nltk 3.2__zip → 3.3__zip

{nltk-3.2 → nltk-3.3}/nltk/wsd.py

@@ -1,53 +1,53 @@
-# Natural Language Toolkit: Word Sense Disambiguation Algorithms
-#
-# Authors: Liling Tan <alvations@gmail.com>,
-#          Dmitrijs Milajevs <dimazest@gmail.com>
-#
-# Copyright (C) 2001-2015 NLTK Project
-# URL: <http://nltk.org/>
-# For license information, see LICENSE.TXT
-
-from nltk.corpus import wordnet
-
-
-def lesk(context_sentence, ambiguous_word, pos=None, synsets=None):
-    """Return a synset for an ambiguous word in a context.
-
-    :param iter context_sentence: The context sentence where the ambiguous word
-    occurs, passed as an iterable of words.
-    :param str ambiguous_word: The ambiguous word that requires WSD.
-    :param str pos: A specified Part-of-Speech (POS).
-    :param iter synsets: Possible synsets of the ambiguous word.
-    :return: ``lesk_sense`` The Synset() object with the highest signature overlaps.
-
-    This function is an implementation of the original Lesk algorithm (1986) [1].
-
-    Usage example::
-
-        >>> lesk(['I', 'went', 'to', 'the', 'bank', 'to', 'deposit', 'money', '.'], 'bank', 'n')
-        Synset('savings_bank.n.02')
-
-    [1] Lesk, Michael. "Automatic sense disambiguation using machine
-    readable dictionaries: how to tell a pine cone from an ice cream
-    cone." Proceedings of the 5th Annual International Conference on
-    Systems Documentation. ACM, 1986.
-    http://dl.acm.org/citation.cfm?id=318728
-    """
-
-    context = set(context_sentence)
-    if synsets is None:
-        synsets = wordnet.synsets(ambiguous_word)
-
-    if pos:
-        synsets = [ss for ss in synsets if str(ss.pos()) == pos]
-
-    if not synsets:
-        return None
-
-    _, sense = max(
-        (len(context.intersection(ss.definition().split())), ss) for ss in synsets
-    )
-
-    return sense
-
-
+# Natural Language Toolkit: Word Sense Disambiguation Algorithms
+#
+# Authors: Liling Tan <alvations@gmail.com>,
+#          Dmitrijs Milajevs <dimazest@gmail.com>
+#
+# Copyright (C) 2001-2018 NLTK Project
+# URL: <http://nltk.org/>
+# For license information, see LICENSE.TXT
+
+from nltk.corpus import wordnet
+
+
+def lesk(context_sentence, ambiguous_word, pos=None, synsets=None):
+    """Return a synset for an ambiguous word in a context.
+
+    :param iter context_sentence: The context sentence where the ambiguous word
+         occurs, passed as an iterable of words.
+    :param str ambiguous_word: The ambiguous word that requires WSD.
+    :param str pos: A specified Part-of-Speech (POS).
+    :param iter synsets: Possible synsets of the ambiguous word.
+    :return: ``lesk_sense`` The Synset() object with the highest signature overlaps.
+
+    This function is an implementation of the original Lesk algorithm (1986) [1].
+
+    Usage example::
+
+        >>> lesk(['I', 'went', 'to', 'the', 'bank', 'to', 'deposit', 'money', '.'], 'bank', 'n')
+        Synset('savings_bank.n.02')
+
+    [1] Lesk, Michael. "Automatic sense disambiguation using machine
+    readable dictionaries: how to tell a pine cone from an ice cream
+    cone." Proceedings of the 5th Annual International Conference on
+    Systems Documentation. ACM, 1986.
+    http://dl.acm.org/citation.cfm?id=318728
+    """
+
+    context = set(context_sentence)
+    if synsets is None:
+        synsets = wordnet.synsets(ambiguous_word)
+
+    if pos:
+        synsets = [ss for ss in synsets if str(ss.pos()) == pos]
+
+    if not synsets:
+        return None
+
+    _, sense = max(
+        (len(context.intersection(ss.definition().split())), ss) for ss in synsets
+    )
+
+    return sense
+
+

