├── .github ├── FUNDING.yml ├── dependabot.yml └── workflows │ ├── build-docs.yml │ ├── build-wheels.yml │ ├── installwheel.py │ ├── linters.yml │ ├── test_wheel.py │ ├── tests.yml │ └── update_index.py ├── .gitignore ├── CHANGELOG.md ├── CITATION.cff ├── CONTRIBUTING.md ├── COPYING ├── HACKTOBERFEST.md ├── ISSUE_TEMPLATE.md ├── MANIFEST.in ├── README.md ├── SECURITY.md ├── config.sh ├── continuous_integration ├── BucketLifecycleConfiguration.json ├── BucketLifecycleConfiguration.txt ├── check_wheels.py ├── debug.gdb ├── install_wheel.py └── upgrade_pip_py310.py ├── docs ├── notebooks │ ├── Any2Vec_Filebased.ipynb │ ├── Coherence.gif │ ├── Convergence.gif │ ├── Corpora_and_Vector_Spaces.ipynb │ ├── Diff.gif │ ├── Dynamic Topic Model.png │ ├── FastText_Tutorial.ipynb │ ├── Monkey Brains New.png │ ├── Monkey Brains.png │ ├── Perplexity.gif │ ├── Poincare Evaluation.ipynb │ ├── Poincare Tutorial.ipynb │ ├── Similarity_Queries.ipynb │ ├── Tensorboard.png │ ├── Tensorboard_visualizations.ipynb │ ├── Topic_dendrogram.ipynb │ ├── Topics_and_Transformations.ipynb │ ├── Training_visualizations.ipynb │ ├── Varembed.ipynb │ ├── WMD_tutorial.ipynb │ ├── Word2Vec_FastText_Comparison.ipynb │ ├── WordRank_wrapper_quickstart.ipynb │ ├── Wordrank_comparisons.ipynb │ ├── annoytutorial.ipynb │ ├── atmodel_prediction_tutorial.ipynb │ ├── atmodel_tutorial.ipynb │ ├── datasets │ │ ├── keras_classifier_training_data.csv │ │ ├── mycorpus.txt │ │ ├── news_corpus │ │ ├── news_corpus.index │ │ ├── news_corpus.vocab │ │ ├── news_dictionary │ │ ├── questions-words.txt │ │ └── word_vectors_training_data.txt │ ├── deepir.ipynb │ ├── distance_metrics.ipynb │ ├── distributed.md │ ├── doc2vec-IMDB.ipynb │ ├── doc2vec-lee.ipynb │ ├── doc2vec-wikipedia.ipynb │ ├── doc_lda_pca.png │ ├── doc_lda_tsne.png │ ├── downloader_api_tutorial.ipynb │ ├── dtm_example.ipynb │ ├── ensemble_lda_with_opinosis.ipynb │ ├── gensim Quick Start.ipynb │ ├── gensim_news_classification.ipynb │ ├── index │ ├── index.d │ ├── lda_model_difference.ipynb │ ├── lda_training_tips.ipynb │ ├── ldaseqmodel.ipynb │ ├── nmf_tutorial.ipynb │ ├── nmslib.png │ ├── nmslibtutorial.ipynb │ ├── online_w2v_tutorial.ipynb │ ├── pca.png │ ├── pivoted_document_length_normalisation.ipynb │ ├── poincare │ │ ├── data │ │ │ └── wordnet_mammal_hypernyms.tsv │ │ ├── entailment_eval.png │ │ ├── entailment_paper.png │ │ ├── example_tree.png │ │ ├── link_prediction_eval.png │ │ ├── link_prediction_paper.png │ │ ├── poincare_burn_in_eps.patch │ │ ├── poincare_numpy.patch │ │ ├── reconstruction_eval.png │ │ └── reconstruction_paper.png │ ├── sklearn_api.ipynb │ ├── soft_cosine_benchmark.ipynb │ ├── soft_cosine_tutorial.ipynb │ ├── soft_cosine_tutorial.png │ ├── summarization_tutorial.ipynb │ ├── test_notebooks.py │ ├── topic_coherence-movies.ipynb │ ├── topic_coherence_model_selection.ipynb │ ├── topic_coherence_tutorial.ipynb │ ├── topic_methods.ipynb │ ├── topic_network.ipynb │ ├── topic_with_coordinate.png │ ├── translation_matrix.ipynb │ ├── tsne.png │ ├── visdom_graph.png │ ├── wikinews-bigram-en.ipynb │ ├── word2vec.ipynb │ └── word2vec_file_scaling.png └── src │ ├── Makefile │ ├── _index.rst.unused │ ├── _license.rst.unused │ ├── _static │ ├── css │ │ ├── docs.css │ │ ├── erp2.css │ │ ├── fonts │ │ │ ├── mfn-icons.css │ │ │ ├── mfn-icons.eot │ │ │ ├── mfn-icons.svg │ │ │ ├── mfn-icons.ttf │ │ │ └── mfn-icons.woff │ │ ├── global.css │ │ └── structure.css │ ├── favicon.ico │ ├── images │ │ ├── Gensim-OG-Image.jpg │ │ ├── bg_panel.png │ │ ├── box_shadow_button.png │ │ ├── eaccidents-logo.png │ │ ├── erp2-footer-pic1.png │ │ ├── erp2-sectionbg3.png │ │ ├── erp2-slider-bg.png │ │ ├── erp2-slider-pic1.png │ │ ├── erp2-slider-pic2.png │ │ ├── erp2-subheader.jpg │ │ ├── gensim.png │ │ ├── gensim_logo_positive_complete_tb.png │ │ ├── icons │ │ │ ├── github.png │ │ │ ├── groups.png │ │ │ ├── list_check.png │ │ │ ├── loader.svg │ │ │ └── twitter.png │ │ ├── misha_radim.jpeg │ │ ├── references │ │ │ ├── logo_dtu.gif │ │ │ ├── logo_dynadmic.png │ │ │ ├── logo_eudml.png │ │ │ ├── logo_ghent.png │ │ │ ├── logo_ibcn.png │ │ │ ├── logo_issuu.jpeg │ │ │ ├── logo_roistr.png │ │ │ ├── logo_sportsauthority.png │ │ │ └── logo_tailwind.png │ │ ├── route4me-logo.png │ │ ├── techtarget-logo.png │ │ ├── transparent.png │ │ └── wilabs-logo.png │ ├── js │ │ ├── animations.js │ │ ├── jquery-2.1.4.min.js │ │ ├── jquery.jplayer.min.js │ │ ├── jquery.plugins.js │ │ ├── mfn.menu.js │ │ ├── scripts.js │ │ └── translate3d.js │ └── plugins │ │ └── rs-plugin-6 │ │ ├── css │ │ └── rs6.css │ │ └── js │ │ ├── revolution.tools.min.js │ │ └── rs6.min.js │ ├── _templates │ └── indexcontent.html │ ├── apiref.rst │ ├── auto_examples │ ├── .gitignore │ ├── core │ │ ├── images │ │ │ ├── sphx_glr_run_core_concepts_001.png │ │ │ ├── sphx_glr_run_corpora_and_vector_spaces_001.png │ │ │ ├── sphx_glr_run_similarity_queries_001.png │ │ │ ├── sphx_glr_run_topics_and_transformations_001.png │ │ │ └── thumb │ │ │ │ ├── sphx_glr_run_core_concepts_thumb.png │ │ │ │ ├── sphx_glr_run_corpora_and_vector_spaces_thumb.png │ │ │ │ ├── sphx_glr_run_similarity_queries_thumb.png │ │ │ │ └── sphx_glr_run_topics_and_transformations_thumb.png │ │ ├── index.rst │ │ ├── run_core_concepts.ipynb │ │ ├── run_core_concepts.py │ │ ├── run_core_concepts.py.md5 │ │ ├── run_core_concepts.rst │ │ ├── run_corpora_and_vector_spaces.ipynb │ │ ├── run_corpora_and_vector_spaces.py │ │ ├── run_corpora_and_vector_spaces.py.md5 │ │ ├── run_corpora_and_vector_spaces.rst │ │ ├── run_similarity_queries.ipynb │ │ ├── run_similarity_queries.py │ │ ├── run_similarity_queries.py.md5 │ │ ├── run_similarity_queries.rst │ │ ├── run_topics_and_transformations.ipynb │ │ ├── run_topics_and_transformations.py │ │ ├── run_topics_and_transformations.py.md5 │ │ ├── run_topics_and_transformations.rst │ │ └── sg_execution_times.rst │ ├── howtos │ │ ├── images │ │ │ ├── sphx_glr_run_compare_lda_001.png │ │ │ ├── sphx_glr_run_compare_lda_002.png │ │ │ ├── sphx_glr_run_compare_lda_003.png │ │ │ ├── sphx_glr_run_compare_lda_004.png │ │ │ ├── sphx_glr_run_news_classification_001.png │ │ │ ├── sphx_glr_run_news_classification_002.png │ │ │ └── thumb │ │ │ │ ├── sphx_glr_run_binder_thumb.png │ │ │ │ ├── sphx_glr_run_compare_lda_thumb.png │ │ │ │ ├── sphx_glr_run_doc2vec_imdb_thumb.png │ │ │ │ ├── sphx_glr_run_doc_thumb.png │ │ │ │ ├── sphx_glr_run_downloader_api_thumb.png │ │ │ │ ├── sphx_glr_run_news_classification_thumb.png │ │ │ │ └── sphx_glr_rxx_040_compare_lda_thumb.png │ │ ├── index.rst │ │ ├── run_compare_lda.ipynb │ │ ├── run_compare_lda.py │ │ ├── run_compare_lda.py.md5 │ │ ├── run_compare_lda.rst │ │ ├── run_doc.ipynb │ │ ├── run_doc.py │ │ ├── run_doc.py.md5 │ │ ├── run_doc.rst │ │ ├── run_doc2vec_imdb.ipynb │ │ ├── run_doc2vec_imdb.py │ │ ├── run_doc2vec_imdb.py.md5 │ │ ├── run_doc2vec_imdb.rst │ │ ├── run_downloader_api.ipynb │ │ ├── run_downloader_api.py │ │ ├── run_downloader_api.py.md5 │ │ ├── run_downloader_api.rst │ │ └── sg_execution_times.rst │ ├── index.rst │ ├── other │ │ └── index.rst │ └── tutorials │ │ ├── images │ │ ├── sphx_glr_run_annoy_001.png │ │ ├── sphx_glr_run_distance_metrics_001.png │ │ ├── sphx_glr_run_fasttext_001.png │ │ ├── sphx_glr_run_pivoted_doc_norm_001.png │ │ ├── sphx_glr_run_scm_001.png │ │ ├── sphx_glr_run_summarization_001.png │ │ ├── sphx_glr_run_wmd_001.png │ │ ├── sphx_glr_run_word2vec_001.png │ │ └── thumb │ │ │ ├── sphx_glr_run_annoy_thumb.png │ │ │ ├── sphx_glr_run_distance_metrics_thumb.png │ │ │ ├── sphx_glr_run_doc2vec_lee_thumb.png │ │ │ ├── sphx_glr_run_ensemblelda_thumb.png │ │ │ ├── sphx_glr_run_fasttext_thumb.png │ │ │ ├── sphx_glr_run_lda_thumb.png │ │ │ ├── sphx_glr_run_pivoted_doc_norm_thumb.png │ │ │ ├── sphx_glr_run_scm_thumb.png │ │ │ ├── sphx_glr_run_summarization_thumb.png │ │ │ ├── sphx_glr_run_wmd_thumb.png │ │ │ └── sphx_glr_run_word2vec_thumb.png │ │ ├── index.rst │ │ ├── run_annoy.ipynb │ │ ├── run_annoy.py │ │ ├── run_annoy.py.md5 │ │ ├── run_annoy.rst │ │ ├── run_doc2vec_lee.ipynb │ │ ├── run_doc2vec_lee.py │ │ ├── run_doc2vec_lee.py.md5 │ │ ├── run_doc2vec_lee.rst │ │ ├── run_ensemblelda.ipynb │ │ ├── run_ensemblelda.py │ │ ├── run_ensemblelda.py.md5 │ │ ├── run_ensemblelda.rst │ │ ├── run_fasttext.ipynb │ │ ├── run_fasttext.py │ │ ├── run_fasttext.py.md5 │ │ ├── run_fasttext.rst │ │ ├── run_fasttext_codeobj.pickle │ │ ├── run_lda.ipynb │ │ ├── run_lda.py │ │ ├── run_lda.py.md5 │ │ ├── run_lda.rst │ │ ├── run_scm.ipynb │ │ ├── run_scm.py │ │ ├── run_scm.py.md5 │ │ ├── run_scm.rst │ │ ├── run_wmd.ipynb │ │ ├── run_wmd.py │ │ ├── run_wmd.py.md5 │ │ ├── run_wmd.rst │ │ ├── run_wmd_codeobj.pickle │ │ ├── run_word2vec.ipynb │ │ ├── run_word2vec.py │ │ ├── run_word2vec.py.md5 │ │ ├── run_word2vec.rst │ │ └── sg_execution_times.rst │ ├── check_gallery.py │ ├── conf.py │ ├── corpora │ ├── bleicorpus.rst │ ├── corpora.rst │ ├── csvcorpus.rst │ ├── dictionary.rst │ ├── hashdictionary.rst │ ├── indexedcorpus.rst │ ├── lowcorpus.rst │ ├── malletcorpus.rst │ ├── mmcorpus.rst │ ├── opinosiscorpus.rst │ ├── sharded_corpus.rst │ ├── svmlightcorpus.rst │ ├── textcorpus.rst │ ├── ucicorpus.rst │ └── wikicorpus.rst │ ├── dist_lda.rst │ ├── dist_lsi.rst │ ├── distributed.rst │ ├── downloader.rst │ ├── gallery │ ├── README.rst │ ├── README.txt │ ├── core │ │ ├── README.txt │ │ ├── run_core_concepts.png │ │ ├── run_core_concepts.py │ │ ├── run_corpora_and_vector_spaces.png │ │ ├── run_corpora_and_vector_spaces.py │ │ ├── run_similarity_queries.png │ │ ├── run_similarity_queries.py │ │ ├── run_topics_and_transformations.png │ │ └── run_topics_and_transformations.py │ ├── howtos │ │ ├── README.txt │ │ ├── run_compare_lda.py │ │ ├── run_doc.py │ │ ├── run_doc2vec_imdb.py │ │ └── run_downloader_api.py │ ├── other │ │ └── README.txt │ └── tutorials │ │ ├── README.txt │ │ ├── datasets │ │ └── questions-words.txt │ │ ├── fasttext-logo-color-web.png │ │ ├── nips12raw_str602.tgz │ │ ├── run_annoy.py │ │ ├── run_doc2vec_lee.py │ │ ├── run_ensemblelda.py │ │ ├── run_fasttext.py │ │ ├── run_lda.py │ │ ├── run_scm.py │ │ ├── run_wmd.py │ │ ├── run_word2vec.py │ │ ├── scm-hello.png │ │ ├── summarization_tutorial_plot.png │ │ └── wmd-obama.png │ ├── indextoc.rst │ ├── interfaces.rst │ ├── intro.rst │ ├── matutils.rst │ ├── models │ ├── _fasttext_bin.rst │ ├── atmodel.rst │ ├── basemodel.rst │ ├── callbacks.rst │ ├── coherencemodel.rst │ ├── doc2vec.rst │ ├── doc2vec_inner.rst │ ├── ensemblelda.rst │ ├── fasttext.rst │ ├── fasttext_inner.rst │ ├── hdpmodel.rst │ ├── keyedvectors.rst │ ├── lda_dispatcher.rst │ ├── lda_worker.rst │ ├── ldamodel.rst │ ├── ldamulticore.rst │ ├── ldaseqmodel.rst │ ├── logentropy_model.rst │ ├── lsi_dispatcher.rst │ ├── lsi_worker.rst │ ├── lsimodel.rst │ ├── models.rst │ ├── nmf.rst │ ├── normmodel.rst │ ├── phrases.rst │ ├── poincare.rst │ ├── rpmodel.rst │ ├── tfidfmodel.rst │ ├── translation_matrix.rst │ ├── word2vec.rst │ └── word2vec_inner.rst │ ├── parsing │ ├── porter.rst │ └── preprocessing.rst │ ├── people.rst │ ├── readme_images │ ├── 12k.png │ ├── amazon.png │ ├── capitalone.png │ ├── channel4.png │ ├── cisco.png │ ├── codeq.png │ ├── issuu.png │ ├── juju.png │ ├── mass-cognition.png │ ├── mindseye.png │ ├── nih.png │ ├── nlpub.png │ ├── rare.png │ ├── search-metrics.png │ ├── siteground.png │ ├── sports-authority.png │ ├── stillwater.png │ ├── tailwind.png │ └── talent-pair.png │ ├── scripts │ ├── glove2word2vec.rst │ ├── make_wiki_online.rst │ ├── make_wiki_online_nodebug.rst │ ├── make_wikicorpus.rst │ ├── package_info.rst │ ├── segment_wiki.rst │ ├── word2vec2tensor.rst │ └── word2vec_standalone.rst │ ├── similarities │ ├── annoy.rst │ ├── docsim.rst │ ├── fastss.rst │ ├── levenshtein.rst │ ├── nmslib.rst │ └── termsim.rst │ ├── sphinx_rtd_theme │ ├── __init__.py │ ├── advertisement.html │ ├── breadcrumbs.html │ ├── footer.html │ ├── layout.html │ ├── layouthome.html │ ├── locale │ │ ├── de │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── en │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── es │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── et │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── fr │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── nl │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── pt_BR │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── ru │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── sphinx.pot │ │ ├── sv │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ ├── tr │ │ │ └── LC_MESSAGES │ │ │ │ ├── sphinx.mo │ │ │ │ └── sphinx.po │ │ └── zh_CN │ │ │ └── LC_MESSAGES │ │ │ ├── sphinx.mo │ │ │ └── sphinx.po │ ├── notification.html │ ├── search.html │ ├── searchbox.html │ ├── sideslide.html │ ├── static │ │ ├── css │ │ │ ├── badge_only.css │ │ │ ├── fonts │ │ │ │ ├── Roboto-Slab-Bold.woff │ │ │ │ ├── Roboto-Slab-Bold.woff2 │ │ │ │ ├── Roboto-Slab-Regular.woff │ │ │ │ ├── Roboto-Slab-Regular.woff2 │ │ │ │ ├── fontawesome-webfont.eot │ │ │ │ ├── fontawesome-webfont.svg │ │ │ │ ├── fontawesome-webfont.ttf │ │ │ │ ├── fontawesome-webfont.woff │ │ │ │ ├── fontawesome-webfont.woff2 │ │ │ │ ├── lato-bold-italic.woff │ │ │ │ ├── lato-bold-italic.woff2 │ │ │ │ ├── lato-bold.woff │ │ │ │ ├── lato-bold.woff2 │ │ │ │ ├── lato-normal-italic.woff │ │ │ │ ├── lato-normal-italic.woff2 │ │ │ │ ├── lato-normal.woff │ │ │ │ └── lato-normal.woff2 │ │ │ └── theme.css │ │ └── js │ │ │ ├── badge_only.js │ │ │ └── theme.js │ ├── theme.conf │ ├── topbar.html │ └── versions.html │ ├── support.rst │ ├── test │ └── utils.rst │ ├── tools │ ├── check_gallery.py │ ├── four.png │ ├── one.png │ ├── three.png │ ├── to_python.py │ ├── two.png │ └── wordcloud.ipynb │ ├── topic_coherence │ ├── aggregation.rst │ ├── direct_confirmation_measure.rst │ ├── indirect_confirmation_measure.rst │ ├── probability_estimation.rst │ ├── segmentation.rst │ └── text_analysis.rst │ ├── utils.rst │ └── wiki.rst ├── gensim Quick Start.ipynb ├── gensim ├── __init__.py ├── _matutils.pyx ├── corpora │ ├── __init__.py │ ├── _mmreader.pyx │ ├── bleicorpus.py │ ├── csvcorpus.py │ ├── dictionary.py │ ├── hashdictionary.py │ ├── indexedcorpus.py │ ├── lowcorpus.py │ ├── malletcorpus.py │ ├── mmcorpus.py │ ├── opinosiscorpus.py │ ├── sharded_corpus.py │ ├── svmlightcorpus.py │ ├── textcorpus.py │ ├── ucicorpus.py │ └── wikicorpus.py ├── downloader.py ├── examples │ └── dmlcz │ │ ├── __init__.py │ │ ├── dmlcorpus.py │ │ ├── gensim_build.py │ │ ├── gensim_genmodel.py │ │ ├── gensim_xml.py │ │ ├── runall.sh │ │ └── sources.py ├── interfaces.py ├── matutils.py ├── models │ ├── __init__.py │ ├── _fasttext_bin.py │ ├── atmodel.py │ ├── basemodel.py │ ├── bm25model.py │ ├── callbacks.py │ ├── coherencemodel.py │ ├── doc2vec.py │ ├── doc2vec_corpusfile.pyx │ ├── doc2vec_inner.pxd │ ├── doc2vec_inner.pyx │ ├── ensemblelda.py │ ├── fast_line_sentence.h │ ├── fasttext.py │ ├── fasttext_corpusfile.pyx │ ├── fasttext_inner.pxd │ ├── fasttext_inner.pyx │ ├── hdpmodel.py │ ├── keyedvectors.py │ ├── lda_dispatcher.py │ ├── lda_worker.py │ ├── ldamodel.py │ ├── ldamulticore.py │ ├── ldaseqmodel.py │ ├── logentropy_model.py │ ├── lsi_dispatcher.py │ ├── lsi_worker.py │ ├── lsimodel.py │ ├── nmf.py │ ├── nmf_pgd.pyx │ ├── normmodel.py │ ├── phrases.py │ ├── poincare.py │ ├── rpmodel.py │ ├── stdint_wrapper.h │ ├── tfidfmodel.py │ ├── translation_matrix.py │ ├── voidptr.h │ ├── word2vec.py │ ├── word2vec_corpusfile.pxd │ ├── word2vec_corpusfile.pyx │ ├── word2vec_inner.pxd │ └── word2vec_inner.pyx ├── nosy.py ├── parsing │ ├── __init__.py │ ├── porter.py │ └── preprocessing.py ├── scripts │ ├── __init__.py │ ├── benchmark.py │ ├── glove2word2vec.py │ ├── make_wiki.py │ ├── make_wiki_online.py │ ├── make_wiki_online_nodebug.py │ ├── make_wikicorpus.py │ ├── package_info.py │ ├── segment_wiki.py │ ├── word2vec2tensor.py │ └── word2vec_standalone.py ├── similarities │ ├── __init__.py │ ├── annoy.py │ ├── docsim.py │ ├── fastss.pyx │ ├── levenshtein.py │ ├── nmslib.py │ └── termsim.py ├── test │ ├── __init__.py │ ├── basetmtests.py │ ├── simspeed.py │ ├── simspeed2.py │ ├── svd_error.py │ ├── test_aggregation.py │ ├── test_api.py │ ├── test_atmodel.py │ ├── test_big.py │ ├── test_bm25model.py │ ├── test_coherencemodel.py │ ├── test_corpora.py │ ├── test_corpora_dictionary.py │ ├── test_corpora_hashdictionary.py │ ├── test_data │ │ ├── DTM │ │ │ ├── ldaseq_3_0_1_model │ │ │ └── sstats_test.txt │ │ ├── EN.1-10.cbow1_wind5_hs0_neg10_size300_smpl1e-05.txt │ │ ├── IT.1-10.cbow1_wind5_hs0_neg10_size300_smpl1e-05.txt │ │ ├── OPUS_en_it_europarl_train_one2ten.txt │ │ ├── PathLineSentences │ │ │ ├── 1.txt │ │ │ └── 2.txt.bz2 │ │ ├── alldata-id-10.txt │ │ ├── atmodel_3_0_1_model │ │ ├── atmodel_3_0_1_model.expElogbeta.npy │ │ ├── atmodel_3_0_1_model.id2word │ │ ├── atmodel_3_0_1_model.state │ │ ├── bgwiki-latest-pages-articles-shortened.xml.bz2 │ │ ├── compatible-hash-true.model │ │ ├── cp852_fasttext.bin │ │ ├── crime-and-punishment.bin │ │ ├── crime-and-punishment.txt │ │ ├── crime-and-punishment.vec │ │ ├── d2v-lee-v0.13.0 │ │ ├── doc2vec_old │ │ ├── doc2vec_old_sep │ │ ├── doc2vec_old_sep.syn0_lockf.npy │ │ ├── doc2vec_old_sep.syn1neg.npy │ │ ├── dtm_test.dict │ │ ├── dtm_test.mm │ │ ├── ensemblelda │ │ ├── enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2 │ │ ├── enwiki-table-markup.xml.bz2 │ │ ├── euclidean_vectors.bin │ │ ├── fasttext_old │ │ ├── fasttext_old_sep │ │ ├── fasttext_old_sep.syn0_lockf.npy │ │ ├── fasttext_old_sep.syn1neg.npy │ │ ├── fb-ngrams.txt │ │ ├── ft_kv_3.6.0.model.gz │ │ ├── ft_model_2.3.0 │ │ ├── head500.noblanks.cor │ │ ├── head500.noblanks.cor.bz2 │ │ ├── head500.noblanks.cor_tfidf.model │ │ ├── head500.noblanks.cor_wordids.txt │ │ ├── high_precision.kv.bin │ │ ├── high_precision.kv.txt │ │ ├── large_tag_doc_10_iter50 │ │ ├── lda_3_0_1_model │ │ ├── lda_3_0_1_model.expElogbeta.npy │ │ ├── lda_3_0_1_model.id2word │ │ ├── lda_3_0_1_model.state │ │ ├── ldamodel_python_2_7 │ │ ├── ldamodel_python_2_7.expElogbeta.npy │ │ ├── ldamodel_python_2_7.id2word │ │ ├── ldamodel_python_2_7.state │ │ ├── ldamodel_python_3_5 │ │ ├── ldamodel_python_3_5.expElogbeta.npy │ │ ├── ldamodel_python_3_5.id2word │ │ ├── ldamodel_python_3_5.state │ │ ├── ldavowpalwabbit.dict.txt │ │ ├── ldavowpalwabbit.txt │ │ ├── lee.cor │ │ ├── lee_background.cor │ │ ├── lee_fasttext │ │ ├── lee_fasttext.bin │ │ ├── lee_fasttext.vec │ │ ├── lee_fasttext_new.bin │ │ ├── miIslita.cor │ │ ├── mini_newsgroup │ │ ├── model-from-gensim-3.8.0.w2v │ │ ├── nmf_model │ │ ├── non_ascii_fasttext.bin │ │ ├── old_d2v_models │ │ │ ├── d2v_0.12.0.mdl │ │ │ ├── d2v_0.12.1.mdl │ │ │ ├── d2v_0.12.2.mdl │ │ │ ├── d2v_0.12.3.mdl │ │ │ ├── d2v_0.12.4.mdl │ │ │ ├── d2v_0.13.0.mdl │ │ │ ├── d2v_0.13.1.mdl │ │ │ ├── d2v_0.13.2.mdl │ │ │ ├── d2v_0.13.3.mdl │ │ │ ├── d2v_0.13.4.mdl │ │ │ ├── d2v_1.0.0.mdl │ │ │ ├── d2v_1.0.1.mdl │ │ │ ├── d2v_2.0.0.mdl │ │ │ ├── d2v_2.1.0.mdl │ │ │ ├── d2v_2.2.0.mdl │ │ │ ├── d2v_2.3.0.mdl │ │ │ ├── d2v_3.0.0.mdl │ │ │ ├── d2v_3.1.0.mdl │ │ │ ├── d2v_3.2.0.mdl │ │ │ ├── d2v_3.3.0.mdl │ │ │ └── d2v_3.4.0.mdl │ │ ├── old_keyedvectors_320.dat │ │ ├── old_w2v_models │ │ │ ├── w2v_0.12.0.mdl │ │ │ ├── w2v_0.12.1.mdl │ │ │ ├── w2v_0.12.2.mdl │ │ │ ├── w2v_0.12.3.mdl │ │ │ ├── w2v_0.12.4.mdl │ │ │ ├── w2v_0.13.0.mdl │ │ │ ├── w2v_0.13.1.mdl │ │ │ ├── w2v_0.13.2.mdl │ │ │ ├── w2v_0.13.3.mdl │ │ │ ├── w2v_0.13.4.mdl │ │ │ ├── w2v_1.0.0.mdl │ │ │ ├── w2v_1.0.1.mdl │ │ │ ├── w2v_2.0.0.mdl │ │ │ ├── w2v_2.1.0.mdl │ │ │ ├── w2v_2.2.0.mdl │ │ │ ├── w2v_2.3.0.mdl │ │ │ ├── w2v_3.0.0.mdl │ │ │ ├── w2v_3.1.0.mdl │ │ │ ├── w2v_3.2.0.mdl │ │ │ ├── w2v_3.3.0.mdl │ │ │ └── w2v_3.4.0.mdl │ │ ├── pang_lee_polarity.cor │ │ ├── pang_lee_polarity_fasttext.bin │ │ ├── pang_lee_polarity_fasttext.vec │ │ ├── para2para_text1.txt │ │ ├── para2para_text2.txt │ │ ├── phraser-3.6.0.model │ │ ├── phraser-no-common-terms.pkl │ │ ├── phraser-no-scoring.pkl │ │ ├── phraser-scoring-str.pkl │ │ ├── phrases-3.6.0.model │ │ ├── phrases-no-common-terms.pkl │ │ ├── phrases-no-scoring.pkl │ │ ├── phrases-scoring-str.pkl │ │ ├── poincare_cp852.tsv │ │ ├── poincare_hypernyms.tsv │ │ ├── poincare_hypernyms_large.tsv │ │ ├── poincare_test_3.4.0 │ │ ├── poincare_utf8.tsv │ │ ├── poincare_vectors.bin │ │ ├── pre_0_13_2_model │ │ ├── pre_0_13_2_model.state │ │ ├── pretrained.vec │ │ ├── questions-words.txt │ │ ├── reproduce.dat │ │ ├── reproduce.dat.gz │ │ ├── similarities0-1.txt │ │ ├── simlex999.txt │ │ ├── small_tag_doc_5_iter50 │ │ ├── test_corpus_ok.mm │ │ ├── test_corpus_small.mm │ │ ├── test_glove.txt │ │ ├── test_mmcorpus_corrupt.mm │ │ ├── test_mmcorpus_no_index.mm │ │ ├── test_mmcorpus_no_index.mm.bz2 │ │ ├── test_mmcorpus_no_index.mm.gz │ │ ├── test_mmcorpus_overflow.mm │ │ ├── test_mmcorpus_with_index.mm │ │ ├── test_mmcorpus_with_index.mm.index │ │ ├── testcorpus.blei │ │ ├── testcorpus.blei.index │ │ ├── testcorpus.blei.vocab │ │ ├── testcorpus.low │ │ ├── testcorpus.low.index │ │ ├── testcorpus.mallet │ │ ├── testcorpus.mallet.index │ │ ├── testcorpus.mm │ │ ├── testcorpus.mm.index │ │ ├── testcorpus.svmlight │ │ ├── testcorpus.svmlight.index │ │ ├── testcorpus.txt │ │ ├── testcorpus.uci │ │ ├── testcorpus.uci.index │ │ ├── testcorpus.uci.vocab │ │ ├── testcorpus.xml.bz2 │ │ ├── tfidf_model.tst │ │ ├── tfidf_model.tst.bz2 │ │ ├── tfidf_model_3_2.tst │ │ ├── toy-data.txt │ │ ├── toy-model-pretrained.bin │ │ ├── toy-model.bin │ │ ├── toy-model.vec │ │ ├── varembed_lee_subcorpus.cor │ │ ├── varembed_morfessor.bin │ │ ├── varembed_vectors.pkl │ │ ├── w2v-lee-v0.12.0 │ │ ├── w2v_keyedvectors_load_test.modeldata │ │ ├── w2v_keyedvectors_load_test.vocab │ │ ├── word2vec_3.3 │ │ ├── word2vec_old │ │ ├── word2vec_old_sep │ │ ├── word2vec_old_sep.syn0_lockf.npy │ │ ├── word2vec_old_sep.syn1neg.npy │ │ ├── word2vec_pre_kv_c │ │ ├── word2vec_pre_kv_py2 │ │ ├── word2vec_pre_kv_py3 │ │ ├── word2vec_pre_kv_py3_4 │ │ ├── word2vec_pre_kv_sep_py2 │ │ ├── word2vec_pre_kv_sep_py2.neg_labels.npy │ │ ├── word2vec_pre_kv_sep_py2.syn0.npy │ │ ├── word2vec_pre_kv_sep_py2.syn0_lockf.npy │ │ ├── word2vec_pre_kv_sep_py2.syn1neg.npy │ │ ├── word2vec_pre_kv_sep_py3 │ │ ├── word2vec_pre_kv_sep_py3.neg_labels.npy │ │ ├── word2vec_pre_kv_sep_py3.syn0.npy │ │ ├── word2vec_pre_kv_sep_py3.syn0_lockf.npy │ │ ├── word2vec_pre_kv_sep_py3.syn1neg.npy │ │ ├── word2vec_pre_kv_sep_py3_4 │ │ ├── word2vec_pre_kv_sep_py3_4.neg_labels.npy │ │ ├── word2vec_pre_kv_sep_py3_4.syn0.npy │ │ ├── word2vec_pre_kv_sep_py3_4.syn0_lockf.npy │ │ ├── word2vec_pre_kv_sep_py3_4.syn1neg.npy │ │ └── wordsim353.tsv │ ├── test_datatype.py │ ├── test_direct_confirmation.py │ ├── test_doc2vec.py │ ├── test_ensemblelda.py │ ├── test_fasttext.py │ ├── test_glove2word2vec.py │ ├── test_hdpmodel.py │ ├── test_indirect_confirmation.py │ ├── test_keyedvectors.py │ ├── test_lda_callback.py │ ├── test_ldamodel.py │ ├── test_ldaseqmodel.py │ ├── test_lee.py │ ├── test_logentropy_model.py │ ├── test_lsimodel.py │ ├── test_matutils.py │ ├── test_miislita.py │ ├── test_nmf.py │ ├── test_normmodel.py │ ├── test_parsing.py │ ├── test_phrases.py │ ├── test_poincare.py │ ├── test_probability_estimation.py │ ├── test_rpmodel.py │ ├── test_scripts.py │ ├── test_segmentation.py │ ├── test_sharded_corpus.py │ ├── test_similarities.py │ ├── test_similarity_metrics.py │ ├── test_text_analysis.py │ ├── test_tfidfmodel.py │ ├── test_tmdiff.py │ ├── test_translation_matrix.py │ ├── test_utils.py │ ├── test_word2vec.py │ └── utils.py ├── topic_coherence │ ├── __init__.py │ ├── aggregation.py │ ├── direct_confirmation_measure.py │ ├── indirect_confirmation_measure.py │ ├── probability_estimation.py │ ├── segmentation.py │ └── text_analysis.py └── utils.py ├── pip.sh ├── pyproject.toml ├── release ├── README.md ├── annotate_pr.py ├── bump_version.py ├── check_wheels.py ├── generate_changelog.py ├── hijack_pr.py ├── merge.sh ├── prepare.sh ├── push.sh ├── update_changelog.py └── upload_docs.sh ├── requirements_docs.txt ├── setup.cfg └── setup.py /.github/FUNDING.yml: -------------------------------------------------------------------------------- 1 | # These are supported funding model platforms 2 | 3 | github: [piskvorky] # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2] 4 | patreon: # Replace with a single Patreon username 5 | open_collective: # Replace with a single Open Collective username 6 | ko_fi: # Replace with a single Ko-fi username 7 | tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel 8 | community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry 9 | liberapay: # Replace with a single Liberapay username 10 | issuehunt: # Replace with a single IssueHunt username 11 | otechie: # Replace with a single Otechie username 12 | custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2'] 13 | 14 | -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- 1 | version: 2 2 | updates: 3 | - package-ecosystem: "github-actions" 4 | directory: "/" 5 | schedule: 6 | interval: "monthly" 7 | -------------------------------------------------------------------------------- /.github/workflows/installwheel.py: -------------------------------------------------------------------------------- 1 | """Install a wheel for the current platform.""" 2 | import os 3 | import platform 4 | import subprocess 5 | import sys 6 | 7 | 8 | def main(): 9 | subdir = sys.argv[1] 10 | vi = sys.version_info 11 | 12 | if platform.system() in ('Linux', 'Darwin'): 13 | arch = 'x86_64' 14 | else: 15 | arch = 'amd64' 16 | 17 | want = f'-cp{vi.major}{vi.minor}-' 18 | suffix = f'_{arch}.whl' 19 | 20 | files = sorted(os.listdir(subdir)) 21 | for f in files: 22 | if want in f and f.endswith(suffix): 23 | command = [sys.executable, '-m', 'pip', 'install', os.path.join(subdir, f)] 24 | subprocess.check_call(command) 25 | return 0 26 | 27 | print(f'no matches for {want} / {suffix} in {subdir}:') 28 | print('\n'.join(files)) 29 | 30 | return 1 31 | 32 | 33 | 34 | if __name__ == '__main__': 35 | sys.exit(main()) 36 | -------------------------------------------------------------------------------- /.github/workflows/linters.yml: -------------------------------------------------------------------------------- 1 | name: Linters 2 | 3 | on: 4 | workflow_call: 5 | 6 | jobs: 7 | 8 | linters: 9 | runs-on: ubuntu-latest 10 | steps: 11 | 12 | - uses: actions/checkout@v4 13 | 14 | - name: Setup up Python ${{ matrix.python }} 15 | uses: actions/setup-python@v5 16 | with: 17 | python-version: 3.11 18 | 19 | - name: Update pip 20 | run: python -m pip install -U pip 21 | 22 | - name: Install dependencies 23 | run: python -m pip install flake8 flake8-rst 24 | 25 | - name: Run flake8 linter (source) 26 | run: flake8 --ignore E12,W503 --max-line-length 120 --show-source gensim 27 | 28 | # - name: Run flake8 linter (documentation) 29 | # run: flake8 --ignore E202,E402,E302,E305,F821 --max-line-length 120 --filename '*.py,*.rst' docs 30 | 31 | - name: Check Sphinx Gallery cache 32 | run: python docs/src/check_gallery.py 33 | -------------------------------------------------------------------------------- /.github/workflows/update_index.py: -------------------------------------------------------------------------------- 1 | """Update index.html for the bucket listing 2 | 3 | http://gensim-wheels.s3-website-us-east-1.amazonaws.com/ 4 | 5 | We do this ourselves as opposed to using wheelhouse_uploader because it's 6 | much faster this way (seconds as compared to nearly an hour). 7 | """ 8 | 9 | import sys 10 | import boto3 11 | 12 | 13 | def main(): 14 | bucket = sys.argv[1] 15 | prefix = sys.argv[2] 16 | 17 | client = boto3.client('s3') 18 | 19 | print("") 32 | 33 | 34 | if __name__ == '__main__': 35 | main() 36 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Compiled source # 2 | ################### 3 | *.com 4 | *.class 5 | *.dll 6 | *.exe 7 | *.o 8 | *.so 9 | *.pyc 10 | *.pyo 11 | *.pyd 12 | 13 | # Packages # 14 | ############ 15 | # it's better to unpack these files and commit the raw source 16 | # git has its own built in compression methods 17 | *.7z 18 | *.dmg 19 | *.gz 20 | *.iso 21 | *.jar 22 | *.rar 23 | *.tar 24 | *.zip 25 | 26 | # Logs and databases # 27 | ###################### 28 | *.log 29 | *.sql 30 | *.sqlite 31 | *.pkl 32 | *.bak 33 | *.npy 34 | *.npz 35 | 36 | # OS generated files # 37 | ###################### 38 | .DS_Store? 39 | ehthumbs.db 40 | Icon? 41 | Thumbs.db 42 | 43 | # Other # 44 | ######### 45 | .cache/ 46 | .project 47 | .pydevproject 48 | .ropeproject 49 | .settings/ 50 | .eggs 51 | cython_debug 52 | docs/src/_build/ 53 | docs/_static 54 | docs/notebooks/.ipynb_checkpoints 55 | dedan_gensim.tmproj 56 | gensim*.egg-info 57 | *,cover 58 | .idea 59 | *.dict 60 | *.index 61 | .coverage 62 | .*.sw[op] 63 | data 64 | *.bak 65 | /build/ 66 | /dist/ 67 | *.prof 68 | *.lprof 69 | *.bin 70 | *.old 71 | *.model 72 | *~ 73 | *_out.txt 74 | *.html 75 | *.inv 76 | *.js 77 | docs/_images/ 78 | docs/_downloads/ 79 | 80 | # 81 | # Generated by Cython 82 | # 83 | gensim/_matutils.c 84 | gensim/corpora/_mmreader.c 85 | gensim/models/doc2vec_corpusfile.cpp 86 | gensim/models/doc2vec_inner.cpp 87 | gensim/models/fasttext_corpusfile.cpp 88 | gensim/models/fasttext_inner.c 89 | gensim/models/nmf_pgd.c 90 | gensim/models/word2vec_corpusfile.cpp 91 | gensim/models/word2vec_inner.c 92 | gensim/similarities/fastss.c 93 | 94 | .ipynb_checkpoints 95 | -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- 1 | cff-version: 1.2.0 2 | message: "If you use this software, please cite it as below." 3 | authors: 4 | - family-names: "Řehůřek" 5 | given-names: "Radim" 6 | title: "Gensim: Topic modelling for humans" 7 | version: 4.1.0 8 | url: "https://github.com/RaRe-Technologies/gensim" 9 | preferred-citation: 10 | type: conference-paper 11 | authors: 12 | - family-names: "Řehůřek" 13 | given-names: "Radim" 14 | - family-names: "Sojka" 15 | given-names: "Petr" 16 | publisher: 17 | name: "University of Malta" 18 | date-published: "2010-05-22" 19 | year: 2010 20 | month: 5 21 | start: 45 # First page number 22 | end: 50 # Last page number 23 | pages: 5 24 | title: "Software Framework for Topic Modelling with Large Corpora" 25 | languages: ["eng"] 26 | url: "http://is.muni.cz/publication/884893/en" 27 | conference: 28 | name: "Proceedings of LREC 2010 workshop New Challenges for NLP Frameworks" 29 | city: Valetta 30 | country: MT 31 | location: "University of Malta, Valletta, Malta" 32 | -------------------------------------------------------------------------------- /ISSUE_TEMPLATE.md: -------------------------------------------------------------------------------- 1 | 9 | 10 | #### Problem description 11 | 12 | What are you trying to achieve? What is the expected result? What are you seeing instead? 13 | 14 | #### Steps/code/corpus to reproduce 15 | 16 | Include full tracebacks, logs and datasets if necessary. Please keep the examples minimal ("minimal reproducible example"). 17 | 18 | If your problem is with a specific Gensim model (word2vec, lsimodel, doc2vec, fasttext, ldamodel etc), include the following: 19 | 20 | ```python 21 | print(my_model.lifecycle_events) 22 | ``` 23 | 24 | #### Versions 25 | 26 | Please provide the output of: 27 | 28 | ```python 29 | import platform; print(platform.platform()) 30 | import sys; print("Python", sys.version) 31 | import struct; print("Bits", 8 * struct.calcsize("P")) 32 | import numpy; print("NumPy", numpy.__version__) 33 | import scipy; print("SciPy", scipy.__version__) 34 | import gensim; print("gensim", gensim.__version__) 35 | from gensim.models import word2vec;print("FAST_VERSION", word2vec.FAST_VERSION) 36 | ``` 37 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | recursive-include gensim/test/test_data * 2 | include README.md 3 | include CHANGELOG.md 4 | include COPYING 5 | 6 | include gensim/models/voidptr.h 7 | include gensim/models/stdint_wrapper.h 8 | include gensim/models/fast_line_sentence.h 9 | 10 | include gensim/models/word2vec_inner.c 11 | include gensim/models/word2vec_inner.pyx 12 | include gensim/models/word2vec_inner.pxd 13 | include gensim/models/word2vec_corpusfile.cpp 14 | include gensim/models/word2vec_corpusfile.pyx 15 | include gensim/models/word2vec_corpusfile.pxd 16 | 17 | include gensim/models/doc2vec_inner.cpp 18 | include gensim/models/doc2vec_inner.pyx 19 | include gensim/models/doc2vec_inner.pxd 20 | include gensim/models/doc2vec_corpusfile.cpp 21 | include gensim/models/doc2vec_corpusfile.pyx 22 | 23 | include gensim/models/fasttext_inner.c 24 | include gensim/models/fasttext_inner.pyx 25 | include gensim/models/fasttext_inner.pxd 26 | include gensim/models/fasttext_corpusfile.cpp 27 | include gensim/models/fasttext_corpusfile.pyx 28 | 29 | include gensim/corpora/_mmreader.c 30 | include gensim/corpora/_mmreader.pyx 31 | include gensim/_matutils.c 32 | include gensim/_matutils.pyx 33 | 34 | include gensim/models/nmf_pgd.c 35 | include gensim/models/nmf_pgd.pyx 36 | 37 | -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- 1 | # Security Policy 2 | 3 | ## Supported Versions 4 | 5 | Use this section to tell people about which versions of your project are 6 | currently being supported with security updates. 7 | 8 | | Version | Supported | 9 | | ------- | ------------------ | 10 | | 4. x | :white_check_mark: | 11 | | < 4.0 | :x: | 12 | 13 | ## Reporting a Vulnerability 14 | 15 | Open a ticket and add the "security" label to it. 16 | Describe the vulnerability in general. 17 | We'll reach out to you for specifics. 18 | -------------------------------------------------------------------------------- /config.sh: -------------------------------------------------------------------------------- 1 | # Define custom utilities 2 | 3 | function pre_build { 4 | # Any stuff that you need to do before you start building the wheels 5 | # Runs in the root directory of this repository. 6 | : 7 | } 8 | 9 | function pip_opts { 10 | [ -n "$MANYLINUX_URL" ] && echo "--find-links $MANYLINUX_URL" 11 | echo "-v" 12 | } 13 | 14 | function build_wheel_cmd { 15 | set -x 16 | local cmd=${1:-pip_wheel_cmd} 17 | local wheelhouse=$(abspath ${WHEEL_SDIR:-wheelhouse}) 18 | start_spinner 19 | if [ -n "$(is_function "pre_build")" ]; then pre_build; fi 20 | stop_spinner 21 | if [ -n "$BUILD_DEPENDS" ]; then 22 | pip install $(pip_opts) $BUILD_DEPENDS 23 | fi 24 | pip --version 25 | pip freeze 26 | $cmd $wheelhouse 27 | repair_wheelhouse $wheelhouse 28 | set +x 29 | } 30 | 31 | function run_tests { 32 | # Runs tests on installed distribution from an empty directory 33 | set -x 34 | pip freeze 35 | pytest -rfxEXs --durations=20 --disable-warnings --showlocals --pyargs gensim 36 | set +x 37 | } 38 | 39 | # 40 | # We do this here because we want to upgrade pip before the wheel gets installed. 41 | # docker_test_wrap.sh sources this file before the wheel install. The sourcing 42 | # happens from multiple places, and some of the Python versions can be really 43 | # ancient (e.g. when working outside a virtual environment, using the default 44 | # Python install). 45 | # 46 | # We don't use pip to do the actual upgrade because something appears broken 47 | # with the default pip on the Python 3.10 multibuild image. This is really 48 | # dodgy, but I couldn't work out a better way to get this done. 49 | # 50 | python continuous_integration/upgrade_pip_py310.py 51 | -------------------------------------------------------------------------------- /continuous_integration/BucketLifecycleConfiguration.json: -------------------------------------------------------------------------------- 1 | { 2 | "Rules": [ 3 | { 4 | "Expiration": {"Days": 30}, 5 | "Filter": {"Prefix": ""}, 6 | "ID": "Delete all files older than 30 days to save storage costs", 7 | "Status": "Enabled" 8 | } 9 | ] 10 | } 11 | -------------------------------------------------------------------------------- /continuous_integration/BucketLifecycleConfiguration.txt: -------------------------------------------------------------------------------- 1 | JSON files can't have comments, so this file is here to explain the rules in BucketLifecycleConfiguration.json. 2 | 3 | Our CI puts wheels in a publicly readable, privately writable S3 bucket (s3://gensim-wheels). 4 | These wheels can be for gensim releases, in which case we fetch them and push them to PyPI when making a release. 5 | Once the wheels are on PyPI, we don't need to keep our own copy. 6 | 7 | These wheels can also be development wheels: we currently build wheels on every push to develop. 8 | These can be helpful when tracking down a problem, but they can also build up quickly, consume storage space and contribute to AWS costs. 9 | 10 | So, we delete all files in the gensim-wheels bucket every 90 days. 11 | We rarely need to access wheels that are several months old, anyway. 12 | 13 | If you modify the JSON configuration, then you can update it using the command: 14 | 15 | aws --profile smart_open s3api put-bucket-lifecycle-configuration --bucket gensim-wheels --lifecycle-configuration file://continuous_integration/BucketLifecycleConfiguration.json 16 | -------------------------------------------------------------------------------- /continuous_integration/check_wheels.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | # 4 | # Copyright (C) 2019 RaRe Technologies s.r.o. 5 | # Licensed under the GNU LGPL v2.1 - https://www.gnu.org/licenses/old-licenses/lgpl-2.1.en.html 6 | """Print available wheels for a particular Python package.""" 7 | import re 8 | import sys 9 | 10 | import requests 11 | 12 | def to_int(value): 13 | value = ''.join((x for x in value if x.isdigit())) 14 | try: 15 | return int(value) 16 | except Exception: 17 | return 0 18 | 19 | 20 | def to_tuple(version): 21 | return tuple(to_int(x) for x in version.split('.')) 22 | 23 | 24 | def main(): 25 | project = sys.argv[1] 26 | json = requests.get('https://pypi.org/pypi/%s/json' % project).json() 27 | for version in sorted(json['releases'], key=to_tuple): 28 | print(version) 29 | wheel_packages = [ 30 | p for p in json['releases'][version] 31 | if p['packagetype'] == 'bdist_wheel' 32 | ] 33 | for p in wheel_packages: 34 | print(' %(python_version)s %(filename)s' % p) 35 | 36 | 37 | if __name__ == '__main__': 38 | main() 39 | -------------------------------------------------------------------------------- /continuous_integration/debug.gdb: -------------------------------------------------------------------------------- 1 | # commands to run on CI machine in event of testing core-dump 2 | 3 | set trace-commands on 4 | 5 | thread apply all bt 6 | 7 | f 8 | info args 9 | info locals 10 | 11 | up 12 | 13 | f 14 | info args 15 | info locals 16 | 17 | up 18 | 19 | f 20 | info args 21 | info locals 22 | -------------------------------------------------------------------------------- /continuous_integration/install_wheel.py: -------------------------------------------------------------------------------- 1 | """Install the built wheel for testing under AppVeyor. 2 | 3 | Assumes that gensim/dist contains a single wheel to install. 4 | """ 5 | import os 6 | import subprocess 7 | 8 | curr_dir = os.path.dirname(__file__) 9 | dist_path = os.path.join(curr_dir, '..', 'dist') 10 | wheels = [ 11 | os.path.join(dist_path, f) 12 | for f in os.listdir(dist_path) if f.endswith('.whl') 13 | ] 14 | assert len(wheels) == 1, "wheels = %r" % wheels 15 | 16 | command = 'pip install --pre --force-reinstall'.split() + [wheels[0]] 17 | subprocess.check_call(command) 18 | -------------------------------------------------------------------------------- /continuous_integration/upgrade_pip_py310.py: -------------------------------------------------------------------------------- 1 | # This script needs to be able run under both Python 2 and 3 without crashing 2 | # It only achieves the desired effect under Py3.10 on Linux and MacOS. 3 | import subprocess 4 | import sys 5 | import tempfile 6 | if sys.platform in ('linux', 'darwin') and sys.version_info[:2] == (3, 10): 7 | import urllib.request 8 | with tempfile.NamedTemporaryFile(suffix='.py') as fout: 9 | urllib.request.urlretrieve("https://bootstrap.pypa.io/get-pip.py", fout.name) 10 | subprocess.call([sys.executable, fout.name]) 11 | -------------------------------------------------------------------------------- /docs/notebooks/Coherence.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Coherence.gif -------------------------------------------------------------------------------- /docs/notebooks/Convergence.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Convergence.gif -------------------------------------------------------------------------------- /docs/notebooks/Corpora_and_Vector_Spaces.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/Diff.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Diff.gif -------------------------------------------------------------------------------- /docs/notebooks/Dynamic Topic Model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Dynamic Topic Model.png -------------------------------------------------------------------------------- /docs/notebooks/Monkey Brains New.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Monkey Brains New.png -------------------------------------------------------------------------------- /docs/notebooks/Monkey Brains.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Monkey Brains.png -------------------------------------------------------------------------------- /docs/notebooks/Perplexity.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Perplexity.gif -------------------------------------------------------------------------------- /docs/notebooks/Similarity_Queries.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/Tensorboard.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/Tensorboard.png -------------------------------------------------------------------------------- /docs/notebooks/Topics_and_Transformations.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/annoytutorial.