Merge branch 'release-3.2.0'

Author: menshikh-iv

.gitignore

@@ -40,6 +40,8 @@ Thumbs.db
 
 # Other #
 #########
+.tox/
+.cache/
 .project
 .pydevproject
 .ropeproject

.travis.yml

@@ -5,18 +5,24 @@ cache:
   directories:
   - $HOME/.cache/pip
   - $HOME/.ccache
-
+  - $HOME/.pip-cache
 dist: trusty
 language: python
 
 
 matrix:
   include:
-    - env: PYTHON_VERSION="2.7" NUMPY_VERSION="1.11.3" SCIPY_VERSION="0.18.1" ONLY_CODESTYLE="yes"
-    - env: PYTHON_VERSION="2.7" NUMPY_VERSION="1.11.3" SCIPY_VERSION="0.18.1" ONLY_CODESTYLE="no"
-    - env: PYTHON_VERSION="3.5" NUMPY_VERSION="1.11.3" SCIPY_VERSION="0.18.1" ONLY_CODESTYLE="no"
-    - env: PYTHON_VERSION="3.6" NUMPY_VERSION="1.11.3" SCIPY_VERSION="0.18.1" ONLY_CODESTYLE="no"
+    - python: '2.7'
+      env: TOXENV="flake8, docs"
+
+    - python: '2.7'
+      env: TOXENV="py27-linux"
+
+    - python: '3.5'
+      env: TOXENV="py35-linux"
 
+    - python: '3.6'
+      env: TOXENV="py36-linux"
 
-install: source continuous_integration/travis/install.sh
-script: bash continuous_integration/travis/run.sh
+install: pip install tox
+script: tox -vv