{nltk-3.2 → nltk-3.3/nltk.egg-info}/PKG-INFO

@@ -1,13 +1,15 @@
-Metadata-Version: 1.1
+Metadata-Version: 2.1
 Name: nltk
-Version: 3.2
+Version: 3.3
 Summary: Natural Language Toolkit
 Home-page: http://nltk.org/
 Author: Steven Bird
 Author-email: stevenbird1@gmail.com
+Maintainer: Steven Bird
+Maintainer-email: stevenbird1@gmail.com
 License: Apache License, Version 2.0
 Description: The Natural Language Toolkit (NLTK) is a Python package for
-        natural language processing.  NLTK requires Python 2.7, or 3.2+.
+        natural language processing.  NLTK requires Python 2.7, 3.4, 3.5, or 3.6.
 Keywords: NLP,CL,natural language processing,computational linguistics,parsing,tagging,tokenizing,syntax,linguistics,language,natural language,text analytics
 Platform: UNKNOWN
 Classifier: Development Status :: 5 - Production/Stable
@@ -18,9 +20,9 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 2.7
-Classifier: Programming Language :: Python :: 3.2
-Classifier: Programming Language :: Python :: 3.3
 Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Human Machine Interfaces
@@ -30,3 +32,9 @@ Classifier: Topic :: Text Processing :: Filters
 Classifier: Topic :: Text Processing :: General
 Classifier: Topic :: Text Processing :: Indexing
 Classifier: Topic :: Text Processing :: Linguistic
+Provides-Extra: corenlp
+Provides-Extra: twitter
+Provides-Extra: tgrep
+Provides-Extra: plot
+Provides-Extra: machine_learning
+Provides-Extra: all