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/datasets/keras_classifier_training_data.csv: -------------------------------------------------------------------------------- 1 | subject,content 2 | mathematics,linear algebra 3 | mathematics,topology 4 | mathematics,algebra 5 | mathematics,calculus 6 | mathematics,variational calculus 7 | mathematics,functional field 8 | mathematics,real analysis 9 | mathematics,complex analysis 10 | mathematics,differential equation 11 | mathematics,statistics 12 | mathematics,statistical optimization 13 | mathematics,probability 14 | mathematics,stochastic calculus 15 | mathematics,numerical analysis 16 | mathematics,differential geometry 17 | physics,renormalization 18 | physics,classical mechanics 19 | physics,quantum mechanics 20 | physics,statistical mechanics 21 | physics,functional field 22 | physics,path integral 23 | physics,quantum field theory 24 | physics,electrodynamics 25 | physics,condensed matter 26 | physics,particle physics 27 | physics,topological solitons 28 | physics,astrophysics 29 | physics,spontaneous symmetry breaking 30 | physics,atomic molecular and optical physics 31 | physics,quantum chaos 32 | theology,divine providence 33 | theology,soteriology 34 | theology,anthropology 35 | theology,pneumatology 36 | theology,Christology 37 | theology,Holy Trinity 38 | theology,eschatology 39 | theology,scripture 40 | theology,ecclesiology 41 | theology,predestination 42 | theology,divine degree 43 | theology,creedal confessionalism 44 | theology,scholasticism 45 | theology,prayer 46 | theology,eucharist -------------------------------------------------------------------------------- /docs/notebooks/datasets/mycorpus.txt: -------------------------------------------------------------------------------- 1 | Human machine interface for lab abc computer applications 2 | A survey of user opinion of computer system response time 3 | The EPS user interface management system 4 | System and human system engineering testing of EPS 5 | Relation of user perceived response time to error measurement 6 | The generation of random binary unordered trees 7 | The intersection graph of paths in trees 8 | Graph minors IV Widths of trees and well quasi ordering 9 | Graph minors A survey 10 | -------------------------------------------------------------------------------- /docs/notebooks/datasets/news_corpus.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/datasets/news_corpus.index -------------------------------------------------------------------------------- /docs/notebooks/datasets/news_dictionary: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/datasets/news_dictionary -------------------------------------------------------------------------------- /docs/notebooks/distance_metrics.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/doc2vec-IMDB.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/doc2vec-lee.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/doc_lda_pca.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/doc_lda_pca.png -------------------------------------------------------------------------------- /docs/notebooks/doc_lda_tsne.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/doc_lda_tsne.png -------------------------------------------------------------------------------- /docs/notebooks/gensim Quick Start.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/gensim_news_classification.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/index -------------------------------------------------------------------------------- /docs/notebooks/index.d: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/index.d -------------------------------------------------------------------------------- /docs/notebooks/lda_training_tips.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/nmslib.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/nmslib.png -------------------------------------------------------------------------------- /docs/notebooks/pca.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/pca.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/entailment_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/entailment_eval.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/entailment_paper.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/entailment_paper.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/example_tree.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/example_tree.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/link_prediction_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/link_prediction_eval.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/link_prediction_paper.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/link_prediction_paper.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/reconstruction_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/reconstruction_eval.png -------------------------------------------------------------------------------- /docs/notebooks/poincare/reconstruction_paper.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/poincare/reconstruction_paper.png -------------------------------------------------------------------------------- /docs/notebooks/soft_cosine_tutorial.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/soft_cosine_tutorial.png -------------------------------------------------------------------------------- /docs/notebooks/summarization_tutorial.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/test_notebooks.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import tempfile 4 | from glob import glob 5 | 6 | import nbformat 7 | from nbconvert.preprocessors import ExecutePreprocessor 8 | from nbconvert.preprocessors.execute import CellExecutionError 9 | "from smart_open import smart_open\n", 10 | 11 | 12 | def _notebook_run(path): 13 | """Execute a notebook via nbconvert and collect output. 14 | :returns (parsed nb object, execution errors) 15 | """ 16 | kernel_name = 'python%d' % sys.version_info[0] 17 | this_file_directory = os.path.dirname(__file__) 18 | errors = [] 19 | with tempfile.NamedTemporaryFile(suffix=".ipynb", mode='wt') as fout: 20 | with smart_open(path, 'rb') as f: 21 | nb = nbformat.read(f, as_version=4) 22 | nb.metadata.get('kernelspec', {})['name'] = kernel_name 23 | ep = ExecutePreprocessor(kernel_name=kernel_name, timeout=10) 24 | 25 | try: 26 | ep.preprocess(nb, {'metadata': {'path': this_file_directory}}) 27 | except CellExecutionError as e: 28 | if "SKIP" in e.traceback: 29 | print(str(e.traceback).split("\n")[-2]) 30 | else: 31 | raise e 32 | except RuntimeError as e: 33 | print(e) 34 | 35 | finally: 36 | nbformat.write(nb, fout) 37 | 38 | return nb, errors 39 | 40 | 41 | def test_notebooks(): 42 | for notebook in glob("*.ipynb"): 43 | if " " in notebook: 44 | continue 45 | print("Testing {}".format(notebook)) 46 | nb, errors = _notebook_run(notebook) 47 | assert errors == [] 48 | -------------------------------------------------------------------------------- /docs/notebooks/topic_with_coordinate.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/topic_with_coordinate.png -------------------------------------------------------------------------------- /docs/notebooks/tsne.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/tsne.png -------------------------------------------------------------------------------- /docs/notebooks/visdom_graph.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/visdom_graph.png -------------------------------------------------------------------------------- /docs/notebooks/word2vec.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /docs/notebooks/word2vec_file_scaling.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/notebooks/word2vec_file_scaling.png -------------------------------------------------------------------------------- /docs/src/_license.rst.unused: -------------------------------------------------------------------------------- 1 | :orphan: 2 | 3 | .. _license: 4 | 5 | Licensing 6 | --------- 7 | 8 | Gensim is licensed under the OSI-approved `GNU LGPLv2.1 license `_. 9 | 10 | This means that it's free for both personal and commercial use, but if you make any 11 | modification to Gensim that you distribute to other people, you have to disclose 12 | the source code of these modifications. 13 | 14 | Apart from that, you are free to redistribute Gensim in any way you like, though you're 15 | not allowed to modify its license (doh!). 16 | 17 | My intent here is to **get more help and community involvement** with the development of Gensim. 18 | The legalese is therefore less important to me than your input and contributions. 19 | 20 | `Contact me `_ if LGPL doesn't fit your bill but you'd like the LGPL restrictions liften. 21 | 22 | .. seealso:: 23 | 24 | We built a high performance server for NLP, document analysis, indexing, search and clustering: https://scaletext.ai. 25 | ScaleText is a commercial product, available both on-prem or as SaaS. 26 | Reach out at info@scaletext.com if you need an industry-grade tool with professional support. 27 | -------------------------------------------------------------------------------- /docs/src/_static/css/fonts/mfn-icons.eot: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/css/fonts/mfn-icons.eot -------------------------------------------------------------------------------- /docs/src/_static/css/fonts/mfn-icons.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/css/fonts/mfn-icons.ttf -------------------------------------------------------------------------------- /docs/src/_static/css/fonts/mfn-icons.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/css/fonts/mfn-icons.woff -------------------------------------------------------------------------------- /docs/src/_static/favicon.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/favicon.ico -------------------------------------------------------------------------------- /docs/src/_static/images/Gensim-OG-Image.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/Gensim-OG-Image.jpg -------------------------------------------------------------------------------- /docs/src/_static/images/bg_panel.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/bg_panel.png -------------------------------------------------------------------------------- /docs/src/_static/images/box_shadow_button.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/box_shadow_button.png -------------------------------------------------------------------------------- /docs/src/_static/images/eaccidents-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/eaccidents-logo.png -------------------------------------------------------------------------------- /docs/src/_static/images/erp2-footer-pic1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/erp2-footer-pic1.png -------------------------------------------------------------------------------- /docs/src/_static/images/erp2-sectionbg3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/erp2-sectionbg3.png -------------------------------------------------------------------------------- /docs/src/_static/images/erp2-slider-bg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/erp2-slider-bg.png -------------------------------------------------------------------------------- /docs/src/_static/images/erp2-slider-pic1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/erp2-slider-pic1.png -------------------------------------------------------------------------------- /docs/src/_static/images/erp2-slider-pic2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/erp2-slider-pic2.png -------------------------------------------------------------------------------- /docs/src/_static/images/erp2-subheader.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/erp2-subheader.jpg -------------------------------------------------------------------------------- /docs/src/_static/images/gensim.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/gensim.png -------------------------------------------------------------------------------- /docs/src/_static/images/gensim_logo_positive_complete_tb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/gensim_logo_positive_complete_tb.png -------------------------------------------------------------------------------- /docs/src/_static/images/icons/github.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/icons/github.png -------------------------------------------------------------------------------- /docs/src/_static/images/icons/groups.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/icons/groups.png -------------------------------------------------------------------------------- /docs/src/_static/images/icons/list_check.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/icons/list_check.png -------------------------------------------------------------------------------- /docs/src/_static/images/icons/loader.svg: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 6 | 7 | 8 | 9 | -------------------------------------------------------------------------------- /docs/src/_static/images/icons/twitter.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/icons/twitter.png -------------------------------------------------------------------------------- /docs/src/_static/images/misha_radim.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/misha_radim.jpeg -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_dtu.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_dtu.gif -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_dynadmic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_dynadmic.png -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_eudml.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_eudml.png -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_ghent.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_ghent.png -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_ibcn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_ibcn.png -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_issuu.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_issuu.jpeg -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_roistr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_roistr.png -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_sportsauthority.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_sportsauthority.png -------------------------------------------------------------------------------- /docs/src/_static/images/references/logo_tailwind.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/references/logo_tailwind.png -------------------------------------------------------------------------------- /docs/src/_static/images/route4me-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/route4me-logo.png -------------------------------------------------------------------------------- /docs/src/_static/images/techtarget-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/techtarget-logo.png -------------------------------------------------------------------------------- /docs/src/_static/images/transparent.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/transparent.png -------------------------------------------------------------------------------- /docs/src/_static/images/wilabs-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/_static/images/wilabs-logo.png -------------------------------------------------------------------------------- /docs/src/auto_examples/.gitignore: -------------------------------------------------------------------------------- 1 | *.zip 2 | -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/sphx_glr_run_core_concepts_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/sphx_glr_run_core_concepts_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/sphx_glr_run_corpora_and_vector_spaces_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/sphx_glr_run_corpora_and_vector_spaces_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/sphx_glr_run_similarity_queries_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/sphx_glr_run_similarity_queries_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/sphx_glr_run_topics_and_transformations_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/sphx_glr_run_topics_and_transformations_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/thumb/sphx_glr_run_core_concepts_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/thumb/sphx_glr_run_core_concepts_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/thumb/sphx_glr_run_corpora_and_vector_spaces_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/thumb/sphx_glr_run_corpora_and_vector_spaces_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/thumb/sphx_glr_run_similarity_queries_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/thumb/sphx_glr_run_similarity_queries_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/images/thumb/sphx_glr_run_topics_and_transformations_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/core/images/thumb/sphx_glr_run_topics_and_transformations_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/core/run_core_concepts.py.md5: -------------------------------------------------------------------------------- 1 | e562837df1242b45d0ab623f5a5254f0 -------------------------------------------------------------------------------- /docs/src/auto_examples/core/run_corpora_and_vector_spaces.py.md5: -------------------------------------------------------------------------------- 1 | 9bf95a9406b723f4397c3912a2fd7865 -------------------------------------------------------------------------------- /docs/src/auto_examples/core/run_similarity_queries.py.md5: -------------------------------------------------------------------------------- 1 | 94f0e6b35e3a81a5ccc6d24a26101a2d -------------------------------------------------------------------------------- /docs/src/auto_examples/core/run_topics_and_transformations.py.md5: -------------------------------------------------------------------------------- 1 | af09faa792495c0a9b03b53125b735a6 -------------------------------------------------------------------------------- /docs/src/auto_examples/core/sg_execution_times.rst: -------------------------------------------------------------------------------- 1 | 2 | :orphan: 3 | 4 | .. _sphx_glr_auto_examples_core_sg_execution_times: 5 | 6 | Computation times 7 | ================= 8 | **00:01.658** total execution time for **auto_examples_core** files: 9 | 10 | +--------------------------------------------------------------------------------------------------------------+-----------+---------+ 11 | | :ref:`sphx_glr_auto_examples_core_run_topics_and_transformations.py` (``run_topics_and_transformations.py``) | 00:01.658 | 58.1 MB | 12 | +--------------------------------------------------------------------------------------------------------------+-----------+---------+ 13 | | :ref:`sphx_glr_auto_examples_core_run_core_concepts.py` (``run_core_concepts.py``) | 00:00.000 | 0.0 MB | 14 | +--------------------------------------------------------------------------------------------------------------+-----------+---------+ 15 | | :ref:`sphx_glr_auto_examples_core_run_corpora_and_vector_spaces.py` (``run_corpora_and_vector_spaces.py``) | 00:00.000 | 0.0 MB | 16 | +--------------------------------------------------------------------------------------------------------------+-----------+---------+ 17 | | :ref:`sphx_glr_auto_examples_core_run_similarity_queries.py` (``run_similarity_queries.py``) | 00:00.000 | 0.0 MB | 18 | +--------------------------------------------------------------------------------------------------------------+-----------+---------+ 19 | -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_002.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_002.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_003.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_003.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_004.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/sphx_glr_run_compare_lda_004.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/sphx_glr_run_news_classification_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/sphx_glr_run_news_classification_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/sphx_glr_run_news_classification_002.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/sphx_glr_run_news_classification_002.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_binder_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_binder_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_compare_lda_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_compare_lda_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_doc2vec_imdb_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_doc2vec_imdb_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_doc_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_doc_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_downloader_api_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_downloader_api_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_news_classification_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_run_news_classification_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/images/thumb/sphx_glr_rxx_040_compare_lda_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/howtos/images/thumb/sphx_glr_rxx_040_compare_lda_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/run_compare_lda.py.md5: -------------------------------------------------------------------------------- 1 | 1370542e21d2047c5f9ca51f2ca878d6 -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/run_doc.py.md5: -------------------------------------------------------------------------------- 1 | 96cefb1417d54ac8010e38cc739d5ff1 -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/run_doc2vec_imdb.py.md5: -------------------------------------------------------------------------------- 1 | ba0868fcd69185ffc435fc591667b67a -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/run_downloader_api.py.md5: -------------------------------------------------------------------------------- 1 | ef5ef32c1d6de82f5624515af4948b69 -------------------------------------------------------------------------------- /docs/src/auto_examples/howtos/sg_execution_times.rst: -------------------------------------------------------------------------------- 1 | 2 | :orphan: 3 | 4 | .. _sphx_glr_auto_examples_howtos_sg_execution_times: 5 | 6 | Computation times 7 | ================= 8 | **56:58.813** total execution time for **auto_examples_howtos** files: 9 | 10 | +----------------------------------------------------------------------------------------+-----------+-----------+ 11 | | :ref:`sphx_glr_auto_examples_howtos_run_doc2vec_imdb.py` (``run_doc2vec_imdb.py``) | 56:58.813 | 3772.5 MB | 12 | +----------------------------------------------------------------------------------------+-----------+-----------+ 13 | | :ref:`sphx_glr_auto_examples_howtos_run_compare_lda.py` (``run_compare_lda.py``) | 00:00.000 | 0.0 MB | 14 | +----------------------------------------------------------------------------------------+-----------+-----------+ 15 | | :ref:`sphx_glr_auto_examples_howtos_run_doc.py` (``run_doc.py``) | 00:00.000 | 0.0 MB | 16 | +----------------------------------------------------------------------------------------+-----------+-----------+ 17 | | :ref:`sphx_glr_auto_examples_howtos_run_downloader_api.py` (``run_downloader_api.py``) | 00:00.000 | 0.0 MB | 18 | +----------------------------------------------------------------------------------------+-----------+-----------+ 19 | -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_annoy_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_annoy_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_distance_metrics_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_distance_metrics_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_fasttext_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_fasttext_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_pivoted_doc_norm_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_pivoted_doc_norm_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_scm_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_scm_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_summarization_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_summarization_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_wmd_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_wmd_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/sphx_glr_run_word2vec_001.