nltk 3.2__zip → 3.3__zip

{nltk-3.2 → nltk-3.3}/nltk/test/wordnet_fixt.py

@@ -1,6 +1,7 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-
-def teardown_module(module=None):
-    from nltk.corpus import wordnet
-    wordnet._unload()
+# -*- coding: utf-8 -*-
+from __future__ import absolute_import
+
+
+def teardown_module(module=None):
+    from nltk.corpus import wordnet
+    wordnet._unload()

{nltk-3.2 → nltk-3.3}/nltk/test/wordnet_lch.doctest

@@ -1,53 +1,53 @@
-.. Copyright (C) 2001-2015 NLTK Project
-.. For license information, see LICENSE.TXT
-
-===============================
-WordNet Lowest Common Hypernyms
-===============================
-
-Wordnet's lowest_common_hypernyms() method is based used to locate the 
-lowest single hypernym that is shared by two given words:
-
-    >>> from nltk.corpus import wordnet as wn
-    >>> wn.synset('kin.n.01').lowest_common_hypernyms(wn.synset('mother.n.01'))
-    [Synset('relative.n.01')]
-
-    >>> wn.synset('policeman.n.01').lowest_common_hypernyms(wn.synset('chef.n.01'))
-    [Synset('person.n.01')]
-
-This method generally returns a single result, but in some cases, more than one
-valid LCH is possible:
-
-    >>> wn.synset('body.n.09').lowest_common_hypernyms(wn.synset('sidereal_day.n.01'))
-    [Synset('attribute.n.02'), Synset('measure.n.02')]
-
-In some cases, lowest_common_hypernyms() can return one of the synsets which was 
-passed to it as an argument:
-
-    >>> wn.synset('woman.n.01').lowest_common_hypernyms(wn.synset('girlfriend.n.02'))
-    [Synset('woman.n.01')]
-
-In NLTK 3.0a2 the behavior of lowest_common_hypernyms() was changed to give more
-accurate results in a small set of cases, generally when dealing with nouns describing 
-social roles or jobs. To emulate the pre v3.0a2 behavior, you can set the use_min_depth=True
-flag:
-
-    >>> wn.synset('policeman.n.01').lowest_common_hypernyms(wn.synset('chef.n.01'))
-    [Synset('person.n.01')]
-    >>> wn.synset('policeman.n.01').lowest_common_hypernyms(wn.synset('chef.n.01'), use_min_depth=True)
-    [Synset('organism.n.01')]
-
-In some cases use_min_depth=True may return more or fewer results than the default
-behavior:
-
-    >>> wn.synset('woman.n.01').lowest_common_hypernyms(wn.synset('girlfriend.n.02'))
-    [Synset('woman.n.01')]
-    >>> wn.synset('woman.n.01').lowest_common_hypernyms(wn.synset('girlfriend.n.02'), use_min_depth=True)
-    [Synset('organism.n.01'), Synset('woman.n.01')]
-
-In the general case, however, they tend to return the same results:
-
-    >>> wn.synset('body.n.09').lowest_common_hypernyms(wn.synset('sidereal_day.n.01'))
-    [Synset('attribute.n.02'), Synset('measure.n.02')]
-    >>> wn.synset('body.n.09').lowest_common_hypernyms(wn.synset('sidereal_day.n.01'), use_min_depth=True)
-    [Synset('attribute.n.02'), Synset('measure.n.02')]
+.. Copyright (C) 2001-2018 NLTK Project
+.. For license information, see LICENSE.TXT
+
+===============================
+WordNet Lowest Common Hypernyms
+===============================
+
+Wordnet's lowest_common_hypernyms() method is based used to locate the 
+lowest single hypernym that is shared by two given words:
+
+    >>> from nltk.corpus import wordnet as wn
+    >>> wn.synset('kin.n.01').lowest_common_hypernyms(wn.synset('mother.n.01'))
+    [Synset('relative.n.01')]
+
+    >>> wn.synset('policeman.n.01').lowest_common_hypernyms(wn.synset('chef.n.01'))
+    [Synset('person.n.01')]
+
+This method generally returns a single result, but in some cases, more than one
+valid LCH is possible:
+
+    >>> wn.synset('body.n.09').lowest_common_hypernyms(wn.synset('sidereal_day.n.01'))
+    [Synset('attribute.n.02'), Synset('measure.n.02')]
+
+In some cases, lowest_common_hypernyms() can return one of the synsets which was 
+passed to it as an argument:
+
+    >>> wn.synset('woman.n.01').lowest_common_hypernyms(wn.synset('girlfriend.n.02'))
+    [Synset('woman.n.01')]
+
+In NLTK 3.0a2 the behavior of lowest_common_hypernyms() was changed to give more
+accurate results in a small set of cases, generally when dealing with nouns describing 
+social roles or jobs. To emulate the pre v3.0a2 behavior, you can set the use_min_depth=True
+flag:
+
+    >>> wn.synset('policeman.n.01').lowest_common_hypernyms(wn.synset('chef.n.01'))
+    [Synset('person.n.01')]
+    >>> wn.synset('policeman.n.01').lowest_common_hypernyms(wn.synset('chef.n.01'), use_min_depth=True)
+    [Synset('organism.n.01')]
+
+In some cases use_min_depth=True may return more or fewer results than the default
+behavior:
+
+    >>> wn.synset('woman.n.01').lowest_common_hypernyms(wn.synset('girlfriend.n.02'))
+    [Synset('woman.n.01')]
+    >>> wn.synset('woman.n.01').lowest_common_hypernyms(wn.synset('girlfriend.n.02'), use_min_depth=True)
+    [Synset('organism.n.01'), Synset('woman.n.01')]
+
+In the general case, however, they tend to return the same results:
+
+    >>> wn.synset('body.n.09').lowest_common_hypernyms(wn.synset('sidereal_day.n.01'))
+    [Synset('attribute.n.02'), Synset('measure.n.02')]
+    >>> wn.synset('body.n.09').lowest_common_hypernyms(wn.synset('sidereal_day.n.01'), use_min_depth=True)
+    [Synset('attribute.n.02'), Synset('measure.n.02')]