{nltk-3.2 → nltk-3.3}/nltk.egg-info/SOURCES.txt

@@ -1,12 +1,13 @@
 INSTALL.txt
 LICENSE.txt
 MANIFEST.in
-README.txt
+README.md
 setup.cfg
 setup.py
 nltk/VERSION
 nltk/__init__.py
 nltk/book.py
+nltk/collections.py
 nltk/collocations.py
 nltk/compat.py
 nltk/data.py
@@ -19,7 +20,6 @@ nltk/internals.py
 nltk/jsontags.py
 nltk/lazyimport.py
 nltk/probability.py
-nltk/six.py
 nltk/text.py
 nltk/tgrep.py
 nltk/toolbox.py
@@ -32,6 +32,7 @@ nltk.egg-info/PKG-INFO
 nltk.egg-info/SOURCES.txt
 nltk.egg-info/dependency_links.txt
 nltk.egg-info/not-zip-safe
+nltk.egg-info/requires.txt
 nltk.egg-info/top_level.txt
 nltk/app/__init__.py
 nltk/app/chartparser_app.py
@@ -48,6 +49,7 @@ nltk/ccg/api.py
 nltk/ccg/chart.py
 nltk/ccg/combinator.py
 nltk/ccg/lexicon.py
+nltk/ccg/logic.py
 nltk/chat/__init__.py
 nltk/chat/eliza.py
 nltk/chat/iesha.py
@@ -150,6 +152,7 @@ nltk/inference/resolution.py
 nltk/inference/tableau.py
 nltk/metrics/__init__.py
 nltk/metrics/agreement.py
+nltk/metrics/aline.py
 nltk/metrics/association.py
 nltk/metrics/confusionmatrix.py
 nltk/metrics/distance.py
@@ -167,6 +170,7 @@ nltk/parse/__init__.py
 nltk/parse/api.py
 nltk/parse/bllip.py
 nltk/parse/chart.py
+nltk/parse/corenlp.py
 nltk/parse/dependencygraph.py
 nltk/parse/earleychart.py
 nltk/parse/evaluate.py
@@ -201,9 +205,9 @@ nltk/sentiment/__init__.py
 nltk/sentiment/sentiment_analyzer.py
 nltk/sentiment/util.py
 nltk/sentiment/vader.py
-nltk/sentiment/vader_lexicon.txt
 nltk/stem/__init__.py
 nltk/stem/api.py
+nltk/stem/arlstem.py
 nltk/stem/isri.py
 nltk/stem/lancaster.py
 nltk/stem/porter.py
@@ -238,15 +242,18 @@ nltk/test/all.py
 nltk/test/bleu.doctest
 nltk/test/bnc.doctest
 nltk/test/ccg.doctest
+nltk/test/ccg_semantics.doctest
 nltk/test/chat80.doctest
 nltk/test/childes.doctest
 nltk/test/childes_fixt.py
 nltk/test/chunk.doctest
 nltk/test/classify.doctest
 nltk/test/classify_fixt.py
+nltk/test/collections.doctest
 nltk/test/collocations.doctest
 nltk/test/compat.doctest
 nltk/test/compat_fixt.py
+nltk/test/concordance.doctest
 nltk/test/corpus.doctest
 nltk/test/corpus_fixt.py
 nltk/test/crubadan.doctest
@@ -309,46 +316,61 @@ nltk/test/wordnet_lch.doctest
 nltk/test/wsd.doctest
 nltk/test/unit/__init__.py
 nltk/test/unit/test_2x_compat.py
+nltk/test/unit/test_aline.py
+nltk/test/unit/test_chunk.py
 nltk/test/unit/test_classify.py
 nltk/test/unit/test_collocations.py
+nltk/test/unit/test_concordance.py
+nltk/test/unit/test_corenlp.py
 nltk/test/unit/test_corpora.py
 nltk/test/unit/test_corpus_views.py
 nltk/test/unit/test_hmm.py
 nltk/test/unit/test_json2csv_corpus.py
 nltk/test/unit/test_naivebayes.py
+nltk/test/unit/test_rte_classify.py
 nltk/test/unit/test_seekable_unicode_stream_reader.py
+nltk/test/unit/test_senna.py
 nltk/test/unit/test_stem.py
 nltk/test/unit/test_tag.py
 nltk/test/unit/test_tgrep.py
 nltk/test/unit/test_tokenize.py
 nltk/test/unit/test_twitter_auth.py
+nltk/test/unit/test_wordnet.py
 nltk/test/unit/utils.py
 nltk/test/unit/translate/__init__.py
 nltk/test/unit/translate/test_bleu.py
+nltk/test/unit/translate/test_gdfa.py
 nltk/test/unit/translate/test_ibm1.py
 nltk/test/unit/translate/test_ibm2.py
 nltk/test/unit/translate/test_ibm3.py
 nltk/test/unit/translate/test_ibm4.py
 nltk/test/unit/translate/test_ibm5.py
 nltk/test/unit/translate/test_ibm_model.py
+nltk/test/unit/translate/test_nist.py
 nltk/test/unit/translate/test_stack_decoder.py
 nltk/tokenize/__init__.py
 nltk/tokenize/api.py
 nltk/tokenize/casual.py
 nltk/tokenize/mwe.py
+nltk/tokenize/nist.py
 nltk/tokenize/punkt.py
 nltk/tokenize/regexp.py
+nltk/tokenize/repp.py
 nltk/tokenize/sexpr.py
 nltk/tokenize/simple.py
 nltk/tokenize/stanford.py
+nltk/tokenize/stanford_segmenter.py
 nltk/tokenize/texttiling.py
+nltk/tokenize/toktok.py
 nltk/tokenize/treebank.py
 nltk/tokenize/util.py
 nltk/translate/__init__.py
 nltk/translate/api.py
 nltk/translate/bleu_score.py
+nltk/translate/chrf_score.py
 nltk/translate/gale_church.py
 nltk/translate/gdfa.py
+nltk/translate/gleu_score.py
 nltk/translate/ibm1.py
 nltk/translate/ibm2.py
 nltk/translate/ibm3.py
@@ -356,6 +378,7 @@ nltk/translate/ibm4.py
 nltk/translate/ibm5.py
 nltk/translate/ibm_model.py
 nltk/translate/metrics.py
+nltk/translate/nist_score.py
 nltk/translate/phrase_based.py
 nltk/translate/ribes_score.py
 nltk/translate/stack_decoder.py

