github piskvorky/gensim 4.0.1
on GitHub

latest releases: 4.3.3, 4.3.2, 4.3.1...
3 years ago

4.0.1, 2021-04-01

Bugfix release to address issues with wheels on Windows due to Numpy binary incompatibility:

4.0.0, 2021-03-24

⚠️ Gensim 4.0 contains breaking API changes! See the Migration guide to update your existing Gensim 3.x code and models.

Gensim 4.0 is a major release with lots of performance & robustness improvements, and a new website.

Main highlights

  • Massively optimized popular algorithms the community has grown to love: fastText, word2vec, doc2vec, phrases:

    a. Efficiency

    model 3.8.3: wall time / peak RAM / throughput 4.0.0: wall time / peak RAM / throughput
    fastText 2.9h / 4.11 GB / 822k words/s 2.3h / 1.26 GB / 914k words/s
    word2vec 1.7h / 0.36 GB / 1685k words/s 1.2h / 0.33 GB / 1762k words/s

    In other words, fastText now needs 3x less RAM (and is faster); word2vec has 2x faster init (and needs less RAM, and is faster); detecting collocation phrases is 2x faster. (4.0 benchmarks)

    b. Robustness. We fixed a bunch of long-standing bugs by refactoring the internal code structure (see 🔴 Bug fixes below)

    c. Simplified OOP model for easier model exports and integration with TensorFlow, PyTorch &co.

    These improvements come to you transparently aka "for free", but see Migration guide for some changes that break the old Gensim 3.x API. Update your code accordingly.

  • Dropped a bunch of externally contributed modules and wrappers: summarization, pivoted TFIDF, Mallet…

    • Code quality was not up to our standards. Also there was no one to maintain these modules, answer user questions, support them.

      So rather than let them rot, we took the hard decision of removing these contributed modules from Gensim. If anyone's interested in maintaining them, please fork & publish into your own repo. They can live happily outside of Gensim.

  • Dropped Python 2. Gensim 4.0 is Py3.6+. Read our Python version support policy.

    • If you still need Python 2 for some reason, stay at Gensim 3.8.3.

  • A new Gensim website – finally! 🙃

So, a major clean-up release overall. We're happy with this tighter, leaner and faster Gensim.

This is the direction we'll keep going forward: less kitchen-sink of "latest academic algorithms", more focus on robust engineering, targetting concrete NLP & document similarity use-cases.

👍 New features

📚 Tutorials and docs

🔴 Bug fixes

  • #2891: Fix fastText word-vectors with ngrams off, by @gojomo
  • #2907: Fix doc2vec crash for large sets of doc-vectors, by @gojomo
  • #2899: Fix similarity bug in NMSLIB indexer, by @piskvorky
  • #2899: Fix deprecation warnings in Annoy integration, by @piskvorky
  • #2901: Fix inheritance of WikiCorpus from TextCorpus, by @jenishah
  • #2940: Fix deprecations in SoftCosineSimilarity, by @Witiko
  • #2944: Fix save_facebook_model failure after update-vocab & other initialization streamlining, by @gojomo
  • #2846: Fix for Python 3.9/3.10: remove xml.etree.cElementTree, by @hugovk
  • #2973: phrases.export_phrases() doesn't yield all bigrams, by @piskvorky
  • #2942: Segfault when training doc2vec, by @gojomo
  • #3041: Fix RuntimeError in export_phrases (change defaultdict to dict), by @thalishsajeed
  • #3059: Fix race condition in FastText tests, by @sleepy-owl

⚠️ Removed functionality & deprecations

🔮 Testing, CI, housekeeping

4.0.0.rc1, 2021-03-19

⚠️ Gensim 4.0 contains breaking API changes! See the Migration guide to update your existing Gensim 3.x code and models.

Gensim 4.0 is a major release with lots of performance & robustness improvements and a new website.

Main highlights (see also 👍 Improvements below)

  • Massively optimized popular algorithms the community has grown to love: fastText, word2vec, doc2vec, phrases:

    a. Efficiency

    model 3.8.3: wall time / peak RAM / throughput 4.0.0: wall time / peak RAM / throughput
    fastText 2.9h / 4.11 GB / 822k words/s 2.3h / 1.26 GB / 914k words/s
    word2vec 1.7h / 0.36 GB / 1685k words/s 1.2h / 0.33 GB / 1762k words/s

    In other words, fastText now needs 3x less RAM (and is faster); word2vec has 2x faster init (and needs less RAM, and is faster); detecting collocation phrases is 2x faster. (4.0 benchmarks)

    b. Robustness. We fixed a bunch of long-standing bugs by refactoring the internal code structure (see 🔴 Bug fixes below)

    c. Simplified OOP model for easier model exports and integration with TensorFlow, PyTorch &co.

    These improvements come to you transparently aka "for free", but see Migration guide for some changes that break the old Gensim 3.x API. Update your code accordingly.

  • Dropped a bunch of externally contributed modules: summarization, pivoted TFIDF normalization, FIXME.

    • Code quality was not up to our standards. Also there was no one to maintain them, answer user questions, support these modules.

      So rather than let them rot, we took the hard decision of removing these contributed modules from Gensim. If anyone's interested in maintaining them please fork into your own repo, they can live happily outside of Gensim.

  • Dropped Python 2. Gensim 4.0 is Py3.6+. Read our Python version support policy.

    • If you still need Python 2 for some reason, stay at Gensim 3.8.3.

  • A new Gensim website – finally! 🙃

So, a major clean-up release overall. We're happy with this tighter, leaner and faster Gensim.

This is the direction we'll keep going forward: less kitchen-sink of "latest academic algorithms", more focus on robust engineering, targetting common concrete NLP & document similarity use-cases.

🌟 New Features

🔴 Bug fixes

📚 Tutorial and doc improvements

  • fix various documentation warnings (mpenkov, #3077)
  • Fix broken link in run_doc how-to (sezanzeb, #2991)
  • Point WordEmbeddingSimilarityIndex documentation to gensim.similarities (Witiko, #3003)
  • Make the link to the Gensim 3.8.3 documentation dynamic (Witiko, #2996)

⚠️ Removed functionality

🔮 Miscellaneous

4.0.0beta, 2020-10-31

⚠️ Gensim 4.0 contains breaking API changes! See the Migration guide to update your existing Gensim 3.x code and models.

Gensim 4.0 is a major release with lots of performance & robustness improvements and a new website.

Main highlights (see also 👍 Improvements below)

  • Massively optimized popular algorithms the community has grown to love: fastText, word2vec, doc2vec, phrases:

    a. Efficiency

    model 3.8.3: wall time / peak RAM / throughput 4.0.0: wall time / peak RAM / throughput
    fastText 2.9h / 4.11 GB / 822k words/s 2.3h / 1.26 GB / 914k words/s
    word2vec 1.7h / 0.36 GB / 1685k words/s 1.2h / 0.33 GB / 1762k words/s

    In other words, fastText now needs 3x less RAM (and is faster); word2vec has 2x faster init (and needs less RAM, and is faster); detecting collocation phrases is 2x faster. (4.0 benchmarks)

    b. Robustness. We fixed a bunch of long-standing bugs by refactoring the internal code structure (see 🔴 Bug fixes below)

    c. Simplified OOP model for easier model exports and integration with TensorFlow, PyTorch &co.

    These improvements come to you transparently aka "for free", but see Migration guide for some changes that break the old Gensim 3.x API. Update your code accordingly.

  • Dropped a bunch of externally contributed modules: summarization, pivoted TFIDF normalization, FIXME.

    • Code quality was not up to our standards. Also there was no one to maintain them, answer user questions, support these modules.

      So rather than let them rot, we took the hard decision of removing these contributed modules from Gensim. If anyone's interested in maintaining them please fork into your own repo, they can live happily outside of Gensim.

  • Dropped Python 2. Gensim 4.0 is Py3.6+. Read our Python version support policy.

    • If you still need Python 2 for some reason, stay at Gensim 3.8.3.

  • A new Gensim website – finally! 🙃

So, a major clean-up release overall. We're happy with this tighter, leaner and faster Gensim.

This is the direction we'll keep going forward: less kitchen-sink of "latest academic algorithms", more focus on robust engineering, targetting common concrete NLP & document similarity use-cases.

Why pre-release?

This 4.0.0beta pre-release is for users who want the cutting edge performance and bug fixes. Plus users who want to help out, by testing and providing feedback: code, documentation, workflows… Please let us know on the mailing list!

Install the pre-release with: 

pip install --pre --upgrade gensim

What will change between this pre-release and a "full" 4.0 release?

Production stability is important to Gensim, so we're improving the process of upgrading already-trained saved models. There'll be an explicit model upgrade script between each 4.n to 4.(n+1) Gensim release. Check progress here.

👍 Improvements

📚 Tutorials and docs

🔴 Bug fixes

  • #2891: Fix fastText word-vectors with ngrams off, by @gojomo
  • #2907: Fix doc2vec crash for large sets of doc-vectors, by @gojomo
  • #2899: Fix similarity bug in NMSLIB indexer, by @piskvorky
  • #2899: Fix deprecation warnings in Annoy integration, by @piskvorky
  • #2901: Fix inheritance of WikiCorpus from TextCorpus, by @jenishah
  • #2940; Fix deprecations in SoftCosineSimilarity, by @Witiko
  • #2944: Fix save_facebook_model failure after update-vocab & other initialization streamlining, by @gojomo
  • #2846: Fix for Python 3.9/3.10: remove xml.etree.cElementTree, by @hugovk
  • #2973: phrases.export_phrases() doesn't yield all bigrams
  • #2942: Segfault when training doc2vec

⚠️ Removed functionality & deprecations

  • #6: No more binary wheels for x32 platforms, by menshikh-iv
  • #2899: Renamed overly broad similarities.index to the more appropriate similarities.annoy, by @piskvorky
  • #2958: Remove gensim.summarization subpackage, docs and test data, by @mpenkov
  • #2926: Rename num_words to topn in dtm_coherence, by @MeganStodel
  • #2937: Remove Keras dependency, by @piskvorky
  • Removed all code, methods, attributes and functions marked as deprecated in Gensim 3.8.3.
  • Removed pattern dependency (PR #3012, @mpenkov). If you need to lemmatize, do it prior to passing the corpus to gensim.

3.8.3, 2020-05-03

⚠️ 3.8.x will be the last Gensim version to support Py2.7. Starting with 4.0.0, Gensim will only support Py3.5 and above.

This is primarily a bugfix release to bring back Py2.7 compatibility to gensim 3.8.

