim # <<<<<<<<<<<<<< * info.itemsize = self.view.itemsize * info.len = self.view.len */ - __pyx_t_5 = __pyx_v_self->view.ndim; - __pyx_v_info->ndim = __pyx_t_5; + __pyx_t_7 = __pyx_v_self->view.ndim; + __pyx_v_info->ndim = __pyx_t_7; - /* "View.MemoryView":532 + /* "View.MemoryView":539 * info.buf = self.view.buf * info.ndim = self.view.ndim * info.itemsize = self.view.itemsize # <<<<<<<<<<<<<< * info.len = self.view.len - * info.readonly = 0 + * info.readonly = self.view.readonly */ - __pyx_t_6 = __pyx_v_self->view.itemsize; - __pyx_v_info->itemsize = __pyx_t_6; + __pyx_t_8 = __pyx_v_self->view.itemsize; + __pyx_v_info->itemsize = __pyx_t_8; - /* "View.MemoryView":533 + /* "View.MemoryView":540 * info.ndim = self.view.ndim * info.itemsize = self.view.itemsize * info.len = self.view.len # <<<<<<<<<<<<<< - * info.readonly = 0 + * info.readonly = self.view.readonly * info.obj = self */ - __pyx_t_6 = __pyx_v_self->view.len; - __pyx_v_info->len = __pyx_t_6; + __pyx_t_8 = __pyx_v_self->view.len; + __pyx_v_info->len = __pyx_t_8; - /* "View.MemoryView":534 + /* "View.MemoryView":541 * info.itemsize = self.view.itemsize * info.len = self.view.len - * info.readonly = 0 # <<<<<<<<<<<<<< + * info.readonly = self.view.readonly # <<<<<<<<<<<<<< * info.obj = self * */ - __pyx_v_info->readonly = 0; + __pyx_t_1 = __pyx_v_self->view.readonly; + __pyx_v_info->readonly = __pyx_t_1; - /* "View.MemoryView":535 + /* "View.MemoryView":542 * info.len = self.view.len - * info.readonly = 0 + * info.readonly = self.view.readonly * info.obj = self # <<<<<<<<<<<<<< * * __pyx_getbuffer = capsule( &__pyx_memoryview_getbuffer, "getbuffer(obj, view, flags)") @@ -13669,25 +13673,37 @@ static int __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_8__getbu __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = ((PyObject *)__pyx_v_self); - /* "View.MemoryView":509 + /* "View.MemoryView":513 * * @cname('getbuffer') * def __getbuffer__(self, Py_buffer *info, int flags): # <<<<<<<<<<<<<< - * if flags & PyBUF_STRIDES: - * info.shape = self.view.shape + * if flags & PyBUF_WRITABLE and self.view.readonly: + * raise ValueError("Cannot create writable memory view from read-only memoryview") */ /* function exit code */ __pyx_r = 0; - if (__pyx_v_info != NULL && __pyx_v_info->obj == Py_None) { - __Pyx_GOTREF(Py_None); - __Pyx_DECREF(Py_None); __pyx_v_info->obj = NULL; + goto __pyx_L0; + __pyx_L1_error:; + __Pyx_XDECREF(__pyx_t_3); + __Pyx_AddTraceback("View.MemoryView.memoryview.__getbuffer__", __pyx_clineno, __pyx_lineno, __pyx_filename); + __pyx_r = -1; + if (__pyx_v_info->obj != NULL) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; + } + goto __pyx_L2; + __pyx_L0:; + if (__pyx_v_info->obj == Py_None) { + __Pyx_GOTREF(__pyx_v_info->obj); + __Pyx_DECREF(__pyx_v_info->obj); __pyx_v_info->obj = 0; } + __pyx_L2:; __Pyx_RefNannyFinishContext(); return __pyx_r; } -/* "View.MemoryView":541 +/* "View.MemoryView":548 * * @property * def T(self): # <<<<<<<<<<<<<< @@ -13716,29 +13732,29 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_1T___get__(struct _ int __pyx_t_2; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":542 + /* "View.MemoryView":549 * @property * def T(self): * cdef _memoryviewslice result = memoryview_copy(self) # <<<<<<<<<<<<<< * transpose_memslice(&result.from_slice) * return result */ - __pyx_t_1 = __pyx_memoryview_copy_object(__pyx_v_self); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 542, __pyx_L1_error) + __pyx_t_1 = __pyx_memoryview_copy_object(__pyx_v_self); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 549, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_memoryviewslice_type))))) __PYX_ERR(2, 542, __pyx_L1_error) + if (!(likely(((__pyx_t_1) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_1, __pyx_memoryviewslice_type))))) __PYX_ERR(2, 549, __pyx_L1_error) __pyx_v_result = ((struct __pyx_memoryviewslice_obj *)__pyx_t_1); __pyx_t_1 = 0; - /* "View.MemoryView":543 + /* "View.MemoryView":550 * def T(self): * cdef _memoryviewslice result = memoryview_copy(self) * transpose_memslice(&result.from_slice) # <<<<<<<<<<<<<< * return result * */ - __pyx_t_2 = __pyx_memslice_transpose((&__pyx_v_result->from_slice)); if (unlikely(__pyx_t_2 == ((int)0))) __PYX_ERR(2, 543, __pyx_L1_error) + __pyx_t_2 = __pyx_memslice_transpose((&__pyx_v_result->from_slice)); if (unlikely(__pyx_t_2 == ((int)0))) __PYX_ERR(2, 550, __pyx_L1_error) - /* "View.MemoryView":544 + /* "View.MemoryView":551 * cdef _memoryviewslice result = memoryview_copy(self) * transpose_memslice(&result.from_slice) * return result # <<<<<<<<<<<<<< @@ -13750,7 +13766,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_1T___get__(struct _ __pyx_r = ((PyObject *)__pyx_v_result); goto __pyx_L0; - /* "View.MemoryView":541 + /* "View.MemoryView":548 * * @property * def T(self): # <<<<<<<<<<<<<< @@ -13770,7 +13786,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_1T___get__(struct _ return __pyx_r; } -/* "View.MemoryView":547 +/* "View.MemoryView":554 * * @property * def base(self): # <<<<<<<<<<<<<< @@ -13796,7 +13812,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4base___get__(struc __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":548 + /* "View.MemoryView":555 * @property * def base(self): * return self.obj # <<<<<<<<<<<<<< @@ -13808,7 +13824,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4base___get__(struc __pyx_r = __pyx_v_self->obj; goto __pyx_L0; - /* "View.MemoryView":547 + /* "View.MemoryView":554 * * @property * def base(self): # <<<<<<<<<<<<<< @@ -13823,7 +13839,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4base___get__(struc return __pyx_r; } -/* "View.MemoryView":551 +/* "View.MemoryView":558 * * @property * def shape(self): # <<<<<<<<<<<<<< @@ -13855,7 +13871,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_5shape___get__(stru PyObject *__pyx_t_5 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":552 + /* "View.MemoryView":559 * @property * def shape(self): * return tuple([length for length in self.view.shape[:self.view.ndim]]) # <<<<<<<<<<<<<< @@ -13863,25 +13879,25 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_5shape___get__(stru * @property */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 552, __pyx_L1_error) + __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 559, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_3 = (__pyx_v_self->view.shape + __pyx_v_self->view.ndim); for (__pyx_t_4 = __pyx_v_self->view.shape; __pyx_t_4 < __pyx_t_3; __pyx_t_4++) { __pyx_t_2 = __pyx_t_4; __pyx_v_length = (__pyx_t_2[0]); - __pyx_t_5 = PyInt_FromSsize_t(__pyx_v_length); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 552, __pyx_L1_error) + __pyx_t_5 = PyInt_FromSsize_t(__pyx_v_length); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 559, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); - if (unlikely(__Pyx_ListComp_Append(__pyx_t_1, (PyObject*)__pyx_t_5))) __PYX_ERR(2, 552, __pyx_L1_error) + if (unlikely(__Pyx_ListComp_Append(__pyx_t_1, (PyObject*)__pyx_t_5))) __PYX_ERR(2, 559, __pyx_L1_error) __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } - __pyx_t_5 = PyList_AsTuple(((PyObject*)__pyx_t_1)); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 552, __pyx_L1_error) + __pyx_t_5 = PyList_AsTuple(((PyObject*)__pyx_t_1)); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 559, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_r = __pyx_t_5; __pyx_t_5 = 0; goto __pyx_L0; - /* "View.MemoryView":551 + /* "View.MemoryView":558 * * @property * def shape(self): # <<<<<<<<<<<<<< @@ -13901,7 +13917,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_5shape___get__(stru return __pyx_r; } -/* "View.MemoryView":555 +/* "View.MemoryView":562 * * @property * def strides(self): # <<<<<<<<<<<<<< @@ -13934,7 +13950,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_7strides___get__(st PyObject *__pyx_t_6 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":556 + /* "View.MemoryView":563 * @property * def strides(self): * if self.view.strides == NULL: # <<<<<<<<<<<<<< @@ -13942,22 +13958,22 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_7strides___get__(st * raise ValueError("Buffer view does not expose strides") */ __pyx_t_1 = ((__pyx_v_self->view.strides == NULL) != 0); - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "View.MemoryView":558 + /* "View.MemoryView":565 * if self.view.strides == NULL: * * raise ValueError("Buffer view does not expose strides") # <<<<<<<<<<<<<< * * return tuple([stride for stride in self.view.strides[:self.view.ndim]]) */ - __pyx_t_2 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__27, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 558, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__29, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 565, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_Raise(__pyx_t_2, 0, 0, 0); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __PYX_ERR(2, 558, __pyx_L1_error) + __PYX_ERR(2, 565, __pyx_L1_error) - /* "View.MemoryView":556 + /* "View.MemoryView":563 * @property * def strides(self): * if self.view.strides == NULL: # <<<<<<<<<<<<<< @@ -13966,7 +13982,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_7strides___get__(st */ } - /* "View.MemoryView":560 + /* "View.MemoryView":567 * raise ValueError("Buffer view does not expose strides") * * return tuple([stride for stride in self.view.strides[:self.view.ndim]]) # <<<<<<<<<<<<<< @@ -13974,25 +13990,25 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_7strides___get__(st * @property */ __Pyx_XDECREF(__pyx_r); - __pyx_t_2 = PyList_New(0); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 560, __pyx_L1_error) + __pyx_t_2 = PyList_New(0); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 567, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_4 = (__pyx_v_self->view.strides + __pyx_v_self->view.ndim); for (__pyx_t_5 = __pyx_v_self->view.strides; __pyx_t_5 < __pyx_t_4; __pyx_t_5++) { __pyx_t_3 = __pyx_t_5; __pyx_v_stride = (__pyx_t_3[0]); - __pyx_t_6 = PyInt_FromSsize_t(__pyx_v_stride); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 560, __pyx_L1_error) + __pyx_t_6 = PyInt_FromSsize_t(__pyx_v_stride); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 567, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - if (unlikely(__Pyx_ListComp_Append(__pyx_t_2, (PyObject*)__pyx_t_6))) __PYX_ERR(2, 560, __pyx_L1_error) + if (unlikely(__Pyx_ListComp_Append(__pyx_t_2, (PyObject*)__pyx_t_6))) __PYX_ERR(2, 567, __pyx_L1_error) __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; } - __pyx_t_6 = PyList_AsTuple(((PyObject*)__pyx_t_2)); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 560, __pyx_L1_error) + __pyx_t_6 = PyList_AsTuple(((PyObject*)__pyx_t_2)); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 567, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_r = __pyx_t_6; __pyx_t_6 = 0; goto __pyx_L0; - /* "View.MemoryView":555 + /* "View.MemoryView":562 * * @property * def strides(self): # <<<<<<<<<<<<<< @@ -14012,7 +14028,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_7strides___get__(st return __pyx_r; } -/* "View.MemoryView":563 +/* "View.MemoryView":570 * * @property * def suboffsets(self): # <<<<<<<<<<<<<< @@ -14045,7 +14061,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_10suboffsets___get_ Py_ssize_t *__pyx_t_6; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":564 + /* "View.MemoryView":571 * @property * def suboffsets(self): * if self.view.suboffsets == NULL: # <<<<<<<<<<<<<< @@ -14055,7 +14071,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_10suboffsets___get_ __pyx_t_1 = ((__pyx_v_self->view.suboffsets == NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":565 + /* "View.MemoryView":572 * def suboffsets(self): * if self.view.suboffsets == NULL: * return (-1,) * self.view.ndim # <<<<<<<<<<<<<< @@ -14063,16 +14079,16 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_10suboffsets___get_ * return tuple([suboffset for suboffset in self.view.suboffsets[:self.view.ndim]]) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_2 = __Pyx_PyInt_From_int(__pyx_v_self->view.ndim); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 565, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyInt_From_int(__pyx_v_self->view.ndim); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 572, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyNumber_Multiply(__pyx_tuple__28, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 565, __pyx_L1_error) + __pyx_t_3 = PyNumber_Multiply(__pyx_tuple__30, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 572, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; - /* "View.MemoryView":564 + /* "View.MemoryView":571 * @property * def suboffsets(self): * if self.view.suboffsets == NULL: # <<<<<<<<<<<<<< @@ -14081,7 +14097,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_10suboffsets___get_ */ } - /* "View.MemoryView":567 + /* "View.MemoryView":574 * return (-1,) * self.view.ndim * * return tuple([suboffset for suboffset in self.view.suboffsets[:self.view.ndim]]) # <<<<<<<<<<<<<< @@ -14089,25 +14105,25 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_10suboffsets___get_ * @property */ __Pyx_XDECREF(__pyx_r); - __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 567, __pyx_L1_error) + __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 574, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_5 = (__pyx_v_self->view.suboffsets + __pyx_v_self->view.ndim); for (__pyx_t_6 = __pyx_v_self->view.suboffsets; __pyx_t_6 < __pyx_t_5; __pyx_t_6++) { __pyx_t_4 = __pyx_t_6; __pyx_v_suboffset = (__pyx_t_4[0]); - __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_suboffset); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 567, __pyx_L1_error) + __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_suboffset); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 574, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - if (unlikely(__Pyx_ListComp_Append(__pyx_t_3, (PyObject*)__pyx_t_2))) __PYX_ERR(2, 567, __pyx_L1_error) + if (unlikely(__Pyx_ListComp_Append(__pyx_t_3, (PyObject*)__pyx_t_2))) __PYX_ERR(2, 574, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } - __pyx_t_2 = PyList_AsTuple(((PyObject*)__pyx_t_3)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 567, __pyx_L1_error) + __pyx_t_2 = PyList_AsTuple(((PyObject*)__pyx_t_3)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 574, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":563 + /* "View.MemoryView":570 * * @property * def suboffsets(self): # <<<<<<<<<<<<<< @@ -14127,7 +14143,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_10suboffsets___get_ return __pyx_r; } -/* "View.MemoryView":570 +/* "View.MemoryView":577 * * @property * def ndim(self): # <<<<<<<<<<<<<< @@ -14154,7 +14170,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4ndim___get__(struc PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":571 + /* "View.MemoryView":578 * @property * def ndim(self): * return self.view.ndim # <<<<<<<<<<<<<< @@ -14162,13 +14178,13 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4ndim___get__(struc * @property */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_self->view.ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 571, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_self->view.ndim); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 578, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":570 + /* "View.MemoryView":577 * * @property * def ndim(self): # <<<<<<<<<<<<<< @@ -14187,7 +14203,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4ndim___get__(struc return __pyx_r; } -/* "View.MemoryView":574 +/* "View.MemoryView":581 * * @property * def itemsize(self): # <<<<<<<<<<<<<< @@ -14214,7 +14230,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_8itemsize___get__(s PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":575 + /* "View.MemoryView":582 * @property * def itemsize(self): * return self.view.itemsize # <<<<<<<<<<<<<< @@ -14222,13 +14238,13 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_8itemsize___get__(s * @property */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = PyInt_FromSsize_t(__pyx_v_self->view.itemsize); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 575, __pyx_L1_error) + __pyx_t_1 = PyInt_FromSsize_t(__pyx_v_self->view.itemsize); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 582, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":574 + /* "View.MemoryView":581 * * @property * def itemsize(self): # <<<<<<<<<<<<<< @@ -14247,7 +14263,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_8itemsize___get__(s return __pyx_r; } -/* "View.MemoryView":578 +/* "View.MemoryView":585 * * @property * def nbytes(self): # <<<<<<<<<<<<<< @@ -14276,7 +14292,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_6nbytes___get__(str PyObject *__pyx_t_3 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":579 + /* "View.MemoryView":586 * @property * def nbytes(self): * return self.size * self.view.itemsize # <<<<<<<<<<<<<< @@ -14284,11 +14300,11 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_6nbytes___get__(str * @property */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 579, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_size); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 586, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_self->view.itemsize); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 579, __pyx_L1_error) + __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_self->view.itemsize); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 586, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyNumber_Multiply(__pyx_t_1, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 579, __pyx_L1_error) + __pyx_t_3 = PyNumber_Multiply(__pyx_t_1, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 586, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; @@ -14296,7 +14312,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_6nbytes___get__(str __pyx_t_3 = 0; goto __pyx_L0; - /* "View.MemoryView":578 + /* "View.MemoryView":585 * * @property * def nbytes(self): # <<<<<<<<<<<<<< @@ -14317,7 +14333,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_6nbytes___get__(str return __pyx_r; } -/* "View.MemoryView":582 +/* "View.MemoryView":589 * * @property * def size(self): # <<<<<<<<<<<<<< @@ -14351,7 +14367,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc PyObject *__pyx_t_6 = NULL; __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":583 + /* "View.MemoryView":590 * @property * def size(self): * if self._size is None: # <<<<<<<<<<<<<< @@ -14362,7 +14378,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":584 + /* "View.MemoryView":591 * def size(self): * if self._size is None: * result = 1 # <<<<<<<<<<<<<< @@ -14372,7 +14388,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc __Pyx_INCREF(__pyx_int_1); __pyx_v_result = __pyx_int_1; - /* "View.MemoryView":586 + /* "View.MemoryView":593 * result = 1 * * for length in self.view.shape[:self.view.ndim]: # <<<<<<<<<<<<<< @@ -14382,25 +14398,25 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc __pyx_t_4 = (__pyx_v_self->view.shape + __pyx_v_self->view.ndim); for (__pyx_t_5 = __pyx_v_self->view.shape; __pyx_t_5 < __pyx_t_4; __pyx_t_5++) { __pyx_t_3 = __pyx_t_5; - __pyx_t_6 = PyInt_FromSsize_t((__pyx_t_3[0])); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 586, __pyx_L1_error) + __pyx_t_6 = PyInt_FromSsize_t((__pyx_t_3[0])); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 593, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_XDECREF_SET(__pyx_v_length, __pyx_t_6); __pyx_t_6 = 0; - /* "View.MemoryView":587 + /* "View.MemoryView":594 * * for length in self.view.shape[:self.view.ndim]: * result *= length # <<<<<<<<<<<<<< * * self._size = result */ - __pyx_t_6 = PyNumber_InPlaceMultiply(__pyx_v_result, __pyx_v_length); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 587, __pyx_L1_error) + __pyx_t_6 = PyNumber_InPlaceMultiply(__pyx_v_result, __pyx_v_length); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 594, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_DECREF_SET(__pyx_v_result, __pyx_t_6); __pyx_t_6 = 0; } - /* "View.MemoryView":589 + /* "View.MemoryView":596 * result *= length * * self._size = result # <<<<<<<<<<<<<< @@ -14413,7 +14429,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc __Pyx_DECREF(__pyx_v_self->_size); __pyx_v_self->_size = __pyx_v_result; - /* "View.MemoryView":583 + /* "View.MemoryView":590 * @property * def size(self): * if self._size is None: # <<<<<<<<<<<<<< @@ -14422,7 +14438,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc */ } - /* "View.MemoryView":591 + /* "View.MemoryView":598 * self._size = result * * return self._size # <<<<<<<<<<<<<< @@ -14434,7 +14450,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc __pyx_r = __pyx_v_self->_size; goto __pyx_L0; - /* "View.MemoryView":582 + /* "View.MemoryView":589 * * @property * def size(self): # <<<<<<<<<<<<<< @@ -14455,7 +14471,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_10memoryview_4size___get__(struc return __pyx_r; } -/* "View.MemoryView":593 +/* "View.MemoryView":600 * return self._size * * def __len__(self): # <<<<<<<<<<<<<< @@ -14482,7 +14498,7 @@ static Py_ssize_t __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_1 int __pyx_t_1; __Pyx_RefNannySetupContext("__len__", 0); - /* "View.MemoryView":594 + /* "View.MemoryView":601 * * def __len__(self): * if self.view.ndim >= 1: # <<<<<<<<<<<<<< @@ -14492,7 +14508,7 @@ static Py_ssize_t __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_1 __pyx_t_1 = ((__pyx_v_self->view.ndim >= 1) != 0); if (__pyx_t_1) { - /* "View.MemoryView":595 + /* "View.MemoryView":602 * def __len__(self): * if self.view.ndim >= 1: * return self.view.shape[0] # <<<<<<<<<<<<<< @@ -14502,7 +14518,7 @@ static Py_ssize_t __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_1 __pyx_r = (__pyx_v_self->view.shape[0]); goto __pyx_L0; - /* "View.MemoryView":594 + /* "View.MemoryView":601 * * def __len__(self): * if self.view.ndim >= 1: # <<<<<<<<<<<<<< @@ -14511,7 +14527,7 @@ static Py_ssize_t __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_1 */ } - /* "View.MemoryView":597 + /* "View.MemoryView":604 * return self.view.shape[0] * * return 0 # <<<<<<<<<<<<<< @@ -14521,7 +14537,7 @@ static Py_ssize_t __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_1 __pyx_r = 0; goto __pyx_L0; - /* "View.MemoryView":593 + /* "View.MemoryView":600 * return self._size * * def __len__(self): # <<<<<<<<<<<<<< @@ -14535,7 +14551,7 @@ static Py_ssize_t __pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_1 return __pyx_r; } -/* "View.MemoryView":599 +/* "View.MemoryView":606 * return 0 * * def __repr__(self): # <<<<<<<<<<<<<< @@ -14564,7 +14580,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_12 PyObject *__pyx_t_3 = NULL; __Pyx_RefNannySetupContext("__repr__", 0); - /* "View.MemoryView":600 + /* "View.MemoryView":607 * * def __repr__(self): * return "" % (self.base.__class__.__name__, # <<<<<<<<<<<<<< @@ -14572,54 +14588,48 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_12 * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_base); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 600, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_base); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 607, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_class); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 600, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_class); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 607, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_name_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 600, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_name_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 607, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":601 + /* "View.MemoryView":608 * def __repr__(self): * return "" % (self.base.__class__.__name__, * id(self)) # <<<<<<<<<<<<<< * * def __str__(self): */ - __pyx_t_2 = PyTuple_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 601, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_builtin_id, ((PyObject *)__pyx_v_self)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 608, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __Pyx_INCREF(((PyObject *)__pyx_v_self)); - __Pyx_GIVEREF(((PyObject *)__pyx_v_self)); - PyTuple_SET_ITEM(__pyx_t_2, 0, ((PyObject *)__pyx_v_self)); - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_id, __pyx_t_2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 601, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":600 + /* "View.MemoryView":607 * * def __repr__(self): * return "" % (self.base.__class__.__name__, # <<<<<<<<<<<<<< * id(self)) * */ - __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 600, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_2); + __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 607, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_1); - PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_1); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_t_3); + PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1); + __Pyx_GIVEREF(__pyx_t_2); + PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_t_2); __pyx_t_1 = 0; - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_MemoryView_of_r_at_0x_x, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 600, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_r = __pyx_t_3; - __pyx_t_3 = 0; + __pyx_t_2 = 0; + __pyx_t_2 = __Pyx_PyString_Format(__pyx_kp_s_MemoryView_of_r_at_0x_x, __pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 607, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_2); + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_r = __pyx_t_2; + __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":599 + /* "View.MemoryView":606 * return 0 * * def __repr__(self): # <<<<<<<<<<<<<< @@ -14640,7 +14650,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_12 return __pyx_r; } -/* "View.MemoryView":603 +/* "View.MemoryView":610 * id(self)) * * def __str__(self): # <<<<<<<<<<<<<< @@ -14668,7 +14678,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_14 PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("__str__", 0); - /* "View.MemoryView":604 + /* "View.MemoryView":611 * * def __str__(self): * return "" % (self.base.__class__.__name__,) # <<<<<<<<<<<<<< @@ -14676,27 +14686,27 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_14 * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_base); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 604, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_base); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 611, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_class); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 604, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_1, __pyx_n_s_class); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 611, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_name_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 604, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_name_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 611, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = PyTuple_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 604, __pyx_L1_error) + __pyx_t_2 = PyTuple_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 611, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_1); __pyx_t_1 = 0; - __pyx_t_1 = __Pyx_PyString_Format(__pyx_kp_s_MemoryView_of_r_object, __pyx_t_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 604, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyString_Format(__pyx_kp_s_MemoryView_of_r_object, __pyx_t_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 611, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":603 + /* "View.MemoryView":610 * id(self)) * * def __str__(self): # <<<<<<<<<<<<<< @@ -14716,7 +14726,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_14 return __pyx_r; } -/* "View.MemoryView":607 +/* "View.MemoryView":614 * * * def is_c_contig(self): # <<<<<<<<<<<<<< @@ -14745,7 +14755,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_16 PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("is_c_contig", 0); - /* "View.MemoryView":610 + /* "View.MemoryView":617 * cdef __Pyx_memviewslice *mslice * cdef __Pyx_memviewslice tmp * mslice = get_slice_from_memview(self, &tmp) # <<<<<<<<<<<<<< @@ -14754,7 +14764,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_16 */ __pyx_v_mslice = __pyx_memoryview_get_slice_from_memoryview(__pyx_v_self, (&__pyx_v_tmp)); - /* "View.MemoryView":611 + /* "View.MemoryView":618 * cdef __Pyx_memviewslice tmp * mslice = get_slice_from_memview(self, &tmp) * return slice_is_contig(mslice[0], 'C', self.view.ndim) # <<<<<<<<<<<<<< @@ -14762,13 +14772,13 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_16 * def is_f_contig(self): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_memviewslice_is_contig((__pyx_v_mslice[0]), 'C', __pyx_v_self->view.ndim)); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 611, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_memviewslice_is_contig((__pyx_v_mslice[0]), 'C', __pyx_v_self->view.ndim)); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 618, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":607 + /* "View.MemoryView":614 * * * def is_c_contig(self): # <<<<<<<<<<<<<< @@ -14787,7 +14797,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_16 return __pyx_r; } -/* "View.MemoryView":613 +/* "View.MemoryView":620 * return slice_is_contig(mslice[0], 'C', self.view.ndim) * * def is_f_contig(self): # <<<<<<<<<<<<<< @@ -14816,7 +14826,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_18 PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("is_f_contig", 0); - /* "View.MemoryView":616 + /* "View.MemoryView":623 * cdef __Pyx_memviewslice *mslice * cdef __Pyx_memviewslice tmp * mslice = get_slice_from_memview(self, &tmp) # <<<<<<<<<<<<<< @@ -14825,7 +14835,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_18 */ __pyx_v_mslice = __pyx_memoryview_get_slice_from_memoryview(__pyx_v_self, (&__pyx_v_tmp)); - /* "View.MemoryView":617 + /* "View.MemoryView":624 * cdef __Pyx_memviewslice tmp * mslice = get_slice_from_memview(self, &tmp) * return slice_is_contig(mslice[0], 'F', self.view.ndim) # <<<<<<<<<<<<<< @@ -14833,13 +14843,13 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_18 * def copy(self): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_memviewslice_is_contig((__pyx_v_mslice[0]), 'F', __pyx_v_self->view.ndim)); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 617, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_memviewslice_is_contig((__pyx_v_mslice[0]), 'F', __pyx_v_self->view.ndim)); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 624, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":613 + /* "View.MemoryView":620 * return slice_is_contig(mslice[0], 'C', self.view.ndim) * * def is_f_contig(self): # <<<<<<<<<<<<<< @@ -14858,7 +14868,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_18 return __pyx_r; } -/* "View.MemoryView":619 +/* "View.MemoryView":626 * return slice_is_contig(mslice[0], 'F', self.view.ndim) * * def copy(self): # <<<<<<<<<<<<<< @@ -14888,7 +14898,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_20 PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("copy", 0); - /* "View.MemoryView":621 + /* "View.MemoryView":628 * def copy(self): * cdef __Pyx_memviewslice mslice * cdef int flags = self.flags & ~PyBUF_F_CONTIGUOUS # <<<<<<<<<<<<<< @@ -14897,7 +14907,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_20 */ __pyx_v_flags = (__pyx_v_self->flags & (~PyBUF_F_CONTIGUOUS)); - /* "View.MemoryView":623 + /* "View.MemoryView":630 * cdef int flags = self.flags & ~PyBUF_F_CONTIGUOUS * * slice_copy(self, &mslice) # <<<<<<<<<<<<<< @@ -14906,17 +14916,17 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_20 */ __pyx_memoryview_slice_copy(__pyx_v_self, (&__pyx_v_mslice)); - /* "View.MemoryView":624 + /* "View.MemoryView":631 * * slice_copy(self, &mslice) * mslice = slice_copy_contig(&mslice, "c", self.view.ndim, # <<<<<<<<<<<<<< * self.view.itemsize, * flags|PyBUF_C_CONTIGUOUS, */ - __pyx_t_1 = __pyx_memoryview_copy_new_contig((&__pyx_v_mslice), ((char *)"c"), __pyx_v_self->view.ndim, __pyx_v_self->view.itemsize, (__pyx_v_flags | PyBUF_C_CONTIGUOUS), __pyx_v_self->dtype_is_object); if (unlikely(PyErr_Occurred())) __PYX_ERR(2, 624, __pyx_L1_error) + __pyx_t_1 = __pyx_memoryview_copy_new_contig((&__pyx_v_mslice), ((char *)"c"), __pyx_v_self->view.ndim, __pyx_v_self->view.itemsize, (__pyx_v_flags | PyBUF_C_CONTIGUOUS), __pyx_v_self->dtype_is_object); if (unlikely(PyErr_Occurred())) __PYX_ERR(2, 631, __pyx_L1_error) __pyx_v_mslice = __pyx_t_1; - /* "View.MemoryView":629 + /* "View.MemoryView":636 * self.dtype_is_object) * * return memoryview_copy_from_slice(self, &mslice) # <<<<<<<<<<<<<< @@ -14924,13 +14934,13 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_20 * def copy_fortran(self): */ __Pyx_XDECREF(__pyx_r); - __pyx_t_2 = __pyx_memoryview_copy_object_from_slice(__pyx_v_self, (&__pyx_v_mslice)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 629, __pyx_L1_error) + __pyx_t_2 = __pyx_memoryview_copy_object_from_slice(__pyx_v_self, (&__pyx_v_mslice)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 636, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":619 + /* "View.MemoryView":626 * return slice_is_contig(mslice[0], 'F', self.view.ndim) * * def copy(self): # <<<<<<<<<<<<<< @@ -14949,7 +14959,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_20 return __pyx_r; } -/* "View.MemoryView":631 +/* "View.MemoryView":638 * return memoryview_copy_from_slice(self, &mslice) * * def copy_fortran(self): # <<<<<<<<<<<<<< @@ -14980,7 +14990,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_22 PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("copy_fortran", 0); - /* "View.MemoryView":633 + /* "View.MemoryView":640 * def copy_fortran(self): * cdef __Pyx_memviewslice src, dst * cdef int flags = self.flags & ~PyBUF_C_CONTIGUOUS # <<<<<<<<<<<<<< @@ -14989,7 +14999,7 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_22 */ __pyx_v_flags = (__pyx_v_self->flags & (~PyBUF_C_CONTIGUOUS)); - /* "View.MemoryView":635 + /* "View.MemoryView":642 * cdef int flags = self.flags & ~PyBUF_C_CONTIGUOUS * * slice_copy(self, &src) # <<<<<<<<<<<<<< @@ -14998,17 +15008,17 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_22 */ __pyx_memoryview_slice_copy(__pyx_v_self, (&__pyx_v_src)); - /* "View.MemoryView":636 + /* "View.MemoryView":643 * * slice_copy(self, &src) * dst = slice_copy_contig(&src, "fortran", self.view.ndim, # <<<<<<<<<<<<<< * self.view.itemsize, * flags|PyBUF_F_CONTIGUOUS, */ - __pyx_t_1 = __pyx_memoryview_copy_new_contig((&__pyx_v_src), ((char *)"fortran"), __pyx_v_self->view.ndim, __pyx_v_self->view.itemsize, (__pyx_v_flags | PyBUF_F_CONTIGUOUS), __pyx_v_self->dtype_is_object); if (unlikely(PyErr_Occurred())) __PYX_ERR(2, 636, __pyx_L1_error) + __pyx_t_1 = __pyx_memoryview_copy_new_contig((&__pyx_v_src), ((char *)"fortran"), __pyx_v_self->view.ndim, __pyx_v_self->view.itemsize, (__pyx_v_flags | PyBUF_F_CONTIGUOUS), __pyx_v_self->dtype_is_object); if (unlikely(PyErr_Occurred())) __PYX_ERR(2, 643, __pyx_L1_error) __pyx_v_dst = __pyx_t_1; - /* "View.MemoryView":641 + /* "View.MemoryView":648 * self.dtype_is_object) * * return memoryview_copy_from_slice(self, &dst) # <<<<<<<<<<<<<< @@ -15016,13 +15026,13 @@ static PyObject *__pyx_memoryview___pyx_pf_15View_dot_MemoryView_10memoryview_22 * */ __Pyx_XDECREF(__pyx_r); - __pyx_t_2 = __pyx_memoryview_copy_object_from_slice(__pyx_v_self, (&__pyx_v_dst)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 641, __pyx_L1_error) + __pyx_t_2 = __pyx_memoryview_copy_object_from_slice(__pyx_v_self, (&__pyx_v_dst)); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 648, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":631 + /* "View.MemoryView":638 * return memoryview_copy_from_slice(self, &mslice) * * def copy_fortran(self): # <<<<<<<<<<<<<< @@ -15072,7 +15082,7 @@ static PyObject *__pyx_pf___pyx_memoryview___reduce_cython__(CYTHON_UNUSED struc * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") */ - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__29, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 2, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__31, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 2, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -15125,7 +15135,7 @@ static PyObject *__pyx_pf___pyx_memoryview_2__setstate_cython__(CYTHON_UNUSED st * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") # <<<<<<<<<<<<<< */ - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__30, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 4, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__32, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 4, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -15148,7 +15158,7 @@ static PyObject *__pyx_pf___pyx_memoryview_2__setstate_cython__(CYTHON_UNUSED st return __pyx_r; } -/* "View.MemoryView":645 +/* "View.MemoryView":652 * * @cname('__pyx_memoryview_new') * cdef memoryview_cwrapper(object o, int flags, bint dtype_is_object, __Pyx_TypeInfo *typeinfo): # <<<<<<<<<<<<<< @@ -15165,18 +15175,18 @@ static PyObject *__pyx_memoryview_new(PyObject *__pyx_v_o, int __pyx_v_flags, in PyObject *__pyx_t_3 = NULL; __Pyx_RefNannySetupContext("memoryview_cwrapper", 0); - /* "View.MemoryView":646 + /* "View.MemoryView":653 * @cname('__pyx_memoryview_new') * cdef memoryview_cwrapper(object o, int flags, bint dtype_is_object, __Pyx_TypeInfo *typeinfo): * cdef memoryview result = memoryview(o, flags, dtype_is_object) # <<<<<<<<<<<<<< * result.typeinfo = typeinfo * return result */ - __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_flags); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 646, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_flags); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 653, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __Pyx_PyBool_FromLong(__pyx_v_dtype_is_object); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 646, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyBool_FromLong(__pyx_v_dtype_is_object); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 653, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyTuple_New(3); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 646, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(3); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 653, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_v_o); __Pyx_GIVEREF(__pyx_v_o); @@ -15187,13 +15197,13 @@ static PyObject *__pyx_memoryview_new(PyObject *__pyx_v_o, int __pyx_v_flags, in PyTuple_SET_ITEM(__pyx_t_3, 2, __pyx_t_2); __pyx_t_1 = 0; __pyx_t_2 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryview_type), __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 646, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryview_type), __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 653, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_result = ((struct __pyx_memoryview_obj *)__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":647 + /* "View.MemoryView":654 * cdef memoryview_cwrapper(object o, int flags, bint dtype_is_object, __Pyx_TypeInfo *typeinfo): * cdef memoryview result = memoryview(o, flags, dtype_is_object) * result.typeinfo = typeinfo # <<<<<<<<<<<<<< @@ -15202,7 +15212,7 @@ static PyObject *__pyx_memoryview_new(PyObject *__pyx_v_o, int __pyx_v_flags, in */ __pyx_v_result->typeinfo = __pyx_v_typeinfo; - /* "View.MemoryView":648 + /* "View.MemoryView":655 * cdef memoryview result = memoryview(o, flags, dtype_is_object) * result.typeinfo = typeinfo * return result # <<<<<<<<<<<<<< @@ -15214,7 +15224,7 @@ static PyObject *__pyx_memoryview_new(PyObject *__pyx_v_o, int __pyx_v_flags, in __pyx_r = ((PyObject *)__pyx_v_result); goto __pyx_L0; - /* "View.MemoryView":645 + /* "View.MemoryView":652 * * @cname('__pyx_memoryview_new') * cdef memoryview_cwrapper(object o, int flags, bint dtype_is_object, __Pyx_TypeInfo *typeinfo): # <<<<<<<<<<<<<< @@ -15236,7 +15246,7 @@ static PyObject *__pyx_memoryview_new(PyObject *__pyx_v_o, int __pyx_v_flags, in return __pyx_r; } -/* "View.MemoryView":651 +/* "View.MemoryView":658 * * @cname('__pyx_memoryview_check') * cdef inline bint memoryview_check(object o): # <<<<<<<<<<<<<< @@ -15250,7 +15260,7 @@ static CYTHON_INLINE int __pyx_memoryview_check(PyObject *__pyx_v_o) { int __pyx_t_1; __Pyx_RefNannySetupContext("memoryview_check", 0); - /* "View.MemoryView":652 + /* "View.MemoryView":659 * @cname('__pyx_memoryview_check') * cdef inline bint memoryview_check(object o): * return isinstance(o, memoryview) # <<<<<<<<<<<<<< @@ -15261,7 +15271,7 @@ static CYTHON_INLINE int __pyx_memoryview_check(PyObject *__pyx_v_o) { __pyx_r = __pyx_t_1; goto __pyx_L0; - /* "View.MemoryView":651 + /* "View.MemoryView":658 * * @cname('__pyx_memoryview_check') * cdef inline bint memoryview_check(object o): # <<<<<<<<<<<<<< @@ -15275,7 +15285,7 @@ static CYTHON_INLINE int __pyx_memoryview_check(PyObject *__pyx_v_o) { return __pyx_r; } -/* "View.MemoryView":654 +/* "View.MemoryView":661 * return isinstance(o, memoryview) * * cdef tuple _unellipsify(object index, int ndim): # <<<<<<<<<<<<<< @@ -15306,7 +15316,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { PyObject *__pyx_t_11 = NULL; __Pyx_RefNannySetupContext("_unellipsify", 0); - /* "View.MemoryView":659 + /* "View.MemoryView":666 * full slices. * """ * if not isinstance(index, tuple): # <<<<<<<<<<<<<< @@ -15317,14 +15327,14 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_2 = ((!(__pyx_t_1 != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":660 + /* "View.MemoryView":667 * """ * if not isinstance(index, tuple): * tup = (index,) # <<<<<<<<<<<<<< * else: * tup = index */ - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 660, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 667, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_v_index); __Pyx_GIVEREF(__pyx_v_index); @@ -15332,7 +15342,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_v_tup = __pyx_t_3; __pyx_t_3 = 0; - /* "View.MemoryView":659 + /* "View.MemoryView":666 * full slices. * """ * if not isinstance(index, tuple): # <<<<<<<<<<<<<< @@ -15342,7 +15352,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { goto __pyx_L3; } - /* "View.MemoryView":662 + /* "View.MemoryView":669 * tup = (index,) * else: * tup = index # <<<<<<<<<<<<<< @@ -15355,19 +15365,19 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { } __pyx_L3:; - /* "View.MemoryView":664 + /* "View.MemoryView":671 * tup = index * * result = [] # <<<<<<<<<<<<<< * have_slices = False * seen_ellipsis = False */ - __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 664, __pyx_L1_error) + __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 671, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_v_result = ((PyObject*)__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":665 + /* "View.MemoryView":672 * * result = [] * have_slices = False # <<<<<<<<<<<<<< @@ -15376,7 +15386,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { */ __pyx_v_have_slices = 0; - /* "View.MemoryView":666 + /* "View.MemoryView":673 * result = [] * have_slices = False * seen_ellipsis = False # <<<<<<<<<<<<<< @@ -15385,7 +15395,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { */ __pyx_v_seen_ellipsis = 0; - /* "View.MemoryView":667 + /* "View.MemoryView":674 * have_slices = False * seen_ellipsis = False * for idx, item in enumerate(tup): # <<<<<<<<<<<<<< @@ -15398,26 +15408,26 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_4 = __pyx_v_tup; __Pyx_INCREF(__pyx_t_4); __pyx_t_5 = 0; __pyx_t_6 = NULL; } else { - __pyx_t_5 = -1; __pyx_t_4 = PyObject_GetIter(__pyx_v_tup); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_5 = -1; __pyx_t_4 = PyObject_GetIter(__pyx_v_tup); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 674, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_6 = Py_TYPE(__pyx_t_4)->tp_iternext; if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_6 = Py_TYPE(__pyx_t_4)->tp_iternext; if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 674, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_6)) { if (likely(PyList_CheckExact(__pyx_t_4))) { if (__pyx_t_5 >= PyList_GET_SIZE(__pyx_t_4)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_7 = PyList_GET_ITEM(__pyx_t_4, __pyx_t_5); __Pyx_INCREF(__pyx_t_7); __pyx_t_5++; if (unlikely(0 < 0)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_7 = PyList_GET_ITEM(__pyx_t_4, __pyx_t_5); __Pyx_INCREF(__pyx_t_7); __pyx_t_5++; if (unlikely(0 < 0)) __PYX_ERR(2, 674, __pyx_L1_error) #else - __pyx_t_7 = PySequence_ITEM(__pyx_t_4, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_7 = PySequence_ITEM(__pyx_t_4, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 674, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); #endif } else { if (__pyx_t_5 >= PyTuple_GET_SIZE(__pyx_t_4)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_7 = PyTuple_GET_ITEM(__pyx_t_4, __pyx_t_5); __Pyx_INCREF(__pyx_t_7); __pyx_t_5++; if (unlikely(0 < 0)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_7 = PyTuple_GET_ITEM(__pyx_t_4, __pyx_t_5); __Pyx_INCREF(__pyx_t_7); __pyx_t_5++; if (unlikely(0 < 0)) __PYX_ERR(2, 674, __pyx_L1_error) #else - __pyx_t_7 = PySequence_ITEM(__pyx_t_4, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_7 = PySequence_ITEM(__pyx_t_4, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 674, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); #endif } @@ -15427,7 +15437,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(2, 667, __pyx_L1_error) + else __PYX_ERR(2, 674, __pyx_L1_error) } break; } @@ -15437,13 +15447,13 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_7 = 0; __Pyx_INCREF(__pyx_t_3); __Pyx_XDECREF_SET(__pyx_v_idx, __pyx_t_3); - __pyx_t_7 = __Pyx_PyInt_AddObjC(__pyx_t_3, __pyx_int_1, 1, 0); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 667, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyInt_AddObjC(__pyx_t_3, __pyx_int_1, 1, 0); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 674, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = __pyx_t_7; __pyx_t_7 = 0; - /* "View.MemoryView":668 + /* "View.MemoryView":675 * seen_ellipsis = False * for idx, item in enumerate(tup): * if item is Ellipsis: # <<<<<<<<<<<<<< @@ -15454,7 +15464,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_1 = (__pyx_t_2 != 0); if (__pyx_t_1) { - /* "View.MemoryView":669 + /* "View.MemoryView":676 * for idx, item in enumerate(tup): * if item is Ellipsis: * if not seen_ellipsis: # <<<<<<<<<<<<<< @@ -15464,27 +15474,27 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_1 = ((!(__pyx_v_seen_ellipsis != 0)) != 0); if (__pyx_t_1) { - /* "View.MemoryView":670 + /* "View.MemoryView":677 * if item is Ellipsis: * if not seen_ellipsis: * result.extend([slice(None)] * (ndim - len(tup) + 1)) # <<<<<<<<<<<<<< * seen_ellipsis = True * else: */ - __pyx_t_8 = PyObject_Length(__pyx_v_tup); if (unlikely(__pyx_t_8 == ((Py_ssize_t)-1))) __PYX_ERR(2, 670, __pyx_L1_error) - __pyx_t_7 = PyList_New(1 * ((((__pyx_v_ndim - __pyx_t_8) + 1)<0) ? 0:((__pyx_v_ndim - __pyx_t_8) + 1))); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 670, __pyx_L1_error) + __pyx_t_8 = PyObject_Length(__pyx_v_tup); if (unlikely(__pyx_t_8 == ((Py_ssize_t)-1))) __PYX_ERR(2, 677, __pyx_L1_error) + __pyx_t_7 = PyList_New(1 * ((((__pyx_v_ndim - __pyx_t_8) + 1)<0) ? 0:((__pyx_v_ndim - __pyx_t_8) + 1))); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 677, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < ((__pyx_v_ndim - __pyx_t_8) + 1); __pyx_temp++) { - __Pyx_INCREF(__pyx_slice__31); - __Pyx_GIVEREF(__pyx_slice__31); - PyList_SET_ITEM(__pyx_t_7, __pyx_temp, __pyx_slice__31); + __Pyx_INCREF(__pyx_slice__33); + __Pyx_GIVEREF(__pyx_slice__33); + PyList_SET_ITEM(__pyx_t_7, __pyx_temp, __pyx_slice__33); } } - __pyx_t_9 = __Pyx_PyList_Extend(__pyx_v_result, __pyx_t_7); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 670, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyList_Extend(__pyx_v_result, __pyx_t_7); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 677, __pyx_L1_error) __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - /* "View.MemoryView":671 + /* "View.MemoryView":678 * if not seen_ellipsis: * result.extend([slice(None)] * (ndim - len(tup) + 1)) * seen_ellipsis = True # <<<<<<<<<<<<<< @@ -15493,7 +15503,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { */ __pyx_v_seen_ellipsis = 1; - /* "View.MemoryView":669 + /* "View.MemoryView":676 * for idx, item in enumerate(tup): * if item is Ellipsis: * if not seen_ellipsis: # <<<<<<<<<<<<<< @@ -15503,7 +15513,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { goto __pyx_L7; } - /* "View.MemoryView":673 + /* "View.MemoryView":680 * seen_ellipsis = True * else: * result.append(slice(None)) # <<<<<<<<<<<<<< @@ -15511,11 +15521,11 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { * else: */ /*else*/ { - __pyx_t_9 = __Pyx_PyList_Append(__pyx_v_result, __pyx_slice__32); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 673, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyList_Append(__pyx_v_result, __pyx_slice__34); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 680, __pyx_L1_error) } __pyx_L7:; - /* "View.MemoryView":674 + /* "View.MemoryView":681 * else: * result.append(slice(None)) * have_slices = True # <<<<<<<<<<<<<< @@ -15524,7 +15534,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { */ __pyx_v_have_slices = 1; - /* "View.MemoryView":668 + /* "View.MemoryView":675 * seen_ellipsis = False * for idx, item in enumerate(tup): * if item is Ellipsis: # <<<<<<<<<<<<<< @@ -15534,7 +15544,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { goto __pyx_L6; } - /* "View.MemoryView":676 + /* "View.MemoryView":683 * have_slices = True * else: * if not isinstance(item, slice) and not PyIndex_Check(item): # <<<<<<<<<<<<<< @@ -15552,30 +15562,25 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_10 = ((!(PyIndex_Check(__pyx_v_item) != 0)) != 0); __pyx_t_1 = __pyx_t_10; __pyx_L9_bool_binop_done:; - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "View.MemoryView":677 + /* "View.MemoryView":684 * else: * if not isinstance(item, slice) and not PyIndex_Check(item): * raise TypeError("Cannot index with type '%s'" % type(item)) # <<<<<<<<<<<<<< * * have_slices = have_slices or isinstance(item, slice) */ - __pyx_t_7 = __Pyx_PyString_Format(__pyx_kp_s_Cannot_index_with_type_s, ((PyObject *)Py_TYPE(__pyx_v_item))); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 677, __pyx_L1_error) + __pyx_t_7 = __Pyx_PyString_Format(__pyx_kp_s_Cannot_index_with_type_s, ((PyObject *)Py_TYPE(__pyx_v_item))); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 684, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); - __pyx_t_11 = PyTuple_New(1); if (unlikely(!__pyx_t_11)) __PYX_ERR(2, 677, __pyx_L1_error) + __pyx_t_11 = __Pyx_PyObject_CallOneArg(__pyx_builtin_TypeError, __pyx_t_7); if (unlikely(!__pyx_t_11)) __PYX_ERR(2, 684, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); - __Pyx_GIVEREF(__pyx_t_7); - PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_t_7); - __pyx_t_7 = 0; - __pyx_t_7 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_t_11, NULL); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 677, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_7); - __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - __Pyx_Raise(__pyx_t_7, 0, 0, 0); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; - __PYX_ERR(2, 677, __pyx_L1_error) + __Pyx_Raise(__pyx_t_11, 0, 0, 0); + __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; + __PYX_ERR(2, 684, __pyx_L1_error) - /* "View.MemoryView":676 + /* "View.MemoryView":683 * have_slices = True * else: * if not isinstance(item, slice) and not PyIndex_Check(item): # <<<<<<<<<<<<<< @@ -15584,7 +15589,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { */ } - /* "View.MemoryView":679 + /* "View.MemoryView":686 * raise TypeError("Cannot index with type '%s'" % type(item)) * * have_slices = have_slices or isinstance(item, slice) # <<<<<<<<<<<<<< @@ -15603,18 +15608,18 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_L11_bool_binop_done:; __pyx_v_have_slices = __pyx_t_1; - /* "View.MemoryView":680 + /* "View.MemoryView":687 * * have_slices = have_slices or isinstance(item, slice) * result.append(item) # <<<<<<<<<<<<<< * * nslices = ndim - len(result) */ - __pyx_t_9 = __Pyx_PyList_Append(__pyx_v_result, __pyx_v_item); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 680, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyList_Append(__pyx_v_result, __pyx_v_item); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 687, __pyx_L1_error) } __pyx_L6:; - /* "View.MemoryView":667 + /* "View.MemoryView":674 * have_slices = False * seen_ellipsis = False * for idx, item in enumerate(tup): # <<<<<<<<<<<<<< @@ -15625,17 +15630,17 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":682 + /* "View.MemoryView":689 * result.append(item) * * nslices = ndim - len(result) # <<<<<<<<<<<<<< * if nslices: * result.extend([slice(None)] * nslices) */ - __pyx_t_5 = PyList_GET_SIZE(__pyx_v_result); if (unlikely(__pyx_t_5 == ((Py_ssize_t)-1))) __PYX_ERR(2, 682, __pyx_L1_error) + __pyx_t_5 = PyList_GET_SIZE(__pyx_v_result); if (unlikely(__pyx_t_5 == ((Py_ssize_t)-1))) __PYX_ERR(2, 689, __pyx_L1_error) __pyx_v_nslices = (__pyx_v_ndim - __pyx_t_5); - /* "View.MemoryView":683 + /* "View.MemoryView":690 * * nslices = ndim - len(result) * if nslices: # <<<<<<<<<<<<<< @@ -15645,26 +15650,26 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __pyx_t_1 = (__pyx_v_nslices != 0); if (__pyx_t_1) { - /* "View.MemoryView":684 + /* "View.MemoryView":691 * nslices = ndim - len(result) * if nslices: * result.extend([slice(None)] * nslices) # <<<<<<<<<<<<<< * * return have_slices or nslices, tuple(result) */ - __pyx_t_3 = PyList_New(1 * ((__pyx_v_nslices<0) ? 