nltk-3.3/nltk.egg-info/requires.txt

@@ -0,0 +1,31 @@
+six
+
+[all]
+pyparsing
+gensim
+requests
+scipy
+twython
+scikit-learn
+numpy
+matplotlib
+python-crfsuite
+
+[corenlp]
+requests
+
+[machine_learning]
+gensim
+numpy
+python-crfsuite
+scikit-learn
+scipy
+
+[plot]
+matplotlib
+
+[tgrep]
+pyparsing
+
+[twitter]
+twython

{nltk-3.2 → nltk-3.3}/setup.cfg

@@ -1,5 +1,4 @@
 [egg_info]
 tag_build = 
 tag_date = 0
-tag_svn_revision = 0
 

{nltk-3.2 → nltk-3.3}/setup.py

@@ -1,75 +1,102 @@
-#!/usr/bin/env python
-#
-# Setup script for the Natural Language Toolkit
-#
-# Copyright (C) 2001-2015 NLTK Project
-# Author: Steven Bird <stevenbird1@gmail.com>
-#         Edward Loper <edloper@gmail.com>
-#         Ewan Klein <ewan@inf.ed.ac.uk>
-# URL: <http://nltk.org/>
-# For license information, see LICENSE.TXT
-
-# Work around mbcs bug in distutils.
-# http://bugs.python.org/issue10945
-import codecs
-try:
-    codecs.lookup('mbcs')
-except LookupError:
-    ascii = codecs.lookup('ascii')
-    func = lambda name, enc=ascii: {True: enc}.get(name=='mbcs')
-    codecs.register(func)
-
-import os
-
-# Use the VERSION file to get NLTK version
-version_file = os.path.join(os.path.dirname(__file__), 'nltk', 'VERSION')
-with open(version_file) as fh:
-    nltk_version = fh.read().strip()
-
-# setuptools
-from setuptools import setup, find_packages
-
-setup(
-    name = "nltk",
-    description = "Natural Language Toolkit",
-    version = nltk_version,
-    url = "http://nltk.org/",
-    long_description = """\
-The Natural Language Toolkit (NLTK) is a Python package for
-natural language processing.  NLTK requires Python 2.7, or 3.2+.""",
-    license = "Apache License, Version 2.0",
-    keywords = ['NLP', 'CL', 'natural language processing',
-                'computational linguistics', 'parsing', 'tagging',
-                'tokenizing', 'syntax', 'linguistics', 'language',
-                'natural language', 'text analytics'],
-    maintainer = "Steven Bird",
-    maintainer_email = "stevenbird1@gmail.com",
-    author = "Steven Bird",
-    author_email = "stevenbird1@gmail.com",
-    classifiers = [
-    'Development Status :: 5 - Production/Stable',
-    'Intended Audience :: Developers',
-    'Intended Audience :: Education',
-    'Intended Audience :: Information Technology',
-    'Intended Audience :: Science/Research',
-    'License :: OSI Approved :: Apache Software License',
-    'Operating System :: OS Independent',
-    'Programming Language :: Python :: 2.7',
-    'Programming Language :: Python :: 3.2',
-    'Programming Language :: Python :: 3.3',
-    'Programming Language :: Python :: 3.4',
-    'Topic :: Scientific/Engineering',
-    'Topic :: Scientific/Engineering :: Artificial Intelligence',
-    'Topic :: Scientific/Engineering :: Human Machine Interfaces',
-    'Topic :: Scientific/Engineering :: Information Analysis',
-    'Topic :: Text Processing',
-    'Topic :: Text Processing :: Filters',
-    'Topic :: Text Processing :: General',
-    'Topic :: Text Processing :: Indexing',
-    'Topic :: Text Processing :: Linguistic',
-    ],
-    package_data = {'nltk': ['test/*.doctest', 'VERSION', 'sentiment/vader_lexicon.txt']},
-#    install_requires = ['six>=1.9.0'],
-    packages = find_packages(),
-    zip_safe=False, # since normal files will be present too?
-    )
+#!/usr/bin/env python
+#
+# Setup script for the Natural Language Toolkit