🔴 Bug fixes

  • Bring back Py27 support (PR #2812, @mpenkov)
  • Fix wrong version reported by setup.py (Issue #2796)
  • Fix missing C extensions (Issues #2794 and #2802)

👍 Improvements

📚 Tutorial and doc improvements

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.FastText.load_fasttext_format: use load_facebook_vectors to load embeddings only (faster, less CPU/memory usage, does not support training continuation) and load_facebook_model to load full model (slower, more CPU/memory intensive, supports training continuation)
    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.8.2, 2020-04-10

🔴 Bug fixes

  • Pin smart_open version for compatibility with Py2.7

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.FastText.load_fasttext_format: use load_facebook_vectors to load embeddings only (faster, less CPU/memory usage, does not support training continuation) and load_facebook_model to load full model (slower, more CPU/memory intensive, supports training continuation)
    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.8.1, 2019-09-23

🔴 Bug fixes

  • Fix usage of base_dir instead of BASE_DIR in _load_info in downloader. (movb, #2605)
  • Update the version of smart_open in the setup.py file (AMR-KELEG, #2582)
  • Properly handle unicode_errors arg parameter when loading a vocab file (wmtzk, #2570)
  • Catch loading older TfidfModels without smartirs (bnomis, #2559)
  • Fix bug where a module import set up logging, pin doctools for Py2 (piskvorky, #2552)

📚 Tutorial and doc improvements

👍 Improvements

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.FastText.load_fasttext_format: use load_facebook_vectors to load embeddings only (faster, less CPU/memory usage, does not support training continuation) and load_facebook_model to load full model (slower, more CPU/memory intensive, supports training continuation)
    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.8.0, 2019-07-08

🌟 New Features

  • Enable online training of Poincare models (koiizukag, #2505)
  • Make BM25 more scalable by adding support for generator inputs (saraswatmks, #2479)
  • Allow the Gensim dataset / pre-trained model downloader gensim.downloader to run offline, by introducing a local file cache (mpenkov, #2545)
  • Make the gensim.downloader target directory configurable (mpenkov, #2456)
  • Add nmslib indexer (masa3141, #2417)

🔴 Bug fixes

  • Fix smart_open deprecation warning globally (itayB, #2530)
  • Fix AppVeyor issues with Windows and Py2 (mpenkov, #2546)
  • Fix topn=0 versus topn=None bug in most_similar, accept topn of any integer type (Witiko, #2497)
  • Fix Python version check (charsyam, #2547)
  • Fix typo in FastText documentation (Guitaricet, #2518)
  • Fix "Market Matrix" to "Matrix Market" typo. (Shooter23, #2513)
  • Fix auto-generated hyperlinks in CHANGELOG.md (mpenkov, #2482)

📚 Tutorial and doc improvements

  • Generate documentation for the gensim.similarities.termsim module (Witiko, #2485)
  • Simplify the Support section in README (piskvorky, #2542)

👍 Improvements

  • Pin sklearn version for Py2, because sklearn dropped py2 support (mpenkov, #2510)

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.FastText.load_fasttext_format: use load_facebook_vectors to load embeddings only (faster, less CPU/memory usage, does not support training continuation) and load_facebook_model to load full model (slower, more CPU/memory intensive, supports training continuation)
    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.7.3, 2019-05-06

🔴 Bug fixes

📚 Tutorial and doc improvements

👍 Improvements

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.FastText.load_fasttext_format: use load_facebook_vectors to load embeddings only (faster, less CPU/memory usage, does not support training continuation) and load_facebook_model to load full model (slower, more CPU/memory intensive, supports training continuation)
    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.7.2, 2019-04-06

🌟 New Features

  • gensim.models.fasttext.load_facebook_model function: load full model (slower, more CPU/memory intensive, supports training continuation)
  • gensim.models.fasttext.load_facebook_vectors function: load embeddings only (faster, less CPU/memory usage, does not support training continuation)

🔴 Bug fixes

  • Fix unicode error when loading FastText vocabulary (@mpenkov, #2390)
  • Avoid division by zero in fasttext_inner.pyx (@mpenkov, #2404)
  • Avoid incorrect filename inference when loading model (@mpenkov, #2408)
  • Handle invalid unicode when loading native FastText models (@mpenkov, #2411)
  • Avoid divide by zero when calculating vectors for terms with no ngrams (@mpenkov, #2411)

📚 Tutorial and doc improvements

👍 Improvements

⚠️ Changes in FastText behavior

Out-of-vocab word handling

To achieve consistency with the reference implementation from Facebook,
a FastText model will now always report any word, out-of-vocabulary or
not, as being in the model, and always return some vector for any word
looked-up. Specifically:

  1. 'any_word' in ft_model will always return True. Previously, it
    returned True only if the full word was in the vocabulary. (To test if a
    full word is in the known vocabulary, you can consult the wv.vocab
    property: 'any_word' in ft_model.wv.vocab will return False if the full
    word wasn't learned during model training.)
  2. ft_model['any_word'] will always return a vector. Previously, it
    raised KeyError for OOV words when the model had no vectors
    for any ngrams of the word.
  3. If no ngrams from the term are present in the model,
    or when no ngrams could be extracted from the term, a vector pointing
    to the origin will be returned. Previously, a vector of NaN (not a number)
    was returned as a consequence of a divide-by-zero problem.
  4. Models may use more more memory, or take longer for word-vector
    lookup, especially after training on smaller corpuses where the previous
    non-compliant behavior discarded some ngrams from consideration.

Loading models in Facebook .bin format

The gensim.models.FastText.load_fasttext_format function (deprecated) now loads the entire model contained in the .bin file, including the shallow neural network that enables training continuation.
Loading this NN requires more CPU and RAM than previously required.

Since this function is deprecated, consider using one of its alternatives (see below).

Furthermore, you must now pass the full path to the file to load, including the file extension.
Previously, if you specified a model path that ends with anything other than .bin, the code automatically appended .bin to the path before loading the model.
This behavior was confusing, so we removed it.

⚠️ Deprecations (will be removed in the next major release)

Remove:

  • gensim.models.FastText.load_fasttext_format: use load_facebook_vectors to load embeddings only (faster, less CPU/memory usage, does not support training continuation) and load_facebook_model to load full model (slower, more CPU/memory intensive, supports training continuation)

3.7.1, 2019-01-31

👍 Improvements

🔴 Bug fixes

  • Fix infinite diff in LdaModel.do_mstep (@horpto, #2344)
  • Fix backward compatibility issue: loading FastTextKeyedVectors using KeyedVectors (missing attribute compatible_hash) (@menshikh-iv, #2349)
  • Fix logging issue (conda-forge related) (@menshikh-iv, #2339)
  • Fix WordEmbeddingsKeyedVectors.most_similar (@Witiko, #2356)
  • Fix issues of flake8==3.7.1 (@horpto, #2365)

📚 Tutorial and doc improvements

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.7.0, 2019-01-18

🌟 New features

  • Fast Online NMF (@anotherbugmaster, #2007)

    • Benchmark wiki-english-20171001

      Model Perplexity Coherence L2 norm Train time (minutes)
      LDA 4727.07 -2.514 7.372 138
      NMF 975.74 -2.814 7.265 73
      NMF (with regularization) 985.57 -2.436 7.269 441

    • Simple to use (same interface as LdaModel) 

      from gensim.models.nmf import Nmf
from gensim.corpora import Dictionary
import gensim.downloader as api

text8 = api.load('text8')

dictionary = Dictionary(text8)
dictionary.filter_extremes()

corpus = [
    dictionary.doc2bow(doc) for doc in text8
]

nmf = Nmf(
    corpus=corpus,
    num_topics=5,
    id2word=dictionary,
    chunksize=2000,
    passes=5,
    random_state=42,
)

nmf.show_topics()
"""
[(0, '0.007*"km" + 0.006*"est" + 0.006*"islands" + 0.004*"league" + 0.004*"rate" + 0.004*"female" + 0.004*"economy" + 0.003*"male" + 0.003*"team" + 0.003*"elections"'),
 (1, '0.006*"actor" + 0.006*"player" + 0.004*"bwv" + 0.004*"writer" + 0.004*"actress" + 0.004*"singer" + 0.003*"emperor" + 0.003*"jewish" + 0.003*"italian" + 0.003*"prize"'),
 (2, '0.036*"college" + 0.007*"institute" + 0.004*"jewish" + 0.004*"universidad" + 0.003*"engineering" + 0.003*"colleges" + 0.003*"connecticut" + 0.003*"technical" + 0.003*"jews" + 0.003*"universities"'),
 (3, '0.016*"import" + 0.008*"insubstantial" + 0.007*"y" + 0.006*"soviet" + 0.004*"energy" + 0.004*"info" + 0.003*"duplicate" + 0.003*"function" + 0.003*"z" + 0.003*"jargon"'),
 (4, '0.005*"software" + 0.004*"games" + 0.004*"windows" + 0.003*"microsoft" + 0.003*"films" + 0.003*"apple" + 0.003*"video" + 0.002*"album" + 0.002*"fiction" + 0.002*"characters"')]
"""

    • See also:

  • Massive improvementFastText compatibilities (@mpenkov, #2313) 

    from gensim.models import FastText

# 'cc.ru.300.bin' - Russian Facebook FT model trained on Common Crawl
# Can be downloaded from https://s3-us-west-1.amazonaws.com/fasttext-vectors/word-vectors-v2/cc.ru.300.bin.gz

model = FastText.load_fasttext_format("cc.ru.300.bin")

# Fixed hash-function allow to produce same output as FB FastText & works correctly for non-latin languages (for example, Russian)
assert "мяу" in m.wv.vocab  # 'мяу' - vocab word
model.wv.most_similar("мяу")
"""
[('Мяу', 0.6820122003555298),
 ('МЯУ', 0.6373013257980347),
 ('мяу-мяу', 0.593108594417572),
 ('кис-кис', 0.5899622440338135),
 ('гав', 0.5866007804870605),
 ('Кис-кис', 0.5798211097717285),
 ('Кис-кис-кис', 0.5742273330688477),
 ('Мяу-мяу', 0.5699705481529236),
 ('хрю-хрю', 0.5508339405059814),
 ('ав-ав', 0.5479759573936462)]
"""

assert "котогород" not in m.wv.vocab  # 'котогород' - out-of-vocab word
model.wv.most_similar("котогород", topn=3)
"""
[('автогород', 0.5463314652442932),
 ('ТагилНовокузнецкНовомосковскНовороссийскНовосибирскНовотроицкНовочеркасскНовошахтинскНовый',
  0.5423436164855957),
 ('областьНовосибирскБарабинскБердскБолотноеИскитимКарасукКаргатКуйбышевКупиноОбьТатарскТогучинЧерепаново',
  0.5377570390701294)]
"""

# Now we load full model, for this reason, we can continue an training

from gensim.test.utils import datapath
from smart_open import smart_open

with smart_open(datapath("crime-and-punishment.txt"), encoding="utf-8") as infile:  # russian text
    corpus = [line.strip().split() for line in infile]

model.train(corpus, total_examples=len(corpus), epochs=5)

  • Similarity search improvements (@Witiko, #2016)

    • Add similarity search using the Levenshtein distance in gensim.similarities.LevenshteinSimilarityIndex

    • Performance optimizations to gensim.similarities.SoftCosineSimilarity (full benchmark)

      dictionary size corpus size speed
      1000 100 1.0×
      1000 1000 53.4×
      1000 100000 156784.8×
      100000 100 3.8×
      100000 1000 405.8×
      100000 100000 66262.0×

    • See updated soft-cosine tutorial for more information and usage examples

  • Add python3.7 support (@menshikh-iv, #2211)

👍 Improvements

Optimizations
  • Reduce Phraser memory usage (drop frequencies) (@jenishah, #2208)
  • Reduce memory consumption of summarizer (@horpto, #2298)
  • Replace inline slow equivalent of mean_absolute_difference with fast (@horpto, #2284)
  • Reuse precalculated updated prior in ldamodel.update_dir_prior (@horpto, #2274)
  • Improve KeyedVector.wmdistance (@horpto, #2326)
  • Optimize remove_unreachable_nodes in gensim.summarization (@horpto, #2263)
  • Optimize mz_entropy from gensim.summarization (@horpto, #2267)
  • Improve filter_extremes methods in Dictionary and HashDictionary (@horpto, #2303)
Additions
Cleanup

🔴 Bug fixes

📚 Tutorial and doc improvements

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.6.0, 2018-09-20

🌟 New features

  • File-based training for *2Vec models (@persiyanov, #2127 & #2078 & #2048)

    New training mode for *2Vec models (word2vec, doc2vec, fasttext) that allows model training to scale linearly with the number of cores (full GIL elimination). The result of our Google Summer of Code 2018 project by Dmitry Persiyanov.