{nltk-3.2 → nltk-3.3}/nltk/test/wsd.doctest

@@ -1,68 +1,68 @@
-.. Copyright (C) 2001-2015 NLTK Project
-.. For license information, see LICENSE.TXT
-
-.. -*- coding: utf-8 -*-
-
-=========================
-Word Sense Disambiguation
-=========================
-
-
-Lesk Algorithm
---------------
-
-
-Performs the classic Lesk algorithm for Word Sense Disambiguation (WSD) using
-a the definitions of the ambiguous word.
-
-Given an ambiguous word and the context in which the word occurs, Lesk returns
-a Synset with the highest number of overlapping words between the context
-sentence and different definitions from each Synset.
-
-    >>> from nltk.wsd import lesk
-    >>> sent = ['I', 'went', 'to', 'the', 'bank', 'to', 'deposit', 'money', '.']
-
-    >>> print(lesk(sent, 'bank', 'n'))
-    Synset('savings_bank.n.02')
-
-    >>> print(lesk(sent, 'bank'))
-    Synset('savings_bank.n.02')
-
-The definitions for "bank" are:
-
-    >>> from nltk.corpus import wordnet as wn
-    >>> for ss in wn.synsets('bank'):
-    ...     print(ss, ss.definition())
-    ...
-    Synset('bank.n.01') sloping land (especially the slope beside a body of water)
-    Synset('depository_financial_institution.n.01') a financial institution that accepts deposits and channels the money into lending activities
-    Synset('bank.n.03') a long ridge or pile
-    Synset('bank.n.04') an arrangement of similar objects in a row or in tiers
-    Synset('bank.n.05') a supply or stock held in reserve for future use (especially in emergencies)
-    Synset('bank.n.06') the funds held by a gambling house or the dealer in some gambling games
-    Synset('bank.n.07') a slope in the turn of a road or track; the outside is higher than the inside in order to reduce the effects of centrifugal force
-    Synset('savings_bank.n.02') a container (usually with a slot in the top) for keeping money at home
-    Synset('bank.n.09') a building in which the business of banking transacted
-    Synset('bank.n.10') a flight maneuver; aircraft tips laterally about its longitudinal axis (especially in turning)
-    Synset('bank.v.01') tip laterally
-    Synset('bank.v.02') enclose with a bank
-    Synset('bank.v.03') do business with a bank or keep an account at a bank
-    Synset('bank.v.04') act as the banker in a game or in gambling
-    Synset('bank.v.05') be in the banking business
-    Synset('deposit.v.02') put into a bank account
-    Synset('bank.v.07') cover with ashes so to control the rate of burning
-    Synset('trust.v.01') have confidence or faith in
-
-Test disambiguation of POS tagged `able`.
-
-    >>> [(s, s.pos()) for s in wn.synsets('able')]
-    [(Synset('able.a.01'), 'a'), (Synset('able.s.02'), 's'), (Synset('able.s.03'), 's'), (Synset('able.s.04'), 's')]
-    >>> sent = 'people should be able to marry a person of their choice'.split()
-    >>> lesk(sent, 'able')
-    Synset('able.s.04')
-    >>> lesk(sent, 'able', pos='a')
-    Synset('able.a.01')
-
-Test behavior if there is are no matching senses.
-