CHANGELOG.md

@@ -1,5 +1,151 @@
 Changes
 ===========
+## 3.2.0, 2017-12-09
+
+:star2: New features:
+
+* New download API for corpora and pre-trained models (__[@chaitaliSaini](https://github.com/chaitaliSaini)__ & __[@menshikh-iv](https://github.com/menshikh-iv)__, [#1705](https://github.com/RaRe-Technologies/gensim/pull/1705) & [#1632](https://github.com/RaRe-Technologies/gensim/pull/1632) & [#1492](https://github.com/RaRe-Technologies/gensim/pull/1492))
+    - Download large NLP datasets in one line of Python, then use with memory-efficient data streaming:
+        ```python
+        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:
+        ```python
+        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](https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/) introducing the API and design decisions.
+  - [Notebook with examples](https://github.com/RaRe-Technologies/gensim/blob/be4500e4f0616ec2864c2ce70cb5d4db4b46512d/docs/notebooks/downloader_api_tutorial.ipynb)
+
+* New model: Poincaré embeddings (__[@jayantj](https://github.com/jayantj)__, [#1696](https://github.com/RaRe-Technologies/gensim/pull/1696) & [#1700](https://github.com/RaRe-Technologies/gensim/pull/1700) & [#1757](https://github.com/RaRe-Technologies/gensim/pull/1757) & [#1734](https://github.com/RaRe-Technologies/gensim/pull/1734))
+    - Embed a graph (taxonomy) in the same way as word2vec embeds words:
+        ```python
+        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](https://github.com/RaRe-Technologies/gensim/blob/920c029ca97f961c8df264672c34936607876694/docs/notebooks/Poincare%20Tutorial.ipynb)
+    - [Model introduction and the journey of its implementation](https://rare-technologies.com/implementing-poincare-embeddings/)
+    - [Original paper](https://arxiv.org/abs/1705.08039) on arXiv
+
+* Optimized FastText (__[@manneshiva](https://github.com/manneshiva)__, [#1742](https://github.com/RaRe-Technologies/gensim/pull/1742))
+  - New fast multithreaded implementation of FastText, natively in Python/Cython. Deprecates the existing wrapper for Facebook’s C++ implementation.
+    ```python
+    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](https://github.com/menshikh-iv)__, [MacPython/gensim-wheels/#7](https://github.com/MacPython/gensim-wheels/pull/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.
+
+:+1: Improvements:
+* Add Montemurro and Zanette's entropy based keyword extraction algorithm. Fix #665 (__[@PeteBleackley](https://github.com/PeteBleackley)__, [#1738](https://github.com/RaRe-Technologies/gensim/pull/1738))
+* Fix flake8 E731, E402, refactor tests & sklearn API code. Partial fix #1644  (__[@horpto](https://github.com/horpto)__, [#1689](https://github.com/RaRe-Technologies/gensim/pull/1689))
+* Reduce distribution size. Fix #1698 (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1699](https://github.com/RaRe-Technologies/gensim/pull/1699))
+* Improve `scan_vocab` speed, `build_vocab_from_freq` method (__[@jodevak](https://github.com/jodevak)__, [#1695](https://github.com/RaRe-Technologies/gensim/pull/1695))
+* Improve `segment_wiki` script (__[@piskvorky](https://github.com/piskvorky)__, [#1707](https://github.com/RaRe-Technologies/gensim/pull/1707))
+* Add custom `dtype` support for `LdaModel`. Partially fix #1576 (__[@xelez](https://github.com/xelez)__, [#1656](https://github.com/RaRe-Technologies/gensim/pull/1656))
+* Add `doc2idx` method for `gensim.corpora.Dictionary`. Fix #1634 (__[@roopalgarg](https://github.com/roopalgarg)__, [#1720](https://github.com/RaRe-Technologies/gensim/pull/1720))
+* Add tox and pytest to gensim, integration with Travis and Appveyor. Fix #1613, #1644 (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1721](https://github.com/RaRe-Technologies/gensim/pull/1721))
+* Add flag for hiding outdated data for `gensim.downloader.info` (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1736](https://github.com/RaRe-Technologies/gensim/pull/1736))
+* Add reproducible order between python versions for `gensim.corpora.Dictionary` (__[@formi23](https://github.com/formi23)__, [#1715](https://github.com/RaRe-Technologies/gensim/pull/1715))
+* Update `tox.ini`, `setup.cfg`, `README.md` (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1741](https://github.com/RaRe-Technologies/gensim/pull/1741))
+* Add custom `logsumexp` for `LdaModel` (__[@arlenk](https://github.com/arlenk)__, [#1745](https://github.com/RaRe-Technologies/gensim/pull/1745))
+
+:red_circle: Bug fixes:
+* Fix ranking formula in `gensim.summarization.bm25`. Fix #1718 (__[@souravsingh](https://github.com/souravsingh)__, [#1726](https://github.com/RaRe-Technologies/gensim/pull/1726))
+* Fixed incompatibility in persistence for `FastText` wrapper. Fix #1642 (__[@chinmayapancholi13](https://github.com/chinmayapancholi13)__, [#1723](https://github.com/RaRe-Technologies/gensim/pull/1723))
+* Fix `gensim.sklearn_api` bug with `documents_columns` parameter. Fix #1676 (__[@chinmayapancholi13](https://github.com/chinmayapancholi13)__, [#1704](https://github.com/RaRe-Technologies/gensim/pull/1704))
+* Fix slowdown of CI, remove pytest-cov (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1728](https://github.com/RaRe-Technologies/gensim/pull/1728))
+* Replace outdated packages in Dockerfile (__[@rbahumi](https://github.com/rbahumi)__, [#1730](https://github.com/RaRe-Technologies/gensim/pull/1730))
+* Replace `num_words` to `topn` in `LdaMallet.show_topics`. Fix #1747 (__[@apoorvaeternity](https://github.com/apoorvaeternity)__, [#1749](https://github.com/RaRe-Technologies/gensim/pull/1749))
+* Fix `os.rename` from `gensim.downloader` when 'src' and 'dst' on different partitions (__[@anotherbugmaster](https://github.com/anotherbugmaster)__, [#1733](https://github.com/RaRe-Technologies/gensim/pull/1733))
+* Fix `DeprecationWarning` from `logsumexp` (__[@dreamgonfly](https://github.com/dreamgonfly)__, [#1703](https://github.com/RaRe-Technologies/gensim/pull/1703))
+* Fix backward compatibility problem in `Phrases.load`. Fix #1751 (__[@alexgarel](https://github.com/alexgarel)__, [#1758](https://github.com/RaRe-Technologies/gensim/pull/1758))
+* Fix `load_word2vec_format` from `FastText`. Fix #1743 (__[@manneshiva](https://github.com/manneshiva)__, [#1755](https://github.com/RaRe-Technologies/gensim/pull/1755))
+* Fix ipython kernel version in `Dockerfile`. Fix #1762 (__[@rbahumi](https://github.com/rbahumi)__, [#1764](https://github.com/RaRe-Technologies/gensim/pull/1764))
+* Fix writing in `segment_wiki` (__[@horpto](https://github.com/horpto)__, [#1763](https://github.com/RaRe-Technologies/gensim/pull/1763))
+* Fix write method of file requires byte-like object in `segment_wiki` (__[@horpto](https://github.com/horpto)__, [#1750](https://github.com/RaRe-Technologies/gensim/pull/1750))
+* Fix incorrect vectors learned during online training for `FastText`. Fix #1752 (__[@manneshiva](https://github.com/manneshiva)__, [#1756](https://github.com/RaRe-Technologies/gensim/pull/1756))
+* Fix `dtype` of `model.wv.syn0_vocab` on updating `vocab` for `FastText`. Fix  #1759 (__[@manneshiva](https://github.com/manneshiva)__, [#1760](https://github.com/RaRe-Technologies/gensim/pull/1760))
+* Fix hashing-trick from `FastText.build_vocab`. Fix #1765 (__[@manneshiva](https://github.com/manneshiva)__, [#1768](https://github.com/RaRe-Technologies/gensim/pull/1768))
+* Add explicit `DeprecationWarning` for all outdated stuff. Fix #1753 (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1769](https://github.com/RaRe-Technologies/gensim/pull/1769))
+* Fix epsilon according to `dtype` in `LdaModel` (__[@menshikh-iv](https://github.com/menshikh-iv)__, [#1770](https://github.com/RaRe-Technologies/gensim/pull/1770))
+
+:books: Tutorial and doc improvements:
+* Update perf numbers of `segment_wiki` (__[@piskvorky](https://github.com/piskvorky)__, [#1708](https://github.com/RaRe-Technologies/gensim/pull/1708))
+* Update docstring for `gensim.summarization.summarize`. Fix #1575 (__[@fbarrios](https://github.com/fbarrios)__, [#1702](https://github.com/RaRe-Technologies/gensim/pull/1702))
+* Refactor API Reference for `gensim.parsing`. Fix #1664 (__[@CLearERR](https://github.com/CLearERR)__, [#1684](https://github.com/RaRe-Technologies/gensim/pull/1684))
+* Fix typos in doc2vec-wikipedia notebook (__[@youqad](https://github.com/youqad)__, [#1727](https://github.com/RaRe-Technologies/gensim/pull/1727))
+* Fix PyPI long description rendering (__[@edigaryev](https://github.com/edigaryev)__, [#1739](https://github.com/RaRe-Technologies/gensim/pull/1739))
+* Fix twitter badge src  (__[@menshikh-iv](https://github.com/menshikh-iv)__)
+* Fix maillist badge color (__[@menshikh-iv](https://github.com/menshikh-iv)__)
+
+:warning: 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
 