0:__pyx_v_nslices)); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 684, __pyx_L1_error) + __pyx_t_3 = PyList_New(1 * ((__pyx_v_nslices<0) ? 0:__pyx_v_nslices)); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 691, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < __pyx_v_nslices; __pyx_temp++) { - __Pyx_INCREF(__pyx_slice__33); - __Pyx_GIVEREF(__pyx_slice__33); - PyList_SET_ITEM(__pyx_t_3, __pyx_temp, __pyx_slice__33); + __Pyx_INCREF(__pyx_slice__35); + __Pyx_GIVEREF(__pyx_slice__35); + PyList_SET_ITEM(__pyx_t_3, __pyx_temp, __pyx_slice__35); } } - __pyx_t_9 = __Pyx_PyList_Extend(__pyx_v_result, __pyx_t_3); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 684, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyList_Extend(__pyx_v_result, __pyx_t_3); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 691, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":683 + /* "View.MemoryView":690 * * nslices = ndim - len(result) * if nslices: # <<<<<<<<<<<<<< @@ -15673,7 +15678,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { */ } - /* "View.MemoryView":686 + /* "View.MemoryView":693 * result.extend([slice(None)] * nslices) * * return have_slices or nslices, tuple(result) # <<<<<<<<<<<<<< @@ -15683,32 +15688,32 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { __Pyx_XDECREF(__pyx_r); if (!__pyx_v_have_slices) { } else { - __pyx_t_4 = __Pyx_PyBool_FromLong(__pyx_v_have_slices); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 686, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyBool_FromLong(__pyx_v_have_slices); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 693, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_3 = __pyx_t_4; __pyx_t_4 = 0; goto __pyx_L14_bool_binop_done; } - __pyx_t_4 = PyInt_FromSsize_t(__pyx_v_nslices); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 686, __pyx_L1_error) + __pyx_t_4 = PyInt_FromSsize_t(__pyx_v_nslices); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 693, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_3 = __pyx_t_4; __pyx_t_4 = 0; __pyx_L14_bool_binop_done:; - __pyx_t_4 = PyList_AsTuple(__pyx_v_result); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 686, __pyx_L1_error) + __pyx_t_4 = PyList_AsTuple(__pyx_v_result); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 693, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __pyx_t_7 = PyTuple_New(2); if (unlikely(!__pyx_t_7)) __PYX_ERR(2, 686, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_7); + __pyx_t_11 = PyTuple_New(2); if (unlikely(!__pyx_t_11)) __PYX_ERR(2, 693, __pyx_L1_error) + __Pyx_GOTREF(__pyx_t_11); __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_7, 0, __pyx_t_3); + PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_4); - PyTuple_SET_ITEM(__pyx_t_7, 1, __pyx_t_4); + PyTuple_SET_ITEM(__pyx_t_11, 1, __pyx_t_4); __pyx_t_3 = 0; __pyx_t_4 = 0; - __pyx_r = ((PyObject*)__pyx_t_7); - __pyx_t_7 = 0; + __pyx_r = ((PyObject*)__pyx_t_11); + __pyx_t_11 = 0; goto __pyx_L0; - /* "View.MemoryView":654 + /* "View.MemoryView":661 * return isinstance(o, memoryview) * * cdef tuple _unellipsify(object index, int ndim): # <<<<<<<<<<<<<< @@ -15734,7 +15739,7 @@ static PyObject *_unellipsify(PyObject *__pyx_v_index, int __pyx_v_ndim) { return __pyx_r; } -/* "View.MemoryView":688 +/* "View.MemoryView":695 * return have_slices or nslices, tuple(result) * * cdef assert_direct_dimensions(Py_ssize_t *suboffsets, int ndim): # <<<<<<<<<<<<<< @@ -15753,7 +15758,7 @@ static PyObject *assert_direct_dimensions(Py_ssize_t *__pyx_v_suboffsets, int __ PyObject *__pyx_t_5 = NULL; __Pyx_RefNannySetupContext("assert_direct_dimensions", 0); - /* "View.MemoryView":689 + /* "View.MemoryView":696 * * cdef assert_direct_dimensions(Py_ssize_t *suboffsets, int ndim): * for suboffset in suboffsets[:ndim]: # <<<<<<<<<<<<<< @@ -15765,7 +15770,7 @@ static PyObject *assert_direct_dimensions(Py_ssize_t *__pyx_v_suboffsets, int __ __pyx_t_1 = __pyx_t_3; __pyx_v_suboffset = (__pyx_t_1[0]); - /* "View.MemoryView":690 + /* "View.MemoryView":697 * cdef assert_direct_dimensions(Py_ssize_t *suboffsets, int ndim): * for suboffset in suboffsets[:ndim]: * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -15773,22 +15778,22 @@ static PyObject *assert_direct_dimensions(Py_ssize_t *__pyx_v_suboffsets, int __ * */ __pyx_t_4 = ((__pyx_v_suboffset >= 0) != 0); - if (__pyx_t_4) { + if (unlikely(__pyx_t_4)) { - /* "View.MemoryView":691 + /* "View.MemoryView":698 * for suboffset in suboffsets[:ndim]: * if suboffset >= 0: * raise ValueError("Indirect dimensions not supported") # <<<<<<<<<<<<<< * * */ - __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__34, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 691, __pyx_L1_error) + __pyx_t_5 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_tuple__36, NULL); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 698, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_Raise(__pyx_t_5, 0, 0, 0); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; - __PYX_ERR(2, 691, __pyx_L1_error) + __PYX_ERR(2, 698, __pyx_L1_error) - /* "View.MemoryView":690 + /* "View.MemoryView":697 * cdef assert_direct_dimensions(Py_ssize_t *suboffsets, int ndim): * for suboffset in suboffsets[:ndim]: * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -15798,7 +15803,7 @@ static PyObject *assert_direct_dimensions(Py_ssize_t *__pyx_v_suboffsets, int __ } } - /* "View.MemoryView":688 + /* "View.MemoryView":695 * return have_slices or nslices, tuple(result) * * cdef assert_direct_dimensions(Py_ssize_t *suboffsets, int ndim): # <<<<<<<<<<<<<< @@ -15819,7 +15824,7 @@ static PyObject *assert_direct_dimensions(Py_ssize_t *__pyx_v_suboffsets, int __ return __pyx_r; } -/* "View.MemoryView":698 +/* "View.MemoryView":705 * * @cname('__pyx_memview_slice') * cdef memoryview memview_slice(memoryview memview, object indices): # <<<<<<<<<<<<<< @@ -15860,7 +15865,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ Py_ssize_t __pyx_t_12; __Pyx_RefNannySetupContext("memview_slice", 0); - /* "View.MemoryView":699 + /* "View.MemoryView":706 * @cname('__pyx_memview_slice') * cdef memoryview memview_slice(memoryview memview, object indices): * cdef int new_ndim = 0, suboffset_dim = -1, dim # <<<<<<<<<<<<<< @@ -15870,16 +15875,16 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_v_new_ndim = 0; __pyx_v_suboffset_dim = -1; - /* "View.MemoryView":706 + /* "View.MemoryView":713 * * * memset(&dst, 0, sizeof(dst)) # <<<<<<<<<<<<<< * * cdef _memoryviewslice memviewsliceobj */ - memset((&__pyx_v_dst), 0, (sizeof(__pyx_v_dst))); + (void)(memset((&__pyx_v_dst), 0, (sizeof(__pyx_v_dst)))); - /* "View.MemoryView":710 + /* "View.MemoryView":717 * cdef _memoryviewslice memviewsliceobj * * assert memview.view.ndim > 0 # <<<<<<<<<<<<<< @@ -15890,12 +15895,12 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ if (unlikely(!Py_OptimizeFlag)) { if (unlikely(!((__pyx_v_memview->view.ndim > 0) != 0))) { PyErr_SetNone(PyExc_AssertionError); - __PYX_ERR(2, 710, __pyx_L1_error) + __PYX_ERR(2, 717, __pyx_L1_error) } } #endif - /* "View.MemoryView":712 + /* "View.MemoryView":719 * assert memview.view.ndim > 0 * * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -15906,20 +15911,20 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":713 + /* "View.MemoryView":720 * * if isinstance(memview, _memoryviewslice): * memviewsliceobj = memview # <<<<<<<<<<<<<< * p_src = &memviewsliceobj.from_slice * else: */ - if (!(likely(((((PyObject *)__pyx_v_memview)) == Py_None) || likely(__Pyx_TypeTest(((PyObject *)__pyx_v_memview), __pyx_memoryviewslice_type))))) __PYX_ERR(2, 713, __pyx_L1_error) + if (!(likely(((((PyObject *)__pyx_v_memview)) == Py_None) || likely(__Pyx_TypeTest(((PyObject *)__pyx_v_memview), __pyx_memoryviewslice_type))))) __PYX_ERR(2, 720, __pyx_L1_error) __pyx_t_3 = ((PyObject *)__pyx_v_memview); __Pyx_INCREF(__pyx_t_3); __pyx_v_memviewsliceobj = ((struct __pyx_memoryviewslice_obj *)__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":714 + /* "View.MemoryView":721 * if isinstance(memview, _memoryviewslice): * memviewsliceobj = memview * p_src = &memviewsliceobj.from_slice # <<<<<<<<<<<<<< @@ -15928,7 +15933,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ __pyx_v_p_src = (&__pyx_v_memviewsliceobj->from_slice); - /* "View.MemoryView":712 + /* "View.MemoryView":719 * assert memview.view.ndim > 0 * * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -15938,7 +15943,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ goto __pyx_L3; } - /* "View.MemoryView":716 + /* "View.MemoryView":723 * p_src = &memviewsliceobj.from_slice * else: * slice_copy(memview, &src) # <<<<<<<<<<<<<< @@ -15948,7 +15953,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ /*else*/ { __pyx_memoryview_slice_copy(__pyx_v_memview, (&__pyx_v_src)); - /* "View.MemoryView":717 + /* "View.MemoryView":724 * else: * slice_copy(memview, &src) * p_src = &src # <<<<<<<<<<<<<< @@ -15959,7 +15964,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ } __pyx_L3:; - /* "View.MemoryView":723 + /* "View.MemoryView":730 * * * dst.memview = p_src.memview # <<<<<<<<<<<<<< @@ -15969,7 +15974,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_4 = __pyx_v_p_src->memview; __pyx_v_dst.memview = __pyx_t_4; - /* "View.MemoryView":724 + /* "View.MemoryView":731 * * dst.memview = p_src.memview * dst.data = p_src.data # <<<<<<<<<<<<<< @@ -15979,7 +15984,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_5 = __pyx_v_p_src->data; __pyx_v_dst.data = __pyx_t_5; - /* "View.MemoryView":729 + /* "View.MemoryView":736 * * * cdef __Pyx_memviewslice *p_dst = &dst # <<<<<<<<<<<<<< @@ -15988,7 +15993,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ __pyx_v_p_dst = (&__pyx_v_dst); - /* "View.MemoryView":730 + /* "View.MemoryView":737 * * cdef __Pyx_memviewslice *p_dst = &dst * cdef int *p_suboffset_dim = &suboffset_dim # <<<<<<<<<<<<<< @@ -15997,7 +16002,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ __pyx_v_p_suboffset_dim = (&__pyx_v_suboffset_dim); - /* "View.MemoryView":734 + /* "View.MemoryView":741 * cdef bint have_start, have_stop, have_step * * for dim, index in enumerate(indices): # <<<<<<<<<<<<<< @@ -16009,26 +16014,26 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_3 = __pyx_v_indices; __Pyx_INCREF(__pyx_t_3); __pyx_t_7 = 0; __pyx_t_8 = NULL; } else { - __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_indices); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 734, __pyx_L1_error) + __pyx_t_7 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_v_indices); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 741, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_8 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_8)) __PYX_ERR(2, 734, __pyx_L1_error) + __pyx_t_8 = Py_TYPE(__pyx_t_3)->tp_iternext; if (unlikely(!__pyx_t_8)) __PYX_ERR(2, 741, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_8)) { if (likely(PyList_CheckExact(__pyx_t_3))) { if (__pyx_t_7 >= PyList_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_9 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_9); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(2, 734, __pyx_L1_error) + __pyx_t_9 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_9); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(2, 741, __pyx_L1_error) #else - __pyx_t_9 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 734, __pyx_L1_error) + __pyx_t_9 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 741, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); #endif } else { if (__pyx_t_7 >= PyTuple_GET_SIZE(__pyx_t_3)) break; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS - __pyx_t_9 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_9); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(2, 734, __pyx_L1_error) + __pyx_t_9 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_7); __Pyx_INCREF(__pyx_t_9); __pyx_t_7++; if (unlikely(0 < 0)) __PYX_ERR(2, 741, __pyx_L1_error) #else - __pyx_t_9 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 734, __pyx_L1_error) + __pyx_t_9 = PySequence_ITEM(__pyx_t_3, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 741, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); #endif } @@ -16038,7 +16043,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); - else __PYX_ERR(2, 734, __pyx_L1_error) + else __PYX_ERR(2, 741, __pyx_L1_error) } break; } @@ -16049,7 +16054,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_v_dim = __pyx_t_6; __pyx_t_6 = (__pyx_t_6 + 1); - /* "View.MemoryView":735 + /* "View.MemoryView":742 * * for dim, index in enumerate(indices): * if PyIndex_Check(index): # <<<<<<<<<<<<<< @@ -16059,25 +16064,25 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_2 = (PyIndex_Check(__pyx_v_index) != 0); if (__pyx_t_2) { - /* "View.MemoryView":739 + /* "View.MemoryView":746 * p_dst, p_src.shape[dim], p_src.strides[dim], p_src.suboffsets[dim], * dim, new_ndim, p_suboffset_dim, * index, 0, 0, # start, stop, step # <<<<<<<<<<<<<< * 0, 0, 0, # have_{start,stop,step} * False) */ - __pyx_t_10 = __Pyx_PyIndex_AsSsize_t(__pyx_v_index); if (unlikely((__pyx_t_10 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 739, __pyx_L1_error) + __pyx_t_10 = __Pyx_PyIndex_AsSsize_t(__pyx_v_index); if (unlikely((__pyx_t_10 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 746, __pyx_L1_error) - /* "View.MemoryView":736 + /* "View.MemoryView":743 * for dim, index in enumerate(indices): * if PyIndex_Check(index): * slice_memviewslice( # <<<<<<<<<<<<<< * p_dst, p_src.shape[dim], p_src.strides[dim], p_src.suboffsets[dim], * dim, new_ndim, p_suboffset_dim, */ - __pyx_t_11 = __pyx_memoryview_slice_memviewslice(__pyx_v_p_dst, (__pyx_v_p_src->shape[__pyx_v_dim]), (__pyx_v_p_src->strides[__pyx_v_dim]), (__pyx_v_p_src->suboffsets[__pyx_v_dim]), __pyx_v_dim, __pyx_v_new_ndim, __pyx_v_p_suboffset_dim, __pyx_t_10, 0, 0, 0, 0, 0, 0); if (unlikely(__pyx_t_11 == ((int)-1))) __PYX_ERR(2, 736, __pyx_L1_error) + __pyx_t_11 = __pyx_memoryview_slice_memviewslice(__pyx_v_p_dst, (__pyx_v_p_src->shape[__pyx_v_dim]), (__pyx_v_p_src->strides[__pyx_v_dim]), (__pyx_v_p_src->suboffsets[__pyx_v_dim]), __pyx_v_dim, __pyx_v_new_ndim, __pyx_v_p_suboffset_dim, __pyx_t_10, 0, 0, 0, 0, 0, 0); if (unlikely(__pyx_t_11 == ((int)-1))) __PYX_ERR(2, 743, __pyx_L1_error) - /* "View.MemoryView":735 + /* "View.MemoryView":742 * * for dim, index in enumerate(indices): * if PyIndex_Check(index): # <<<<<<<<<<<<<< @@ -16087,7 +16092,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ goto __pyx_L6; } - /* "View.MemoryView":742 + /* "View.MemoryView":749 * 0, 0, 0, # have_{start,stop,step} * False) * elif index is None: # <<<<<<<<<<<<<< @@ -16098,7 +16103,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_1 = (__pyx_t_2 != 0); if (__pyx_t_1) { - /* "View.MemoryView":743 + /* "View.MemoryView":750 * False) * elif index is None: * p_dst.shape[new_ndim] = 1 # <<<<<<<<<<<<<< @@ -16107,7 +16112,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ (__pyx_v_p_dst->shape[__pyx_v_new_ndim]) = 1; - /* "View.MemoryView":744 + /* "View.MemoryView":751 * elif index is None: * p_dst.shape[new_ndim] = 1 * p_dst.strides[new_ndim] = 0 # <<<<<<<<<<<<<< @@ -16116,7 +16121,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ (__pyx_v_p_dst->strides[__pyx_v_new_ndim]) = 0; - /* "View.MemoryView":745 + /* "View.MemoryView":752 * p_dst.shape[new_ndim] = 1 * p_dst.strides[new_ndim] = 0 * p_dst.suboffsets[new_ndim] = -1 # <<<<<<<<<<<<<< @@ -16125,7 +16130,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ (__pyx_v_p_dst->suboffsets[__pyx_v_new_ndim]) = -1L; - /* "View.MemoryView":746 + /* "View.MemoryView":753 * p_dst.strides[new_ndim] = 0 * p_dst.suboffsets[new_ndim] = -1 * new_ndim += 1 # <<<<<<<<<<<<<< @@ -16134,7 +16139,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ __pyx_v_new_ndim = (__pyx_v_new_ndim + 1); - /* "View.MemoryView":742 + /* "View.MemoryView":749 * 0, 0, 0, # have_{start,stop,step} * False) * elif index is None: # <<<<<<<<<<<<<< @@ -16144,7 +16149,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ goto __pyx_L6; } - /* "View.MemoryView":748 + /* "View.MemoryView":755 * new_ndim += 1 * else: * start = index.start or 0 # <<<<<<<<<<<<<< @@ -16152,13 +16157,13 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ * step = index.step or 0 */ /*else*/ { - __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_start); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 748, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_start); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 755, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); - __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_t_9); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 748, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_t_9); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 755, __pyx_L1_error) if (!__pyx_t_1) { __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } else { - __pyx_t_12 = __Pyx_PyIndex_AsSsize_t(__pyx_t_9); if (unlikely((__pyx_t_12 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 748, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyIndex_AsSsize_t(__pyx_t_9); if (unlikely((__pyx_t_12 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 755, __pyx_L1_error) __pyx_t_10 = __pyx_t_12; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; goto __pyx_L7_bool_binop_done; @@ -16167,20 +16172,20 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_L7_bool_binop_done:; __pyx_v_start = __pyx_t_10; - /* "View.MemoryView":749 + /* "View.MemoryView":756 * else: * start = index.start or 0 * stop = index.stop or 0 # <<<<<<<<<<<<<< * step = index.step or 0 * */ - __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_stop); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 749, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_stop); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 756, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); - __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_t_9); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 749, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_t_9); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 756, __pyx_L1_error) if (!__pyx_t_1) { __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } else { - __pyx_t_12 = __Pyx_PyIndex_AsSsize_t(__pyx_t_9); if (unlikely((__pyx_t_12 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 749, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyIndex_AsSsize_t(__pyx_t_9); if (unlikely((__pyx_t_12 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 756, __pyx_L1_error) __pyx_t_10 = __pyx_t_12; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; goto __pyx_L9_bool_binop_done; @@ -16189,20 +16194,20 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_L9_bool_binop_done:; __pyx_v_stop = __pyx_t_10; - /* "View.MemoryView":750 + /* "View.MemoryView":757 * start = index.start or 0 * stop = index.stop or 0 * step = index.step or 0 # <<<<<<<<<<<<<< * * have_start = index.start is not None */ - __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_step); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 750, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_step); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 757, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); - __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_t_9); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 750, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_IsTrue(__pyx_t_9); if (unlikely(__pyx_t_1 < 0)) __PYX_ERR(2, 757, __pyx_L1_error) if (!__pyx_t_1) { __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } else { - __pyx_t_12 = __Pyx_PyIndex_AsSsize_t(__pyx_t_9); if (unlikely((__pyx_t_12 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 750, __pyx_L1_error) + __pyx_t_12 = __Pyx_PyIndex_AsSsize_t(__pyx_t_9); if (unlikely((__pyx_t_12 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 757, __pyx_L1_error) __pyx_t_10 = __pyx_t_12; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; goto __pyx_L11_bool_binop_done; @@ -16211,55 +16216,55 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_L11_bool_binop_done:; __pyx_v_step = __pyx_t_10; - /* "View.MemoryView":752 + /* "View.MemoryView":759 * step = index.step or 0 * * have_start = index.start is not None # <<<<<<<<<<<<<< * have_stop = index.stop is not None * have_step = index.step is not None */ - __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_start); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 752, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_start); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 759, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __pyx_t_1 = (__pyx_t_9 != Py_None); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; __pyx_v_have_start = __pyx_t_1; - /* "View.MemoryView":753 + /* "View.MemoryView":760 * * have_start = index.start is not None * have_stop = index.stop is not None # <<<<<<<<<<<<<< * have_step = index.step is not None * */ - __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_stop); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 753, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_stop); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 760, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __pyx_t_1 = (__pyx_t_9 != Py_None); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; __pyx_v_have_stop = __pyx_t_1; - /* "View.MemoryView":754 + /* "View.MemoryView":761 * have_start = index.start is not None * have_stop = index.stop is not None * have_step = index.step is not None # <<<<<<<<<<<<<< * * slice_memviewslice( */ - __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_step); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 754, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_v_index, __pyx_n_s_step); if (unlikely(!__pyx_t_9)) __PYX_ERR(2, 761, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __pyx_t_1 = (__pyx_t_9 != Py_None); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; __pyx_v_have_step = __pyx_t_1; - /* "View.MemoryView":756 + /* "View.MemoryView":763 * have_step = index.step is not None * * slice_memviewslice( # <<<<<<<<<<<<<< * p_dst, p_src.shape[dim], p_src.strides[dim], p_src.suboffsets[dim], * dim, new_ndim, p_suboffset_dim, */ - __pyx_t_11 = __pyx_memoryview_slice_memviewslice(__pyx_v_p_dst, (__pyx_v_p_src->shape[__pyx_v_dim]), (__pyx_v_p_src->strides[__pyx_v_dim]), (__pyx_v_p_src->suboffsets[__pyx_v_dim]), __pyx_v_dim, __pyx_v_new_ndim, __pyx_v_p_suboffset_dim, __pyx_v_start, __pyx_v_stop, __pyx_v_step, __pyx_v_have_start, __pyx_v_have_stop, __pyx_v_have_step, 1); if (unlikely(__pyx_t_11 == ((int)-1))) __PYX_ERR(2, 756, __pyx_L1_error) + __pyx_t_11 = __pyx_memoryview_slice_memviewslice(__pyx_v_p_dst, (__pyx_v_p_src->shape[__pyx_v_dim]), (__pyx_v_p_src->strides[__pyx_v_dim]), (__pyx_v_p_src->suboffsets[__pyx_v_dim]), __pyx_v_dim, __pyx_v_new_ndim, __pyx_v_p_suboffset_dim, __pyx_v_start, __pyx_v_stop, __pyx_v_step, __pyx_v_have_start, __pyx_v_have_stop, __pyx_v_have_step, 1); if (unlikely(__pyx_t_11 == ((int)-1))) __PYX_ERR(2, 763, __pyx_L1_error) - /* "View.MemoryView":762 + /* "View.MemoryView":769 * have_start, have_stop, have_step, * True) * new_ndim += 1 # <<<<<<<<<<<<<< @@ -16270,7 +16275,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ } __pyx_L6:; - /* "View.MemoryView":734 + /* "View.MemoryView":741 * cdef bint have_start, have_stop, have_step * * for dim, index in enumerate(indices): # <<<<<<<<<<<<<< @@ -16280,7 +16285,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":764 + /* "View.MemoryView":771 * new_ndim += 1 * * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -16291,7 +16296,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":765 + /* "View.MemoryView":772 * * if isinstance(memview, _memoryviewslice): * return memoryview_fromslice(dst, new_ndim, # <<<<<<<<<<<<<< @@ -16300,39 +16305,39 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ __Pyx_XDECREF(((PyObject *)__pyx_r)); - /* "View.MemoryView":766 + /* "View.MemoryView":773 * if isinstance(memview, _memoryviewslice): * return memoryview_fromslice(dst, new_ndim, * memviewsliceobj.to_object_func, # <<<<<<<<<<<<<< * memviewsliceobj.to_dtype_func, * memview.dtype_is_object) */ - if (unlikely(!__pyx_v_memviewsliceobj)) { __Pyx_RaiseUnboundLocalError("memviewsliceobj"); __PYX_ERR(2, 766, __pyx_L1_error) } + if (unlikely(!__pyx_v_memviewsliceobj)) { __Pyx_RaiseUnboundLocalError("memviewsliceobj"); __PYX_ERR(2, 773, __pyx_L1_error) } - /* "View.MemoryView":767 + /* "View.MemoryView":774 * return memoryview_fromslice(dst, new_ndim, * memviewsliceobj.to_object_func, * memviewsliceobj.to_dtype_func, # <<<<<<<<<<<<<< * memview.dtype_is_object) * else: */ - if (unlikely(!__pyx_v_memviewsliceobj)) { __Pyx_RaiseUnboundLocalError("memviewsliceobj"); __PYX_ERR(2, 767, __pyx_L1_error) } + if (unlikely(!__pyx_v_memviewsliceobj)) { __Pyx_RaiseUnboundLocalError("memviewsliceobj"); __PYX_ERR(2, 774, __pyx_L1_error) } - /* "View.MemoryView":765 + /* "View.MemoryView":772 * * if isinstance(memview, _memoryviewslice): * return memoryview_fromslice(dst, new_ndim, # <<<<<<<<<<<<<< * memviewsliceobj.to_object_func, * memviewsliceobj.to_dtype_func, */ - __pyx_t_3 = __pyx_memoryview_fromslice(__pyx_v_dst, __pyx_v_new_ndim, __pyx_v_memviewsliceobj->to_object_func, __pyx_v_memviewsliceobj->to_dtype_func, __pyx_v_memview->dtype_is_object); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 765, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_fromslice(__pyx_v_dst, __pyx_v_new_ndim, __pyx_v_memviewsliceobj->to_object_func, __pyx_v_memviewsliceobj->to_dtype_func, __pyx_v_memview->dtype_is_object); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 772, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_memoryview_type))))) __PYX_ERR(2, 765, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_memoryview_type))))) __PYX_ERR(2, 772, __pyx_L1_error) __pyx_r = ((struct __pyx_memoryview_obj *)__pyx_t_3); __pyx_t_3 = 0; goto __pyx_L0; - /* "View.MemoryView":764 + /* "View.MemoryView":771 * new_ndim += 1 * * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -16341,7 +16346,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ */ } - /* "View.MemoryView":770 + /* "View.MemoryView":777 * memview.dtype_is_object) * else: * return memoryview_fromslice(dst, new_ndim, NULL, NULL, # <<<<<<<<<<<<<< @@ -16351,30 +16356,30 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ /*else*/ { __Pyx_XDECREF(((PyObject *)__pyx_r)); - /* "View.MemoryView":771 + /* "View.MemoryView":778 * else: * return memoryview_fromslice(dst, new_ndim, NULL, NULL, * memview.dtype_is_object) # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __pyx_memoryview_fromslice(__pyx_v_dst, __pyx_v_new_ndim, NULL, NULL, __pyx_v_memview->dtype_is_object); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 770, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_fromslice(__pyx_v_dst, __pyx_v_new_ndim, NULL, NULL, __pyx_v_memview->dtype_is_object); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 777, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - /* "View.MemoryView":770 + /* "View.MemoryView":777 * memview.dtype_is_object) * else: * return memoryview_fromslice(dst, new_ndim, NULL, NULL, # <<<<<<<<<<<<<< * memview.dtype_is_object) * */ - if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_memoryview_type))))) __PYX_ERR(2, 770, __pyx_L1_error) + if (!(likely(((__pyx_t_3) == Py_None) || likely(__Pyx_TypeTest(__pyx_t_3, __pyx_memoryview_type))))) __PYX_ERR(2, 777, __pyx_L1_error) __pyx_r = ((struct __pyx_memoryview_obj *)__pyx_t_3); __pyx_t_3 = 0; goto __pyx_L0; } - /* "View.MemoryView":698 + /* "View.MemoryView":705 * * @cname('__pyx_memview_slice') * cdef memoryview memview_slice(memoryview memview, object indices): # <<<<<<<<<<<<<< @@ -16396,7 +16401,7 @@ static struct __pyx_memoryview_obj *__pyx_memview_slice(struct __pyx_memoryview_ return __pyx_r; } -/* "View.MemoryView":795 +/* "View.MemoryView":802 * * @cname('__pyx_memoryview_slice_memviewslice') * cdef int slice_memviewslice( # <<<<<<<<<<<<<< @@ -16412,7 +16417,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, int __pyx_t_2; int __pyx_t_3; - /* "View.MemoryView":815 + /* "View.MemoryView":822 * cdef bint negative_step * * if not is_slice: # <<<<<<<<<<<<<< @@ -16422,7 +16427,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_1 = ((!(__pyx_v_is_slice != 0)) != 0); if (__pyx_t_1) { - /* "View.MemoryView":817 + /* "View.MemoryView":824 * if not is_slice: * * if start < 0: # <<<<<<<<<<<<<< @@ -16432,7 +16437,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_1 = ((__pyx_v_start < 0) != 0); if (__pyx_t_1) { - /* "View.MemoryView":818 + /* "View.MemoryView":825 * * if start < 0: * start += shape # <<<<<<<<<<<<<< @@ -16441,7 +16446,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_start = (__pyx_v_start + __pyx_v_shape); - /* "View.MemoryView":817 + /* "View.MemoryView":824 * if not is_slice: * * if start < 0: # <<<<<<<<<<<<<< @@ -16450,7 +16455,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":819 + /* "View.MemoryView":826 * if start < 0: * start += shape * if not 0 <= start < shape: # <<<<<<<<<<<<<< @@ -16464,16 +16469,16 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((!(__pyx_t_1 != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":820 + /* "View.MemoryView":827 * start += shape * if not 0 <= start < shape: * _err_dim(IndexError, "Index out of bounds (axis %d)", dim) # <<<<<<<<<<<<<< * else: * */ - __pyx_t_3 = __pyx_memoryview_err_dim(__pyx_builtin_IndexError, ((char *)"Index out of bounds (axis %d)"), __pyx_v_dim); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 820, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_err_dim(__pyx_builtin_IndexError, ((char *)"Index out of bounds (axis %d)"), __pyx_v_dim); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 827, __pyx_L1_error) - /* "View.MemoryView":819 + /* "View.MemoryView":826 * if start < 0: * start += shape * if not 0 <= start < shape: # <<<<<<<<<<<<<< @@ -16482,7 +16487,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":815 + /* "View.MemoryView":822 * cdef bint negative_step * * if not is_slice: # <<<<<<<<<<<<<< @@ -16492,7 +16497,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L3; } - /* "View.MemoryView":823 + /* "View.MemoryView":830 * else: * * negative_step = have_step != 0 and step < 0 # <<<<<<<<<<<<<< @@ -16511,7 +16516,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_L6_bool_binop_done:; __pyx_v_negative_step = __pyx_t_2; - /* "View.MemoryView":825 + /* "View.MemoryView":832 * negative_step = have_step != 0 and step < 0 * * if have_step and step == 0: # <<<<<<<<<<<<<< @@ -16529,16 +16534,16 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_L9_bool_binop_done:; if (__pyx_t_2) { - /* "View.MemoryView":826 + /* "View.MemoryView":833 * * if have_step and step == 0: * _err_dim(ValueError, "Step may not be zero (axis %d)", dim) # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __pyx_memoryview_err_dim(__pyx_builtin_ValueError, ((char *)"Step may not be zero (axis %d)"), __pyx_v_dim); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 826, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_err_dim(__pyx_builtin_ValueError, ((char *)"Step may not be zero (axis %d)"), __pyx_v_dim); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 833, __pyx_L1_error) - /* "View.MemoryView":825 + /* "View.MemoryView":832 * negative_step = have_step != 0 and step < 0 * * if have_step and step == 0: # <<<<<<<<<<<<<< @@ -16547,7 +16552,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":829 + /* "View.MemoryView":836 * * * if have_start: # <<<<<<<<<<<<<< @@ -16557,7 +16562,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (__pyx_v_have_start != 0); if (__pyx_t_2) { - /* "View.MemoryView":830 + /* "View.MemoryView":837 * * if have_start: * if start < 0: # <<<<<<<<<<<<<< @@ -16567,7 +16572,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_start < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":831 + /* "View.MemoryView":838 * if have_start: * if start < 0: * start += shape # <<<<<<<<<<<<<< @@ -16576,7 +16581,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_start = (__pyx_v_start + __pyx_v_shape); - /* "View.MemoryView":832 + /* "View.MemoryView":839 * if start < 0: * start += shape * if start < 0: # <<<<<<<<<<<<<< @@ -16586,7 +16591,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_start < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":833 + /* "View.MemoryView":840 * start += shape * if start < 0: * start = 0 # <<<<<<<<<<<<<< @@ -16595,7 +16600,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_start = 0; - /* "View.MemoryView":832 + /* "View.MemoryView":839 * if start < 0: * start += shape * if start < 0: # <<<<<<<<<<<<<< @@ -16604,7 +16609,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":830 + /* "View.MemoryView":837 * * if have_start: * if start < 0: # <<<<<<<<<<<<<< @@ -16614,7 +16619,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L12; } - /* "View.MemoryView":834 + /* "View.MemoryView":841 * if start < 0: * start = 0 * elif start >= shape: # <<<<<<<<<<<<<< @@ -16624,7 +16629,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_start >= __pyx_v_shape) != 0); if (__pyx_t_2) { - /* "View.MemoryView":835 + /* "View.MemoryView":842 * start = 0 * elif start >= shape: * if negative_step: # <<<<<<<<<<<<<< @@ -16634,7 +16639,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (__pyx_v_negative_step != 0); if (__pyx_t_2) { - /* "View.MemoryView":836 + /* "View.MemoryView":843 * elif start >= shape: * if negative_step: * start = shape - 1 # <<<<<<<<<<<<<< @@ -16643,7 +16648,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_start = (__pyx_v_shape - 1); - /* "View.MemoryView":835 + /* "View.MemoryView":842 * start = 0 * elif start >= shape: * if negative_step: # <<<<<<<<<<<<<< @@ -16653,7 +16658,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L14; } - /* "View.MemoryView":838 + /* "View.MemoryView":845 * start = shape - 1 * else: * start = shape # <<<<<<<<<<<<<< @@ -16665,7 +16670,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L14:; - /* "View.MemoryView":834 + /* "View.MemoryView":841 * if start < 0: * start = 0 * elif start >= shape: # <<<<<<<<<<<<<< @@ -16675,7 +16680,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L12:; - /* "View.MemoryView":829 + /* "View.MemoryView":836 * * * if have_start: # <<<<<<<<<<<<<< @@ -16685,7 +16690,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L11; } - /* "View.MemoryView":840 + /* "View.MemoryView":847 * start = shape * else: * if negative_step: # <<<<<<<<<<<<<< @@ -16696,7 +16701,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (__pyx_v_negative_step != 0); if (__pyx_t_2) { - /* "View.MemoryView":841 + /* "View.MemoryView":848 * else: * if negative_step: * start = shape - 1 # <<<<<<<<<<<<<< @@ -16705,7 +16710,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_start = (__pyx_v_shape - 1); - /* "View.MemoryView":840 + /* "View.MemoryView":847 * start = shape * else: * if negative_step: # <<<<<<<<<<<<<< @@ -16715,7 +16720,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L15; } - /* "View.MemoryView":843 + /* "View.MemoryView":850 * start = shape - 1 * else: * start = 0 # <<<<<<<<<<<<<< @@ -16729,7 +16734,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L11:; - /* "View.MemoryView":845 + /* "View.MemoryView":852 * start = 0 * * if have_stop: # <<<<<<<<<<<<<< @@ -16739,7 +16744,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (__pyx_v_have_stop != 0); if (__pyx_t_2) { - /* "View.MemoryView":846 + /* "View.MemoryView":853 * * if have_stop: * if stop < 0: # <<<<<<<<<<<<<< @@ -16749,7 +16754,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_stop < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":847 + /* "View.MemoryView":854 * if have_stop: * if stop < 0: * stop += shape # <<<<<<<<<<<<<< @@ -16758,7 +16763,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_stop = (__pyx_v_stop + __pyx_v_shape); - /* "View.MemoryView":848 + /* "View.MemoryView":855 * if stop < 0: * stop += shape * if stop < 0: # <<<<<<<<<<<<<< @@ -16768,7 +16773,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_stop < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":849 + /* "View.MemoryView":856 * stop += shape * if stop < 0: * stop = 0 # <<<<<<<<<<<<<< @@ -16777,7 +16782,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_stop = 0; - /* "View.MemoryView":848 + /* "View.MemoryView":855 * if stop < 0: * stop += shape * if stop < 0: # <<<<<<<<<<<<<< @@ -16786,7 +16791,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":846 + /* "View.MemoryView":853 * * if have_stop: * if stop < 0: # <<<<<<<<<<<<<< @@ -16796,7 +16801,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L17; } - /* "View.MemoryView":850 + /* "View.MemoryView":857 * if stop < 0: * stop = 0 * elif stop > shape: # <<<<<<<<<<<<<< @@ -16806,7 +16811,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_stop > __pyx_v_shape) != 0); if (__pyx_t_2) { - /* "View.MemoryView":851 + /* "View.MemoryView":858 * stop = 0 * elif stop > shape: * stop = shape # <<<<<<<<<<<<<< @@ -16815,7 +16820,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_stop = __pyx_v_shape; - /* "View.MemoryView":850 + /* "View.MemoryView":857 * if stop < 0: * stop = 0 * elif stop > shape: # <<<<<<<<<<<<<< @@ -16825,7 +16830,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L17:; - /* "View.MemoryView":845 + /* "View.MemoryView":852 * start = 0 * * if have_stop: # <<<<<<<<<<<<<< @@ -16835,7 +16840,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L16; } - /* "View.MemoryView":853 + /* "View.MemoryView":860 * stop = shape * else: * if negative_step: # <<<<<<<<<<<<<< @@ -16846,7 +16851,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (__pyx_v_negative_step != 0); if (__pyx_t_2) { - /* "View.MemoryView":854 + /* "View.MemoryView":861 * else: * if negative_step: * stop = -1 # <<<<<<<<<<<<<< @@ -16855,7 +16860,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_stop = -1L; - /* "View.MemoryView":853 + /* "View.MemoryView":860 * stop = shape * else: * if negative_step: # <<<<<<<<<<<<<< @@ -16865,7 +16870,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L19; } - /* "View.MemoryView":856 + /* "View.MemoryView":863 * stop = -1 * else: * stop = shape # <<<<<<<<<<<<<< @@ -16879,7 +16884,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L16:; - /* "View.MemoryView":858 + /* "View.MemoryView":865 * stop = shape * * if not have_step: # <<<<<<<<<<<<<< @@ -16889,7 +16894,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((!(__pyx_v_have_step != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":859 + /* "View.MemoryView":866 * * if not have_step: * step = 1 # <<<<<<<<<<<<<< @@ -16898,7 +16903,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_step = 1; - /* "View.MemoryView":858 + /* "View.MemoryView":865 * stop = shape * * if not have_step: # <<<<<<<<<<<<<< @@ -16907,7 +16912,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":863 + /* "View.MemoryView":870 * * with cython.cdivision(True): * new_shape = (stop - start) // step # <<<<<<<<<<<<<< @@ -16916,7 +16921,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_new_shape = ((__pyx_v_stop - __pyx_v_start) / __pyx_v_step); - /* "View.MemoryView":865 + /* "View.MemoryView":872 * new_shape = (stop - start) // step * * if (stop - start) - step * new_shape: # <<<<<<<<<<<<<< @@ -16926,7 +16931,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (((__pyx_v_stop - __pyx_v_start) - (__pyx_v_step * __pyx_v_new_shape)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":866 + /* "View.MemoryView":873 * * if (stop - start) - step * new_shape: * new_shape += 1 # <<<<<<<<<<<<<< @@ -16935,7 +16940,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_new_shape = (__pyx_v_new_shape + 1); - /* "View.MemoryView":865 + /* "View.MemoryView":872 * new_shape = (stop - start) // step * * if (stop - start) - step * new_shape: # <<<<<<<<<<<<<< @@ -16944,7 +16949,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":868 + /* "View.MemoryView":875 * new_shape += 1 * * if new_shape < 0: # <<<<<<<<<<<<<< @@ -16954,7 +16959,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_new_shape < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":869 + /* "View.MemoryView":876 * * if new_shape < 0: * new_shape = 0 # <<<<<<<<<<<<<< @@ -16963,7 +16968,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_new_shape = 0; - /* "View.MemoryView":868 + /* "View.MemoryView":875 * new_shape += 1 * * if new_shape < 0: # <<<<<<<<<<<<<< @@ -16972,7 +16977,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":872 + /* "View.MemoryView":879 * * * dst.strides[new_ndim] = stride * step # <<<<<<<<<<<<<< @@ -16981,7 +16986,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ (__pyx_v_dst->strides[__pyx_v_new_ndim]) = (__pyx_v_stride * __pyx_v_step); - /* "View.MemoryView":873 + /* "View.MemoryView":880 * * dst.strides[new_ndim] = stride * step * dst.shape[new_ndim] = new_shape # <<<<<<<<<<<<<< @@ -16990,7 +16995,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ (__pyx_v_dst->shape[__pyx_v_new_ndim]) = __pyx_v_new_shape; - /* "View.MemoryView":874 + /* "View.MemoryView":881 * dst.strides[new_ndim] = stride * step * dst.shape[new_ndim] = new_shape * dst.suboffsets[new_ndim] = suboffset # <<<<<<<<<<<<<< @@ -17001,7 +17006,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L3:; - /* "View.MemoryView":877 + /* "View.MemoryView":884 * * * if suboffset_dim[0] < 0: # <<<<<<<<<<<<<< @@ -17011,7 +17016,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = (((__pyx_v_suboffset_dim[0]) < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":878 + /* "View.MemoryView":885 * * if suboffset_dim[0] < 0: * dst.data += start * stride # <<<<<<<<<<<<<< @@ -17020,7 +17025,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_dst->data = (__pyx_v_dst->data + (__pyx_v_start * __pyx_v_stride)); - /* "View.MemoryView":877 + /* "View.MemoryView":884 * * * if suboffset_dim[0] < 0: # <<<<<<<<<<<<<< @@ -17030,7 +17035,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L23; } - /* "View.MemoryView":880 + /* "View.MemoryView":887 * dst.data += start * stride * else: * dst.suboffsets[suboffset_dim[0]] += start * stride # <<<<<<<<<<<<<< @@ -17043,7 +17048,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L23:; - /* "View.MemoryView":882 + /* "View.MemoryView":889 * dst.suboffsets[suboffset_dim[0]] += start * stride * * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -17053,7 +17058,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_suboffset >= 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":883 + /* "View.MemoryView":890 * * if suboffset >= 0: * if not is_slice: # <<<<<<<<<<<<<< @@ -17063,7 +17068,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((!(__pyx_v_is_slice != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":884 + /* "View.MemoryView":891 * if suboffset >= 0: * if not is_slice: * if new_ndim == 0: # <<<<<<<<<<<<<< @@ -17073,7 +17078,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_t_2 = ((__pyx_v_new_ndim == 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":885 + /* "View.MemoryView":892 * if not is_slice: * if new_ndim == 0: * dst.data = ( dst.data)[0] + suboffset # <<<<<<<<<<<<<< @@ -17082,7 +17087,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ __pyx_v_dst->data = ((((char **)__pyx_v_dst->data)[0]) + __pyx_v_suboffset); - /* "View.MemoryView":884 + /* "View.MemoryView":891 * if suboffset >= 0: * if not is_slice: * if new_ndim == 0: # <<<<<<<<<<<<<< @@ -17092,7 +17097,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L26; } - /* "View.MemoryView":887 + /* "View.MemoryView":894 * dst.data = ( dst.data)[0] + suboffset * else: * _err_dim(IndexError, "All dimensions preceding dimension %d " # <<<<<<<<<<<<<< @@ -17101,18 +17106,18 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ /*else*/ { - /* "View.MemoryView":888 + /* "View.MemoryView":895 * else: * _err_dim(IndexError, "All dimensions preceding dimension %d " * "must be indexed and not sliced", dim) # <<<<<<<<<<<<<< * else: * suboffset_dim[0] = new_ndim */ - __pyx_t_3 = __pyx_memoryview_err_dim(__pyx_builtin_IndexError, ((char *)"All dimensions preceding dimension %d must be indexed and not sliced"), __pyx_v_dim); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 887, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_err_dim(__pyx_builtin_IndexError, ((char *)"All dimensions preceding dimension %d must be indexed and not sliced"), __pyx_v_dim); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 894, __pyx_L1_error) } __pyx_L26:; - /* "View.MemoryView":883 + /* "View.MemoryView":890 * * if suboffset >= 0: * if not is_slice: # <<<<<<<<<<<<<< @@ -17122,7 +17127,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, goto __pyx_L25; } - /* "View.MemoryView":890 + /* "View.MemoryView":897 * "must be indexed and not sliced", dim) * else: * suboffset_dim[0] = new_ndim # <<<<<<<<<<<<<< @@ -17134,7 +17139,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, } __pyx_L25:; - /* "View.MemoryView":882 + /* "View.MemoryView":889 * dst.suboffsets[suboffset_dim[0]] += start * stride * * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -17143,7 +17148,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, */ } - /* "View.MemoryView":892 + /* "View.MemoryView":899 * suboffset_dim[0] = new_ndim * * return 0 # <<<<<<<<<<<<<< @@ -17153,7 +17158,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, __pyx_r = 0; goto __pyx_L0; - /* "View.MemoryView":795 + /* "View.MemoryView":802 * * @cname('__pyx_memoryview_slice_memviewslice') * cdef int slice_memviewslice( # <<<<<<<<<<<<<< @@ -17177,7 +17182,7 @@ static int __pyx_memoryview_slice_memviewslice(__Pyx_memviewslice *__pyx_v_dst, return __pyx_r; } -/* "View.MemoryView":898 +/* "View.MemoryView":905 * * @cname('__pyx_pybuffer_index') * cdef char *pybuffer_index(Py_buffer *view, char *bufp, Py_ssize_t index, # <<<<<<<<<<<<<< @@ -17199,7 +17204,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P PyObject *__pyx_t_4 = NULL; __Pyx_RefNannySetupContext("pybuffer_index", 0); - /* "View.MemoryView":900 + /* "View.MemoryView":907 * cdef char *pybuffer_index(Py_buffer *view, char *bufp, Py_ssize_t index, * Py_ssize_t dim) except NULL: * cdef Py_ssize_t shape, stride, suboffset = -1 # <<<<<<<<<<<<<< @@ -17208,7 +17213,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_suboffset = -1L; - /* "View.MemoryView":901 + /* "View.MemoryView":908 * Py_ssize_t dim) except NULL: * cdef Py_ssize_t shape, stride, suboffset = -1 * cdef Py_ssize_t itemsize = view.itemsize # <<<<<<<<<<<<<< @@ -17218,7 +17223,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P __pyx_t_1 = __pyx_v_view->itemsize; __pyx_v_itemsize = __pyx_t_1; - /* "View.MemoryView":904 + /* "View.MemoryView":911 * cdef char *resultp * * if view.ndim == 0: # <<<<<<<<<<<<<< @@ -17228,7 +17233,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P __pyx_t_2 = ((__pyx_v_view->ndim == 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":905 + /* "View.MemoryView":912 * * if view.ndim == 0: * shape = view.len / itemsize # <<<<<<<<<<<<<< @@ -17237,15 +17242,15 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ if (unlikely(__pyx_v_itemsize == 0)) { PyErr_SetString(PyExc_ZeroDivisionError, "integer division or modulo by zero"); - __PYX_ERR(2, 905, __pyx_L1_error) + __PYX_ERR(2, 912, __pyx_L1_error) } else if (sizeof(Py_ssize_t) == sizeof(long) && (!