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/sphx_glr_run_word2vec_001.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_annoy_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_annoy_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_distance_metrics_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_distance_metrics_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_doc2vec_lee_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_doc2vec_lee_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_ensemblelda_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_ensemblelda_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_fasttext_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_fasttext_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_lda_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_lda_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_pivoted_doc_norm_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_pivoted_doc_norm_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_scm_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_scm_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_summarization_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_summarization_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_wmd_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_wmd_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_word2vec_thumb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/images/thumb/sphx_glr_run_word2vec_thumb.png -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_annoy.py.md5: -------------------------------------------------------------------------------- 1 | 1949c38a738ed05d2e3784f8e94a30a0 -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_doc2vec_lee.py.md5: -------------------------------------------------------------------------------- 1 | 581caa67e8496a210a030c2886fb8bbc -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_ensemblelda.py.md5: -------------------------------------------------------------------------------- 1 | 9f666b02b1eeac820f2a2200e6d14f6e -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_fasttext.py.md5: -------------------------------------------------------------------------------- 1 | 5f5ac745a06ff512074def4c0eb15f79 -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_fasttext_codeobj.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/run_fasttext_codeobj.pickle -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_lda.py.md5: -------------------------------------------------------------------------------- 1 | 802d286d0c620260af50bf5ef0e08253 -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_scm.py.md5: -------------------------------------------------------------------------------- 1 | 0bbd28e31784997fb257771856183106 -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_wmd.py.md5: -------------------------------------------------------------------------------- 1 | eefa5904436cd2661aa2236b1d5bb22d -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_wmd_codeobj.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/auto_examples/tutorials/run_wmd_codeobj.pickle -------------------------------------------------------------------------------- /docs/src/auto_examples/tutorials/run_word2vec.py.md5: -------------------------------------------------------------------------------- 1 | 37d9258acf496e76463d2e34d40c8c67 -------------------------------------------------------------------------------- /docs/src/corpora/bleicorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.bleicorpus` -- Corpus in Blei's LDA-C format 2 | ========================================================== 3 | 4 | .. automodule:: gensim.corpora.bleicorpus 5 | :synopsis: Corpus in Blei's LDA-C format 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/corpora.rst: -------------------------------------------------------------------------------- 1 | :orphan: 2 | 3 | :mod:`corpora` -- Package for corpora I/O 4 | ========================================== 5 | 6 | .. automodule:: gensim.corpora 7 | :synopsis: Package for corpora I/O 8 | :members: 9 | :inherited-members: 10 | 11 | -------------------------------------------------------------------------------- /docs/src/corpora/csvcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.csvcorpus` -- Corpus in CSV format 2 | ========================================================== 3 | 4 | .. automodule:: gensim.corpora.csvcorpus 5 | :synopsis: Corpus in CSV format 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/dictionary.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.dictionary` -- Construct word<->id mappings 2 | ========================================================== 3 | 4 | .. automodule:: gensim.corpora.dictionary 5 | :synopsis: Construct word<->id mappings 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/hashdictionary.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.hashdictionary` -- Construct word<->id mappings 2 | ============================================================= 3 | 4 | .. automodule:: gensim.corpora.hashdictionary 5 | :synopsis: Construct word<->id mappings on the fly (the "hashing trick") 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/indexedcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.indexedcorpus` -- Random access to corpus documents 2 | ================================================================= 3 | 4 | .. automodule:: gensim.corpora.indexedcorpus 5 | :synopsis: Random access to corpus documents 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | 11 | -------------------------------------------------------------------------------- /docs/src/corpora/lowcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.lowcorpus` -- Corpus in GibbsLda++ format 2 | ======================================================= 3 | 4 | .. automodule:: gensim.corpora.lowcorpus 5 | :synopsis: Corpus in GibbsLda++ format 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/malletcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.malletcorpus` -- Corpus in Mallet format 2 | ====================================================== 3 | 4 | .. automodule:: gensim.corpora.malletcorpus 5 | :synopsis: Corpus in Mallet format. 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/mmcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.mmcorpus` -- Corpus in Matrix Market format 2 | ========================================================== 3 | 4 | .. automodule:: gensim.corpora.mmcorpus 5 | :synopsis: Corpus in Matrix Market format 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/opinosiscorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.opinosiscorpus` -- Topic related review sentences 2 | =============================================================== 3 | 4 | .. automodule:: gensim.corpora.opinosiscorpus 5 | :synopsis: Topic related review sentences 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/sharded_corpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.sharded_corpus` -- Corpus stored in separate files 2 | ================================================================ 3 | 4 | .. automodule:: gensim.corpora.sharded_corpus 5 | :synopsis: Numpy arrays on disk for iterative processing 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/svmlightcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.svmlightcorpus` -- Corpus in SVMlight format 2 | ================================================================== 3 | 4 | .. automodule:: gensim.corpora.svmlightcorpus 5 | :synopsis: Corpus in SVMlight format 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/textcorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.textcorpus` -- Tools for building corpora with dictionaries 2 | ========================================================================= 3 | 4 | .. automodule:: gensim.corpora.textcorpus 5 | :synopsis: Tools for building corpora with dictionaries 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/ucicorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.ucicorpus` -- Corpus in UCI format 2 | ================================================ 3 | 4 | .. automodule:: gensim.corpora.ucicorpus 5 | :synopsis: Corpus in UCI format 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/corpora/wikicorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`corpora.wikicorpus` -- Corpus from a Wikipedia dump 2 | ========================================================== 3 | 4 | .. automodule:: gensim.corpora.wikicorpus 5 | :synopsis: Corpus from a Wikipedia dump 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/downloader.rst: -------------------------------------------------------------------------------- 1 | :mod:`downloader` -- Downloader API for gensim 2 | ============================================== 3 | 4 | .. automodule:: gensim.downloader 5 | :synopsis: Downloader API for gensim 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/gallery/README.txt: -------------------------------------------------------------------------------- 1 | Documentation 2 | ============= 3 | 4 | .. _gallery_top: 5 | 6 | We welcome contributions to our documentation via GitHub pull requests, whether it's fixing a typo or authoring an entirely new tutorial or guide. 7 | If you're thinking about contributing documentation, please see :ref:`sphx_glr_auto_examples_howtos_run_doc.py`. 8 | -------------------------------------------------------------------------------- /docs/src/gallery/core/README.txt: -------------------------------------------------------------------------------- 1 | Core Tutorials: New Users Start Here! 2 | ------------------------------------- 3 | 4 | If you're new to gensim, we recommend going through all core tutorials in order. 5 | Understanding this functionality is vital for using gensim effectively. 6 | -------------------------------------------------------------------------------- /docs/src/gallery/core/run_core_concepts.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/core/run_core_concepts.png -------------------------------------------------------------------------------- /docs/src/gallery/core/run_corpora_and_vector_spaces.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/core/run_corpora_and_vector_spaces.png -------------------------------------------------------------------------------- /docs/src/gallery/core/run_similarity_queries.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/core/run_similarity_queries.png -------------------------------------------------------------------------------- /docs/src/gallery/core/run_topics_and_transformations.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/core/run_topics_and_transformations.png -------------------------------------------------------------------------------- /docs/src/gallery/howtos/README.txt: -------------------------------------------------------------------------------- 1 | How-to Guides: Solve a Problem 2 | ------------------------------ 3 | 4 | These **goal-oriented guides** demonstrate how to **solve a specific problem** using gensim. 5 | -------------------------------------------------------------------------------- /docs/src/gallery/tutorials/README.txt: -------------------------------------------------------------------------------- 1 | Tutorials: Learning Oriented Lessons 2 | ------------------------------------ 3 | 4 | Learning-oriented lessons that introduce a particular gensim feature, e.g. a model (Word2Vec, FastText) or technique (similarity queries or text summarization). 5 | -------------------------------------------------------------------------------- /docs/src/gallery/tutorials/fasttext-logo-color-web.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/tutorials/fasttext-logo-color-web.png -------------------------------------------------------------------------------- /docs/src/gallery/tutorials/nips12raw_str602.tgz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/tutorials/nips12raw_str602.tgz -------------------------------------------------------------------------------- /docs/src/gallery/tutorials/scm-hello.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/tutorials/scm-hello.png -------------------------------------------------------------------------------- /docs/src/gallery/tutorials/summarization_tutorial_plot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/tutorials/summarization_tutorial_plot.png -------------------------------------------------------------------------------- /docs/src/gallery/tutorials/wmd-obama.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/gallery/tutorials/wmd-obama.png -------------------------------------------------------------------------------- /docs/src/indextoc.rst: -------------------------------------------------------------------------------- 1 | .. toctree:: 2 | :hidden: 3 | :maxdepth: 1 4 | 5 | intro 6 | auto_examples/index 7 | apiref 8 | support 9 | people 10 | -------------------------------------------------------------------------------- /docs/src/interfaces.rst: -------------------------------------------------------------------------------- 1 | :mod:`interfaces` -- Core gensim interfaces 2 | ============================================ 3 | 4 | .. automodule:: gensim.interfaces 5 | :synopsis: Core gensim interfaces 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/matutils.rst: -------------------------------------------------------------------------------- 1 | :mod:`matutils` -- Math utils 2 | ============================== 3 | 4 | .. automodule:: gensim.matutils 5 | :synopsis: Math utils 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/_fasttext_bin.rst: -------------------------------------------------------------------------------- 1 | :mod:`models._fasttext_bin` -- Facebook's fastText I/O 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models._fasttext_bin 5 | :synopsis: I/O routines for Facebook's fastText format 6 | :members: 7 | :inherited-members: 8 | :special-members: __getitem__ 9 | :undoc-members: 10 | :show-inheritance: 11 | -------------------------------------------------------------------------------- /docs/src/models/atmodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.atmodel` -- Author-topic models 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.atmodel 5 | :synopsis: Author-topic model 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/basemodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.basemodel` -- Core TM interface 2 | ============================================ 3 | 4 | .. automodule:: gensim.models.basemodel 5 | :synopsis: Core TM interface 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/callbacks.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.callbacks` -- Callbacks for track and viz LDA train process 2 | ======================================================================== 3 | 4 | .. automodule:: gensim.models.callbacks 5 | :synopsis: Callbacks for track and viz LDA train process 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/coherencemodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.coherencemodel` -- Topic coherence pipeline 2 | ======================================================== 3 | 4 | .. automodule:: gensim.models.coherencemodel 5 | :synopsis: Topic coherence pipeline 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/doc2vec.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.doc2vec` -- Doc2vec paragraph embeddings 2 | ===================================================== 3 | 4 | .. automodule:: gensim.models.doc2vec 5 | :synopsis: Doc2vec paragraph embeddings 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :special-members: __getitem__ 11 | -------------------------------------------------------------------------------- /docs/src/models/doc2vec_inner.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.doc2vec_inner` -- Cython routines for training Doc2Vec models 2 | ========================================================================== 3 | 4 | .. automodule:: gensim.models.doc2vec_inner 5 | :synopsis: Optimized Cython routines for training Doc2Vec models 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/ensemblelda.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.ensembelda` -- Ensemble Latent Dirichlet Allocation 2 | ================================================================ 3 | 4 | .. automodule:: gensim.models.ensemblelda 5 | :synopsis: Ensemble Latent Dirichlet Allocation 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/fasttext.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.fasttext` -- FastText model 2 | ======================================== 3 | 4 | .. automodule:: gensim.models.fasttext 5 | :synopsis: FastText model 6 | :members: 7 | :inherited-members: 8 | :special-members: __getitem__, __contains__ 9 | :undoc-members: 10 | :show-inheritance: 11 | -------------------------------------------------------------------------------- /docs/src/models/fasttext_inner.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.fasttext_inner` -- Cython routines for training FastText models 2 | ============================================================================ 3 | 4 | .. automodule:: gensim.models.fasttext_inner 5 | :synopsis: Optimized Cython routines for training FastText models 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/hdpmodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.hdpmodel` -- Hierarchical Dirichlet Process 2 | ======================================================== 3 | 4 | .. automodule:: gensim.models.hdpmodel 5 | :synopsis: Hierarchical Dirichlet Process 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/keyedvectors.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.keyedvectors` -- Store and query word vectors 2 | ========================================================== 3 | 4 | .. automodule:: gensim.models.keyedvectors 5 | :synopsis: Store and query word vectors 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :special-members: __getitem__, __setitem__, __contains__ 11 | -------------------------------------------------------------------------------- /docs/src/models/lda_dispatcher.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.lda_dispatcher` -- Dispatcher for distributed LDA 2 | ================================================================ 3 | 4 | .. automodule:: gensim.models.lda_dispatcher 5 | :synopsis: Dispatcher for distributed LDA 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/models/lda_worker.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.lda_worker` -- Worker for distributed LDA 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.lda_worker 5 | :synopsis: Worker for distributed LDA 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/models/ldamodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.ldamodel` -- Latent Dirichlet Allocation 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.ldamodel 5 | :synopsis: Latent Dirichlet Allocation 6 | :members: 7 | :special-members: __getitem__ 8 | :inherited-members: 9 | :undoc-members: 10 | :show-inheritance: 11 | -------------------------------------------------------------------------------- /docs/src/models/ldamulticore.