    Benchmark

    • Dataset: full English Wikipedia
    • Cloud: GCE
    • CPU: Intel(R) Xeon(R) CPU @ 2.30GHz 32 cores
    • BLAS: MKL
    Model Queue-based version [sec] File-based version [sec] speed up Accuracy (queue-based) Accuracy (file-based)
    Word2Vec 9230 2437 3.79x 0.754 (± 0.003) 0.750 (± 0.001)
    Doc2Vec 18264 2889 6.32x 0.721 (± 0.002) 0.683 (± 0.003)
    FastText 16361 10625 1.54x 0.642 (± 0.002) 0.660 (± 0.001)

    Usage: 

    import gensim.downloader as api
from multiprocessing import cpu_count
from gensim.utils import save_as_line_sentence
from gensim.test.utils import get_tmpfile
from gensim.models import Word2Vec, Doc2Vec, FastText


# Convert any corpus to the needed format: 1 document per line, words delimited by " "
corpus = api.load("text8")
corpus_fname = get_tmpfile("text8-file-sentence.txt")
save_as_line_sentence(corpus, corpus_fname)

# Choose num of cores that you want to use (let's use all, models scale linearly now!)
num_cores = cpu_count()

# Train models using all cores
w2v_model = Word2Vec(corpus_file=corpus_fname, workers=num_cores)
d2v_model = Doc2Vec(corpus_file=corpus_fname, workers=num_cores)
ft_model = FastText(corpus_file=corpus_fname, workers=num_cores)

    Read notebook tutorial with full description.

👍 Improvements

🔴 Bug fixes

📚 Tutorial and doc improvements

  • Update docstring with new analogy evaluation method (@akutuzov, #2130)
  • Improve prune_at parameter description for gensim.corpora.Dictionary (@yxonic, #2128)
  • Fix default -> auto prior parameter in documentation for lda-related models (@Laubeee, #2156)
  • Use heading instead of bold style in gensim.models.translation_matrix (@nzw0301, #2164)
  • Fix quote of vocabulary from gensim.models.Word2Vec (@nzw0301, #2161)
  • Replace deprecated parameters with new in docstring of gensim.models.Doc2Vec (@xuhdev, #2165)
  • Fix formula in Mallet documentation (@Laubeee, #2186)
  • Fix minor semantic issue in docs for Phrases (@RunHorst, #2148)
  • Fix typo in documentation (@KenjiOhtsuka, #2157)
  • Additional documentation fixes (@piskvorky, #2121)

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.5.0, 2018-07-06

This release comprises a glorious 38 pull requests from 28 contributors. Most of the effort went into improving the documentation—hence the release code name "Docs 💬"!

Apart from the massive overhaul of all Gensim documentation (including docstring style and examples—you asked for it), we also managed to sneak in some new functionality and a number of bug fixes. As usual, see the notes below for a complete list, with links to pull requests for more details.

Huge thanks to all contributors! Nobody loves working on documentation. 3.5.0 is a result of several months of laborious, unglamorous, and sometimes invisible work. Enjoy!

📚 Documentation improvements

🌟 New features:

  • Add add_entity method to KeyedVectors to allow adding word vectors manually (@persiyanov, #1957)
  • Add inference for new unseen author to AuthorTopicModel (@Stamenov, #1766)
  • Add evaluate_word_analogies (will replace accuracy) method to KeyedVectors (@akutuzov, #1935)
  • Add Pivot Normalization to TfidfModel (@markroxor, #1780)

👍 Improvements

🔴 Bug fixes:

  • Fix Doc2Vec.infer_vector + notebook cleanup (@gojomo, #2103)
  • Fix linear decay for learning rate in Doc2Vec.infer_vector (@umangv, #2063)
  • Fix negative sampling floating-point error for `gensim.models.Poincare (@jayantj, #1959)
  • Fix loading word2vec and doc2vec models saved using old Gensim versions (@manneshiva, #2012)
  • Fix SoftCosineSimilarity.get_similarities on corpora ssues/1955) (@Witiko, #1972)
  • Fix return dtype for matutils.unitvec according to input dtype (@o-P-o, #1992)
  • Fix passing empty dictionary to gensim.corpora.WikiCorpus (@steremma, #2042)
  • Fix bug in Similarity.query_shards in multiprocessing case (@bohea, #2044)
  • Fix SMART from TfidfModel for case when df == "n" (@PeteBleackley, #2021)
  • Fix OverflowError when loading a large term-document matrix in compiled MatrixMarket format (@arlenk, #2001)
  • Update rules for removing table markup from Wikipedia dumps (@chaitaliSaini, #1954)
  • Fix _is_single from Phrases for case when corpus is a NumPy array (@rmalouf, #1987)
  • Fix tests for EuclideanKeyedVectors.similarity_matrix (@Witiko, #1984)
  • Fix deprecated parameters in D2VTransformer and W2VTransformer(@MritunjayMohitesh, #1945)
  • Fix Doc2Vec.infer_vector after loading old Doc2Vec (gensim<=3.2)(@manneshiva, #1974)
  • Fix inheritance chain for load_word2vec_format (@DennisChen0307, #1968)
  • Update Keras version (avoid bug from keras==2.1.5) (@menshikh-iv, #1963)

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.4.0, 2018-03-01

🌟 New features:

👍 Improvements:

  • New method to show the Gensim installation parameters: python -m gensim.scripts.package_info --info. Use this when reporting problems, for easier debugging. Fix #1902 (@sharanry, #1903)
  • Added a flag to optionally skip network-related tests, to help maintainers avoid network issues with CI services (@menshikh-iv, #1930)
  • Added license field to setup.py, allowing the use of tools like pip-licenses (@nils-werner, #1909)

🔴 Bug fixes:

📚 Tutorial and doc improvements:

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.3.0, 2018-02-02

🌟 New features:

  • Re-designed all "*2vec" implementations (@manneshiva, #1777)

  • Improve gensim.scripts.segment_wiki by retaining interwiki links. Fix #1712
    (@steremma, PR #1839)

    • Optionally extract interlinks from Wikipedia pages (use the --include-interlinks option). This will output one additional JSON dict for each article: 

      {
    "interlinks": {
        "article title 1": "interlink text 1",
        "article title 2": "interlink text 2",
        ...
    }
}

    • Example: extract the Wikipedia graph with article links as edges, from a raw Wikipedia dump: 

      python -m gensim.scripts.segment_wiki --include-interlinks --file ~/Downloads/enwiki-latest-pages-articles.xml.bz2 --output ~/Desktop/enwiki-latest.jsonl.gz
      • Read this field from the segment_wiki output: 
      import json
from smart_open import smart_open

with smart_open("enwiki-latest.jsonl.gz") as infile:
    for doc in infile:
        doc = json.loads(doc)

        src_node = doc['title']
        dst_nodes = doc['interlinks'].keys()

        print(u"Source node: {}".format(src_node))
        print(u"Destination nodes: {}".format(u", ".join(dst_nodes)))
        break

"""
OUTPUT:

Source node: Anarchism
Destination nodes: anarcha-feminist, Ivan Illich, Adolf Brand, Josiah Warren, will (philosophy), anarcha-feminism, Anarchism in Mexico, Lysander Spooner, English Civil War, G8, Sebastien Faure, Nihilist movement, Sébastien Faure, Left-wing politics, imamate, Pierre Joseph Proudhon, anarchist communism, Università popolare (Italian newspaper), 1848 Revolution, Synthesis anarchism, labour movement, anarchist communists, collectivist anarchism, polyamory, post-humanism, postcolonialism, anti war movement, State (polity), security culture, Catalan people, Stoicism, Progressive education, stateless society, Umberto I of Italy, German language, Anarchist schools of thought, NEFAC, Jacques Ellul, Spanish Communist Party, Crypto-anarchism, ruling class, non-violence, Platformist, The History of Sexuality, Revolutions of 1917–23, Federación Anarquista Ibérica, propaganda of the deed, William B. Greene, Platformism, mutually exclusive, Fraye Arbeter Shtime, Adolf Hitler, oxymoron, Paris Commune, Anarchism in Italy#Postwar years and today, Oranienburg, abstentionism, Free Society, Henry David Thoreau, privative alpha, George I of Greece, communards, Gustav Landauer, Lucifer the Lightbearer, Moses Harman, coercion, regicide, rationalist, Resistance during World War II, Christ (title), Bohemianism, individualism, Crass, black bloc, Spanish Revolution of 1936, Erich Mühsam, Empress Elisabeth of Austria, Free association (communism and anarchism), general strike, Francesc Ferrer i Guàrdia, Catalan anarchist pedagogue and free-thinker, veganarchism, Traditional knowledge, Japanese Anarchist Federation, Diogenes of Sinope, Hierarchy, sexual revolution, Naturism, Bavarian Soviet Republic, February Revolution, Eugene Varlin, Renaissance humanism, Mexican Liberal Party, Friedrich Engels, Fernando Tarrida del Mármol, Caliphate, Marxism, Jesus, John Cage, Umanita Nova, Anarcho-pacifism, Peter Kropotkin, Religious anarchism, Anselme Bellegarrigue, civilisation, moral obligation, hedonist, Free Territory (Ukraine), -ism, neo-liberalism, Austrian School, philosophy, freethought, Joseph Goebbels, Conservatism, anarchist economics, Cavalier, Maximilien de Robespierre, Comstockery, Dorothy Day, Anarchism in France, Fédération anarchiste, World Economic Forum, Amparo Poch y Gascón, Sex Pistols, women's rights, collectivisation, Taoism, common ownership, William Batchelder Greene, Collective farming, popular education, biphobia, targeted killings, Protestant Christianity, state socialism, Marie François Sadi Carnot, Stephen Pearl Andrews, World Trade Organization, Communist Party of Spain (main), Pluto Press, Levante, Spain, Alexander Berkman, Wilhelm Weitling, Kharijites, Bolshevik, Liberty (1881–1908), Anarchist Aragon, social democrats, Dielo Truda, Post-left anarchy, Age of Enlightenment, Blanquism, Walden, mutual aid (organization), Far-left politics, privative, revolutions of 1848, anarchism and nationalism, punk rock, Étienne de La Boétie, Max Stirner, Jacobin (politics), agriculture, anarchy, Confederacion General del Trabajo de España, toleration, reformism, International Anarchist Congress of Amsterdam, The Ego and Its Own, Ukraine, Civil Disobedience (Thoreau), Spanish Civil War, David Graeber, Anarchism and issues related to love and sex, James Guillaume, Insurrectionary anarchism, Political repression, International Workers' Association, Barcelona, Bulgaria, Voline, Zeno of Citium, anarcho-communists, organized religion, libertarianism, bisexuality, Ricardo Flores Magón, Henri Zisly, Eight-hour day, Freetown Christiania, heteronormativity, Mikhail Bakunin, Propagandaministerium, Ezra Heywood, individual reappropriation, Modern School (United States), archon, Confédération nationale du travail, socialist movement, History of Islam, Max Nettlau, Political Justice, Reichstag fire, Anti-Christianity, decentralised, Issues in anarchism#Communism, deschooling, Christian movement, squatter, Anarchism in Germany, Catalonia, Louise Michel, Solidarity Federation, What is Property?, European individualist anarchism, Pierre-Joseph Proudhon, Mexican Revolution, wikt:anarchism, Blackshirts, Jewish anarchism, Russian Civil War, property rights, anti-authoritarian, individual reclamation, propaganda by the deed, from each according to his ability, to each according to his need, Feminist movement, Confiscation, social anarchism, Anarchism in Russia, Daniel Guérin, Uruguayan Anarchist Federation, Anarcha-feminism, Enragés, Cynicism (philosophy), workers' council, The Word (free love), Allen Ginsberg, Campaign for Nuclear Disarmament, antimilitarism, Workers' self-management, Federación Obrera Regional Argentina, self-governance, free market, Carlos I of Portugal, Simon Critchley, Anti-clericalism, heterosexual, Layla AbdelRahim, Mexican Anarchist Federation, Anarchism and Marxism, October Revolution, Anti-nuclear movement, Joseph Déjacque, Bolsheviks, Luigi Fabbri, morality, Communist party, Sam Dolgoff, united front, Ammon Hennacy, social ecology, commune (intentional community), Oscar Wilde, French Revolution, egoist anarchism, Comintern, transphobia, anarchism without adjectives, social control, means of production, Michel Onfray, Anarchism in France#The Fourth Republic (1945–1958), syndicalism, Anarchism in Spain, Iberian Anarchist Federation, International of Anarchist Federations, Emma Goldman, Netherlands, anarchist free school, International Workingmen's Association, Queer anarchism, Cantonal Revolution, trade unionism, Karl Marx, LGBT community, humanism, Anti-fascism, Carrara, political philosophy, Anarcho-transhumanism, libertarian socialist, Russian Revolution (1917), Two Cheers for Anarchism: Six Easy Pieces on Autonomy, Dignity, and Meaningful Work and Play, Emile Armand, insurrectionary anarchism, individual, Zhuang Zhou, Free Territory, White movement, Greenwich Village, Virginia Bolten, transcendentalist, public choice theory, wikt:brigand, Issues in anarchism#Participation in statist democracy, free love, Mutualism (economic theory), Anarchist St. Imier International, censorship, federalist, 6 February 1934 crisis, biennio rosso, anti-clerical, centralism, Anarchism: A Documentary History of Libertarian Ideas, minarchism, James C. Scott, First International, homosexuality, political theology, spontaneous order, Oranienburg concentration camp, anarcho-communism, negative liberty, post-modernism, Anarchism in Italy, Leopold Kohr, union of egoists, counterculture, Miguel Gimenez Igualada, philosophical anarchism, International Libertarian Solidarity, homosexual, Counterculture of the 1960s, Errico Malatesta, strikebreaker, Workers' Party of Marxist Unification, Clifford Harper, Reification (fallacy), patriarchy, anarchist law, Apostle (Christian), market (economics), Summerhill School, positive liberty, socialism, feminism, Direct action, Melchor Rodríguez García, William Godwin, Nazi concentration camps, Synthesist anarchism, Margaret Anderson, Han Ryner, Federation of Organized Trades and Labor Unions, technology, Workers Solidarity Movement, Edmund Burke, Encyclopædia Britannica, state (polity), Herbert Read, Park Güell, utilitarian, far right leagues, Limited government, self-ownership, Pejorative, homophobia, Industrial Workers of the World, The Dispossessed, Hague Congress (1872), Stalinism, Reciprocity (cultural anthropology), Fernand Pelloutier, individualist anarchism in France, The False Principle of our Education, individualist anarchism, Pierre Monatte, Soviet Union, counter-economics, Rudolf Rocker, Anarchism and capitalism, Parma, Black Rose Books, lesbian, Arditi del Popolo, Emile Armand (1872–1962), who propounded the virtues of free love in the Parisian anarchist milieu of the early 20th century, collectivism, Development criticism, John Henry Mackay, Benoît Broutchoux, Illegalism, Laozi, feminist, Christiaan Cornelissen, Syndicalist Workers' Federation, anarcho-syndicalism, Andalusia, Renzo Novatore, trade union, autonomist marxism, dictatorship of the proletariat, Mujeres Libres, Voltairine de Cleyre, Post-anarchism, participatory economics, Confederación Nacional del Trabajo, Syncretic politics, direct democracy, Jean-Jacques Rousseau, Green anarchism, Surrealism, labour unions, A. S. Neill, christian anarchist, Bonnot Gang, Anti-capitalism, Anarchism in Brazil, simple living, enlightened self-interest, Confédération générale du travail, class conflict, International Workers' Day, Hébertists, Gerrard Winstanley, Francoism, anarcho-pacifist, Andrej Grubacic, individualist anarchist and social anarchist thinkers., April Carter, private property, penal colonies, Libertarian socialism, Camillo Berneri, Christian anarchism, transhumanism, Lucifer, the Light-Bearer, Edna St. Vincent Millay, unschooling, Leo Tolstoy, M. E. Lazarus, Spanish Anarchists, Buddhist anarchism, ideology, William McKinley, anarcho-primitivism, Francesc Pi i Margall, :Category:Anarchism by country, International Workers Association, Anarcho-capitalism, Lois Waisbrooker, wikt:Solidarity, Baja California, social revolution, Unione Sindacale Italiana, Lev Chernyi, Alex Comfort, Sonnenburg, Leon Czolgosz, Volin, utopian, Argentine Libertarian Federation, Nudism, Left-wing market anarchism, insurrection, definitional concerns in anarchist theory, infinitive, affinity group, World Trade Organization Ministerial Conference of 1999 protest activity, class struggle, nonviolence, John Zerzan, poststructuralist, Noam Chomsky, Second Fitna, Julian Beck, Philadelphes, League of Peace and Freedom, Fédération Anarchiste, Kronstadt rebellion, Cold War, André Breton, Silvio Gesell, libertarian anarchism, voluntary association, anti-globalisation movement, birth control, L. Susan Brown, anarcho-naturism, personal property, Roundhead, Harold Barclay, The Joy of Sex, Council communism, Lucía Sánchez Saornil, tyrannicide, Neopaganism, lois scélérates, Johann Most, Anarchist Catalonia, Albert Camus, Protests of 1968, Alexander II of Russia, Spain's economy, Federazione Anarchica Italiana, Cuba, German Revolution of 1918–1919, stirner, Property is theft, Situationist International, law and economics

  • Add support for SMART notation for TfidfModel. Fix #1785 (@markroxor, #1791)

    • Natural extension of TfidfModel to allow different weighting and normalization schemes 
      from gensim.corpora import Dictionary
from gensim.models import TfidfModel
import gensim.downloader as api

data = api.load("text8")
dct = Dictionary(data)
corpus = [dct.doc2bow(line) for line in data]

# Train Tfidf model using the SMART notation, smartirs="ntc" where
# 'n' - natural term frequency
# 't' - idf document frequency
# 'c' - cosine normalization
#
# More information about possible values available in documentation or https://nlp.stanford.edu/IR-book/html/htmledition/document-and-query-weighting-schemes-1.html

model = TfidfModel(corpus, id2word=dct, smartirs="ntc")
vectorized_corpus = list(model[corpus])
    • SMART Information Retrieval System (wiki)

  • Add CircleCI for building Gensim documentation. Fix #1807 (@menshikh-iv, #1822)

    • An easy way to preview the rendered documentation (especially, if don't use Linux)
      • Go to "Details" link of CircleCI in your PR, click on the "Artifacts" tab, choose the HTML file that you want to view; a new tab will open with the rendered HTML page
    • Integration with Github, to see the documentation directly from the pull request page

🔴 Bug fixes:

📚 Tutorial and doc improvements:

👍 Improvements:

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.models.wrappers.fasttext (obsoleted by the new native gensim.models.fasttext implementation)
    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki (all of these obsoleted by the new native gensim.scripts.segment_wiki implementation)
    • "deprecated" functions and attributes

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.2.0, 2017-12-09

🌟 New features:

  • New download API for corpora and pre-trained models (@chaitaliSaini & @menshikh-iv, #1705 & #1632 & #1492)

    • Download large NLP datasets in one line of Python, then use with memory-efficient data streaming: 
      import gensim.downloader as api

for article in api.load("wiki-english-20171001"):
    pass
    • Don’t waste time searching for good word embeddings, use the curated ones we included: 
      import gensim.downloader as api

model = api.load("glove-twitter-25")
model.most_similar("engineer")

# [('specialist', 0.957542896270752),
#  ('developer', 0.9548177123069763),
#  ('administrator', 0.9432312846183777),
#  ('consultant', 0.93915855884552),
#  ('technician', 0.9368376135826111),
#  ('analyst', 0.9342101216316223),
#  ('architect', 0.9257484674453735),
#  ('engineering', 0.9159940481185913),
#  ('systems', 0.9123805165290833),
#  ('consulting', 0.9112802147865295)]
    • Blog post introducing the API and design decisions.
    • Notebook with examples

  • New model: Poincaré embeddings (@jayantj, #1696 & #1700 & #1757 & #1734)

    • Embed a graph (taxonomy) in the same way as word2vec embeds words: 
      from gensim.models.poincare import PoincareRelations, PoincareModel
from gensim.test.utils import datapath

data = PoincareRelations(datapath('poincare_hypernyms.tsv'))
model = PoincareModel(data)
model.kv.most_similar("cat.n.01")

# [('kangaroo.n.01', 0.010581353439700418),
# ('gib.n.02', 0.011171531439892076),
# ('striped_skunk.n.01', 0.012025106076442395),
# ('metatherian.n.01', 0.01246679759214648),
# ('mammal.n.01', 0.013281303506525968),
# ('marsupial.n.01', 0.013941330203709653)]
    • Tutorial notebook on Poincaré embeddings
    • Model introduction and the journey of its implementation
    • Original paper on arXiv

  • Optimized FastText (@manneshiva, #1742)

    • New fast multithreaded implementation of FastText, natively in Python/Cython. Deprecates the existing wrapper for Facebook’s C++ implementation. 
      import gensim.downloader as api
from gensim.models import FastText

model = FastText(api.load("text8"))
model.most_similar("cat")

# [('catnip', 0.8538144826889038),
#  ('catwalk', 0.8136177062988281),
#  ('catchy', 0.7828493118286133),
#  ('caf', 0.7826495170593262),
#  ('bobcat', 0.7745151519775391),
#  ('tomcat', 0.7732658386230469),
#  ('moat', 0.7728310823440552),
#  ('caye', 0.7666271328926086),
#  ('catv', 0.7651021480560303),
#  ('caveat', 0.7643581628799438)]

  • Binary pre-compiled wheels for Windows, OSX and Linux (@menshikh-iv, MacPython/gensim-wheels/#7)

    • Users no longer need to have a C compiler for using the fast (Cythonized) version of word2vec, doc2vec, etc.
    • Faster Gensim pip installation

  • Added DeprecationWarnings to deprecated methods and parameters, with a clear schedule for removal.