(((Py_ssize_t)-1) > 0)) && unlikely(__pyx_v_itemsize == (Py_ssize_t)-1) && unlikely(UNARY_NEG_WOULD_OVERFLOW(__pyx_v_view->len))) { PyErr_SetString(PyExc_OverflowError, "value too large to perform division"); - __PYX_ERR(2, 905, __pyx_L1_error) + __PYX_ERR(2, 912, __pyx_L1_error) } __pyx_v_shape = __Pyx_div_Py_ssize_t(__pyx_v_view->len, __pyx_v_itemsize); - /* "View.MemoryView":906 + /* "View.MemoryView":913 * if view.ndim == 0: * shape = view.len / itemsize * stride = itemsize # <<<<<<<<<<<<<< @@ -17254,7 +17259,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_stride = __pyx_v_itemsize; - /* "View.MemoryView":904 + /* "View.MemoryView":911 * cdef char *resultp * * if view.ndim == 0: # <<<<<<<<<<<<<< @@ -17264,7 +17269,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P goto __pyx_L3; } - /* "View.MemoryView":908 + /* "View.MemoryView":915 * stride = itemsize * else: * shape = view.shape[dim] # <<<<<<<<<<<<<< @@ -17274,7 +17279,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P /*else*/ { __pyx_v_shape = (__pyx_v_view->shape[__pyx_v_dim]); - /* "View.MemoryView":909 + /* "View.MemoryView":916 * else: * shape = view.shape[dim] * stride = view.strides[dim] # <<<<<<<<<<<<<< @@ -17283,7 +17288,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_stride = (__pyx_v_view->strides[__pyx_v_dim]); - /* "View.MemoryView":910 + /* "View.MemoryView":917 * shape = view.shape[dim] * stride = view.strides[dim] * if view.suboffsets != NULL: # <<<<<<<<<<<<<< @@ -17293,7 +17298,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P __pyx_t_2 = ((__pyx_v_view->suboffsets != NULL) != 0); if (__pyx_t_2) { - /* "View.MemoryView":911 + /* "View.MemoryView":918 * stride = view.strides[dim] * if view.suboffsets != NULL: * suboffset = view.suboffsets[dim] # <<<<<<<<<<<<<< @@ -17302,7 +17307,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_suboffset = (__pyx_v_view->suboffsets[__pyx_v_dim]); - /* "View.MemoryView":910 + /* "View.MemoryView":917 * shape = view.shape[dim] * stride = view.strides[dim] * if view.suboffsets != NULL: # <<<<<<<<<<<<<< @@ -17313,7 +17318,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P } __pyx_L3:; - /* "View.MemoryView":913 + /* "View.MemoryView":920 * suboffset = view.suboffsets[dim] * * if index < 0: # <<<<<<<<<<<<<< @@ -17323,7 +17328,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P __pyx_t_2 = ((__pyx_v_index < 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":914 + /* "View.MemoryView":921 * * if index < 0: * index += view.shape[dim] # <<<<<<<<<<<<<< @@ -17332,7 +17337,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_index = (__pyx_v_index + (__pyx_v_view->shape[__pyx_v_dim])); - /* "View.MemoryView":915 + /* "View.MemoryView":922 * if index < 0: * index += view.shape[dim] * if index < 0: # <<<<<<<<<<<<<< @@ -17340,33 +17345,28 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P * */ __pyx_t_2 = ((__pyx_v_index < 0) != 0); - if (__pyx_t_2) { + if (unlikely(__pyx_t_2)) { - /* "View.MemoryView":916 + /* "View.MemoryView":923 * index += view.shape[dim] * if index < 0: * raise IndexError("Out of bounds on buffer access (axis %d)" % dim) # <<<<<<<<<<<<<< * * if index >= shape: */ - __pyx_t_3 = PyInt_FromSsize_t(__pyx_v_dim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 916, __pyx_L1_error) + __pyx_t_3 = PyInt_FromSsize_t(__pyx_v_dim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 923, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = __Pyx_PyString_Format(__pyx_kp_s_Out_of_bounds_on_buffer_access_a, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 916, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyString_Format(__pyx_kp_s_Out_of_bounds_on_buffer_access_a, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 923, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 916, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_IndexError, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 923, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_GIVEREF(__pyx_t_4); - PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_4); - __pyx_t_4 = 0; - __pyx_t_4 = __Pyx_PyObject_Call(__pyx_builtin_IndexError, __pyx_t_3, NULL); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 916, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __Pyx_Raise(__pyx_t_4, 0, 0, 0); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __PYX_ERR(2, 916, __pyx_L1_error) + __Pyx_Raise(__pyx_t_3, 0, 0, 0); + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __PYX_ERR(2, 923, __pyx_L1_error) - /* "View.MemoryView":915 + /* "View.MemoryView":922 * if index < 0: * index += view.shape[dim] * if index < 0: # <<<<<<<<<<<<<< @@ -17375,7 +17375,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ } - /* "View.MemoryView":913 + /* "View.MemoryView":920 * suboffset = view.suboffsets[dim] * * if index < 0: # <<<<<<<<<<<<<< @@ -17384,7 +17384,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ } - /* "View.MemoryView":918 + /* "View.MemoryView":925 * raise IndexError("Out of bounds on buffer access (axis %d)" % dim) * * if index >= shape: # <<<<<<<<<<<<<< @@ -17392,33 +17392,28 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P * */ __pyx_t_2 = ((__pyx_v_index >= __pyx_v_shape) != 0); - if (__pyx_t_2) { + if (unlikely(__pyx_t_2)) { - /* "View.MemoryView":919 + /* "View.MemoryView":926 * * if index >= shape: * raise IndexError("Out of bounds on buffer access (axis %d)" % dim) # <<<<<<<<<<<<<< * * resultp = bufp + index * stride */ - __pyx_t_4 = PyInt_FromSsize_t(__pyx_v_dim); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 919, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_4); - __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_Out_of_bounds_on_buffer_access_a, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 919, __pyx_L1_error) + __pyx_t_3 = PyInt_FromSsize_t(__pyx_v_dim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 926, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 919, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyString_Format(__pyx_kp_s_Out_of_bounds_on_buffer_access_a, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 926, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_IndexError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 919, __pyx_L1_error) + __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; + __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_IndexError, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 926, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(2, 919, __pyx_L1_error) + __PYX_ERR(2, 926, __pyx_L1_error) - /* "View.MemoryView":918 + /* "View.MemoryView":925 * raise IndexError("Out of bounds on buffer access (axis %d)" % dim) * * if index >= shape: # <<<<<<<<<<<<<< @@ -17427,7 +17422,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ } - /* "View.MemoryView":921 + /* "View.MemoryView":928 * raise IndexError("Out of bounds on buffer access (axis %d)" % dim) * * resultp = bufp + index * stride # <<<<<<<<<<<<<< @@ -17436,7 +17431,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_resultp = (__pyx_v_bufp + (__pyx_v_index * __pyx_v_stride)); - /* "View.MemoryView":922 + /* "View.MemoryView":929 * * resultp = bufp + index * stride * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -17446,7 +17441,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P __pyx_t_2 = ((__pyx_v_suboffset >= 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":923 + /* "View.MemoryView":930 * resultp = bufp + index * stride * if suboffset >= 0: * resultp = ( resultp)[0] + suboffset # <<<<<<<<<<<<<< @@ -17455,7 +17450,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ __pyx_v_resultp = ((((char **)__pyx_v_resultp)[0]) + __pyx_v_suboffset); - /* "View.MemoryView":922 + /* "View.MemoryView":929 * * resultp = bufp + index * stride * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -17464,7 +17459,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P */ } - /* "View.MemoryView":925 + /* "View.MemoryView":932 * resultp = ( resultp)[0] + suboffset * * return resultp # <<<<<<<<<<<<<< @@ -17474,7 +17469,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P __pyx_r = __pyx_v_resultp; goto __pyx_L0; - /* "View.MemoryView":898 + /* "View.MemoryView":905 * * @cname('__pyx_pybuffer_index') * cdef char *pybuffer_index(Py_buffer *view, char *bufp, Py_ssize_t index, # <<<<<<<<<<<<<< @@ -17493,7 +17488,7 @@ static char *__pyx_pybuffer_index(Py_buffer *__pyx_v_view, char *__pyx_v_bufp, P return __pyx_r; } -/* "View.MemoryView":931 +/* "View.MemoryView":938 * * @cname('__pyx_memslice_transpose') * cdef int transpose_memslice(__Pyx_memviewslice *memslice) nogil except 0: # <<<<<<<<<<<<<< @@ -17511,13 +17506,14 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { int __pyx_t_1; Py_ssize_t *__pyx_t_2; long __pyx_t_3; - Py_ssize_t __pyx_t_4; + long __pyx_t_4; Py_ssize_t __pyx_t_5; - int __pyx_t_6; + Py_ssize_t __pyx_t_6; int __pyx_t_7; int __pyx_t_8; + int __pyx_t_9; - /* "View.MemoryView":932 + /* "View.MemoryView":939 * @cname('__pyx_memslice_transpose') * cdef int transpose_memslice(__Pyx_memviewslice *memslice) nogil except 0: * cdef int ndim = memslice.memview.view.ndim # <<<<<<<<<<<<<< @@ -17527,7 +17523,7 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { __pyx_t_1 = __pyx_v_memslice->memview->view.ndim; __pyx_v_ndim = __pyx_t_1; - /* "View.MemoryView":934 + /* "View.MemoryView":941 * cdef int ndim = memslice.memview.view.ndim * * cdef Py_ssize_t *shape = memslice.shape # <<<<<<<<<<<<<< @@ -17537,7 +17533,7 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { __pyx_t_2 = __pyx_v_memslice->shape; __pyx_v_shape = __pyx_t_2; - /* "View.MemoryView":935 + /* "View.MemoryView":942 * * cdef Py_ssize_t *shape = memslice.shape * cdef Py_ssize_t *strides = memslice.strides # <<<<<<<<<<<<<< @@ -17547,7 +17543,7 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { __pyx_t_2 = __pyx_v_memslice->strides; __pyx_v_strides = __pyx_t_2; - /* "View.MemoryView":939 + /* "View.MemoryView":946 * * cdef int i, j * for i in range(ndim / 2): # <<<<<<<<<<<<<< @@ -17555,10 +17551,11 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { * strides[i], strides[j] = strides[j], strides[i] */ __pyx_t_3 = __Pyx_div_long(__pyx_v_ndim, 2); - for (__pyx_t_1 = 0; __pyx_t_1 < __pyx_t_3; __pyx_t_1+=1) { + __pyx_t_4 = __pyx_t_3; + for (__pyx_t_1 = 0; __pyx_t_1 < __pyx_t_4; __pyx_t_1+=1) { __pyx_v_i = __pyx_t_1; - /* "View.MemoryView":940 + /* "View.MemoryView":947 * cdef int i, j * for i in range(ndim / 2): * j = ndim - 1 - i # <<<<<<<<<<<<<< @@ -17567,58 +17564,58 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { */ __pyx_v_j = ((__pyx_v_ndim - 1) - __pyx_v_i); - /* "View.MemoryView":941 + /* "View.MemoryView":948 * for i in range(ndim / 2): * j = ndim - 1 - i * strides[i], strides[j] = strides[j], strides[i] # <<<<<<<<<<<<<< * shape[i], shape[j] = shape[j], shape[i] * */ - __pyx_t_4 = (__pyx_v_strides[__pyx_v_j]); - __pyx_t_5 = (__pyx_v_strides[__pyx_v_i]); - (__pyx_v_strides[__pyx_v_i]) = __pyx_t_4; - (__pyx_v_strides[__pyx_v_j]) = __pyx_t_5; + __pyx_t_5 = (__pyx_v_strides[__pyx_v_j]); + __pyx_t_6 = (__pyx_v_strides[__pyx_v_i]); + (__pyx_v_strides[__pyx_v_i]) = __pyx_t_5; + (__pyx_v_strides[__pyx_v_j]) = __pyx_t_6; - /* "View.MemoryView":942 + /* "View.MemoryView":949 * j = ndim - 1 - i * strides[i], strides[j] = strides[j], strides[i] * shape[i], shape[j] = shape[j], shape[i] # <<<<<<<<<<<<<< * * if memslice.suboffsets[i] >= 0 or memslice.suboffsets[j] >= 0: */ - __pyx_t_5 = (__pyx_v_shape[__pyx_v_j]); - __pyx_t_4 = (__pyx_v_shape[__pyx_v_i]); - (__pyx_v_shape[__pyx_v_i]) = __pyx_t_5; - (__pyx_v_shape[__pyx_v_j]) = __pyx_t_4; + __pyx_t_6 = (__pyx_v_shape[__pyx_v_j]); + __pyx_t_5 = (__pyx_v_shape[__pyx_v_i]); + (__pyx_v_shape[__pyx_v_i]) = __pyx_t_6; + (__pyx_v_shape[__pyx_v_j]) = __pyx_t_5; - /* "View.MemoryView":944 + /* "View.MemoryView":951 * shape[i], shape[j] = shape[j], shape[i] * * if memslice.suboffsets[i] >= 0 or memslice.suboffsets[j] >= 0: # <<<<<<<<<<<<<< * _err(ValueError, "Cannot transpose memoryview with indirect dimensions") * */ - __pyx_t_7 = (((__pyx_v_memslice->suboffsets[__pyx_v_i]) >= 0) != 0); - if (!__pyx_t_7) { + __pyx_t_8 = (((__pyx_v_memslice->suboffsets[__pyx_v_i]) >= 0) != 0); + if (!__pyx_t_8) { } else { - __pyx_t_6 = __pyx_t_7; + __pyx_t_7 = __pyx_t_8; goto __pyx_L6_bool_binop_done; } - __pyx_t_7 = (((__pyx_v_memslice->suboffsets[__pyx_v_j]) >= 0) != 0); - __pyx_t_6 = __pyx_t_7; + __pyx_t_8 = (((__pyx_v_memslice->suboffsets[__pyx_v_j]) >= 0) != 0); + __pyx_t_7 = __pyx_t_8; __pyx_L6_bool_binop_done:; - if (__pyx_t_6) { + if (__pyx_t_7) { - /* "View.MemoryView":945 + /* "View.MemoryView":952 * * if memslice.suboffsets[i] >= 0 or memslice.suboffsets[j] >= 0: * _err(ValueError, "Cannot transpose memoryview with indirect dimensions") # <<<<<<<<<<<<<< * * return 1 */ - __pyx_t_8 = __pyx_memoryview_err(__pyx_builtin_ValueError, ((char *)"Cannot transpose memoryview with indirect dimensions")); if (unlikely(__pyx_t_8 == ((int)-1))) __PYX_ERR(2, 945, __pyx_L1_error) + __pyx_t_9 = __pyx_memoryview_err(__pyx_builtin_ValueError, ((char *)"Cannot transpose memoryview with indirect dimensions")); if (unlikely(__pyx_t_9 == ((int)-1))) __PYX_ERR(2, 952, __pyx_L1_error) - /* "View.MemoryView":944 + /* "View.MemoryView":951 * shape[i], shape[j] = shape[j], shape[i] * * if memslice.suboffsets[i] >= 0 or memslice.suboffsets[j] >= 0: # <<<<<<<<<<<<<< @@ -17628,7 +17625,7 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { } } - /* "View.MemoryView":947 + /* "View.MemoryView":954 * _err(ValueError, "Cannot transpose memoryview with indirect dimensions") * * return 1 # <<<<<<<<<<<<<< @@ -17638,7 +17635,7 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { __pyx_r = 1; goto __pyx_L0; - /* "View.MemoryView":931 + /* "View.MemoryView":938 * * @cname('__pyx_memslice_transpose') * cdef int transpose_memslice(__Pyx_memviewslice *memslice) nogil except 0: # <<<<<<<<<<<<<< @@ -17662,7 +17659,7 @@ static int __pyx_memslice_transpose(__Pyx_memviewslice *__pyx_v_memslice) { return __pyx_r; } -/* "View.MemoryView":964 +/* "View.MemoryView":971 * cdef int (*to_dtype_func)(char *, object) except 0 * * def __dealloc__(self): # <<<<<<<<<<<<<< @@ -17685,7 +17682,7 @@ static void __pyx_memoryviewslice___pyx_pf_15View_dot_MemoryView_16_memoryviewsl __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__dealloc__", 0); - /* "View.MemoryView":965 + /* "View.MemoryView":972 * * def __dealloc__(self): * __PYX_XDEC_MEMVIEW(&self.from_slice, 1) # <<<<<<<<<<<<<< @@ -17694,7 +17691,7 @@ static void __pyx_memoryviewslice___pyx_pf_15View_dot_MemoryView_16_memoryviewsl */ __PYX_XDEC_MEMVIEW((&__pyx_v_self->from_slice), 1); - /* "View.MemoryView":964 + /* "View.MemoryView":971 * cdef int (*to_dtype_func)(char *, object) except 0 * * def __dealloc__(self): # <<<<<<<<<<<<<< @@ -17706,7 +17703,7 @@ static void __pyx_memoryviewslice___pyx_pf_15View_dot_MemoryView_16_memoryviewsl __Pyx_RefNannyFinishContext(); } -/* "View.MemoryView":967 +/* "View.MemoryView":974 * __PYX_XDEC_MEMVIEW(&self.from_slice, 1) * * cdef convert_item_to_object(self, char *itemp): # <<<<<<<<<<<<<< @@ -17721,7 +17718,7 @@ static PyObject *__pyx_memoryviewslice_convert_item_to_object(struct __pyx_memor PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("convert_item_to_object", 0); - /* "View.MemoryView":968 + /* "View.MemoryView":975 * * cdef convert_item_to_object(self, char *itemp): * if self.to_object_func != NULL: # <<<<<<<<<<<<<< @@ -17731,7 +17728,7 @@ static PyObject *__pyx_memoryviewslice_convert_item_to_object(struct __pyx_memor __pyx_t_1 = ((__pyx_v_self->to_object_func != NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":969 + /* "View.MemoryView":976 * cdef convert_item_to_object(self, char *itemp): * if self.to_object_func != NULL: * return self.to_object_func(itemp) # <<<<<<<<<<<<<< @@ -17739,13 +17736,13 @@ static PyObject *__pyx_memoryviewslice_convert_item_to_object(struct __pyx_memor * return memoryview.convert_item_to_object(self, itemp) */ __Pyx_XDECREF(__pyx_r); - __pyx_t_2 = __pyx_v_self->to_object_func(__pyx_v_itemp); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 969, __pyx_L1_error) + __pyx_t_2 = __pyx_v_self->to_object_func(__pyx_v_itemp); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 976, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; - /* "View.MemoryView":968 + /* "View.MemoryView":975 * * cdef convert_item_to_object(self, char *itemp): * if self.to_object_func != NULL: # <<<<<<<<<<<<<< @@ -17754,7 +17751,7 @@ static PyObject *__pyx_memoryviewslice_convert_item_to_object(struct __pyx_memor */ } - /* "View.MemoryView":971 + /* "View.MemoryView":978 * return self.to_object_func(itemp) * else: * return memoryview.convert_item_to_object(self, itemp) # <<<<<<<<<<<<<< @@ -17763,14 +17760,14 @@ static PyObject *__pyx_memoryviewslice_convert_item_to_object(struct __pyx_memor */ /*else*/ { __Pyx_XDECREF(__pyx_r); - __pyx_t_2 = __pyx_memoryview_convert_item_to_object(((struct __pyx_memoryview_obj *)__pyx_v_self), __pyx_v_itemp); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 971, __pyx_L1_error) + __pyx_t_2 = __pyx_memoryview_convert_item_to_object(((struct __pyx_memoryview_obj *)__pyx_v_self), __pyx_v_itemp); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 978, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; } - /* "View.MemoryView":967 + /* "View.MemoryView":974 * __PYX_XDEC_MEMVIEW(&self.from_slice, 1) * * cdef convert_item_to_object(self, char *itemp): # <<<<<<<<<<<<<< @@ -17789,7 +17786,7 @@ static PyObject *__pyx_memoryviewslice_convert_item_to_object(struct __pyx_memor return __pyx_r; } -/* "View.MemoryView":973 +/* "View.MemoryView":980 * return memoryview.convert_item_to_object(self, itemp) * * cdef assign_item_from_object(self, char *itemp, object value): # <<<<<<<<<<<<<< @@ -17805,7 +17802,7 @@ static PyObject *__pyx_memoryviewslice_assign_item_from_object(struct __pyx_memo PyObject *__pyx_t_3 = NULL; __Pyx_RefNannySetupContext("assign_item_from_object", 0); - /* "View.MemoryView":974 + /* "View.MemoryView":981 * * cdef assign_item_from_object(self, char *itemp, object value): * if self.to_dtype_func != NULL: # <<<<<<<<<<<<<< @@ -17815,16 +17812,16 @@ static PyObject *__pyx_memoryviewslice_assign_item_from_object(struct __pyx_memo __pyx_t_1 = ((__pyx_v_self->to_dtype_func != NULL) != 0); if (__pyx_t_1) { - /* "View.MemoryView":975 + /* "View.MemoryView":982 * cdef assign_item_from_object(self, char *itemp, object value): * if self.to_dtype_func != NULL: * self.to_dtype_func(itemp, value) # <<<<<<<<<<<<<< * else: * memoryview.assign_item_from_object(self, itemp, value) */ - __pyx_t_2 = __pyx_v_self->to_dtype_func(__pyx_v_itemp, __pyx_v_value); if (unlikely(__pyx_t_2 == ((int)0))) __PYX_ERR(2, 975, __pyx_L1_error) + __pyx_t_2 = __pyx_v_self->to_dtype_func(__pyx_v_itemp, __pyx_v_value); if (unlikely(__pyx_t_2 == ((int)0))) __PYX_ERR(2, 982, __pyx_L1_error) - /* "View.MemoryView":974 + /* "View.MemoryView":981 * * cdef assign_item_from_object(self, char *itemp, object value): * if self.to_dtype_func != NULL: # <<<<<<<<<<<<<< @@ -17834,7 +17831,7 @@ static PyObject *__pyx_memoryviewslice_assign_item_from_object(struct __pyx_memo goto __pyx_L3; } - /* "View.MemoryView":977 + /* "View.MemoryView":984 * self.to_dtype_func(itemp, value) * else: * memoryview.assign_item_from_object(self, itemp, value) # <<<<<<<<<<<<<< @@ -17842,13 +17839,13 @@ static PyObject *__pyx_memoryviewslice_assign_item_from_object(struct __pyx_memo * @property */ /*else*/ { - __pyx_t_3 = __pyx_memoryview_assign_item_from_object(((struct __pyx_memoryview_obj *)__pyx_v_self), __pyx_v_itemp, __pyx_v_value); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 977, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_assign_item_from_object(((struct __pyx_memoryview_obj *)__pyx_v_self), __pyx_v_itemp, __pyx_v_value); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 984, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } __pyx_L3:; - /* "View.MemoryView":973 + /* "View.MemoryView":980 * return memoryview.convert_item_to_object(self, itemp) * * cdef assign_item_from_object(self, char *itemp, object value): # <<<<<<<<<<<<<< @@ -17869,7 +17866,7 @@ static PyObject *__pyx_memoryviewslice_assign_item_from_object(struct __pyx_memo return __pyx_r; } -/* "View.MemoryView":980 +/* "View.MemoryView":987 * * @property * def base(self): # <<<<<<<<<<<<<< @@ -17895,7 +17892,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_16_memoryviewslice_4base___get__ __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__get__", 0); - /* "View.MemoryView":981 + /* "View.MemoryView":988 * @property * def base(self): * return self.from_object # <<<<<<<<<<<<<< @@ -17907,7 +17904,7 @@ static PyObject *__pyx_pf_15View_dot_MemoryView_16_memoryviewslice_4base___get__ __pyx_r = __pyx_v_self->from_object; goto __pyx_L0; - /* "View.MemoryView":980 + /* "View.MemoryView":987 * * @property * def base(self): # <<<<<<<<<<<<<< @@ -17953,7 +17950,7 @@ static PyObject *__pyx_pf___pyx_memoryviewslice___reduce_cython__(CYTHON_UNUSED * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") */ - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__35, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 2, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__37, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 2, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -18006,7 +18003,7 @@ static PyObject *__pyx_pf___pyx_memoryviewslice_2__setstate_cython__(CYTHON_UNUS * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") # <<<<<<<<<<<<<< */ - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__36, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 4, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_tuple__38, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 4, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; @@ -18029,7 +18026,7 @@ static PyObject *__pyx_pf___pyx_memoryviewslice_2__setstate_cython__(CYTHON_UNUS return __pyx_r; } -/* "View.MemoryView":987 +/* "View.MemoryView":994 * * @cname('__pyx_memoryview_fromslice') * cdef memoryview_fromslice(__Pyx_memviewslice memviewslice, # <<<<<<<<<<<<<< @@ -18054,7 +18051,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl Py_ssize_t __pyx_t_9; __Pyx_RefNannySetupContext("memoryview_fromslice", 0); - /* "View.MemoryView":995 + /* "View.MemoryView":1002 * cdef _memoryviewslice result * * if memviewslice.memview == Py_None: # <<<<<<<<<<<<<< @@ -18064,7 +18061,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_1 = ((((PyObject *)__pyx_v_memviewslice.memview) == Py_None) != 0); if (__pyx_t_1) { - /* "View.MemoryView":996 + /* "View.MemoryView":1003 * * if memviewslice.memview == Py_None: * return None # <<<<<<<<<<<<<< @@ -18072,11 +18069,10 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl * */ __Pyx_XDECREF(__pyx_r); - __Pyx_INCREF(Py_None); - __pyx_r = Py_None; + __pyx_r = Py_None; __Pyx_INCREF(Py_None); goto __pyx_L0; - /* "View.MemoryView":995 + /* "View.MemoryView":1002 * cdef _memoryviewslice result * * if memviewslice.memview == Py_None: # <<<<<<<<<<<<<< @@ -18085,16 +18081,16 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ } - /* "View.MemoryView":1001 + /* "View.MemoryView":1008 * * * result = _memoryviewslice(None, 0, dtype_is_object) # <<<<<<<<<<<<<< * * result.from_slice = memviewslice */ - __pyx_t_2 = __Pyx_PyBool_FromLong(__pyx_v_dtype_is_object); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1001, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyBool_FromLong(__pyx_v_dtype_is_object); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1008, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyTuple_New(3); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1001, __pyx_L1_error) + __pyx_t_3 = PyTuple_New(3); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1008, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(Py_None); __Pyx_GIVEREF(Py_None); @@ -18105,13 +18101,13 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_3, 2, __pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryviewslice_type), __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1001, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_memoryviewslice_type), __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1008, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_result = ((struct __pyx_memoryviewslice_obj *)__pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":1003 + /* "View.MemoryView":1010 * result = _memoryviewslice(None, 0, dtype_is_object) * * result.from_slice = memviewslice # <<<<<<<<<<<<<< @@ -18120,7 +18116,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->from_slice = __pyx_v_memviewslice; - /* "View.MemoryView":1004 + /* "View.MemoryView":1011 * * result.from_slice = memviewslice * __PYX_INC_MEMVIEW(&memviewslice, 1) # <<<<<<<<<<<<<< @@ -18129,14 +18125,14 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __PYX_INC_MEMVIEW((&__pyx_v_memviewslice), 1); - /* "View.MemoryView":1006 + /* "View.MemoryView":1013 * __PYX_INC_MEMVIEW(&memviewslice, 1) * * result.from_object = ( memviewslice.memview).base # <<<<<<<<<<<<<< * result.typeinfo = memviewslice.memview.typeinfo * */ - __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_memviewslice.memview), __pyx_n_s_base); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1006, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_memviewslice.memview), __pyx_n_s_base); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1013, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_2); __Pyx_GOTREF(__pyx_v_result->from_object); @@ -18144,7 +18140,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_v_result->from_object = __pyx_t_2; __pyx_t_2 = 0; - /* "View.MemoryView":1007 + /* "View.MemoryView":1014 * * result.from_object = ( memviewslice.memview).base * result.typeinfo = memviewslice.memview.typeinfo # <<<<<<<<<<<<<< @@ -18154,7 +18150,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_4 = __pyx_v_memviewslice.memview->typeinfo; __pyx_v_result->__pyx_base.typeinfo = __pyx_t_4; - /* "View.MemoryView":1009 + /* "View.MemoryView":1016 * result.typeinfo = memviewslice.memview.typeinfo * * result.view = memviewslice.memview.view # <<<<<<<<<<<<<< @@ -18164,7 +18160,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_5 = __pyx_v_memviewslice.memview->view; __pyx_v_result->__pyx_base.view = __pyx_t_5; - /* "View.MemoryView":1010 + /* "View.MemoryView":1017 * * result.view = memviewslice.memview.view * result.view.buf = memviewslice.data # <<<<<<<<<<<<<< @@ -18173,7 +18169,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->__pyx_base.view.buf = ((void *)__pyx_v_memviewslice.data); - /* "View.MemoryView":1011 + /* "View.MemoryView":1018 * result.view = memviewslice.memview.view * result.view.buf = memviewslice.data * result.view.ndim = ndim # <<<<<<<<<<<<<< @@ -18182,7 +18178,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->__pyx_base.view.ndim = __pyx_v_ndim; - /* "View.MemoryView":1012 + /* "View.MemoryView":1019 * result.view.buf = memviewslice.data * result.view.ndim = ndim * (<__pyx_buffer *> &result.view).obj = Py_None # <<<<<<<<<<<<<< @@ -18191,26 +18187,58 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ ((Py_buffer *)(&__pyx_v_result->__pyx_base.view))->obj = Py_None; - /* "View.MemoryView":1013 + /* "View.MemoryView":1020 * result.view.ndim = ndim * (<__pyx_buffer *> &result.view).obj = Py_None * Py_INCREF(Py_None) # <<<<<<<<<<<<<< * - * result.flags = PyBUF_RECORDS + * if (memviewslice.memview).flags & PyBUF_WRITABLE: */ Py_INCREF(Py_None); - /* "View.MemoryView":1015 + /* "View.MemoryView":1022 + * Py_INCREF(Py_None) + * + * if (memviewslice.memview).flags & PyBUF_WRITABLE: # <<<<<<<<<<<<<< + * result.flags = PyBUF_RECORDS + * else: + */ + __pyx_t_1 = ((((struct __pyx_memoryview_obj *)__pyx_v_memviewslice.memview)->flags & PyBUF_WRITABLE) != 0); + if (__pyx_t_1) { + + /* "View.MemoryView":1023 + * + * if (memviewslice.memview).flags & PyBUF_WRITABLE: + * result.flags = PyBUF_RECORDS # <<<<<<<<<<<<<< + * else: + * result.flags = PyBUF_RECORDS_RO + */ + __pyx_v_result->__pyx_base.flags = PyBUF_RECORDS; + + /* "View.MemoryView":1022 * Py_INCREF(Py_None) * - * result.flags = PyBUF_RECORDS # <<<<<<<<<<<<<< + * if (memviewslice.memview).flags & PyBUF_WRITABLE: # <<<<<<<<<<<<<< + * result.flags = PyBUF_RECORDS + * else: + */ + goto __pyx_L4; + } + + /* "View.MemoryView":1025 + * result.flags = PyBUF_RECORDS + * else: + * result.flags = PyBUF_RECORDS_RO # <<<<<<<<<<<<<< * * result.view.shape = result.from_slice.shape */ - __pyx_v_result->__pyx_base.flags = PyBUF_RECORDS; + /*else*/ { + __pyx_v_result->__pyx_base.flags = PyBUF_RECORDS_RO; + } + __pyx_L4:; - /* "View.MemoryView":1017 - * result.flags = PyBUF_RECORDS + /* "View.MemoryView":1027 + * result.flags = PyBUF_RECORDS_RO * * result.view.shape = result.from_slice.shape # <<<<<<<<<<<<<< * result.view.strides = result.from_slice.strides @@ -18218,7 +18246,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->__pyx_base.view.shape = ((Py_ssize_t *)__pyx_v_result->from_slice.shape); - /* "View.MemoryView":1018 + /* "View.MemoryView":1028 * * result.view.shape = result.from_slice.shape * result.view.strides = result.from_slice.strides # <<<<<<<<<<<<<< @@ -18227,7 +18255,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->__pyx_base.view.strides = ((Py_ssize_t *)__pyx_v_result->from_slice.strides); - /* "View.MemoryView":1021 + /* "View.MemoryView":1031 * * * result.view.suboffsets = NULL # <<<<<<<<<<<<<< @@ -18236,7 +18264,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->__pyx_base.view.suboffsets = NULL; - /* "View.MemoryView":1022 + /* "View.MemoryView":1032 * * result.view.suboffsets = NULL * for suboffset in result.from_slice.suboffsets[:ndim]: # <<<<<<<<<<<<<< @@ -18248,7 +18276,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_6 = __pyx_t_8; __pyx_v_suboffset = (__pyx_t_6[0]); - /* "View.MemoryView":1023 + /* "View.MemoryView":1033 * result.view.suboffsets = NULL * for suboffset in result.from_slice.suboffsets[:ndim]: * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -18258,7 +18286,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_1 = ((__pyx_v_suboffset >= 0) != 0); if (__pyx_t_1) { - /* "View.MemoryView":1024 + /* "View.MemoryView":1034 * for suboffset in result.from_slice.suboffsets[:ndim]: * if suboffset >= 0: * result.view.suboffsets = result.from_slice.suboffsets # <<<<<<<<<<<<<< @@ -18267,16 +18295,16 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->__pyx_base.view.suboffsets = ((Py_ssize_t *)__pyx_v_result->from_slice.suboffsets); - /* "View.MemoryView":1025 + /* "View.MemoryView":1035 * if suboffset >= 0: * result.view.suboffsets = result.from_slice.suboffsets * break # <<<<<<<<<<<<<< * * result.view.len = result.view.itemsize */ - goto __pyx_L5_break; + goto __pyx_L6_break; - /* "View.MemoryView":1023 + /* "View.MemoryView":1033 * result.view.suboffsets = NULL * for suboffset in result.from_slice.suboffsets[:ndim]: * if suboffset >= 0: # <<<<<<<<<<<<<< @@ -18285,9 +18313,9 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ } } - __pyx_L5_break:; + __pyx_L6_break:; - /* "View.MemoryView":1027 + /* "View.MemoryView":1037 * break * * result.view.len = result.view.itemsize # <<<<<<<<<<<<<< @@ -18297,7 +18325,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_9 = __pyx_v_result->__pyx_base.view.itemsize; __pyx_v_result->__pyx_base.view.len = __pyx_t_9; - /* "View.MemoryView":1028 + /* "View.MemoryView":1038 * * result.view.len = result.view.itemsize * for length in result.view.shape[:ndim]: # <<<<<<<<<<<<<< @@ -18307,29 +18335,29 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_t_7 = (__pyx_v_result->__pyx_base.view.shape + __pyx_v_ndim); for (__pyx_t_8 = __pyx_v_result->__pyx_base.view.shape; __pyx_t_8 < __pyx_t_7; __pyx_t_8++) { __pyx_t_6 = __pyx_t_8; - __pyx_t_2 = PyInt_FromSsize_t((__pyx_t_6[0])); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1028, __pyx_L1_error) + __pyx_t_2 = PyInt_FromSsize_t((__pyx_t_6[0])); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1038, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_XDECREF_SET(__pyx_v_length, __pyx_t_2); __pyx_t_2 = 0; - /* "View.MemoryView":1029 + /* "View.MemoryView":1039 * result.view.len = result.view.itemsize * for length in result.view.shape[:ndim]: * result.view.len *= length # <<<<<<<<<<<<<< * * result.to_object_func = to_object_func */ - __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_result->__pyx_base.view.len); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1029, __pyx_L1_error) + __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_result->__pyx_base.view.len); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1039, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyNumber_InPlaceMultiply(__pyx_t_2, __pyx_v_length); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1029, __pyx_L1_error) + __pyx_t_3 = PyNumber_InPlaceMultiply(__pyx_t_2, __pyx_v_length); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1039, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_9 = __Pyx_PyIndex_AsSsize_t(__pyx_t_3); if (unlikely((__pyx_t_9 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 1029, __pyx_L1_error) + __pyx_t_9 = __Pyx_PyIndex_AsSsize_t(__pyx_t_3); if (unlikely((__pyx_t_9 == (Py_ssize_t)-1) && PyErr_Occurred())) __PYX_ERR(2, 1039, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_v_result->__pyx_base.view.len = __pyx_t_9; } - /* "View.MemoryView":1031 + /* "View.MemoryView":1041 * result.view.len *= length * * result.to_object_func = to_object_func # <<<<<<<<<<<<<< @@ -18338,7 +18366,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->to_object_func = __pyx_v_to_object_func; - /* "View.MemoryView":1032 + /* "View.MemoryView":1042 * * result.to_object_func = to_object_func * result.to_dtype_func = to_dtype_func # <<<<<<<<<<<<<< @@ -18347,7 +18375,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl */ __pyx_v_result->to_dtype_func = __pyx_v_to_dtype_func; - /* "View.MemoryView":1034 + /* "View.MemoryView":1044 * result.to_dtype_func = to_dtype_func * * return result # <<<<<<<<<<<<<< @@ -18359,7 +18387,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl __pyx_r = ((PyObject *)__pyx_v_result); goto __pyx_L0; - /* "View.MemoryView":987 + /* "View.MemoryView":994 * * @cname('__pyx_memoryview_fromslice') * cdef memoryview_fromslice(__Pyx_memviewslice memviewslice, # <<<<<<<<<<<<<< @@ -18381,7 +18409,7 @@ static PyObject *__pyx_memoryview_fromslice(__Pyx_memviewslice __pyx_v_memviewsl return __pyx_r; } -/* "View.MemoryView":1037 +/* "View.MemoryView":1047 * * @cname('__pyx_memoryview_get_slice_from_memoryview') * cdef __Pyx_memviewslice *get_slice_from_memview(memoryview memview, # <<<<<<<<<<<<<< @@ -18398,7 +18426,7 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p PyObject *__pyx_t_3 = NULL; __Pyx_RefNannySetupContext("get_slice_from_memview", 0); - /* "View.MemoryView":1040 + /* "View.MemoryView":1050 * __Pyx_memviewslice *mslice): * cdef _memoryviewslice obj * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -18409,20 +18437,20 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":1041 + /* "View.MemoryView":1051 * cdef _memoryviewslice obj * if isinstance(memview, _memoryviewslice): * obj = memview # <<<<<<<<<<<<<< * return &obj.from_slice * else: */ - if (!(likely(((((PyObject *)__pyx_v_memview)) == Py_None) || likely(__Pyx_TypeTest(((PyObject *)__pyx_v_memview), __pyx_memoryviewslice_type))))) __PYX_ERR(2, 1041, __pyx_L1_error) + if (!(likely(((((PyObject *)__pyx_v_memview)) == Py_None) || likely(__Pyx_TypeTest(((PyObject *)__pyx_v_memview), __pyx_memoryviewslice_type))))) __PYX_ERR(2, 1051, __pyx_L1_error) __pyx_t_3 = ((PyObject *)__pyx_v_memview); __Pyx_INCREF(__pyx_t_3); __pyx_v_obj = ((struct __pyx_memoryviewslice_obj *)__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":1042 + /* "View.MemoryView":1052 * if isinstance(memview, _memoryviewslice): * obj = memview * return &obj.from_slice # <<<<<<<<<<<<<< @@ -18432,7 +18460,7 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p __pyx_r = (&__pyx_v_obj->from_slice); goto __pyx_L0; - /* "View.MemoryView":1040 + /* "View.MemoryView":1050 * __Pyx_memviewslice *mslice): * cdef _memoryviewslice obj * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -18441,7 +18469,7 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p */ } - /* "View.MemoryView":1044 + /* "View.MemoryView":1054 * return &obj.from_slice * else: * slice_copy(memview, mslice) # <<<<<<<<<<<<<< @@ -18451,7 +18479,7 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p /*else*/ { __pyx_memoryview_slice_copy(__pyx_v_memview, __pyx_v_mslice); - /* "View.MemoryView":1045 + /* "View.MemoryView":1055 * else: * slice_copy(memview, mslice) * return mslice # <<<<<<<<<<<<<< @@ -18462,7 +18490,7 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p goto __pyx_L0; } - /* "View.MemoryView":1037 + /* "View.MemoryView":1047 * * @cname('__pyx_memoryview_get_slice_from_memoryview') * cdef __Pyx_memviewslice *get_slice_from_memview(memoryview memview, # <<<<<<<<<<<<<< @@ -18481,7 +18509,7 @@ static __Pyx_memviewslice *__pyx_memoryview_get_slice_from_memoryview(struct __p return __pyx_r; } -/* "View.MemoryView":1048 +/* "View.MemoryView":1058 * * @cname('__pyx_memoryview_slice_copy') * cdef void slice_copy(memoryview memview, __Pyx_memviewslice *dst): # <<<<<<<<<<<<<< @@ -18498,10 +18526,11 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem Py_ssize_t *__pyx_t_1; int __pyx_t_2; int __pyx_t_3; - Py_ssize_t __pyx_t_4; + int __pyx_t_4; + Py_ssize_t __pyx_t_5; __Pyx_RefNannySetupContext("slice_copy", 0); - /* "View.MemoryView":1052 + /* "View.MemoryView":1062 * cdef (Py_ssize_t*) shape, strides, suboffsets * * shape = memview.view.shape # <<<<<<<<<<<<<< @@ -18511,7 +18540,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem __pyx_t_1 = __pyx_v_memview->view.shape; __pyx_v_shape = __pyx_t_1; - /* "View.MemoryView":1053 + /* "View.MemoryView":1063 * * shape = memview.view.shape * strides = memview.view.strides # <<<<<<<<<<<<<< @@ -18521,7 +18550,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem __pyx_t_1 = __pyx_v_memview->view.strides; __pyx_v_strides = __pyx_t_1; - /* "View.MemoryView":1054 + /* "View.MemoryView":1064 * shape = memview.view.shape * strides = memview.view.strides * suboffsets = memview.view.suboffsets # <<<<<<<<<<<<<< @@ -18531,7 +18560,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem __pyx_t_1 = __pyx_v_memview->view.suboffsets; __pyx_v_suboffsets = __pyx_t_1; - /* "View.MemoryView":1056 + /* "View.MemoryView":1066 * suboffsets = memview.view.suboffsets * * dst.memview = <__pyx_memoryview *> memview # <<<<<<<<<<<<<< @@ -18540,7 +18569,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem */ __pyx_v_dst->memview = ((struct __pyx_memoryview_obj *)__pyx_v_memview); - /* "View.MemoryView":1057 + /* "View.MemoryView":1067 * * dst.memview = <__pyx_memoryview *> memview * dst.data = memview.view.buf # <<<<<<<<<<<<<< @@ -18549,7 +18578,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem */ __pyx_v_dst->data = ((char *)__pyx_v_memview->view.buf); - /* "View.MemoryView":1059 + /* "View.MemoryView":1069 * dst.data = memview.view.buf * * for dim in range(memview.view.ndim): # <<<<<<<<<<<<<< @@ -18557,10 +18586,11 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem * dst.strides[dim] = strides[dim] */ __pyx_t_2 = __pyx_v_memview->view.ndim; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { - __pyx_v_dim = __pyx_t_3; + __pyx_t_3 = __pyx_t_2; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_dim = __pyx_t_4; - /* "View.MemoryView":1060 + /* "View.MemoryView":1070 * * for dim in range(memview.view.ndim): * dst.shape[dim] = shape[dim] # <<<<<<<<<<<<<< @@ -18569,7 +18599,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem */ (__pyx_v_dst->shape[__pyx_v_dim]) = (__pyx_v_shape[__pyx_v_dim]); - /* "View.MemoryView":1061 + /* "View.MemoryView":1071 * for dim in range(memview.view.ndim): * dst.shape[dim] = shape[dim] * dst.strides[dim] = strides[dim] # <<<<<<<<<<<<<< @@ -18578,7 +18608,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem */ (__pyx_v_dst->strides[__pyx_v_dim]) = (__pyx_v_strides[__pyx_v_dim]); - /* "View.MemoryView":1062 + /* "View.MemoryView":1072 * dst.shape[dim] = shape[dim] * dst.strides[dim] = strides[dim] * dst.suboffsets[dim] = suboffsets[dim] if suboffsets else -1 # <<<<<<<<<<<<<< @@ -18586,14 +18616,14 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem * @cname('__pyx_memoryview_copy_object') */ if ((__pyx_v_suboffsets != 0)) { - __pyx_t_4 = (__pyx_v_suboffsets[__pyx_v_dim]); + __pyx_t_5 = (__pyx_v_suboffsets[__pyx_v_dim]); } else { - __pyx_t_4 = -1L; + __pyx_t_5 = -1L; } - (__pyx_v_dst->suboffsets[__pyx_v_dim]) = __pyx_t_4; + (__pyx_v_dst->suboffsets[__pyx_v_dim]) = __pyx_t_5; } - /* "View.MemoryView":1048 + /* "View.MemoryView":1058 * * @cname('__pyx_memoryview_slice_copy') * cdef void slice_copy(memoryview memview, __Pyx_memviewslice *dst): # <<<<<<<<<<<<<< @@ -18605,7 +18635,7 @@ static void __pyx_memoryview_slice_copy(struct __pyx_memoryview_obj *__pyx_v_mem __Pyx_RefNannyFinishContext(); } -/* "View.MemoryView":1065 +/* "View.MemoryView":1075 * * @cname('__pyx_memoryview_copy_object') * cdef memoryview_copy(memoryview memview): # <<<<<<<<<<<<<< @@ -18620,7 +18650,7 @@ static PyObject *__pyx_memoryview_copy_object(struct __pyx_memoryview_obj *__pyx PyObject *__pyx_t_1 = NULL; __Pyx_RefNannySetupContext("memoryview_copy", 0); - /* "View.MemoryView":1068 + /* "View.MemoryView":1078 * "Create a new memoryview object" * cdef __Pyx_memviewslice memviewslice * slice_copy(memview, &memviewslice) # <<<<<<<<<<<<<< @@ -18629,7 +18659,7 @@ static PyObject *__pyx_memoryview_copy_object(struct __pyx_memoryview_obj *__pyx */ __pyx_memoryview_slice_copy(__pyx_v_memview, (&__pyx_v_memviewslice)); - /* "View.MemoryView":1069 + /* "View.MemoryView":1079 * cdef __Pyx_memviewslice memviewslice * slice_copy(memview, &memviewslice) * return memoryview_copy_from_slice(memview, &memviewslice) # <<<<<<<<<<<<<< @@ -18637,13 +18667,13 @@ static PyObject *__pyx_memoryview_copy_object(struct __pyx_memoryview_obj *__pyx * @cname('__pyx_memoryview_copy_object_from_slice') */ __Pyx_XDECREF(__pyx_r); - __pyx_t_1 = __pyx_memoryview_copy_object_from_slice(__pyx_v_memview, (&__pyx_v_memviewslice)); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1069, __pyx_L1_error) + __pyx_t_1 = __pyx_memoryview_copy_object_from_slice(__pyx_v_memview, (&__pyx_v_memviewslice)); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1079, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; - /* "View.MemoryView":1065 + /* "View.MemoryView":1075 * * @cname('__pyx_memoryview_copy_object') * cdef memoryview_copy(memoryview memview): # <<<<<<<<<<<<<< @@ -18662,7 +18692,7 @@ static PyObject *__pyx_memoryview_copy_object(struct __pyx_memoryview_obj *__pyx return __pyx_r; } -/* "View.MemoryView":1072 +/* "View.MemoryView":1082 * * @cname('__pyx_memoryview_copy_object_from_slice') * cdef memoryview_copy_from_slice(memoryview memview, __Pyx_memviewslice *memviewslice): # <<<<<<<<<<<<<< @@ -18682,7 +18712,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview PyObject *__pyx_t_5 = NULL; __Pyx_RefNannySetupContext("memoryview_copy_from_slice", 0); - /* "View.MemoryView":1079 + /* "View.MemoryView":1089 * cdef int (*to_dtype_func)(char *, object) except 0 * * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -18693,7 +18723,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "View.MemoryView":1080 + /* "View.MemoryView":1090 * * if isinstance(memview, _memoryviewslice): * to_object_func = (<_memoryviewslice> memview).to_object_func # <<<<<<<<<<<<<< @@ -18703,7 +18733,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview __pyx_t_3 = ((struct __pyx_memoryviewslice_obj *)__pyx_v_memview)->to_object_func; __pyx_v_to_object_func = __pyx_t_3; - /* "View.MemoryView":1081 + /* "View.MemoryView":1091 * if isinstance(memview, _memoryviewslice): * to_object_func = (<_memoryviewslice> memview).to_object_func * to_dtype_func = (<_memoryviewslice> memview).to_dtype_func # <<<<<<<<<<<<<< @@ -18713,7 +18743,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview __pyx_t_4 = ((struct __pyx_memoryviewslice_obj *)__pyx_v_memview)->to_dtype_func; __pyx_v_to_dtype_func = __pyx_t_4; - /* "View.MemoryView":1079 + /* "View.MemoryView":1089 * cdef int (*to_dtype_func)(char *, object) except 0 * * if isinstance(memview, _memoryviewslice): # <<<<<<<<<<<<<< @@ -18723,7 +18753,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview goto __pyx_L3; } - /* "View.MemoryView":1083 + /* "View.MemoryView":1093 * to_dtype_func = (<_memoryviewslice> memview).to_dtype_func * else: * to_object_func = NULL # <<<<<<<<<<<<<< @@ -18733,7 +18763,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview /*else*/ { __pyx_v_to_object_func = NULL; - /* "View.MemoryView":1084 + /* "View.MemoryView":1094 * else: * to_object_func = NULL * to_dtype_func = NULL # <<<<<<<<<<<<<< @@ -18744,7 +18774,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview } __pyx_L3:; - /* "View.MemoryView":1086 + /* "View.MemoryView":1096 * to_dtype_func = NULL * * return memoryview_fromslice(memviewslice[0], memview.view.ndim, # <<<<<<<<<<<<<< @@ -18753,20 +18783,20 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview */ __Pyx_XDECREF(__pyx_r); - /* "View.MemoryView":1088 + /* "View.MemoryView":1098 * return memoryview_fromslice(memviewslice[0], memview.view.ndim, * to_object_func, to_dtype_func, * memview.dtype_is_object) # <<<<<<<<<<<<<< * * */ - __pyx_t_5 = __pyx_memoryview_fromslice((__pyx_v_memviewslice[0]), __pyx_v_memview->view.ndim, __pyx_v_to_object_func, __pyx_v_to_dtype_func, __pyx_v_memview->dtype_is_object); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 1086, __pyx_L1_error) + __pyx_t_5 = __pyx_memoryview_fromslice((__pyx_v_memviewslice[0]), __pyx_v_memview->view.ndim, __pyx_v_to_object_func, __pyx_v_to_dtype_func, __pyx_v_memview->dtype_is_object); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 1096, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __pyx_r = __pyx_t_5; __pyx_t_5 = 0; goto __pyx_L0; - /* "View.MemoryView":1072 + /* "View.MemoryView":1082 * * @cname('__pyx_memoryview_copy_object_from_slice') * cdef memoryview_copy_from_slice(memoryview memview, __Pyx_memviewslice *memviewslice): # <<<<<<<<<<<<<< @@ -18785,7 +18815,7 @@ static PyObject *__pyx_memoryview_copy_object_from_slice(struct __pyx_memoryview return __pyx_r; } -/* "View.MemoryView":1094 +/* "View.MemoryView":1104 * * * cdef Py_ssize_t abs_py_ssize_t(Py_ssize_t arg) nogil: # <<<<<<<<<<<<<< @@ -18797,7 +18827,7 @@ static Py_ssize_t abs_py_ssize_t(Py_ssize_t __pyx_v_arg) { Py_ssize_t __pyx_r; int __pyx_t_1; - /* "View.MemoryView":1095 + /* "View.MemoryView":1105 * * cdef Py_ssize_t abs_py_ssize_t(Py_ssize_t arg) nogil: * if arg < 0: # <<<<<<<<<<<<<< @@ -18807,7 +18837,7 @@ static Py_ssize_t abs_py_ssize_t(Py_ssize_t __pyx_v_arg) { __pyx_t_1 = ((__pyx_v_arg < 0) != 0); if (__pyx_t_1) { - /* "View.MemoryView":1096 + /* "View.MemoryView":1106 * cdef Py_ssize_t abs_py_ssize_t(Py_ssize_t arg) nogil: * if arg < 0: * return -arg # <<<<<<<<<<<<<< @@ -18817,7 +18847,7 @@ static Py_ssize_t abs_py_ssize_t(Py_ssize_t __pyx_v_arg) { __pyx_r = (-__pyx_v_arg); goto __pyx_L0; - /* "View.MemoryView":1095 + /* "View.MemoryView":1105 * * cdef Py_ssize_t abs_py_ssize_t(Py_ssize_t arg) nogil: * if arg < 0: # <<<<<<<<<<<<<< @@ -18826,7 +18856,7 @@ static Py_ssize_t abs_py_ssize_t(Py_ssize_t __pyx_v_arg) { */ } - /* "View.MemoryView":1098 + /* "View.MemoryView":1108 * return -arg * else: * return arg # <<<<<<<<<<<<<< @@ -18838,7 +18868,7 @@ static Py_ssize_t abs_py_ssize_t(Py_ssize_t __pyx_v_arg) { goto __pyx_L0; } - /* "View.MemoryView":1094 + /* "View.MemoryView":1104 * * * cdef Py_ssize_t abs_py_ssize_t(Py_ssize_t arg) nogil: # <<<<<<<<<<<<<< @@ -18851,7 +18881,7 @@ static Py_ssize_t abs_py_ssize_t(Py_ssize_t __pyx_v_arg) { return __pyx_r; } -/* "View.MemoryView":1101 +/* "View.MemoryView":1111 * * @cname('__pyx_get_best_slice_order') * cdef char get_best_order(__Pyx_memviewslice *mslice, int ndim) nogil: # <<<<<<<<<<<<<< @@ -18867,8 +18897,9 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ int __pyx_t_1; int __pyx_t_2; int __pyx_t_3; + int __pyx_t_4; - /* "View.MemoryView":1106 + /* "View.MemoryView":1116 * """ * cdef int i * cdef Py_ssize_t c_stride = 0 # <<<<<<<<<<<<<< @@ -18877,7 +18908,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ __pyx_v_c_stride = 0; - /* "View.MemoryView":1107 + /* "View.MemoryView":1117 * cdef int i * cdef Py_ssize_t c_stride = 0 * cdef Py_ssize_t f_stride = 0 # <<<<<<<<<<<<<< @@ -18886,17 +18917,17 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ __pyx_v_f_stride = 0; - /* "View.MemoryView":1109 + /* "View.MemoryView":1119 * cdef Py_ssize_t f_stride = 0 * * for i in range(ndim - 1, -1, -1): # <<<<<<<<<<<<<< * if mslice.shape[i] > 1: * c_stride = mslice.strides[i] */ - for (__pyx_t_1 = (__pyx_v_ndim - 1); __pyx_t_1 > -1L; __pyx_t_1-=1) { + for (__pyx_t_1 = (__pyx_v_ndim - 1); __pyx_t_1 > -1; __pyx_t_1-=1) { __pyx_v_i = __pyx_t_1; - /* "View.MemoryView":1110 + /* "View.MemoryView":1120 * * for i in range(ndim - 1, -1, -1): * if mslice.shape[i] > 1: # <<<<<<<<<<<<<< @@ -18906,7 +18937,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ __pyx_t_2 = (((__pyx_v_mslice->shape[__pyx_v_i]) > 1) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1111 + /* "View.MemoryView":1121 * for i in range(ndim - 1, -1, -1): * if mslice.shape[i] > 1: * c_stride = mslice.strides[i] # <<<<<<<<<<<<<< @@ -18915,7 +18946,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ __pyx_v_c_stride = (__pyx_v_mslice->strides[__pyx_v_i]); - /* "View.MemoryView":1112 + /* "View.MemoryView":1122 * if mslice.shape[i] > 1: * c_stride = mslice.strides[i] * break # <<<<<<<<<<<<<< @@ -18924,7 +18955,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ goto __pyx_L4_break; - /* "View.MemoryView":1110 + /* "View.MemoryView":1120 * * for i in range(ndim - 1, -1, -1): * if mslice.shape[i] > 1: # <<<<<<<<<<<<<< @@ -18935,7 +18966,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ } __pyx_L4_break:; - /* "View.MemoryView":1114 + /* "View.MemoryView":1124 * break * * for i in range(ndim): # <<<<<<<<<<<<<< @@ -18943,10 +18974,11 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ * f_stride = mslice.strides[i] */ __pyx_t_1 = __pyx_v_ndim; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_1; __pyx_t_3+=1) { - __pyx_v_i = __pyx_t_3; + __pyx_t_3 = __pyx_t_1; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_i = __pyx_t_4; - /* "View.MemoryView":1115 + /* "View.MemoryView":1125 * * for i in range(ndim): * if mslice.shape[i] > 1: # <<<<<<<<<<<<<< @@ -18956,7 +18988,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ __pyx_t_2 = (((__pyx_v_mslice->shape[__pyx_v_i]) > 1) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1116 + /* "View.MemoryView":1126 * for i in range(ndim): * if mslice.shape[i] > 1: * f_stride = mslice.strides[i] # <<<<<<<<<<<<<< @@ -18965,7 +18997,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ __pyx_v_f_stride = (__pyx_v_mslice->strides[__pyx_v_i]); - /* "View.MemoryView":1117 + /* "View.MemoryView":1127 * if mslice.shape[i] > 1: * f_stride = mslice.strides[i] * break # <<<<<<<<<<<<<< @@ -18974,7 +19006,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ goto __pyx_L7_break; - /* "View.MemoryView":1115 + /* "View.MemoryView":1125 * * for i in range(ndim): * if mslice.shape[i] > 1: # <<<<<<<<<<<<<< @@ -18985,7 +19017,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ } __pyx_L7_break:; - /* "View.MemoryView":1119 + /* "View.MemoryView":1129 * break * * if abs_py_ssize_t(c_stride) <= abs_py_ssize_t(f_stride): # <<<<<<<<<<<<<< @@ -18995,7 +19027,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ __pyx_t_2 = ((abs_py_ssize_t(__pyx_v_c_stride) <= abs_py_ssize_t(__pyx_v_f_stride)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1120 + /* "View.MemoryView":1130 * * if abs_py_ssize_t(c_stride) <= abs_py_ssize_t(f_stride): * return 'C' # <<<<<<<<<<<<<< @@ -19005,7 +19037,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ __pyx_r = 'C'; goto __pyx_L0; - /* "View.MemoryView":1119 + /* "View.MemoryView":1129 * break * * if abs_py_ssize_t(c_stride) <= abs_py_ssize_t(f_stride): # <<<<<<<<<<<<<< @@ -19014,7 +19046,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ */ } - /* "View.MemoryView":1122 + /* "View.MemoryView":1132 * return 'C' * else: * return 'F' # <<<<<<<<<<<<<< @@ -19026,7 +19058,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ goto __pyx_L0; } - /* "View.MemoryView":1101 + /* "View.MemoryView":1111 * * @cname('__pyx_get_best_slice_order') * cdef char get_best_order(__Pyx_memviewslice *mslice, int ndim) nogil: # <<<<<<<<<<<<<< @@ -19039,7 +19071,7 @@ static char __pyx_get_best_slice_order(__Pyx_memviewslice *__pyx_v_mslice, int _ return __pyx_r; } -/* "View.MemoryView":1125 +/* "View.MemoryView":1135 * * @cython.cdivision(True) * cdef void _copy_strided_to_strided(char *src_data, Py_ssize_t *src_strides, # <<<<<<<<<<<<<< @@ -19058,8 +19090,9 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v int __pyx_t_3; Py_ssize_t __pyx_t_4; Py_ssize_t __pyx_t_5; + Py_ssize_t __pyx_t_6; - /* "View.MemoryView":1132 + /* "View.MemoryView":1142 * * cdef Py_ssize_t i * cdef Py_ssize_t src_extent = src_shape[0] # <<<<<<<<<<<<<< @@ -19068,7 +19101,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ __pyx_v_src_extent = (__pyx_v_src_shape[0]); - /* "View.MemoryView":1133 + /* "View.MemoryView":1143 * cdef Py_ssize_t i * cdef Py_ssize_t src_extent = src_shape[0] * cdef Py_ssize_t dst_extent = dst_shape[0] # <<<<<<<<<<<<<< @@ -19077,7 +19110,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ __pyx_v_dst_extent = (__pyx_v_dst_shape[0]); - /* "View.MemoryView":1134 + /* "View.MemoryView":1144 * cdef Py_ssize_t src_extent = src_shape[0] * cdef Py_ssize_t dst_extent = dst_shape[0] * cdef Py_ssize_t src_stride = src_strides[0] # <<<<<<<<<<<<<< @@ -19086,7 +19119,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ __pyx_v_src_stride = (__pyx_v_src_strides[0]); - /* "View.MemoryView":1135 + /* "View.MemoryView":1145 * cdef Py_ssize_t dst_extent = dst_shape[0] * cdef Py_ssize_t src_stride = src_strides[0] * cdef Py_ssize_t dst_stride = dst_strides[0] # <<<<<<<<<<<<<< @@ -19095,7 +19128,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ __pyx_v_dst_stride = (__pyx_v_dst_strides[0]); - /* "View.MemoryView":1137 + /* "View.MemoryView":1147 * cdef Py_ssize_t dst_stride = dst_strides[0] * * if ndim == 1: # <<<<<<<<<<<<<< @@ -19105,7 +19138,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v __pyx_t_1 = ((__pyx_v_ndim == 1) != 0); if (__pyx_t_1) { - /* "View.MemoryView":1138 + /* "View.MemoryView":1148 * * if ndim == 1: * if (src_stride > 0 and dst_stride > 0 and # <<<<<<<<<<<<<< @@ -19125,7 +19158,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v goto __pyx_L5_bool_binop_done; } - /* "View.MemoryView":1139 + /* "View.MemoryView":1149 * if ndim == 1: * if (src_stride > 0 and dst_stride > 0 and * src_stride == itemsize == dst_stride): # <<<<<<<<<<<<<< @@ -19140,7 +19173,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v __pyx_t_1 = __pyx_t_3; __pyx_L5_bool_binop_done:; - /* "View.MemoryView":1138 + /* "View.MemoryView":1148 * * if ndim == 1: * if (src_stride > 0 and dst_stride > 0 and # <<<<<<<<<<<<<< @@ -19149,16 +19182,16 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ if (__pyx_t_1) { - /* "View.MemoryView":1140 + /* "View.MemoryView":1150 * if (src_stride > 0 and dst_stride > 0 and * src_stride == itemsize == dst_stride): * memcpy(dst_data, src_data, itemsize * dst_extent) # <<<<<<<<<<<<<< * else: * for i in range(dst_extent): */ - memcpy(__pyx_v_dst_data, __pyx_v_src_data, (__pyx_v_itemsize * __pyx_v_dst_extent)); + (void)(memcpy(__pyx_v_dst_data, __pyx_v_src_data, (__pyx_v_itemsize * __pyx_v_dst_extent))); - /* "View.MemoryView":1138 + /* "View.MemoryView":1148 * * if ndim == 1: * if (src_stride > 0 and dst_stride > 0 and # <<<<<<<<<<<<<< @@ -19168,7 +19201,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v goto __pyx_L4; } - /* "View.MemoryView":1142 + /* "View.MemoryView":1152 * memcpy(dst_data, src_data, itemsize * dst_extent) * else: * for i in range(dst_extent): # <<<<<<<<<<<<<< @@ -19177,19 +19210,20 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ /*else*/ { __pyx_t_4 = __pyx_v_dst_extent; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "View.MemoryView":1143 + /* "View.MemoryView":1153 * else: * for i in range(dst_extent): * memcpy(dst_data, src_data, itemsize) # <<<<<<<<<<<<<< * src_data += src_stride * dst_data += dst_stride */ - memcpy(__pyx_v_dst_data, __pyx_v_src_data, __pyx_v_itemsize); + (void)(memcpy(__pyx_v_dst_data, __pyx_v_src_data, __pyx_v_itemsize)); - /* "View.MemoryView":1144 + /* "View.MemoryView":1154 * for i in range(dst_extent): * memcpy(dst_data, src_data, itemsize) * src_data += src_stride # <<<<<<<<<<<<<< @@ -19198,7 +19232,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ __pyx_v_src_data = (__pyx_v_src_data + __pyx_v_src_stride); - /* "View.MemoryView":1145 + /* "View.MemoryView":1155 * memcpy(dst_data, src_data, itemsize) * src_data += src_stride * dst_data += dst_stride # <<<<<<<<<<<<<< @@ -19210,7 +19244,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v } __pyx_L4:; - /* "View.MemoryView":1137 + /* "View.MemoryView":1147 * cdef Py_ssize_t dst_stride = dst_strides[0] * * if ndim == 1: # <<<<<<<<<<<<<< @@ -19220,7 +19254,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v goto __pyx_L3; } - /* "View.MemoryView":1147 + /* "View.MemoryView":1157 * dst_data += dst_stride * else: * for i in range(dst_extent): # <<<<<<<<<<<<<< @@ -19229,10 +19263,11 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ /*else*/ { __pyx_t_4 = __pyx_v_dst_extent; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_4; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_4; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "View.MemoryView":1148 + /* "View.MemoryView":1158 * else: * for i in range(dst_extent): * _copy_strided_to_strided(src_data, src_strides + 1, # <<<<<<<<<<<<<< @@ -19241,7 +19276,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ _copy_strided_to_strided(__pyx_v_src_data, (__pyx_v_src_strides + 1), __pyx_v_dst_data, (__pyx_v_dst_strides + 1), (__pyx_v_src_shape + 1), (__pyx_v_dst_shape + 1), (__pyx_v_ndim - 1), __pyx_v_itemsize); - /* "View.MemoryView":1152 + /* "View.MemoryView":1162 * src_shape + 1, dst_shape + 1, * ndim - 1, itemsize) * src_data += src_stride # <<<<<<<<<<<<<< @@ -19250,7 +19285,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v */ __pyx_v_src_data = (__pyx_v_src_data + __pyx_v_src_stride); - /* "View.MemoryView":1153 + /* "View.MemoryView":1163 * ndim - 1, itemsize) * src_data += src_stride * dst_data += dst_stride # <<<<<<<<<<<<<< @@ -19262,7 +19297,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v } __pyx_L3:; - /* "View.MemoryView":1125 + /* "View.MemoryView":1135 * * @cython.cdivision(True) * cdef void _copy_strided_to_strided(char *src_data, Py_ssize_t *src_strides, # <<<<<<<<<<<<<< @@ -19273,7 +19308,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v /* function exit code */ } -/* "View.MemoryView":1155 +/* "View.MemoryView":1165 * dst_data += dst_stride * * cdef void copy_strided_to_strided(__Pyx_memviewslice *src, # <<<<<<<<<<<<<< @@ -19283,7 +19318,7 @@ static void _copy_strided_to_strided(char *__pyx_v_src_data, Py_ssize_t *__pyx_v static void copy_strided_to_strided(__Pyx_memviewslice *__pyx_v_src, __Pyx_memviewslice *__pyx_v_dst, int __pyx_v_ndim, size_t __pyx_v_itemsize) { - /* "View.MemoryView":1158 + /* "View.MemoryView":1168 * __Pyx_memviewslice *dst, * int ndim, size_t itemsize) nogil: * _copy_strided_to_strided(src.data, src.strides, dst.data, dst.strides, # <<<<<<<<<<<<<< @@ -19292,7 +19327,7 @@ static void copy_strided_to_strided(__Pyx_memviewslice *__pyx_v_src, __Pyx_memvi */ _copy_strided_to_strided(__pyx_v_src->data, __pyx_v_src->strides, __pyx_v_dst->data, __pyx_v_dst->strides, __pyx_v_src->shape, __pyx_v_dst->shape, __pyx_v_ndim, __pyx_v_itemsize); - /* "View.MemoryView":1155 + /* "View.MemoryView":1165 * dst_data += dst_stride * * cdef void copy_strided_to_strided(__Pyx_memviewslice *src, # <<<<<<<<<<<<<< @@ -19303,7 +19338,7 @@ static void copy_strided_to_strided(__Pyx_memviewslice *__pyx_v_src, __Pyx_memvi /* function exit code */ } -/* "View.MemoryView":1162 +/* "View.MemoryView":1172 * * @cname('__pyx_memoryview_slice_get_size') * cdef Py_ssize_t slice_get_size(__Pyx_memviewslice *src, int ndim) nogil: # <<<<<<<<<<<<<< @@ -19318,8 +19353,9 @@ static Py_ssize_t __pyx_memoryview_slice_get_size(__Pyx_memviewslice *__pyx_v_sr Py_ssize_t __pyx_t_1; int __pyx_t_2; int __pyx_t_3; + int __pyx_t_4; - /* "View.MemoryView":1165 + /* "View.MemoryView":1175 * "Return the size of the memory occupied by the slice in number of bytes" * cdef int i * cdef Py_ssize_t size = src.memview.view.itemsize # <<<<<<<<<<<<<< @@ -19329,7 +19365,7 @@ static Py_ssize_t __pyx_memoryview_slice_get_size(__Pyx_memviewslice *__pyx_v_sr __pyx_t_1 = __pyx_v_src->memview->view.itemsize; __pyx_v_size = __pyx_t_1; - /* "View.MemoryView":1167 + /* "View.MemoryView":1177 * cdef Py_ssize_t size = src.memview.view.itemsize * * for i in range(ndim): # <<<<<<<<<<<<<< @@ -19337,10 +19373,11 @@ static Py_ssize_t __pyx_memoryview_slice_get_size(__Pyx_memviewslice *__pyx_v_sr * */ __pyx_t_2 = __pyx_v_ndim; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { - __pyx_v_i = __pyx_t_3; + __pyx_t_3 = __pyx_t_2; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_i = __pyx_t_4; - /* "View.MemoryView":1168 + /* "View.MemoryView":1178 * * for i in range(ndim): * size *= src.shape[i] # <<<<<<<<<<<<<< @@ -19350,7 +19387,7 @@ static Py_ssize_t __pyx_memoryview_slice_get_size(__Pyx_memviewslice *__pyx_v_sr __pyx_v_size = (__pyx_v_size * (__pyx_v_src->shape[__pyx_v_i])); } - /* "View.MemoryView":1170 + /* "View.MemoryView":1180 * size *= src.shape[i] * * return size # <<<<<<<<<<<<<< @@ -19360,7 +19397,7 @@ static Py_ssize_t __pyx_memoryview_slice_get_size(__Pyx_memviewslice *__pyx_v_sr __pyx_r = __pyx_v_size; goto __pyx_L0; - /* "View.MemoryView":1162 + /* "View.MemoryView":1172 * * @cname('__pyx_memoryview_slice_get_size') * cdef Py_ssize_t slice_get_size(__Pyx_memviewslice *src, int ndim) nogil: # <<<<<<<<<<<<<< @@ -19373,7 +19410,7 @@ static Py_ssize_t __pyx_memoryview_slice_get_size(__Pyx_memviewslice *__pyx_v_sr return __pyx_r; } -/* "View.MemoryView":1173 +/* "View.MemoryView":1183 * * @cname('__pyx_fill_contig_strides_array') * cdef Py_ssize_t fill_contig_strides_array( # <<<<<<<<<<<<<< @@ -19387,8 +19424,9 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ int __pyx_t_1; int __pyx_t_2; int __pyx_t_3; + int __pyx_t_4; - /* "View.MemoryView":1182 + /* "View.MemoryView":1192 * cdef int idx * * if order == 'F': # <<<<<<<<<<<<<< @@ -19398,7 +19436,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ __pyx_t_1 = ((__pyx_v_order == 'F') != 0); if (__pyx_t_1) { - /* "View.MemoryView":1183 + /* "View.MemoryView":1193 * * if order == 'F': * for idx in range(ndim): # <<<<<<<<<<<<<< @@ -19406,10 +19444,11 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ * stride = stride * shape[idx] */ __pyx_t_2 = __pyx_v_ndim; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { - __pyx_v_idx = __pyx_t_3; + __pyx_t_3 = __pyx_t_2; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_idx = __pyx_t_4; - /* "View.MemoryView":1184 + /* "View.MemoryView":1194 * if order == 'F': * for idx in range(ndim): * strides[idx] = stride # <<<<<<<<<<<<<< @@ -19418,7 +19457,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ */ (__pyx_v_strides[__pyx_v_idx]) = __pyx_v_stride; - /* "View.MemoryView":1185 + /* "View.MemoryView":1195 * for idx in range(ndim): * strides[idx] = stride * stride = stride * shape[idx] # <<<<<<<<<<<<<< @@ -19428,7 +19467,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ __pyx_v_stride = (__pyx_v_stride * (__pyx_v_shape[__pyx_v_idx])); } - /* "View.MemoryView":1182 + /* "View.MemoryView":1192 * cdef int idx * * if order == 'F': # <<<<<<<<<<<<<< @@ -19438,7 +19477,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ goto __pyx_L3; } - /* "View.MemoryView":1187 + /* "View.MemoryView":1197 * stride = stride * shape[idx] * else: * for idx in range(ndim - 1, -1, -1): # <<<<<<<<<<<<<< @@ -19446,10 +19485,10 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ * stride = stride * shape[idx] */ /*else*/ { - for (__pyx_t_2 = (__pyx_v_ndim - 1); __pyx_t_2 > -1L; __pyx_t_2-=1) { + for (__pyx_t_2 = (__pyx_v_ndim - 1); __pyx_t_2 > -1; __pyx_t_2-=1) { __pyx_v_idx = __pyx_t_2; - /* "View.MemoryView":1188 + /* "View.MemoryView":1198 * else: * for idx in range(ndim - 1, -1, -1): * strides[idx] = stride # <<<<<<<<<<<<<< @@ -19458,7 +19497,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ */ (__pyx_v_strides[__pyx_v_idx]) = __pyx_v_stride; - /* "View.MemoryView":1189 + /* "View.MemoryView":1199 * for idx in range(ndim - 1, -1, -1): * strides[idx] = stride * stride = stride * shape[idx] # <<<<<<<<<<<<<< @@ -19470,7 +19509,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ } __pyx_L3:; - /* "View.MemoryView":1191 + /* "View.MemoryView":1201 * stride = stride * shape[idx] * * return stride # <<<<<<<<<<<<<< @@ -19480,7 +19519,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ __pyx_r = __pyx_v_stride; goto __pyx_L0; - /* "View.MemoryView":1173 + /* "View.MemoryView":1183 * * @cname('__pyx_fill_contig_strides_array') * cdef Py_ssize_t fill_contig_strides_array( # <<<<<<<<<<<<<< @@ -19493,7 +19532,7 @@ static Py_ssize_t __pyx_fill_contig_strides_array(Py_ssize_t *__pyx_v_shape, Py_ return __pyx_r; } -/* "View.MemoryView":1194 +/* "View.MemoryView":1204 * * @cname('__pyx_memoryview_copy_data_to_temp') * cdef void *copy_data_to_temp(__Pyx_memviewslice *src, # <<<<<<<<<<<<<< @@ -19512,8 +19551,9 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, int __pyx_t_3; struct __pyx_memoryview_obj *__pyx_t_4; int __pyx_t_5; + int __pyx_t_6; - /* "View.MemoryView":1205 + /* "View.MemoryView":1215 * cdef void *result * * cdef size_t itemsize = src.memview.view.itemsize # <<<<<<<<<<<<<< @@ -19523,7 +19563,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, __pyx_t_1 = __pyx_v_src->memview->view.itemsize; __pyx_v_itemsize = __pyx_t_1; - /* "View.MemoryView":1206 + /* "View.MemoryView":1216 * * cdef size_t itemsize = src.memview.view.itemsize * cdef size_t size = slice_get_size(src, ndim) # <<<<<<<<<<<<<< @@ -19532,7 +19572,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, */ __pyx_v_size = __pyx_memoryview_slice_get_size(__pyx_v_src, __pyx_v_ndim); - /* "View.MemoryView":1208 + /* "View.MemoryView":1218 * cdef size_t size = slice_get_size(src, ndim) * * result = malloc(size) # <<<<<<<<<<<<<< @@ -19541,7 +19581,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, */ __pyx_v_result = malloc(__pyx_v_size); - /* "View.MemoryView":1209 + /* "View.MemoryView":1219 * * result = malloc(size) * if not result: # <<<<<<<<<<<<<< @@ -19551,16 +19591,16 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, __pyx_t_2 = ((!(__pyx_v_result != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1210 + /* "View.MemoryView":1220 * result = malloc(size) * if not result: * _err(MemoryError, NULL) # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __pyx_memoryview_err(__pyx_builtin_MemoryError, NULL); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 1210, __pyx_L1_error) + __pyx_t_3 = __pyx_memoryview_err(__pyx_builtin_MemoryError, NULL); if (unlikely(__pyx_t_3 == ((int)-1))) __PYX_ERR(2, 1220, __pyx_L1_error) - /* "View.MemoryView":1209 + /* "View.MemoryView":1219 * * result = malloc(size) * if not result: # <<<<<<<<<<<<<< @@ -19569,7 +19609,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, */ } - /* "View.MemoryView":1213 + /* "View.MemoryView":1223 * * * tmpslice.data = result # <<<<<<<<<<<<<< @@ -19578,7 +19618,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, */ __pyx_v_tmpslice->data = ((char *)__pyx_v_result); - /* "View.MemoryView":1214 + /* "View.MemoryView":1224 * * tmpslice.data = result * tmpslice.memview = src.memview # <<<<<<<<<<<<<< @@ -19588,7 +19628,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, __pyx_t_4 = __pyx_v_src->memview; __pyx_v_tmpslice->memview = __pyx_t_4; - /* "View.MemoryView":1215 + /* "View.MemoryView":1225 * tmpslice.data = result * tmpslice.memview = src.memview * for i in range(ndim): # <<<<<<<<<<<<<< @@ -19596,10 +19636,11 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, * tmpslice.suboffsets[i] = -1 */ __pyx_t_3 = __pyx_v_ndim; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_3; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_3; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "View.MemoryView":1216 + /* "View.MemoryView":1226 * tmpslice.memview = src.memview * for i in range(ndim): * tmpslice.shape[i] = src.shape[i] # <<<<<<<<<<<<<< @@ -19608,7 +19649,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, */ (__pyx_v_tmpslice->shape[__pyx_v_i]) = (__pyx_v_src->shape[__pyx_v_i]); - /* "View.MemoryView":1217 + /* "View.MemoryView":1227 * for i in range(ndim): * tmpslice.shape[i] = src.shape[i] * tmpslice.suboffsets[i] = -1 # <<<<<<<<<<<<<< @@ -19618,16 +19659,16 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, (__pyx_v_tmpslice->suboffsets[__pyx_v_i]) = -1L; } - /* "View.MemoryView":1219 + /* "View.MemoryView":1229 * tmpslice.suboffsets[i] = -1 * * fill_contig_strides_array(&tmpslice.shape[0], &tmpslice.strides[0], itemsize, # <<<<<<<<<<<<<< * ndim, order) * */ - __pyx_fill_contig_strides_array((&(__pyx_v_tmpslice->shape[0])), (&(__pyx_v_tmpslice->strides[0])), __pyx_v_itemsize, __pyx_v_ndim, __pyx_v_order); + (void)(__pyx_fill_contig_strides_array((&(__pyx_v_tmpslice->shape[0])), (&(__pyx_v_tmpslice->strides[0])), __pyx_v_itemsize, __pyx_v_ndim, __pyx_v_order)); - /* "View.MemoryView":1223 + /* "View.MemoryView":1233 * * * for i in range(ndim): # <<<<<<<<<<<<<< @@ -19635,10 +19676,11 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, * tmpslice.strides[i] = 0 */ __pyx_t_3 = __pyx_v_ndim; - for (__pyx_t_5 = 0; __pyx_t_5 < __pyx_t_3; __pyx_t_5+=1) { - __pyx_v_i = __pyx_t_5; + __pyx_t_5 = __pyx_t_3; + for (__pyx_t_6 = 0; __pyx_t_6 < __pyx_t_5; __pyx_t_6+=1) { + __pyx_v_i = __pyx_t_6; - /* "View.MemoryView":1224 + /* "View.MemoryView":1234 * * for i in range(ndim): * if tmpslice.shape[i] == 1: # <<<<<<<<<<<<<< @@ -19648,7 +19690,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, __pyx_t_2 = (((__pyx_v_tmpslice->shape[__pyx_v_i]) == 1) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1225 + /* "View.MemoryView":1235 * for i in range(ndim): * if tmpslice.shape[i] == 1: * tmpslice.strides[i] = 0 # <<<<<<<<<<<<<< @@ -19657,7 +19699,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, */ (__pyx_v_tmpslice->strides[__pyx_v_i]) = 0; - /* "View.MemoryView":1224 + /* "View.MemoryView":1234 * * for i in range(ndim): * if tmpslice.shape[i] == 1: # <<<<<<<<<<<<<< @@ -19667,7 +19709,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, } } - /* "View.MemoryView":1227 + /* "View.MemoryView":1237 * tmpslice.strides[i] = 0 * * if slice_is_contig(src[0], order, ndim): # <<<<<<<<<<<<<< @@ -19677,16 +19719,16 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, __pyx_t_2 = (__pyx_memviewslice_is_contig((__pyx_v_src[0]), __pyx_v_order, __pyx_v_ndim) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1228 + /* "View.MemoryView":1238 * * if slice_is_contig(src[0], order, ndim): * memcpy(result, src.data, size) # <<<<<<<<<<<<<< * else: * copy_strided_to_strided(src, tmpslice, ndim, itemsize) */ - memcpy(__pyx_v_result, __pyx_v_src->data, __pyx_v_size); + (void)(memcpy(__pyx_v_result, __pyx_v_src->data, __pyx_v_size)); - /* "View.MemoryView":1227 + /* "View.MemoryView":1237 * tmpslice.strides[i] = 0 * * if slice_is_contig(src[0], order, ndim): # <<<<<<<<<<<<<< @@ -19696,7 +19738,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, goto __pyx_L9; } - /* "View.MemoryView":1230 + /* "View.MemoryView":1240 * memcpy(result, src.data, size) * else: * copy_strided_to_strided(src, tmpslice, ndim, itemsize) # <<<<<<<<<<<<<< @@ -19708,7 +19750,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, } __pyx_L9:; - /* "View.MemoryView":1232 + /* "View.MemoryView":1242 * copy_strided_to_strided(src, tmpslice, ndim, itemsize) * * return result # <<<<<<<<<<<<<< @@ -19718,7 +19760,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, __pyx_r = __pyx_v_result; goto __pyx_L0; - /* "View.MemoryView":1194 + /* "View.MemoryView":1204 * * @cname('__pyx_memoryview_copy_data_to_temp') * cdef void *copy_data_to_temp(__Pyx_memviewslice *src, # <<<<<<<<<<<<<< @@ -19742,7 +19784,7 @@ static void *__pyx_memoryview_copy_data_to_temp(__Pyx_memviewslice *__pyx_v_src, return __pyx_r; } -/* "View.MemoryView":1237 +/* "View.MemoryView":1247 * * @cname('__pyx_memoryview_err_extents') * cdef int _err_extents(int i, Py_ssize_t extent1, # <<<<<<<<<<<<<< @@ -19762,20 +19804,20 @@ static int __pyx_memoryview_err_extents(int __pyx_v_i, Py_ssize_t __pyx_v_extent #endif __Pyx_RefNannySetupContext("_err_extents", 0); - /* "View.MemoryView":1240 + /* "View.MemoryView":1250 * Py_ssize_t extent2) except -1 with gil: * raise ValueError("got differing extents in dimension %d (got %d and %d)" % * (i, extent1, extent2)) # <<<<<<<<<<<<<< * * @cname('__pyx_memoryview_err_dim') */ - __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_i); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1240, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyInt_From_int(__pyx_v_i); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_extent1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1240, __pyx_L1_error) + __pyx_t_2 = PyInt_FromSsize_t(__pyx_v_extent1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = PyInt_FromSsize_t(__pyx_v_extent2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1240, __pyx_L1_error) + __pyx_t_3 = PyInt_FromSsize_t(__pyx_v_extent2); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyTuple_New(3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 1240, __pyx_L1_error) + __pyx_t_4 = PyTuple_New(3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 1250, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_GIVEREF(__pyx_t_1); PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_1); @@ -19787,29 +19829,24 @@ static int __pyx_memoryview_err_extents(int __pyx_v_i, Py_ssize_t __pyx_v_extent __pyx_t_2 = 0; __pyx_t_3 = 0; - /* "View.MemoryView":1239 + /* "View.MemoryView":1249 * cdef int _err_extents(int i, Py_ssize_t extent1, * Py_ssize_t extent2) except -1 with gil: * raise ValueError("got differing extents in dimension %d (got %d and %d)" % # <<<<<<<<<<<<<< * (i, extent1, extent2)) * */ - __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_got_differing_extents_in_dimensi, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1239, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyString_Format(__pyx_kp_s_got_differing_extents_in_dimensi, __pyx_t_4); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1249, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __pyx_t_4 = PyTuple_New(1); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 1239, __pyx_L1_error) + __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 1249, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); - __Pyx_GIVEREF(__pyx_t_3); - PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_3); - __pyx_t_3 = 0; - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_ValueError, __pyx_t_4, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1239, __pyx_L1_error) - __Pyx_GOTREF(__pyx_t_3); - __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(2, 1239, __pyx_L1_error) + __Pyx_Raise(__pyx_t_4, 0, 0, 0); + __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; + __PYX_ERR(2, 1249, __pyx_L1_error) - /* "View.MemoryView":1237 + /* "View.MemoryView":1247 * * @cname('__pyx_memoryview_err_extents') * cdef int _err_extents(int i, Py_ssize_t extent1, # <<<<<<<<<<<<<< @@ -19832,7 +19869,7 @@ static int __pyx_memoryview_err_extents(int __pyx_v_i, Py_ssize_t __pyx_v_extent return __pyx_r; } -/* "View.MemoryView":1243 +/* "View.MemoryView":1253 * * @cname('__pyx_memoryview_err_dim') * cdef int _err_dim(object error, char *msg, int dim) except -1 with gil: # <<<<<<<<<<<<<< @@ -19854,18 +19891,18 @@ static int __pyx_memoryview_err_dim(PyObject *__pyx_v_error, char *__pyx_v_msg, __Pyx_RefNannySetupContext("_err_dim", 0); __Pyx_INCREF(__pyx_v_error); - /* "View.MemoryView":1244 + /* "View.MemoryView":1254 * @cname('__pyx_memoryview_err_dim') * cdef int _err_dim(object error, char *msg, int dim) except -1 with gil: * raise error(msg.decode('ascii') % dim) # <<<<<<<<<<<<<< * * @cname('__pyx_memoryview_err') */ - __pyx_t_2 = __Pyx_decode_c_string(__pyx_v_msg, 0, strlen(__pyx_v_msg), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_2 = __Pyx_decode_c_string(__pyx_v_msg, 0, strlen(__pyx_v_msg), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_dim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_dim); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_4 = PyUnicode_Format(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_4 = PyUnicode_Format(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; @@ -19881,14 +19918,14 @@ static int __pyx_memoryview_err_dim(PyObject *__pyx_v_error, char *__pyx_v_msg, } } if (!__pyx_t_2) { - __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_4); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_GOTREF(__pyx_t_1); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[2] = {__pyx_t_2, __pyx_t_4}; - __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; @@ -19897,20 +19934,20 @@ static int __pyx_memoryview_err_dim(PyObject *__pyx_v_error, char *__pyx_v_msg, #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_3)) { PyObject *__pyx_temp[2] = {__pyx_t_2, __pyx_t_4}; - __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyCFunction_FastCall(__pyx_t_3, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; } else #endif { - __pyx_t_5 = PyTuple_New(1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_5 = PyTuple_New(1+1); if (unlikely(!__pyx_t_5)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_2); __pyx_t_2 = NULL; __Pyx_GIVEREF(__pyx_t_4); PyTuple_SET_ITEM(__pyx_t_5, 0+1, __pyx_t_4); __pyx_t_4 = 0; - __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_5, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1244, __pyx_L1_error) + __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_t_5, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(2, 1254, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } @@ -19918,9 +19955,9 @@ static int __pyx_memoryview_err_dim(PyObject *__pyx_v_error, char *__pyx_v_msg, __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; - __PYX_ERR(2, 1244, __pyx_L1_error) + __PYX_ERR(2, 1254, __pyx_L1_error) - /* "View.MemoryView":1243 + /* "View.MemoryView":1253 * * @cname('__pyx_memoryview_err_dim') * cdef int _err_dim(object error, char *msg, int dim) except -1 with gil: # <<<<<<<<<<<<<< @@ -19945,7 +19982,7 @@ static int __pyx_memoryview_err_dim(PyObject *__pyx_v_error, char *__pyx_v_msg, return __pyx_r; } -/* "View.MemoryView":1247 +/* "View.MemoryView":1257 * * @cname('__pyx_memoryview_err') * cdef int _err(object error, char *msg) except -1 with gil: # <<<<<<<<<<<<<< @@ -19968,7 +20005,7 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { __Pyx_RefNannySetupContext("_err", 0); __Pyx_INCREF(__pyx_v_error); - /* "View.MemoryView":1248 + /* "View.MemoryView":1258 * @cname('__pyx_memoryview_err') * cdef int _err(object error, char *msg) except -1 with gil: * if msg != NULL: # <<<<<<<<<<<<<< @@ -19976,16 +20013,16 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { * else: */ __pyx_t_1 = ((__pyx_v_msg != NULL) != 0); - if (__pyx_t_1) { + if (unlikely(__pyx_t_1)) { - /* "View.MemoryView":1249 + /* "View.MemoryView":1259 * cdef int _err(object error, char *msg) except -1 with gil: * if msg != NULL: * raise error(msg.decode('ascii')) # <<<<<<<<<<<<<< * else: * raise error */ - __pyx_t_3 = __Pyx_decode_c_string(__pyx_v_msg, 0, strlen(__pyx_v_msg), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1249, __pyx_L1_error) + __pyx_t_3 = __Pyx_decode_c_string(__pyx_v_msg, 0, strlen(__pyx_v_msg), NULL, NULL, PyUnicode_DecodeASCII); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 1259, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_v_error); __pyx_t_4 = __pyx_v_error; __pyx_t_5 = NULL; @@ -19999,14 +20036,14 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { } } if (!__pyx_t_5) { - __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_4, __pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1249, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_4, __pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1259, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GOTREF(__pyx_t_2); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_4)) { PyObject *__pyx_temp[2] = {__pyx_t_5, __pyx_t_3}; - __pyx_t_2 = __Pyx_PyFunction_FastCall(__pyx_t_4, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1249, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyFunction_FastCall(__pyx_t_4, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1259, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; @@ -20015,20 +20052,20 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_4)) { PyObject *__pyx_temp[2] = {__pyx_t_5, __pyx_t_3}; - __pyx_t_2 = __Pyx_PyCFunction_FastCall(__pyx_t_4, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1249, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyCFunction_FastCall(__pyx_t_4, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1259, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else #endif { - __pyx_t_6 = PyTuple_New(1+1); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 1249, __pyx_L1_error) + __pyx_t_6 = PyTuple_New(1+1); if (unlikely(!__pyx_t_6)) __PYX_ERR(2, 1259, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_GIVEREF(__pyx_t_5); PyTuple_SET_ITEM(__pyx_t_6, 0, __pyx_t_5); __pyx_t_5 = NULL; __Pyx_GIVEREF(__pyx_t_3); PyTuple_SET_ITEM(__pyx_t_6, 0+1, __pyx_t_3); __pyx_t_3 = 0; - __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_t_6, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1249, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_t_6, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(2, 1259, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; } @@ -20036,9 +20073,9 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_Raise(__pyx_t_2, 0, 0, 0); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __PYX_ERR(2, 1249, __pyx_L1_error) + __PYX_ERR(2, 1259, __pyx_L1_error) - /* "View.MemoryView":1248 + /* "View.MemoryView":1258 * @cname('__pyx_memoryview_err') * cdef int _err(object error, char *msg) except -1 with gil: * if msg != NULL: # <<<<<<<<<<<<<< @@ -20047,7 +20084,7 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { */ } - /* "View.MemoryView":1251 + /* "View.MemoryView":1261 * raise error(msg.decode('ascii')) * else: * raise error # <<<<<<<<<<<<<< @@ -20056,10 +20093,10 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { */ /*else*/ { __Pyx_Raise(__pyx_v_error, 0, 0, 0); - __PYX_ERR(2, 1251, __pyx_L1_error) + __PYX_ERR(2, 1261, __pyx_L1_error) } - /* "View.MemoryView":1247 + /* "View.MemoryView":1257 * * @cname('__pyx_memoryview_err') * cdef int _err(object error, char *msg) except -1 with gil: # <<<<<<<<<<<<<< @@ -20084,7 +20121,7 @@ static int __pyx_memoryview_err(PyObject *__pyx_v_error, char *__pyx_v_msg) { return __pyx_r; } -/* "View.MemoryView":1254 +/* "View.MemoryView":1264 * * @cname('__pyx_memoryview_copy_contents') * cdef int memoryview_copy_contents(__Pyx_memviewslice src, # <<<<<<<<<<<<<< @@ -20107,10 +20144,11 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ int __pyx_t_3; int __pyx_t_4; int __pyx_t_5; - void *__pyx_t_6; - int __pyx_t_7; + int __pyx_t_6; + void *__pyx_t_7; + int __pyx_t_8; - /* "View.MemoryView":1262 + /* "View.MemoryView":1272 * Check for overlapping memory and verify the shapes. * """ * cdef void *tmpdata = NULL # <<<<<<<<<<<<<< @@ -20119,7 +20157,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_tmpdata = NULL; - /* "View.MemoryView":1263 + /* "View.MemoryView":1273 * """ * cdef void *tmpdata = NULL * cdef size_t itemsize = src.memview.view.itemsize # <<<<<<<<<<<<<< @@ -20129,7 +20167,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_1 = __pyx_v_src.memview->view.itemsize; __pyx_v_itemsize = __pyx_t_1; - /* "View.MemoryView":1265 + /* "View.MemoryView":1275 * cdef size_t itemsize = src.memview.view.itemsize * cdef int i * cdef char order = get_best_order(&src, src_ndim) # <<<<<<<<<<<<<< @@ -20138,7 +20176,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_order = __pyx_get_best_slice_order((&__pyx_v_src), __pyx_v_src_ndim); - /* "View.MemoryView":1266 + /* "View.MemoryView":1276 * cdef int i * cdef char order = get_best_order(&src, src_ndim) * cdef bint broadcasting = False # <<<<<<<<<<<<<< @@ -20147,7 +20185,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_broadcasting = 0; - /* "View.MemoryView":1267 + /* "View.MemoryView":1277 * cdef char order = get_best_order(&src, src_ndim) * cdef bint broadcasting = False * cdef bint direct_copy = False # <<<<<<<<<<<<<< @@ -20156,7 +20194,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_direct_copy = 0; - /* "View.MemoryView":1270 + /* "View.MemoryView":1280 * cdef __Pyx_memviewslice tmp * * if src_ndim < dst_ndim: # <<<<<<<<<<<<<< @@ -20166,7 +20204,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = ((__pyx_v_src_ndim < __pyx_v_dst_ndim) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1271 + /* "View.MemoryView":1281 * * if src_ndim < dst_ndim: * broadcast_leading(&src, src_ndim, dst_ndim) # <<<<<<<<<<<<<< @@ -20175,7 +20213,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_memoryview_broadcast_leading((&__pyx_v_src), __pyx_v_src_ndim, __pyx_v_dst_ndim); - /* "View.MemoryView":1270 + /* "View.MemoryView":1280 * cdef __Pyx_memviewslice tmp * * if src_ndim < dst_ndim: # <<<<<<<<<<<<<< @@ -20185,7 +20223,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ goto __pyx_L3; } - /* "View.MemoryView":1272 + /* "View.MemoryView":1282 * if src_ndim < dst_ndim: * broadcast_leading(&src, src_ndim, dst_ndim) * elif dst_ndim < src_ndim: # <<<<<<<<<<<<<< @@ -20195,7 +20233,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = ((__pyx_v_dst_ndim < __pyx_v_src_ndim) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1273 + /* "View.MemoryView":1283 * broadcast_leading(&src, src_ndim, dst_ndim) * elif dst_ndim < src_ndim: * broadcast_leading(&dst, dst_ndim, src_ndim) # <<<<<<<<<<<<<< @@ -20204,7 +20242,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_memoryview_broadcast_leading((&__pyx_v_dst), __pyx_v_dst_ndim, __pyx_v_src_ndim); - /* "View.MemoryView":1272 + /* "View.MemoryView":1282 * if src_ndim < dst_ndim: * broadcast_leading(&src, src_ndim, dst_ndim) * elif dst_ndim < src_ndim: # <<<<<<<<<<<<<< @@ -20214,7 +20252,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ } __pyx_L3:; - /* "View.MemoryView":1275 + /* "View.MemoryView":1285 * broadcast_leading(&dst, dst_ndim, src_ndim) * * cdef int ndim = max(src_ndim, dst_ndim) # <<<<<<<<<<<<<< @@ -20230,7 +20268,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ } __pyx_v_ndim = __pyx_t_5; - /* "View.MemoryView":1277 + /* "View.MemoryView":1287 * cdef int ndim = max(src_ndim, dst_ndim) * * for i in range(ndim): # <<<<<<<<<<<<<< @@ -20238,10 +20276,11 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ * if src.shape[i] == 1: */ __pyx_t_5 = __pyx_v_ndim; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_5; __pyx_t_3+=1) { - __pyx_v_i = __pyx_t_3; + __pyx_t_3 = __pyx_t_5; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_i = __pyx_t_4; - /* "View.MemoryView":1278 + /* "View.MemoryView":1288 * * for i in range(ndim): * if src.shape[i] != dst.shape[i]: # <<<<<<<<<<<<<< @@ -20251,7 +20290,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (((__pyx_v_src.shape[__pyx_v_i]) != (__pyx_v_dst.shape[__pyx_v_i])) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1279 + /* "View.MemoryView":1289 * for i in range(ndim): * if src.shape[i] != dst.shape[i]: * if src.shape[i] == 1: # <<<<<<<<<<<<<< @@ -20261,7 +20300,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (((__pyx_v_src.shape[__pyx_v_i]) == 1) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1280 + /* "View.MemoryView":1290 * if src.shape[i] != dst.shape[i]: * if src.shape[i] == 1: * broadcasting = True # <<<<<<<<<<<<<< @@ -20270,7 +20309,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_broadcasting = 1; - /* "View.MemoryView":1281 + /* "View.MemoryView":1291 * if src.shape[i] == 1: * broadcasting = True * src.strides[i] = 0 # <<<<<<<<<<<<<< @@ -20279,7 +20318,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ (__pyx_v_src.strides[__pyx_v_i]) = 0; - /* "View.MemoryView":1279 + /* "View.MemoryView":1289 * for i in range(ndim): * if src.shape[i] != dst.shape[i]: * if src.shape[i] == 1: # <<<<<<<<<<<<<< @@ -20289,7 +20328,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ goto __pyx_L7; } - /* "View.MemoryView":1283 + /* "View.MemoryView":1293 * src.strides[i] = 0 * else: * _err_extents(i, dst.shape[i], src.shape[i]) # <<<<<<<<<<<<<< @@ -20297,11 +20336,11 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ * if src.suboffsets[i] >= 0: */ /*else*/ { - __pyx_t_4 = __pyx_memoryview_err_extents(__pyx_v_i, (__pyx_v_dst.shape[__pyx_v_i]), (__pyx_v_src.shape[__pyx_v_i])); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(2, 1283, __pyx_L1_error) + __pyx_t_6 = __pyx_memoryview_err_extents(__pyx_v_i, (__pyx_v_dst.shape[__pyx_v_i]), (__pyx_v_src.shape[__pyx_v_i])); if (unlikely(__pyx_t_6 == ((int)-1))) __PYX_ERR(2, 1293, __pyx_L1_error) } __pyx_L7:; - /* "View.MemoryView":1278 + /* "View.MemoryView":1288 * * for i in range(ndim): * if src.shape[i] != dst.shape[i]: # <<<<<<<<<<<<<< @@ -20310,7 +20349,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ } - /* "View.MemoryView":1285 + /* "View.MemoryView":1295 * _err_extents(i, dst.shape[i], src.shape[i]) * * if src.suboffsets[i] >= 0: # <<<<<<<<<<<<<< @@ -20320,16 +20359,16 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (((__pyx_v_src.suboffsets[__pyx_v_i]) >= 0) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1286 + /* "View.MemoryView":1296 * * if src.suboffsets[i] >= 0: * _err_dim(ValueError, "Dimension %d is not direct", i) # <<<<<<<<<<<<<< * * if slices_overlap(&src, &dst, ndim, itemsize): */ - __pyx_t_4 = __pyx_memoryview_err_dim(__pyx_builtin_ValueError, ((char *)"Dimension %d is not direct"), __pyx_v_i); if (unlikely(__pyx_t_4 == ((int)-1))) __PYX_ERR(2, 1286, __pyx_L1_error) + __pyx_t_6 = __pyx_memoryview_err_dim(__pyx_builtin_ValueError, ((char *)"Dimension %d is not direct"), __pyx_v_i); if (unlikely(__pyx_t_6 == ((int)-1))) __PYX_ERR(2, 1296, __pyx_L1_error) - /* "View.MemoryView":1285 + /* "View.MemoryView":1295 * _err_extents(i, dst.shape[i], src.shape[i]) * * if src.suboffsets[i] >= 0: # <<<<<<<<<<<<<< @@ -20339,7 +20378,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ } } - /* "View.MemoryView":1288 + /* "View.MemoryView":1298 * _err_dim(ValueError, "Dimension %d is not direct", i) * * if slices_overlap(&src, &dst, ndim, itemsize): # <<<<<<<<<<<<<< @@ -20349,7 +20388,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (__pyx_slices_overlap((&__pyx_v_src), (&__pyx_v_dst), __pyx_v_ndim, __pyx_v_itemsize) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1290 + /* "View.MemoryView":1300 * if slices_overlap(&src, &dst, ndim, itemsize): * * if not slice_is_contig(src, order, ndim): # <<<<<<<<<<<<<< @@ -20359,7 +20398,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = ((!(__pyx_memviewslice_is_contig(__pyx_v_src, __pyx_v_order, __pyx_v_ndim) != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1291 + /* "View.MemoryView":1301 * * if not slice_is_contig(src, order, ndim): * order = get_best_order(&dst, ndim) # <<<<<<<<<<<<<< @@ -20368,7 +20407,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_order = __pyx_get_best_slice_order((&__pyx_v_dst), __pyx_v_ndim); - /* "View.MemoryView":1290 + /* "View.MemoryView":1300 * if slices_overlap(&src, &dst, ndim, itemsize): * * if not slice_is_contig(src, order, ndim): # <<<<<<<<<<<<<< @@ -20377,17 +20416,17 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ } - /* "View.MemoryView":1293 + /* "View.MemoryView":1303 * order = get_best_order(&dst, ndim) * * tmpdata = copy_data_to_temp(&src, &tmp, order, ndim) # <<<<<<<<<<<<<< * src = tmp * */ - __pyx_t_6 = __pyx_memoryview_copy_data_to_temp((&__pyx_v_src), (&__pyx_v_tmp), __pyx_v_order, __pyx_v_ndim); if (unlikely(__pyx_t_6 == ((void *)NULL))) __PYX_ERR(2, 1293, __pyx_L1_error) - __pyx_v_tmpdata = __pyx_t_6; + __pyx_t_7 = __pyx_memoryview_copy_data_to_temp((&__pyx_v_src), (&__pyx_v_tmp), __pyx_v_order, __pyx_v_ndim); if (unlikely(__pyx_t_7 == ((void *)NULL))) __PYX_ERR(2, 1303, __pyx_L1_error) + __pyx_v_tmpdata = __pyx_t_7; - /* "View.MemoryView":1294 + /* "View.MemoryView":1304 * * tmpdata = copy_data_to_temp(&src, &tmp, order, ndim) * src = tmp # <<<<<<<<<<<<<< @@ -20396,7 +20435,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_src = __pyx_v_tmp; - /* "View.MemoryView":1288 + /* "View.MemoryView":1298 * _err_dim(ValueError, "Dimension %d is not direct", i) * * if slices_overlap(&src, &dst, ndim, itemsize): # <<<<<<<<<<<<<< @@ -20405,7 +20444,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ } - /* "View.MemoryView":1296 + /* "View.MemoryView":1306 * src = tmp * * if not broadcasting: # <<<<<<<<<<<<<< @@ -20415,7 +20454,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = ((!(__pyx_v_broadcasting != 0)) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1299 + /* "View.MemoryView":1309 * * * if slice_is_contig(src, 'C', ndim): # <<<<<<<<<<<<<< @@ -20425,7 +20464,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (__pyx_memviewslice_is_contig(__pyx_v_src, 'C', __pyx_v_ndim) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1300 + /* "View.MemoryView":1310 * * if slice_is_contig(src, 'C', ndim): * direct_copy = slice_is_contig(dst, 'C', ndim) # <<<<<<<<<<<<<< @@ -20434,7 +20473,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_direct_copy = __pyx_memviewslice_is_contig(__pyx_v_dst, 'C', __pyx_v_ndim); - /* "View.MemoryView":1299 + /* "View.MemoryView":1309 * * * if slice_is_contig(src, 'C', ndim): # <<<<<<<<<<<<<< @@ -20444,7 +20483,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ goto __pyx_L12; } - /* "View.MemoryView":1301 + /* "View.MemoryView":1311 * if slice_is_contig(src, 'C', ndim): * direct_copy = slice_is_contig(dst, 'C', ndim) * elif slice_is_contig(src, 'F', ndim): # <<<<<<<<<<<<<< @@ -20454,7 +20493,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (__pyx_memviewslice_is_contig(__pyx_v_src, 'F', __pyx_v_ndim) != 0); if (__pyx_t_2) { - /* "View.MemoryView":1302 + /* "View.MemoryView":1312 * direct_copy = slice_is_contig(dst, 'C', ndim) * elif slice_is_contig(src, 'F', ndim): * direct_copy = slice_is_contig(dst, 'F', ndim) # <<<<<<<<<<<<<< @@ -20463,7 +20502,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_v_direct_copy = __pyx_memviewslice_is_contig(__pyx_v_dst, 'F', __pyx_v_ndim); - /* "View.MemoryView":1301 + /* "View.MemoryView":1311 * if slice_is_contig(src, 'C', ndim): * direct_copy = slice_is_contig(dst, 'C', ndim) * elif slice_is_contig(src, 'F', ndim): # <<<<<<<<<<<<<< @@ -20473,7 +20512,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ } __pyx_L12:; - /* "View.MemoryView":1304 + /* "View.MemoryView":1314 * direct_copy = slice_is_contig(dst, 'F', ndim) * * if direct_copy: # <<<<<<<<<<<<<< @@ -20483,7 +20522,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_t_2 = (__pyx_v_direct_copy != 0); if (__pyx_t_2) { - /* "View.MemoryView":1306 + /* "View.MemoryView":1316 * if direct_copy: * * refcount_copying(&dst, dtype_is_object, ndim, False) # <<<<<<<<<<<<<< @@ -20492,16 +20531,16 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_memoryview_refcount_copying((&__pyx_v_dst), __pyx_v_dtype_is_object, __pyx_v_ndim, 0); - /* "View.MemoryView":1307 + /* "View.MemoryView":1317 * * refcount_copying(&dst, dtype_is_object, ndim, False) * memcpy(dst.data, src.data, slice_get_size(&src, ndim)) # <<<<<<<<<<<<<< * refcount_copying(&dst, dtype_is_object, ndim, True) * free(tmpdata) */ - memcpy(__pyx_v_dst.data, __pyx_v_src.data, __pyx_memoryview_slice_get_size((&__pyx_v_src), __pyx_v_ndim)); + (void)(memcpy(__pyx_v_dst.data, __pyx_v_src.data, __pyx_memoryview_slice_get_size((&__pyx_v_src), __pyx_v_ndim))); - /* "View.MemoryView":1308 + /* "View.MemoryView":1318 * refcount_copying(&dst, dtype_is_object, ndim, False) * memcpy(dst.data, src.data, slice_get_size(&src, ndim)) * refcount_copying(&dst, dtype_is_object, ndim, True) # <<<<<<<<<<<<<< @@ -20510,7 +20549,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_memoryview_refcount_copying((&__pyx_v_dst), __pyx_v_dtype_is_object, __pyx_v_ndim, 1); - /* "View.MemoryView":1309 + /* "View.MemoryView":1319 * memcpy(dst.data, src.data, slice_get_size(&src, ndim)) * refcount_copying(&dst, dtype_is_object, ndim, True) * free(tmpdata) # <<<<<<<<<<<<<< @@ -20519,7 +20558,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ free(__pyx_v_tmpdata); - /* "View.MemoryView":1310 + /* "View.MemoryView":1320 * refcount_copying(&dst, dtype_is_object, ndim, True) * free(tmpdata) * return 0 # <<<<<<<<<<<<<< @@ -20529,7 +20568,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_r = 0; goto __pyx_L0; - /* "View.MemoryView":1304 + /* "View.MemoryView":1314 * direct_copy = slice_is_contig(dst, 'F', ndim) * * if direct_copy: # <<<<<<<<<<<<<< @@ -20538,7 +20577,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ } - /* "View.MemoryView":1296 + /* "View.MemoryView":1306 * src = tmp * * if not broadcasting: # <<<<<<<<<<<<<< @@ -20547,7 +20586,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ } - /* "View.MemoryView":1312 + /* "View.MemoryView":1322 * return 0 * * if order == 'F' == get_best_order(&dst, ndim): # <<<<<<<<<<<<<< @@ -20558,28 +20597,28 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ if (__pyx_t_2) { __pyx_t_2 = ('F' == __pyx_get_best_slice_order((&__pyx_v_dst), __pyx_v_ndim)); } - __pyx_t_7 = (__pyx_t_2 != 0); - if (__pyx_t_7) { + __pyx_t_8 = (__pyx_t_2 != 0); + if (__pyx_t_8) { - /* "View.MemoryView":1315 + /* "View.MemoryView":1325 * * * transpose_memslice(&src) # <<<<<<<<<<<<<< * transpose_memslice(&dst) * */ - __pyx_t_5 = __pyx_memslice_transpose((&__pyx_v_src)); if (unlikely(__pyx_t_5 == ((int)0))) __PYX_ERR(2, 1315, __pyx_L1_error) + __pyx_t_5 = __pyx_memslice_transpose((&__pyx_v_src)); if (unlikely(__pyx_t_5 == ((int)0))) __PYX_ERR(2, 1325, __pyx_L1_error) - /* "View.MemoryView":1316 + /* "View.MemoryView":1326 * * transpose_memslice(&src) * transpose_memslice(&dst) # <<<<<<<<<<<<<< * * refcount_copying(&dst, dtype_is_object, ndim, False) */ - __pyx_t_5 = __pyx_memslice_transpose((&__pyx_v_dst)); if (unlikely(__pyx_t_5 == ((int)0))) __PYX_ERR(2, 1316, __pyx_L1_error) + __pyx_t_5 = __pyx_memslice_transpose((&__pyx_v_dst)); if (unlikely(__pyx_t_5 == ((int)0))) __PYX_ERR(2, 1326, __pyx_L1_error) - /* "View.MemoryView":1312 + /* "View.MemoryView":1322 * return 0 * * if order == 'F' == get_best_order(&dst, ndim): # <<<<<<<<<<<<<< @@ -20588,7 +20627,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ } - /* "View.MemoryView":1318 + /* "View.MemoryView":1328 * transpose_memslice(&dst) * * refcount_copying(&dst, dtype_is_object, ndim, False) # <<<<<<<<<<<<<< @@ -20597,7 +20636,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_memoryview_refcount_copying((&__pyx_v_dst), __pyx_v_dtype_is_object, __pyx_v_ndim, 0); - /* "View.MemoryView":1319 + /* "View.MemoryView":1329 * * refcount_copying(&dst, dtype_is_object, ndim, False) * copy_strided_to_strided(&src, &dst, ndim, itemsize) # <<<<<<<<<<<<<< @@ -20606,7 +20645,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ copy_strided_to_strided((&__pyx_v_src), (&__pyx_v_dst), __pyx_v_ndim, __pyx_v_itemsize); - /* "View.MemoryView":1320 + /* "View.MemoryView":1330 * refcount_copying(&dst, dtype_is_object, ndim, False) * copy_strided_to_strided(&src, &dst, ndim, itemsize) * refcount_copying(&dst, dtype_is_object, ndim, True) # <<<<<<<<<<<<<< @@ -20615,7 +20654,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ __pyx_memoryview_refcount_copying((&__pyx_v_dst), __pyx_v_dtype_is_object, __pyx_v_ndim, 1); - /* "View.MemoryView":1322 + /* "View.MemoryView":1332 * refcount_copying(&dst, dtype_is_object, ndim, True) * * free(tmpdata) # <<<<<<<<<<<<<< @@ -20624,7 +20663,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ */ free(__pyx_v_tmpdata); - /* "View.MemoryView":1323 + /* "View.MemoryView":1333 * * free(tmpdata) * return 0 # <<<<<<<<<<<<<< @@ -20634,7 +20673,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ __pyx_r = 0; goto __pyx_L0; - /* "View.MemoryView":1254 + /* "View.MemoryView":1264 * * @cname('__pyx_memoryview_copy_contents') * cdef int memoryview_copy_contents(__Pyx_memviewslice src, # <<<<<<<<<<<<<< @@ -20658,7 +20697,7 @@ static int __pyx_memoryview_copy_contents(__Pyx_memviewslice __pyx_v_src, __Pyx_ return __pyx_r; } -/* "View.MemoryView":1326 +/* "View.MemoryView":1336 * * @cname('__pyx_memoryview_broadcast_leading') * cdef void broadcast_leading(__Pyx_memviewslice *mslice, # <<<<<<<<<<<<<< @@ -20671,8 +20710,9 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic int __pyx_v_offset; int __pyx_t_1; int __pyx_t_2; + int __pyx_t_3; - /* "View.MemoryView":1330 + /* "View.MemoryView":1340 * int ndim_other) nogil: * cdef int i * cdef int offset = ndim_other - ndim # <<<<<<<<<<<<<< @@ -20681,17 +20721,17 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic */ __pyx_v_offset = (__pyx_v_ndim_other - __pyx_v_ndim); - /* "View.MemoryView":1332 + /* "View.MemoryView":1342 * cdef int offset = ndim_other - ndim * * for i in range(ndim - 1, -1, -1): # <<<<<<<<<<<<<< * mslice.shape[i + offset] = mslice.shape[i] * mslice.strides[i + offset] = mslice.strides[i] */ - for (__pyx_t_1 = (__pyx_v_ndim - 1); __pyx_t_1 > -1L; __pyx_t_1-=1) { + for (__pyx_t_1 = (__pyx_v_ndim - 1); __pyx_t_1 > -1; __pyx_t_1-=1) { __pyx_v_i = __pyx_t_1; - /* "View.MemoryView":1333 + /* "View.MemoryView":1343 * * for i in range(ndim - 1, -1, -1): * mslice.shape[i + offset] = mslice.shape[i] # <<<<<<<<<<<<<< @@ -20700,7 +20740,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic */ (__pyx_v_mslice->shape[(__pyx_v_i + __pyx_v_offset)]) = (__pyx_v_mslice->shape[__pyx_v_i]); - /* "View.MemoryView":1334 + /* "View.MemoryView":1344 * for i in range(ndim - 1, -1, -1): * mslice.shape[i + offset] = mslice.shape[i] * mslice.strides[i + offset] = mslice.strides[i] # <<<<<<<<<<<<<< @@ -20709,7 +20749,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic */ (__pyx_v_mslice->strides[(__pyx_v_i + __pyx_v_offset)]) = (__pyx_v_mslice->strides[__pyx_v_i]); - /* "View.MemoryView":1335 + /* "View.MemoryView":1345 * mslice.shape[i + offset] = mslice.shape[i] * mslice.strides[i + offset] = mslice.strides[i] * mslice.suboffsets[i + offset] = mslice.suboffsets[i] # <<<<<<<<<<<<<< @@ -20719,7 +20759,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic (__pyx_v_mslice->suboffsets[(__pyx_v_i + __pyx_v_offset)]) = (__pyx_v_mslice->suboffsets[__pyx_v_i]); } - /* "View.MemoryView":1337 + /* "View.MemoryView":1347 * mslice.suboffsets[i + offset] = mslice.suboffsets[i] * * for i in range(offset): # <<<<<<<<<<<<<< @@ -20727,10 +20767,11 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic * mslice.strides[i] = mslice.strides[0] */ __pyx_t_1 = __pyx_v_offset; - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; - /* "View.MemoryView":1338 + /* "View.MemoryView":1348 * * for i in range(offset): * mslice.shape[i] = 1 # <<<<<<<<<<<<<< @@ -20739,7 +20780,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic */ (__pyx_v_mslice->shape[__pyx_v_i]) = 1; - /* "View.MemoryView":1339 + /* "View.MemoryView":1349 * for i in range(offset): * mslice.shape[i] = 1 * mslice.strides[i] = mslice.strides[0] # <<<<<<<<<<<<<< @@ -20748,7 +20789,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic */ (__pyx_v_mslice->strides[__pyx_v_i]) = (__pyx_v_mslice->strides[0]); - /* "View.MemoryView":1340 + /* "View.MemoryView":1350 * mslice.shape[i] = 1 * mslice.strides[i] = mslice.strides[0] * mslice.suboffsets[i] = -1 # <<<<<<<<<<<<<< @@ -20758,7 +20799,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic (__pyx_v_mslice->suboffsets[__pyx_v_i]) = -1L; } - /* "View.MemoryView":1326 + /* "View.MemoryView":1336 * * @cname('__pyx_memoryview_broadcast_leading') * cdef void broadcast_leading(__Pyx_memviewslice *mslice, # <<<<<<<<<<<<<< @@ -20769,7 +20810,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic /* function exit code */ } -/* "View.MemoryView":1348 +/* "View.MemoryView":1358 * * @cname('__pyx_memoryview_refcount_copying') * cdef void refcount_copying(__Pyx_memviewslice *dst, bint dtype_is_object, # <<<<<<<<<<<<<< @@ -20780,7 +20821,7 @@ static void __pyx_memoryview_broadcast_leading(__Pyx_memviewslice *__pyx_v_mslic static void __pyx_memoryview_refcount_copying(__Pyx_memviewslice *__pyx_v_dst, int __pyx_v_dtype_is_object, int __pyx_v_ndim, int __pyx_v_inc) { int __pyx_t_1; - /* "View.MemoryView":1352 + /* "View.MemoryView":1362 * * * if dtype_is_object: # <<<<<<<<<<<<<< @@ -20790,7 +20831,7 @@ static void __pyx_memoryview_refcount_copying(__Pyx_memviewslice *__pyx_v_dst, i __pyx_t_1 = (__pyx_v_dtype_is_object != 0); if (__pyx_t_1) { - /* "View.MemoryView":1353 + /* "View.MemoryView":1363 * * if dtype_is_object: * refcount_objects_in_slice_with_gil(dst.data, dst.shape, # <<<<<<<<<<<<<< @@ -20799,7 +20840,7 @@ static void __pyx_memoryview_refcount_copying(__Pyx_memviewslice *__pyx_v_dst, i */ __pyx_memoryview_refcount_objects_in_slice_with_gil(__pyx_v_dst->data, __pyx_v_dst->shape, __pyx_v_dst->strides, __pyx_v_ndim, __pyx_v_inc); - /* "View.MemoryView":1352 + /* "View.MemoryView":1362 * * * if dtype_is_object: # <<<<<<<<<<<<<< @@ -20808,7 +20849,7 @@ static void __pyx_memoryview_refcount_copying(__Pyx_memviewslice *__pyx_v_dst, i */ } - /* "View.MemoryView":1348 + /* "View.MemoryView":1358 * * @cname('__pyx_memoryview_refcount_copying') * cdef void refcount_copying(__Pyx_memviewslice *dst, bint dtype_is_object, # <<<<<<<<<<<<<< @@ -20819,7 +20860,7 @@ static void __pyx_memoryview_refcount_copying(__Pyx_memviewslice *__pyx_v_dst, i /* function exit code */ } -/* "View.MemoryView":1357 +/* "View.MemoryView":1367 * * @cname('__pyx_memoryview_refcount_objects_in_slice_with_gil') * cdef void refcount_objects_in_slice_with_gil(char *data, Py_ssize_t *shape, # <<<<<<<<<<<<<< @@ -20834,7 +20875,7 @@ static void __pyx_memoryview_refcount_objects_in_slice_with_gil(char *__pyx_v_da #endif __Pyx_RefNannySetupContext("refcount_objects_in_slice_with_gil", 0); - /* "View.MemoryView":1360 + /* "View.MemoryView":1370 * Py_ssize_t *strides, int ndim, * bint inc) with gil: * refcount_objects_in_slice(data, shape, strides, ndim, inc) # <<<<<<<<<<<<<< @@ -20843,7 +20884,7 @@ static void __pyx_memoryview_refcount_objects_in_slice_with_gil(char *__pyx_v_da */ __pyx_memoryview_refcount_objects_in_slice(__pyx_v_data, __pyx_v_shape, __pyx_v_strides, __pyx_v_ndim, __pyx_v_inc); - /* "View.MemoryView":1357 + /* "View.MemoryView":1367 * * @cname('__pyx_memoryview_refcount_objects_in_slice_with_gil') * cdef void refcount_objects_in_slice_with_gil(char *data, Py_ssize_t *shape, # <<<<<<<<<<<<<< @@ -20858,7 +20899,7 @@ static void __pyx_memoryview_refcount_objects_in_slice_with_gil(char *__pyx_v_da #endif } -/* "View.MemoryView":1363 +/* "View.MemoryView":1373 * * @cname('__pyx_memoryview_refcount_objects_in_slice') * cdef void refcount_objects_in_slice(char *data, Py_ssize_t *shape, # <<<<<<<<<<<<<< @@ -20871,10 +20912,11 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss __Pyx_RefNannyDeclarations Py_ssize_t __pyx_t_1; Py_ssize_t __pyx_t_2; - int __pyx_t_3; + Py_ssize_t __pyx_t_3; + int __pyx_t_4; __Pyx_RefNannySetupContext("refcount_objects_in_slice", 0); - /* "View.MemoryView":1367 + /* "View.MemoryView":1377 * cdef Py_ssize_t i * * for i in range(shape[0]): # <<<<<<<<<<<<<< @@ -20882,30 +20924,31 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss * if inc: */ __pyx_t_1 = (__pyx_v_shape[0]); - for (__pyx_t_2 = 0; __pyx_t_2 < __pyx_t_1; __pyx_t_2+=1) { - __pyx_v_i = __pyx_t_2; + __pyx_t_2 = __pyx_t_1; + for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { + __pyx_v_i = __pyx_t_3; - /* "View.MemoryView":1368 + /* "View.MemoryView":1378 * * for i in range(shape[0]): * if ndim == 1: # <<<<<<<<<<<<<< * if inc: * Py_INCREF(( data)[0]) */ - __pyx_t_3 = ((__pyx_v_ndim == 1) != 0); - if (__pyx_t_3) { + __pyx_t_4 = ((__pyx_v_ndim == 1) != 0); + if (__pyx_t_4) { - /* "View.MemoryView":1369 + /* "View.MemoryView":1379 * for i in range(shape[0]): * if ndim == 1: * if inc: # <<<<<<<<<<<<<< * Py_INCREF(( data)[0]) * else: */ - __pyx_t_3 = (__pyx_v_inc != 0); - if (__pyx_t_3) { + __pyx_t_4 = (__pyx_v_inc != 0); + if (__pyx_t_4) { - /* "View.MemoryView":1370 + /* "View.MemoryView":1380 * if ndim == 1: * if inc: * Py_INCREF(( data)[0]) # <<<<<<<<<<<<<< @@ -20914,7 +20957,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss */ Py_INCREF((((PyObject **)__pyx_v_data)[0])); - /* "View.MemoryView":1369 + /* "View.MemoryView":1379 * for i in range(shape[0]): * if ndim == 1: * if inc: # <<<<<<<<<<<<<< @@ -20924,7 +20967,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss goto __pyx_L6; } - /* "View.MemoryView":1372 + /* "View.MemoryView":1382 * Py_INCREF(( data)[0]) * else: * Py_DECREF(( data)[0]) # <<<<<<<<<<<<<< @@ -20936,7 +20979,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss } __pyx_L6:; - /* "View.MemoryView":1368 + /* "View.MemoryView":1378 * * for i in range(shape[0]): * if ndim == 1: # <<<<<<<<<<<<<< @@ -20946,7 +20989,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss goto __pyx_L5; } - /* "View.MemoryView":1374 + /* "View.MemoryView":1384 * Py_DECREF(( data)[0]) * else: * refcount_objects_in_slice(data, shape + 1, strides + 1, # <<<<<<<<<<<<<< @@ -20955,7 +20998,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss */ /*else*/ { - /* "View.MemoryView":1375 + /* "View.MemoryView":1385 * else: * refcount_objects_in_slice(data, shape + 1, strides + 1, * ndim - 1, inc) # <<<<<<<<<<<<<< @@ -20966,7 +21009,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss } __pyx_L5:; - /* "View.MemoryView":1377 + /* "View.MemoryView":1387 * ndim - 1, inc) * * data += strides[0] # <<<<<<<<<<<<<< @@ -20976,7 +21019,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss __pyx_v_data = (__pyx_v_data + (__pyx_v_strides[0])); } - /* "View.MemoryView":1363 + /* "View.MemoryView":1373 * * @cname('__pyx_memoryview_refcount_objects_in_slice') * cdef void refcount_objects_in_slice(char *data, Py_ssize_t *shape, # <<<<<<<<<<<<<< @@ -20988,7 +21031,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss __Pyx_RefNannyFinishContext(); } -/* "View.MemoryView":1383 +/* "View.MemoryView":1393 * * @cname('__pyx_memoryview_slice_assign_scalar') * cdef void slice_assign_scalar(__Pyx_memviewslice *dst, int ndim, # <<<<<<<<<<<<<< @@ -20998,7 +21041,7 @@ static void __pyx_memoryview_refcount_objects_in_slice(char *__pyx_v_data, Py_ss static void __pyx_memoryview_slice_assign_scalar(__Pyx_memviewslice *__pyx_v_dst, int __pyx_v_ndim, size_t __pyx_v_itemsize, void *__pyx_v_item, int __pyx_v_dtype_is_object) { - /* "View.MemoryView":1386 + /* "View.MemoryView":1396 * size_t itemsize, void *item, * bint dtype_is_object) nogil: * refcount_copying(dst, dtype_is_object, ndim, False) # <<<<<<<<<<<<<< @@ -21007,7 +21050,7 @@ static void __pyx_memoryview_slice_assign_scalar(__Pyx_memviewslice *__pyx_v_dst */ __pyx_memoryview_refcount_copying(__pyx_v_dst, __pyx_v_dtype_is_object, __pyx_v_ndim, 0); - /* "View.MemoryView":1387 + /* "View.MemoryView":1397 * bint dtype_is_object) nogil: * refcount_copying(dst, dtype_is_object, ndim, False) * _slice_assign_scalar(dst.data, dst.shape, dst.strides, ndim, # <<<<<<<<<<<<<< @@ -21016,7 +21059,7 @@ static void __pyx_memoryview_slice_assign_scalar(__Pyx_memviewslice *__pyx_v_dst */ __pyx_memoryview__slice_assign_scalar(__pyx_v_dst->data, __pyx_v_dst->shape, __pyx_v_dst->strides, __pyx_v_ndim, __pyx_v_itemsize, __pyx_v_item); - /* "View.MemoryView":1389 + /* "View.MemoryView":1399 * _slice_assign_scalar(dst.data, dst.shape, dst.strides, ndim, * itemsize, item) * refcount_copying(dst, dtype_is_object, ndim, True) # <<<<<<<<<<<<<< @@ -21025,7 +21068,7 @@ static void __pyx_memoryview_slice_assign_scalar(__Pyx_memviewslice *__pyx_v_dst */ __pyx_memoryview_refcount_copying(__pyx_v_dst, __pyx_v_dtype_is_object, __pyx_v_ndim, 1); - /* "View.MemoryView":1383 + /* "View.MemoryView":1393 * * @cname('__pyx_memoryview_slice_assign_scalar') * cdef void slice_assign_scalar(__Pyx_memviewslice *dst, int ndim, # <<<<<<<<<<<<<< @@ -21036,7 +21079,7 @@ static void __pyx_memoryview_slice_assign_scalar(__Pyx_memviewslice *__pyx_v_dst /* function exit code */ } -/* "View.MemoryView":1393 +/* "View.MemoryView":1403 * * @cname('__pyx_memoryview__slice_assign_scalar') * cdef void _slice_assign_scalar(char *data, Py_ssize_t *shape, # <<<<<<<<<<<<<< @@ -21051,8 +21094,9 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t int __pyx_t_1; Py_ssize_t __pyx_t_2; Py_ssize_t __pyx_t_3; + Py_ssize_t __pyx_t_4; - /* "View.MemoryView":1397 + /* "View.MemoryView":1407 * size_t itemsize, void *item) nogil: * cdef Py_ssize_t i * cdef Py_ssize_t stride = strides[0] # <<<<<<<<<<<<<< @@ -21061,7 +21105,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t */ __pyx_v_stride = (__pyx_v_strides[0]); - /* "View.MemoryView":1398 + /* "View.MemoryView":1408 * cdef Py_ssize_t i * cdef Py_ssize_t stride = strides[0] * cdef Py_ssize_t extent = shape[0] # <<<<<<<<<<<<<< @@ -21070,7 +21114,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t */ __pyx_v_extent = (__pyx_v_shape[0]); - /* "View.MemoryView":1400 + /* "View.MemoryView":1410 * cdef Py_ssize_t extent = shape[0] * * if ndim == 1: # <<<<<<<<<<<<<< @@ -21080,7 +21124,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t __pyx_t_1 = ((__pyx_v_ndim == 1) != 0); if (__pyx_t_1) { - /* "View.MemoryView":1401 + /* "View.MemoryView":1411 * * if ndim == 1: * for i in range(extent): # <<<<<<<<<<<<<< @@ -21088,19 +21132,20 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t * data += stride */ __pyx_t_2 = __pyx_v_extent; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { - __pyx_v_i = __pyx_t_3; + __pyx_t_3 = __pyx_t_2; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_i = __pyx_t_4; - /* "View.MemoryView":1402 + /* "View.MemoryView":1412 * if ndim == 1: * for i in range(extent): * memcpy(data, item, itemsize) # <<<<<<<<<<<<<< * data += stride * else: */ - memcpy(__pyx_v_data, __pyx_v_item, __pyx_v_itemsize); + (void)(memcpy(__pyx_v_data, __pyx_v_item, __pyx_v_itemsize)); - /* "View.MemoryView":1403 + /* "View.MemoryView":1413 * for i in range(extent): * memcpy(data, item, itemsize) * data += stride # <<<<<<<<<<<<<< @@ -21110,7 +21155,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t __pyx_v_data = (__pyx_v_data + __pyx_v_stride); } - /* "View.MemoryView":1400 + /* "View.MemoryView":1410 * cdef Py_ssize_t extent = shape[0] * * if ndim == 1: # <<<<<<<<<<<<<< @@ -21120,7 +21165,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t goto __pyx_L3; } - /* "View.MemoryView":1405 + /* "View.MemoryView":1415 * data += stride * else: * for i in range(extent): # <<<<<<<<<<<<<< @@ -21129,10 +21174,11 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t */ /*else*/ { __pyx_t_2 = __pyx_v_extent; - for (__pyx_t_3 = 0; __pyx_t_3 < __pyx_t_2; __pyx_t_3+=1) { - __pyx_v_i = __pyx_t_3; + __pyx_t_3 = __pyx_t_2; + for (__pyx_t_4 = 0; __pyx_t_4 < __pyx_t_3; __pyx_t_4+=1) { + __pyx_v_i = __pyx_t_4; - /* "View.MemoryView":1406 + /* "View.MemoryView":1416 * else: * for i in range(extent): * _slice_assign_scalar(data, shape + 1, strides + 1, # <<<<<<<<<<<<<< @@ -21141,7 +21187,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t */ __pyx_memoryview__slice_assign_scalar(__pyx_v_data, (__pyx_v_shape + 1), (__pyx_v_strides + 1), (__pyx_v_ndim - 1), __pyx_v_itemsize, __pyx_v_item); - /* "View.MemoryView":1408 + /* "View.MemoryView":1418 * _slice_assign_scalar(data, shape + 1, strides + 1, * ndim - 1, itemsize, item) * data += stride # <<<<<<<<<<<<<< @@ -21153,7 +21199,7 @@ static void __pyx_memoryview__slice_assign_scalar(char *__pyx_v_data, Py_ssize_t } __pyx_L3:; - /* "View.MemoryView":1393 + /* "View.MemoryView":1403 * * @cname('__pyx_memoryview__slice_assign_scalar') * cdef void _slice_assign_scalar(char *data, Py_ssize_t *shape, # <<<<<<<<<<<<<< @@ -21199,17 +21245,17 @@ static PyObject *__pyx_pw_15View_dot_MemoryView_1__pyx_unpickle_Enum(PyObject *_ kw_args = PyDict_Size(__pyx_kwds); switch (pos_args) { case 0: - if (likely((values[0] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_pyx_type)) != 0)) kw_args--; + if (likely((values[0] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_pyx_type)) != 0)) kw_args--; else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: - if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_pyx_checksum)) != 0)) kw_args--; + if (likely((values[1] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_pyx_checksum)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_unpickle_Enum", 1, 3, 3, 1); __PYX_ERR(2, 1, __pyx_L3_error) } CYTHON_FALLTHROUGH; case 2: - if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_pyx_state)) != 0)) kw_args--; + if (likely((values[2] = __Pyx_PyDict_GetItemStr(__pyx_kwds, __pyx_n_s_pyx_state)) != 0)) kw_args--; else { __Pyx_RaiseArgtupleInvalid("__pyx_unpickle_Enum", 1, 3, 3, 2); __PYX_ERR(2, 1, __pyx_L3_error) } @@ -21702,7 +21748,7 @@ static int __pyx_mp_ass_subscript_array(PyObject *o, PyObject *i, PyObject *v) { } static PyObject *__pyx_tp_getattro_array(PyObject *o, PyObject *n) { - PyObject *v = PyObject_GenericGetAttr(o, n); + PyObject *v = __Pyx_PyObject_GenericGetAttr(o, n); if (!v && PyErr_ExceptionMatches(PyExc_AttributeError)) { PyErr_Clear(); v = __pyx_array___getattr__(o, n); @@ -22353,6 +22399,8 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {&__pyx_n_s_ASCII, __pyx_k_ASCII, sizeof(__pyx_k_ASCII), 0, 0, 1, 1}, {&__pyx_kp_s_Buffer_view_does_not_expose_stri, __pyx_k_Buffer_view_does_not_expose_stri, sizeof(__pyx_k_Buffer_view_does_not_expose_stri), 0, 0, 1, 0}, {&__pyx_kp_s_Can_only_create_a_buffer_that_is, __pyx_k_Can_only_create_a_buffer_that_is, sizeof(__pyx_k_Can_only_create_a_buffer_that_is), 0, 0, 1, 0}, + {&__pyx_kp_s_Cannot_assign_to_read_only_memor, __pyx_k_Cannot_assign_to_read_only_memor, sizeof(__pyx_k_Cannot_assign_to_read_only_memor), 0, 0, 1, 0}, + {&__pyx_kp_s_Cannot_create_writable_memory_vi, __pyx_k_Cannot_create_writable_memory_vi, sizeof(__pyx_k_Cannot_create_writable_memory_vi), 0, 0, 1, 0}, {&__pyx_kp_s_Cannot_index_with_type_s, __pyx_k_Cannot_index_with_type_s, sizeof(__pyx_k_Cannot_index_with_type_s), 0, 0, 1, 0}, {&__pyx_n_s_Ellipsis, __pyx_k_Ellipsis, sizeof(__pyx_k_Ellipsis), 0, 0, 1, 1}, {&__pyx_kp_s_Empty_shape_tuple_for_cython_arr, __pyx_k_Empty_shape_tuple_for_cython_arr, sizeof(__pyx_k_Empty_shape_tuple_for_cython_arr), 0, 0, 1, 0}, @@ -22486,13 +22534,13 @@ static int __Pyx_InitCachedBuiltins(void) { __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(0, 31, __pyx_L1_error) __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 68, __pyx_L1_error) __pyx_builtin_TypeError = __Pyx_GetBuiltinName(__pyx_n_s_TypeError); if (!__pyx_builtin_TypeError) __PYX_ERR(0, 282, __pyx_L1_error) - __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 823, __pyx_L1_error) - __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(1, 1013, __pyx_L1_error) - __pyx_builtin_MemoryError = __Pyx_GetBuiltinName(__pyx_n_s_MemoryError); if (!__pyx_builtin_MemoryError) __PYX_ERR(2, 146, __pyx_L1_error) - __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(2, 149, __pyx_L1_error) - __pyx_builtin_Ellipsis = __Pyx_GetBuiltinName(__pyx_n_s_Ellipsis); if (!__pyx_builtin_Ellipsis) __PYX_ERR(2, 398, __pyx_L1_error) - __pyx_builtin_id = __Pyx_GetBuiltinName(__pyx_n_s_id); if (!__pyx_builtin_id) __PYX_ERR(2, 601, __pyx_L1_error) - __pyx_builtin_IndexError = __Pyx_GetBuiltinName(__pyx_n_s_IndexError); if (!__pyx_builtin_IndexError) __PYX_ERR(2, 820, __pyx_L1_error) + __pyx_builtin_RuntimeError = __Pyx_GetBuiltinName(__pyx_n_s_RuntimeError); if (!__pyx_builtin_RuntimeError) __PYX_ERR(1, 810, __pyx_L1_error) + __pyx_builtin_ImportError = __Pyx_GetBuiltinName(__pyx_n_s_ImportError); if (!__pyx_builtin_ImportError) __PYX_ERR(1, 1000, __pyx_L1_error) + __pyx_builtin_MemoryError = __Pyx_GetBuiltinName(__pyx_n_s_MemoryError); if (!__pyx_builtin_MemoryError) __PYX_ERR(2, 147, __pyx_L1_error) + __pyx_builtin_enumerate = __Pyx_GetBuiltinName(__pyx_n_s_enumerate); if (!__pyx_builtin_enumerate) __PYX_ERR(2, 150, __pyx_L1_error) + __pyx_builtin_Ellipsis = __Pyx_GetBuiltinName(__pyx_n_s_Ellipsis); if (!__pyx_builtin_Ellipsis) __PYX_ERR(2, 399, __pyx_L1_error) + __pyx_builtin_id = __Pyx_GetBuiltinName(__pyx_n_s_id); if (!__pyx_builtin_id) __PYX_ERR(2, 608, __pyx_L1_error) + __pyx_builtin_IndexError = __Pyx_GetBuiltinName(__pyx_n_s_IndexError); if (!__pyx_builtin_IndexError) __PYX_ERR(2, 827, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; @@ -22533,166 +22581,166 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_GOTREF(__pyx_tuple__8); __Pyx_GIVEREF(__pyx_tuple__8); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":235 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":229 * if ((flags & pybuf.PyBUF_C_CONTIGUOUS == pybuf.PyBUF_C_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_C_CONTIGUOUS)): * raise ValueError(u"ndarray is not C contiguous") # <<<<<<<<<<<<<< * * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) */ - __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 235, __pyx_L1_error) + __pyx_tuple__9 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_C_contiguous); if (unlikely(!__pyx_tuple__9)) __PYX_ERR(1, 229, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__9); __Pyx_GIVEREF(__pyx_tuple__9); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":239 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":233 * if ((flags & pybuf.PyBUF_F_CONTIGUOUS == pybuf.PyBUF_F_CONTIGUOUS) * and not PyArray_CHKFLAGS(self, NPY_F_CONTIGUOUS)): * raise ValueError(u"ndarray is not Fortran contiguous") # <<<<<<<<<<<<<< * * info.buf = PyArray_DATA(self) */ - __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 239, __pyx_L1_error) + __pyx_tuple__10 = PyTuple_Pack(1, __pyx_kp_u_ndarray_is_not_Fortran_contiguou); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(1, 233, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__10); __Pyx_GIVEREF(__pyx_tuple__10); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":276 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":263 * if ((descr.byteorder == c'>' and little_endian) or * (descr.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * if t == NPY_BYTE: f = "b" * elif t == NPY_UBYTE: f = "B" */ - __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 276, __pyx_L1_error) + __pyx_tuple__11 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__11)) __PYX_ERR(1, 263, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__11); __Pyx_GIVEREF(__pyx_tuple__11); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":823 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":810 * * if (end - f) - (new_offset - offset[0]) < 15: * raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd") # <<<<<<<<<<<<<< * * if ((child.byteorder == c'>' and little_endian) or */ - __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 823, __pyx_L1_error) + __pyx_tuple__12 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(1, 810, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__12); __Pyx_GIVEREF(__pyx_tuple__12); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":827 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":814 * if ((child.byteorder == c'>' and little_endian) or * (child.byteorder == c'<' and not little_endian)): * raise ValueError(u"Non-native byte order not supported") # <<<<<<<<<<<<<< * # One could encode it in the format string and have Cython * # complain instead, BUT: < and > in format strings also imply */ - __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 827, __pyx_L1_error) + __pyx_tuple__13 = PyTuple_Pack(1, __pyx_kp_u_Non_native_byte_order_not_suppor); if (unlikely(!__pyx_tuple__13)) __PYX_ERR(1, 814, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__13); __Pyx_GIVEREF(__pyx_tuple__13); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":847 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":834 * t = child.type_num * if end - f < 5: * raise RuntimeError(u"Format string allocated too short.") # <<<<<<<<<<<<<< * * # Until ticket #99 is fixed, use integers to avoid warnings */ - __pyx_tuple__14 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__14)) __PYX_ERR(1, 847, __pyx_L1_error) + __pyx_tuple__14 = PyTuple_Pack(1, __pyx_kp_u_Format_string_allocated_too_shor_2); if (unlikely(!__pyx_tuple__14)) __PYX_ERR(1, 834, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__14); __Pyx_GIVEREF(__pyx_tuple__14); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1013 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1000 * _import_array() * except Exception: * raise ImportError("numpy.core.multiarray failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_umath() except -1: */ - __pyx_tuple__15 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(1, 1013, __pyx_L1_error) + __pyx_tuple__15 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_multiarray_failed_to); if (unlikely(!__pyx_tuple__15)) __PYX_ERR(1, 1000, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__15); __Pyx_GIVEREF(__pyx_tuple__15); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1019 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1006 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< * * cdef inline int import_ufunc() except -1: */ - __pyx_tuple__16 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__16)) __PYX_ERR(1, 1019, __pyx_L1_error) + __pyx_tuple__16 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__16)) __PYX_ERR(1, 1006, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__16); __Pyx_GIVEREF(__pyx_tuple__16); - /* "../../.local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1025 + /* "../../.virtualenvs/math/local/lib/python2.7/site-packages/Cython/Includes/numpy/__init__.pxd":1012 * _import_umath() * except Exception: * raise ImportError("numpy.core.umath failed to import") # <<<<<<<<<<<<<< */ - __pyx_tuple__17 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__17)) __PYX_ERR(1, 1025, __pyx_L1_error) + __pyx_tuple__17 = PyTuple_Pack(1, __pyx_kp_s_numpy_core_umath_failed_to_impor); if (unlikely(!__pyx_tuple__17)) __PYX_ERR(1, 1012, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__17); __Pyx_GIVEREF(__pyx_tuple__17); - /* "View.MemoryView":131 + /* "View.MemoryView":132 * * if not self.ndim: * raise ValueError("Empty shape tuple for cython.array") # <<<<<<<<<<<<<< * * if itemsize <= 0: */ - __pyx_tuple__18 = PyTuple_Pack(1, __pyx_kp_s_Empty_shape_tuple_for_cython_arr); if (unlikely(!__pyx_tuple__18)) __PYX_ERR(2, 131, __pyx_L1_error) + __pyx_tuple__18 = PyTuple_Pack(1, __pyx_kp_s_Empty_shape_tuple_for_cython_arr); if (unlikely(!__pyx_tuple__18)) __PYX_ERR(2, 132, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__18); __Pyx_GIVEREF(__pyx_tuple__18); - /* "View.MemoryView":134 + /* "View.MemoryView":135 * * if itemsize <= 0: * raise ValueError("itemsize <= 0 for cython.array") # <<<<<<<<<<<<<< * * if not isinstance(format, bytes): */ - __pyx_tuple__19 = PyTuple_Pack(1, __pyx_kp_s_itemsize_0_for_cython_array); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(2, 134, __pyx_L1_error) + __pyx_tuple__19 = PyTuple_Pack(1, __pyx_kp_s_itemsize_0_for_cython_array); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(2, 135, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__19); __Pyx_GIVEREF(__pyx_tuple__19); - /* "View.MemoryView":137 + /* "View.MemoryView":138 * * if not isinstance(format, bytes): * format = format.encode('ASCII') # <<<<<<<<<<<<<< * self._format = format # keep a reference to the byte string * self.format = self._format */ - __pyx_tuple__20 = PyTuple_Pack(1, __pyx_n_s_ASCII); if (unlikely(!__pyx_tuple__20)) __PYX_ERR(2, 137, __pyx_L1_error) + __pyx_tuple__20 = PyTuple_Pack(1, __pyx_n_s_ASCII); if (unlikely(!__pyx_tuple__20)) __PYX_ERR(2, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__20); __Pyx_GIVEREF(__pyx_tuple__20); - /* "View.MemoryView":146 + /* "View.MemoryView":147 * * if not self._shape: * raise MemoryError("unable to allocate shape and strides.") # <<<<<<<<<<<<<< * * */ - __pyx_tuple__21 = PyTuple_Pack(1, __pyx_kp_s_unable_to_allocate_shape_and_str); if (unlikely(!__pyx_tuple__21)) __PYX_ERR(2, 146, __pyx_L1_error) + __pyx_tuple__21 = PyTuple_Pack(1, __pyx_kp_s_unable_to_allocate_shape_and_str); if (unlikely(!__pyx_tuple__21)) __PYX_ERR(2, 147, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__21); __Pyx_GIVEREF(__pyx_tuple__21); - /* "View.MemoryView":174 + /* "View.MemoryView":175 * self.data = malloc(self.len) * if not self.data: * raise MemoryError("unable to allocate array data.") # <<<<<<<<<<<<<< * * if self.dtype_is_object: */ - __pyx_tuple__22 = PyTuple_Pack(1, __pyx_kp_s_unable_to_allocate_array_data); if (unlikely(!__pyx_tuple__22)) __PYX_ERR(2, 174, __pyx_L1_error) + __pyx_tuple__22 = PyTuple_Pack(1, __pyx_kp_s_unable_to_allocate_array_data); if (unlikely(!__pyx_tuple__22)) __PYX_ERR(2, 175, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__22); __Pyx_GIVEREF(__pyx_tuple__22); - /* "View.MemoryView":190 + /* "View.MemoryView":191 * bufmode = PyBUF_F_CONTIGUOUS | PyBUF_ANY_CONTIGUOUS * if not (flags & bufmode): * raise ValueError("Can only create a buffer that is contiguous in memory.") # <<<<<<<<<<<<<< * info.buf = self.data * info.len = self.len */ - __pyx_tuple__23 = PyTuple_Pack(1, __pyx_kp_s_Can_only_create_a_buffer_that_is); if (unlikely(!__pyx_tuple__23)) __PYX_ERR(2, 190, __pyx_L1_error) + __pyx_tuple__23 = PyTuple_Pack(1, __pyx_kp_s_Can_only_create_a_buffer_that_is); if (unlikely(!__pyx_tuple__23)) __PYX_ERR(2, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__23); __Pyx_GIVEREF(__pyx_tuple__23); @@ -22715,41 +22763,63 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_GOTREF(__pyx_tuple__25); __Pyx_GIVEREF(__pyx_tuple__25); - /* "View.MemoryView":486 + /* "View.MemoryView":413 + * def __setitem__(memoryview self, object index, object value): + * if self.view.readonly: + * raise TypeError("Cannot assign to read-only memoryview") # <<<<<<<<<<<<<< + * + * have_slices, index = _unellipsify(index, self.view.ndim) + */ + __pyx_tuple__26 = PyTuple_Pack(1, __pyx_kp_s_Cannot_assign_to_read_only_memor); if (unlikely(!__pyx_tuple__26)) __PYX_ERR(2, 413, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__26); + __Pyx_GIVEREF(__pyx_tuple__26); + + /* "View.MemoryView":490 * result = struct.unpack(self.view.format, bytesitem) * except struct.error: * raise ValueError("Unable to convert item to object") # <<<<<<<<<<<<<< * else: * if len(self.view.format) == 1: */ - __pyx_tuple__26 = PyTuple_Pack(1, __pyx_kp_s_Unable_to_convert_item_to_object); if (unlikely(!__pyx_tuple__26)) __PYX_ERR(2, 486, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__26); - __Pyx_GIVEREF(__pyx_tuple__26); + __pyx_tuple__27 = PyTuple_Pack(1, __pyx_kp_s_Unable_to_convert_item_to_object); if (unlikely(!__pyx_tuple__27)) __PYX_ERR(2, 490, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__27); + __Pyx_GIVEREF(__pyx_tuple__27); - /* "View.MemoryView":558 + /* "View.MemoryView":515 + * def __getbuffer__(self, Py_buffer *info, int flags): + * if flags & PyBUF_WRITABLE and self.view.readonly: + * raise ValueError("Cannot create writable memory view from read-only memoryview") # <<<<<<<<<<<<<< + * + * if flags & PyBUF_STRIDES: + */ + __pyx_tuple__28 = PyTuple_Pack(1, __pyx_kp_s_Cannot_create_writable_memory_vi); if (unlikely(!__pyx_tuple__28)) __PYX_ERR(2, 515, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__28); + __Pyx_GIVEREF(__pyx_tuple__28); + + /* "View.MemoryView":565 * if self.view.strides == NULL: * * raise ValueError("Buffer view does not expose strides") # <<<<<<<<<<<<<< * * return tuple([stride for stride in self.view.strides[:self.view.ndim]]) */ - __pyx_tuple__27 = PyTuple_Pack(1, __pyx_kp_s_Buffer_view_does_not_expose_stri); if (unlikely(!__pyx_tuple__27)) __PYX_ERR(2, 558, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__27); - __Pyx_GIVEREF(__pyx_tuple__27); + __pyx_tuple__29 = PyTuple_Pack(1, __pyx_kp_s_Buffer_view_does_not_expose_stri); if (unlikely(!__pyx_tuple__29)) __PYX_ERR(2, 565, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__29); + __Pyx_GIVEREF(__pyx_tuple__29); - /* "View.MemoryView":565 + /* "View.MemoryView":572 * def suboffsets(self): * if self.view.suboffsets == NULL: * return (-1,) * self.view.ndim # <<<<<<<<<<<<<< * * return tuple([suboffset for suboffset in self.view.suboffsets[:self.view.ndim]]) */ - __pyx_tuple__28 = PyTuple_New(1); if (unlikely(!__pyx_tuple__28)) __PYX_ERR(2, 565, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__28); + __pyx_tuple__30 = PyTuple_New(1); if (unlikely(!__pyx_tuple__30)) __PYX_ERR(2, 572, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__30); __Pyx_INCREF(__pyx_int_neg_1); __Pyx_GIVEREF(__pyx_int_neg_1); - PyTuple_SET_ITEM(__pyx_tuple__28, 0, __pyx_int_neg_1); - __Pyx_GIVEREF(__pyx_tuple__28); + PyTuple_SET_ITEM(__pyx_tuple__30, 0, __pyx_int_neg_1); + __Pyx_GIVEREF(__pyx_tuple__30); /* "(tree fragment)":2 * def __reduce_cython__(self): @@ -22757,62 +22827,62 @@ static int __Pyx_InitCachedConstants(void) { * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") */ - __pyx_tuple__29 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__29)) __PYX_ERR(2, 2, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__29); - __Pyx_GIVEREF(__pyx_tuple__29); + __pyx_tuple__31 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__31)) __PYX_ERR(2, 2, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__31); + __Pyx_GIVEREF(__pyx_tuple__31); /* "(tree fragment)":4 * raise TypeError("no default __reduce__ due to non-trivial __cinit__") * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") # <<<<<<<<<<<<<< */ - __pyx_tuple__30 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__30)) __PYX_ERR(2, 4, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__30); - __Pyx_GIVEREF(__pyx_tuple__30); + __pyx_tuple__32 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__32)) __PYX_ERR(2, 4, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__32); + __Pyx_GIVEREF(__pyx_tuple__32); - /* "View.MemoryView":670 + /* "View.MemoryView":677 * if item is Ellipsis: * if not seen_ellipsis: * result.extend([slice(None)] * (ndim - len(tup) + 1)) # <<<<<<<<<<<<<< * seen_ellipsis = True * else: */ - __pyx_slice__31 = PySlice_New(Py_None, Py_None, Py_None); if (unlikely(!__pyx_slice__31)) __PYX_ERR(2, 670, __pyx_L1_error) - __Pyx_GOTREF(__pyx_slice__31); - __Pyx_GIVEREF(__pyx_slice__31); + __pyx_slice__33 = PySlice_New(Py_None, Py_None, Py_None); if (unlikely(!__pyx_slice__33)) __PYX_ERR(2, 677, __pyx_L1_error) + __Pyx_GOTREF(__pyx_slice__33); + __Pyx_GIVEREF(__pyx_slice__33); - /* "View.MemoryView":673 + /* "View.MemoryView":680 * seen_ellipsis = True * else: * result.append(slice(None)) # <<<<<<<<<<<<<< * have_slices = True * else: */ - __pyx_slice__32 = PySlice_New(Py_None, Py_None, Py_None); if (unlikely(!__pyx_slice__32)) __PYX_ERR(2, 673, __pyx_L1_error) - __Pyx_GOTREF(__pyx_slice__32); - __Pyx_GIVEREF(__pyx_slice__32); + __pyx_slice__34 = PySlice_New(Py_None, Py_None, Py_None); if (unlikely(!__pyx_slice__34)) __PYX_ERR(2, 680, __pyx_L1_error) + __Pyx_GOTREF(__pyx_slice__34); + __Pyx_GIVEREF(__pyx_slice__34); - /* "View.MemoryView":684 + /* "View.MemoryView":691 * nslices = ndim - len(result) * if nslices: * result.extend([slice(None)] * nslices) # <<<<<<<<<<<<<< * * return have_slices or nslices, tuple(result) */ - __pyx_slice__33 = PySlice_New(Py_None, Py_None, Py_None); if (unlikely(!__pyx_slice__33)) __PYX_ERR(2, 684, __pyx_L1_error) - __Pyx_GOTREF(__pyx_slice__33); - __Pyx_GIVEREF(__pyx_slice__33); + __pyx_slice__35 = PySlice_New(Py_None, Py_None, Py_None); if (unlikely(!__pyx_slice__35)) __PYX_ERR(2, 691, __pyx_L1_error) + __Pyx_GOTREF(__pyx_slice__35); + __Pyx_GIVEREF(__pyx_slice__35); - /* "View.MemoryView":691 + /* "View.MemoryView":698 * for suboffset in suboffsets[:ndim]: * if suboffset >= 0: * raise ValueError("Indirect dimensions not supported") # <<<<<<<<<<<<<< * * */ - __pyx_tuple__34 = PyTuple_Pack(1, __pyx_kp_s_Indirect_dimensions_not_supporte); if (unlikely(!__pyx_tuple__34)) __PYX_ERR(2, 691, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__34); - __Pyx_GIVEREF(__pyx_tuple__34); + __pyx_tuple__36 = PyTuple_Pack(1, __pyx_kp_s_Indirect_dimensions_not_supporte); if (unlikely(!__pyx_tuple__36)) __PYX_ERR(2, 698, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__36); + __Pyx_GIVEREF(__pyx_tuple__36); /* "(tree fragment)":2 * def __reduce_cython__(self): @@ -22820,18 +22890,18 @@ static int __Pyx_InitCachedConstants(void) { * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") */ - __pyx_tuple__35 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__35)) __PYX_ERR(2, 2, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__35); - __Pyx_GIVEREF(__pyx_tuple__35); + __pyx_tuple__37 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__37)) __PYX_ERR(2, 2, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__37); + __Pyx_GIVEREF(__pyx_tuple__37); /* "(tree fragment)":4 * raise TypeError("no default __reduce__ due to non-trivial __cinit__") * def __setstate_cython__(self, __pyx_state): * raise TypeError("no default __reduce__ due to non-trivial __cinit__") # <<<<<<<<<<<<<< */ - __pyx_tuple__36 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__36)) __PYX_ERR(2, 4, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__36); - __Pyx_GIVEREF(__pyx_tuple__36); + __pyx_tuple__38 = PyTuple_Pack(1, __pyx_kp_s_no_default___reduce___due_to_non); if (unlikely(!__pyx_tuple__38)) __PYX_ERR(2, 4, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__38); + __Pyx_GIVEREF(__pyx_tuple__38); /* "gensim/_matutils.pyx":14 * @@ -22840,10 +22910,10 @@ static int __Pyx_InitCachedConstants(void) { * """Mean absolute difference between two arrays, using :func:`~gensim._matutils._mean_absolute_difference`. * */ - __pyx_tuple__37 = PyTuple_Pack(2, __pyx_n_s_a, __pyx_n_s_b); if (unlikely(!__pyx_tuple__37)) __PYX_ERR(0, 14, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__37); - __Pyx_GIVEREF(__pyx_tuple__37); - __pyx_codeobj__38 = (PyObject*)__Pyx_PyCode_New(2, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__37, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_mean_absolute_difference, 14, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__38)) __PYX_ERR(0, 14, __pyx_L1_error) + __pyx_tuple__39 = PyTuple_Pack(2, __pyx_n_s_a, __pyx_n_s_b); if (unlikely(!__pyx_tuple__39)) __PYX_ERR(0, 14, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__39); + __Pyx_GIVEREF(__pyx_tuple__39); + __pyx_codeobj__40 = (PyObject*)__Pyx_PyCode_New(2, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__39, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_mean_absolute_difference, 14, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__40)) __PYX_ERR(0, 14, __pyx_L1_error) /* "gensim/_matutils.pyx":75 * @@ -22852,10 +22922,10 @@ static int __Pyx_InitCachedConstants(void) { * """Log of sum of exponentials, using :func:`~gensim._matutils._logsumexp_2d`. * */ - __pyx_tuple__39 = PyTuple_Pack(1, __pyx_n_s_x); if (unlikely(!__pyx_tuple__39)) __PYX_ERR(0, 75, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__39); - __Pyx_GIVEREF(__pyx_tuple__39); - __pyx_codeobj__40 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__39, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_logsumexp, 75, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__40)) __PYX_ERR(0, 75, __pyx_L1_error) + __pyx_tuple__41 = PyTuple_Pack(1, __pyx_n_s_x); if (unlikely(!__pyx_tuple__41)) __PYX_ERR(0, 75, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__41); + __Pyx_GIVEREF(__pyx_tuple__41); + __pyx_codeobj__42 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__41, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_logsumexp, 75, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__42)) __PYX_ERR(0, 75, __pyx_L1_error) /* "gensim/_matutils.pyx":142 * @@ -22864,10 +22934,10 @@ static int __Pyx_InitCachedConstants(void) { * """Expected value of log(theta) where theta is drawn from a Dirichlet distribution. * Using :func:`~gensim._matutils.dirichlet_expectation_1d` or :func:`~gensim._matutils.dirichlet_expectation_2d`. */ - __pyx_tuple__41 = PyTuple_Pack(1, __pyx_n_s_alpha); if (unlikely(!__pyx_tuple__41)) __PYX_ERR(0, 142, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__41); - __Pyx_GIVEREF(__pyx_tuple__41); - __pyx_codeobj__42 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__41, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_dirichlet_expectation, 142, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__42)) __PYX_ERR(0, 142, __pyx_L1_error) + __pyx_tuple__43 = PyTuple_Pack(1, __pyx_n_s_alpha); if (unlikely(!__pyx_tuple__43)) __PYX_ERR(0, 142, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__43); + __Pyx_GIVEREF(__pyx_tuple__43); + __pyx_codeobj__44 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__43, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_dirichlet_expectation, 142, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__44)) __PYX_ERR(0, 142, __pyx_L1_error) /* "gensim/_matutils.pyx":164 * @@ -22876,10 +22946,10 @@ static int __Pyx_InitCachedConstants(void) { * """Expected value of log(theta) where theta is drawn from a Dirichlet distribution. * Using :func:`~gensim._matutils._dirichlet_expectation_2d`. */ - __pyx_tuple__43 = PyTuple_Pack(2, __pyx_n_s_alpha, __pyx_n_s_out); if (unlikely(!__pyx_tuple__43)) __PYX_ERR(0, 164, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__43); - __Pyx_GIVEREF(__pyx_tuple__43); - __pyx_codeobj__44 = (PyObject*)__Pyx_PyCode_New(1, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__43, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_dirichlet_expectation_2d, 164, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__44)) __PYX_ERR(0, 164, __pyx_L1_error) + __pyx_tuple__45 = PyTuple_Pack(2, __pyx_n_s_alpha, __pyx_n_s_out); if (unlikely(!__pyx_tuple__45)) __PYX_ERR(0, 164, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__45); + __Pyx_GIVEREF(__pyx_tuple__45); + __pyx_codeobj__46 = (PyObject*)__Pyx_PyCode_New(1, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__45, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_dirichlet_expectation_2d, 164, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__46)) __PYX_ERR(0, 164, __pyx_L1_error) /* "gensim/_matutils.pyx":194 * @@ -22888,10 +22958,10 @@ static int __Pyx_InitCachedConstants(void) { * """Expected value of log(theta) where theta is drawn from a Dirichlet distribution. * Using :func:`~gensim._matutils._dirichlet_expectation_1d`. */ - __pyx_tuple__45 = PyTuple_Pack(2, __pyx_n_s_alpha, __pyx_n_s_out); if (unlikely(!__pyx_tuple__45)) __PYX_ERR(0, 194, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__45); - __Pyx_GIVEREF(__pyx_tuple__45); - __pyx_codeobj__46 = (PyObject*)__Pyx_PyCode_New(1, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__45, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_dirichlet_expectation_1d, 194, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__46)) __PYX_ERR(0, 194, __pyx_L1_error) + __pyx_tuple__47 = PyTuple_Pack(2, __pyx_n_s_alpha, __pyx_n_s_out); if (unlikely(!__pyx_tuple__47)) __PYX_ERR(0, 194, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__47); + __Pyx_GIVEREF(__pyx_tuple__47); + __pyx_codeobj__48 = (PyObject*)__Pyx_PyCode_New(1, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__47, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_dirichlet_expectation_1d, 194, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__48)) __PYX_ERR(0, 194, __pyx_L1_error) /* "gensim/_matutils.pyx":282 * @@ -22900,75 +22970,75 @@ static int __Pyx_InitCachedConstants(void) { * """Digamma function for positive floats, using :func:`~gensim._matutils._digamma`. * */ - __pyx_tuple__47 = PyTuple_Pack(2, __pyx_n_s_x, __pyx_n_s_x); if (unlikely(!__pyx_tuple__47)) __PYX_ERR(0, 282, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__47); - __Pyx_GIVEREF(__pyx_tuple__47); - __pyx_codeobj__48 = (PyObject*)__Pyx_PyCode_New(1, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__47, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_digamma, 282, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__48)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_tuple__49 = PyTuple_Pack(2, __pyx_n_s_x, __pyx_n_s_x); if (unlikely(!__pyx_tuple__49)) __PYX_ERR(0, 282, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__49); + __Pyx_GIVEREF(__pyx_tuple__49); + __pyx_codeobj__50 = (PyObject*)__Pyx_PyCode_New(1, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__49, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_gensim__matutils_pyx, __pyx_n_s_digamma, 282, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__50)) __PYX_ERR(0, 282, __pyx_L1_error) - /* "View.MemoryView":284 + /* "View.MemoryView":285 * return self.name * * cdef generic = Enum("") # <<<<<<<<<<<<<< * cdef strided = Enum("") # default * cdef indirect = Enum("") */ - __pyx_tuple__49 = PyTuple_Pack(1, __pyx_kp_s_strided_and_direct_or_indirect); if (unlikely(!__pyx_tuple__49)) __PYX_ERR(2, 284, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__49); - __Pyx_GIVEREF(__pyx_tuple__49); + __pyx_tuple__51 = PyTuple_Pack(1, __pyx_kp_s_strided_and_direct_or_indirect); if (unlikely(!__pyx_tuple__51)) __PYX_ERR(2, 285, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__51); + __Pyx_GIVEREF(__pyx_tuple__51); - /* "View.MemoryView":285 + /* "View.MemoryView":286 * * cdef generic = Enum("") * cdef strided = Enum("") # default # <<<<<<<<<<<<<< * cdef indirect = Enum("") * */ - __pyx_tuple__50 = PyTuple_Pack(1, __pyx_kp_s_strided_and_direct); if (unlikely(!__pyx_tuple__50)) __PYX_ERR(2, 285, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__50); - __Pyx_GIVEREF(__pyx_tuple__50); + __pyx_tuple__52 = PyTuple_Pack(1, __pyx_kp_s_strided_and_direct); if (unlikely(!__pyx_tuple__52)) __PYX_ERR(2, 286, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__52); + __Pyx_GIVEREF(__pyx_tuple__52); - /* "View.MemoryView":286 + /* "View.MemoryView":287 * cdef generic = Enum("") * cdef strided = Enum("") # default * cdef indirect = Enum("") # <<<<<<<<<<<<<< * * */ - __pyx_tuple__51 = PyTuple_Pack(1, __pyx_kp_s_strided_and_indirect); if (unlikely(!__pyx_tuple__51)) __PYX_ERR(2, 286, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__51); - __Pyx_GIVEREF(__pyx_tuple__51); + __pyx_tuple__53 = PyTuple_Pack(1, __pyx_kp_s_strided_and_indirect); if (unlikely(!__pyx_tuple__53)) __PYX_ERR(2, 287, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__53); + __Pyx_GIVEREF(__pyx_tuple__53); - /* "View.MemoryView":289 + /* "View.MemoryView":290 * * * cdef contiguous = Enum("") # <<<<<<<<<<<<<< * cdef indirect_contiguous = Enum("") * */ - __pyx_tuple__52 = PyTuple_Pack(1, __pyx_kp_s_contiguous_and_direct); if (unlikely(!__pyx_tuple__52)) __PYX_ERR(2, 289, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__52); - __Pyx_GIVEREF(__pyx_tuple__52); + __pyx_tuple__54 = PyTuple_Pack(1, __pyx_kp_s_contiguous_and_direct); if (unlikely(!__pyx_tuple__54)) __PYX_ERR(2, 290, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__54); + __Pyx_GIVEREF(__pyx_tuple__54); - /* "View.MemoryView":290 + /* "View.MemoryView":291 * * cdef contiguous = Enum("") * cdef indirect_contiguous = Enum("") # <<<<<<<<<<<<<< * * */ - __pyx_tuple__53 = PyTuple_Pack(1, __pyx_kp_s_contiguous_and_indirect); if (unlikely(!__pyx_tuple__53)) __PYX_ERR(2, 290, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__53); - __Pyx_GIVEREF(__pyx_tuple__53); + __pyx_tuple__55 = PyTuple_Pack(1, __pyx_kp_s_contiguous_and_indirect); if (unlikely(!__pyx_tuple__55)) __PYX_ERR(2, 291, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__55); + __Pyx_GIVEREF(__pyx_tuple__55); /* "(tree fragment)":1 * def __pyx_unpickle_Enum(__pyx_type, long __pyx_checksum, __pyx_state): # <<<<<<<<<<<<<< * if __pyx_checksum != 0xb068931: * from pickle import PickleError as __pyx_PickleError */ - __pyx_tuple__54 = PyTuple_Pack(5, __pyx_n_s_pyx_type, __pyx_n_s_pyx_checksum, __pyx_n_s_pyx_state, __pyx_n_s_pyx_PickleError, __pyx_n_s_pyx_result); if (unlikely(!__pyx_tuple__54)) __PYX_ERR(2, 1, __pyx_L1_error) - __Pyx_GOTREF(__pyx_tuple__54); - __Pyx_GIVEREF(__pyx_tuple__54); - __pyx_codeobj__55 = (PyObject*)__Pyx_PyCode_New(3, 0, 5, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__54, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_stringsource, __pyx_n_s_pyx_unpickle_Enum, 1, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__55)) __PYX_ERR(2, 1, __pyx_L1_error) + __pyx_tuple__56 = PyTuple_Pack(5, __pyx_n_s_pyx_type, __pyx_n_s_pyx_checksum, __pyx_n_s_pyx_state, __pyx_n_s_pyx_PickleError, __pyx_n_s_pyx_result); if (unlikely(!__pyx_tuple__56)) __PYX_ERR(2, 1, __pyx_L1_error) + __Pyx_GOTREF(__pyx_tuple__56); + __Pyx_GIVEREF(__pyx_tuple__56); + __pyx_codeobj__57 = (PyObject*)__Pyx_PyCode_New(3, 0, 5, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__56, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_stringsource, __pyx_n_s_pyx_unpickle_Enum, 1, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__57)) __PYX_ERR(2, 1, __pyx_L1_error) __Pyx_RefNannyFinishContext(); return 0; __pyx_L1_error:; @@ -22995,12 +23065,167 @@ if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 1, __pyx_L1_error) return -1; } +static int __Pyx_modinit_global_init_code(void); /*proto*/ +static int __Pyx_modinit_variable_export_code(void); /*proto*/ +static int __Pyx_modinit_function_export_code(void); /*proto*/ +static int __Pyx_modinit_type_init_code(void); /*proto*/ +static int __Pyx_modinit_type_import_code(void); /*proto*/ +static int __Pyx_modinit_variable_import_code(void); /*proto*/ +static int __Pyx_modinit_function_import_code(void); /*proto*/ + +static int __Pyx_modinit_global_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); + /*--- Global init code ---*/ + generic = Py_None; Py_INCREF(Py_None); + strided = Py_None; Py_INCREF(Py_None); + indirect = Py_None; Py_INCREF(Py_None); + contiguous = Py_None; Py_INCREF(Py_None); + indirect_contiguous = Py_None; Py_INCREF(Py_None); + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_variable_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); + /*--- Variable export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_export_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); + /*--- Function export code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_type_init_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); + /*--- Type init code ---*/ + __pyx_vtabptr_array = &__pyx_vtable_array; + __pyx_vtable_array.get_memview = (PyObject *(*)(struct __pyx_array_obj *))__pyx_array_get_memview; + if (PyType_Ready(&__pyx_type___pyx_array) < 0) __PYX_ERR(2, 104, __pyx_L1_error) + __pyx_type___pyx_array.tp_print = 0; + if (__Pyx_SetVtable(__pyx_type___pyx_array.tp_dict, __pyx_vtabptr_array) < 0) __PYX_ERR(2, 104, __pyx_L1_error) + if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_array) < 0) __PYX_ERR(2, 104, __pyx_L1_error) + __pyx_array_type = &__pyx_type___pyx_array; + if (PyType_Ready(&__pyx_type___pyx_MemviewEnum) < 0) __PYX_ERR(2, 278, __pyx_L1_error) + __pyx_type___pyx_MemviewEnum.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type___pyx_MemviewEnum.tp_dictoffset && __pyx_type___pyx_MemviewEnum.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type___pyx_MemviewEnum.tp_getattro = __Pyx_PyObject_GenericGetAttr; + } + if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_MemviewEnum) < 0) __PYX_ERR(2, 278, __pyx_L1_error) + __pyx_MemviewEnum_type = &__pyx_type___pyx_MemviewEnum; + __pyx_vtabptr_memoryview = &__pyx_vtable_memoryview; + __pyx_vtable_memoryview.get_item_pointer = (char *(*)(struct __pyx_memoryview_obj *, PyObject *))__pyx_memoryview_get_item_pointer; + __pyx_vtable_memoryview.is_slice = (PyObject *(*)(struct __pyx_memoryview_obj *, PyObject *))__pyx_memoryview_is_slice; + __pyx_vtable_memoryview.setitem_slice_assignment = (PyObject *(*)(struct __pyx_memoryview_obj *, PyObject *, PyObject *))__pyx_memoryview_setitem_slice_assignment; + __pyx_vtable_memoryview.setitem_slice_assign_scalar = (PyObject *(*)(struct __pyx_memoryview_obj *, struct __pyx_memoryview_obj *, PyObject *))__pyx_memoryview_setitem_slice_assign_scalar; + __pyx_vtable_memoryview.setitem_indexed = (PyObject *(*)(struct __pyx_memoryview_obj *, PyObject *, PyObject *))__pyx_memoryview_setitem_indexed; + __pyx_vtable_memoryview.convert_item_to_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *))__pyx_memoryview_convert_item_to_object; + __pyx_vtable_memoryview.assign_item_from_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *, PyObject *))__pyx_memoryview_assign_item_from_object; + if (PyType_Ready(&__pyx_type___pyx_memoryview) < 0) __PYX_ERR(2, 329, __pyx_L1_error) + __pyx_type___pyx_memoryview.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type___pyx_memoryview.tp_dictoffset && __pyx_type___pyx_memoryview.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type___pyx_memoryview.tp_getattro = __Pyx_PyObject_GenericGetAttr; + } + if (__Pyx_SetVtable(__pyx_type___pyx_memoryview.tp_dict, __pyx_vtabptr_memoryview) < 0) __PYX_ERR(2, 329, __pyx_L1_error) + if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_memoryview) < 0) __PYX_ERR(2, 329, __pyx_L1_error) + __pyx_memoryview_type = &__pyx_type___pyx_memoryview; + __pyx_vtabptr__memoryviewslice = &__pyx_vtable__memoryviewslice; + __pyx_vtable__memoryviewslice.__pyx_base = *__pyx_vtabptr_memoryview; + __pyx_vtable__memoryviewslice.__pyx_base.convert_item_to_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *))__pyx_memoryviewslice_convert_item_to_object; + __pyx_vtable__memoryviewslice.__pyx_base.assign_item_from_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *, PyObject *))__pyx_memoryviewslice_assign_item_from_object; + __pyx_type___pyx_memoryviewslice.tp_base = __pyx_memoryview_type; + if (PyType_Ready(&__pyx_type___pyx_memoryviewslice) < 0) __PYX_ERR(2, 960, __pyx_L1_error) + __pyx_type___pyx_memoryviewslice.tp_print = 0; + if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_type___pyx_memoryviewslice.tp_dictoffset && __pyx_type___pyx_memoryviewslice.tp_getattro == PyObject_GenericGetAttr)) { + __pyx_type___pyx_memoryviewslice.tp_getattro = __Pyx_PyObject_GenericGetAttr; + } + if (__Pyx_SetVtable(__pyx_type___pyx_memoryviewslice.tp_dict, __pyx_vtabptr__memoryviewslice) < 0) __PYX_ERR(2, 960, __pyx_L1_error) + if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_memoryviewslice) < 0) __PYX_ERR(2, 960, __pyx_L1_error) + __pyx_memoryviewslice_type = &__pyx_type___pyx_memoryviewslice; + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_type_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); + /*--- Type import code ---*/ + __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", + #if defined(PYPY_VERSION_NUM) && PYPY_VERSION_NUM < 0x050B0000 + sizeof(PyTypeObject), + #else + sizeof(PyHeapTypeObject), + #endif + 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(3, 9, __pyx_L1_error) + __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 164, __pyx_L1_error) + __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 186, __pyx_L1_error) + __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 190, __pyx_L1_error) + __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 199, __pyx_L1_error) + __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 872, __pyx_L1_error) + __Pyx_RefNannyFinishContext(); + return 0; + __pyx_L1_error:; + __Pyx_RefNannyFinishContext(); + return -1; +} + +static int __Pyx_modinit_variable_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); + /*--- Variable import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + +static int __Pyx_modinit_function_import_code(void) { + __Pyx_RefNannyDeclarations + __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); + /*--- Function import code ---*/ + __Pyx_RefNannyFinishContext(); + return 0; +} + + #if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC init_matutils(void); /*proto*/ -PyMODINIT_FUNC init_matutils(void) +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC void +#else +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#else +#ifdef CYTHON_NO_PYINIT_EXPORT +#define __Pyx_PyMODINIT_FUNC PyObject * #else -PyMODINIT_FUNC PyInit__matutils(void); /*proto*/ -PyMODINIT_FUNC PyInit__matutils(void) +#define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC +#endif +#endif +#ifndef CYTHON_SMALL_CODE +#if defined(__clang__) + #define CYTHON_SMALL_CODE +#elif defined(__GNUC__) && (!(defined(__cplusplus)) || (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ > 4))) + #define CYTHON_SMALL_CODE __attribute__((optimize("Os"))) +#else + #define CYTHON_SMALL_CODE +#endif +#endif + + +#if PY_MAJOR_VERSION < 3 +__Pyx_PyMODINIT_FUNC init_matutils(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC init_matutils(void) +#else +__Pyx_PyMODINIT_FUNC PyInit__matutils(void) CYTHON_SMALL_CODE; /*proto*/ +__Pyx_PyMODINIT_FUNC PyInit__matutils(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); @@ -23051,17 +23276,19 @@ static int __pyx_pymod_exec__matutils(PyObject *__pyx_pyinit_module) __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m && __pyx_m == __pyx_pyinit_module) return 0; + #elif PY_MAJOR_VERSION >= 3 + if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif #if CYTHON_REFNANNY - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); - if (!__Pyx_RefNanny) { - PyErr_Clear(); - __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); - if (!__Pyx_RefNanny) - Py_FatalError("failed to import 'refnanny' module"); - } - #endif - __Pyx_RefNannySetupContext("PyMODINIT_FUNC PyInit__matutils(void)", 0); +__Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); +if (!__Pyx_RefNanny) { + PyErr_Clear(); + __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); + if (!__Pyx_RefNanny) + Py_FatalError("failed to import 'refnanny' module"); +} +#endif + __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit__matutils(void)", 0); if (__Pyx_check_binary_version() < 0) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) @@ -23114,81 +23341,31 @@ static int __pyx_pymod_exec__matutils(PyObject *__pyx_pyinit_module) /*--- Initialize various global constants etc. ---*/ if (__Pyx_InitGlobals() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #if PY_MAJOR_VERSION < 3 && (__PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT) - if (__Pyx_init_sys_getdefaultencoding_params() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - #endif - if (__pyx_module_is_main_gensim___matutils) { - if (PyObject_SetAttrString(__pyx_m, "__name__", __pyx_n_s_main) < 0) __PYX_ERR(0, 1, __pyx_L1_error) - } - #if PY_MAJOR_VERSION >= 3 - { - PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) __PYX_ERR(0, 1, __pyx_L1_error) - if (!PyDict_GetItemString(modules, "gensim._matutils")) { - if (unlikely(PyDict_SetItemString(modules, "gensim._matutils", __pyx_m) < 0)) __PYX_ERR(0, 1, __pyx_L1_error) - } - } - #endif - /*--- Builtin init code ---*/ - if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Constants init code ---*/ - if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) - /*--- Global init code ---*/ - generic = Py_None; Py_INCREF(Py_None); - strided = Py_None; Py_INCREF(Py_None); - indirect = Py_None; Py_INCREF(Py_None); - contiguous = Py_None; Py_INCREF(Py_None); - indirect_contiguous = Py_None; Py_INCREF(Py_None); - /*--- Variable export code ---*/ - /*--- Function export code ---*/ - /*--- Type init code ---*/ - __pyx_vtabptr_array = &__pyx_vtable_array; - __pyx_vtable_array.get_memview = (PyObject *(*)(struct __pyx_array_obj *))__pyx_array_get_memview; - if (PyType_Ready(&__pyx_type___pyx_array) < 0) __PYX_ERR(2, 103, __pyx_L1_error) - __pyx_type___pyx_array.tp_print = 0; - if (__Pyx_SetVtable(__pyx_type___pyx_array.tp_dict, __pyx_vtabptr_array) < 0) __PYX_ERR(2, 103, __pyx_L1_error) - if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_array) < 0) __PYX_ERR(2, 103, __pyx_L1_error) - __pyx_array_type = &__pyx_type___pyx_array; - if (PyType_Ready(&__pyx_type___pyx_MemviewEnum) < 0) __PYX_ERR(2, 277, __pyx_L1_error) - __pyx_type___pyx_MemviewEnum.tp_print = 0; - if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_MemviewEnum) < 0) __PYX_ERR(2, 277, __pyx_L1_error) - __pyx_MemviewEnum_type = &__pyx_type___pyx_MemviewEnum; - __pyx_vtabptr_memoryview = &__pyx_vtable_memoryview; - __pyx_vtable_memoryview.get_item_pointer = (char *(*)(struct __pyx_memoryview_obj *, PyObject *))__pyx_memoryview_get_item_pointer; - __pyx_vtable_memoryview.is_slice = (PyObject *(*)(struct __pyx_memoryview_obj *, PyObject *))__pyx_memoryview_is_slice; - __pyx_vtable_memoryview.setitem_slice_assignment = (PyObject *(*)(struct __pyx_memoryview_obj *, PyObject *, PyObject *))__pyx_memoryview_setitem_slice_assignment; - __pyx_vtable_memoryview.setitem_slice_assign_scalar = (PyObject *(*)(struct __pyx_memoryview_obj *, struct __pyx_memoryview_obj *, PyObject *))__pyx_memoryview_setitem_slice_assign_scalar; - __pyx_vtable_memoryview.setitem_indexed = (PyObject *(*)(struct __pyx_memoryview_obj *, PyObject *, PyObject *))__pyx_memoryview_setitem_indexed; - __pyx_vtable_memoryview.convert_item_to_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *))__pyx_memoryview_convert_item_to_object; - __pyx_vtable_memoryview.assign_item_from_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *, PyObject *))__pyx_memoryview_assign_item_from_object; - if (PyType_Ready(&__pyx_type___pyx_memoryview) < 0) __PYX_ERR(2, 328, __pyx_L1_error) - __pyx_type___pyx_memoryview.tp_print = 0; - if (__Pyx_SetVtable(__pyx_type___pyx_memoryview.tp_dict, __pyx_vtabptr_memoryview) < 0) __PYX_ERR(2, 328, __pyx_L1_error) - if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_memoryview) < 0) __PYX_ERR(2, 328, __pyx_L1_error) - __pyx_memoryview_type = &__pyx_type___pyx_memoryview; - __pyx_vtabptr__memoryviewslice = &__pyx_vtable__memoryviewslice; - __pyx_vtable__memoryviewslice.