+#
+# Copyright (C) 2001-2018 NLTK Project
+# Author: Steven Bird <stevenbird1@gmail.com>
+#         Edward Loper <edloper@gmail.com>
+#         Ewan Klein <ewan@inf.ed.ac.uk>
+# URL: <http://nltk.org/>
+# For license information, see LICENSE.TXT
+
+# Work around mbcs bug in distutils.
+# http://bugs.python.org/issue10945
+import codecs
+try:
+    codecs.lookup('mbcs')
+except LookupError:
+    ascii = codecs.lookup('ascii')
+    func = lambda name, enc=ascii: {True: enc}.get(name=='mbcs')
+    codecs.register(func)
+
+import os
+
+# Use the VERSION file to get NLTK version
+version_file = os.path.join(os.path.dirname(__file__), 'nltk', 'VERSION')
+with open(version_file) as fh:
+    nltk_version = fh.read().strip()
+
+# setuptools
+from setuptools import setup, find_packages
+
+# Specify groups of optional dependencies
+extras_require = {
+    'machine_learning': [
+        'gensim',
+        'numpy',
+        'python-crfsuite',
+        'scikit-learn',
+        'scipy'
+    ],
+    'plot': [
+        'matplotlib',
+    ],
+    'tgrep': [
+        'pyparsing',
+    ],
+    'twitter': [
+        'twython',
+    ],
+    'corenlp': [
+        'requests',
+    ],
+}
+
+# Add a group made up of all optional dependencies
+extras_require['all'] = set(package for group in extras_require.values() for package in group)
+
+setup(
+    name = "nltk",
+    description = "Natural Language Toolkit",
+    version = nltk_version,
+    url = "http://nltk.org/",
+    long_description = """\
+The Natural Language Toolkit (NLTK) is a Python package for
+natural language processing.  NLTK requires Python 2.7, 3.4, 3.5, or 3.6.""",
+    license = "Apache License, Version 2.0",
+    keywords = ['NLP', 'CL', 'natural language processing',
+                'computational linguistics', 'parsing', 'tagging',
+                'tokenizing', 'syntax', 'linguistics', 'language',
+                'natural language', 'text analytics'],
+    maintainer = "Steven Bird",
+    maintainer_email = "stevenbird1@gmail.com",
+    author = "Steven Bird",
+    author_email = "stevenbird1@gmail.com",
+    classifiers = [
+    'Development Status :: 5 - Production/Stable',
+    'Intended Audience :: Developers',
+    'Intended Audience :: Education',
+    'Intended Audience :: Information Technology',
+    'Intended Audience :: Science/Research',
+    'License :: OSI Approved :: Apache Software License',
+    'Operating System :: OS Independent',
+    'Programming Language :: Python :: 2.7',
+    'Programming Language :: Python :: 3.4',
+    'Programming Language :: Python :: 3.5',
+    'Programming Language :: Python :: 3.6',
+    'Topic :: Scientific/Engineering',
+    'Topic :: Scientific/Engineering :: Artificial Intelligence',
+    'Topic :: Scientific/Engineering :: Human Machine Interfaces',
+    'Topic :: Scientific/Engineering :: Information Analysis',
+    'Topic :: Text Processing',
+    'Topic :: Text Processing :: Filters',
+    'Topic :: Text Processing :: General',
+    'Topic :: Text Processing :: Indexing',
+    'Topic :: Text Processing :: Linguistic',
+    ],
+    package_data = {'nltk': ['test/*.doctest', 'VERSION']},
+    install_requires = ['six'],
+    extras_require = extras_require,
+    packages = find_packages(),
+    zip_safe=False, # since normal files will be present too?
+    )

nltk-3.2/nltk/VERSION

@@ -1 +0,0 @@
-3.2