Update numpy -> 2.0 and removing deprecated scipy

.github/workflows/build-docs.yml

@@ -25,7 +25,7 @@ jobs:
           #
           # We use Py3.8 here for historical reasons.
           #
-          python-version: "3.8"
+          python-version: "3.9"
 
       - name: Update pip
         run: python -m pip install -U pip
@@ -35,7 +35,7 @@ jobs:
           sudo apt-get -yq update
           sudo apt-get -yq remove texlive-binaries --purge
           sudo apt-get -yq --no-install-suggests --no-install-recommends --force-yes install dvipng texlive-latex-base texlive-latex-extra texlive-latex-recommended texlive-latex-extra texlive-fonts-recommended latexmk
-          sudo apt-get -yq install build-essential python3.8-dev
+          sudo apt-get -yq install build-essential python3.9-dev
       - name: Install gensim and its dependencies
         run: pip install -e .[docs]
 

.github/workflows/build-wheels.yml

@@ -23,7 +23,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, windows-2019, macos-11]
+        os: [ubuntu-20.04, windows-2019, macos-12]
     steps:
 
       - name: Checkout
@@ -61,21 +61,17 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - {python: '3.8', os: macos-11}
-          - {python: '3.9', os: macos-11}
-          - {python: '3.10', os: macos-11}
-          - {python: '3.11', os: macos-11}
-          - {python: '3.12', os: macos-11}
+          - {python: '3.9', os: macos-12}
+          - {python: '3.10', os: macos-12}
+          - {python: '3.11', os: macos-12}
+          - {python: '3.12', os: macos-12}
 
-          - {python: '3.8', os: ubuntu-20.04}
           - {python: '3.9', os: ubuntu-20.04}
           - {python: '3.10', os: ubuntu-20.04}
           - {python: '3.11', os: ubuntu-20.04}
           - {python: '3.12', os: ubuntu-20.04}
 
-          - {python: '3.8', os: windows-2019}
           - {python: '3.9', os: windows-2019}
-
           - {python: '3.10', os: windows-2019}
           - {python: '3.11', os: windows-2019}
           - {python: '3.12', os: windows-2019}

.github/workflows/tests.yml

@@ -33,7 +33,7 @@ jobs:
           #
           # We use Py3.8 here for historical reasons.
           #
-          python-version: "3.8"
+          python-version: "3.9"
 
       - name: Update pip
         run: python -m pip install -U pip
@@ -43,7 +43,7 @@ jobs:
           sudo apt-get -yq update
           sudo apt-get -yq remove texlive-binaries --purge
           sudo apt-get -yq --no-install-suggests --no-install-recommends --force-yes install dvipng texlive-latex-base texlive-latex-extra texlive-latex-recommended texlive-latex-extra texlive-fonts-recommended latexmk
-          sudo apt-get -yq install build-essential python3.8-dev
+          sudo apt-get -yq install build-essential python3.9-dev
       - name: Install gensim and its dependencies
         run: pip install -e .[docs]
 
@@ -63,13 +63,11 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - {python: '3.8', os: ubuntu-20.04}
           - {python: '3.9', os: ubuntu-20.04}
           - {python: '3.10', os: ubuntu-20.04}
           - {python: '3.11', os: ubuntu-20.04}
           - {python: '3.12', os: ubuntu-20.04}
 
-          - {python: '3.8', os: windows-2019}
           - {python: '3.9', os: windows-2019}
           - {python: '3.10', os: windows-2019}
           - {python: '3.11', os: windows-2019}
@@ -161,7 +159,7 @@ jobs:
 
       - name: Upload coverage to Codecov
         if: matrix.coverage == true
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
         with:
           fail_ci_if_error: true
           files: ./coverage.xml

