fix W504

gensim/models/coherencemodel.py

@@ -460,9 +460,9 @@ def _relevant_ids_will_differ(self, new_topics):
         return not self._accumulator.relevant_ids.issuperset(new_set)
 
     def _topics_differ(self, new_topics):
-        return (new_topics is not None and
-                self._topics is not None and
-                not np.array_equal(new_topics, self._topics))
+        return (new_topics is not None
+                and self._topics is not None
+                and not np.array_equal(new_topics, self._topics))
 
     def _get_topics(self):
         """Internal helper function to return topics from a trained topic model."""

gensim/models/deprecated/doc2vec.py

@@ -242,8 +242,8 @@ def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=N
     if doctag_locks is None:
         doctag_locks = model.docvecs.doctag_syn0_lockf
 
-    word_vocabs = [model.wv.vocab[w] for w in doc_words 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 doc_words 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 doc2vec code
@@ -298,8 +298,8 @@ def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None,
     if doctag_locks is None:
         doctag_locks = model.docvecs.doctag_syn0_lockf
 
-    word_vocabs = [model.wv.vocab[w] for w in doc_words 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 doc_words if w in model.wv.vocab
+                   and model.wv.vocab[w].sample_int > model.random.rand() * 2**32]
     doctag_len = len(doctag_indexes)
     if doctag_len != model.dm_tag_count:
         return 0  # skip doc without expected number of doctag(s) (TODO: warn/pad?)

gensim/models/deprecated/fasttext.py

@@ -148,8 +148,8 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None):
     """
     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)
             start = max(0, pos - model.window + reduced_window)
@@ -211,8 +211,8 @@ def train_batch_sg(model, sentences, alpha, work=None, neu1=None):
     """
     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
             # now go over all words from the (reduced) window, predicting each one in turn

gensim/models/deprecated/old_saveload.py

@@ -108,8 +108,8 @@ def _load_specials(self, fname, mmap, compress, subname):
         """
         def mmap_error(obj, filename):
             return IOError(
-                'Cannot mmap compressed object %s in file %s. ' % (obj, filename) +
-                'Use `load(fname, mmap=None)` or uncompress files manually.'
+                'Cannot mmap compressed object %s in file %s. ' % (obj, filename)
+                + 'Use `load(fname, mmap=None)` or uncompress files manually.'
             )
 
         for attrib in getattr(self, '__recursive_saveloads', []):

gensim/models/deprecated/word2vec.py

@@ -232,8 +232,8 @@ def train_batch_sg(model, sentences, alpha, work=None, compute_loss=False):
     """
     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
 
@@ -263,8 +263,8 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None, compute_loss
     """
     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)

gensim/models/doc2vec.py

@@ -227,8 +227,8 @@ def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=N
         if doctag_locks is None:
             doctag_locks = model.docvecs.doctag_syn0_lockf
 
-        word_vocabs = [model.wv.vocab[w] for w in doc_words 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 doc_words 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 doc2vec code
@@ -314,8 +314,8 @@ def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None,
         if doctag_locks is None:
             doctag_locks = model.docvecs.doctag_syn0_lockf
 
-        word_vocabs = [model.wv.vocab[w] for w in doc_words 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 doc_words if w in model.wv.vocab
+                       and model.wv.vocab[w].sample_int > model.random.rand() * 2 ** 32]
         doctag_len = len(doctag_indexes)
         if doctag_len != model.dm_tag_count:
             return 0  # skip doc without expected number of doctag(s) (TODO: warn/pad?)

gensim/models/fasttext.py

@@ -140,8 +140,8 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None):
         """
         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)
                 start = max(0, pos - model.window + reduced_window)
@@ -199,8 +199,8 @@ def train_batch_sg(model, sentences, alpha, work=None, neu1=None):
         """
         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
                 # now go over all words from the (reduced) window, predicting each one in turn

gensim/models/hdpmodel.py

@@ -510,13 +510,13 @@ def update_finished(self, start_time, chunks_processed, docs_processed):
         """
         return (
             # chunk limit reached
-            (self.max_chunks and chunks_processed == self.max_chunks) or
+            (self.max_chunks and chunks_processed == self.max_chunks)
 