👍 Improvements:

🔴 Bug fixes:

📚 Tutorial and doc improvements:

⚠️ Deprecations (will be removed in the next major release)

  • Remove

    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

3.1.0, 2017-11-06

🌟 New features:

  • Massive optimizations to LSI model training (@isamaru, #1620 & #1622)
    • LSI model allows use of single precision (float32), to consume 40% less memory while being 40% faster.
    • LSI model can now also accept CSC matrix as input, for further memory and speed boost.
    • Overall, if your entire corpus fits in RAM: 3x faster LSI training (SVD) in 4x less memory! 
      # just an example; the corpus stream is up to you
streaming_corpus = gensim.corpora.MmCorpus("my_tfidf_corpus.mm.gz")

# convert your corpus to a CSC sparse matrix (assumes the entire corpus fits in RAM)
in_memory_csc_matrix = gensim.matutils.corpus2csc(streaming_corpus, dtype=np.float32)

# then pass the CSC to LsiModel directly
model = LsiModel(corpus=in_memory_csc_matrix, num_topics=500, dtype=np.float32)
    • Even if you continue to use streaming corpora (your training dataset is too large for RAM), you should see significantly faster processing times and a lower memory footprint. In our experiments with a very large LSI model, we saw a drop from 29 GB peak RAM and 38 minutes (before) to 19 GB peak RAM and 26 minutes (now): 
      model = LsiModel(corpus=streaming_corpus, num_topics=500, dtype=np.float32)
  • Add common terms to Phrases. Fix #1258 (@alexgarel, #1568)
    • Phrases allows to use common terms in bigrams. Before, if you are searching to reveal ngrams like car_with_driver and car_without_driver, you can either remove stop words before processing, but you will only find car_driver, or you won't find any of those forms (because they have three words, but also because high frequency of with will avoid them to be scored correctly), inspired by ES common grams token filter. 
      phr_old = Phrases(corpus)
phr_new = Phrases(corpus, common_terms=stopwords.words('en'))

print(phr_old[["we", "provide", "car", "with", "driver"]])  # ["we", "provide", "car_with", "driver"]
print(phr_new[["we", "provide", "car", "with", "driver"]])  # ["we", "provide", "car_with_driver"]
  • New segment_wiki.py script (@menshikh-iv, #1483 & #1694)

    • CLI script for processing a raw Wikipedia dump (the xml.bz2 format provided by WikiMedia) to extract its articles in a plain text format. It extracts each article's title, section names and section content and saves them as json-line: 

      python -m gensim.scripts.segment_wiki -f enwiki-latest-pages-articles.xml.bz2 | gzip > enwiki-latest-pages-articles.json.gz

      Processing the entire English Wikipedia dump (13.5 GB, link here) takes about 2.5 hours (i7-6700HQ, SSD).

      The output format is one article per line, serialized into JSON: 