 

MANIFEST.in

@@ -1,8 +1,4 @@
-recursive-include docs *
 recursive-include gensim/test/test_data *
-recursive-include . *.sh
-prune docs/src*
-prune docs/notebooks/datasets
 include README.md
 include CHANGELOG.md
 include COPYING
@@ -14,3 +10,5 @@ include gensim/models/word2vec_inner.pyx
 include gensim/models/word2vec_inner.pxd
 include gensim/models/doc2vec_inner.c
 include gensim/models/doc2vec_inner.pyx
+include gensim/models/fasttext_inner.c
+include gensim/models/fasttext_inner.pyx

README.md

@@ -5,9 +5,9 @@ gensim – Topic Modelling in Python
 [![GitHub release](https://img.shields.io/github/release/rare-technologies/gensim.svg?maxAge=3600)](https://github.com/RaRe-Technologies/gensim/releases)
 [![Wheel](https://img.shields.io/pypi/wheel/gensim.svg)](https://pypi.python.org/pypi/gensim)
 [![DOI](https://zenodo.org/badge/DOI/10.13140/2.1.2393.1847.svg)](https://doi.org/10.13140/2.1.2393.1847)
-[![Mailing List](https://img.shields.io/badge/-Mailing%20List-lightgrey.svg)](https://groups.google.com/forum/#!forum/gensim)
+[![Mailing List](https://img.shields.io/badge/-Mailing%20List-brightgreen.svg)](https://groups.google.com/forum/#!forum/gensim)
 [![Gitter](https://img.shields.io/badge/gitter-join%20chat%20%E2%86%92-09a3d5.svg)](https://gitter.im/RaRe-Technologies/gensim)
-[![Follow](https://img.shields.io/twitter/follow/spacy_io.svg?style=social&label=Follow)](https://twitter.com/gensim_py)
+[![Follow](https://img.shields.io/twitter/follow/gensim_py.svg?style=social&label=Follow)](https://twitter.com/gensim_py)
 