.github/workflows/update_index.py

@@ -21,7 +21,13 @@ def main():
     for page in paginator.paginate(Bucket=bucket, Delimiter='/', Prefix=prefix):
         for content in page.get('Contents', []):
             key = content['Key']
-            print(f"<li><a href='{key}'>{key}</a></li>")
+            #
+            # NB. use double quotes in href because that's that
+            # wheelhouse_uploader expects.
+            #
+            # https://github.com/ogrisel/wheelhouse-uploader/blob/eb32a7bb410769bb4212a9aa7fb3bfa3cef1aaec/wheelhouse_uploader/fetch.py#L15
+            #
+            print(f"""<li><a href="{key}">{key}</a></li>""")
     print("</ul></body></html>")
 
 

CHANGELOG.md

@@ -1,5 +1,26 @@
 Changes
 =======
+
+## 4.3.3, 2024-07-19
+
+### :star2: New Features
+
+### :red_circle: Bug fixes
+
+* Correct file argument name in KeyedVectors.save docstring (__[hammad7](https://github.com/hammad7)__, [#3532](https://github.com/piskvorky/gensim/pull/3532))
+* Import deprecated scipy.linalg.triu from numpy.triu instead (__[Luffy610](https://github.com/Luffy610)__, [#3524](https://github.com/piskvorky/gensim/pull/3524))
+
+### :books: Tutorial and doc improvements
+
+* Updated the broken Documentation Link on the README.md (__[wittyicon29](https://github.com/wittyicon29)__, [#3505](https://github.com/piskvorky/gensim/pull/3505))
+
+### :+1: Improvements
+
+* Add support for python3.12 wheels (__[YoungMind1](https://github.com/YoungMind1)__, [#3531](https://github.com/piskvorky/gensim/pull/3531))
+* Removed scipy from build-only dependencies (__[filip-komarzyniec](https://github.com/filip-komarzyniec)__, [#3538](https://github.com/piskvorky/gensim/pull/3538))
+* Use newer unittest.mock everwhere (__[a-detiste](https://github.com/a-detiste)__, [#3529](https://github.com/piskvorky/gensim/pull/3529))
+* Handle optional parameters without implicit bool cast (__[nk-fouque](https://github.com/nk-fouque)__, [#3502](https://github.com/piskvorky/gensim/pull/3502))
+
 ## 4.3.2, 2023-08-23
 
 ### :red_circle: Bug fixes

README.md

@@ -49,13 +49,12 @@ on Wikipedia.
 Installation
 ------------
 
-This software depends on [NumPy and Scipy], two Python packages for
-scientific computing. You must have them installed prior to installing
-gensim.
-
-It is also recommended you install a fast BLAS library before installing
-NumPy. This is optional, but using an optimized BLAS such as MKL, [ATLAS] or
-[OpenBLAS] is known to improve performance by as much as an order of
+This software depends on [NumPy], a Python package for
+scientific computing. Please bear in mind that building NumPy from source
+(e.g. by installing gensim on a platform which lacks NumPy .whl distribution)
+is a non-trivial task involving [linking NumPy to a BLAS library].  
+It is recommended to provide a fast one (such as MKL, [ATLAS] or
+[OpenBLAS]) which can improve performance by as much as an order of
 magnitude. On OSX, NumPy picks up its vecLib BLAS automatically,
 so you don’t need to do anything special.
 
@@ -69,7 +68,9 @@ Or, if you have instead downloaded and unzipped the [source tar.gz]
 package:
 
 ```bash
-    python setup.py install
+    tar -xvzf gensim-X.X.X.tar.gz
+    cd gensim-X.X.X/
+    pip install .
 ```
 
 For alternative modes of installation, see the [documentation].
@@ -172,8 +173,10 @@ BibTeX entry:
   [documentation and Jupyter Notebook tutorials]: https://github.com/RaRe-Technologies/gensim/#documentation
   [Vector Space Model]: https://en.wikipedia.org/wiki/Vector_space_model
   [unsupervised document analysis]: https://en.wikipedia.org/wiki/Latent_semantic_indexing
-  [NumPy and Scipy]: https://scipy.org/install/
+  [NumPy]: https://numpy.org/install/
+  [linking NumPy to a BLAS library]: https://numpy.org/devdocs/building/blas_lapack.html
   [ATLAS]: https://math-atlas.sourceforge.net/
   [OpenBLAS]: https://xianyi.github.io/OpenBLAS/
   [source tar.gz]: https://pypi.org/project/gensim/
   [documentation]: https://radimrehurek.com/gensim/#install
+