         for line in smart_open('enwiki-latest-pages-articles.json.gz'):  # read the file we just created
       article = json.loads(line)
       print("Article title: %s" % article['title'])
       for section_title, section_text in zip(article['section_titles'], article['section_texts']):
           print("Section title: %s" % section_title)
           print("Section text: %s" % section_text)
 ```

👍 Improvements:

🔴 Bug fixes:

📚 Tutorial and doc improvements:

⚠️ Deprecation part (will come into force in the next major release)

  • Remove

    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

Also, we'll create experimental subpackage for unstable models. Specific lists will be available in the next major release.

3.0.1, 2017-10-12

🔴 Bug fixes:

📚 Tutorial and doc improvements:

⚠️ Deprecation part (will come into force in the next release)

  • Remove

    • gensim.examples
    • gensim.nosy
    • gensim.scripts.word2vec_standalone
    • gensim.scripts.make_wiki_lemma
    • gensim.scripts.make_wiki_online
    • gensim.scripts.make_wiki_online_lemma
    • gensim.scripts.make_wiki_online_nodebug
    • gensim.scripts.make_wiki

  • Move

    • gensim.scripts.make_wikicorpus ➡ gensim.scripts.make_wiki.py
    • gensim.summarization ➡ gensim.models.summarization
    • gensim.topic_coherence ➡ gensim.models._coherence
    • gensim.utils ➡ gensim.utils.utils (old imports will continue to work)
    • gensim.parsing.* ➡ gensim.utils.text_utils

Also, we'll create experimental subpackage for unstable models. Specific lists will be available in the next release.

3.0.0, 2017-09-27

🌟 New features:

👍 Improvements:

🔴 Bug fixes:

📚 Tutorial and doc improvements:

2.3.0, 2017-07-25

🌟 New features:

👍 Improvements:

🔴 Bug fixes:

📚 Tutorial and doc improvements:

2.2.0, 2017-06-21

🌟 New features:

👍 Improvements:

🔴 Bug fixes:

📚 Tutorial and doc improvements:

2.1.0, 2017-05-12

🌟 New features:

  • Add modified save_word2vec_format for Doc2Vec, to save document vectors. (@parulsethi, #1256)

👍 Improvements:

  • Add automatic code style check limited only to the code modified in PR (@tmylk, #1287)
  • Replace logger.warn by logger.warning (@chinmayapancholi13, #1295)
  • Docs word2vec docstring improvement, deprecation labels (@shubhvachher, #1274)
  • Stop passing 'sentences' as parameter to Doc2Vec. Fix #511 (@gogokaradjov, #1306)

🔴 Bug fixes:

  • Allow indexing with np.int64 in doc2vec. Fix #1231 (@bogdanteleaga, #1254)
  • Update Doc2Vec docstring. Fix #1302 (@datapythonista, #1307)
  • Ignore rst and ipynb file in Travis flake8 validations (@datapythonista, #1309)

📚 Tutorial and doc improvements:

2.0.0, 2017-04-10

Breaking changes:

Any direct calls to method train() of Word2Vec/Doc2Vec now require an explicit epochs parameter and explicit estimate of corpus size. The most usual way to call train is vec_model.train(sentences, total_examples=self.corpus_count, epochs=self.iter)
See the method documentation for more information.

New features:

Improvements:

  • Fix loading large FastText models on Mac. (@jaksmid, #1196)
  • Sklearn LDA wrapper now works in sklearn pipeline (@kris-singh, #1213)
  • glove2word2vec conversion script refactoring (@parulsethi, #1247)
  • Word2vec error message when update called before train . Fix #1162 (@hemavakade, #1205)
  • Allow training if model is not modified by "_minimize_model". Add deprecation warning. (@chinmayapancholi13, #1207)
  • Update the warning text when building vocab on a trained w2v model (@prakhar2b, #1190)

Bug fixes:

  • Fix word2vec reset_from bug in v1.0.1 Fix #1230. (@Kreiswolke, #1234)

  • Distributed LDA: checking the length of docs instead of the boolean value, plus int index conversion (@saparina, #1191)

  • syn0_lockf initialised with zero in intersect_word2vec_format() (@KiddoZhu, #1267)

  • Fix wordrank max_iter_dump calculation. Fix #1216 (@ajkl, #1217)

  • Make SgNegative test use skip-gram (@shubhvachher, #1252)

  • pep8/pycodestyle fixes for hanging indents in Summarization module (@SamriddhiJain, #1202)

  • WordRank and Mallet wrappers single vs double quote issue in windows. (@prakhar2b, #1208)

  • Fix #824 : no corpus in init, but trim_rule in init (@prakhar2b, #1186)

  • Hardcode version number. Fix #1138. (@tmylk, #1138)

Tutorial and doc improvements:

  • Color dictionary according to topic notebook update (@bhargavvader, #1164)

  • Fix hdp show_topic/s docstring (@parulsethi, #1264)

  • Add docstrings for word2vec.py forwarding functions (@shubhvachher, #1251)

  • updated description for worker_loop function used in score function (@chinmayapancholi13, #1206)

1.0.1, 2017-03-03

  • Rebuild cumulative table on load. Fix #1180. (@tmylk, #1181)
  • most_similar_cosmul bug fix (@dkim010, #1177)
  • Fix loading old word2vec models pre-1.0.0 (@jayantj, #1179)
  • Load utf-8 words in fasttext (@jayantj, #1176)

1.0.0, 2017-02-24

New features:

  • Add Author-topic modeling (@olavurmortensen, #893)
  • Add FastText word embedding wrapper (@jayantj, #847)
  • Add WordRank word embedding wrapper (@parulsethi, #1066, #1125)
  • Add VarEmbed word embedding wrapper (@anmol01gulati, #1067))
  • Add sklearn wrapper for LDAModel (@AadityaJ, #932)

Deprecated features:

  • Move load_word2vec_format and save_word2vec_format out of Word2Vec class to KeyedVectors (@tmylk, #1107)
  • Move properties syn0norm, syn0, vocab, index2word from Word2Vec class to KeyedVectors (@tmylk,#1147)
  • Remove support for Python 2.6, 3.3 and 3.4 (@tmylk,#1145)

Improvements:

  • Python 3.6 support (@tmylk #1077)
  • Phrases and Phraser allow a generator corpus (ELind77 #1099)
  • Ignore DocvecsArray.doctag_syn0norm in save. Fix #789 (@accraze, #1053)
  • Fix bug in LsiModel that occurs when id2word is a Python 3 dictionary. (@cvangysel, #1103
  • Fix broken link to paper in readme (@bhargavvader, #1101)
  • Lazy formatting in evaluate_word_pairs (@akutuzov, #1084)
  • Deacc option to keywords pre-processing (@bhargavvader, #1076)
  • Generate Deprecated exception when using Word2Vec.load_word2vec_format (@tmylk, #1165)
  • Fix hdpmodel constructor docstring for print_topics (#1152) (@toliwa, #1152)
  • Default to per_word_topics=False in LDA get_item for performance (@menshikh-iv, #1154)
  • Fix bound computation in Author Topic models. (@olavurmortensen, #1156)
  • Write UTF-8 byte strings in tensorboard conversion (@tmylk, #1144)
  • Make top_topics and sparse2full compatible with numpy 1.12 strictly int idexing (@tmylk, #1146)

Tutorial and doc improvements:

  • Clarifying comment in is_corpus func in utils.py (@greninja, #1109)
  • Tutorial Topics_and_Transformations fix markdown and add references (@lgmoneda, #1120)
  • Fix doc2vec-lee.ipynb results to match previous behavior (@bahbbc, #1119)
  • Remove Pattern lib dependency in News Classification tutorial (@luizcavalcanti, #1118)
  • Corpora_and_Vector_Spaces tutorial text clarification (@lgmoneda, #1116)
  • Update Transformation and Topics link from quick start notebook (@mariana393, #1115)
  • Quick Start Text clarification and typo correction (@luizcavalcanti, #1114)
  • Fix typos in Author-topic tutorial (@Fil, #1102)
  • Address benchmark inconsistencies in Annoy tutorial (@droudy, #1113)
  • Add note about Annoy speed depending on numpy BLAS setup in annoytutorial.ipynb (@greninja, #1137)
  • Fix dependencies description on doc2vec-IMDB notebook (@luizcavalcanti, #1132)
  • Add documentation for WikiCorpus metadata. (@kirit93, #1163)

1.0.0RC2, 2017-02-16

  • Add note about Annoy speed depending on numpy BLAS setup in annoytutorial.ipynb (@greninja, #1137)
  • Remove direct access to properties moved to KeyedVectors (@tmylk, #1147)
  • Remove support for Python 2.6, 3.3 and 3.4 (@tmylk, #1145)
  • Write UTF-8 byte strings in tensorboard conversion (@tmylk, #1144)
  • Make top_topics and sparse2full compatible with numpy 1.12 strictly int idexing (@tmylk, #1146)

1.0.0RC1, 2017-01-31

New features:

  • Add Author-topic modeling (@olavurmortensen, #893)
  • Add FastText word embedding wrapper (@jayantj, #847)
  • Add WordRank word embedding wrapper (@parulsethi, #1066, #1125)
  • Add sklearn wrapper for LDAModel (@AadityaJ, #932)

Improvements:

  • Python 3.6 support (@tmylk #1077)
  • Phrases and Phraser allow a generator corpus (ELind77 #1099)
  • Ignore DocvecsArray.doctag_syn0norm in save. Fix #789 (@accraze, #1053)
  • Move load and save word2vec_format out of word2vec class to KeyedVectors (@tmylk, #1107)
  • Fix bug in LsiModel that occurs when id2word is a Python 3 dictionary. (@cvangysel, #1103
  • Fix broken link to paper in readme (@bhargavvader, #1101)
  • Lazy formatting in evaluate_word_pairs (@akutuzov, #1084)
  • Deacc option to keywords pre-processing (@bhargavvader, #1076)

Tutorial and doc improvements:

  • Clarifying comment in is_corpus func in utils.py (@greninja, #1109)
  • Tutorial Topics_and_Transformations fix markdown and add references (@lgmoneda, #1120)
  • Fix doc2vec-lee.ipynb results to match previous behavior (@bahbbc, #1119)
  • Remove Pattern lib dependency in News Classification tutorial (@luizcavalcanti, #1118)
  • Corpora_and_Vector_Spaces tutorial text clarification (@lgmoneda, #1116)
  • Update Transformation and Topics link from quick start notebook (@mariana393, #1115)
  • Quick Start Text clarification and typo correction (@luizcavalcanti, #1114)
  • Fix typos in Author-topic tutorial (@Fil, #1102)
  • Address benchmark inconsistencies in Annoy tutorial (@droudy, #1113)

0.13.4.1, 2017-01-04

  • Disable direct access warnings on save and load of Word2vec/Doc2vec (@tmylk, #1072)
  • Making Default hs error explicit (@accraze, #1054)
  • Removed unnecessary numpy imports (@bhargavvader, #1065)
  • Utils and Matutils changes (@bhargavvader, #1062)
  • Tests for the evaluate_word_pairs function (@akutuzov, #1061)

0.13.4, 2016-12-22

  • Added suggested lda model method and print methods to HDP class (@bhargavvader, #1055)
  • New class KeyedVectors to store embedding separate from training code (@anmol01gulati and @droudy, #980)
  • Evaluation of word2vec models against semantic similarity datasets like SimLex-999 (@akutuzov, #1047)
  • TensorBoard word embedding visualisation of Gensim Word2vec format (@loretoparisi, #1051)
  • Throw exception if load() is called on instance rather than the class in word2vec and doc2vec (@dust0x, #889)
  • Loading and Saving LDA Models across Python 2 and 3. Fix #853 (@anmolgulati, #913, #1093)
  • Fix automatic learning of eta (prior over words) in LDA (@olavurmortensen, #1024).
    • eta should have dimensionality V (size of vocab) not K (number of topics). eta with shape K x V is still allowed, as the user may want to impose specific prior information to each topic.
    • eta is no longer allowed the "asymmetric" option. Asymmetric priors over words in general are fine (learned or user defined).
    • As a result, the eta update (update_eta) was simplified some. It also no longer logs eta when updated, because it is too large for that.
    • Unit tests were updated accordingly. The unit tests expect a different shape than before; some unit tests were redundant after the change; eta='asymmetric' now should raise an error.
  • Optimise show_topics to only call get_lambda once. Fix #1006. (@bhargavvader, #1028)
  • HdpModel doc improvement. Inference and print_topics (@dsquareindia, #1029)
  • Removing Doc2Vec defaults so that it won't override Word2Vec defaults. Fix #795. (@markroxor, #929)
  • Remove warning on gensim import "pattern not installed". Fix #1009 (@shashankg7, #1018)
  • Add delete_temporary_training_data() function to word2vec and doc2vec models. (@deepmipt-VladZhukov, #987)
  • Documentation improvements (@IrinaGoloshchapova, #1010, #1011)
  • LDA tutorial by Olavur, tips and tricks (@olavurmortensen, #779)
  • Add double quote in commmand line to run on Windows (@akarazeev, #1005)
  • Fix directory names in notebooks to be OS-independent (@mamamot, #1004)
  • Respect clip_start, clip_end in most_similar. Fix #601. (@parulsethi, #994)
  • Replace Python sigmoid function with scipy in word2vec & doc2vec (@markroxor, #989)
  • WMD to return 0 instead of inf for sentences that contain a single word (@rbahumi, #986)
  • Pass all the params through the apply call in lda.get_document_topics(), test case to use the per_word_topics through the corpus in test_ldamodel (@parthoiiitm, #978)
  • Pyro annotations for lsi_worker (@markroxor, #968)

0.13.3, 2016-10-20

  • Add vocabulary expansion feature to word2vec. (@isohyt, #900)
  • Tutorial: Reproducing Doc2vec paper result on wikipedia. (@isohyt, #654)
  • Add Save/Load interface to AnnoyIndexer for index persistence (@fortiema, #845)
  • Fixed issue #938,Creating a unified base class for all topic models. (@markroxor, #946)
    • breaking change in HdpTopicFormatter.show_topics