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.ldamulticore` -- parallelized Latent Dirichlet Allocation 2 | ====================================================================== 3 | 4 | .. automodule:: gensim.models.ldamulticore 5 | :synopsis: Latent Dirichlet Allocation 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/ldaseqmodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.ldaseqmodel` -- Dynamic Topic Modeling in Python 2 | ============================================================= 3 | 4 | .. automodule:: gensim.models.ldaseqmodel 5 | :synopsis: Dynamic Topic Modeling in Python 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/logentropy_model.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.logentropy_model` -- LogEntropy model 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.logentropy_model 5 | :synopsis: LogEntropy model 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/lsi_dispatcher.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.lsi_dispatcher` -- Dispatcher for distributed LSI 2 | =============================================================== 3 | 4 | .. automodule:: gensim.models.lsi_dispatcher 5 | :synopsis: Dispatcher for distributed LSI 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/lsi_worker.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.lsi_worker` -- Worker for distributed LSI 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.lsi_worker 5 | :synopsis: Worker for distributed LSI 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/lsimodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.lsimodel` -- Latent Semantic Indexing 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.lsimodel 5 | :synopsis: Latent Semantic Indexing 6 | :members: 7 | :special-members: __getitem__ 8 | :inherited-members: 9 | :undoc-members: 10 | :show-inheritance: 11 | -------------------------------------------------------------------------------- /docs/src/models/models.rst: -------------------------------------------------------------------------------- 1 | :orphan: 2 | 3 | :mod:`models` -- Package for transformation models 4 | ====================================================== 5 | 6 | .. automodule:: gensim.models 7 | :synopsis: Package for transformation models 8 | :members: 9 | :inherited-members: 10 | 11 | -------------------------------------------------------------------------------- /docs/src/models/nmf.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.nmf` -- Non-Negative Matrix factorization 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.nmf 5 | :synopsis: Non-Negative Matrix Factorization 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/normmodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.normmodel` -- Normalization model 2 | =============================================== 3 | 4 | .. automodule:: gensim.models.normmodel 5 | :synopsis: Normalization model 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :special-members: __getitem__ 11 | -------------------------------------------------------------------------------- /docs/src/models/phrases.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.phrases` -- Phrase (collocation) detection 2 | ======================================================= 3 | 4 | .. automodule:: gensim.models.phrases 5 | :synopsis: Phrase (collocation) detection 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/poincare.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.poincare` -- Train and use Poincare embeddings 2 | ============================================================= 3 | 4 | .. automodule:: gensim.models.poincare 5 | :synopsis: Train and use Poincare embeddings 6 | :members: 7 | :inherited-members: 8 | :special-members: __iter__, __getitem__, __contains__ 9 | :undoc-members: 10 | :show-inheritance: 11 | -------------------------------------------------------------------------------- /docs/src/models/rpmodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.rpmodel` -- Random Projections 2 | ====================================================== 3 | 4 | .. automodule:: gensim.models.rpmodel 5 | :synopsis: Random Projections 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :special-members: __getitem__ 11 | -------------------------------------------------------------------------------- /docs/src/models/tfidfmodel.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.tfidfmodel` -- TF-IDF model 2 | ======================================== 3 | 4 | .. automodule:: gensim.models.tfidfmodel 5 | :synopsis: TF-IDF model 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :special-members: __getitem__ 11 | -------------------------------------------------------------------------------- /docs/src/models/translation_matrix.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.translation_matrix` -- Translation Matrix model 2 | ============================================================= 3 | 4 | .. automodule:: gensim.models.translation_matrix 5 | :synopsis: Translation Matrix 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/word2vec.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.word2vec` -- Word2vec embeddings 2 | ============================================= 3 | 4 | .. automodule:: gensim.models.word2vec 5 | :synopsis: Word2vec embeddings 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/models/word2vec_inner.rst: -------------------------------------------------------------------------------- 1 | :mod:`models.word2vec_inner` -- Cython routines for training Word2Vec models 2 | ============================================================================ 3 | 4 | .. automodule:: gensim.models.word2vec_inner 5 | :synopsis: Optimized Cython routines for training Word2Vec models 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/parsing/porter.rst: -------------------------------------------------------------------------------- 1 | :mod:`parsing.porter` -- Porter Stemming Algorithm 2 | ================================================== 3 | 4 | .. automodule:: gensim.parsing.porter 5 | :synopsis: Porter Stemming Algorithm 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/parsing/preprocessing.rst: -------------------------------------------------------------------------------- 1 | :mod:`parsing.preprocessing` -- Functions to preprocess raw text 2 | ================================================================ 3 | 4 | .. automodule:: gensim.parsing.preprocessing 5 | :synopsis: Functions to preprocess raw text 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/readme_images/12k.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/12k.png -------------------------------------------------------------------------------- /docs/src/readme_images/amazon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/amazon.png -------------------------------------------------------------------------------- /docs/src/readme_images/capitalone.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/capitalone.png -------------------------------------------------------------------------------- /docs/src/readme_images/channel4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/channel4.png -------------------------------------------------------------------------------- /docs/src/readme_images/cisco.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/cisco.png -------------------------------------------------------------------------------- /docs/src/readme_images/codeq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/codeq.png -------------------------------------------------------------------------------- /docs/src/readme_images/issuu.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/issuu.png -------------------------------------------------------------------------------- /docs/src/readme_images/juju.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/juju.png -------------------------------------------------------------------------------- /docs/src/readme_images/mass-cognition.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/mass-cognition.png -------------------------------------------------------------------------------- /docs/src/readme_images/mindseye.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/mindseye.png -------------------------------------------------------------------------------- /docs/src/readme_images/nih.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/nih.png -------------------------------------------------------------------------------- /docs/src/readme_images/nlpub.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/nlpub.png -------------------------------------------------------------------------------- /docs/src/readme_images/rare.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/rare.png -------------------------------------------------------------------------------- /docs/src/readme_images/search-metrics.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/search-metrics.png -------------------------------------------------------------------------------- /docs/src/readme_images/siteground.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/siteground.png -------------------------------------------------------------------------------- /docs/src/readme_images/sports-authority.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/sports-authority.png -------------------------------------------------------------------------------- /docs/src/readme_images/stillwater.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/stillwater.png -------------------------------------------------------------------------------- /docs/src/readme_images/tailwind.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/tailwind.png -------------------------------------------------------------------------------- /docs/src/readme_images/talent-pair.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/readme_images/talent-pair.png -------------------------------------------------------------------------------- /docs/src/scripts/glove2word2vec.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.glove2word2vec` -- Convert glove format to word2vec 2 | ================================================================= 3 | 4 | .. automodule:: gensim.scripts.glove2word2vec 5 | :synopsis: Convert glove format to word2vec 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/make_wiki_online.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.make_wiki_online` -- Convert articles from a Wikipedia dump 2 | ========================================================================= 3 | 4 | .. automodule:: gensim.scripts.make_wiki_online 5 | :synopsis: Convert articles from a Wikipedia dump 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/make_wiki_online_nodebug.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.make_wiki_online_nodebug` -- Convert articles from a Wikipedia dump 2 | ================================================================================= 3 | 4 | .. automodule:: gensim.scripts.make_wiki_online_nodebug 5 | :synopsis: Convert articles from a Wikipedia dump 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/make_wikicorpus.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.make_wikicorpus` -- Convert articles from a Wikipedia dump to vectors. 2 | ==================================================================================== 3 | 4 | .. automodule:: gensim.scripts.make_wikicorpus 5 | :synopsis: Convert articles from a Wikipedia dump to vectors. 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/package_info.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.package_info` -- Information about gensim package 2 | =============================================================== 3 | 4 | .. automodule:: gensim.scripts.package_info 5 | :synopsis: Information about gensim package. 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/segment_wiki.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.segment_wiki` -- Convert wikipedia dump to json-line format 2 | ========================================================================= 3 | 4 | .. automodule:: gensim.scripts.segment_wiki 5 | :synopsis: Convert wikipedia dump to json-line format. 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/word2vec2tensor.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.word2vec2tensor` -- Convert the word2vec format to Tensorflow 2D tensor 2 | ===================================================================================== 3 | 4 | .. automodule:: gensim.scripts.word2vec2tensor 5 | :synopsis: Convert the word2vec format to Tensorflow 2D tensor 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/scripts/word2vec_standalone.rst: -------------------------------------------------------------------------------- 1 | :mod:`scripts.word2vec_standalone` -- Train word2vec on text file CORPUS 2 | ======================================================================== 3 | 4 | .. automodule:: gensim.scripts.word2vec_standalone 5 | :synopsis: Train word2vec on text file CORPUS 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/similarities/annoy.rst: -------------------------------------------------------------------------------- 1 | :mod:`similarities.annoy` -- Approximate Vector Search using Annoy 2 | ================================================================== 3 | 4 | .. automodule:: gensim.similarities.annoy 5 | :synopsis: Fast Approximate Nearest Neighbor Similarity with the Annoy package 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/similarities/docsim.rst: -------------------------------------------------------------------------------- 1 | :mod:`similarities.docsim` -- Document similarity queries 2 | ======================================================================== 3 | 4 | .. automodule:: gensim.similarities.docsim 5 | :synopsis: Document similarity queries 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/similarities/fastss.rst: -------------------------------------------------------------------------------- 1 | :mod:`similarities.fastss` -- Fast Levenshtein edit distance 2 | ================================================================== 3 | 4 | .. automodule:: gensim.similarities.fastss 5 | :synopsis: Fast fuzzy search between strings, using the Levenshtein edit distance 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/similarities/levenshtein.rst: -------------------------------------------------------------------------------- 1 | :mod:`similarities.levenshtein` -- Fast soft-cosine semantic similarity search 2 | ============================================================================== 3 | 4 | .. automodule:: gensim.similarities.levenshtein 5 | :synopsis: Fast fuzzy search between strings, using the Soft-Cosine Semantic Similarity 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/similarities/nmslib.rst: -------------------------------------------------------------------------------- 1 | :mod:`similarities.nmslib` -- Approximate Vector Search using NMSLIB 2 | ==================================================================== 3 | 4 | .. automodule:: gensim.similarities.nmslib 5 | :synopsis: Fast Approximate Nearest Neighbor Similarity with the NMSLIB package 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/similarities/termsim.rst: -------------------------------------------------------------------------------- 1 | :mod:`similarities.termsim` -- Term similarity queries 2 | ======================================================================== 3 | 4 | .. automodule:: gensim.similarities.termsim 5 | :synopsis: Term similarity queries 6 | :members: 7 | :inherited-members: 8 | 9 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | Sphinx Read the Docs theme. 3 | 4 | From https://github.com/ryan-roemer/sphinx-bootstrap-theme. 5 | """ 6 | 7 | from os import path 8 | 9 | import sphinx 10 | 11 | 12 | __version__ = '0.5.0' 13 | __version_full__ = __version__ 14 | 15 | 16 | def get_html_theme_path(): 17 | """Return list of HTML theme paths.""" 18 | cur_dir = path.abspath(path.dirname(path.dirname(__file__))) 19 | return cur_dir 20 | 21 | 22 | # See http://www.sphinx-doc.org/en/stable/theming.html#distribute-your-theme-as-a-python-package 23 | def setup(app): 24 | if sphinx.version_info >= (1, 6, 0): 25 | # Register the theme that can be referenced without adding a theme path 26 | app.add_html_theme('sphinx_rtd_theme', path.abspath(path.dirname(__file__))) 27 | 28 | if sphinx.version_info >= (1, 8, 0): 29 | # Add Sphinx message catalog for newer versions of Sphinx 30 | # See http://www.sphinx-doc.org/en/master/extdev/appapi.html#sphinx.application.Sphinx.add_message_catalog 31 | rtd_locale_path = path.join(path.abspath(path.dirname(__file__)), 'locale') 32 | app.add_message_catalog('sphinx', rtd_locale_path) 33 | 34 | return {'parallel_read_safe': True, 'parallel_write_safe': True} 35 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/advertisement.html: -------------------------------------------------------------------------------- 1 | 6 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/footer.html: -------------------------------------------------------------------------------- 1 |
2 | {% if (theme_prev_next_buttons_location == 'bottom' or theme_prev_next_buttons_location == 'both') and (next or prev) %} 3 | 11 | {% endif %} 12 | 13 | {%- if show_sphinx %} 14 |
15 | {% set sphinx_web = 'Sphinx' %} 16 | {% set readthedocs_web = 'Read the Docs' %} 17 | {# Translators: the variable "sphinx_web" is a link to the Sphinx project documentation with the text "Sphinx" #} 18 | {% trans sphinx_web=sphinx_web, readthedocs_web=readthedocs_web %}Built with {{ sphinx_web }} using a{% endtrans %} 19 | {# Translators: "theme" refers to a theme for Sphinx, which alters the appearance of the generated documenation #} 20 | {% trans %}theme{% endtrans %} 21 | {# Translators: this is always used as "provided by Read the Docs", and should not imply Read the Docs is an author of the generated documentation. #} 22 | {% trans %}provided by {{ readthedocs_web }}{% endtrans %}. 23 | {%- endif %} 24 | 25 | {%- block extrafooter %} {% endblock %} 26 | 27 |
28 | 29 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/de/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/de/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/en/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/en/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/es/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/es/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/et/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/et/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/fr/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/fr/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/nl/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/nl/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/pt_BR/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/pt_BR/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/ru/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/ru/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/sv/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/sv/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/tr/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/tr/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/locale/zh_CN/LC_MESSAGES/sphinx.mo: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/locale/zh_CN/LC_MESSAGES/sphinx.mo -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/notification.html: -------------------------------------------------------------------------------- 1 |
2 | Gensim relies on your donations for sustenance. If you like Gensim, please consider donating. 3 |
4 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/searchbox.html: -------------------------------------------------------------------------------- 1 | {%- if builder != 'singlehtml' %} 2 |
3 |
4 | 5 | 6 | 7 |
8 |
9 | {%- endif %} 10 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/sideslide.html: -------------------------------------------------------------------------------- 1 |
2 |
3 | 4 |
5 | 6 |
7 |
8 | Fork on Github 9 |
10 |
11 |
12 |
13 | -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Bold.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Bold.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Bold.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Bold.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Regular.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Regular.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Regular.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/Roboto-Slab-Regular.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.eot: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.eot -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.ttf -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/fontawesome-webfont.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold-italic.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold-italic.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold-italic.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold-italic.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-bold.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal-italic.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal-italic.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal-italic.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal-italic.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal.woff -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/sphinx_rtd_theme/static/css/fonts/lato-normal.woff2 -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/static/js/badge_only.js: -------------------------------------------------------------------------------- 1 | !function(e){var t={};function r(n){if(t[n])return t[n].exports;var o=t[n]={i:n,l:!1,exports:{}};return e[n].call(o.exports,o,o.exports,r),o.l=!0,o.exports}r.m=e,r.c=t,r.d=function(e,t,n){r.o(e,t)||Object.defineProperty(e,t,{enumerable:!0,get:n})},r.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},r.t=function(e,t){if(1&t&&(e=r(e)),8&t)return e;if(4&t&&"object"==typeof e&&e&&e.__esModule)return e;var n=Object.create(null);if(r.r(n),Object.defineProperty(n,"default",{enumerable:!0,value:e}),2&t&&"string"!=typeof e)for(var o in e)r.d(n,o,function(t){return e[t]}.bind(null,o));return n},r.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return r.d(t,"a",t),t},r.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r.p="",r(r.s=4)}({4:function(e,t,r){}}); -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/theme.conf: -------------------------------------------------------------------------------- 1 | [theme] 2 | inherit = basic 3 | stylesheet = css/theme.css 4 | pygments_style = default 5 | 6 | [options] 7 | canonical_url = 8 | analytics_id = 9 | collapse_navigation = True 10 | sticky_navigation = True 11 | navigation_depth = 4 12 | includehidden = True 13 | titles_only = 14 | logo_only = 15 | display_version = True 16 | prev_next_buttons_location = bottom 17 | style_external_links = False 18 | style_nav_header_background = -------------------------------------------------------------------------------- /docs/src/sphinx_rtd_theme/versions.html: -------------------------------------------------------------------------------- 1 | {% if READTHEDOCS %} 2 | {# Add rst-badge after rst-versions for small badge style. #} 3 |