__pyx_base = *__pyx_vtabptr_memoryview; - __pyx_vtable__memoryviewslice.__pyx_base.convert_item_to_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *))__pyx_memoryviewslice_convert_item_to_object; - __pyx_vtable__memoryviewslice.__pyx_base.assign_item_from_object = (PyObject *(*)(struct __pyx_memoryview_obj *, char *, PyObject *))__pyx_memoryviewslice_assign_item_from_object; - __pyx_type___pyx_memoryviewslice.tp_base = __pyx_memoryview_type; - if (PyType_Ready(&__pyx_type___pyx_memoryviewslice) < 0) __PYX_ERR(2, 953, __pyx_L1_error) - __pyx_type___pyx_memoryviewslice.tp_print = 0; - if (__Pyx_SetVtable(__pyx_type___pyx_memoryviewslice.tp_dict, __pyx_vtabptr__memoryviewslice) < 0) __PYX_ERR(2, 953, __pyx_L1_error) - if (__Pyx_setup_reduce((PyObject*)&__pyx_type___pyx_memoryviewslice) < 0) __PYX_ERR(2, 953, __pyx_L1_error) - __pyx_memoryviewslice_type = &__pyx_type___pyx_memoryviewslice; - /*--- Type import code ---*/ - __pyx_ptype_7cpython_4type_type = __Pyx_ImportType(__Pyx_BUILTIN_MODULE_NAME, "type", - #if CYTHON_COMPILING_IN_PYPY - sizeof(PyTypeObject), - #else - sizeof(PyHeapTypeObject), + if (__Pyx_init_sys_getdefaultencoding_params() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif - 0); if (unlikely(!__pyx_ptype_7cpython_4type_type)) __PYX_ERR(3, 9, __pyx_L1_error) - __pyx_ptype_5numpy_dtype = __Pyx_ImportType("numpy", "dtype", sizeof(PyArray_Descr), 0); if (unlikely(!__pyx_ptype_5numpy_dtype)) __PYX_ERR(1, 163, __pyx_L1_error) - __pyx_ptype_5numpy_flatiter = __Pyx_ImportType("numpy", "flatiter", sizeof(PyArrayIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_flatiter)) __PYX_ERR(1, 185, __pyx_L1_error) - __pyx_ptype_5numpy_broadcast = __Pyx_ImportType("numpy", "broadcast", sizeof(PyArrayMultiIterObject), 0); if (unlikely(!__pyx_ptype_5numpy_broadcast)) __PYX_ERR(1, 189, __pyx_L1_error) - __pyx_ptype_5numpy_ndarray = __Pyx_ImportType("numpy", "ndarray", sizeof(PyArrayObject), 0); if (unlikely(!__pyx_ptype_5numpy_ndarray)) __PYX_ERR(1, 198, __pyx_L1_error) - __pyx_ptype_5numpy_ufunc = __Pyx_ImportType("numpy", "ufunc", sizeof(PyUFuncObject), 0); if (unlikely(!__pyx_ptype_5numpy_ufunc)) __PYX_ERR(1, 885, __pyx_L1_error) - /*--- Variable import code ---*/ - /*--- Function import code ---*/ + if (__pyx_module_is_main_gensim___matutils) { + if (PyObject_SetAttrString(__pyx_m, "__name__", __pyx_n_s_main) < 0) __PYX_ERR(0, 1, __pyx_L1_error) + } + #if PY_MAJOR_VERSION >= 3 + { + PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) __PYX_ERR(0, 1, __pyx_L1_error) + if (!PyDict_GetItemString(modules, "gensim._matutils")) { + if (unlikely(PyDict_SetItemString(modules, "gensim._matutils", __pyx_m) < 0)) __PYX_ERR(0, 1, __pyx_L1_error) + } + } + #endif + /*--- Builtin init code ---*/ + if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + /*--- Constants init code ---*/ + if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) + /*--- Global type/function init code ---*/ + (void)__Pyx_modinit_global_init_code(); + (void)__Pyx_modinit_variable_export_code(); + (void)__Pyx_modinit_function_export_code(); + if (unlikely(__Pyx_modinit_type_init_code() != 0)) goto __pyx_L1_error; + if (unlikely(__Pyx_modinit_type_import_code() != 0)) goto __pyx_L1_error; + (void)__Pyx_modinit_variable_import_code(); + (void)__Pyx_modinit_function_import_code(); /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) @@ -23275,17 +23452,17 @@ static int __pyx_pymod_exec__matutils(PyObject *__pyx_pyinit_module) */ __pyx_t_1 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); - __pyx_t_2 = __pyx_FusedFunction_NewEx(&__pyx_fuse_0__pyx_mdef_6gensim_9_matutils_13digamma, 0, __pyx_n_s_digamma, NULL, __pyx_n_s_gensim__matutils, __pyx_d, ((PyObject *)__pyx_codeobj__48)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_2 = __pyx_FusedFunction_NewEx(&__pyx_fuse_0__pyx_mdef_6gensim_9_matutils_13digamma, 0, __pyx_n_s_digamma, NULL, __pyx_n_s_gensim__matutils, __pyx_d, ((PyObject *)__pyx_codeobj__50)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_CyFunction_SetDefaultsTuple(__pyx_t_2, __pyx_empty_tuple); if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_float, __pyx_t_2) < 0) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = __pyx_FusedFunction_NewEx(&__pyx_fuse_1__pyx_mdef_6gensim_9_matutils_15digamma, 0, __pyx_n_s_digamma, NULL, __pyx_n_s_gensim__matutils, __pyx_d, ((PyObject *)__pyx_codeobj__48)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_2 = __pyx_FusedFunction_NewEx(&__pyx_fuse_1__pyx_mdef_6gensim_9_matutils_15digamma, 0, __pyx_n_s_digamma, NULL, __pyx_n_s_gensim__matutils, __pyx_d, ((PyObject *)__pyx_codeobj__50)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_CyFunction_SetDefaultsTuple(__pyx_t_2, __pyx_empty_tuple); if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_double, __pyx_t_2) < 0) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __pyx_t_2 = __pyx_FusedFunction_NewEx(&__pyx_mdef_6gensim_9_matutils_11digamma, 0, __pyx_n_s_digamma, NULL, __pyx_n_s_gensim__matutils, __pyx_d, ((PyObject *)__pyx_codeobj__48)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 282, __pyx_L1_error) + __pyx_t_2 = __pyx_FusedFunction_NewEx(&__pyx_mdef_6gensim_9_matutils_11digamma, 0, __pyx_n_s_digamma, NULL, __pyx_n_s_gensim__matutils, __pyx_d, ((PyObject *)__pyx_codeobj__50)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 282, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_CyFunction_SetDefaultsTuple(__pyx_t_2, __pyx_empty_tuple); ((__pyx_FusedFunctionObject *) __pyx_t_2)->__signatures__ = __pyx_t_1; @@ -23303,90 +23480,90 @@ static int __pyx_pymod_exec__matutils(PyObject *__pyx_pyinit_module) if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_3) < 0) __PYX_ERR(0, 1, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":207 + /* "View.MemoryView":208 * info.obj = self * * __pyx_getbuffer = capsule( &__pyx_array_getbuffer, "getbuffer(obj, view, flags)") # <<<<<<<<<<<<<< * * def __dealloc__(array self): */ - __pyx_t_3 = __pyx_capsule_create(((void *)(&__pyx_array_getbuffer)), ((char *)"getbuffer(obj, view, flags)")); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 207, __pyx_L1_error) + __pyx_t_3 = __pyx_capsule_create(((void *)(&__pyx_array_getbuffer)), ((char *)"getbuffer(obj, view, flags)")); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 208, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem((PyObject *)__pyx_array_type->tp_dict, __pyx_n_s_pyx_getbuffer, __pyx_t_3) < 0) __PYX_ERR(2, 207, __pyx_L1_error) + if (PyDict_SetItem((PyObject *)__pyx_array_type->tp_dict, __pyx_n_s_pyx_getbuffer, __pyx_t_3) < 0) __PYX_ERR(2, 208, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; PyType_Modified(__pyx_array_type); - /* "View.MemoryView":284 + /* "View.MemoryView":285 * return self.name * * cdef generic = Enum("") # <<<<<<<<<<<<<< * cdef strided = Enum("") # default * cdef indirect = Enum("") */ - __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__49, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 284, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__51, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 285, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_XGOTREF(generic); __Pyx_DECREF_SET(generic, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":285 + /* "View.MemoryView":286 * * cdef generic = Enum("") * cdef strided = Enum("") # default # <<<<<<<<<<<<<< * cdef indirect = Enum("") * */ - __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__50, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 285, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__52, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 286, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_XGOTREF(strided); __Pyx_DECREF_SET(strided, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":286 + /* "View.MemoryView":287 * cdef generic = Enum("") * cdef strided = Enum("") # default * cdef indirect = Enum("") # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__51, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 286, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__53, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 287, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_XGOTREF(indirect); __Pyx_DECREF_SET(indirect, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":289 + /* "View.MemoryView":290 * * * cdef contiguous = Enum("") # <<<<<<<<<<<<<< * cdef indirect_contiguous = Enum("") * */ - __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__52, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 289, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__54, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 290, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_XGOTREF(contiguous); __Pyx_DECREF_SET(contiguous, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":290 + /* "View.MemoryView":291 * * cdef contiguous = Enum("") * cdef indirect_contiguous = Enum("") # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__53, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 290, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_MemviewEnum_type), __pyx_tuple__55, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 291, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_XGOTREF(indirect_contiguous); __Pyx_DECREF_SET(indirect_contiguous, __pyx_t_3); __Pyx_GIVEREF(__pyx_t_3); __pyx_t_3 = 0; - /* "View.MemoryView":314 + /* "View.MemoryView":315 * * DEF THREAD_LOCKS_PREALLOCATED = 8 * cdef int __pyx_memoryview_thread_locks_used = 0 # <<<<<<<<<<<<<< @@ -23395,7 +23572,7 @@ static int __pyx_pymod_exec__matutils(PyObject *__pyx_pyinit_module) */ __pyx_memoryview_thread_locks_used = 0; - /* "View.MemoryView":315 + /* "View.MemoryView":316 * DEF THREAD_LOCKS_PREALLOCATED = 8 * cdef int __pyx_memoryview_thread_locks_used = 0 * cdef PyThread_type_lock[THREAD_LOCKS_PREALLOCATED] __pyx_memoryview_thread_locks = [ # <<<<<<<<<<<<<< @@ -23412,29 +23589,29 @@ static int __pyx_pymod_exec__matutils(PyObject *__pyx_pyinit_module) __pyx_t_4[7] = PyThread_allocate_lock(); memcpy(&(__pyx_memoryview_thread_locks[0]), __pyx_t_4, sizeof(__pyx_memoryview_thread_locks[0]) * (8)); - /* "View.MemoryView":537 + /* "View.MemoryView":544 * info.obj = self * * __pyx_getbuffer = capsule( &__pyx_memoryview_getbuffer, "getbuffer(obj, view, flags)") # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __pyx_capsule_create(((void *)(&__pyx_memoryview_getbuffer)), ((char *)"getbuffer(obj, view, flags)")); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 537, __pyx_L1_error) + __pyx_t_3 = __pyx_capsule_create(((void *)(&__pyx_memoryview_getbuffer)), ((char *)"getbuffer(obj, view, flags)")); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 544, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem((PyObject *)__pyx_memoryview_type->tp_dict, __pyx_n_s_pyx_getbuffer, __pyx_t_3) < 0) __PYX_ERR(2, 537, __pyx_L1_error) + if (PyDict_SetItem((PyObject *)__pyx_memoryview_type->tp_dict, __pyx_n_s_pyx_getbuffer, __pyx_t_3) < 0) __PYX_ERR(2, 544, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; PyType_Modified(__pyx_memoryview_type); - /* "View.MemoryView":983 + /* "View.MemoryView":990 * return self.from_object * * __pyx_getbuffer = capsule( &__pyx_memoryview_getbuffer, "getbuffer(obj, view, flags)") # <<<<<<<<<<<<<< * * */ - __pyx_t_3 = __pyx_capsule_create(((void *)(&__pyx_memoryview_getbuffer)), ((char *)"getbuffer(obj, view, flags)")); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 983, __pyx_L1_error) + __pyx_t_3 = __pyx_capsule_create(((void *)(&__pyx_memoryview_getbuffer)), ((char *)"getbuffer(obj, view, flags)")); if (unlikely(!__pyx_t_3)) __PYX_ERR(2, 990, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - if (PyDict_SetItem((PyObject *)__pyx_memoryviewslice_type->tp_dict, __pyx_n_s_pyx_getbuffer, __pyx_t_3) < 0) __PYX_ERR(2, 983, __pyx_L1_error) + if (PyDict_SetItem((PyObject *)__pyx_memoryviewslice_type->tp_dict, __pyx_n_s_pyx_getbuffer, __pyx_t_3) < 0) __PYX_ERR(2, 990, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; PyType_Modified(__pyx_memoryviewslice_type); @@ -23500,6 +23677,20 @@ static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { } #endif +/* PyObjectGetAttrStr */ +#if CYTHON_USE_TYPE_SLOTS +static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { + PyTypeObject* tp = Py_TYPE(obj); + if (likely(tp->tp_getattro)) + return tp->tp_getattro(obj, attr_name); +#if PY_MAJOR_VERSION < 3 + if (likely(tp->tp_getattr)) + return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); +#endif + return PyObject_GetAttr(obj, attr_name); +} +#endif + /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStr(__pyx_b, name); @@ -23863,10 +24054,19 @@ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { PyObject *result; #if !CYTHON_AVOID_BORROWED_REFS +#if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 + result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); + if (likely(result)) { + Py_INCREF(result); + } else if (unlikely(PyErr_Occurred())) { + result = NULL; + } else { +#else result = PyDict_GetItem(__pyx_d, name); if (likely(result)) { Py_INCREF(result); } else { +#endif #else result = PyObject_GetItem(__pyx_d, name); if (!result) { @@ -23878,7 +24078,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetModuleGlobalName(PyObject *name) { } /* MemviewSliceInit */ - static int + static int __Pyx_init_memviewslice(struct __pyx_memoryview_obj *memview, int ndim, __Pyx_memviewslice *memviewslice, @@ -24016,7 +24216,7 @@ static CYTHON_INLINE void __Pyx_XDEC_MEMVIEW(__Pyx_memviewslice *memslice, } /* PyCFunctionFastCall */ - #if CYTHON_FAST_PYCCALL + #if CYTHON_FAST_PYCCALL static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, PyObject **args, Py_ssize_t nargs) { PyCFunctionObject *func = (PyCFunctionObject*)func_obj; PyCFunction meth = PyCFunction_GET_FUNCTION(func); @@ -24039,7 +24239,7 @@ static CYTHON_INLINE PyObject * __Pyx_PyCFunction_FastCall(PyObject *func_obj, P #endif /* PyFunctionFastCall */ - #if CYTHON_FAST_PYCALL + #if CYTHON_FAST_PYCALL #include "frameobject.h" static PyObject* __Pyx_PyFunction_FastCallNoKw(PyCodeObject *co, PyObject **args, Py_ssize_t na, PyObject *globals) { @@ -24159,7 +24359,7 @@ static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, #endif /* PyObjectCallMethO */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { PyObject *self, *result; PyCFunction cfunc; @@ -24179,7 +24379,7 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject #endif /* PyObjectCallOneArg */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static PyObject* __Pyx__PyObject_CallOneArg(PyObject *func, PyObject *arg) { PyObject *result; PyObject *args = PyTuple_New(1); @@ -24219,7 +24419,7 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObjec #endif /* PyIntBinop */ - #if !CYTHON_COMPILING_IN_PYPY + #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED long intval, CYTHON_UNUSED int inplace) { if (op1 == op2) { Py_RETURN_TRUE; @@ -24251,31 +24451,37 @@ static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED a = -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; } + CYTHON_FALLTHROUGH; #if PyLong_SHIFT < 30 && PyLong_SHIFT != 15 default: return PyLong_Type.tp_richcompare(op1, op2, Py_EQ); #else @@ -24304,12 +24510,12 @@ static PyObject* __Pyx_PyInt_EqObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED #endif /* None */ - static CYTHON_INLINE void __Pyx_RaiseUnboundLocalError(const char *varname) { + static CYTHON_INLINE void __Pyx_RaiseUnboundLocalError(const char *varname) { PyErr_Format(PyExc_UnboundLocalError, "local variable '%s' referenced before assignment", varname); } /* GetItemInt */ - static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { + static PyObject *__Pyx_GetItemInt_Generic(PyObject *o, PyObject* j) { PyObject *r; if (!j) return NULL; r = PyObject_GetItem(o, j); @@ -24395,8 +24601,27 @@ static CYTHON_INLINE PyObject *__Pyx_GetItemInt_Fast(PyObject *o, Py_ssize_t i, return __Pyx_GetItemInt_Generic(o, PyInt_FromSsize_t(i)); } +/* DictGetItem */ + #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY +static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { + PyObject *value; + value = PyDict_GetItemWithError(d, key); + if (unlikely(!value)) { + if (!PyErr_Occurred()) { + PyObject* args = PyTuple_Pack(1, key); + if (likely(args)) + PyErr_SetObject(PyExc_KeyError, args); + Py_XDECREF(args); + } + return NULL; + } + Py_INCREF(value); + return value; +} +#endif + /* SetItemInt */ - static int __Pyx_SetItemInt_Generic(PyObject *o, PyObject *j, PyObject *v) { + static int __Pyx_SetItemInt_Generic(PyObject *o, PyObject *j, PyObject *v) { int r; if (!j) return -1; r = PyObject_SetItem(o, j, v); @@ -24444,7 +24669,7 @@ static CYTHON_INLINE int __Pyx_SetItemInt_Fast(PyObject *o, Py_ssize_t i, PyObje } /* IterFinish */ - static CYTHON_INLINE int __Pyx_IterFinish(void) { + static CYTHON_INLINE int __Pyx_IterFinish(void) { #if CYTHON_FAST_THREAD_STATE PyThreadState *tstate = __Pyx_PyThreadState_Current; PyObject* exc_type = tstate->curexc_type; @@ -24479,7 +24704,7 @@ static CYTHON_INLINE int __Pyx_SetItemInt_Fast(PyObject *o, Py_ssize_t i, PyObje } /* PyObjectCallNoArg */ - #if CYTHON_COMPILING_IN_CPYTHON + #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { #if CYTHON_FAST_PYCALL if (PyFunction_Check(func)) { @@ -24500,7 +24725,7 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { #endif /* PyObjectCallMethod0 */ - static PyObject* __Pyx_PyObject_CallMethod0(PyObject* obj, PyObject* method_name) { + static PyObject* __Pyx_PyObject_CallMethod0(PyObject* obj, PyObject* method_name) { PyObject *method, *result = NULL; method = __Pyx_PyObject_GetAttrStr(obj, method_name); if (unlikely(!method)) goto bad; @@ -24522,20 +24747,20 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { } /* RaiseNeedMoreValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { + static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { PyErr_Format(PyExc_ValueError, "need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack", index, (index == 1) ? "" : "s"); } /* RaiseTooManyValuesToUnpack */ - static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { + static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { PyErr_Format(PyExc_ValueError, "too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected); } /* UnpackItemEndCheck */ - static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected) { + static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected) { if (unlikely(retval)) { Py_DECREF(retval); __Pyx_RaiseTooManyValuesError(expected); @@ -24547,12 +24772,12 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { } /* RaiseNoneIterError */ - static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) { + static CYTHON_INLINE void __Pyx_RaiseNoneNotIterableError(void) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not iterable"); } /* UnpackTupleError */ - static void __Pyx_UnpackTupleError(PyObject *t, Py_ssize_t index) { + static void __Pyx_UnpackTupleError(PyObject *t, Py_ssize_t index) { if (t == Py_None) { __Pyx_RaiseNoneNotIterableError(); } else if (PyTuple_GET_SIZE(t) < index) { @@ -24563,7 +24788,7 @@ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { } /* UnpackTuple2 */ - static CYTHON_INLINE int __Pyx_unpack_tuple2_exact( + static CYTHON_INLINE int __Pyx_unpack_tuple2_exact( PyObject* tuple, PyObject** pvalue1, PyObject** pvalue2, int decref_tuple) { PyObject *value1 = NULL, *value2 = NULL; #if CYTHON_COMPILING_IN_PYPY @@ -24615,7 +24840,7 @@ static int __Pyx_unpack_tuple2_generic(PyObject* tuple, PyObject** pvalue1, PyOb } /* dict_iter */ - static CYTHON_INLINE PyObject* __Pyx_dict_iterator(PyObject* iterable, int is_dict, PyObject* method_name, + static CYTHON_INLINE PyObject* __Pyx_dict_iterator(PyObject* iterable, int is_dict, PyObject* method_name, Py_ssize_t* p_orig_length, int* p_source_is_dict) { is_dict = is_dict || likely(PyDict_CheckExact(iterable)); *p_source_is_dict = is_dict; @@ -24728,7 +24953,7 @@ static CYTHON_INLINE int __Pyx_dict_iter_next( } /* ExtTypeTest */ - static CYTHON_INLINE int __Pyx_TypeTest(PyObject *obj, PyTypeObject *type) { + static CYTHON_INLINE int __Pyx_TypeTest(PyObject *obj, PyTypeObject *type) { if (unlikely(!type)) { PyErr_SetString(PyExc_SystemError, "Missing type object"); return 0; @@ -24741,7 +24966,7 @@ static CYTHON_INLINE int __Pyx_dict_iter_next( } /* SaveResetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #if PY_VERSION_HEX >= 0x030700A2 *type = tstate->exc_state.exc_type; @@ -24780,7 +25005,7 @@ static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject #endif /* PyErrExceptionMatches */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx_PyErr_ExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(tuple); @@ -24805,7 +25030,7 @@ static CYTHON_INLINE int __Pyx_PyErr_ExceptionMatchesInState(PyThreadState* tsta #endif /* GetException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #else static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) { @@ -24875,7 +25100,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* ArgTypeTest */ - static int __Pyx__ArgTypeTest(PyObject *obj, PyTypeObject *type, const char *name, int exact) + static int __Pyx__ArgTypeTest(PyObject *obj, PyTypeObject *type, const char *name, int exact) { if (unlikely(!type)) { PyErr_SetString(PyExc_SystemError, "Missing type object"); @@ -24896,7 +25121,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* BytesEquals */ - static CYTHON_INLINE int __Pyx_PyBytes_Equals(PyObject* s1, PyObject* s2, int equals) { + static CYTHON_INLINE int __Pyx_PyBytes_Equals(PyObject* s1, PyObject* s2, int equals) { #if CYTHON_COMPILING_IN_PYPY return PyObject_RichCompareBool(s1, s2, equals); #else @@ -24943,7 +25168,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* UnicodeEquals */ - static CYTHON_INLINE int __Pyx_PyUnicode_Equals(PyObject* s1, PyObject* s2, int equals) { + static CYTHON_INLINE int __Pyx_PyUnicode_Equals(PyObject* s1, PyObject* s2, int equals) { #if CYTHON_COMPILING_IN_PYPY return PyObject_RichCompareBool(s1, s2, equals); #else @@ -25042,7 +25267,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* None */ - static CYTHON_INLINE Py_ssize_t __Pyx_div_Py_ssize_t(Py_ssize_t a, Py_ssize_t b) { + static CYTHON_INLINE Py_ssize_t __Pyx_div_Py_ssize_t(Py_ssize_t a, Py_ssize_t b) { Py_ssize_t q = a / b; Py_ssize_t r = a - q*b; q -= ((r != 0) & ((r ^ b) < 0)); @@ -25050,7 +25275,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* GetAttr */ - static CYTHON_INLINE PyObject *__Pyx_GetAttr(PyObject *o, PyObject *n) { + static CYTHON_INLINE PyObject *__Pyx_GetAttr(PyObject *o, PyObject *n) { #if CYTHON_USE_TYPE_SLOTS #if PY_MAJOR_VERSION >= 3 if (likely(PyUnicode_Check(n))) @@ -25062,8 +25287,37 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) return PyObject_GetAttr(o, n); } +/* ObjectGetItem */ + #if CYTHON_USE_TYPE_SLOTS +static PyObject *__Pyx_PyObject_GetIndex(PyObject *obj, PyObject* index) { + PyObject *runerr; + Py_ssize_t key_value; + PySequenceMethods *m = Py_TYPE(obj)->tp_as_sequence; + if (unlikely(!(m && m->sq_item))) { + PyErr_Format(PyExc_TypeError, "'%.200s' object is not subscriptable", Py_TYPE(obj)->tp_name); + return NULL; + } + key_value = __Pyx_PyIndex_AsSsize_t(index); + if (likely(key_value != -1 || !(runerr = PyErr_Occurred()))) { + return __Pyx_GetItemInt_Fast(obj, key_value, 0, 1, 1); + } + if (PyErr_GivenExceptionMatches(runerr, PyExc_OverflowError)) { + PyErr_Clear(); + PyErr_Format(PyExc_IndexError, "cannot fit '%.200s' into an index-sized integer", Py_TYPE(index)->tp_name); + } + return NULL; +} +static PyObject *__Pyx_PyObject_GetItem(PyObject *obj, PyObject* key) { + PyMappingMethods *m = Py_TYPE(obj)->tp_as_mapping; + if (likely(m && m->mp_subscript)) { + return m->mp_subscript(obj, key); + } + return __Pyx_PyObject_GetIndex(obj, key); +} +#endif + /* decode_c_string */ - static CYTHON_INLINE PyObject* __Pyx_decode_c_string( + static CYTHON_INLINE PyObject* __Pyx_decode_c_string( const char* cstring, Py_ssize_t start, Py_ssize_t stop, const char* encoding, const char* errors, PyObject* (*decode_func)(const char *s, Py_ssize_t size, const char *errors)) { @@ -25096,7 +25350,7 @@ static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) } /* GetAttr3 */ - static PyObject *__Pyx_GetAttr3Default(PyObject *d) { + static PyObject *__Pyx_GetAttr3Default(PyObject *d) { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign if (unlikely(!__Pyx_PyErr_ExceptionMatches(PyExc_AttributeError))) @@ -25111,7 +25365,7 @@ static CYTHON_INLINE PyObject *__Pyx_GetAttr3(PyObject *o, PyObject *n, PyObject } /* SwapException */ - #if CYTHON_FAST_THREAD_STATE + #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSwap(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { PyObject *tmp_type, *tmp_value, *tmp_tb; #if PY_VERSION_HEX >= 0x030700A2 @@ -25145,7 +25399,7 @@ static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, #endif /* Import */ - static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { + static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { PyObject *empty_list = 0; PyObject *module = 0; PyObject *global_dict = 0; @@ -25209,8 +25463,80 @@ static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, return module; } +/* FastTypeChecks */ + #if CYTHON_COMPILING_IN_CPYTHON +static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { + while (a) { + a = a->tp_base; + if (a == b) + return 1; + } + return b == &PyBaseObject_Type; +} +static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b) { + PyObject *mro; + if (a == b) return 1; + mro = a->tp_mro; + if (likely(mro)) { + Py_ssize_t i, n; + n = PyTuple_GET_SIZE(mro); + for (i = 0; i < n; i++) { + if (PyTuple_GET_ITEM(mro, i) == (PyObject *)b) + return 1; + } + return 0; + } + return __Pyx_InBases(a, b); +} +#if PY_MAJOR_VERSION == 2 +static int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject* exc_type2) { + PyObject *exception, *value, *tb; + int res; + __Pyx_PyThreadState_declare + __Pyx_PyThreadState_assign + __Pyx_ErrFetch(&exception, &value, &tb); + res = exc_type1 ? PyObject_IsSubclass(err, exc_type1) : 0; + if (unlikely(res == -1)) { + PyErr_WriteUnraisable(err); + res = 0; + } + if (!res) { + res = PyObject_IsSubclass(err, exc_type2); + if (unlikely(res == -1)) { + PyErr_WriteUnraisable(err); + res = 0; + } + } + __Pyx_ErrRestore(exception, value, tb); + return res; +} +#else +static CYTHON_INLINE int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject *exc_type2) { + int res = exc_type1 ? __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type1) : 0; + if (!res) { + res = __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type2); + } + return res; +} +#endif +static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches(PyObject *err, PyObject* exc_type) { + if (likely(err == exc_type)) return 1; + if (likely(PyExceptionClass_Check(err))) { + return __Pyx_inner_PyErr_GivenExceptionMatches2(err, NULL, exc_type); + } + return PyErr_GivenExceptionMatches(err, exc_type); +} +static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObject *exc_type1, PyObject *exc_type2) { + if (likely(err == exc_type1 || err == exc_type2)) return 1; + if (likely(PyExceptionClass_Check(err))) { + return __Pyx_inner_PyErr_GivenExceptionMatches2(err, exc_type1, exc_type2); + } + return (PyErr_GivenExceptionMatches(err, exc_type1) || PyErr_GivenExceptionMatches(err, exc_type2)); +} +#endif + /* PyIntBinop */ - #if !CYTHON_COMPILING_IN_PYPY + #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED long intval, CYTHON_UNUSED int inplace) { #if PY_MAJOR_VERSION < 3 if (likely(PyInt_CheckExact(op1))) { @@ -25248,6 +25574,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -25258,6 +25585,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -25268,6 +25596,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -25278,6 +25607,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -25288,6 +25618,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); @@ -25298,6 +25629,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED goto long_long; #endif } + CYTHON_FALLTHROUGH; default: return PyLong_Type.tp_as_number->nb_add(op1, op2); } } @@ -25326,7 +25658,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED #endif /* None */ - static CYTHON_INLINE long __Pyx_div_long(long a, long b) { + static CYTHON_INLINE long __Pyx_div_long(long a, long b) { long q = a / b; long r = a - q*b; q -= ((r != 0) & ((r ^ b) < 0)); @@ -25334,7 +25666,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* WriteUnraisableException */ - static void __Pyx_WriteUnraisable(const char *name, CYTHON_UNUSED int clineno, + static void __Pyx_WriteUnraisable(const char *name, CYTHON_UNUSED int clineno, CYTHON_UNUSED int lineno, CYTHON_UNUSED const char *filename, int full_traceback, CYTHON_UNUSED int nogil) { PyObject *old_exc, *old_val, *old_tb; @@ -25376,7 +25708,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* ImportFrom */ - static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { + static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { PyObject* value = __Pyx_PyObject_GetAttrStr(module, name); if (unlikely(!value) && PyErr_ExceptionMatches(PyExc_AttributeError)) { PyErr_Format(PyExc_ImportError, @@ -25390,7 +25722,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* HasAttr */ - static CYTHON_INLINE int __Pyx_HasAttr(PyObject *o, PyObject *n) { + static CYTHON_INLINE int __Pyx_HasAttr(PyObject *o, PyObject *n) { PyObject *r; if (unlikely(!__Pyx_PyBaseString_Check(n))) { PyErr_SetString(PyExc_TypeError, @@ -25407,8 +25739,58 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } } +/* PyObject_GenericGetAttrNoDict */ + #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static PyObject *__Pyx_RaiseGenericGetAttributeError(PyTypeObject *tp, PyObject *attr_name) { + PyErr_Format(PyExc_AttributeError, +#if PY_MAJOR_VERSION >= 3 + "'%.50s' object has no attribute '%U'", + tp->tp_name, attr_name); +#else + "'%.50s' object has no attribute '%.400s'", + tp->tp_name, PyString_AS_STRING(attr_name)); +#endif + return NULL; +} +static CYTHON_INLINE PyObject* __Pyx_PyObject_GenericGetAttrNoDict(PyObject* obj, PyObject* attr_name) { + PyObject *descr; + PyTypeObject *tp = Py_TYPE(obj); + if (unlikely(!PyString_Check(attr_name))) { + return PyObject_GenericGetAttr(obj, attr_name); + } + assert(!tp->tp_dictoffset); + descr = _PyType_Lookup(tp, attr_name); + if (unlikely(!descr)) { + return __Pyx_RaiseGenericGetAttributeError(tp, attr_name); + } + Py_INCREF(descr); + #if PY_MAJOR_VERSION < 3 + if (likely(PyType_HasFeature(Py_TYPE(descr), Py_TPFLAGS_HAVE_CLASS))) + #endif + { + descrgetfunc f = Py_TYPE(descr)->tp_descr_get; + if (unlikely(f)) { + PyObject *res = f(descr, obj, (PyObject *)tp); + Py_DECREF(descr); + return res; + } + } + return descr; +} +#endif + +/* PyObject_GenericGetAttr */ + #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 +static PyObject* __Pyx_PyObject_GenericGetAttr(PyObject* obj, PyObject* attr_name) { + if (unlikely(Py_TYPE(obj)->tp_dictoffset)) { + return PyObject_GenericGetAttr(obj, attr_name); + } + return __Pyx_PyObject_GenericGetAttrNoDict(obj, attr_name); +} +#endif + /* SetVTable */ - static int __Pyx_SetVtable(PyObject *dict, void *vtable) { + static int __Pyx_SetVtable(PyObject *dict, void *vtable) { #if PY_VERSION_HEX >= 0x02070000 PyObject *ob = PyCapsule_New(vtable, 0, 0); #else @@ -25426,7 +25808,7 @@ static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, CYTHON_UNUSED } /* SetupReduce */ - static int __Pyx_setup_reduce_is_named(PyObject* meth, PyObject* name) { + static int __Pyx_setup_reduce_is_named(PyObject* meth, PyObject* name) { int ret; PyObject *name_attr; name_attr = __Pyx_PyObject_GetAttrStr(meth, __pyx_n_s_name_2); @@ -25502,7 +25884,7 @@ static int __Pyx_setup_reduce(PyObject* type_obj) { } /* FetchCommonType */ - static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type) { + static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type) { PyObject* fake_module; PyTypeObject* cached_type = NULL; fake_module = PyImport_AddModule((char*) "_cython_" CYTHON_ABI); @@ -25541,7 +25923,8 @@ static int __Pyx_setup_reduce(PyObject* type_obj) { } /* CythonFunction */ - static PyObject * + #include +static PyObject * __Pyx_CyFunction_get_doc(__pyx_CyFunctionObject *op, CYTHON_UNUSED void *closure) { if (unlikely(op->func_doc == NULL)) { @@ -26134,7 +26517,7 @@ static CYTHON_INLINE void __Pyx_CyFunction_SetAnnotationsDict(PyObject *func, Py } /* FusedFunction */ - static PyObject * + static PyObject * __pyx_FusedFunction_New(PyTypeObject *type, PyMethodDef *ml, int flags, PyObject *qualname, PyObject *self, PyObject *module, PyObject *globals, @@ -26464,18 +26847,21 @@ static int __pyx_FusedFunction_init(void) { } /* CLineInTraceback */ - #ifndef CYTHON_CLINE_IN_TRACEBACK + #ifndef CYTHON_CLINE_IN_TRACEBACK static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_line) { PyObject *use_cline; PyObject *ptype, *pvalue, *ptraceback; #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif + if (unlikely(!__pyx_cython_runtime)) { + return c_line; + } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { - use_cline = PyDict_GetItem(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); + use_cline = __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback); } else #endif { @@ -26501,7 +26887,7 @@ static int __Pyx_CLineForTraceback(CYTHON_UNUSED PyThreadState *tstate, int c_li #endif /* CodeObjectCache */ - static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { + static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { int start = 0, mid = 0, end = count - 1; if (end >= 0 && code_line > entries[end].code_line) { return count; @@ -26581,7 +26967,7 @@ static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { } /* AddTraceback */ - #include "compile.h" + #include "compile.h" #include "frameobject.h" #include "traceback.h" static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( @@ -26689,8 +27075,8 @@ static void __Pyx_ReleaseBuffer(Py_buffer *view) { #endif - /* MemviewSliceIsContig */ - static int + /* MemviewSliceIsContig */ + static int __pyx_memviewslice_is_contig(const __Pyx_memviewslice mvs, char order, int ndim) { int i, index, step, start; @@ -26712,7 +27098,7 @@ __pyx_memviewslice_is_contig(const __Pyx_memviewslice mvs, char order, int ndim) } /* OverlappingSlices */ - static void + static void __pyx_get_array_memory_extents(__Pyx_memviewslice *slice, void **out_start, void **out_end, int ndim, size_t itemsize) @@ -26748,7 +27134,7 @@ __pyx_slices_overlap(__Pyx_memviewslice *slice1, } /* Capsule */ - static CYTHON_INLINE PyObject * + static CYTHON_INLINE PyObject * __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) { PyObject *cobj; @@ -26761,7 +27147,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) } /* CIntFromPyVerify */ - #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ + #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) #define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) @@ -26783,7 +27169,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -26814,7 +27200,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) } /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_float_complex __pyx_t_float_complex_from_parts(float x, float y) { return ::std::complex< float >(x, y); @@ -26834,7 +27220,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_float(__pyx_t_float_complex a, __pyx_t_float_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -26969,7 +27355,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) #endif /* Declarations */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #ifdef __cplusplus static CYTHON_INLINE __pyx_t_double_complex __pyx_t_double_complex_from_parts(double x, double y) { return ::std::complex< double >(x, y); @@ -26989,7 +27375,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) #endif /* Arithmetic */ - #if CYTHON_CCOMPLEX + #if CYTHON_CCOMPLEX #else static CYTHON_INLINE int __Pyx_c_eq_double(__pyx_t_double_complex a, __pyx_t_double_complex b) { return (a.real == b.real) && (a.imag == b.imag); @@ -27124,7 +27510,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) #endif /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -27155,7 +27541,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) } /* CIntToPy */ - static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { + static CYTHON_INLINE PyObject* __Pyx_PyInt_From_enum__NPY_TYPES(enum NPY_TYPES value) { const enum NPY_TYPES neg_one = (enum NPY_TYPES) -1, const_zero = (enum NPY_TYPES) 0; const int is_unsigned = neg_one > const_zero; if (is_unsigned) { @@ -27186,7 +27572,7 @@ __pyx_capsule_create(void *p, CYTHON_UNUSED const char *sig) } /* MemviewSliceCopyTemplate */ - static __Pyx_memviewslice + static __Pyx_memviewslice __pyx_memoryview_copy_new_contig(const __Pyx_memviewslice *from_mvs, const char *mode, int ndim, size_t sizeof_dtype, int contig_flag, @@ -27253,7 +27639,7 @@ __pyx_memoryview_copy_new_contig(const __Pyx_memviewslice *from_mvs, } /* CIntFromPy */ - static CYTHON_INLINE size_t __Pyx_PyInt_As_size_t(PyObject *x) { + static CYTHON_INLINE size_t __Pyx_PyInt_As_size_t(PyObject *x) { const size_t neg_one = (size_t) -1, const_zero = (size_t) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -27442,7 +27828,7 @@ __pyx_memoryview_copy_new_contig(const __Pyx_memviewslice *from_mvs, } /* CIntFromPy */ - static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { + static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { const int neg_one = (int) -1, const_zero = (int) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -27631,7 +28017,7 @@ __pyx_memoryview_copy_new_contig(const __Pyx_memviewslice *from_mvs, } /* ImportNumPyArray */ - static PyObject* __Pyx__ImportNumPyArray(void) { + static PyObject* __Pyx__ImportNumPyArray(void) { PyObject *numpy_module, *ndarray_object = NULL; numpy_module = __Pyx_Import(__pyx_n_s_numpy, NULL, 0); if (likely(numpy_module)) { @@ -27657,7 +28043,7 @@ static CYTHON_INLINE PyObject* __Pyx_ImportNumPyArrayTypeIfAvailable(void) { } /* CIntFromPy */ - static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { + static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { const long neg_one = (long) -1, const_zero = (long) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -27846,7 +28232,7 @@ static CYTHON_INLINE PyObject* __Pyx_ImportNumPyArrayTypeIfAvailable(void) { } /* CIntFromPy */ - static CYTHON_INLINE char __Pyx_PyInt_As_char(PyObject *x) { + static CYTHON_INLINE char __Pyx_PyInt_As_char(PyObject *x) { const char neg_one = (char) -1, const_zero = (char) 0; const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 @@ -28034,80 +28420,8 @@ static CYTHON_INLINE PyObject* __Pyx_ImportNumPyArrayTypeIfAvailable(void) { return (char) -1; } -/* FastTypeChecks */ - #if CYTHON_COMPILING_IN_CPYTHON -static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { - while (a) { - a = a->tp_base; - if (a == b) - return 1; - } - return b == &PyBaseObject_Type; -} -static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b) { - PyObject *mro; - if (a == b) return 1; - mro = a->tp_mro; - if (likely(mro)) { - Py_ssize_t i, n; - n = PyTuple_GET_SIZE(mro); - for (i = 0; i < n; i++) { - if (PyTuple_GET_ITEM(mro, i) == (PyObject *)b) - return 1; - } - return 0; - } - return __Pyx_InBases(a, b); -} -#if PY_MAJOR_VERSION == 2 -static int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject* exc_type2) { - PyObject *exception, *value, *tb; - int res; - __Pyx_PyThreadState_declare - __Pyx_PyThreadState_assign - __Pyx_ErrFetch(&exception, &value, &tb); - res = exc_type1 ? PyObject_IsSubclass(err, exc_type1) : 0; - if (unlikely(res == -1)) { - PyErr_WriteUnraisable(err); - res = 0; - } - if (!res) { - res = PyObject_IsSubclass(err, exc_type2); - if (unlikely(res == -1)) { - PyErr_WriteUnraisable(err); - res = 0; - } - } - __Pyx_ErrRestore(exception, value, tb); - return res; -} -#else -static CYTHON_INLINE int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject *exc_type2) { - int res = exc_type1 ? __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type1) : 0; - if (!res) { - res = __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type2); - } - return res; -} -#endif -static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches(PyObject *err, PyObject* exc_type) { - if (likely(err == exc_type)) return 1; - if (likely(PyExceptionClass_Check(err))) { - return __Pyx_inner_PyErr_GivenExceptionMatches2(err, NULL, exc_type); - } - return PyErr_GivenExceptionMatches(err, exc_type); -} -static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObject *exc_type1, PyObject *exc_type2) { - if (likely(err == exc_type1 || err == exc_type2)) return 1; - if (likely(PyExceptionClass_Check(err))) { - return __Pyx_inner_PyErr_GivenExceptionMatches2(err, exc_type1, exc_type2); - } - return (PyErr_GivenExceptionMatches(err, exc_type1) || PyErr_GivenExceptionMatches(err, exc_type2)); -} -#endif - /* IsLittleEndian */ - static CYTHON_INLINE int __Pyx_Is_Little_Endian(void) + static CYTHON_INLINE int __Pyx_Is_Little_Endian(void) { union { uint32_t u32; @@ -28118,7 +28432,7 @@ static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObj } /* BufferFormatCheck */ - static void __Pyx_BufFmt_Init(__Pyx_BufFmt_Context* ctx, + static void __Pyx_BufFmt_Init(__Pyx_BufFmt_Context* ctx, __Pyx_BufFmt_StackElem* stack, __Pyx_TypeInfo* type) { stack[0].field = &ctx->root; @@ -28577,6 +28891,7 @@ static const char* __Pyx_BufFmt_CheckString(__Pyx_BufFmt_Context* ctx, const cha __Pyx_BufFmt_RaiseUnexpectedChar('Z'); return NULL; } + CYTHON_FALLTHROUGH; case 'c': case 'b': case 'B': case 'h': case 'H': case 'i': case 'I': case 'l': case 'L': case 'q': case 'Q': case 'f': case 'd': case 'g': @@ -28589,6 +28904,7 @@ static const char* __Pyx_BufFmt_CheckString(__Pyx_BufFmt_Context* ctx, const cha ++ts; break; } + CYTHON_FALLTHROUGH; case 's': if (__Pyx_BufFmt_ProcessTypeChunk(ctx) == -1) return NULL; ctx->enc_count = ctx->new_count; @@ -28618,7 +28934,7 @@ static const char* __Pyx_BufFmt_CheckString(__Pyx_BufFmt_Context* ctx, const cha } /* TypeInfoCompare */ - static int + static int __pyx_typeinfo_cmp(__Pyx_TypeInfo *a, __Pyx_TypeInfo *b) { int i; @@ -28659,7 +28975,7 @@ __pyx_typeinfo_cmp(__Pyx_TypeInfo *a, __Pyx_TypeInfo *b) } /* MemviewSliceValidateAndInit */ - static int + static int __pyx_check_strides(Py_buffer *buf, int dim, int ndim, int spec) { if (buf->shape[dim] <= 1) @@ -28841,7 +29157,7 @@ static int __Pyx_ValidateAndInit_memviewslice( } /* ObjectToMemviewSlice */ - static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_double(PyObject *obj) { + static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_double(PyObject *obj, int writable_flag) { __Pyx_memviewslice result = { 0, 0, { 0 }, { 0 }, { 0 } }; __Pyx_BufFmt_StackElem stack[1]; int axes_specs[] = { (__Pyx_MEMVIEW_DIRECT | __Pyx_MEMVIEW_STRIDED) }; @@ -28851,7 +29167,7 @@ static int __Pyx_ValidateAndInit_memviewslice( return result; } retcode = __Pyx_ValidateAndInit_memviewslice(axes_specs, 0, - PyBUF_RECORDS, 1, + PyBUF_RECORDS_RO | writable_flag, 1, &__Pyx_TypeInfo_double, stack, &result, obj); if (unlikely(retcode == -1)) @@ -28864,7 +29180,7 @@ static int __Pyx_ValidateAndInit_memviewslice( } /* ObjectToMemviewSlice */ - static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_float(PyObject *obj) { + static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_ds_float(PyObject *obj, int writable_flag) { __Pyx_memviewslice result = { 0, 0, { 0 }, { 0 }, { 0 } }; __Pyx_BufFmt_StackElem stack[1]; int axes_specs[] = { (__Pyx_MEMVIEW_DIRECT | __Pyx_MEMVIEW_STRIDED) }; @@ -28874,7 +29190,7 @@ static int __Pyx_ValidateAndInit_memviewslice( return result; } retcode = __Pyx_ValidateAndInit_memviewslice(axes_specs, 0, - PyBUF_RECORDS, 1, + PyBUF_RECORDS_RO | writable_flag, 1, &__Pyx_TypeInfo_float, stack, &result, obj); if (unlikely(retcode == -1)) @@ -28887,7 +29203,7 @@ static int __Pyx_ValidateAndInit_memviewslice( } /* ObjectToMemviewSlice */ - static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_double(PyObject *obj) { + static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_double(PyObject *obj, int writable_flag) { __Pyx_memviewslice result = { 0, 0, { 0 }, { 0 }, { 0 } }; __Pyx_BufFmt_StackElem stack[1]; int axes_specs[] = { (__Pyx_MEMVIEW_DIRECT | __Pyx_MEMVIEW_STRIDED), (__Pyx_MEMVIEW_DIRECT | __Pyx_MEMVIEW_STRIDED) }; @@ -28897,7 +29213,7 @@ static int __Pyx_ValidateAndInit_memviewslice( return result; } retcode = __Pyx_ValidateAndInit_memviewslice(axes_specs, 0, - PyBUF_RECORDS, 2, + PyBUF_RECORDS_RO | writable_flag, 2, &__Pyx_TypeInfo_double, stack, &result, obj); if (unlikely(retcode == -1)) @@ -28910,7 +29226,7 @@ static int __Pyx_ValidateAndInit_memviewslice( } /* ObjectToMemviewSlice */ - static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_float(PyObject *obj) { + static CYTHON_INLINE __Pyx_memviewslice __Pyx_PyObject_to_MemoryviewSlice_dsds_float(PyObject *obj, int writable_flag) { __Pyx_memviewslice result = { 0, 0, { 0 }, { 0 }, { 0 } }; __Pyx_BufFmt_StackElem stack[1]; int axes_specs[] = { (__Pyx_MEMVIEW_DIRECT | __Pyx_MEMVIEW_STRIDED), (__Pyx_MEMVIEW_DIRECT | __Pyx_MEMVIEW_STRIDED) }; @@ -28920,7 +29236,7 @@ static int __Pyx_ValidateAndInit_memviewslice( return result; } retcode = __Pyx_ValidateAndInit_memviewslice(axes_specs, 0, - PyBUF_RECORDS, 2, + PyBUF_RECORDS_RO | writable_flag, 2, &__Pyx_TypeInfo_float, stack, &result, obj); if (unlikely(retcode == -1)) @@ -28933,7 +29249,7 @@ static int __Pyx_ValidateAndInit_memviewslice( } /* CheckBinaryVersion */ - static int __Pyx_check_binary_version(void) { + static int __Pyx_check_binary_version(void) { char ctversion[4], rtversion[4]; PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION); PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion()); @@ -28949,7 +29265,7 @@ static int __Pyx_ValidateAndInit_memviewslice( } /* ModuleImport */ - #ifndef __PYX_HAVE_RT_ImportModule + #ifndef __PYX_HAVE_RT_ImportModule #define __PYX_HAVE_RT_ImportModule static PyObject *__Pyx_ImportModule(const char *name) { PyObject *py_name = 0; @@ -28967,7 +29283,7 @@ static PyObject *__Pyx_ImportModule(const char *name) { #endif /* TypeImport */ - #ifndef __PYX_HAVE_RT_ImportType + #ifndef __PYX_HAVE_RT_ImportType #define __PYX_HAVE_RT_ImportType static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class_name, size_t size, int strict) @@ -29032,7 +29348,7 @@ static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class #endif /* InitStrings */ - static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { + static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { while (t->p) { #if PY_MAJOR_VERSION < 3 if (t->is_unicode) { @@ -29058,7 +29374,7 @@ static PyTypeObject *__Pyx_ImportType(const char *module_name, const char *class if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) - PyErr_Clear(); + return -1; ++t; } return 0; @@ -29272,6 +29588,9 @@ static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_DECREF(x); return ival; } +static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { + return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); +} static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } From 408a714e836484e914a7e3622b4f0f99a6d27ddd Mon Sep 17 00:00:00 2001 From: Dmitry Persiyanov Date: Thu, 12 Jul 2018 06:35:20 +0300 Subject: [PATCH 24/40] [GSoC 2018] Multistream API for vocabulary building in *2vec (#2078) * multistream scan vocab for doc2vec, word2vec & fastText * fixes * fix tags for doc2vec * fix tests * removed benchmark vocab * addressing comments * make interfaces and documentation more pretty * add word2vec multistream tests * fix pep8 * iteritems -> items * more precise test * add doc2vec tests * add fasttext tests * remove prints * fix seed=42 * fixed tests * add build_vocab test for fasttext * fix * change size from 10 to 5 in fasttext test because of appveyor memory limits * another test with memory error * fix py3 tests * fix iteritems for py3 * fix functools reduce * addressing comments * addressing @jayantj comments * fix language * add final vocab pruning in multistream modes * keys -> iterkeys * use heapq.nlargest * fix * multistream flag to input_streams param * fix tests * fix flake 8 * fix doc2vec docstrings * fix merging streams * fix doc2vec * max_vocab_size -> max_vocab_size / workers * fixed * / -> // (py3 division) * fix * fix docstring --- gensim/models/base_any2vec.py | 65 +++++++--- gensim/models/doc2vec.py | 230 +++++++++++++++++++++++++--------- gensim/models/fasttext.py | 41 +++--- gensim/models/word2vec.py | 135 ++++++++++++++++---- gensim/test/test_doc2vec.py | 34 ++++- gensim/test/test_fasttext.py | 47 +++++++ gensim/test/test_utils.py | 23 ++++ gensim/test/test_word2vec.py | 40 +++++- gensim/utils.py | 47 ++++++- 9 files changed, 541 insertions(+), 121 deletions(-) diff --git a/gensim/models/base_any2vec.py b/gensim/models/base_any2vec.py index 5cdb54930d..8f7123e1d7 100644 --- a/gensim/models/base_any2vec.py +++ b/gensim/models/base_any2vec.py @@ -43,6 +43,7 @@ from types import GeneratorType from gensim.utils import deprecated import warnings +import itertools try: from queue import Queue @@ -130,6 +131,11 @@ def _check_training_sanity(self, epochs=None, total_examples=None, total_words=N """Check that the training parameters provided make sense. e.g. raise error if `epochs` not provided.""" raise NotImplementedError() + def _check_input_data_sanity(self, data_iterable=None, data_iterables=None): + """Check that only one argument is not None.""" + if not ((data_iterable is not None) ^ (data_iterables is not None)): + raise ValueError("You must provide only one of singlestream or multistream arguments.") + def _worker_loop(self, job_queue, progress_queue): """Train the model, lifting batches of data from the queue. @@ -322,7 +328,7 @@ def _log_epoch_progress(self, progress_queue, job_queue, cur_epoch=0, total_exam self.total_train_time += elapsed return trained_word_count, raw_word_count, job_tally - def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, + def _train_epoch(self, data_iterable=None, data_iterables=None, cur_epoch=0, total_examples=None, total_words=None, queue_factor=2, report_delay=1.0): """Train the model for a single epoch. @@ -330,6 +336,8 @@ def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, ---------- data_iterable : iterable of list of object The input corpus. This will be split in chunks and these chunks will be pushed to the queue. + data_iterables : iterable of iterables of list of object + The iterable of input streams like `data_iterable`. Use this parameter in multistream mode. cur_epoch : int, optional The current training epoch, needed to compute the training parameters for each job. For example in many implementations the learning rate would be dropping with the number of epochs. @@ -353,6 +361,7 @@ def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, * Total word count used in training. """ + self._check_input_data_sanity(data_iterable, data_iterables) job_queue = Queue(maxsize=queue_factor * self.workers) progress_queue = Queue(maxsize=(queue_factor + 1) * self.workers) @@ -363,6 +372,9 @@ def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, for _ in xrange(self.workers) ] + # Chain all input streams into one, because multistream training is not supported yet. + if data_iterables is not None: + data_iterable = itertools.chain(*data_iterables) workers.append(threading.Thread( target=self._job_producer, args=(data_iterable, job_queue), @@ -378,7 +390,7 @@ def _train_epoch(self, data_iterable, cur_epoch=0, total_examples=None, return trained_word_count, raw_word_count, job_tally - def train(self, data_iterable, epochs=None, total_examples=None, + def train(self, data_iterable=None, data_iterables=None, epochs=None, total_examples=None, total_words=None, queue_factor=2, report_delay=1.0, callbacks=(), **kwargs): """Train the model for multiple epochs using multiple workers. @@ -433,8 +445,9 @@ def train(self, data_iterable, epochs=None, total_examples=None, callback.on_epoch_begin(self) trained_word_count_epoch, raw_word_count_epoch, job_tally_epoch = self._train_epoch( - data_iterable, cur_epoch=cur_epoch, total_examples=total_examples, total_words=total_words, - queue_factor=queue_factor, report_delay=report_delay) + data_iterable=data_iterable, data_iterables=data_iterables, cur_epoch=cur_epoch, + total_examples=total_examples, total_words=total_words, queue_factor=queue_factor, + report_delay=report_delay) trained_word_count += trained_word_count_epoch raw_word_count += raw_word_count_epoch job_tally += job_tally_epoch @@ -525,9 +538,9 @@ def _do_train_job(self, data_iterable, job_parameters, thread_private_mem): def _set_train_params(self, **kwargs): raise NotImplementedError() - def __init__(self, sentences=None, workers=3, vector_size=100, epochs=5, callbacks=(), batch_words=10000, - trim_rule=None, sg=0, alpha=0.025, window=5, seed=1, hs=0, negative=5, ns_exponent=0.75, cbow_mean=1, - min_alpha=0.0001, compute_loss=False, fast_version=0, **kwargs): + def __init__(self, sentences=None, input_streams=None, workers=3, vector_size=100, epochs=5, callbacks=(), + batch_words=10000, trim_rule=None, sg=0, alpha=0.025, window=5, seed=1, hs=0, negative=5, + ns_exponent=0.75, cbow_mean=1, min_alpha=0.0001, compute_loss=False, fast_version=0, **kwargs): """ Parameters @@ -624,13 +637,20 @@ def __init__(self, sentences=None, workers=3, vector_size=100, epochs=5, callbac self.neg_labels = zeros(self.negative + 1) self.neg_labels[0] = 1. - if sentences is not None: - if isinstance(sentences, GeneratorType): + if sentences is not None or input_streams is not None: + self._check_input_data_sanity(data_iterable=sentences, data_iterables=input_streams) + if input_streams is not None: + if not isinstance(input_streams, (tuple, list)): + raise TypeError("You must pass tuple or list as the input_streams argument.") + if any(isinstance(stream, GeneratorType) for stream in input_streams): + raise TypeError("You can't pass a generator as any of input streams. Try an iterator.") + elif isinstance(sentences, GeneratorType): raise TypeError("You can't pass a generator as the sentences argument. Try an iterator.") - self.build_vocab(sentences, trim_rule=trim_rule) + + self.build_vocab(sentences=sentences, input_streams=input_streams, trim_rule=trim_rule) self.train( - sentences, total_examples=self.corpus_count, epochs=self.epochs, start_alpha=self.alpha, - end_alpha=self.min_alpha, compute_loss=compute_loss) + sentences=sentences, input_streams=input_streams, total_examples=self.corpus_count, epochs=self.epochs, + start_alpha=self.alpha, end_alpha=self.min_alpha, compute_loss=compute_loss) else: if trim_rule is not None: logger.warning( @@ -763,7 +783,8 @@ def __str__(self): self.