  • Add Phraser for Phrases optimization. ( @gojomo & @anujkhare , #837)
  • Fix issue #743, in word2vec's n_similarity method if at least one empty list is passed ZeroDivisionError is raised (@pranay360, #883)
  • Change export_phrases in Phrases model. Fix issue #794 (@AadityaJ, #879)
    • bigram construction can now support multiple bigrams within one sentence
  • Fix issue #838, RuntimeWarning: overflow encountered in exp (@markroxor, #895)
  • Change some log messages to warnings as suggested in issue #828. (@rhnvrm, #884)
  • Fix issue #851, In summarizer.py, RunTimeError is raised if single sentence input is provided to avoid ZeroDivionError. (@metalaman, #887)
  • Fix issue #791, correct logic for iterating over SimilarityABC interface. (@MridulS, #839)
  • Fix RP model loading for large Fortran-order arrays (@piskvorky, #605)
  • Remove ShardedCorpus from init because of Theano dependency (@tmylk, #919)
  • Documentation improvements ( @dsquareindia & @tmylk, #914, #906 )
  • Add Annoy memory-mapping example (@harshul1610, #899)
  • Fixed issue #601, correct docID in most_similar for clip range (@parulsethi, #994)

0.13.2, 2016-08-19

  • wordtopics has changed to word_topics in ldamallet, and fixed issue #764. (@bhargavvader, #771)
    • assigning wordtopics value of word_topics to keep backward compatibility, for now
  • topics, topn parameters changed to num_topics and num_words in show_topics() and print_topics() (@droudy, #755)
    • In hdpmodel and dtmmodel
    • NOT BACKWARDS COMPATIBLE!
  • Added random_state parameter to LdaState initializer and check_random_state() (@droudy, #113)
  • Topic coherence update with c_uci, c_npmi measures. LdaMallet, LdaVowpalWabbit support. Add topics parameter to coherencemodel. Can now provide tokenized topics to calculate coherence value. Faster backtracking. (@dsquareindia, #750, #793)
  • Added a check for empty (no words) documents before starting to run the DTM wrapper if model = "fixed" is used (DIM model) as this causes the an error when such documents are reached in training. (@eickho, #806)
  • New parameters limit, datatype for load_word2vec_format(); lockf for intersect_word2vec_format (@gojomo, #817)
  • Changed use_lowercase option in word2vec accuracy to case_insensitive to account for case variations in training vocabulary (@jayantj, #804
  • Link to Doc2Vec on airline tweets example in tutorials page (@544895340, #823)
  • Small error on Doc2vec notebook tutorial (@charlessutton, #816)
  • Bugfix: Full2sparse clipped to use abs value (@tmylk, #811)
  • WMD docstring: add tutorial link and query example (@tmylk, #813)
  • Annoy integration to speed word2vec and doc2vec similarity. Tutorial update (@droudy, #799,#792 )
  • Add converter of LDA model between Mallet, Vowpal Wabit and gensim (@dsquareindia, #798, #766)
  • Distributed LDA in different network segments without broadcast (@menshikh-iv, #782)
  • Update Corpora_and_Vector_Spaces.ipynb (@megansquire, #772)
  • DTM wrapper bug fixes caused by renaming num_words in #755 (@bhargavvader, #770)
  • Add LsiModel.docs_processed attribute (@hobson, #763)
  • Dynamic Topic Modelling in Python. Google Summer of Code 2016 project. (@bhargavvader, #739, #831)

0.13.1, 2016-06-22

  • Topic coherence C_v and U_mass (@dsquareindia, #710)

0.13.0, 2016-06-21

  • Added Distance Metrics to matutils.pt (@bhargavvader, #656)
  • Tutorials migrated from website to ipynb (@j9chan, #721), (@jesford, #733), (@jesford, #725), (@jesford, #716)
  • New doc2vec intro tutorial (@seanlaw, #730)
  • Gensim Quick Start Tutorial (@andrewjlm, #727)
  • Add export_phrases(sentences) to model Phrases (hanabi1224 #588)
  • SparseMatrixSimilarity returns a sparse matrix if maintain_sparsity is True (@davechallis, #590)
  • added functionality for Topics of Words in document - i.e, dynamic topics. (@bhargavvader, #704)
    • also included tutorial which explains new functionalities, and document word-topic colring.
  • Made normalization an explicit transformation. Added 'l1' norm support (@dsquareindia, #649)
  • added term-topics API for most probable topic for word in vocab. (@bhargavvader, #706)
  • build_vocab takes progress_per parameter for smaller output (@zer0n, #624)
  • Control whether to use lowercase for computing word2vec accuracy. (@alantian, #607)
  • Easy import of GloVe vectors using Gensim (Manas Ranjan Kar, #625)
    • Allow easy port of GloVe vectors into Gensim
    • Standalone script with command line arguments, compatible with Python>=2.6
    • Usage: python -m gensim.scripts.glove2word2vec -i glove_vectors.txt -o output_word2vec_compatible.txt
  • Add similar_by_word() and similar_by_vector() to word2vec (@isohyt, #381)
  • Convenience method for similarity of two out of training sentences to doc2vec (@ellolo, #707)
  • Dynamic Topic Modelling Tutorial updated with Dynamic Influence Model (@bhargavvader, #689)
  • Added function to filter 'n' most frequent words from the dictionary (@abhinavchawla, #718)
  • Raise warnings if vocab is single character elements and if alpha is increased in word2vec/doc2vec (@dsquareindia, #705)
  • Tests for wikidump (@jonmcoe, #723)
  • Mallet wrapper sparse format support (@RishabGoel, #664)
  • Doc2vec pre-processing script translated from bash to Python (@andrewjlm, #720)

0.12.4, 2016-01-29

  • Better internal handling of job batching in word2vec (#535)
    • up to 300% speed up when training on very short documents (~tweets)
  • Word2vec CLI in line with original word2vec.c (Andrey Kutuzov, #538)
    • Same default values. See diff akutuzov@6456cbc
    • Standalone script with command line arguments matching those of original C tool.
    • Usage: python -m gensim.scripts.word2vec_standalone -train data.txt -output trained_vec.txt -size 200 -window 2 -sample 1e-4
  • Improved load_word2vec_format() performance (@svenkreiss, #555)
    • Remove init_sims() call for performance improvements when normalized vectors are not needed.
    • Remove norm_only parameter (API change). Call init_sims(replace=True) after the load_word2vec_format() call for the old norm_only=True behavior.
  • Word2vec allows non-strict unicode error handling (ignore or replace) (Gordon Mohr, #466)
  • Doc2Vec model.docvecs[key] now raises KeyError for unknown keys (Gordon Mohr, #520)
  • Fix DocvecsArray.index_to_doctag so most_similar() returns string doctags (Gordon Mohr, #560)
  • On-demand loading of the pattern library in utils.lemmatize (Jan Zikes, #461)
    • utils.HAS_PATTERN flag moved to utils.has_pattern()
  • Threadsafe Word2Vec/Doc2Vec finish-check to avoid hang/unending Word2Vec/Doc2Vec training (Gordon Mohr, #571)
  • Tuned TestWord2VecModel.test_cbow_hs() against random failures (Gordon Mohr, #531)
  • Prevent ZeroDivisionError when default_timer() indicate no elapsed time (Gordon Mohr, #518)
  • Forwards compatibility for NumPy > 1.10 (Matti Lyra, #494, #513)
    • LdaModel and LdaMulticore produce a large number of DeprecationWarnings from
      .inference() because the term ids in each chunk returned from utils.grouper
      are floats. This behaviour has been changed so that the term IDs are now ints.
    • utils.grouper returns a python list instead of a numpy array in .update() when
      LdaModel is called in non distributed mode
    • in distributed mode .update() will still call utils.grouper with as_numpy=True
      to save memory
    • LdaModel.update and LdaMulticore.update have a new keyword parameter
      chunks_as_numpy=True/False (defaults to False) that allows controlling
      this behaviour

0.12.3, 2015-11-05

  • Make show_topics return value consistent across models (Christopher Corley, #448)
    • All models with the show_topics method should return a list of
      (topic_number, topic) tuples, where topic is a list of
      (word, probability) tuples.
    • This is a breaking change that affects users of the LsiModel, LdaModel,
      and LdaMulticore that may be reliant on the old tuple layout of
      (probability, word).
  • Mixed integer & string document-tags (keys to doc-vectors) will work (Gordon Mohr, #491)
    • DocvecsArray's index2doctag list is renamed/reinterpreted as offset2doctag
    • offset2doctag entries map to doctag_syn0 indexes after last plain-int doctag (if any)
    • (If using only string doctags, offset2doctag may be interpreted same as index2doctag.)
  • New Tutorials on Dynamic Topic Modelling and Classification via Word2Vec (@arttii #471, @mataddy #500)
  • Auto-learning for the eta parameter on the LdaModel (Christopher Corley, #479)
  • Python 3.5 support
  • Speed improvements to keyword and summarisation methods (@erbas #441)
  • OSX wheels (#504)
  • Win build (#492)

0.12.2, 2015-09-19

  • tutorial on text summarization (Ólavur Mortensen, #436)
  • more flexible vocabulary construction in word2vec & doc2vec (Philipp Dowling, #434)
  • added support for sliced TransformedCorpus objects, so that after applying (for instance) TfidfModel the returned corpus remains randomly indexable. (Matti Lyra, #425)
  • changed the LdaModel.save so that a custom ignore list can be passed in (Matti Lyra, #331)
  • added support for NumPy style fancy indexing to corpus objects (Matti Lyra, #414)
  • py3k fix in distributed LSI (spacecowboy, #433)
  • Windows fix for setup.py (#428)
  • fix compatibility for scipy 0.16.0 (#415)

0.12.1, 2015-07-20

  • improvements to testing, switch to Travis CI containers
  • support for loading old word2vec models (<=0.11.1) in 0.12+ (Gordon Mohr, #405)
  • various bug fixes to word2vec, doc2vec (Gordon Mohr, #393, #386, #404)
  • TextSummatization support for very short texts (Federico Barrios, #390)
  • support for word2vec[['word1', 'word2'...]] convenience API calls (Satish Palaniappan, #395)
  • MatrixSimilarity supports indexing generator corpora (single pass)

0.12.0, 2015-07-06

  • complete API, performance, memory overhaul of doc2vec (Gordon Mohr, #356, #373, #380, #384)
    • fast infer_vector(); optional memory-mapped doc vectors; memory savings with int doc IDs
    • 'dbow_words' for combined DBOW & word skip-gram training; new 'dm_concat' mode
    • multithreading & negative-sampling optimizations (also benefitting word2vec)
    • API NOTE: doc vectors must now be accessed/compared through model's 'docvecs' field
      (eg: "model.docvecs['my_ID']" or "model.docvecs.most_similar('my_ID')")
    • https://github.com/piskvorky/gensim/blob/develop/docs/notebooks/doc2vec-IMDB.ipynb
  • new "text summarization" module (PR #324: Federico Lopez, Federico Barrios)
  • new matutils.argsort with partial sort
    • performance speedups to all similarity queries (word2vec, Similarity classes...)
  • word2vec can compute likelihood scores for classification (Mat Addy, #358)
  • word2vec supports "encoding" parameter when loading from C format, for non-utf8 models
  • more memory-efficient word2vec training (#385)
  • fixes to Python3 compatibility (Pavel Kalaidin #330, S-Eugene #369)
  • enhancements to save/load format (Liang Bo Wang #363, Gordon Mohr #356)
    • pickle defaults to protocol=2 for better py3 compatibility
  • fixes and improvements to wiki parsing (Lukas Elmer #357, Excellent5 #333)
  • fix to phrases scoring (Ikuya Yamada, #353)
  • speed up of phrases generation (Dave Challis, #349)
  • changes to multipass LDA training (Christopher Corley, #298)
  • various doc improvements and fixes (Matti Lyra #331, Hongjoo Lee #334)
  • fixes and improvements to LDA (Christopher Corley #323)

0.11.0 = 0.11.1 = 0.11.1-1, 2015-04-10

  • added "topic ranking" to sort topics by coherence in LdaModel (jtmcmc, #311)
  • new fast ShardedCorpus out-of-core corpus (Jan Hajic jr., #284)
  • utils.smart_open now uses the smart_open package (#316)
  • new wrapper for LDA in Vowpal Wabbit (Dave Challis, #304)
  • improvements to the DtmModel wrapper (Yang Han, #272, #277)
  • move wrappers for external modeling programs into a submodule (Christopher Corley, #295)
  • allow transparent compression of NumPy files in save/load (Christopher Corley, #248)
  • save/load methods now accept file handles, in addition to file names (macks22, #292)
  • fixes to LdaMulticore on Windows (Feng Mai, #305)
  • lots of small fixes & py3k compatibility improvements (Chyi-Kwei Yau, Daniel Nouri, Timothy Emerick, Juarez Bochi, Christopher Corley, Chirag Nagpal, Jan Hajic jr., Flávio Codeço Coelho)
  • re-released as 0.11.1 and 0.11.1-1 because of a packaging bug

0.10.3, 2014-11-17

  • added streamed phrases = collocation detection (Miguel Cabrera, #258)
  • added param for multiple word2vec epochs (sebastienj, #243)
  • added doc2vec (=paragraph2vec = extension of word2vec) model (Timothy Emerick, #231)
  • initialize word2vec deterministically, for increased experiment reproducibility (KCzar, #240)