 
 

appveyor.yml

@@ -13,29 +13,20 @@ environment:
       secure: qXqY3dFmLOqvxa3Om2gQi/BjotTOK+EP2IPLolBNo0c61yDtNWxbmE4wH3up72Be
 
   matrix:
-    # - PYTHON: "C:\\Python27"
-    #   PYTHON_VERSION: "2.7.12"
-    #   PYTHON_ARCH: "32"
-
     - PYTHON: "C:\\Python27-x64"
       PYTHON_VERSION: "2.7.12"
       PYTHON_ARCH: "64"
-
-    # - PYTHON: "C:\\Python35"
-    #   PYTHON_VERSION: "3.5.2"
-    #   PYTHON_ARCH: "32"
+      TOXENV: "py27-win"
 
     - PYTHON: "C:\\Python35-x64"
       PYTHON_VERSION: "3.5.2"
       PYTHON_ARCH: "64"
-      
-    # - PYTHON: "C:\\Python36"
-    #   PYTHON_VERSION: "3.6.0"
-    #   PYTHON_ARCH: "32"
+      TOXENV: "py35-win"
 
     - PYTHON: "C:\\Python36-x64"
       PYTHON_VERSION: "3.6.0"
       PYTHON_ARCH: "64"
+      TOXENV: "py36-win"
 
 init:
   - "ECHO %PYTHON% %PYTHON_VERSION% %PYTHON_ARCH%"
@@ -57,48 +48,16 @@ install:
   # not already installed.
   - "powershell ./continuous_integration/appveyor/install.ps1"
   - "SET PATH=%PYTHON%;%PYTHON%\\Scripts;%PATH%"
-  - "python -m pip install -U pip"
+  - "python -m pip install -U pip tox"
 
   # Check that we have the expected version and architecture for Python
   - "python --version"
   - "python -c \"import struct; print(struct.calcsize('P') * 8)\""
 
-  # Install the build and runtime dependencies of the project.
-  - "%CMD_IN_ENV% pip install --timeout=60 --trusted-host 28daf2247a33ed269873-7b1aad3fab3cc330e1fd9d109892382a.r6.cf2.rackcdn.com -r continuous_integration/appveyor/requirements.txt"
-  - "%CMD_IN_ENV% python setup.py bdist_wheel bdist_wininst"
-  - ps: "ls dist"
-
-  # Install the genreated wheel package to test it
-  - "pip install --pre --no-index --find-links dist/ gensim"
-
-# Not a .NET project, we build scikit-learn in the install step instead
 build: false
 
 test_script:
-  # Change to a non-source folder to make sure we run the tests on the
-  # installed library.
-  - "mkdir empty_folder"
-  - "cd empty_folder"
-  - "pip install pyemd testfixtures sklearn Morfessor==2.0.2a4"
-  - "pip freeze"
-  - "python -c \"import nose; nose.main()\" -s -v gensim"
-  # Move back to the project folder
-  - "cd .."
-
-artifacts:
-  # Archive the generated wheel package in the ci.appveyor.com build report.
-  - path: dist\*
-on_success:
-  # Upload the generated wheel package to Rackspace
-  # On Windows, Apache Libcloud cannot find a standard CA cert bundle so we
-  # disable the ssl checks.
-  - "python -m wheelhouse_uploader upload --no-ssl-check --local-folder=dist gensim-windows-wheels"
-
-notifications:
-  - provider: Webhook
-    url: https://webhooks.gitter.im/e/62c44ad26933cd7ed7e8
-    on_build_success: false
-    on_build_failure: True
+  - tox -vv
 
 cache:
   # Use the appveyor cache to avoid re-downloading large archives such