__class__.__name__, len(self.wv.index2word), self.vector_size, self.alpha ) - def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_vocab=False, trim_rule=None, **kwargs): + def build_vocab(self, sentences=None, input_streams=None, workers=None, update=False, progress_per=10000, + keep_raw_vocab=False, trim_rule=None, **kwargs): """Build vocabulary from a sequence of sentences (can be a once-only generator stream). Parameters @@ -773,7 +794,13 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` module for such examples. - update : bool, optional + input_streams : list or tuple of iterable of iterables + The tuple or list of `sentences`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. + workers : int + Used if `input_streams` is passed. Determines how many processes to use for vocab building. + Actual number of workers is determined by `min(len(input_streams), workers)`. + update : bool If true, the new words in `sentences` will be added to model's vocab. progress_per : int, optional Indicates how many words to process before showing/updating the progress. @@ -797,8 +824,10 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca Key word arguments propagated to `self.vocabulary.prepare_vocab` """ + workers = workers or self.workers total_words, corpus_count = self.vocabulary.scan_vocab( - sentences, progress_per=progress_per, trim_rule=trim_rule) + sentences=sentences, input_streams=input_streams, progress_per=progress_per, trim_rule=trim_rule, + workers=workers) self.corpus_count = corpus_count report_values = self.vocabulary.prepare_vocab( self.hs, self.negative, self.wv, update=update, keep_raw_vocab=keep_raw_vocab, @@ -887,7 +916,7 @@ def estimate_memory(self, vocab_size=None, report=None): ) return report - def train(self, sentences, total_examples=None, total_words=None, + def train(self, sentences=None, input_streams=None, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, compute_loss=False, callbacks=()): """Train the model. If the hyper-parameters are passed, they override the ones set in the constructor. @@ -933,8 +962,8 @@ def train(self, sentences, total_examples=None, total_words=None, self.compute_loss = compute_loss self.running_training_loss = 0.0 return super(BaseWordEmbeddingsModel, self).train( - sentences, total_examples=total_examples, total_words=total_words, - epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, + data_iterable=sentences, data_iterables=input_streams, total_examples=total_examples, + total_words=total_words, epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, queue_factor=queue_factor, report_delay=report_delay, compute_loss=compute_loss, callbacks=callbacks) def _get_job_params(self, cur_epoch): diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py index bf1eac8264..57638e71bc 100644 --- a/gensim/models/doc2vec.py +++ b/gensim/models/doc2vec.py @@ -56,6 +56,7 @@ import logging import os import warnings +import multiprocessing try: from queue import Queue @@ -64,6 +65,7 @@ from collections import namedtuple, defaultdict from timeit import default_timer +from functools import reduce from numpy import zeros, float32 as REAL, empty, ones, \ memmap as np_memmap, vstack, integer, dtype, sum as np_sum, add as np_add, repeat as np_repeat, concatenate @@ -74,7 +76,7 @@ from gensim.models.word2vec import Word2VecKeyedVectors, Word2VecVocab, Word2VecTrainables, train_cbow_pair,\ train_sg_pair, train_batch_sg from six.moves import xrange -from six import string_types, integer_types, itervalues +from six import string_types, integer_types, itervalues, iteritems from gensim.models.base_any2vec import BaseWordEmbeddingsModel from gensim.models.keyedvectors import Doc2VecKeyedVectors from types import GeneratorType @@ -435,8 +437,9 @@ class Doc2Vec(BaseWordEmbeddingsModel): includes not only the word vectors of each word in the context, but also the paragraph vector. """ - def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0, dm_tag_count=1, - docvecs=None, docvecs_mapfile=None, comment=None, trim_rule=None, callbacks=(), **kwargs): + def __init__(self, documents=None, input_streams=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0, + dm_tag_count=1, docvecs=None, docvecs_mapfile=None, comment=None, trim_rule=None, callbacks=(), + **kwargs): """ Parameters @@ -445,6 +448,9 @@ def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0 Input corpus, can be simply a list of elements, but for larger corpora,consider an iterable that streams the documents directly from disk/network. If you don't supply `documents`, the model is left uninitialized -- use if you plan to initialize it in some other way. + input_streams : list or tuple of iterable of iterables + The tuple or list of `documents`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. dm : {1,0}, optional Defines the training algorithm. If `dm=1`, 'distributed memory' (PV-DM) is used. Otherwise, `distributed bag of words` (PV-DBOW) is employed. @@ -566,12 +572,22 @@ def __init__(self, documents=None, dm_mean=None, dm=1, dbow_words=0, dm_concat=0 self.docvecs = docvecs or Doc2VecKeyedVectors(self.vector_size, docvecs_mapfile) self.comment = comment - if documents is not None: - if isinstance(documents, GeneratorType): + if documents is not None or input_streams is not None: + self._check_input_data_sanity(data_iterable=documents, data_iterables=input_streams) + if input_streams is not None: + if not isinstance(input_streams, (tuple, list)): + raise TypeError("You must pass tuple or list as the input_streams argument.") + if any(isinstance(stream, GeneratorType) for stream in input_streams): + raise TypeError("You can't pass a generator as any of input streams. Try an iterator.") + if any(isinstance(stream, TaggedLineDocument) for stream in input_streams): + warnings.warn("Using TaggedLineDocument in multistream mode can lead to incorrect results " + "because of tags collision.") + elif isinstance(documents, GeneratorType): raise TypeError("You can't pass a generator as the documents argument. Try an iterator.") - self.build_vocab(documents, trim_rule=trim_rule) + self.build_vocab(documents=documents, input_streams=input_streams, + trim_rule=trim_rule, workers=self.workers) self.train( - documents, total_examples=self.corpus_count, epochs=self.epochs, + documents=documents, input_streams=input_streams, total_examples=self.corpus_count, epochs=self.epochs, start_alpha=self.alpha, end_alpha=self.min_alpha, callbacks=callbacks) @property @@ -661,7 +677,7 @@ def _do_train_job(self, job, alpha, inits): ) return tally, self._raw_word_count(job) - def train(self, documents, total_examples=None, total_words=None, + def train(self, documents=None, input_streams=None, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, callbacks=()): """Update the model's neural weights. @@ -683,6 +699,9 @@ def train(self, documents, total_examples=None, total_words=None, Can be simply a list of elements, but for larger corpora,consider an iterable that streams the documents directly from disk/network. If you don't supply `documents`, the model is left uninitialized -- use if you plan to initialize it in some other way. + input_streams : list or tuple of iterable of iterables + The tuple or list of `documents`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. total_examples : int, optional Count of sentences. total_words : int, optional @@ -712,7 +731,7 @@ def train(self, documents, total_examples=None, total_words=None, """ super(Doc2Vec, self).train( - documents, total_examples=total_examples, total_words=total_words, + sentences=documents, input_streams=input_streams, total_examples=total_examples, total_words=total_words, epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, queue_factor=queue_factor, report_delay=report_delay, callbacks=callbacks) @@ -997,7 +1016,8 @@ def estimate_memory(self, vocab_size=None, report=None): report['doctag_syn0'] = self.docvecs.count * self.vector_size * dtype(REAL).itemsize return super(Doc2Vec, self).estimate_memory(vocab_size, report=report) - def build_vocab(self, documents, update=False, progress_per=10000, keep_raw_vocab=False, trim_rule=None, **kwargs): + def build_vocab(self, documents=None, input_streams=None, update=False, progress_per=10000, keep_raw_vocab=False, + trim_rule=None, workers=None, **kwargs): """Build vocabulary from a sequence of sentences (can be a once-only generator stream). Parameters @@ -1006,6 +1026,9 @@ def build_vocab(self, documents, update=False, progress_per=10000, keep_raw_voca Can be simply a list of :class:`~gensim.models.doc2vec.TaggedDocument` elements, but for larger corpora, consider an iterable that streams the documents directly from disk/network. See :class:`~gensim.models.doc2vec.TaggedBrownCorpus` or :class:`~gensim.models.doc2vec.TaggedLineDocument` + input_streams : list or tuple of iterable of iterables + The tuple or list of `documents`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. update : bool If true, the new words in `sentences` will be added to model's vocab. progress_per : int @@ -1026,12 +1049,19 @@ def build_vocab(self, documents, update=False, progress_per=10000, keep_raw_voca * `count` (int) - the word's frequency count in the corpus * `min_count` (int) - the minimum count threshold. + workers : int + Used if `input_streams` is passed. Determines how many processes to use for vocab building. + Actual number of workers is determined by `min(len(input_streams), workers)`. + **kwargs Additional key word arguments passed to the internal vocabulary construction. """ + workers = workers or self.workers total_words, corpus_count = self.vocabulary.scan_vocab( - documents, self.docvecs, progress_per=progress_per, trim_rule=trim_rule) + documents=documents, input_streams=input_streams, docvecs=self.docvecs, + progress_per=progress_per, trim_rule=trim_rule, workers=workers + ) self.corpus_count = corpus_count report_values = self.vocabulary.prepare_vocab( self.hs, self.negative, self.wv, update=update, keep_raw_vocab=keep_raw_vocab, trim_rule=trim_rule, @@ -1095,6 +1125,53 @@ def build_vocab_from_freq(self, word_freq, keep_raw_vocab=False, corpus_count=No self.hs, self.negative, self.wv, self.docvecs, update=update) +def _note_doctag(key, document_length, docvecs): + """Note a document tag during initial corpus scan, for structure sizing.""" + if isinstance(key, integer_types + (integer,)): + docvecs.max_rawint = max(docvecs.max_rawint, key) + else: + if key in docvecs.doctags: + docvecs.doctags[key] = docvecs.doctags[key].repeat(document_length) + else: + docvecs.doctags[key] = Doctag(len(docvecs.offset2doctag), document_length, 1) + docvecs.offset2doctag.append(key) + docvecs.count = docvecs.max_rawint + 1 + len(docvecs.offset2doctag) + + +def _scan_vocab_worker(stream, progress_queue, max_vocab_size, trim_rule): + min_reduce = 1 + vocab = defaultdict(int) + doclen2tags = defaultdict(list) + checked_string_types = 0 + document_no = -1 + total_words = 0 + for document_no, document in enumerate(stream): + if not checked_string_types: + if isinstance(document.words, string_types): + log_msg = "Each 'words' should be a list of words (usually unicode strings). " \ + "First 'words' here is instead plain %s." % type(document.words) + progress_queue.put(log_msg) + + checked_string_types += 1 + + document_length = len(document.words) + + for tag in document.tags: + doclen2tags[document_length].append(tag) + + for word in document.words: + vocab[word] += 1 + total_words += len(document.words) + + if max_vocab_size and len(vocab) > max_vocab_size: + utils.prune_vocab(vocab, min_reduce, trim_rule=trim_rule) + min_reduce += 1 + + progress_queue.put((total_words, document_no + 1)) + progress_queue.put(None) + return vocab, doclen2tags + + class Doc2VecVocab(Word2VecVocab): """Vocabulary used by :class:`~gensim.models.doc2vec.Doc2Vec`. @@ -1132,38 +1209,51 @@ def __init__(self, max_vocab_size=None, min_count=5, sample=1e-3, sorted_vocab=T max_vocab_size=max_vocab_size, min_count=min_count, sample=sample, sorted_vocab=sorted_vocab, null_word=null_word, ns_exponent=ns_exponent) - def scan_vocab(self, documents, docvecs, progress_per=10000, trim_rule=None): - """Create the models Vocabulary: A mapping from unique words in the corpus to their frequency count. - - Parameters - ---------- - documents : iterable of :class:`~gensim.models.doc2vec.TaggedDocument` - The tagged documents used to create the vocabulary. Their tags can be either str tokens or ints (faster). - docvecs : list of :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` - The vector representations of the documents in our corpus. Each of them has a size == `vector_size`. - progress_per : int - Progress will be logged every `progress_per` documents. - trim_rule : function, optional - Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, - be trimmed away, or handled using the default (discard if word count < min_count). - Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), - or a callable that accepts parameters (word, count, min_count) and returns either - :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. - The rule, if given, is only used to prune vocabulary during - :meth:`~gensim.models.doc2vec.Doc2Vec.build_vocab` and is not stored as part of the model. + def _scan_vocab_multistream(self, input_streams, docvecs, workers, trim_rule): + manager = multiprocessing.Manager() + progress_queue = manager.Queue() - The input parameters are of the following types: - * `word` (str) - the word we are examining - * `count` (int) - the word's frequency count in the corpus - * `min_count` (int) - the minimum count threshold. + workers = min(workers, len(input_streams)) + logger.info("Scanning vocab in %i processes.", workers) + pool = multiprocessing.Pool(processes=workers) - Returns - ------- - (int, int) - Tuple of (Total words in the corpus, number of documents) + worker_max_vocab_size = self.max_vocab_size // workers if self.max_vocab_size else None + results = [ + pool.apply_async(_scan_vocab_worker, + (stream, progress_queue, worker_max_vocab_size, trim_rule) + ) for stream in input_streams + ] + pool.close() - """ - logger.info("collecting all words and their counts") + unfinished_tasks = len(results) + total_words = 0 + total_documents = 0 + while unfinished_tasks > 0: + report = progress_queue.get() + if report is None: + unfinished_tasks -= 1 + logger.info("scan vocab task finished, processed %i documents and %i words;" + " awaiting finish of %i more tasks", total_documents, total_words, unfinished_tasks) + elif isinstance(report, string_types): + logger.warning(report) + else: + num_words, num_documents = report + total_words += num_words + total_documents += num_documents + + results = [res.get() for res in results] # pairs (vocab, doclen2tags) + self.raw_vocab = reduce(utils.merge_counts, [r[0] for r in results]) + if self.max_vocab_size: + utils.trim_vocab_by_freq(self.raw_vocab, self.max_vocab_size, trim_rule=trim_rule) + + # Update `docvecs` with document tags information. + for (_, doclen2tags) in results: + for document_length, tags in iteritems(doclen2tags): + for tag in tags: + _note_doctag(tag, document_length, docvecs) + return total_words, total_documents + + def _scan_vocab_singlestream(self, documents, docvecs, progress_per, trim_rule): document_no = -1 total_words = 0 min_reduce = 1 @@ -1191,7 +1281,7 @@ def scan_vocab(self, documents, docvecs, progress_per=10000, trim_rule=None): document_length = len(document.words) for tag in document.tags: - self.note_doctag(tag, document_no, document_length, docvecs) + _note_doctag(tag, document_length, docvecs) for word in document.words: vocab[word] += 1 @@ -1201,38 +1291,54 @@ def scan_vocab(self, documents, docvecs, progress_per=10000, trim_rule=None): utils.prune_vocab(vocab, min_reduce, trim_rule=trim_rule) min_reduce += 1 - logger.info( - "collected %i word types and %i unique tags from a corpus of %i examples and %i words", - len(vocab), docvecs.count, document_no + 1, total_words - ) corpus_count = document_no + 1 self.raw_vocab = vocab return total_words, corpus_count - def note_doctag(self, key, document_no, document_length, docvecs): - """Note a document tag during initial corpus scan, for correctly setting the keyedvectors size. + def scan_vocab(self, documents=None, input_streams=None, docvecs=None, progress_per=10000, workers=None, + trim_rule=None): + """Create the models Vocabulary: A mapping from unique words in the corpus to their frequency count. Parameters ---------- - key : {int, str} - The tag to be noted. - document_no : int - The document's index in `docvecs`. Unused. - document_length : int - The document's length in words. + documents : iterable of :class:`~gensim.models.doc2vec.TaggedDocument` + The tagged documents used to create the vocabulary. Their tags can be either str tokens or ints (faster). docvecs : list of :class:`~gensim.models.keyedvectors.Doc2VecKeyedVectors` - Vector representations of the documents in the corpus. Each vector has size == `vector_size` + The vector representations of the documents in our corpus. Each of them has a size == `vector_size`. + progress_per : int + Progress will be logged every `progress_per` documents. + trim_rule : function, optional + Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, + be trimmed away, or handled using the default (discard if word count < min_count). + Can be None (min_count will be used, look to :func:`~gensim.utils.keep_vocab_item`), + or a callable that accepts parameters (word, count, min_count) and returns either + :attr:`gensim.utils.RULE_DISCARD`, :attr:`gensim.utils.RULE_KEEP` or :attr:`gensim.utils.RULE_DEFAULT`. + The rule, if given, is only used to prune vocabulary during + :meth:`~gensim.models.doc2vec.Doc2Vec.build_vocab` and is not stored as part of the model. + + The input parameters are of the following types: + * `word` (str) - the word we are examining + * `count` (int) - the word's frequency count in the corpus + * `min_count` (int) - the minimum count threshold. + + Returns + ------- + (int, int) + Tuple of (Total words in the corpus, number of documents) """ - if isinstance(key, integer_types + (integer,)): - docvecs.max_rawint = max(docvecs.max_rawint, key) + logger.info("collecting all words and their counts") + if input_streams is None: + total_words, corpus_count = self._scan_vocab_singlestream(documents, docvecs, progress_per, trim_rule) else: - if key in docvecs.doctags: - docvecs.doctags[key] = docvecs.doctags[key].repeat(document_length) - else: - docvecs.doctags[key] = Doctag(len(docvecs.offset2doctag), document_length, 1) - docvecs.offset2doctag.append(key) - docvecs.count = docvecs.max_rawint + 1 + len(docvecs.offset2doctag) + total_words, corpus_count = self._scan_vocab_multistream(input_streams, docvecs, workers, trim_rule) + + logger.info( + "collected %i word types and %i unique tags from a corpus of %i examples and %i words", + len(self.raw_vocab), docvecs.count, corpus_count, total_words + ) + + return total_words, corpus_count def indexed_doctags(self, doctag_tokens, docvecs): """Get the indexes and backing-arrays used in training examples. diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index 0b69ddcc8b..73a223f4a7 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -240,7 +240,7 @@ class FastText(BaseWordEmbeddingsModel): for the internal structure of words, besides their concurrence counts. """ - def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, min_count=5, + def __init__(self, sentences=None, input_streams=None, sg=0, hs=0, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, word_ngrams=1, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, negative=5, ns_exponent=0.75, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, min_n=3, max_n=6, sorted_vocab=1, bucket=2000000, trim_rule=None, batch_words=MAX_WORDS_IN_BATCH, callbacks=()): @@ -255,6 +255,9 @@ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. If you don't supply `sentences`, the model is left uninitialized -- use if you plan to initialize it in some other way. + input_streams : list or tuple of iterable of iterables + The tuple or list of `sentences`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. min_count : int, optional The model ignores all words with total frequency lower than this. size : int, optional @@ -340,11 +343,11 @@ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, Initialize and train a `FastText` model:: >>> from gensim.models import FastText - >>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]] + >>> input_streams = [[["cat", "say", "meow"], ["dog", "say", "woof"]]] >>> - >>> model = FastText(sentences, min_count=1) - >>> say_vector = model['say'] # get vector for a word - >>> of_vector = model['of'] # get vector for an out-of-vocab word + >>> model = FastText(input_streams=input_streams, min_count=1) + >>> say_vector = model['say'] # get vector for word + >>> of_vector = model['of'] # get vector for out-of-vocab word """ self.load = call_on_class_only @@ -363,9 +366,9 @@ def __init__(self, sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, self.wv.bucket = self.bucket super(FastText, self).__init__( - sentences=sentences, workers=workers, vector_size=size, epochs=iter, callbacks=callbacks, - batch_words=batch_words, trim_rule=trim_rule, sg=sg, alpha=alpha, window=window, seed=seed, - hs=hs, negative=negative, cbow_mean=cbow_mean, min_alpha=min_alpha, fast_version=FAST_VERSION) + sentences=sentences, input_streams=input_streams, workers=workers, vector_size=size, epochs=iter, + callbacks=callbacks, batch_words=batch_words, trim_rule=trim_rule, sg=sg, alpha=alpha, window=window, + seed=seed, hs=hs, negative=negative, cbow_mean=cbow_mean, min_alpha=min_alpha, fast_version=FAST_VERSION) @property @deprecated("Attribute will be removed in 4.0.0, use wv.min_n instead") @@ -417,7 +420,8 @@ def syn0_ngrams_lockf(self): def num_ngram_vectors(self): return self.wv.num_ngram_vectors - def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_vocab=False, trim_rule=None, **kwargs): + def build_vocab(self, sentences=None, input_streams=None, update=False, progress_per=10000, keep_raw_vocab=False, + trim_rule=None, workers=None, **kwargs): """Build vocabulary from a sequence of sentences (can be a once-only generator stream). Each sentence must be a list of unicode strings. @@ -428,6 +432,9 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. + input_streams : list or tuple of iterable of iterables + The tuple or list of `sentences`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. update : bool If true, the new words in `sentences` will be added to model's vocab. progress_per : int @@ -448,6 +455,9 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca * `count` (int) - the word's frequency count in the corpus * `min_count` (int) - the minimum count threshold. + workers : int + Used if `input_streams` is passed. Determines how many processes to use for vocab building. + Actual number of workers is determined by `min(len(input_streams), workers)`. **kwargs Additional key word parameters passed to :meth:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel.build_vocab`. @@ -478,8 +488,8 @@ def build_vocab(self, sentences, update=False, progress_per=10000, keep_raw_voca self.trainables.old_hash2index_len = len(self.wv.hash2index) return super(FastText, self).build_vocab( - sentences, update=update, progress_per=progress_per, - keep_raw_vocab=keep_raw_vocab, trim_rule=trim_rule, **kwargs) + sentences=sentences, input_streams=input_streams, update=update, progress_per=progress_per, + keep_raw_vocab=keep_raw_vocab, trim_rule=trim_rule, workers=workers, **kwargs) def _set_train_params(self, **kwargs): pass @@ -558,7 +568,7 @@ def _do_train_job(self, sentences, alpha, inits): return tally, self._raw_word_count(sentences) - def train(self, sentences, total_examples=None, total_words=None, + def train(self, sentences=None, input_streams=None, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, callbacks=(), **kwargs): """Update the model's neural weights from a sequence of sentences (can be a once-only generator stream). @@ -576,11 +586,14 @@ def train(self, sentences, total_examples=None, total_words=None, Parameters ---------- - sentences : iterable of iterables + sentences : {iterable of iterables, list or tuple of iterable of iterables} The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus` or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. + input_streams : list or tuple of iterable of iterables + The tuple or list of `sentences`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. total_examples : int Count of sentences. total_words : int @@ -619,7 +632,7 @@ def train(self, sentences, total_examples=None, total_words=None, """ super(FastText, self).train( - sentences, total_examples=total_examples, total_words=total_words, + sentences=sentences, input_streams=input_streams, total_examples=total_examples, total_words=total_words, epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, queue_factor=queue_factor, report_delay=report_delay, callbacks=callbacks) self.trainables.get_vocab_word_vecs(self.wv) diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py index d163784c1c..933e35e0bd 100755 --- a/gensim/models/word2vec.py +++ b/gensim/models/word2vec.py @@ -113,6 +113,7 @@ from copy import deepcopy from collections import defaultdict import threading +import multiprocessing import itertools import warnings @@ -135,6 +136,7 @@ from gensim.utils import deprecated from six import iteritems, itervalues, string_types from six.moves import xrange +from functools import reduce logger = logging.getLogger(__name__) @@ -626,7 +628,8 @@ class Word2Vec(BaseWordEmbeddingsModel): (which means that the size of the hidden layer is equal to the number of features `self.size`). """ - def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, + + def __init__(self, sentences=None, input_streams=None, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, sg=0, hs=0, negative=5, ns_exponent=0.75, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, trim_rule=None, sorted_vocab=1, batch_words=MAX_WORDS_IN_BATCH, compute_loss=False, callbacks=(), @@ -644,6 +647,9 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, `_. If you don't supply `sentences`, the model is left uninitialized -- use if you plan to initialize it in some other way. + input_streams : list or tuple of iterable of iterables + The tuple or list of `sentences`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. size : int, optional Dimensionality of the word vectors. window : int, optional @@ -707,7 +713,6 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, * `word` (str) - the word we are examining * `count` (int) - the word's frequency count in the corpus * `min_count` (int) - the minimum count threshold. - sorted_vocab : {0, 1}, optional If 1, sort the vocabulary by descending frequency before assigning word indexes. See :meth:`~gensim.models.word2vec.Word2VecVocab.sort_vocab()`. @@ -726,8 +731,8 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, Initialize and train a :class:`~gensim.models.word2vec.Word2Vec` model >>> from gensim.models import Word2Vec - >>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]] - >>> model = Word2Vec(sentences, min_count=1) + >>> input_streams = [[["cat", "say", "meow"], ["dog", "say", "woof"]]] + >>> model = Word2Vec(input_streams=input_streams, min_count=1) """ self.max_final_vocab = max_final_vocab @@ -742,9 +747,9 @@ def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5, self.trainables = Word2VecTrainables(seed=seed, vector_size=size, hashfxn=hashfxn) super(Word2Vec, self).__init__( - sentences=sentences, workers=workers, vector_size=size, epochs=iter, callbacks=callbacks, - batch_words=batch_words, trim_rule=trim_rule, sg=sg, alpha=alpha, window=window, seed=seed, - hs=hs, negative=negative, cbow_mean=cbow_mean, min_alpha=min_alpha, compute_loss=compute_loss, + sentences=sentences, input_streams=input_streams, workers=workers, vector_size=size, epochs=iter, + callbacks=callbacks, batch_words=batch_words, trim_rule=trim_rule, sg=sg, alpha=alpha, window=window, + seed=seed, hs=hs, negative=negative, cbow_mean=cbow_mean, min_alpha=min_alpha, compute_loss=compute_loss, fast_version=FAST_VERSION) def _do_train_job(self, sentences, alpha, inits): @@ -782,7 +787,7 @@ def _set_train_params(self, **kwargs): self.compute_loss = kwargs['compute_loss'] self.running_training_loss = 0 - def train(self, sentences, total_examples=None, total_words=None, + def train(self, sentences=None, input_streams=None, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, compute_loss=False, callbacks=()): """Update the model's neural weights from a sequence of sentences. @@ -810,11 +815,14 @@ def train(self, sentences, total_examples=None, total_words=None, or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples. See also the `tutorial on data streaming in Python `_. - total_examples : int, optional - Count of sentences. Used to decay the `alpha` learning rate. - total_words : int, optional - Count of raw words in sentences. Used to decay the `alpha` learning rate. - epochs : int, optional + input_streams : list or tuple of iterable of iterables + The tuple or list of `sentences`-like arguments. Use it if you have multiple input streams. It is possible + to process streams in parallel, using `workers` parameter. + total_examples : int + Count of sentences. + total_words : int + Count of raw words in sentences. + epochs : int Number of iterations (epochs) over the corpus. start_alpha : float, optional Initial learning rate. If supplied, replaces the starting `alpha` from the constructor, @@ -842,16 +850,17 @@ def train(self, sentences, total_examples=None, total_words=None, Examples -------- >>> from gensim.models import Word2Vec - >>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]] + >>> input_streams = [[["cat", "say", "meow"], ["dog", "say", "woof"]]] >>> >>> model = Word2Vec(min_count=1) - >>> model.build_vocab(sentences) # prepare the model vocabulary - >>> model.train(sentences, total_examples=model.corpus_count, epochs=model.iter) # train word vectors + >>> model.build_vocab(input_streams=input_streams) # prepare the model vocabulary + >>> model.train(input_streams=input_streams, + >>> total_examples=model.corpus_count, epochs=model.iter) # train word vectors (1, 30) """ return super(Word2Vec, self).train( - sentences, total_examples=total_examples, total_words=total_words, + sentences=sentences, input_streams=input_streams, total_examples=total_examples, total_words=total_words, epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count, queue_factor=queue_factor, report_delay=report_delay, compute_loss=compute_loss, callbacks=callbacks) @@ -1446,6 +1455,40 @@ def __iter__(self): i += self.max_sentence_length +def _scan_vocab_worker(stream, progress_queue, max_vocab_size=None, trim_rule=None): + """Do an initial scan of all words appearing in stream. + + Note: This function can not be Word2VecVocab's method because + of multiprocessing synchronization specifics in Python. + """ + min_reduce = 1 + vocab = defaultdict(int) + checked_string_types = 0 + sentence_no = -1 + total_words = 0 + for sentence_no, sentence in enumerate(stream): + if not checked_string_types: + if isinstance(sentence, string_types): + log_msg = "Each 'sentences' item should be a list of words (usually unicode strings). " \ + "First item here is instead plain %s." % type(sentence) + progress_queue.put(log_msg) + + checked_string_types += 1 + + for word in sentence: + vocab[word] += 1 + + if max_vocab_size and len(vocab) > max_vocab_size: + utils.prune_vocab(vocab, min_reduce, trim_rule=trim_rule) + min_reduce += 1 + + total_words += len(sentence) + + progress_queue.put((total_words, sentence_no + 1)) + progress_queue.put(None) + return vocab + + class Word2VecVocab(utils.SaveLoad): """Vocabulary used by :class:`~gensim.models.word2vec.Word2Vec`.""" def __init__( @@ -1461,9 +1504,7 @@ def __init__( self.max_final_vocab = max_final_vocab self.ns_exponent = ns_exponent - def scan_vocab(self, sentences, progress_per=10000, trim_rule=None): - """Do an initial scan of all words appearing in sentences.""" - logger.info("collecting all words and their counts") + def _scan_vocab_singlestream(self, sentences, progress_per, trim_rule): sentence_no = -1 total_words = 0 min_reduce = 1 @@ -1491,12 +1532,60 @@ def scan_vocab(self, sentences, progress_per=10000, trim_rule=None): utils.prune_vocab(vocab, min_reduce, trim_rule=trim_rule) min_reduce += 1 + corpus_count = sentence_no + 1 + self.raw_vocab = vocab + return total_words, corpus_count + + def _scan_vocab_multistream(self, input_streams, workers, trim_rule): + manager = multiprocessing.Manager() + progress_queue = manager.Queue() + + logger.info("Scanning vocab in %i processes.", min(workers, len(input_streams))) + + workers = min(workers, len(input_streams)) + pool = multiprocessing.Pool(processes=workers) + + worker_max_vocab_size = self.max_vocab_size // workers if self.max_vocab_size else None + results = [ + pool.apply_async(_scan_vocab_worker, + (stream, progress_queue, worker_max_vocab_size, trim_rule) + ) for stream in input_streams + ] + pool.close() + + unfinished_tasks = len(results) + total_words = 0 + total_sentences = 0 + while unfinished_tasks > 0: + report = progress_queue.get() + if report is None: + unfinished_tasks -= 1 + logger.info("scan vocab task finished, processed %i sentences and %i words;" + " awaiting finish of %i more tasks", total_sentences, total_words, unfinished_tasks) + elif isinstance(report, string_types): + logger.warning(report) + else: + num_words, num_sentences = report + total_words += num_words + total_sentences += num_sentences + + self.raw_vocab = reduce(utils.merge_counts, [res.get() for res in results]) + if self.max_vocab_size: + utils.trim_vocab_by_freq(self.raw_vocab, self.max_vocab_size, trim_rule=trim_rule) + return total_words, total_sentences + + def scan_vocab(self, sentences=None, input_streams=None, progress_per=10000, workers=None, trim_rule=None): + logger.info("collecting all words and their counts") + if sentences is not None: + total_words, corpus_count = self._scan_vocab_singlestream(sentences, progress_per, trim_rule) + else: + total_words, corpus_count = self._scan_vocab_multistream(input_streams, workers, trim_rule) + logger.info( "collected %i word types from a corpus of %i raw words and %i sentences", - len(vocab), total_words, sentence_no + 1 + len(self.raw_vocab), total_words, corpus_count ) - corpus_count = sentence_no + 1 - self.raw_vocab = vocab + return total_words, corpus_count def sort_vocab(self, wv): diff --git a/gensim/test/test_doc2vec.py b/gensim/test/test_doc2vec.py index b80588c55e..921881a660 100644 --- a/gensim/test/test_doc2vec.py +++ b/gensim/test/test_doc2vec.py @@ -9,7 +9,7 @@ """ -from __future__ import with_statement +from __future__ import with_statement, division import logging import unittest @@ -298,6 +298,37 @@ def test_training(self): model2 = doc2vec.Doc2Vec(corpus, size=100, min_count=2, iter=20, workers=1) self.models_equal(model, model2) + def test_multistream_training(self): + """Test doc2vec multistream training.""" + input_streams = [list_corpus[:len(list_corpus) // 2], list_corpus[len(list_corpus) // 2:]] + + model = doc2vec.Doc2Vec(inpsize=100, min_count=2, iter=20, workers=1, seed=42) + model.build_vocab(input_streams=input_streams, workers=1) + self.assertEqual(model.docvecs.doctag_syn0.shape, (300, 100)) + model.train(input_streams=input_streams, total_examples=model.corpus_count, epochs=model.iter) + self.model_sanity(model) + + # build vocab and train in one step; must be the same as above + model2 = doc2vec.Doc2Vec(input_streams=input_streams, size=100, min_count=2, iter=20, workers=1, seed=42) + + # check resulted vectors; note that order of words may be different + for word in model.wv.index2word: + self.assertEqual(model.wv.most_similar(word, topn=5), model2.wv.most_similar(word, topn=5)) + + def test_multistream_build_vocab(self): + # Expected vocab + model = doc2vec.Doc2Vec(min_count=0) + model.build_vocab(list_corpus) + singlestream_vocab = model.vocabulary.raw_vocab + + # Multistream vocab + model2 = doc2vec.Doc2Vec(min_count=0) + input_streams = [list_corpus[:len(list_corpus) // 2], list_corpus[len(list_corpus) // 2:]] + model2.build_vocab(input_streams=input_streams, workers=2) + multistream_vocab = model2.vocabulary.raw_vocab + + self.assertEqual(singlestream_vocab, multistream_vocab) + def test_dbow_hs(self): """Test DBOW doc2vec training.""" model = doc2vec.Doc2Vec(list_corpus, dm=0, hs=1, negative=0, min_count=2, iter=20) @@ -413,7 +444,6 @@ def models_equal(self, model, model2): # check docvecs self.assertEqual(len(model.docvecs.doctags), len(model2.docvecs.doctags)) self.assertEqual(len(model.docvecs.offset2doctag), len(model2.docvecs.offset2doctag)) - self.assertTrue(np.allclose(model.docvecs.doctag_syn0, model2.docvecs.doctag_syn0)) def test_delete_temporary_training_data(self): """Test doc2vec model after delete_temporary_training_data""" diff --git a/gensim/test/test_fasttext.py b/gensim/test/test_fasttext.py index a2ffcfb0fa..545d75b1e9 100644 --- a/gensim/test/test_fasttext.py +++ b/gensim/test/test_fasttext.py @@ -1,5 +1,6 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import division import logging import unittest @@ -80,6 +81,52 @@ def test_training(self): oov_vec = model['minor'] # oov word self.assertEqual(len(oov_vec), 10) + def test_multistream_training(self): + input_streams = [sentences[:len(sentences) // 2], sentences[len(sentences) // 2:]] + model = FT_gensim(size=5, min_count=1, hs=1, negative=0, seed=42, workers=1) + model.build_vocab(input_streams=input_streams, workers=2) + self.model_sanity(model) + + model.train(input_streams=input_streams, total_examples=model.corpus_count, epochs=model.iter) + sims = model.most_similar('graph', topn=10) + + self.assertEqual(model.wv.syn0.shape, (12, 5)) + self.assertEqual(len(model.wv.vocab), 12) + self.assertEqual(model.wv.syn0_vocab.shape[1], 5) + self.assertEqual(model.wv.syn0_ngrams.shape[1], 5) + self.model_sanity(model) + + # test querying for "most similar" by vector + graph_vector = model.wv.syn0norm[model.wv.vocab['graph'].index] + sims2 = model.most_similar(positive=[graph_vector], topn=11) + sims2 = [(w, sim) for w, sim in sims2 if w != 'graph'] # ignore 'graph' itself + self.assertEqual(sims, sims2) + + # build vocab and train in one step; must be the same as above + model2 = FT_gensim(input_streams=input_streams, size=5, min_count=1, hs=1, negative=0, seed=42, workers=1) + self.models_equal(model, model2) + + # verify oov-word vector retrieval + invocab_vec = model['minors'] # invocab word + self.assertEqual(len(invocab_vec), 5) + + oov_vec = model['minor'] # oov word + self.assertEqual(len(oov_vec), 5) + + def test_multistream_build_vocab(self): + # Expected vocab + model = FT_gensim(size=5, min_count=1, hs=1, negative=0, seed=42) + model.build_vocab(list_corpus) + singlestream_vocab = model.vocabulary.raw_vocab + + # Multistream vocab + model2 = FT_gensim(size=5, min_count=1, hs=1, negative=0, seed=42) + input_streams = [list_corpus[:len(list_corpus) // 2], list_corpus[len(list_corpus) // 2:]] + model2.build_vocab(input_streams=input_streams, workers=2) + multistream_vocab = model2.vocabulary.raw_vocab + + self.assertEqual(singlestream_vocab, multistream_vocab) + def models_equal(self, model, model2): self.assertEqual(len(model.wv.vocab), len(model2.wv.vocab)) self.assertEqual(model.num_ngram_vectors, model2.num_ngram_vectors) diff --git a/gensim/test/test_utils.py b/gensim/test/test_utils.py index 0df0d6efc2..5b265d0f77 100644 --- a/gensim/test/test_utils.py +++ b/gensim/test/test_utils.py @@ -120,6 +120,29 @@ def test_sample_dict(self): self.assertTrue(True) +class TestTrimVocabByFreq(unittest.TestCase): + def test_trim_vocab(self): + d = {"word1": 5, "word2": 1, "word3": 2} + expected_dict = {"word1": 5, "word3": 2} + utils.trim_vocab_by_freq(d, topk=2) + self.assertEqual(d, expected_dict) + + d = {"word1": 5, "word2": 2, "word3": 2, "word4": 1} + expected_dict = {"word1": 5, "word2": 2, "word3": 2} + utils.trim_vocab_by_freq(d, topk=2) + self.assertEqual(d, expected_dict) + + +class TestMergeDicts(unittest.TestCase): + def test_merge_dicts(self): + d1 = {"word1": 5, "word2": 1, "word3": 2} + d2 = {"word1": 2, "word3": 3, "word4": 10} + + res_dict = utils.merge_counts(d1, d2) + expected_dict = {"word1": 7, "word2": 1, "word3": 5, "word4": 10} + self.assertEqual(res_dict, expected_dict) + + class TestWindowing(unittest.TestCase): arr10_5 = np.array([ diff --git a/gensim/test/test_word2vec.py b/gensim/test/test_word2vec.py index 411d200676..c2ee97062d 100644 --- a/gensim/test/test_word2vec.py +++ b/gensim/test/test_word2vec.py @@ -7,7 +7,7 @@ """ Automated tests for checking transformation algorithms (the models package). """ - +from __future__ import division import logging import unittest @@ -166,6 +166,20 @@ def testMaxFinalVocab(self): self.assertEqual(reported_values['num_retained_words'], 4) self.assertEqual(model.vocabulary.effective_min_count, 3) + def testMultiStreamBuildVocab(self): + # Expected vocab + model = word2vec.Word2Vec(min_count=0) + model.build_vocab(sentences) + singlestream_vocab = model.vocabulary.raw_vocab + + # Multistream vocab + model = word2vec.Word2Vec(min_count=0) + input_streams = [sentences[:len(sentences) // 2], sentences[len(sentences) // 2:]] + model.build_vocab(input_streams=input_streams, workers=2) + multistream_vocab = model.vocabulary.raw_vocab + + self.assertEqual(singlestream_vocab, multistream_vocab) + def testOnlineLearning(self): """Test that the algorithm is able to add new words to the vocabulary and to a trained model when using a sorted vocabulary""" @@ -480,6 +494,30 @@ def testTraining(self): model2 = word2vec.Word2Vec(sentences, size=2, min_count=1, hs=1, negative=0) self.models_equal(model, model2) + def testMultistreamTraining(self): + """Test word2vec multistream training.""" + # build vocabulary, don't train yet + input_streams = [sentences[:len(sentences) // 2], sentences[len(sentences) // 2:]] + model = word2vec.Word2Vec(size=2, min_count=1, hs=1, negative=0, workers=1, seed=42) + model.build_vocab(input_streams=input_streams) + + self.assertTrue(model.wv.syn0.shape == (len(model.wv.vocab), 2)) + self.assertTrue(model.syn1.shape == (len(model.wv.vocab), 2)) + + model.train(input_streams=input_streams, total_examples=model.corpus_count, epochs=model.iter) + sims = model.most_similar('graph', topn=10) + + # test querying for "most similar" by vector + graph_vector = model.wv.syn0norm[model.wv.vocab['graph'].index] + sims2 = model.most_similar(positive=[graph_vector], topn=11) + sims2 = [(w, sim) for w, sim in sims2 if w != 'graph'] # ignore 'graph' itself + self.assertEqual(sims, sims2) + + # build vocab and train in one step; must be the same as above + model2 = word2vec.Word2Vec(input_streams=input_streams, size=2, min_count=1, hs=1, negative=0, + workers=1, seed=42) + self.models_equal(model, model2) + def testScoring(self): """Test word2vec scoring.""" model = word2vec.Word2Vec(sentences, size=2, min_count=1, hs=1, negative=0) diff --git a/gensim/utils.py b/gensim/utils.py index 8b8d7ea107..ec02cf4bb2 100644 --- a/gensim/utils.py +++ b/gensim/utils.py @@ -33,12 +33,13 @@ import sys import subprocess import inspect +import heapq import numpy as np import numbers import scipy.sparse -from six import iterkeys, iteritems, u, string_types, unichr +from six import iterkeys, iteritems, itervalues, u, string_types, unichr from six.moves import xrange from smart_open import smart_open @@ -1739,6 +1740,50 @@ def prune_vocab(vocab, min_reduce, trim_rule=None): return result +def trim_vocab_by_freq(vocab, topk, trim_rule=None): + """Retain `topk` most frequent words in `vocab`. + If there are more words with the same frequency as `topk`-th one, they will be kept. + Modifies `vocab` in place, returns nothing. + + Parameters + ---------- + vocab : dict + Input dictionary. + topk : int + Number of words with highest frequencies to keep. + trim_rule : function, optional + Function for trimming entities from vocab, default behaviour is `vocab[w] <= min_count`. + + """ + if topk >= len(vocab): + return + + min_count = heapq.nlargest(topk, itervalues(vocab))[-1] + prune_vocab(vocab, min_count, trim_rule=trim_rule) + + +def merge_counts(dict1, dict2): + """Merge `dict1` of (word, freq1) and `dict2` of (word, freq2) into `dict1` of (word, freq1+freq2). + Parameters + ---------- + dict1 : dict of (str, int) + First dictionary. + dict2 : dict of (str, int) + Second dictionary. + Returns + ------- + result : dict + Merged dictionary with sum of frequencies as values. + """ + for word, freq in iteritems(dict2): + if word in dict1: + dict1[word] += freq + else: + dict1[word] = freq + + return dict1 + + def qsize(queue): """Get the (approximate) queue size where available. From ff8bec22ad97b7936d9bcb02d76dcbec0733b4cb Mon Sep 17 00:00:00 2001 From: Andrey Kutuzov Date: Fri, 13 Jul 2018 21:36:35 +0200 Subject: [PATCH 25/40] Update docstring: new analogy evaluation method (#2130) * Update docstring: new analogy evaluation method * Same for fasttext --- gensim/models/fasttext.py | 2 +- gensim/models/keyedvectors.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index 0b69ddcc8b..6616cab90e 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -70,7 +70,7 @@ And on word analogies ->>> analogies_result = model.wv.accuracy(datapath('questions-words.txt')) +>>> analogies_result = model.wv.evaluate_word_analogies(datapath('questions-words.txt')) """ diff --git a/gensim/models/keyedvectors.py b/gensim/models/keyedvectors.py index 3ac3bff062..963e9e79c5 100644 --- a/gensim/models/keyedvectors.py +++ b/gensim/models/keyedvectors.py @@ -140,7 +140,7 @@ And on word analogies ->>> analogy_scores = model.wv.accuracy(datapath('questions-words.txt')) +>>> analogy_scores = model.wv.evaluate_word_analogies(datapath('questions-words.txt')) and so on. From 46ccefb3dc2a1079c930de71b74576659a06a14a Mon Sep 17 00:00:00 2001 From: Matti Lyra Date: Fri, 13 Jul 2018 21:39:35 +0200 Subject: [PATCH 26/40] [MRG] Wikicorpus custom filters (#2089) * Modified call to user provided filter_article so that all args are passed in as kwargs * Small readability improvements. * Added a catch for pickling errors for self.filter_function, and changed default value check to check against None not against callable(). * Fixed python 2 backwards compatibility issue with exception chaining. * Added import for PicklingError * Fixed linting errors. * Added an example filter function. * Added tests for wikicorpus filter_articles. * Passing tests for wikicorpus filter_articles. * Fixed linting error. * Fixed linting errors. * PEP8 hanging indent. --- gensim/corpora/wikicorpus.py | 90 ++++++++++++++++++++++++++++++++++-- gensim/test/test_corpora.py | 15 ++++++ 2 files changed, 100 insertions(+), 5 deletions(-) diff --git a/gensim/corpora/wikicorpus.py b/gensim/corpora/wikicorpus.py index 966c5d7924..f204a6d834 100644 --- a/gensim/corpora/wikicorpus.py +++ b/gensim/corpora/wikicorpus.py @@ -24,6 +24,7 @@ import multiprocessing import re import signal +from pickle import PicklingError from xml.etree.cElementTree import \ iterparse # LXML isn't faster, so let's go with the built-in solution @@ -32,6 +33,9 @@ from gensim.corpora.dictionary import Dictionary from gensim.corpora.textcorpus import TextCorpus +from six import raise_from + + logger = logging.getLogger(__name__) ARTICLE_MIN_WORDS = 50 @@ -89,6 +93,63 @@ """`MediaWiki namespaces `_ that ought to be ignored.""" +def filter_example(elem, text, *args, **kwargs): + """Example function for filtering arbitrary documents from wikipedia dump. + + + The custom filter function is called _before_ tokenisation and should work on + the raw text and/or XML element information. + + The filter function gets the entire context of the XML element passed into it, + but you can of course choose not the use some or all parts of the context. Please + refer to :func:`gensim.corpora.wikicorpus.extract_pages` for the exact details + of the page context. + + Parameters + ---------- + elem : etree.Element + XML etree element + text : str + The text of the XML node + namespace : str + XML namespace of the XML element + title : str + Page title + page_tag : str + XPath expression for page. + text_path : str + XPath expression for text. + title_path : str + XPath expression for title. + ns_path : str + XPath expression for namespace. + pageid_path : str + XPath expression for page id. + + Example: + ------ + >>> import gensim.corpora + >>> filter_func = gensim.corpora.wikicorpus.filter_example + >>> dewiki = gensim.corpora.WikiCorpus('./dewiki-20180520-pages-articles-multistream.xml.bz2', + filter_articles=filter_func) + """ + # Filter German wikipedia dump for articles that are marked either as + # Lesenswert (featured) or Exzellent (excellent) by wikipedia editors. + # ********************* + # regex is in the function call so that we do not pollute the wikicorpus + # namespace do not do this in production as this function is called for + # every element in the wiki dump + _regex_de_excellent = re.compile('.*\{\{(Exzellent.*?)\}\}[\s]*', flags=re.DOTALL) + _regex_de_featured = re.compile('.*\{\{(Lesenswert.*?)