4 | 5 | Read the Docs 6 | v: {{ current_version }} 7 | 8 | 9 |
10 |
11 |
{{ _('Versions') }}
12 | {% for slug, url in versions %} 13 |
{{ slug }}
14 | {% endfor %} 15 |
16 |
17 |
{{ _('Downloads') }}
18 | {% for type, url in downloads %} 19 |
{{ type }}
20 | {% endfor %} 21 |
22 |
23 | {# Translators: The phrase "Read the Docs" is not translated #} 24 |
{{ _('On Read the Docs') }}
25 |
26 | {{ _('Project Home') }} 27 |
28 |
29 | {{ _('Builds') }} 30 |
31 |
32 |
33 |
34 | {% endif %} 35 | -------------------------------------------------------------------------------- /docs/src/test/utils.rst: -------------------------------------------------------------------------------- 1 | :mod:`test.utils` -- Internal testing functions 2 | =============================================== 3 | 4 | .. automodule:: gensim.test.utils 5 | :synopsis: Common utils used in testing Gensim internally 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/tools/four.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/tools/four.png -------------------------------------------------------------------------------- /docs/src/tools/one.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/tools/one.png -------------------------------------------------------------------------------- /docs/src/tools/three.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/tools/three.png -------------------------------------------------------------------------------- /docs/src/tools/two.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/docs/src/tools/two.png -------------------------------------------------------------------------------- /docs/src/topic_coherence/aggregation.rst: -------------------------------------------------------------------------------- 1 | :mod:`topic_coherence.aggregation` -- Aggregation module 2 | ======================================================== 3 | 4 | .. automodule:: gensim.topic_coherence.aggregation 5 | :synopsis: Aggregation module 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/topic_coherence/direct_confirmation_measure.rst: -------------------------------------------------------------------------------- 1 | :mod:`topic_coherence.direct_confirmation_measure` -- Direct confirmation measure module 2 | ======================================================================================== 3 | 4 | .. automodule:: gensim.topic_coherence.direct_confirmation_measure 5 | :synopsis: Direct confirmation measure module 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/topic_coherence/indirect_confirmation_measure.rst: -------------------------------------------------------------------------------- 1 | :mod:`topic_coherence.indirect_confirmation_measure` -- Indirect confirmation measure module 2 | ============================================================================================ 3 | 4 | .. automodule:: gensim.topic_coherence.indirect_confirmation_measure 5 | :synopsis: Indirect confirmation measure module 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/topic_coherence/probability_estimation.rst: -------------------------------------------------------------------------------- 1 | :mod:`topic_coherence.probability_estimation` -- Probability estimation module 2 | ============================================================================== 3 | 4 | .. automodule:: gensim.topic_coherence.probability_estimation 5 | :synopsis: Probability estimation module 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/topic_coherence/segmentation.rst: -------------------------------------------------------------------------------- 1 | :mod:`topic_coherence.segmentation` -- Segmentation module 2 | ========================================================== 3 | 4 | .. automodule:: gensim.topic_coherence.segmentation 5 | :synopsis: Segmentation module 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /docs/src/topic_coherence/text_analysis.rst: -------------------------------------------------------------------------------- 1 | :mod:`topic_coherence.text_analysis` -- Analyzing the texts of a corpus to accumulate statistical information about word occurrences 2 | ==================================================================================================================================== 3 | 4 | .. automodule:: gensim.topic_coherence.text_analysis 5 | :synopsis: Analyzing the texts of a corpus to accumulate statistical information about word occurrences 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | :special-members: __getitem__ 11 | -------------------------------------------------------------------------------- /docs/src/utils.rst: -------------------------------------------------------------------------------- 1 | :mod:`utils` -- Various utility functions 2 | ========================================== 3 | 4 | .. automodule:: gensim.utils 5 | :synopsis: Various utility functions 6 | :members: 7 | :inherited-members: 8 | :undoc-members: 9 | :show-inheritance: 10 | -------------------------------------------------------------------------------- /gensim Quick Start.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "This tutorial has moved.\n", 8 | "\n", 9 | "Please see https://radimrehurek.com/gensim/auto_examples/." 10 | ] 11 | } 12 | ], 13 | "metadata": { 14 | "kernelspec": { 15 | "display_name": "Python 3", 16 | "language": "python", 17 | "name": "python3" 18 | }, 19 | "language_info": { 20 | "codemirror_mode": { 21 | "name": "ipython", 22 | "version": 3 23 | }, 24 | "file_extension": ".py", 25 | "mimetype": "text/x-python", 26 | "name": "python", 27 | "nbconvert_exporter": "python", 28 | "pygments_lexer": "ipython3", 29 | "version": "3.6.8" 30 | } 31 | }, 32 | "nbformat": 4, 33 | "nbformat_minor": 2 34 | } 35 | -------------------------------------------------------------------------------- /gensim/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | This package contains functionality to transform documents (strings) into vectors, and calculate 3 | similarities between documents. 4 | 5 | """ 6 | 7 | __version__ = '4.3.3' 8 | 9 | import logging 10 | 11 | from gensim import parsing, corpora, matutils, interfaces, models, similarities, utils # noqa:F401 12 | 13 | 14 | logger = logging.getLogger('gensim') 15 | if not logger.handlers: # To ensure reload() doesn't add another one 16 | logger.addHandler(logging.NullHandler()) 17 | -------------------------------------------------------------------------------- /gensim/corpora/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | This package contains implementations of various streaming corpus I/O format. 3 | """ 4 | 5 | # bring corpus classes directly into package namespace, to save some typing 6 | from .indexedcorpus import IndexedCorpus # noqa:F401 must appear before the other classes 7 | 8 | from .mmcorpus import MmCorpus # noqa:F401 9 | from .bleicorpus import BleiCorpus # noqa:F401 10 | from .svmlightcorpus import SvmLightCorpus # noqa:F401 11 | from .lowcorpus import LowCorpus # noqa:F401 12 | from .dictionary import Dictionary # noqa:F401 13 | from .hashdictionary import HashDictionary # noqa:F401 14 | from .wikicorpus import WikiCorpus # noqa:F401 15 | from .textcorpus import TextCorpus, TextDirectoryCorpus # noqa:F401 16 | from .ucicorpus import UciCorpus # noqa:F401 17 | from .malletcorpus import MalletCorpus # noqa:F401 18 | from .opinosiscorpus import OpinosisCorpus # noqa:F401 19 | -------------------------------------------------------------------------------- /gensim/examples/dmlcz/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/examples/dmlcz/__init__.py -------------------------------------------------------------------------------- /gensim/examples/dmlcz/runall.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # full path to gensim executables 4 | BIN_PATH=~/xrehurek/gensim/dmlcz 5 | 6 | # intermediate data will be stored to this dir 7 | RESULT_PATH=~/xrehurek/results 8 | 9 | # set python path, so that python can find and import gensim modules 10 | export PYTHONPATH=~/xrehurek:${PYTHONPATH} 11 | 12 | # Language is set to 'any', meaning all articles are processed for similarity in 13 | # one go, regardless of their language. 14 | # Set language to 'eng', 'fre', 'rus' etc. to only process a specific subset of 15 | # articles (an article's language is determined from its metadata). 16 | language=any 17 | 18 | 19 | # ========== parse all article sources, build article co-occurence matrix ====== 20 | ${BIN_PATH}/gensim_build.py ${language} 2>&1 | tee ${RESULT_PATH}/gensim_build.log 21 | 22 | 23 | # ========== build transformation models ======================================= 24 | for method in tfidf rp; 25 | do 26 | ( ${BIN_PATH}/gensim_genmodel.py ${language} ${method} 2>&1 | tee ${RESULT_PATH}/gensim_genmodel_${method}.log ) & 27 | done 28 | wait 29 | 30 | method=lsi 31 | ${BIN_PATH}/gensim_genmodel.py ${language} ${method} 2>&1 | tee ${RESULT_PATH}/gensim_genmodel_${method}.log 32 | 33 | 34 | # =========== generate output xml files ======================================== 35 | # generate xml files for all methods at once, in parallel, to save time. 36 | # NOTE if out of memory, move tfidf out of the loop (tfidf uses a lot of memory here) 37 | for method in tfidf lsi rp; 38 | do 39 | ( ${BIN_PATH}/gensim_xml.py ${language} ${method} 2>&1 | tee ${RESULT_PATH}/gensim_xml_${method}.log ) & 40 | done 41 | wait 42 | -------------------------------------------------------------------------------- /gensim/models/fast_line_sentence.h: -------------------------------------------------------------------------------- 1 | #pragma once 2 | 3 | #include 4 | #include 5 | #include 6 | 7 | 8 | class FastLineSentence { 9 | public: 10 | explicit FastLineSentence() : is_eof_(false) { } 11 | explicit FastLineSentence(const std::string& filename, size_t offset = 0) : filename_(filename), 12 | fs_(filename), 13 | offset_(offset), 14 | is_eof_(false) { 15 | fs_.seekg(offset_); 16 | } 17 | 18 | std::vector ReadSentence() { 19 | if (is_eof_) { 20 | return {}; 21 | } 22 | std::string line, word; 23 | std::getline(fs_, line); 24 | std::vector res; 25 | 26 | std::istringstream iss(line); 27 | while (iss >> word) { 28 | res.push_back(word); 29 | } 30 | 31 | if (fs_.eof()) { 32 | is_eof_ = true; 33 | } 34 | return res; 35 | } 36 | 37 | inline bool IsEof() const { return is_eof_; } 38 | inline void Reset() { fs_.clear(); fs_.seekg(offset_); is_eof_ = false; } 39 | 40 | private: 41 | std::string filename_; 42 | std::ifstream fs_; 43 | size_t offset_; 44 | bool is_eof_; 45 | }; 46 | -------------------------------------------------------------------------------- /gensim/models/stdint_wrapper.h: -------------------------------------------------------------------------------- 1 | /* 2 | * This file is here to support older versions of the MSVC compiler that don't 3 | * have stdint.h. 4 | */ 5 | #ifdef _MSC_VER 6 | #ifndef _MSC_STDINT_H_ 7 | #if _MSC_VER < 1300 8 | typedef unsigned char uint8_t; 9 | typedef unsigned int uint32_t; 10 | typedef char int8_t; 11 | #else 12 | typedef unsigned __int8 uint8_t; 13 | typedef unsigned __int32 uint32_t; 14 | typedef char int8_t; 15 | #endif 16 | #endif 17 | #else 18 | #include 19 | #endif 20 | -------------------------------------------------------------------------------- /gensim/models/voidptr.h: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | #if PY_VERSION_HEX >= 0x03020000 4 | 5 | /* 6 | ** compatibility with python >= 3.2, which doesn't have CObject anymore 7 | */ 8 | static void * PyCObject_AsVoidPtr(PyObject *obj) 9 | { 10 | void *ret = PyCapsule_GetPointer(obj, NULL); 11 | if (ret == NULL) { 12 | PyErr_Clear(); 13 | } 14 | return ret; 15 | } 16 | 17 | #endif -------------------------------------------------------------------------------- /gensim/nosy.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | 3 | """ 4 | A simple testrunner for nose (or anything else). 5 | 6 | Watch for changes in all file types specified in 'EXTENSIONS'. 7 | If changes, run test executable in 'EXECUTABLE', with default 8 | arguments 'DEFAULTARGS'. 9 | 10 | The --with-color option needs the "rudolf" nose plugin. See: 11 | https://pypi.org/project/rudolf/ 12 | 13 | Originally by Jeff Winkler, http://jeffwinkler.net 14 | Forked from wkral https://github.com/wkral/Nosy 15 | """ 16 | 17 | import os 18 | import stat 19 | import time 20 | import datetime 21 | import sys 22 | import fnmatch 23 | 24 | 25 | EXTENSIONS = ['*.py'] 26 | EXECUTABLE = 'nosetests test/' 27 | DEFAULTARGS = '--with-color -exe' # -w tests' 28 | 29 | 30 | def check_sum(): 31 | """ 32 | Return a long which can be used to know if any .py files have changed. 33 | """ 34 | val = 0 35 | for root, dirs, files in os.walk(os.getcwd()): 36 | for extension in EXTENSIONS: 37 | for f in fnmatch.filter(files, extension): 38 | stats = os.stat(os.path.join(root, f)) 39 | val += stats[stat.ST_SIZE] + stats[stat.ST_MTIME] 40 | return val 41 | 42 | 43 | if __name__ == '__main__': 44 | val = 0 45 | try: 46 | while True: 47 | if check_sum() != val: 48 | val = check_sum() 49 | os.system('%s %s %s' % (EXECUTABLE, DEFAULTARGS, ' '.join(sys.argv[1:]))) 50 | print(datetime.datetime.now().__str__()) 51 | print('=' * 77) 52 | time.sleep(1) 53 | except KeyboardInterrupt: 54 | print('Goodbye') 55 | -------------------------------------------------------------------------------- /gensim/parsing/__init__.py: -------------------------------------------------------------------------------- 1 | """This package contains functions to preprocess raw text""" 2 | 3 | from .porter import PorterStemmer # noqa:F401 4 | from .preprocessing import ( # noqa:F401 5 | preprocess_documents, 6 | preprocess_string, 7 | read_file, 8 | read_files, 9 | remove_stopwords, 10 | split_alphanum, 11 | stem_text, 12 | strip_multiple_whitespaces, 13 | strip_non_alphanum, 14 | strip_numeric, 15 | strip_punctuation, 16 | strip_short, 17 | strip_tags, 18 | ) 19 | -------------------------------------------------------------------------------- /gensim/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/scripts/__init__.py -------------------------------------------------------------------------------- /gensim/scripts/benchmark.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | # 4 | # Copyright (C) 2020 Radim Rehurek 5 | 6 | """ 7 | Help script (template) for benchmarking. Run with: 8 | 9 | /usr/bin/time --format "%E elapsed\n%Mk peak RAM" python -m gensim.scripts.benchmark ~/gensim-data/text9/text9.txt 10 | 11 | """ 12 | 13 | import logging 14 | import sys 15 | 16 | from gensim.models.word2vec import Text8Corpus, LineSentence # noqa: F401 17 | from gensim.models import FastText, Word2Vec, Doc2Vec, Phrases # noqa: F401 18 | from gensim import __version__ 19 | 20 | logger = logging.getLogger(__name__) 21 | 22 | 23 | if __name__ == "__main__": 24 | logging.basicConfig( 25 | format='%(asctime)s [%(processName)s/%(process)d] [%(levelname)s] %(name)s:%(lineno)d: %(message)s', 26 | level=logging.INFO, 27 | ) 28 | 29 | if len(sys.argv) < 2: 30 | print(globals()['__doc__'] % locals()) 31 | sys.exit(1) 32 | 33 | corpus = Text8Corpus(sys.argv[1]) # text8/text9 format from https://mattmahoney.net/dc/textdata.html 34 | cls = FastText 35 | cls(corpus, workers=12, epochs=1).save(f'/tmp/{cls.__name__}.gensim{__version__}') 36 | -------------------------------------------------------------------------------- /gensim/scripts/make_wiki.py: -------------------------------------------------------------------------------- 1 | make_wikicorpus.py -------------------------------------------------------------------------------- /gensim/similarities/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | This package contains implementations of pairwise similarity queries. 3 | """ 4 | 5 | # bring classes directly into package namespace, to save some typing 6 | from .levenshtein import LevenshteinSimilarityIndex # noqa:F401 7 | from .docsim import ( # noqa:F401 8 | Similarity, 9 | MatrixSimilarity, 10 | SparseMatrixSimilarity, 11 | SoftCosineSimilarity, 12 | WmdSimilarity) 13 | from .termsim import ( # noqa:F401 14 | TermSimilarityIndex, 15 | UniformTermSimilarityIndex, 16 | WordEmbeddingSimilarityIndex, 17 | SparseTermSimilarityMatrix) 18 | -------------------------------------------------------------------------------- /gensim/test/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | This package contains automated code tests for all other gensim packages. 3 | """ 4 | -------------------------------------------------------------------------------- /gensim/test/test_aggregation.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | # 4 | # Copyright (C) 2010 Radim Rehurek 5 | # Licensed under the GNU LGPL v2.1 - https://www.gnu.org/licenses/old-licenses/lgpl-2.1.en.html 6 | 7 | """ 8 | Automated tests for checking transformation algorithms (the models package). 9 | """ 10 | 11 | import logging 12 | import unittest 13 | 14 | from gensim.topic_coherence import aggregation 15 | 16 | 17 | class TestAggregation(unittest.TestCase): 18 | def setUp(self): 19 | self.confirmed_measures = [1.1, 2.2, 3.3, 4.4] 20 | 21 | def test_arithmetic_mean(self): 22 | """Test arithmetic_mean()""" 23 | obtained = aggregation.arithmetic_mean(self.confirmed_measures) 24 | expected = 2.75 25 | self.assertEqual(obtained, expected) 26 | 27 | 28 | if __name__ == '__main__': 29 | logging.root.setLevel(logging.WARNING) 30 | unittest.main() 31 | -------------------------------------------------------------------------------- /gensim/test/test_data/DTM/ldaseq_3_0_1_model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/DTM/ldaseq_3_0_1_model -------------------------------------------------------------------------------- /gensim/test/test_data/OPUS_en_it_europarl_train_one2ten.txt: -------------------------------------------------------------------------------- 1 | one uno 2 | two due 3 | three tre 4 | four quattro 5 | five cinque 6 | six sei 7 | seven sette 8 | eight otto 9 | nine nove 10 | ten dieci 11 | dog cane 12 | pig maiale 13 | cat gatto 14 | fish cavallo 15 | birds uccelli 16 | apple mela 17 | orange arancione 18 | grape acino 19 | banana banana 20 | mango mango -------------------------------------------------------------------------------- /gensim/test/test_data/PathLineSentences/1.txt: -------------------------------------------------------------------------------- 1 | this is important text 2 | it is very important 3 | you are learning a lot 4 | from reading this text. 5 | it much be hard to be so special! 6 | we envy you, with your knowledge of this text file, 7 | thank you. -------------------------------------------------------------------------------- /gensim/test/test_data/PathLineSentences/2.txt.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/PathLineSentences/2.txt.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/atmodel_3_0_1_model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/atmodel_3_0_1_model -------------------------------------------------------------------------------- /gensim/test/test_data/atmodel_3_0_1_model.expElogbeta.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/atmodel_3_0_1_model.expElogbeta.npy -------------------------------------------------------------------------------- /gensim/test/test_data/atmodel_3_0_1_model.id2word: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/atmodel_3_0_1_model.id2word -------------------------------------------------------------------------------- /gensim/test/test_data/atmodel_3_0_1_model.state: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/atmodel_3_0_1_model.state -------------------------------------------------------------------------------- /gensim/test/test_data/bgwiki-latest-pages-articles-shortened.xml.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/bgwiki-latest-pages-articles-shortened.xml.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/compatible-hash-true.