gensim latest version

« Changelog History

gensim v4.2.0 Release Notes

• :+1: New features

  • #3188: Add get_sentence_vector() to FastText and get_mean_vector() to KeyedVectors, by @rock420
  • 👀 #3194: Added random_seed parameter to make LsiModel reproducible, by @parashardhapola
  • #3247: Sparse2Corpus: update getitem to work on slices, lists and ellipsis, by @PrimozGodec
  • #3264: Detect when a fasttext executable is available in PATH, by @pabs3
  • #3271: Added new ValueError in place of assertion error for no model data provided in lsi model, by @mark-todd
  • #3299: Enable test_word2vec_stand_alone_script by using sys.executable for python, by @pabs3
  • #3317: Added encoding parameter to TextDirectoryCorpus, by @Sandman-Ren
  • #2656: Streamlining most_similar_cosmul and evaluate_word_analogies, by @n3hrox

  📄 :books: Tutorials and docs

  • 🏗 #3227: Fix FastText doc-comment example for build_vocab and train to use correct argument names, by @HLasse
  • 📄 #3235: Fix TFIDF docs, by @piskvorky
  • 🙋 #3257: Dictionary doc: ref FAQ entry about filter_extremes corpus migration, by @zacchiro
  • 📄 #3279: Add the FastSS and Levenshtein modules to docs, by @piskvorky
  • 📚 #3284: Documentation fixes + added CITATION.cff, by @piskvorky
  • ✏️ #3289: Typos, text and code fix in LDA tutorial, by @davebulaval
  • 🚚 #3301: Remove unused Jupyter screenshots, by @pabs3
  • 📚 #3307: Documentation fixes, by @piskvorky
  • 📜 #3339: Fix parsing error in FastText docs, by @MattYoon
  • #3251: Apply new convention of delimiting instance params in str function, by @menshikh-iv

  🛠 :red_circle: Bug fixes

  • #3117: Ensure next_index available when loading old stored KeyedVectors models, by @gojomo
  • #3182: Fix error message when Doc2Vec does not receive corpus_file or corpus iterable, by @blainedietrich
  • #3190: Fix broken external link for LDA implementation, by @ahaya3776
  • #3197: Fix computation of topic coherence, by @silviatti
  • #3250: Make negative ns_exponent work correctly, by @menshikh-iv
  • #3282: Fix str() method in WmdSimilarity, by @DingQK
  • 🛠 #3286: Fixes 'not enough arguments for format string' error, by @gilbertfrancois
  • #3309: Respect encoding when reading binary keyed vectors, by @alhoo
  • #3332: Missing f prefix on f-strings fix, by @code-review-doctor

  🚚 :warning: Removed functionality & deprecations

  ✅ 🔮 Testing, CI, housekeeping

  • 🔧 #3230: Adding lifecycle configuration, by @mpenkov
  • #3252: Add Codecov to gensim repo, by @menshikh-iv
  • 🏁 #3255: Move windows tests from azure to github actions, by @menshikh-iv
  • 🚚 #3263: Remove commented out pytest-rerunfailures test dependency, by @pabs3
  • #3274: Migrate setup.py from distutils to setuptools, by @geojacobm6
  • 🏗 #3298: test and build wheels for Py3.{7,8,9,10}, by @mpenkov
  • #3300: Fix code formatting for FT_CMD definition, by @pabs3
  • #3303: add GitHub URL for PyPi, by @andriyor
  • 🏗 #3308: get rid of tox, build things via github actions directly, by @mpenkov
  • #3318: Clean up evaluate_word_pairs code, by @piskvorky
  • #3329: Check gallery up to date as part of CI, by @mpenkov
  • #3254: Skip blinking test test_translate_gc on OSX + py3.9, by @menshikh-iv
  • #3258: Adding another check to _check_corpus_sanity for compressed files, adding test, by @dchaplinsky
  • ✅ #3278: Tighten test_parallel bound, by @austereantelope
  • #3280: tighten test_topic_word, by @austereantelope
  • ✅ #3281: adjust test_parallel bound, by @austereantelope
  • ✅ #3297: Use gensim.test.utils datapath() to construct paths to the test data, by @pabs3

Previous changes from v4.1.2

• 🛠 This is a bugfix release that addresses left over compatibility issues with older versions of numpy and MacOS.

• All Versions
• Previous v4.1.2