\}\}[\s]*', flags=re.DOTALL) + + if text is None: + return False + if _regex_de_excellent.match(text) or _regex_de_featured.match(text): + return True + else: + return False + + def find_interlinks(raw): """Find all interlinks to other articles in the dump. @@ -324,7 +385,7 @@ def get_namespace(tag): _get_namespace = get_namespace -def extract_pages(f, filter_namespaces=False): +def extract_pages(f, filter_namespaces=False, filter_articles=None): """Extract pages from a MediaWiki database dump. Parameters @@ -365,6 +426,14 @@ def extract_pages(f, filter_namespaces=False): if ns not in filter_namespaces: text = None + if filter_articles is not None: + if not filter_articles( + elem, namespace=namespace, title=title, + text=text, page_tag=page_tag, + text_path=text_path, title_path=title_path, + ns_path=ns_path, pageid_path=pageid_path): + text = None + pageid = elem.find(pageid_path).text yield title, text or "", pageid # empty page will yield None @@ -500,8 +569,11 @@ class WikiCorpus(TextCorpus): """ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), dictionary=None, filter_namespaces=('0',), tokenizer_func=tokenize, article_min_tokens=ARTICLE_MIN_WORDS, - token_min_len=TOKEN_MIN_LEN, token_max_len=TOKEN_MAX_LEN, lower=True): - """ + token_min_len=TOKEN_MIN_LEN, token_max_len=TOKEN_MAX_LEN, lower=True, filter_articles=None): + """Initialize the corpus. + + Unless a dictionary is provided, this scans the corpus once, + to determine its vocabulary. Parameters ---------- @@ -528,7 +600,11 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction token_max_len : int, optional Maximal token length. lower : bool, optional - Convert all text to lower case? + If True - convert all text to lower case. + filter_articles: callable or None, optional + If set, each XML article element will be passed to this callable before being processed. Only articles + where the callable returns an XML element are processed, returning None allows filtering out + some articles based on customised rules. Warnings -------- @@ -537,6 +613,7 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction """ self.fname = fname self.filter_namespaces = filter_namespaces + self.filter_articles = filter_articles self.metadata = False if processes is None: processes = max(1, multiprocessing.cpu_count() - 1) @@ -589,7 +666,7 @@ def get_texts(self): texts = \ ((text, self.lemmatize, title, pageid, tokenization_params) for title, text, pageid - in extract_pages(bz2.BZ2File(self.fname), self.filter_namespaces)) + in extract_pages(bz2.BZ2File(self.fname), self.filter_namespaces, self.filter_articles)) pool = multiprocessing.Pool(self.processes, init_to_ignore_interrupt) try: @@ -616,6 +693,9 @@ def get_texts(self): "(total %i articles, %i positions before pruning articles shorter than %i words)", articles, positions, articles_all, positions_all, ARTICLE_MIN_WORDS ) + except PicklingError as exc: + raise_from(PicklingError('Can not send filtering function {} to multiprocessing, ' + 'make sure the function can be pickled.'.format(self.filter_articles)), exc) else: logger.info( "finished iterating over Wikipedia corpus of %i documents with %i positions " diff --git a/gensim/test/test_corpora.py b/gensim/test/test_corpora.py index 3fad45df7b..8eb10faa0e 100644 --- a/gensim/test/test_corpora.py +++ b/gensim/test/test_corpora.py @@ -721,6 +721,21 @@ def test_empty_input(self): # An empty file is not legit XML pass + def test_custom_filterfunction(self): + def reject_all(elem, *args, **kwargs): + return False + corpus = self.corpus_class(self.enwiki, filter_articles=reject_all) + texts = corpus.get_texts() + self.assertTrue(all([not t for t in texts])) + + def keep_some(elem, title, *args, **kwargs): + return title[0] == 'C' + corpus = self.corpus_class(self.enwiki, filter_articles=reject_all) + corpus.metadata = True + texts = corpus.get_texts() + for text, (pageid, title) in texts: + self.assertEquals(title[0], 'C') + class TestTextDirectoryCorpus(unittest.TestCase): From 96444a7d0357fc836641ec32c65eb2fbffbee68d Mon Sep 17 00:00:00 2001 From: Philipp Hager Date: Fri, 13 Jul 2018 21:41:20 +0200 Subject: [PATCH 27/40] Fix memory consumption in AuthorTopicModel (#2122) * Fix quadratic iteration * Update comment * Move from list to set --- gensim/models/atmodel.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py index 9253a6a6d8..daa7ea4ab2 100755 --- a/gensim/models/atmodel.py +++ b/gensim/models/atmodel.py @@ -766,13 +766,13 @@ def update(self, corpus=None, author2doc=None, doc2author=None, chunksize=None, self.doc2author[d] = a_list # Train on all documents of authors in input_corpus. - train_corpus_idx = [] - for _ in author2doc.keys(): # For all authors in input corpus. - for doc_ids in self.author2doc.values(): # For all documents in total corpus. - train_corpus_idx.extend(doc_ids) + train_corpus_idx = set() + # Collect all documents of authors. + for doc_ids in self.author2doc.values(): + train_corpus_idx.update(doc_ids) # Make the list of training documents unique. - train_corpus_idx = list(set(train_corpus_idx)) + train_corpus_idx = sorted(train_corpus_idx) # train_corpus_idx is only a list of indexes, so "len" is valid. lencorpus = len(train_corpus_idx) From 2ce4699e048a4bb02be06b0412a42da9bd7fbdfe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?V=C3=ADt=20Novotn=C3=BD?= Date: Mon, 30 Jul 2018 12:49:51 +0200 Subject: [PATCH 28/40] Make `similarity_matrix` support non-contiguous dictionaries (#2047) Closes #2041 --- gensim/models/keyedvectors.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/gensim/models/keyedvectors.py b/gensim/models/keyedvectors.py index 3ac3bff062..18fa9e4f6b 100644 --- a/gensim/models/keyedvectors.py +++ b/gensim/models/keyedvectors.py @@ -148,6 +148,7 @@ from __future__ import division # py3 "true division" +from collections import deque import logging try: @@ -649,16 +650,17 @@ def similarity_matrix(self, dictionary, tfidf=None, threshold=0.0, exponent=2.0, num_skipped = 0 # Decide the order of rows. if tfidf is None: - word_indices = range(matrix_order) + word_indices = deque(sorted(dictionary.keys())) else: assert max(tfidf.idfs) < matrix_order - word_indices = [ + word_indices = deque([ index for index, _ in sorted(tfidf.idfs.items(), key=lambda x: (x[1], -x[0]), reverse=True) - ] + ]) # Traverse rows. - for row_number, w1_index in enumerate(word_indices): + for row_number, w1_index in enumerate(list(word_indices)): + word_indices.popleft() if row_number % 1000 == 0: logger.info( "PROGRESS: at %.02f%% rows (%d / %d, %d skipped, %.06f%% density)", @@ -673,8 +675,8 @@ def similarity_matrix(self, dictionary, tfidf=None, threshold=0.0, exponent=2.0, if matrix_order <= nonzero_limit + 1: # Traverse all columns. columns = ( (w2_index, self.similarity(w1, dictionary[w2_index])) - for w2_index in range(w1_index + 1, matrix_order) - if w1_index != w2_index and dictionary[w2_index] in self.vocab) + for w2_index in word_indices + if dictionary[w2_index] in self.vocab) else: # Traverse only columns corresponding to the embeddings closest to w1. num_nonzero = matrix_nonzero[w1_index] - 1 columns = ( From e4bf94cb83720a2dac5bb1bf129b9ecef051672e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20=C5=98eh=C5=AF=C5=99ek?= Date: Tue, 31 Jul 2018 09:09:23 +0300 Subject: [PATCH 29/40] Additional documentation fixes (#2121) --- docs/src/_index.rst.unused | 100 +++++++++++++++++++++++++++++++++++ docs/src/_license.rst.unused | 26 +++++++++ gensim/models/doc2vec.py | 14 ++--- gensim/models/fasttext.py | 13 ++--- gensim/models/word2vec.py | 13 ++--- 5 files changed, 147 insertions(+), 19 deletions(-) create mode 100644 docs/src/_index.rst.unused create mode 100644 docs/src/_license.rst.unused diff --git a/docs/src/_index.rst.unused b/docs/src/_index.rst.unused new file mode 100644 index 0000000000..71390c1060 --- /dev/null +++ b/docs/src/_index.rst.unused @@ -0,0 +1,100 @@ + +:github_url: https://github.com/RaRe-Technologies/gensim + +Gensim documentation +=================================== + +============ +Introduction +============ + +Gensim is a free Python library designed to automatically extract semantic +topics from documents, as efficiently (computer-wise) and painlessly (human-wise) as possible. + +Gensim is designed to process raw, unstructured digital texts ("plain text"). + +The algorithms in Gensim, such as **Word2Vec**, **FastText**, **Latent Semantic Analysis**, **Latent Dirichlet Allocation** and **Random Projections**, discover semantic structure of documents by examining statistical co-occurrence patterns within a corpus of training documents. These algorithms are **unsupervised**, which means no human input is necessary -- you only need a corpus of plain text documents. + +Once these statistical patterns are found, any plain text documents can be succinctly +expressed in the new, semantic representation and queried for topical similarity +against other documents, words or phrases. + +.. note:: + If the previous paragraphs left you confused, you can read more about the `Vector + Space Model `_ and `unsupervised + document analysis `_ on Wikipedia. + + +.. _design: + +Features +-------- + +* **Memory independence** -- there is no need for the whole training corpus to + reside fully in RAM at any one time (can process large, web-scale corpora). +* **Memory sharing** -- trained models can be persisted to disk and loaded back via mmap. Multiple processes can share the same data, cutting down RAM footprint. +* Efficient implementations for several popular vector space algorithms, + including Word2Vec, Doc2Vec, FastText, TF-IDF, Latent Semantic Analysis (LSI, LSA), + Latent Dirichlet Allocation (LDA) or Random Projection. +* I/O wrappers and readers from several popular data formats. +* Fast similarity queries for documents in their semantic representation. + +The **principal design objectives** behind Gensim are: + +1. Straightforward interfaces and low API learning curve for developers. Good for prototyping. +2. Memory independence with respect to the size of the input corpus; all intermediate + steps and algorithms operate in a streaming fashion, accessing one document + at a time. + +.. seealso:: + + We built a high performance server for NLP, document analysis, indexing, search and clustering: https://scaletext.ai. + ScaleText is a commercial product, available both on-prem or as SaaS. + Reach out at info@scaletext.com if you need an industry-grade tool with professional support. + +.. _availability: + +Availability +------------ + +Gensim is licensed under the OSI-approved `GNU LGPLv2.1 license `_ and can be downloaded either from its `github repository `_ or from the `Python Package Index `_. + +.. seealso:: + + See the :doc:`install ` page for more info on Gensim deployment. + + +.. toctree:: + :glob: + :maxdepth: 1 + :caption: Getting started + + install + intro + support + about + license + citing + + +.. toctree:: + :maxdepth: 1 + :caption: Tutorials + + tutorial + tut1 + tut2 + tut3 + + +.. toctree:: + :maxdepth: 1 + :caption: API Reference + + apiref + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` diff --git a/docs/src/_license.rst.unused b/docs/src/_license.rst.unused new file mode 100644 index 0000000000..d85983aa44 --- /dev/null +++ b/docs/src/_license.rst.unused @@ -0,0 +1,26 @@ +:orphan: + +.. _license: + +Licensing +--------- + +Gensim is licensed under the OSI-approved `GNU LGPLv2.1 license `_. + +This means that it's free for both personal and commercial use, but if you make any +modification to Gensim that you distribute to other people, you have to disclose +the source code of these modifications. + +Apart from that, you are free to redistribute Gensim in any way you like, though you're +not allowed to modify its license (doh!). + +My intent here is to **get more help and community involvement** with the development of Gensim. +The legalese is therefore less important to me than your input and contributions. + +`Contact me `_ if LGPL doesn't fit your bill but you'd like the LGPL restrictions liften. + +.. seealso:: + + We built a high performance server for NLP, document analysis, indexing, search and clustering: https://scaletext.ai. + ScaleText is a commercial product, available both on-prem or as SaaS. + Reach out at info@scaletext.com if you need an industry-grade tool with professional support. diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py index 57638e71bc..08cbf7f106 100644 --- a/gensim/models/doc2vec.py +++ b/gensim/models/doc2vec.py @@ -20,13 +20,13 @@ `_. **Make sure you have a C compiler before installing Gensim, to use the optimized doc2vec routines** (70x speedup -compared to plain NumPy implementation `_). +compared to plain NumPy implementation, https://rare-technologies.com/parallelizing-word2vec-in-python/). -Examples --------- +Usage examples +============== -Initialize & train a model +Initialize & train a model: >>> from gensim.test.utils import common_texts >>> from gensim.models.doc2vec import Doc2Vec, TaggedDocument @@ -34,7 +34,7 @@ >>> documents = [TaggedDocument(doc, [i]) for i, doc in enumerate(common_texts)] >>> model = Doc2Vec(documents, vector_size=5, window=2, min_count=1, workers=4) -Persist a model to disk +Persist a model to disk: >>> from gensim.test.utils import get_tmpfile >>> @@ -43,11 +43,11 @@ >>> model.save(fname) >>> model = Doc2Vec.load(fname) # you can continue training with the loaded model! -If you're finished training a model (=no more updates, only querying, reduce memory usage), you can do +If you're finished training a model (=no more updates, only querying, reduce memory usage), you can do: >>> model.delete_temporary_training_data(keep_doctags_vectors=True, keep_inference=True) -Infer vector for new document +Infer vector for a new document: >>> vector = model.infer_vector(["system", "response"]) diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index 73a223f4a7..5ac973599d 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -13,6 +13,7 @@ This module contains a fast native C implementation of Fasttext with Python interfaces. It is **not** only a wrapper around Facebook's implementation. + For a tutorial see `this noteboook `_. @@ -22,14 +23,14 @@ Usage examples -------------- -Initialize and train a model +Initialize and train a model: >>> from gensim.test.utils import common_texts >>> from gensim.models import FastText >>> >>> model = FastText(common_texts, size=4, window=3, min_count=1, iter=10) -Persist a model to disk with +Persist a model to disk with: >>> from gensim.test.utils import get_tmpfile >>> @@ -38,7 +39,7 @@ >>> model.save(fname) >>> model = FastText.load(fname) # you can continue training with the loaded model! -Retrieve word-vector for vocab and out-of-vocab word +Retrieve word-vector for vocab and out-of-vocab word: >>> existent_word = "computer" >>> existent_word in model.wv.vocab @@ -50,7 +51,7 @@ False >>> oov_vec = model.wv[oov_word] # numpy vector for OOV word -You can perform various NLP word tasks with the model, some of them are already built-in +You can perform various NLP word tasks with the model, some of them are already built-in: >>> similarities = model.wv.most_similar(positive=['computer', 'human'], negative=['interface']) >>> most_similar = similarities[0] @@ -62,13 +63,13 @@ >>> >>> sim_score = model.wv.similarity('computer', 'human') -Correlation with human opinion on word similarity +Correlation with human opinion on word similarity: >>> from gensim.test.utils import datapath >>> >>> similarities = model.wv.evaluate_word_pairs(datapath('wordsim353.tsv')) -And on word analogies +And on word analogies: >>> analogies_result = model.wv.accuracy(datapath('questions-words.txt')) diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py index 933e35e0bd..a84531b57c 100755 --- a/gensim/models/word2vec.py +++ b/gensim/models/word2vec.py @@ -27,12 +27,12 @@ visit https://rare-technologies.com/word2vec-tutorial/. **Make sure you have a C compiler before installing Gensim, to use the optimized word2vec routines** -(70x speedup compared to plain NumPy implementation, https://rare-technologies.com/parallelizing-word2vec-in-python/. +(70x speedup compared to plain NumPy implementation, https://rare-technologies.com/parallelizing-word2vec-in-python/). Usage examples ============== -Initialize a model with e.g. +Initialize a model with e.g.: >>> from gensim.test.utils import common_texts, get_tmpfile >>> from gensim.models import Word2Vec @@ -45,13 +45,13 @@ The training is streamed, meaning `sentences` can be a generator, reading input data from disk on-the-fly, without loading the entire corpus into RAM. -It also means you can continue training the model later +It also means you can continue training the model later: >>> model = Word2Vec.load("word2vec.model") >>> model.train([["hello", "world"]], total_examples=1, epochs=1) (0, 2) -The trained word vectors are stored in a :class:`~gensim.models.KeyedVectors` instance in `model.wv`: +The trained word vectors are stored in a :class:`~gensim.models.keyedvectors.KeyedVectors` instance in `model.wv`: >>> vector = model.wv['computer'] # numpy vector of a word @@ -68,7 +68,8 @@ >>> wv = KeyedVectors.load("model.wv", mmap='r') >>> vector = wv['computer'] # numpy vector of a word -Gensim can also load word vectors in the "word2vec C format", as this :class:`~gensim.models.KeyedVectors` instance:: +Gensim can also load word vectors in the "word2vec C format", as a +:class:`~gensim.models.keyedvectors.KeyedVectors` instance:: >>> from gensim.test.utils import datapath >>> @@ -84,7 +85,7 @@ are already built-in - you can see it in :mod:`gensim.models.keyedvectors`. If you're finished training a model (i.e. no more updates, only querying), -you can switch to the :class:`~gensim.models.KeyedVectors` instance +you can switch to the :class:`~gensim.models.keyedvectors.KeyedVectors` instance: >>> word_vectors = model.wv >>> del model From 4d921da6e34dc6c7c037ba1e4a36bf09ba56143d Mon Sep 17 00:00:00 2001 From: lopusz Date: Tue, 31 Jul 2018 09:25:41 +0200 Subject: [PATCH 30/40] Fix `min_count` handling in phrases detection using `npmi_scorer` (#2072) * Fix min_count handling in phrases detection using npmi * Refactor min_count handling in npmi phrases detection * Fix min_count inequality for compatiblity with the rest of the gensim API * Fix misleading min_count doc_string * Fix misleading min_count comment --- gensim/models/phrases.py | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py index ed6f4c44df..1730d769c4 100644 --- a/gensim/models/phrases.py +++ b/gensim/models/phrases.py @@ -668,7 +668,7 @@ def npmi_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count, co len_vocab : int Not used. min_count: int - Not used. + Ignore all bigrams with total collected count lower than this value. corpus_word_count : int Total number of words in the corpus. @@ -678,10 +678,15 @@ def npmi_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count, co where :math:`prob(word) = \\frac{word\_count}{corpus\_word\_count}` """ - pa = worda_count / corpus_word_count - pb = wordb_count / corpus_word_count - pab = bigram_count / corpus_word_count - return log(pab / (pa * pb)) / -log(pab) + if bigram_count >= min_count: + pa = worda_count / corpus_word_count + pb = wordb_count / corpus_word_count + pab = bigram_count / corpus_word_count + return log(pab / (pa * pb)) / -log(pab) + else: + # Return -infinity to make sure that no phrases will be created + # from bigrams less frequent than min_count + return float('-inf') def pseudocorpus(source_vocab, sep, common_terms=frozenset()): From a6c4ea4fc625174dd9fb12d739b20fe400edd3d6 Mon Sep 17 00:00:00 2001 From: Yu Yin Date: Tue, 31 Jul 2018 16:14:55 +0800 Subject: [PATCH 31/40] Improve `prune_at` parameter description for `gensim.corpora.Dictionary` (#2128) * Make clear `prune_at` documentation According to the code, the `prune_at` parameter in `Dictionary.__init__` and `add_documents` is only for reducing memory usage, and has no guarantee on correctness, but the documentation of this parameter was confusing to users. * add link to method --- gensim/corpora/dictionary.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/gensim/corpora/dictionary.py b/gensim/corpora/dictionary.py index 84e2ed9945..1e13692a2d 100644 --- a/gensim/corpora/dictionary.py +++ b/gensim/corpora/dictionary.py @@ -56,7 +56,9 @@ def __init__(self, documents=None, prune_at=2000000): documents : iterable of iterable of str, optional Documents to be used to initialize the mapping and collect corpus statistics. prune_at : int, optional - Dictionary will keep no more than `prune_at` words in its mapping, to limit its RAM footprint. + Dictionary will try to keep no more than `prune_at` words in its mapping, to limit its RAM + footprint, the correctness is not guaranteed. + Use :meth:`~gensim.corpora.dictionary.Dictionary.filter_extremes` to perform proper filtering. Examples -------- @@ -172,7 +174,9 @@ def add_documents(self, documents, prune_at=2000000): documents : iterable of iterable of str Input corpus. All tokens should be already **tokenized and normalized**. prune_at : int, optional - Dictionary will keep no more than `prune_at` words in its mapping, to limit its RAM footprint. + Dictionary will try to keep no more than `prune_at` words in its mapping, to limit its RAM + footprint, the correctness is not guaranteed. + Use :meth:`~gensim.corpora.dictionary.Dictionary.filter_extremes` to perform proper filtering. Examples -------- From 61728a07e428f486aaa9c84160b9daff0bc8109d Mon Sep 17 00:00:00 2001 From: Philip Date: Wed, 1 Aug 2018 21:21:56 -0700 Subject: [PATCH 32/40] Correctly process empty documents in `AuthorTopicModel` (#2133) * test for #1589 * bugfix #1589 * ignore unused assigned varaible * PR review * Update test_atmodel.py --- gensim/models/atmodel.py | 11 ++++++----- gensim/test/test_atmodel.py | 11 ++++++++++- 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py index daa7ea4ab2..d0a5940512 100755 --- a/gensim/models/atmodel.py +++ b/gensim/models/atmodel.py @@ -461,10 +461,11 @@ def inference(self, chunk, author2doc, doc2author, rhot, collect_sstats=False, c ids = [int(idx) for idx, _ in doc] else: ids = [idx for idx, _ in doc] - cts = np.array([cnt for _, cnt in doc]) + ids = np.array(ids, dtype=np.integer) + cts = np.array([cnt for _, cnt in doc], dtype=np.integer) # Get all authors in current document, and convert the author names to integer IDs. - authors_d = [self.author2id[a] for a in self.doc2author[doc_no]] + authors_d = np.array([self.author2id[a] for a in self.doc2author[doc_no]], dtype=np.integer) gammad = self.state.gamma[authors_d, :] # gamma of document d before update. tilde_gamma = gammad.copy() # gamma that will be updated. @@ -972,9 +973,9 @@ def bound(self, chunk, chunk_doc_idx=None, subsample_ratio=1.0, author2doc=None, else: doc_no = d # Get all authors in current document, and convert the author names to integer IDs. - authors_d = [self.author2id[a] for a in self.doc2author[doc_no]] - ids = np.array([id for id, _ in doc]) # Word IDs in doc. - cts = np.array([cnt for _, cnt in doc]) # Word counts. + authors_d = np.array([self.author2id[a] for a in self.doc2author[doc_no]], dtype=np.integer) + ids = np.array([id for id, _ in doc], dtype=np.integer) # Word IDs in doc. + cts = np.array([cnt for _, cnt in doc], dtype=np.integer) # Word counts. if d % self.chunksize == 0: logger.debug("bound: at document #%i in chunk", d) diff --git a/gensim/test/test_atmodel.py b/gensim/test/test_atmodel.py index 00d4d2aafa..50e6a32ea9 100644 --- a/gensim/test/test_atmodel.py +++ b/gensim/test/test_atmodel.py @@ -35,7 +35,6 @@ # increases the bound. # Test that models are compatiple across versions, as done in LdaModel. - # Assign some authors randomly to the documents above. author2doc = { 'john': [0, 1, 2, 3, 4, 5, 6], @@ -110,6 +109,16 @@ def testBasic(self): jill_topics = matutils.sparse2full(jill_topics, model.num_topics) self.assertTrue(all(jill_topics > 0)) + def testEmptyDocument(self): + local_texts = common_texts + [['only_occurs_once_in_corpus_and_alone_in_doc']] + dictionary = Dictionary(local_texts) + dictionary.filter_extremes(no_below=2) + corpus = [dictionary.doc2bow(text) for text in local_texts] + a2d = author2doc.copy() + a2d['joaquin'] = [len(local_texts) - 1] + + self.class_(corpus, author2doc=a2d, id2word=dictionary, num_topics=2) + def testAuthor2docMissing(self): # Check that the results are the same if author2doc is constructed automatically from doc2author. model = self.class_( From 4520adf534c6f82ebd5fcb695ecc41a8283bc4c3 Mon Sep 17 00:00:00 2001 From: Aneesh Joshi Date: Fri, 3 Aug 2018 07:02:05 +0530 Subject: [PATCH 33/40] Add `name_only` option for downloader api (#2143) * handle deprecation * handle max_count * change flag name * make flake8 compatible * move max_vocab to prepare vocab * correct max_vocab semantics * remove unnecessary nextline * fix bug and make flake8 complaint * refactor code and change sorting to key based * add tests * introduce effective_min_count * make flake8 compliant * remove clobbering of min_count * remove min_count assertion * .\gensim\models\word2vec.py * Revert ".\gensim\models\word2vec.py" This reverts commit 6c06fbccf1c2c44cdba4cd385a4cd335f53c69db. * rename max_vocab to max_final_vocab * update test to max_final_vocab * move and modify comment docs * make flake8 compliant * refactor word2vec.py * handle possible old model load errors * include effective_min_count tests * make flake compliant * remove check for max_final_vocab * include backward compat for 3.3 models * remove unnecessary newline * add test case for max_final_vocab * add name only option to downloader api * add tests * make single argument option for name_only * make name_only into name --- gensim/downloader.py | 15 ++++++++++++--- gensim/test/test_api.py | 3 +++ 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/gensim/downloader.py b/gensim/downloader.py index f3672ead01..3b2cf34ffa 100644 --- a/gensim/downloader.py +++ b/gensim/downloader.py @@ -29,6 +29,7 @@ Also, this API available via CLI:: python -m gensim.downloader --info # same as api.info(dataname) + python -m gensim.downloader --info name # same as api.info(name_only=True) python -m gensim.downloader --download # same as api.load(dataname, return_path=True) """ @@ -154,7 +155,7 @@ def _calculate_md5_checksum(fname): return hash_md5.hexdigest() -def info(name=None, show_only_latest=True): +def info(name=None, show_only_latest=True, name_only=False): """Provide the information related to model/dataset. Parameters @@ -164,6 +165,8 @@ def info(name=None, show_only_latest=True): show_only_latest : bool, optional If storage contains different versions for one data/model, this flag allow to hide outdated versions. Affects only if `name` is None. + name_only : bool, optional + If True, will return only the names of available models and corpora. Returns ------- @@ -205,6 +208,9 @@ def info(name=None, show_only_latest=True): if not show_only_latest: return information + if name_only: + return {"corpora": list(information['corpora'].keys()), "models": list(information['models'])} + return { "corpora": {name: data for (name, data) in information['corpora'].items() if data.get("latest", True)}, "models": {name: data for (name, data) in information['models'].items() if data.get("latest", True)} @@ -444,5 +450,8 @@ def load(name, return_path=False): data_path = load(args.download[0], return_path=True) logger.info("Data has been installed and data path is %s", data_path) elif args.info is not None: - output = info() if (args.info == full_information) else info(name=args.info) - print(json.dumps(output, indent=4)) + if args.info == 'name': + print(json.dumps(info(name_only=True), indent=4)) + else: + output = info() if (args.info == full_information) else info(name=args.info) + print(json.dumps(output, indent=4)) diff --git a/gensim/test/test_api.py b/gensim/test/test_api.py index bf84800205..13245b2205 100644 --- a/gensim/test/test_api.py +++ b/gensim/test/test_api.py @@ -72,6 +72,9 @@ def test_info(self): self.assertEqual(sorted(data.keys()), sorted(['models', 'corpora'])) self.assertTrue(len(data['models'])) self.assertTrue(len(data['corpora'])) + name_only_data = api.info(name_only=True) + self.assertEqual(len(name_only_data.keys()), 2) + self.assertTrue({'models', 'corpora'} == set(name_only_data)) if __name__ == '__main__': From 9c6db73919d032ab2f6ea35b3a9043e3b0d2aed5 Mon Sep 17 00:00:00 2001 From: Ivan Menshikh Date: Fri, 3 Aug 2018 08:12:54 +0500 Subject: [PATCH 34/40] Replace `np.integer` -> `np.int` in `AuthorTopicModel` (#2145) --- gensim/models/atmodel.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py index d0a5940512..412f630099 100755 --- a/gensim/models/atmodel.py +++ b/gensim/models/atmodel.py @@ -461,11 +461,11 @@ def inference(self, chunk, author2doc, doc2author, rhot, collect_sstats=False, c ids = [int(idx) for idx, _ in doc] else: ids = [idx for idx, _ in doc] - ids = np.array(ids, dtype=np.integer) - cts = np.array([cnt for _, cnt in doc], dtype=np.integer) + ids = np.array(ids, dtype=np.int) + cts = np.array([cnt for _, cnt in doc], dtype=np.int) # Get all authors in current document, and convert the author names to integer IDs. - authors_d = np.array([self.author2id[a] for a in self.doc2author[doc_no]], dtype=np.integer) + authors_d = np.array([self.author2id[a] for a in self.doc2author[doc_no]], dtype=np.int) gammad = self.state.gamma[authors_d, :] # gamma of document d before update. tilde_gamma = gammad.copy() # gamma that will be updated. @@ -973,9 +973,9 @@ def bound(self, chunk, chunk_doc_idx=None, subsample_ratio=1.0, author2doc=None, else: doc_no = d # Get all authors in current document, and convert the author names to integer IDs. - authors_d = np.array([self.author2id[a] for a in self.doc2author[doc_no]], dtype=np.integer) - ids = np.array([id for id, _ in doc], dtype=np.integer) # Word IDs in doc. - cts = np.array([cnt for _, cnt in doc], dtype=np.integer) # Word counts. + authors_d = np.array([self.author2id[a] for a in self.doc2author[doc_no]], dtype=np.int) + ids = np.array([id for id, _ in doc], dtype=np.int) # Word IDs in doc. + cts = np.array([cnt for _, cnt in doc], dtype=np.int) # Word counts. if d % self.chunksize == 0: logger.debug("bound: at document #%i in chunk", d) From 2ee7facede554c960b36447439dfe7d616ee6eb9 Mon Sep 17 00:00:00 2001 From: RunHorst Date: Tue, 7 Aug 2018 15:48:25 +0200 Subject: [PATCH 35/40] Fix minor semantic issue in docs for phrases (#2148) * Fix minor semantic issue in docs for phrases * Fix minor issues in docstrings for phrases --- gensim/models/phrases.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py index ed6f4c44df..603769957d 100644 --- a/gensim/models/phrases.py +++ b/gensim/models/phrases.py @@ -113,7 +113,7 @@ def score_item(self, worda, wordb, components, scorer): Returns ------- float - Score for given bi-gram, if bi-gram not presented in dictionary - return -1. + Score for given bi-gram. If bi-gram not present in dictionary - return -1. """ vocab = self.vocab @@ -136,7 +136,7 @@ def analyze_sentence(self, sentence, threshold, common_terms, scorer): threshold : float The minimum score for a bigram to be taken into account. common_terms : list of object - List of common terms, they have special treatment. + List of common terms, they receive special treatment. scorer : function Scorer function, as given to :class:`~gensim.models.phrases.Phrases`. See :func:`~gensim.models.phrases.npmi_scorer` and :func:`~gensim.models.phrases.original_scorer`. @@ -224,7 +224,7 @@ def load(cls, *args, **kwargs): else: raise ValueError( 'failed to load %s model with unknown scoring setting %s' % (cls.__name__, model.scoring)) - # if there is non common_terms attribute, initialize + # if there is no common_terms attribute, initialize if not hasattr(model, "common_terms"): logger.info('older version of %s loaded without common_terms attribute', cls.__name__) logger.info('setting common_terms to empty set') @@ -252,7 +252,7 @@ def __init__(self, sentences=None, min_count=5, threshold=10.0, threshold : float, optional Represent a score threshold for forming the phrases (higher means fewer phrases). A phrase of words `a` followed by `b` is accepted if the score of the phrase is greater than threshold. - Hardly depends on concrete socring-function, see the `scoring` parameter. + Heavily depends on concrete scoring-function, see the `scoring` parameter. max_vocab_size : int, optional Maximum size (number of tokens) of the vocabulary. Used to control pruning of less common words, to keep memory under control. The default of 40M needs about 3.6GB of RAM. Increase/decrease @@ -641,7 +641,7 @@ def original_scorer(worda_count, wordb_count, bigram_count, len_vocab, min_count len_vocab : int Size of vocabulary. min_count: int - Minimum score threshold. + Minimum collocation count threshold. corpus_word_count : int Not used in this particular scoring technique. From 010780003c873938b3fdd9f8ead7bd1ce7f23975 Mon Sep 17 00:00:00 2001 From: Rob Guinness Date: Fri, 10 Aug 2018 13:40:29 +0300 Subject: [PATCH 36/40] Remove duplicate count from `Phraser` log message (#2151) Remove duplicate count from `Phraser` log message --- gensim/models/phrases.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py index 17ee648e30..09d709b193 100644 --- a/gensim/models/phrases.py +++ b/gensim/models/phrases.py @@ -776,7 +776,7 @@ def __init__(self, phrases_model): count += 1 if not count % 50000: logger.info('Phraser added %i phrasegrams', count) - logger.info('Phraser built with %i %i phrasegrams', count, len(self.phrasegrams)) + logger.info('Phraser built with %i phrasegrams', len(self.phrasegrams)) def pseudocorpus(self, phrases_model): """Alias for :func:`gensim.models.phrases.pseudocorpus`. From 17fa0dcea8bb7824f0e709fd3ff60007bcdd85f6 Mon Sep 17 00:00:00 2001 From: Luka Shostenko Date: Fri, 10 Aug 2018 14:41:26 +0300 Subject: [PATCH 37/40] Fix `ZeroDivisionError` `keywords` issue with short input (#2154) * Return keywords before matrix processing if no graph edges. * Add testcase for empty graph. --- gensim/summarization/keywords.py | 3 +++ gensim/test/test_keywords.py | 6 ++++++ 2 files changed, 9 insertions(+) diff --git a/gensim/summarization/keywords.py b/gensim/summarization/keywords.py index 4074088a04..9f43158146 100644 --- a/gensim/summarization/keywords.py +++ b/gensim/summarization/keywords.py @@ -512,6 +512,9 @@ def keywords(text, ratio=0.2, words=None, split=False, scores=False, pos_filter= _remove_unreachable_nodes(graph) + if not graph.edges(): + return _format_results([], [], split, scores) + # Ranks the tokens using the PageRank algorithm. Returns dict of lemma -> score pagerank_scores = _pagerank(graph) diff --git a/gensim/test/test_keywords.py b/gensim/test/test_keywords.py index c8fae400da..79df82fba6 100644 --- a/gensim/test/test_keywords.py +++ b/gensim/test/test_keywords.py @@ -95,6 +95,12 @@ def test_text_keywords_with_small_graph(self): kwds = keywords(text, words=1, split=True) self.assertTrue(len(kwds)) + def test_text_keywords_without_graph_edges(self): + # regression test, we get graph with no edges on this text + text = 'Sitio construcción. Estaremos línea.' + kwds = keywords(text, deacc=False, scores=True) + self.assertFalse(len(kwds)) + if __name__ == '__main__': logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG) From 466b32fe6b5631403fe5be8c16233df3d61a373b Mon Sep 17 00:00:00 2001 From: Shiki-H Date: Mon, 13 Aug 2018 00:02:33 -0400 Subject: [PATCH 38/40] Add multiprocessing support for `BM25` (#2146) * added multiprocessing support for bm25 * added effective_n_job check * added comment for helper function * fixed minor error * deleted unwanted comments * updated example with new api * updated example with new api * updated support for multiprocessing * updated docstring * fixed typo * fixed formatting * changed assertEqual to assertAlmostEqual * fixed docstrings to numpy-style * removed space from blank lines * moved effective_n_jobs to utils --- gensim/summarization/bm25.py | 52 ++++++++++++++++++++++++++++++------ gensim/test/test_BM25.py | 9 +++++++ gensim/utils.py | 28 +++++++++++++++++++ 3 files changed, 81 insertions(+), 8 deletions(-) diff --git a/gensim/summarization/bm25.py b/gensim/summarization/bm25.py index 3a2bf5bbf6..50019c32fe 100644 --- a/gensim/summarization/bm25.py +++ b/gensim/summarization/bm25.py @@ -22,7 +22,7 @@ ... ["cat", "outer", "space"], ... ["wag", "dog"] ... ] ->>> result = get_bm25_weights(corpus) +>>> result = get_bm25_weights(corpus, n_jobs=-1) Data: @@ -37,7 +37,9 @@ import math from six import iteritems from six.moves import xrange - +from functools import partial +from multiprocessing import Pool +from ..utils import effective_n_jobs PARAM_K1 = 1.5 PARAM_B = 0.75 @@ -152,7 +154,33 @@ def get_scores(self, document, average_idf): return scores -def get_bm25_weights(corpus): +def _get_scores(bm25, document, average_idf): + """Helper function for retrieving bm25 scores of given `document` in parallel + in relation to every item in corpus. + + Parameters + ---------- + bm25 : BM25 object + BM25 object fitted on the corpus where documents are retrieved. + document : list of str + Document to be scored. + average_idf : float + Average idf in corpus. + + Returns + ------- + list of float + BM25 scores. + + """ + scores = [] + for index in xrange(bm25.corpus_size): + score = bm25.get_score(document, index, average_idf) + scores.append(score) + return scores + + +def get_bm25_weights(corpus, n_jobs=1): """Returns BM25 scores (weights) of documents in corpus. Each document has to be weighted with every document in given corpus. @@ -160,6 +188,8 @@ def get_bm25_weights(corpus): ---------- corpus : list of list of str Corpus of documents. + n_jobs : int + The number of processes to use for computing bm25. Returns ------- @@ -174,15 +204,21 @@ def get_bm25_weights(corpus): ... ["cat", "outer", "space"], ... ["wag", "dog"] ... ] - >>> result = get_bm25_weights(corpus) + >>> result = get_bm25_weights(corpus, n_jobs=-1) """ bm25 = BM25(corpus) average_idf = sum(float(val) for val in bm25.idf.values()) / len(bm25.idf) - weights = [] - for doc in corpus: - scores = bm25.get_scores(doc, average_idf) - weights.append(scores) + n_processes = effective_n_jobs(n_jobs) + if n_processes == 1: + weights = [bm25.get_scores(doc, average_idf) for doc in corpus] + return weights + + get_score = partial(_get_scores, bm25, average_idf=average_idf) + pool = Pool(n_processes) + weights = pool.map(get_score, corpus) + pool.close() + pool.join() return weights diff --git a/gensim/test/test_BM25.py b/gensim/test/test_BM25.py index a96302e8c9..e37efc2920 100644 --- a/gensim/test/test_BM25.py +++ b/gensim/test/test_BM25.py @@ -44,6 +44,15 @@ def test_disjoint_docs_if_weight_zero(self): self.assertAlmostEqual(weights[0][1], 0) self.assertAlmostEqual(weights[1][0], 0) + def test_multiprocessing(self): + """ Result should be the same using different processes """ + weights1 = get_bm25_weights(common_texts) + weights2 = get_bm25_weights(common_texts, n_jobs=2) + weights3 = get_bm25_weights(common_texts, n_jobs=-1) + self.assertAlmostEqual(weights1, weights2) + self.assertAlmostEqual(weights1, weights3) + self.assertAlmostEqual(weights2, weights3) + if __name__ == '__main__': logging.basicConfig(level=logging.DEBUG) diff --git a/gensim/utils.py b/gensim/utils.py index ec02cf4bb2..35abc203d8 100644 --- a/gensim/utils.py +++ b/gensim/utils.py @@ -44,6 +44,8 @@ from smart_open import smart_open +from multiprocessing import cpu_count + if sys.version_info[0] >= 3: unicode = str @@ -2025,3 +2027,29 @@ def lazy_flatten(nested_list): yield sub else: yield el + + +def effective_n_jobs(n_jobs): + """Determines the number of jobs can run in parallel. + + Just like in sklearn, passing n_jobs=-1 means using all available + CPU cores. + + Parameters + ---------- + n_jobs : int + Number of workers requested by caller. + + Returns + ------- + int + Number of effective jobs. + + """ + if n_jobs == 0: + raise ValueError('n_jobs == 0 in Parallel has no meaning') + elif n_jobs is None: + return 1 + elif n_jobs < 0: + n_jobs = max(cpu_count() + 1 + n_jobs, 1) + return n_jobs From f9beeaa9fff68edf83443f6cd0c14732895c4f44 Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 17:06:46 +0200 Subject: [PATCH 39/40] Fix `default` -> `auto` prior parameter in documentation for lda-related models (#2156) * update documentation to match actual code Change "default" to "auto" since there is no handling on the value "default". * Update ldamodel.py * Update ldamulticore.py * Update ldamodel.py * Update atmodel.py * correct assymetric -> asymmetric * Update ldamulticore.py * Update atmodel.py * Update ldamodel.py --- gensim/models/ldamodel.py | 6 +++--- gensim/models/ldamulticore.py | 4 ++-- gensim/sklearn_api/atmodel.py | 4 ++-- gensim/sklearn_api/ldamodel.py | 4 ++-- 4 files changed, 9 insertions(+), 9 deletions(-) diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py index 2f8fca4768..2f66f30c52 100755 --- a/gensim/models/ldamodel.py +++ b/gensim/models/ldamodel.py @@ -369,7 +369,7 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, Alternatively default prior selecting strategies can be employed by supplying a string: * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. - * 'default': Learns an asymmetric prior from the corpus. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: @@ -530,8 +530,8 @@ def init_dir_prior(self, prior, name): If `name` == 'alpha', then the prior can be: * an 1D array of length equal to the number of expected topics, - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. name : {'alpha', 'eta'} Whether the `prior` is parameterized by the alpha vector (1 parameter per topic) or by the eta (1 parameter per unique term in the vocabulary). diff --git a/gensim/models/ldamulticore.py b/gensim/models/ldamulticore.py index d32a709f80..168a2752c0 100644 --- a/gensim/models/ldamulticore.py +++ b/gensim/models/ldamulticore.py @@ -128,8 +128,8 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, workers=None, our a-priori belief for the each topics' probability. Alternatively default prior selecting strategies can be employed by supplying a string: - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: diff --git a/gensim/sklearn_api/atmodel.py b/gensim/sklearn_api/atmodel.py index 69397833c0..085ed9a745 100644 --- a/gensim/sklearn_api/atmodel.py +++ b/gensim/sklearn_api/atmodel.py @@ -82,8 +82,8 @@ def __init__(self, num_topics=100, id2word=None, author2doc=None, doc2author=Non our a-priori belief for the each topics' probability. Alternatively default prior selecting strategies can be employed by supplying a string: - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: diff --git a/gensim/sklearn_api/ldamodel.py b/gensim/sklearn_api/ldamodel.py index 3e5d65dcc6..33f2575acc 100644 --- a/gensim/sklearn_api/ldamodel.py +++ b/gensim/sklearn_api/ldamodel.py @@ -60,8 +60,8 @@ def __init__(self, num_topics=100, id2word=None, chunksize=2000, passes=1, updat our a-priori belief for the each topics' probability. Alternatively default prior selecting strategies can be employed by supplying a string: - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From 27c524db60828e5ab1580a46a8ca5520dfd4d352 Mon Sep 17 00:00:00 2001 From: Vimig Socrates Date: Mon, 13 Aug 2018 21:53:41 -0400 Subject: [PATCH 40/40] Make `word2vec2tensor` script compatible with `python3` (#2147) * encoded strings to unicode * added test scripts for word2vec2tensor * added acknowledgement * removed windows CRs * changed filenotfound to exception to appease flake8 * addressed comments, added key-wise assert * forgot to check flake8 again * added dec param to pass test --- gensim/scripts/word2vec2tensor.py | 13 +- gensim/test/test_scripts.py | 263 ++++++++++++++++++------------ 2 files changed, 162 insertions(+), 114 deletions(-) diff --git a/gensim/scripts/word2vec2tensor.py b/gensim/scripts/word2vec2tensor.py index 2618bdcae0..5bf8d2e23b 100644 --- a/gensim/scripts/word2vec2tensor.py +++ b/gensim/scripts/word2vec2tensor.py @@ -1,6 +1,7 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- # +# Copyright (C) 2018 Vimig Socrates # Copyright (C) 2016 Loreto Parisi # Copyright (C) 2016 Silvio Olivastri # Copyright (C) 2016 Radim Rehurek @@ -43,6 +44,7 @@ import logging import argparse +from smart_open import smart_open import gensim logger = logging.getLogger(__name__) @@ -67,12 +69,11 @@ def word2vec2tensor(word2vec_model_path, tensor_filename, binary=False): outfiletsv = tensor_filename + '_tensor.tsv' outfiletsvmeta = tensor_filename + '_metadata.tsv' - with open(outfiletsv, 'w+') as file_vector: - with open(outfiletsvmeta, 'w+') as file_metadata: - for word in model.index2word: - file_metadata.write(gensim.utils.to_utf8(word) + gensim.utils.to_utf8('\n')) - vector_row = '\t'.join(str(x) for x in model[word]) - file_vector.write(vector_row + '\n') + with smart_open(outfiletsv, 'wb') as file_vector, smart_open(outfiletsvmeta, 'wb') as file_metadata: + for word in model.index2word: + file_metadata.write(gensim.utils.to_utf8(word) + gensim.utils.to_utf8('\n')) + vector_row = '\t'.join(str(x) for x in model[word]) + file_vector.write(gensim.utils.to_utf8(vector_row) + gensim.utils.to_utf8('\n')) logger.info("2D tensor file saved to %s", outfiletsv) logger.info("Tensor metadata file saved to %s", outfiletsvmeta) diff --git a/gensim/test/test_scripts.py b/gensim/test/test_scripts.py index 001283e3c4..2fa625e942 100644 --- a/gensim/test/test_scripts.py +++ b/gensim/test/test_scripts.py @@ -1,108 +1,155 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- -# -# Copyright (C) 2018 Manos Stergiadis -# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html - -""" -Automated tests for checking the output of gensim.scripts. -""" - -from __future__ import unicode_literals - -import json -import logging -import os.path -import unittest - -from gensim.scripts.segment_wiki import segment_all_articles, segment_and_write_all_articles -from smart_open import smart_open -from gensim.test.utils import datapath, get_tmpfile - - -class TestSegmentWiki(unittest.TestCase): - - def setUp(self): - self.fname = datapath('enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2') - self.expected_title = 'Anarchism' - self.expected_section_titles = [ - 'Introduction', - 'Etymology and terminology', - 'History', - 'Anarchist schools of thought', - 'Internal issues and debates', - 'Topics of interest', - 'Criticisms', - 'References', - 'Further reading', - 'External links' - ] - - def tearDown(self): - # remove all temporary test files - fname = get_tmpfile('script.tst') - extensions = ['', '.json'] - for ext in extensions: - try: - os.remove(fname + ext) - except OSError: - pass - - def test_segment_all_articles(self): - title, sections, interlinks = next(segment_all_articles(self.fname, include_interlinks=True)) - - # Check title - self.assertEqual(title, self.expected_title) - - # Check section titles - section_titles = [s[0] for s in sections] - self.assertEqual(section_titles, self.expected_section_titles) - - # Check text - first_section_text = sections[0][1] - first_sentence = "'''Anarchism''' is a political philosophy that advocates self-governed societies" - self.assertTrue(first_sentence in first_section_text) - - # Check interlinks - self.assertTrue(interlinks['self-governance'] == 'self-governed') - self.assertTrue(interlinks['Hierarchy'] == 'hierarchical') - self.assertTrue(interlinks['Pierre-Joseph Proudhon'] == 'Proudhon') - - def test_generator_len(self): - expected_num_articles = 106 - num_articles = sum(1 for x in segment_all_articles(self.fname)) - - self.assertEqual(num_articles, expected_num_articles) - - def test_json_len(self): - tmpf = get_tmpfile('script.tst.json') - segment_and_write_all_articles(self.fname, tmpf, workers=1) - - expected_num_articles = 106 - num_articles = sum(1 for line in smart_open(tmpf)) - self.assertEqual(num_articles, expected_num_articles) - - def test_segment_and_write_all_articles(self): - tmpf = get_tmpfile('script.tst.json') - segment_and_write_all_articles(self.fname, tmpf, workers=1, include_interlinks=True) - - # Get the first line from the text file we created. - with open(tmpf) as f: - first = next(f) - - # decode JSON line into a Python dictionary object - article = json.loads(first) - title, section_titles, interlinks = article['title'], article['section_titles'], article['interlinks'] - - self.assertEqual(title, self.expected_title) - self.assertEqual(section_titles, self.expected_section_titles) - - # Check interlinks - self.assertTrue(interlinks['self-governance'] == 'self-governed') - self.assertTrue(interlinks['Hierarchy'] == 'hierarchical') - self.assertTrue(interlinks['Pierre-Joseph Proudhon'] == 'Proudhon') - - -if __name__ == '__main__': - logging.basicConfig(level=logging.DEBUG) - unittest.main() +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# +# Copyright (C) 2018 Vimig Socrates heavily influenced from @AakaashRao +# Copyright (C) 2018 Manos Stergiadis +# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html + +""" +Automated tests for checking the output of gensim.scripts. +""" + +from __future__ import unicode_literals + +import json +import logging +import os.path +import unittest + +from smart_open import smart_open +import numpy as np + +from gensim.scripts.segment_wiki import segment_all_articles, segment_and_write_all_articles +from gensim.test.utils import datapath, get_tmpfile + +from gensim.scripts.word2vec2tensor import word2vec2tensor +from gensim.models import KeyedVectors + + +class TestSegmentWiki(unittest.TestCase): + + def setUp(self): + self.fname = datapath('enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2') + self.expected_title = 'Anarchism' + self.expected_section_titles = [ + 'Introduction', + 'Etymology and terminology', + 'History', + 'Anarchist schools of thought', + 'Internal issues and debates', + 'Topics of interest', + 'Criticisms', + 'References', + 'Further reading', + 'External links' + ] + + def tearDown(self): + # remove all temporary test files + fname = get_tmpfile('script.tst') + extensions = ['', '.json'] + for ext in extensions: + try: + os.remove(fname + ext) + except OSError: + pass + + def test_segment_all_articles(self): + title, sections, interlinks = next(segment_all_articles(self.fname, include_interlinks=True)) + + # Check title + self.assertEqual(title, self.expected_title) + + # Check section titles + section_titles = [s[0] for s in sections] + self.assertEqual(section_titles, self.expected_section_titles) + + # Check text + first_section_text = sections[0][1] + first_sentence = "'''Anarchism''' is a political philosophy that advocates self-governed societies" + self.assertTrue(first_sentence in first_section_text) + + # Check interlinks + self.assertTrue(interlinks['self-governance'] == 'self-governed') + self.assertTrue(interlinks['Hierarchy'] == 'hierarchical') + self.assertTrue(interlinks['Pierre-Joseph Proudhon'] == 'Proudhon') + + def test_generator_len(self): + expected_num_articles = 106 + num_articles = sum(1 for x in segment_all_articles(self.fname)) + + self.assertEqual(num_articles, expected_num_articles) + + def test_json_len(self): + tmpf = get_tmpfile('script.tst.json') + segment_and_write_all_articles(self.fname, tmpf, workers=1) + + expected_num_articles = 106 + num_articles = sum(1 for line in smart_open(tmpf)) + self.assertEqual(num_articles, expected_num_articles) + + def test_segment_and_write_all_articles(self): + tmpf = get_tmpfile('script.tst.json') + segment_and_write_all_articles(self.fname, tmpf, workers=1, include_interlinks=True) + + # Get the first line from the text file we created. + with open(tmpf) as f: + first = next(f) + + # decode JSON line into a Python dictionary object + article = json.loads(first) + title, section_titles, interlinks = article['title'], article['section_titles'], article['interlinks'] + + self.assertEqual(title, self.expected_title) + self.assertEqual(section_titles, self.expected_section_titles) + + # Check interlinks + self.assertTrue(interlinks['self-governance'] == 'self-governed') + self.assertTrue(interlinks['Hierarchy'] == 'hierarchical') + self.assertTrue(interlinks['Pierre-Joseph Proudhon'] == 'Proudhon') + + +class TestWord2Vec2Tensor(unittest.TestCase): + def setUp(self): + self.datapath = datapath('word2vec_pre_kv_c') + self.output_folder = get_tmpfile('w2v2t_test') + self.metadata_file = self.output_folder + '_metadata.tsv' + self.tensor_file = self.output_folder + '_tensor.tsv' + self.vector_file = self.output_folder + '_vector.tsv' + + def testConversion(self): + word2vec2tensor(word2vec_model_path=self.datapath, tensor_filename=self.output_folder) + + with smart_open(self.metadata_file, 'rb') as f: + metadata = f.readlines() + + with smart_open(self.tensor_file, 'rb') as f: + vectors = f.readlines() + + # check if number of words and vector size in tensor file line up with word2vec + with smart_open(self.datapath, 'rb') as f: + first_line = f.readline().strip() + + number_words, vector_size = map(int, first_line.split(b' ')) + self.assertTrue(len(metadata) == len(vectors) == number_words, + ('Metadata file %s and tensor file %s imply different number of rows.' + % (self.metadata_file, self.tensor_file))) + + # grab metadata and vectors from written file + metadata = [word.strip() for word in metadata] + vectors = [vector.replace(b'\t', b' ') for vector in vectors] + + # get the originaly vector KV model + orig_model = KeyedVectors.load_word2vec_format(self.datapath, binary=False) + + # check that the KV model and tensor files have the same values key-wise + for word, vector in zip(metadata, vectors): + word_string = word.decode("utf8") + vector_string = vector.decode("utf8") + vector_array = np.array(list(map(float, vector_string.split()))) + np.testing.assert_almost_equal(orig_model[word_string], vector_array, decimal=5) + + +if __name__ == '__main__': + logging.basicConfig(level=logging.DEBUG) + unittest.main()