-    >>> lesk('John loves Mary'.split(), 'loves', synsets=[])
+.. Copyright (C) 2001-2018 NLTK Project
+.. For license information, see LICENSE.TXT
+
+.. -*- coding: utf-8 -*-
+
+=========================
+Word Sense Disambiguation
+=========================
+
+
+Lesk Algorithm
+--------------
+
+
+Performs the classic Lesk algorithm for Word Sense Disambiguation (WSD) using
+a the definitions of the ambiguous word.
+
+Given an ambiguous word and the context in which the word occurs, Lesk returns
+a Synset with the highest number of overlapping words between the context
+sentence and different definitions from each Synset.
+
+    >>> from nltk.wsd import lesk
+    >>> sent = ['I', 'went', 'to', 'the', 'bank', 'to', 'deposit', 'money', '.']
+
+    >>> print(lesk(sent, 'bank', 'n'))
+    Synset('savings_bank.n.02')
+
+    >>> print(lesk(sent, 'bank'))
+    Synset('savings_bank.n.02')
+
+The definitions for "bank" are:
+
+    >>> from nltk.corpus import wordnet as wn
+    >>> for ss in wn.synsets('bank'):
+    ...     print(ss, ss.definition())
+    ...
+    Synset('bank.n.01') sloping land (especially the slope beside a body of water)
+    Synset('depository_financial_institution.n.01') a financial institution that accepts deposits and channels the money into lending activities
+    Synset('bank.n.03') a long ridge or pile
+    Synset('bank.n.04') an arrangement of similar objects in a row or in tiers
+    Synset('bank.n.05') a supply or stock held in reserve for future use (especially in emergencies)
+    Synset('bank.n.06') the funds held by a gambling house or the dealer in some gambling games
+    Synset('bank.n.07') a slope in the turn of a road or track; the outside is higher than the inside in order to reduce the effects of centrifugal force
+    Synset('savings_bank.n.02') a container (usually with a slot in the top) for keeping money at home
+    Synset('bank.n.09') a building in which the business of banking transacted
+    Synset('bank.n.10') a flight maneuver; aircraft tips laterally about its longitudinal axis (especially in turning)
+    Synset('bank.v.01') tip laterally
+    Synset('bank.v.02') enclose with a bank
+    Synset('bank.v.03') do business with a bank or keep an account at a bank
+    Synset('bank.v.04') act as the banker in a game or in gambling
+    Synset('bank.v.05') be in the banking business
+    Synset('deposit.v.02') put into a bank account
+    Synset('bank.v.07') cover with ashes so to control the rate of burning
+    Synset('trust.v.01') have confidence or faith in
+
+Test disambiguation of POS tagged `able`.
+
+    >>> [(s, s.pos()) for s in wn.synsets('able')]
+    [(Synset('able.a.01'), 'a'), (Synset('able.s.02'), 's'), (Synset('able.s.03'), 's'), (Synset('able.s.04'), 's')]
+    >>> sent = 'people should be able to marry a person of their choice'.split()
+    >>> lesk(sent, 'able')
+    Synset('able.s.04')
+    >>> lesk(sent, 'able', pos='a')
+    Synset('able.a.01')
+
+Test behavior if there is are no matching senses.
+
+    >>> lesk('John loves Mary'.split(), 'loves', synsets=[])