docs/src/auto_examples/core/run_core_concepts.ipynb

@@ -195,7 +195,7 @@
       },
       "outputs": [],
       "source": [
-        "from gensim import similarities\n\nindex = similarities.SparseMatrixSimilarity(tfidf[bow_corpus], num_features=12)"
+        "from gensim import similarities\n\nindex = similarities.SparseMatrixSimilarity(tfidf[bow_corpus], num_features=max(tfidf.dfs) + 1)"
       ]
     },
     {
@@ -274,4 +274,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}

docs/src/conf.py

@@ -61,9 +61,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '4.3'
+version = '4.3.3'
 # The full version, including alpha/beta/rc tags.
-release = '4.3.2.dev0'
+release = '4.3.3'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/src/people.rst

@@ -48,6 +48,11 @@ Silver Sponsors
 Bronze Sponsors
 ---------------
 
+.. figure:: _static/images/route4me-logo.png
+   :target: https://route4me.com
+   :width: 50%
+   :alt: Route Optimizer and Route Planner Software
+
 .. figure:: _static/images/eaccidents-logo.png
    :target: https://eaccidents.com/
    :width: 50%

gensim/__init__.py

@@ -4,7 +4,7 @@
 
 """
 
-__version__ = '4.3.2.dev0'
+__version__ = '4.3.3'
 
 import logging
 

gensim/corpora/sharded_corpus.py

@@ -17,8 +17,6 @@
 
 """
 
-from __future__ import print_function
-
 import logging
 import os
 import math

gensim/models/keyedvectors.py

@@ -495,9 +495,9 @@ def get_mean_vector(self, keys, weights=None, pre_normalize=True, post_normalize
         if len(keys) == 0:
             raise ValueError("cannot compute mean with no input")
         if isinstance(weights, list):
-            weights = np.array(weights)
+            weights = np.array(weights, dtype=self.vectors.dtype)
         if weights is None:
-            weights = np.ones(len(keys))
+            weights = np.ones(len(keys), dtype=self.vectors.dtype)
         if len(keys) != weights.shape[0]:  # weights is a 1-D numpy array
             raise ValueError(
                 "keys and weights array must have same number of elements"
@@ -762,7 +762,7 @@ def save(self, *args, **kwargs):
 
         Parameters
         ----------
-        fname : str
+        fname_or_handle : str
             Path to the output file.
 
         See Also
@@ -1667,7 +1667,7 @@ def save_word2vec_format(
                 if binary:
                     fout.write(f"{prefix}{key} ".encode('utf8') + key_vector.astype(REAL).tobytes())
                 else:
-                    fout.write(f"{prefix}{key} {' '.join(repr(val) for val in key_vector)}\n".encode('utf8'))
+                    fout.write(f"{prefix}{key} {' '.join(repr(val) for val in key_vector.tolist())}\n".encode('utf8'))
 
     @classmethod
     def load_word2vec_format(
@@ -1977,7 +1977,7 @@ def _word2vec_read_text(fin, kv, counts, vocab_size, vector_size, datatype, unic
 
 def _word2vec_line_to_vector(line, datatype, unicode_errors, encoding):
     parts = utils.to_unicode(line.rstrip(), encoding=encoding, errors=unicode_errors).split(" ")
-    word, weights = parts[0], [datatype(x) for x in parts[1:]]
+    word, weights = parts[0], [datatype(x).item() for x in parts[1:]]
     return word, weights
 
 

gensim/models/ldamodel.py

@@ -133,10 +133,11 @@ def update_dir_prior(prior, N, logphat, rho):
         The updated prior.
 