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/compatible-hash-true.model -------------------------------------------------------------------------------- /gensim/test/test_data/cp852_fasttext.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/cp852_fasttext.bin -------------------------------------------------------------------------------- /gensim/test/test_data/crime-and-punishment.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/crime-and-punishment.bin -------------------------------------------------------------------------------- /gensim/test/test_data/d2v-lee-v0.13.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/d2v-lee-v0.13.0 -------------------------------------------------------------------------------- /gensim/test/test_data/doc2vec_old: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/doc2vec_old -------------------------------------------------------------------------------- /gensim/test/test_data/doc2vec_old_sep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/doc2vec_old_sep -------------------------------------------------------------------------------- /gensim/test/test_data/doc2vec_old_sep.syn0_lockf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/doc2vec_old_sep.syn0_lockf.npy -------------------------------------------------------------------------------- /gensim/test/test_data/doc2vec_old_sep.syn1neg.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/doc2vec_old_sep.syn1neg.npy -------------------------------------------------------------------------------- /gensim/test/test_data/dtm_test.dict: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/dtm_test.dict -------------------------------------------------------------------------------- /gensim/test/test_data/ensemblelda: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ensemblelda -------------------------------------------------------------------------------- /gensim/test/test_data/enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/enwiki-latest-pages-articles1.xml-p000000010p000030302-shortened.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/enwiki-table-markup.xml.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/enwiki-table-markup.xml.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/euclidean_vectors.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/euclidean_vectors.bin -------------------------------------------------------------------------------- /gensim/test/test_data/fasttext_old: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/fasttext_old -------------------------------------------------------------------------------- /gensim/test/test_data/fasttext_old_sep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/fasttext_old_sep -------------------------------------------------------------------------------- /gensim/test/test_data/fasttext_old_sep.syn0_lockf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/fasttext_old_sep.syn0_lockf.npy -------------------------------------------------------------------------------- /gensim/test/test_data/fasttext_old_sep.syn1neg.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/fasttext_old_sep.syn1neg.npy -------------------------------------------------------------------------------- /gensim/test/test_data/ft_kv_3.6.0.model.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ft_kv_3.6.0.model.gz -------------------------------------------------------------------------------- /gensim/test/test_data/ft_model_2.3.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ft_model_2.3.0 -------------------------------------------------------------------------------- /gensim/test/test_data/head500.noblanks.cor.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/head500.noblanks.cor.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/head500.noblanks.cor_tfidf.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/head500.noblanks.cor_tfidf.model -------------------------------------------------------------------------------- /gensim/test/test_data/high_precision.kv.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/high_precision.kv.bin -------------------------------------------------------------------------------- /gensim/test/test_data/high_precision.kv.txt: -------------------------------------------------------------------------------- 1 | 2 2 2 | kangaroo.n.01 -0.0007369244245224787 -8.269973595356034e-05 3 | horse.n.01 -0.0008546282343595379 0.0007694142576316829 4 | -------------------------------------------------------------------------------- /gensim/test/test_data/large_tag_doc_10_iter50: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/large_tag_doc_10_iter50 -------------------------------------------------------------------------------- /gensim/test/test_data/lda_3_0_1_model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lda_3_0_1_model -------------------------------------------------------------------------------- /gensim/test/test_data/lda_3_0_1_model.expElogbeta.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lda_3_0_1_model.expElogbeta.npy -------------------------------------------------------------------------------- /gensim/test/test_data/lda_3_0_1_model.id2word: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lda_3_0_1_model.id2word -------------------------------------------------------------------------------- /gensim/test/test_data/lda_3_0_1_model.state: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lda_3_0_1_model.state -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_2_7: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_2_7 -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_2_7.expElogbeta.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_2_7.expElogbeta.npy -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_2_7.id2word: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_2_7.id2word -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_2_7.state: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_2_7.state -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_3_5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_3_5 -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_3_5.expElogbeta.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_3_5.expElogbeta.npy -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_3_5.id2word: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_3_5.id2word -------------------------------------------------------------------------------- /gensim/test/test_data/ldamodel_python_3_5.state: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/ldamodel_python_3_5.state -------------------------------------------------------------------------------- /gensim/test/test_data/ldavowpalwabbit.dict.txt: -------------------------------------------------------------------------------- 1 | 28 alex 1 2 | 23 alice 1 3 | 47 bacon 1 4 | 46 beans 1 5 | 25 bob 1 6 | 10 brakes 1 7 | 36 c 1 8 | 12 car 1 9 | 6 cat 1 10 | 40 cereal 1 11 | 0 cheetah 1 12 | 11 clutch 1 13 | 49 coffee 1 14 | 38 cplusplus 1 15 | 37 csharp 1 16 | 18 cylinder 1 17 | 27 dave 1 18 | 48 eggs 1 19 | 19 engine 1 20 | 30 erlang 1 21 | 17 exhaust 1 22 | 34 go 1 23 | 42 ham 1 24 | 24 harry 1 25 | 35 haskell 1 26 | 1 jaguar 1 27 | 39 java 1 28 | 21 jim 1 29 | 41 juice 1 30 | 2 kitten 1 31 | 4 leopard 1 32 | 9 lion 1 33 | 7 lynx 1 34 | 14 motor 1 35 | 3 mouse 1 36 | 44 mushrooms 1 37 | 5 puppy 1 38 | 32 python 1 39 | 26 rachel 1 40 | 22 robert 1 41 | 31 ruby 1 42 | 43 sausages 1 43 | 33 scala 1 44 | 20 sue 1 45 | 16 suspension 1 46 | 45 tea 1 47 | 8 tiger 1 48 | 29 tim 1 49 | 13 tyre 1 50 | 15 wheel 1 51 | -------------------------------------------------------------------------------- /gensim/test/test_data/lee.cor: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lee.cor -------------------------------------------------------------------------------- /gensim/test/test_data/lee_fasttext: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lee_fasttext -------------------------------------------------------------------------------- /gensim/test/test_data/lee_fasttext.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lee_fasttext.bin -------------------------------------------------------------------------------- /gensim/test/test_data/lee_fasttext_new.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/lee_fasttext_new.bin -------------------------------------------------------------------------------- /gensim/test/test_data/miIslita.cor: -------------------------------------------------------------------------------- 1 | LSI tutorials and fast tracks 2 | Books on semantic analysis 3 | Learning latent semantic indexing 4 | Advances in structures and advances in indexing 5 | Analysis of latent structures 6 | -------------------------------------------------------------------------------- /gensim/test/test_data/mini_newsgroup: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/mini_newsgroup -------------------------------------------------------------------------------- /gensim/test/test_data/model-from-gensim-3.8.0.w2v: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/model-from-gensim-3.8.0.w2v -------------------------------------------------------------------------------- /gensim/test/test_data/nmf_model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/nmf_model -------------------------------------------------------------------------------- /gensim/test/test_data/non_ascii_fasttext.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/non_ascii_fasttext.bin -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.12.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.12.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.12.1.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.12.1.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.12.2.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.12.2.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.12.3.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.12.3.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.12.4.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.12.4.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.13.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.13.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.13.1.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.13.1.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.13.2.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.13.2.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.13.3.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.13.3.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_0.13.4.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_0.13.4.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_1.0.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_1.0.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_1.0.1.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_1.0.1.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_2.0.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_2.0.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_2.1.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_2.1.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_2.2.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_2.2.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_2.3.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_2.3.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_3.0.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_3.0.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_3.1.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_3.1.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_3.2.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_3.2.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_3.3.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_3.3.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_d2v_models/d2v_3.4.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_d2v_models/d2v_3.4.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_keyedvectors_320.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_keyedvectors_320.dat -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.12.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.12.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.12.1.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.12.1.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.12.2.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.12.2.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.12.3.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.12.3.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.12.4.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.12.4.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.13.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.13.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.13.1.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.13.1.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.13.2.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.13.2.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.13.3.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.13.3.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_0.13.4.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_0.13.4.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_1.0.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_1.0.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_1.0.1.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_1.0.1.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_2.0.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_2.0.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_2.1.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_2.1.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_2.2.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_2.2.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_2.3.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_2.3.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_3.0.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_3.0.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_3.1.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_3.1.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_3.2.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_3.2.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_3.3.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_3.3.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/old_w2v_models/w2v_3.4.0.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/old_w2v_models/w2v_3.4.0.mdl -------------------------------------------------------------------------------- /gensim/test/test_data/pang_lee_polarity.cor: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/pang_lee_polarity.cor -------------------------------------------------------------------------------- /gensim/test/test_data/pang_lee_polarity_fasttext.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/pang_lee_polarity_fasttext.bin -------------------------------------------------------------------------------- /gensim/test/test_data/pang_lee_polarity_fasttext.vec: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/pang_lee_polarity_fasttext.vec -------------------------------------------------------------------------------- /gensim/test/test_data/phraser-3.6.0.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phraser-3.6.0.model -------------------------------------------------------------------------------- /gensim/test/test_data/phraser-no-common-terms.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phraser-no-common-terms.pkl -------------------------------------------------------------------------------- /gensim/test/test_data/phraser-no-scoring.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phraser-no-scoring.pkl -------------------------------------------------------------------------------- /gensim/test/test_data/phraser-scoring-str.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phraser-scoring-str.pkl -------------------------------------------------------------------------------- /gensim/test/test_data/phrases-3.6.0.model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phrases-3.6.0.model -------------------------------------------------------------------------------- /gensim/test/test_data/phrases-no-common-terms.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phrases-no-common-terms.pkl -------------------------------------------------------------------------------- /gensim/test/test_data/phrases-no-scoring.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phrases-no-scoring.pkl -------------------------------------------------------------------------------- /gensim/test/test_data/phrases-scoring-str.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/phrases-scoring-str.pkl -------------------------------------------------------------------------------- /gensim/test/test_data/poincare_cp852.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/poincare_cp852.tsv -------------------------------------------------------------------------------- /gensim/test/test_data/poincare_hypernyms.tsv: -------------------------------------------------------------------------------- 1 | kangaroo.n.01 marsupial.n.01 2 | kangaroo.n.01 metatherian.n.01 3 | kangaroo.n.01 mammal.n.01 4 | gib.n.02 cat.n.01 5 | striped_skunk.n.01 mammal.n.01 -------------------------------------------------------------------------------- /gensim/test/test_data/poincare_test_3.4.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/poincare_test_3.4.0 -------------------------------------------------------------------------------- /gensim/test/test_data/poincare_utf8.tsv: -------------------------------------------------------------------------------- 1 | tímto budeš 2 | budem byli -------------------------------------------------------------------------------- /gensim/test/test_data/poincare_vectors.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/poincare_vectors.bin -------------------------------------------------------------------------------- /gensim/test/test_data/pre_0_13_2_model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/pre_0_13_2_model -------------------------------------------------------------------------------- /gensim/test/test_data/pre_0_13_2_model.state: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/pre_0_13_2_model.state -------------------------------------------------------------------------------- /gensim/test/test_data/pretrained.vec: -------------------------------------------------------------------------------- 1 | 3 5 2 | dummy 0.069324 0.18155 0.080453 -0.1799 0.032043 3 | -------------------------------------------------------------------------------- /gensim/test/test_data/reproduce.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/reproduce.dat -------------------------------------------------------------------------------- /gensim/test/test_data/reproduce.dat.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/reproduce.dat.gz -------------------------------------------------------------------------------- /gensim/test/test_data/small_tag_doc_5_iter50: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/small_tag_doc_5_iter50 -------------------------------------------------------------------------------- /gensim/test/test_data/test_corpus_ok.mm: -------------------------------------------------------------------------------- 1 | %%matrixmarket matrix coordinate real general 2 | 3 5 9 3 | 1 1 1.000000 4 | 1 2 3.000000 5 | 1 4 5.000000 6 | 2 2 2.000000 7 | 2 3 1.000000 8 | 2 5 4.000000 9 | 3 1 2.000000 10 | 3 2 2.000000 11 | 3 3 8.000000 12 | 3 4 1.000000 13 | 3 5 2.000000 -------------------------------------------------------------------------------- /gensim/test/test_data/test_corpus_small.mm: -------------------------------------------------------------------------------- 1 | %%matrixmarket matrix coordinate real general 2 | 3 5 9 3 | 1 1 1.000000 4 | 1 2 3.000000 5 | 1 4 5.000000 6 | 2 2 2.000000 7 | 2 3 1.000000 8 | 2 5 4.000000 9 | 3 1 2.000000 10 | 3 2 2.000000 11 | 3 4 1.000000 -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_corrupt.mm: -------------------------------------------------------------------------------- 1 | %%MatrixMarket matrix coordinate real general 2 | 9 12 28 3 | 1 1 1.0 4 | 1 2 1.0 5 | 1 3 1.0 6 | 2 1 7 | 2 4 1.0 8 | 2 5 1.0 9 | 2 6 1.0 10 | 2 7 1.0 11 | 2 8 1.0 12 | 3 3 1.0 13 | 3 6 1.0 14 | 3 8 1.0 15 | 3 9 1.0 16 | 4 2 1.0 17 | 4 6 2.0 18 | 4 9 1.0 19 | 5 4 1.0 20 | 5 7 1.0 21 | 5 8 1.0 22 | 6 10 1.0 23 | 7 10 1.0 24 | 7 11 1.0 25 | 8 10 1.0 26 | 8 11 1.0 27 | 8 12 1.0 28 | 9 5 1.0 29 | 9 11 1.0 30 | 9 12 1.0 31 | -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_no_index.mm: -------------------------------------------------------------------------------- 1 | %%MatrixMarket matrix coordinate real general 2 | 9 12 28 3 | 1 1 1 4 | 1 2 1e0 5 | 1 3 1.0 6 | 3 3 0.42371910849 7 | 3 6 6.625174e-01 8 | 3 8 1.0 9 | 3 9 1.0 10 | 4 2 1.0 11 | 4 6 2.0 12 | 4 9 1.0 13 | 5 4 1.0 14 | 5 7 1.0 15 | 5 8 1.0 16 | 6 10 1.0 17 | 7 10 1.0 18 | 7 11 1.0 19 | 8 10 1.0 20 | 8 11 1.0 21 | 8 12 1.0 22 | 9 5 1.0 23 | 9 11 1.0 24 | 9 12 1.0 25 | -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_no_index.mm.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/test_mmcorpus_no_index.mm.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_no_index.mm.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/test_mmcorpus_no_index.mm.gz -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_overflow.mm: -------------------------------------------------------------------------------- 1 | %%MatrixMarket matrix coordinate real general 2 | 44270060 500 22134988630 3 | 1 1 0.3913027376444812 4 | 1 2 -0.07658791716226626 5 | 1 3 -0.020870794080588395 6 | 1 4 0.2145833024464887 7 | 1 5 0.16483779845897858 8 | 1 6 -0.05127146459864627 9 | 1 7 0.007765814982918945 10 | 1 8 -0.01817635794795088 11 | 10 500 .000001 12 | 4427006 1 -3.12 13 | 4427006 500 10.2 14 | 44270060 2 1.999 15 | -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_with_index.mm: -------------------------------------------------------------------------------- 1 | %%MatrixMarket matrix coordinate real general 2 | 9 12 28 3 | 1 1 1.0 4 | 1 2 1.0 5 | 1 3 1.0 6 | 2 1 1.0 7 | 2 4 1.0 8 | 2 5 1.0 9 | 2 6 1.0 10 | 2 7 1.0 11 | 2 8 1.0 12 | 3 3 1.0 13 | 3 6 1.0 14 | 3 8 1.0 15 | 3 9 1.0 16 | 4 2 1.0 17 | 4 6 2.0 18 | 4 9 1.0 19 | 5 4 1.0 20 | 5 7 1.0 21 | 5 8 1.0 22 | 6 10 1.0 23 | 7 10 1.0 24 | 7 11 1.0 25 | 8 10 1.0 26 | 8 11 1.0 27 | 8 12 1.0 28 | 9 5 1.0 29 | 9 11 1.0 30 | 9 12 1.0 31 | -------------------------------------------------------------------------------- /gensim/test/test_data/test_mmcorpus_with_index.mm.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/test_mmcorpus_with_index.mm.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.blei: -------------------------------------------------------------------------------- 1 | 3 0:1.0 1:1.0 2:1.0 2 | 6 2:1.0 3:1.0 4:1.0 5:1.0 6:1.0 8:1.0 3 | 4 1:1.0 3:1.0 4:1.0 7:1.0 4 | 3 0:1.0 4:2.0 7:1.0 5 | 3 3:1.0 5:1.0 6:1.0 6 | 1 9:1.0 7 | 2 9:1.0 10:1.0 8 | 3 9:1.0 10:1.0 11:1.0 9 | 3 8:1.0 10:1.0 11:1.0 10 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.blei.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.blei.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.blei.vocab: -------------------------------------------------------------------------------- 1 | human 2 | interface 3 | computer 4 | user 5 | system 6 | response 7 | time 8 | eps 9 | survey 10 | trees 11 | graph 12 | minors 13 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.low: -------------------------------------------------------------------------------- 1 | 9 2 | computer human interface 3 | computer response survey system time user 4 | interface system user eps 5 | human system system eps 6 | response time user 7 | trees 8 | trees graph 9 | trees graph minors 10 | survey graph minors 11 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.low.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.low.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.mallet: -------------------------------------------------------------------------------- 1 | 1 en computer human interface 2 | 2 en computer response survey system time user 3 | 3 en interface system user eps 4 | 4 en human system system eps 5 | 5 en response time user 6 | 6 en trees 7 | 7 en trees graph 8 | 8 en trees graph minors 9 | 9 en survey graph minors 10 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.mallet.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.mallet.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.mm: -------------------------------------------------------------------------------- 1 | %%MatrixMarket matrix coordinate real general 2 | 9 12 28 3 | 1 1 1.0 4 | 1 2 1.0 5 | 1 3 1.0 6 | 2 1 1.0 7 | 2 4 1.0 8 | 2 5 1.0 9 | 2 6 1.0 10 | 2 7 1.0 11 | 2 8 1.0 12 | 3 3 1.0 13 | 3 6 1.0 14 | 3 8 1.0 15 | 3 9 1.0 16 | 4 2 1.0 17 | 4 6 2.0 18 | 4 9 1.0 19 | 5 4 1.0 20 | 5 7 1.0 21 | 5 8 1.0 22 | 6 10 1.0 23 | 7 10 1.0 24 | 7 11 1.0 25 | 8 10 1.0 26 | 8 11 1.0 27 | 8 12 1.0 28 | 9 5 1.0 29 | 9 11 1.0 30 | 9 12 1.0 31 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.mm.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.mm.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.svmlight: -------------------------------------------------------------------------------- 1 | 0 1:1.0 2:1.0 3:1.0 2 | 0 1:1.0 4:1.0 5:1.0 6:1.0 7:1.0 8:1.0 3 | 0 3:1.0 6:1.0 8:1.0 9:1.0 4 | 0 2:1.0 6:2.0 9:1.0 5 | 0 4:1.0 7:1.0 8:1.0 6 | 0 10:1.0 7 | 0 10:1.0 11:1.0 8 | 0 10:1.0 11:1.0 12:1.0 9 | 0 5:1.0 11:1.0 12:1.0 10 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.svmlight.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.svmlight.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.txt: -------------------------------------------------------------------------------- 1 | computer human interface 2 | computer response survey system time user 3 | interface system user eps 4 | human system system eps 5 | response time user 6 | trees 7 | trees graph 8 | trees graph minors 9 | survey graph minors 10 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.uci: -------------------------------------------------------------------------------- 1 | 9 2 | 12 3 | 28 4 | 1 1 1 5 | 1 2 1 6 | 1 3 1 7 | 2 1 1 8 | 2 4 1 9 | 2 5 1 10 | 2 6 1 11 | 2 7 1 12 | 2 8 1 13 | 3 3 1 14 | 3 6 1 15 | 3 8 1 16 | 3 9 1 17 | 4 2 1 18 | 4 6 2 19 | 4 9 1 20 | 5 4 1 21 | 5 7 1 22 | 5 8 1 23 | 6 10 1 24 | 7 10 1 25 | 7 11 1 26 | 8 10 1 27 | 8 11 1 28 | 8 12 1 29 | 9 5 1 30 | 9 11 1 31 | 9 12 1 32 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.uci.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.uci.index -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.uci.vocab: -------------------------------------------------------------------------------- 1 | human 2 | interface 3 | computer 4 | user 5 | system 6 | response 7 | time 8 | eps 9 | survey 10 | trees 11 | graph 12 | minors 13 | -------------------------------------------------------------------------------- /gensim/test/test_data/testcorpus.xml.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/testcorpus.xml.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/tfidf_model.tst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/tfidf_model.tst -------------------------------------------------------------------------------- /gensim/test/test_data/tfidf_model.tst.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/tfidf_model.tst.bz2 -------------------------------------------------------------------------------- /gensim/test/test_data/tfidf_model_3_2.tst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/tfidf_model_3_2.tst -------------------------------------------------------------------------------- /gensim/test/test_data/toy-model-pretrained.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/toy-model-pretrained.bin -------------------------------------------------------------------------------- /gensim/test/test_data/toy-model.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/toy-model.bin -------------------------------------------------------------------------------- /gensim/test/test_data/toy-model.vec: -------------------------------------------------------------------------------- 1 | 22 5 2 | the 0.068811 0.26619 0.026622 -0.2588 -0.00044401 3 | of 0.074764 0.2619 0.14943 -0.053636 -0.073243 4 | and 0.025684 0.18749 0.067497 -0.19666 -0.062668 5 | in 0.055452 0.14837 0.11453 -0.076973 0.075165 6 | as 0.10787 0.16187 0.043256 -0.12037 -0.011599 7 | is 0.027692 0.056879 0.061164 -0.026575 0.12943 8 | that 0.015852 0.18278 0.086632 -0.17117 -0.072813 9 | to -0.010698 0.2047 0.020393 -0.072041 0.039349 10 | a 0.11679 0.079237 0.018602 -0.029343 -0.10735 11 | anarchist 0.069324 0.18155 0.080453 -0.1799 0.032043 12 | anarchism 0.053744 0.16174 0.085072 -0.16948 0.060652 13 | society 0.042448 0.12715 0.064185 -0.16303 -0.006732 14 | what 0.072764 0.10056 0.047633 -0.12504 -0.00014207 15 | are 0.11297 0.045401 0.095844 -0.12175 0.066899 16 | anarchists 0.058975 0.16489 0.056698 -0.17042 0.047557 17 | this -0.026196 0.12589 0.10777 -0.12444 -0.010785 18 | it 0.051083 0.19504 0.14424 -0.097121 0.032338 19 | property 0.039276 0.13466 0.061619 -0.12174 0.0080965 20 | be 0.14753 0.18994 0.12194 -0.17747 -0.0028654 21 | term -0.010314 0.02472 0.033475 -0.10523 -0.012877 22 | an 0.1387 0.30319 0.14955 -0.35181 -0.046356 23 | by 0.13272 0.12397 0.084777 -0.14616 0.006166 24 | -------------------------------------------------------------------------------- /gensim/test/test_data/varembed_morfessor.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/varembed_morfessor.bin -------------------------------------------------------------------------------- /gensim/test/test_data/w2v-lee-v0.12.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/w2v-lee-v0.12.0 -------------------------------------------------------------------------------- /gensim/test/test_data/w2v_keyedvectors_load_test.modeldata: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/w2v_keyedvectors_load_test.modeldata -------------------------------------------------------------------------------- /gensim/test/test_data/w2v_keyedvectors_load_test.vocab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/w2v_keyedvectors_load_test.vocab -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_3.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_3.3 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_old: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_old -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_old_sep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_old_sep -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_old_sep.syn0_lockf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_old_sep.syn0_lockf.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_old_sep.syn1neg.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_old_sep.syn1neg.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_py2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_py2 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_py3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_py3 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_py3_4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_py3_4 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py2 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py2.neg_labels.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py2.neg_labels.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py2.syn0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py2.syn0.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py2.syn0_lockf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py2.syn0_lockf.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py2.syn1neg.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py2.syn1neg.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3.neg_labels.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3.neg_labels.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3.syn0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3.syn0.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3.syn0_lockf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3.syn0_lockf.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3.syn1neg.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3.syn1neg.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3_4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3_4 -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3_4.neg_labels.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3_4.neg_labels.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3_4.syn0.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3_4.syn0.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3_4.syn0_lockf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3_4.syn0_lockf.npy -------------------------------------------------------------------------------- /gensim/test/test_data/word2vec_pre_kv_sep_py3_4.syn1neg.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/piskvorky/gensim/6591e008f065017adce9d25113a036864e3a9dc6/gensim/test/test_data/word2vec_pre_kv_sep_py3_4.syn1neg.npy -------------------------------------------------------------------------------- /gensim/topic_coherence/__init__.py: -------------------------------------------------------------------------------- 1 | """ 2 | This package contains implementation of the individual components of 3 | the topic coherence pipeline. 4 | """ 5 | -------------------------------------------------------------------------------- /gensim/topic_coherence/aggregation.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | # 4 | # Copyright (C) 2013 Radim Rehurek 5 | # Licensed under the GNU LGPL v2.1 - https://www.gnu.org/licenses/old-licenses/lgpl-2.1.en.html 6 | 7 | """This module contains functions to perform aggregation on a list of values obtained from the confirmation measure.""" 8 | 9 | import logging 10 | import numpy as np 11 | 12 | logger = logging.getLogger(__name__) 13 | 14 | 15 | def arithmetic_mean(confirmed_measures): 16 | """ 17 | Perform the arithmetic mean aggregation on the output obtained from 18 | the confirmation measure module. 19 | 20 | Parameters 21 | ---------- 22 | confirmed_measures : list of float 23 | List of calculated confirmation measure on each set in the segmented topics. 24 | 25 | Returns 26 | ------- 27 | `numpy.float` 28 | Arithmetic mean of all the values contained in confirmation measures. 29 | 30 | Examples 31 | -------- 32 | .. sourcecode:: pycon 33 | 34 | >>> from gensim.topic_coherence.aggregation import arithmetic_mean 35 | >>> arithmetic_mean([1.1, 2.2, 3.3, 4.4]) 36 | 2.75 37 | 38 | """ 39 | return np.mean(confirmed_measures) 40 | -------------------------------------------------------------------------------- /pip.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | pip install --upgrade pip 3 | pip install --timeout=60 --trusted-host 28daf2247a33ed269873-7b1aad3fab3cc330e1fd9d109892382a.r6.cf2.rackcdn.com --find-links http://28daf2247a33ed269873-7b1aad3fab3cc330e1fd9d109892382a.r6.cf2.rackcdn.com/ "$@" 4 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [build-system] 2 | requires = [ 3 | # 4 | # If we build our extensions with Cython 3.0.0, then they will be an 5 | # order of magnitude slower, so avoid it for now. 6 | # 7 | "Cython>=0.29.32,<3.0.0", 8 | # oldest supported Numpy for this platform is 1.17 but the oldest supported by Gensim 9 | # is 1.18.5, remove the line when they increase oldest supported Numpy for this platform 10 | "numpy==1.18.5; python_version=='3.8' and platform_machine not in 'arm64|aarch64'", 11 | "oldest-supported-numpy; python_version>'3.8' or platform_machine in 'arm64|aarch64'", 12 | "setuptools", 13 | "wheel", 14 | ] 15 | -------------------------------------------------------------------------------- /release/README.md: -------------------------------------------------------------------------------- 1 | Scripts to help when making new releases. 2 | 3 | For more info, see [our Wiki page](https://github.com/RaRe-Technologies/gensim/wiki/Maintainer-page). 4 | -------------------------------------------------------------------------------- /release/annotate_pr.py: -------------------------------------------------------------------------------- 1 | """Helper script for including change log entries in an open PR. 2 | 3 | Automatically constructs the change log entry from the PR title. 4 | Copies the entry to the window manager clipboard. 5 | Opens the change log belonging to the specific PR in a browser window. 6 | All you have to do is paste and click "commit changes". 7 | """ 8 | import json 9 | import sys 10 | import webbrowser 11 | 12 | import smart_open 13 | 14 | 15 | def copy_to_clipboard(text): 16 | try: 17 | import pyperclip 18 | except ImportError: 19 | print('pyperclip is missing.', file=sys.stderr) 20 | print('copy-paste the following text manually:', file=sys.stderr) 21 | print('\t', text, file=sys.stderr) 22 | else: 23 | pyperclip.copy(text) 24 | 25 | 26 | prid = int(sys.argv[1]) 27 | url = "https://api.github.com/repos/RaRe-Technologies/gensim/pulls/%d" % prid 28 | with smart_open.open(url) as fin: 29 | prinfo = json.load(fin) 30 | 31 | prinfo['user_login'] = prinfo['user']['login'] 32 | prinfo['user_html_url'] = prinfo['user']['html_url'] 33 | text = '[#%(number)s](%(html_url)s): %(title)s, by [@%(user_login)s](%(user_html_url)s)' % prinfo 34 | copy_to_clipboard(text) 35 | 36 | prinfo['head_repo_html_url'] = prinfo['head']['repo']['html_url'] 37 | prinfo['head_ref'] = prinfo['head']['ref'] 38 | edit_url = '%(head_repo_html_url)s/edit/%(head_ref)s/CHANGELOG.md' % prinfo 39 | webbrowser.open(edit_url) 40 | -------------------------------------------------------------------------------- /release/merge.sh: -------------------------------------------------------------------------------- 1 | # 2 | # This script performs merges between three branches used in a release: 3 | # 4 | # - develop: Our development branch. We merge all PRs into this branch. 5 | # - release-$RELEASE: A local branch containing commits specific to this release. 6 | # This is a local-only branch, we never push this anywhere. 7 | # - master: Our "clean" release branch. Contains tags. 8 | # 9 | # The relationships between the three branches are illustrated below: 10 | # 11 | # github.com PRs 12 | # \ 13 | # develop --+--+----------------------------------+--- 14 | # \ / 15 | # (new branch) \ commits (CHANGELOG.md, etc) / 16 | # \ v / 17 | # release ---*-----X (delete branch) / (merge 2) 18 | # \ / 19 | # (merge 1) \ TAG / 20 | # \ v / 21 | # master -------------------+------*-----+----------- 22 | # 23 | 24 | echo "RELEASE: $RELEASE" 25 | set -euxo pipefail 26 | 27 | 28 | # 29 | # Delete local branches, because we'll be cloning them entirely from the remote. 30 | # You'll need to be on the release branch to be able to delete the other two. 31 | # 32 | git checkout release-${RELEASE} 33 | set +e 34 | git branch -D master develop 35 | set -e 36 | 37 | git fetch upstream 38 | git checkout upstream/master -b master 39 | 40 | # 41 | # Merge the release branch into master. This is merge 1 in the diagram above. 42 | # 43 | git merge --no-ff release-${RELEASE} 44 | git tag -a ${RELEASE} -m "${RELEASE}" 45 | 46 | # 47 | # Merge the master branch into develop. This is merge 2 in the diagram above. 48 | # 49 | git checkout upstream/develop -b develop 50 | git merge --no-ff master 51 | -------------------------------------------------------------------------------- /release/prepare.sh: -------------------------------------------------------------------------------- 1 | # 2 | # This script initiates a new release. 3 | # 4 | # Run it like so: 5 | # 6 | # bash start.sh 1.2.3 7 | # 8 | # where 1.2.3 is the release version. 9 | # 10 | 11 | set -euxo pipefail 12 | 13 | previous_version=$(python -c 'import gensim;print(gensim.__version__)') 14 | 15 | RELEASE=$1 16 | export RELEASE="$RELEASE" 17 | 18 | script_dir="$(dirname "${BASH_SOURCE[0]}")" 19 | root=$(cd "$script_dir/.." && pwd) 20 | cd "$script_dir" 21 | 22 | git fetch upstream 23 | git checkout upstream/develop 24 | 25 | # 26 | # Get rid of the local release branch, if it exists. 27 | # 28 | set +e 29 | git branch -D release-"$RELEASE" 30 | set -e 31 | 32 | git checkout -b release-"$RELEASE" 33 | python bump_version.py "$previous_version" "$RELEASE" 34 | 35 | # 36 | # N.B. grep exits with nonzero if the target string is not found 37 | # 38 | grep "$RELEASE" "$root/setup.py" 39 | grep "$RELEASE" "$root/docs/src/conf.py" 40 | grep "$RELEASE" "$root/gensim/__init__.py" 41 | 42 | set +e 43 | git diff | cat 44 | git commit -a -m "bumped version to $RELEASE" 45 | set -e 46 | 47 | echo "Now update CHANGELOG.md and include the PRs in this release." 48 | read -p "Press Enter to continue. An editor window will open." 49 | python update_changelog.py "$previous_version" "$RELEASE" 50 | $EDITOR "$root/CHANGELOG.md" 51 | 52 | set +e 53 | git commit "$root/CHANGELOG.md" -m "updated CHANGELOG.md for version $RELEASE" 54 | set -e 55 | 56 | echo "Have a look at the current branch, and if all looks good, run merge.sh" 57 | -------------------------------------------------------------------------------- /release/push.sh: -------------------------------------------------------------------------------- 1 | # 2 | # Push local branches to upstream (github.com). 3 | # 4 | # Run this after you've verified the results of merge.sh. 5 | # 6 | set -euxo pipefail 7 | release=$RELEASE 8 | 9 | git push --tags upstream master 10 | git push upstream develop 11 | git push upstream release-"$release" 12 | -------------------------------------------------------------------------------- /release/upload_docs.sh: -------------------------------------------------------------------------------- 1 | python setup.py build_ext --inplace 2 | cd docs/src 3 | make html 4 | make upload 5 | -------------------------------------------------------------------------------- /requirements_docs.txt: -------------------------------------------------------------------------------- 1 | Pyro4==4.77 2 | Sphinx==3.5.2 3 | annoy==1.16.2 4 | memory-profiler==0.55.0 5 | nltk==3.4.5 6 | nmslib==2.1.1 7 | pandas==1.2.3 8 | POT==0.8.1 9 | scikit-learn==0.24.1 10 | sphinx-gallery==0.8.2 11 | sphinxcontrib-napoleon==0.7 12 | sphinxcontrib-programoutput==0.15 13 | statsmodels==0.12.2 14 | testfixtures==6.17.1 15 | -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [wheelhouse_uploader] 2 | artifact_indexes= 3 | # 4 | # See https://github.com/RaRe-Technologies/gensim/wiki/Developer-page 5 | # 6 | http://gensim-wheels.s3-website-us-east-1.amazonaws.com/ 7 | --------------------------------------------------------------------------------