             # time limit reached
-            (self.max_time and time.clock() - start_time > self.max_time) or
+            or (self.max_time and time.clock() - start_time > self.max_time)
 
             # no limits and whole corpus has been processed once
-            (not self.max_chunks and not self.max_time and docs_processed >= self.m_D))
+            or (not self.max_chunks and not self.max_time and docs_processed >= self.m_D))
 
     def update_chunk(self, chunk, update=True, opt_o=True):
         """Performs lazy update on necessary columns of lambda and variational inference for documents in the chunk.

gensim/models/ldamulticore.py

@@ -276,9 +276,9 @@ def process_result_queue(force=False):
                 if (force and merged_new and queue_size[0] == 0) or (not self.batch and (other.numdocs >= updateafter)):
                     self.do_mstep(rho(), other, pass_ > 0)
                     other.reset()
-                    if self.eval_every is not None and \
-                            ((force and queue_size[0] == 0) or
-                                 (self.eval_every != 0 and (self.num_updates / updateafter) % self.eval_every == 0)):
+                    if self.eval_every is not None \
+                            and ((force and queue_size[0] == 0)
+                            or (self.eval_every != 0 and (self.num_updates / updateafter) % self.eval_every == 0)):
                         self.log_perplexity(chunk, total_docs=lencorpus)
 
             chunk_stream = utils.grouper(corpus, self.chunksize, as_numpy=chunks_as_numpy)

gensim/models/word2vec.py

@@ -193,8 +193,8 @@ def train_batch_sg(model, sentences, alpha, work=None, compute_loss=False):
         """
         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
 
@@ -245,8 +245,8 @@ def train_batch_cbow(model, sentences, alpha, work=None, neu1=None, compute_loss
         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
+                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

gensim/summarization/mz_entropy.py

@@ -98,9 +98,9 @@ def marginal_prob(n, m):
            occurring m times in a given block"""
 
         return numpy.exp(
-            __log_combinations(n, m) +
-            __log_combinations(n_words - n, blocksize - m) -
-            __log_combinations(n_words, blocksize)
+            __log_combinations(n, m)
+            + __log_combinations(n_words - n, blocksize - m)
+            - __log_combinations(n_words, blocksize)
         )
 
     return numpy.frompyfunc(marginal_prob, 2, 1)

gensim/test/test_doc2vec.py

@@ -340,8 +340,8 @@ def test_similarity_unseen_docs(self):
         model = doc2vec.Doc2Vec(min_count=1)
         model.build_vocab(corpus)
         self.assertTrue(
-            model.docvecs.similarity_unseen_docs(model, rome_str, rome_str) >
-            model.docvecs.similarity_unseen_docs(model, rome_str, car_str)
+            model.docvecs.similarity_unseen_docs(model, rome_str, rome_str)
+            > model.docvecs.similarity_unseen_docs(model, rome_str, car_str)
         )
 
     def model_sanity(self, model, keep_training=True):

gensim/test/test_keyedvectors.py

@@ -38,8 +38,7 @@ def test_similarity_matrix(self):
         similarity_matrix = self.vectors.similarity_matrix(dictionary).todense()
         self.assertTrue((similarity_matrix.T == similarity_matrix).all())
         self.assertTrue(
-            (np.diag(similarity_matrix) ==
-             np.ones(similarity_matrix.shape[0])).all())
+            (np.diag(similarity_matrix) == np.ones(similarity_matrix.shape[0])).all())
 
         # checking that thresholding works as expected
         similarity_matrix = self.vectors.similarity_matrix(dictionary, threshold=0.45).todense()

gensim/utils.py

@@ -447,8 +447,8 @@ def _load_specials(self, fname, mmap, compress, subname):
         """
         def mmap_error(obj, filename):
             return IOError(
-                'Cannot mmap compressed object %s in file %s. ' % (obj, filename) +
-                'Use `load(fname, mmap=None)` or uncompress files manually.'
+                'Cannot mmap compressed object %s in file %s. ' % (obj, filename)
+                + 'Use `load(fname, mmap=None)` or uncompress files manually.'
             )
 
         for attrib in getattr(self, '__recursive_saveloads', []):