  • all indexed corpora now allow full Python slicing syntax (Christopher Corley, #246)
  • update distributed code for new Pyro4 API and py3k (Michael Brooks, Marco Bonzanini, #255, #249)
  • fixes to six module version (Lars Buitinck, #259)
  • fixes to setup.py (Maxim Avanov and Christopher Corley, #260, #251)
  • ...and lots of minor fixes & updates all around

0.10.2, 2014-09-18

  • new parallelized, LdaMulticore implementation (Jan Zikes, #232)
  • Dynamic Topic Models (DTM) wrapper (Arttii, #205)
  • word2vec compiled from bundled C file at install time: no more pyximport (#233)
  • standardize show_/print_topics in LdaMallet (Benjamin Bray, #223)
  • add new word2vec multiplicative objective (3CosMul) of Levy & Goldberg (Gordon Mohr, #224)
  • preserve case in MALLET wrapper (mcburton, #222)
  • support for matrix-valued topic/word prior eta in LdaModel (mjwillson, #208)
  • py3k fix to SparseCorpus (Andreas Madsen, #234)
  • fix to LowCorpus when switching dictionaries (Christopher Corley, #237)

0.10.1, 2014-07-22

  • word2vec: new n_similarity method for comparing two sets of words (François Scharffe, #219)
  • make LDA print/show topics parameters consistent with LSI (Bram Vandekerckhove, #201)
  • add option for efficient word2vec subsampling (Gordon Mohr, #206)
  • fix length calculation for corpora on empty files (Christopher Corley, #209)
  • improve file cleanup of unit tests (Christopher Corley)
  • more unit tests
  • unicode now stored everywhere in gensim internally; accepted input stays either utf8 or unicode
  • various fixes to the py3k ported code
  • allow any dict-like input in Dictionary.from_corpus (Andreas Madsen)
  • error checking improvements to the MALLET wrapper
  • ignore non-articles during wiki parsig
  • utils.lemmatize now (optionally) ignores stopwords

0.10.0 (aka "PY3K port"), 2014-06-04

  • full Python 3 support (targeting 3.3+, #196)
  • all internal methods now expect & store unicode, instead of utf8
  • new optimized word2vec functionality: negative sampling, cbow (sebastien-j, #162)
  • allow by-frequency sort in Dictionary.save_as_text (Renaud Richardet, #192)
  • add topic printing to HDP model (Tiepes, #190)
  • new gensim_addons package = optional install-time Cython compilations (Björn Esser, #197)
  • added py3.3 and 3.4 to Travis CI tests
  • fix a cbow word2vec bug (Liang-Chi Hsieh)

0.9.1, 2014-04-12

  • MmCorpus fix for Windows
  • LdaMallet support for printing/showing topics
  • fix LdaMallet bug when user specified a file prefix (Victor, #184)
  • fix LdaMallet output when input is single vector (Suvir)
  • added LdaMallet unit tests
  • more py3k fixes (Lars Buitinck)
  • change order of LDA topic printing (Fayimora Femi-Balogun, #188)

0.9.0, 2014-03-16

  • save/load automatically single out large arrays + allow mmap
  • allow .gz/.bz2 corpus filenames => transparently (de)compressed I/O
  • CBOW model for word2vec (Sébastien Jean, #176)
  • new API for storing corpus metadata (Joseph Chang, #169)
  • new LdaMallet class = train LDA using wrapped Mallet
  • new MalletCorpus class for corpora in Mallet format (Christopher Corley, #179)
  • better Wikipedia article parsing (Joseph Chang, #170)
  • word2vec load_word2vec_format uses less memory (Yves Raimond, #164)
  • load/store vocabulary files for word2vec C format (Yves Raimond, #172)
  • HDP estimation on new documents (Elliot Kulakow, #153)
  • store labels in SvmLight corpus (Ritesh, #152)
  • fix word2vec binary load on Windows (Stephanus van Schalkwyk)
  • replace numpy.svd with scipy.svd for more stability (Sven Döring, #159)
  • parametrize LDA constructor (Christopher Corley, #174)
  • steps toward py3k compatibility (Lars Buitinck, #154)

0.8.9, 2013-12-26

  • use travis-ci for continuous integration
  • auto-optimize LDA asymmetric prior (Ben Trahan)
  • update for new word2vec binary format (Daren Race)
  • doc rendering fix (Dan Foreman-Mackey)
  • better LDA perplexity logging
  • fix Pyro thread leak in distributed algos (Brian Feeny)
  • optimizations in word2vec (Bryan Rink)
  • allow compressed input in LineSentence corpus (Eric Moyer)
  • upgrade ez_setup, doc improvements, minor fixes etc.

0.8.8 (aka "word2vec release"), 2013-11-03

  • python3 port by Parikshit Samant: https://github.com/samantp/gensimPy3
  • massive optimizations to word2vec (cython, BLAS, multithreading): ~20x-300x speedup
  • new word2vec functionality (thx to Ghassen Hamrouni, PR #124)
  • new CSV corpus class (thx to Zygmunt Zając)
  • corpus serialization checks to prevent overwriting (by Ian Langmore, PR #125)
  • add context manager support for older Python<=2.6 for gzip and bz2
  • added unittests for word2vec

0.8.7, 2013-09-18

  • initial version of word2vec, a neural network deep learning algo
  • make distributed gensim compatible with the new Pyro
  • allow merging dictionaries (by Florent Chandelier)
  • new design for the gensim website!
  • speed up handling of corner cases when returning top-n most similar
  • make Random Projections compatible with new scipy (andrewjOc360, PR #110)
  • allow "light" (faster) word lemmatization (by Karsten Jeschkies)
  • save/load directly from bzip2 files (by Luis Pedro Coelho, PR #101)
  • Blei corpus now tries harder to find its vocabulary file (by Luis Pedro Coelho, PR #100)
  • sparse vector elements can now be a list (was: only a 2-tuple)
  • simple_preprocess now optionally deaccents letters (ř/š/ú=>r/s/u etc.)
  • better serialization of numpy corpora
  • print_topics() returns the topics, in addition to printing/logging
  • fixes for more robust Windows multiprocessing
  • lots of small fixes, data checks and documentation updates

0.8.6, 2012-09-15

  • added HashDictionary (by Homer Strong)
  • support for adding target classes in SVMlight format (by Corrado Monti)
  • fixed problems with global lemmatizer object when running in parallel on Windows
  • parallelization of Wikipedia processing + added script version that lemmatizes the input documents
  • added class method to initialize Dictionary from an existing corpus (by Marko Burjek)

0.8.5, 2012-07-22

  • improved performance of sharding (similarity queries)
  • better Wikipedia parsing (thx to Alejandro Weinstein and Lars Buitinck)
  • faster Porter stemmer (thx to Lars Buitinck)
  • several minor fixes (in HDP model thx to Greg Ver Steeg)
  • improvements to documentation

0.8.4, 2012-03-09

  • better support for Pandas series input (thx to JT Bates)
  • a new corpus format: UCI bag-of-words (thx to Jonathan Esterhazy)
  • a new model, non-parametric bayes: HDP (thx to Jonathan Esterhazy; based on Chong Wang's code)
  • improved support for new scipy versions (thx to Skipper Seabold)
  • lemmatizer support for wikipedia parsing (via the pattern python package)
  • extended the lemmatizer for multi-core processing, to improve its performance

0.8.3, 2011-12-02

  • fixed Similarity sharding bug (issue #65, thx to Paul Rudin)
  • improved LDA code (clarity & memory footprint)
  • optimized efficiency of Similarity sharding

0.8.2, 2011-10-31

  • improved gensim landing page
  • improved accuracy of SVD (Latent Semantic Analysis) (thx to Mark Tygert)
  • changed interpretation of LDA topics: github issue #57
  • took out similarity server code introduced in 0.8.1 (will become a separate project)
  • started using tox for testing
    • several smaller fixes and optimizations

0.8.1, 2011-10-10

  • transactional similarity server: see docs/simserver.html
  • website moved from university hosting to radimrehurek.com
  • much improved speed of lsi[corpus] transformation:
  • accuracy tests of incremental svd: test/svd_error.py and http://groups.google.com/group/gensim/browse_thread/thread/4b605b72f8062770
  • further improvements to memory-efficiency of LDA and LSA
  • improved wiki preprocessing (thx to Luca de Alfaro)
  • model.print_topics() debug fncs now support std output, in addition to logging (thx to Homer Strong)
  • several smaller fixes and improvements

0.8.0 (Armageddon), 2011-06-28

  • changed all variable and function names to comply with PEP8 (numTopics->num_topics): BREAKS BACKWARD COMPATIBILITY!
  • added support for similarity querying more documents at once (index[query_documents] in addition to index[query_document]; much faster)
  • rewrote Similarity so that it is more efficient and scalable (using disk-based mmap'ed shards)
  • simplified directory structure (src/gensim/ is now only gensim/)
  • several small fixes and optimizations

0.7.8, 2011-03-26

  • added corpora.IndexedCorpus, a base class for corpus serializers (thx to Dieter Plaetinck). This allows corpus formats that inherit from it (MmCorpus, SvmLightCorpus, BleiCorpus etc.) to retrieve individual documents by their id in O(1), e.g. corpus[14] returns document #14.
  • merged new code from the LarKC.eu team (corpora.textcorpus, models.logentropy_model, lots of unit tests etc.)
  • fixed a bug in lda[bow] transformation (was returning gamma distribution instead of theta). LDA model generation was not affected, only transforming new vectors.
  • several small fixes and documentation updates

0.7.7, 2011-02-13

  • new LDA implementation after Hoffman et al.: Online Learning for Latent Dirichlet Allocation
  • distributed LDA
  • updated LDA docs (wiki experiments, distributed tutorial)
  • matrixmarket header now uses capital 'M's: MatrixMarket. (André Lynum reported than Matlab has trouble processing the lowercase version)
  • moved code to github
  • started gensim Google group

0.7.6, 2011-01-10

  • added workaround for a bug in numpy: pickling a fortran-order array (e.g. LSA model) and then loading it back and using it results in segfault (thx to Brian Merrel)
  • bundled a new version of ez_setup.py: old failed with Python2.6 when setuptools were missing (thx to Alan Salmoni).

0.7.5, 2010-11-03

  • further optimization to LSA; this is the version used in my NIPS workshop paper
  • got rid of SVDLIBC dependency (one-pass LSA now uses stochastic algo for base-base decompositions)

0.7.4

  • sped up Latent Dirichlet ~10x (through scipy.weave, optional)
  • finally, distributed LDA! scales almost linearly, but no tutorial yet. see the tutorial on distributed LSI, everything's completely analogous.
  • several minor fixes and improvements; one nasty bug fixed (lsi[corpus] didn't work; thx to Danilo Spinelli)

0.7.3

  • added stochastic SVD decomposition (faster than the current one-pass LSI algo, but needs two passes over the input corpus)
  • published gensim on mloss.org

0.7.2

  • added workaround for a numpy bug where SVD sometimes fails to converge for no good reason
  • changed content of gensims's PyPi title page
  • completed HTML tutorial on distributed LSA

0.7.1

  • fixed a bug in LSA that occurred when the number of features was smaller than the number of topics (thx to Richard Berendsen)

0.7.0

  • optimized vocabulary generation in gensim.corpora.dictionary (faster and less memory-intense)
  • MmCorpus accepts compressed input (file-like objects such as GzipFile, BZ2File; to save disk space)
  • changed sparse solver to SVDLIBC (sparsesvd on PyPi) for large document chunks
  • added distributed LSA, updated tutorials (still experimental though)
  • several minor bug fixes

0.6.0

  • added option for online LSI training (yay!). the transformation can now be
    used after any amount of training, and training can be continued at any time
    with more data.
  • optimized the tf-idf transformation, so that it is a strictly one-pass algorithm in all cases (thx to Brian Merrell).
  • fixed Windows-specific bug in handling binary files (thx to Sutee Sudprasert)
  • fixed 1-based feature counting bug in SVMlight format (thx to Richard Berendsen)
  • added 'Topic :: Text Processing :: Linguistic' to gensim's pypi classifiers
  • change of sphinx documentation css and layout

0.5.0

  • finished all tutorials, stable version

0.4.7

  • tutorial on transformations

0.4.6

  • added Random Projections (aka Random Indexing), as another transformation model.
  • several DML-CZ specific updates

0.4.5

  • updated documentation
  • further memory optimizations in SVD (LSI)

0.4.4

  • added missing test files to MANIFEST.in

0.4.3

  • documentation changes
  • added gensim reference to Wikipedia articles (SVD, LSI, LDA, TFIDF, ...)

0.4.2

  • finally, a tutorial!
  • similarity queries got their own package

0.4.1

  • pdf documentation
  • removed dependency on python2.5 (theoretically, gensim now runs on 2.6 and 2.7 as well).

0.4.0

  • support for python setup.py test
  • fixing package metadata
  • documentation clean-up

0.2.0

  • First version
Check out latest releases or
releases around piskvorky/gensim 4.0.1

Don't miss a new gensim release

NewReleases is sending notifications on new releases.

Get notifications