     """
+    dtype = logphat.dtype
     gradf = N * (psi(np.sum(prior)) - psi(prior) + logphat)
 
-    c = N * polygamma(1, np.sum(prior))
-    q = -N * polygamma(1, prior)
+    c = N * polygamma(1, np.sum(prior)).astype(dtype)
+    q = -N * polygamma(1, prior).astype(dtype)
 
     b = np.sum(gradf / q) / (1 / c + np.sum(1 / q))
 

gensim/models/lsimodel.py

@@ -66,7 +66,6 @@
 import numpy as np
 import scipy.linalg
 import scipy.sparse
-from scipy.sparse import sparsetools
 
 from gensim import interfaces, matutils, utils
 from gensim.models import basemodel
@@ -960,10 +959,8 @@ def stochastic_svd(
         m, n = corpus.shape
         assert num_terms == m, f"mismatch in number of features: {m} in sparse matrix vs. {num_terms} parameter"
         o = random_state.normal(0.0, 1.0, (n, samples)).astype(y.dtype)  # draw a random gaussian matrix
-        sparsetools.csc_matvecs(
-            m, n, samples, corpus.indptr, corpus.indices,
-            corpus.data, o.ravel(), y.ravel(),
-        )  # y = corpus * o
+        y = corpus.dot(o)  # y = corpus * o
+
         del o
 
         # unlike np, scipy.sparse `astype()` copies everything, even if there is no change to dtype!
@@ -994,10 +991,7 @@ def stochastic_svd(
             num_docs += n
             logger.debug("multiplying chunk * gauss")
             o = random_state.normal(0.0, 1.0, (n, samples), ).astype(dtype)  # draw a random gaussian matrix
-            sparsetools.csc_matvecs(
-                m, n, samples, chunk.indptr, chunk.indices,  # y = y + chunk * o
-                chunk.data, o.ravel(), y.ravel(),
-            )
+            y = y + chunk * o
             del chunk, o
         y = [y]
         q, _ = matutils.qr_destroy(y)  # orthonormalize the range

gensim/models/tfidfmodel.py

@@ -360,16 +360,16 @@ def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.iden
         self.pivot = pivot
         self.eps = 1e-12
 
-        if smartirs:
+        if smartirs is not None:
             n_tf, n_df, n_n = self.smartirs
             self.wlocal = partial(smartirs_wlocal, local_scheme=n_tf)
             self.wglobal = partial(smartirs_wglobal, global_scheme=n_df)
 
-        if dictionary:
+        if dictionary is not None:
             # user supplied a Dictionary object, which already contains all the
             # statistics we need to construct the IDF mapping. we can skip the
             # step that goes through the corpus (= an optimization).
-            if corpus:
+            if corpus is not None:
                 logger.warning(
                     "constructor received both corpus and explicit inverse document frequencies; ignoring the corpus"
                 )
@@ -378,17 +378,17 @@ def __init__(self, corpus=None, id2word=None, dictionary=None, wlocal=utils.iden
             self.dfs = dictionary.dfs.copy()
             self.term_lens = {termid: len(term) for termid, term in dictionary.items()}
             self.idfs = precompute_idfs(self.wglobal, self.dfs, self.num_docs)
-            if not id2word:
+            if id2word is None:
                 self.id2word = dictionary
-        elif corpus:
+        elif corpus is not None:
             self.initialize(corpus)
         else:
             # NOTE: everything is left uninitialized; presumably the model will
             # be initialized in some other way
             pass
 
         # If smartirs is not None, override pivot and normalize
-        if not smartirs:
+        if smartirs is None:
             return
         if self.pivot is not None:
             if n_n in 'ub':

gensim/test/test_parsing.py

@@ -7,8 +7,8 @@
 
 import logging
 import unittest
+from unittest import mock
 
-import mock
 import numpy as np
 
 from gensim.parsing.preprocessing import (

gensim/test/test_poincare.py

@@ -13,10 +13,7 @@
 import os
 import tempfile
 import unittest
-try:
-    from mock import Mock
-except ImportError:
-    from unittest.mock import Mock
+from unittest.mock import Mock
 
 import numpy as np
 try: