nltk 3.2.1__zip → 3.3__zip

{nltk-3.2.1 → nltk-3.3}/nltk/test/compat_fixt.py

@@ -2,6 +2,7 @@
 from __future__ import absolute_import
 from nltk.compat import PY3
 
+
 def setup_module(module):
     from nose import SkipTest
     if PY3:

nltk-3.3/nltk/test/concordance.doctest

@@ -0,0 +1,55 @@
+.. Copyright (C) 2001-2016 NLTK Project
+.. For license information, see LICENSE.TXT
+
+==================================
+Concordance Example
+==================================
+
+A concordance view shows us every occurrence of a given
+word, together with some context. Here we look up the word monstrous
+in Moby Dick by entering text1 followed by a period, then the term
+concordance, and then placing "monstrous" in parentheses:
+
+>>> from nltk.corpus import gutenberg
+>>> from nltk.text import Text
+>>> corpus = gutenberg.words('melville-moby_dick.txt')
+>>> text = Text(corpus)
+
+>>> text.concordance("monstrous") # doctest:+NORMALIZE_WHITESPACE
+Displaying 11 of 11 matches:
+ong the former , one was of a most monstrous size . ... This came towards us ,
+ON OF THE PSALMS . " Touching that monstrous bulk of the whale or ork we have r
+ll over with a heathenish array of monstrous clubs and spears . Some were thick
+d as you gazed , and wondered what monstrous cannibal and savage could ever hav
+that has survived the flood ; most monstrous and most mountainous ! That Himmal
+they might scout at Moby Dick as a monstrous fable , or still worse and more de
+th of Radney .'" CHAPTER 55 Of the Monstrous Pictures of Whales . I shall ere l
+ing Scenes . In connexion with the monstrous pictures of whales , I am strongly
+ere to enter upon those still more monstrous stories of them which are to be fo
+ght have been rummaged out of this monstrous cabinet there is no telling . But
+of Whale - Bones ; for Whales of a monstrous size are oftentimes cast up dead u
+
+>>> text.concordance("monstrous") # doctest:+ELLIPSIS, +NORMALIZE_WHITESPACE
+Displaying 11 of 11 matches:
+ong the former , one was of a most monstrous size . ... This came towards us ,
+ON OF THE PSALMS . " Touching that monstrous bulk of the whale or ork we have r
+ll over with a heathenish array of monstrous clubs and spears . Some were thick
+...
+
+=================================
+Concordance List
+=================================
+
+Often we need to store the results of concordance for further usage.
+To do so, call the concordance function with the stdout argument set
+to false:
+
+>>> from nltk.corpus import gutenberg
+>>> from nltk.text import Text
+>>> corpus = gutenberg.words('melville-moby_dick.txt')
+>>> text = Text(corpus)
+>>> con_list = text.concordance_list("monstrous")
+>>> con_list[2].line
+'ll over with a heathenish array of monstrous clubs and spears . Some were thick'
+>>> len(con_list)
+11

{nltk-3.2.1 → nltk-3.3}/nltk/test/corpus.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ================
@@ -372,50 +372,6 @@ Reading the CoNLL 2007 Dependency Treebanks:
             (frente_a , (0,9349_dólares los (de (mañana esta)))))))
       .)
 
-NLTK also provides a corpus reader for the York-Toronto-Helsinki
-Parsed Corpus of Old English Prose (YCOE); but the corpus itself is
-not included in the NLTK data package.  If you install it yourself,
-you can use NLTK to access it:
-
-    >>> from nltk.corpus import ycoe
-    >>> for tree in ycoe.parsed_sents('cocuraC')[:4]:
-    ...     print(tree) # doctest: +SKIP
-    (CP-THT
-      (C +D+atte)
-      (IP-SUB ...)
-      ...
-      (. .))
-    (IP-MAT
-      (IP-MAT-0
-        (PP (P On) (NP (ADJ o+dre) (N wisan)))...)
-      ...
-      (. .))
-    (IP-MAT
-      (NP-NOM-x-2 *exp*)
-      (NP-DAT-1 (D^D +D+am) (ADJ^D unge+dyldegum))
-      ...
-      (. .))
-    (IP-MAT
-      (ADVP (ADV Sw+a))
-      (NP-NOM-x (PRO^N hit))
-      (ADVP-TMP (ADV^T oft))
-      ...
-      (. .))
-
-If the YCOE corpus is not available, you will get an error message
-when you try to access it:
-
-    >>> from nltk.corpus import ycoe
-    >>> print(ycoe) # doctest: +SKIP
-    Traceback (most recent call last):
-    LookupError:
-    **********************************************************************
-      Resource 'corpora/ycoe' not found.  For installation
-      instructions, please see <http://nltk.org/index.php/Installation>.
-      Searched in:
-        - ...
-    **********************************************************************
-
 Word Lists and Lexicons
 =======================
 
@@ -430,7 +386,7 @@ examples illustrate the use of the wordlist corpora:
     ['A', 'a', 'aa', 'aal', 'aalii', 'aam', 'Aani', 'aardvark', 'aardwolf', ...]
 
     >>> stopwords.fileids() # doctest: +ELLIPSIS
-    ['danish', 'dutch', 'english', 'finnish', 'french', 'german', 'hungarian', ...]
+    ['arabic', 'azerbaijani', 'danish', 'dutch', 'english', 'finnish', 'french', ...]
     >>> stopwords.words('portuguese') # doctest: +ELLIPSIS
     ['de', 'a', 'o', 'que', 'e', 'do', 'da', 'em', 'um', 'para', ...]
     >>> names.fileids()
@@ -1021,6 +977,12 @@ a given lemma belongs to:
     >>> verbnet.classids('accept')
     ['approve-77', 'characterize-29.2-1-1', 'obtain-13.5.2']
 
+The `classids()` method may additionally be used to retrieve all classes
+within verbnet if nothing is passed:
+
+    >>> verbnet.classids()
+    ['accompany-51.7', 'admire-31.2', 'admire-31.2-1', 'admit-65', 'adopt-93', 'advise-37.9', 'advise-37.9-1', 'allow-64', 'amalgamate-22.2', 'amalgamate-22.2-1', 'amalgamate-22.2-1-1', 'amalgamate-22.2-2', 'amalgamate-22.2-2-1', 'amalgamate-22.2-3', 'amalgamate-22.2-3-1', 'amalgamate-22.2-3-1-1', 'amalgamate-22.2-3-2', 'amuse-31.1', 'animal_sounds-38', 'appeal-31.4', 'appeal-31.4-1', 'appeal-31.4-2', 'appeal-31.4-3', 'appear-48.1.1', 'appoint-29.1', 'approve-77', 'assessment-34', 'assuming_position-50', 'avoid-52', 'banish-10.2', 'battle-36.4', 'battle-36.4-1', 'begin-55.1', 'begin-55.1-1', 'being_dressed-41.3.3', 'bend-45.2', 'berry-13.7', 'bill-54.5', 'body_internal_motion-49', 'body_internal_states-40.6', 'braid-41.2.2', 'break-45.1', 'breathe-40.1.2', 'breathe-40.1.2-1', 'bring-11.3', 'bring-11.3-1', 'build-26.1', 'build-26.1-1', 'bulge-47.5.3', 'bump-18.4', 'bump-18.4-1', 'butter-9.9', 'calibratable_cos-45.6', 'calibratable_cos-45.6-1', 'calve-28', 'captain-29.8', 'captain-29.8-1', 'captain-29.8-1-1', 'care-88', 'care-88-1', 'carry-11.4', 'carry-11.4-1', 'carry-11.4-1-1', 'carve-21.2', 'carve-21.2-1', 'carve-21.2-2', 'change_bodily_state-40.8.4', 'characterize-29.2', 'characterize-29.2-1', 'characterize-29.2-1-1', 'characterize-29.2-1-2', 'chase-51.6', 'cheat-10.6', 'cheat-10.6-1', 'cheat-10.6-1-1', 'chew-39.2', 'chew-39.2-1', 'chew-39.2-2', 'chit_chat-37.6', 'clear-10.3', 'clear-10.3-1', 'cling-22.5', 'coil-9.6', 'coil-9.6-1', 'coloring-24', 'complain-37.8', 'complete-55.2', 'concealment-16', 'concealment-16-1', 'confess-37.10', 'confine-92', 'confine-92-1', 'conjecture-29.5', 'conjecture-29.5-1', 'conjecture-29.5-2', 'consider-29.9', 'consider-29.9-1', 'consider-29.9-1-1', 'consider-29.9-1-1-1', 'consider-29.9-2', 'conspire-71', 'consume-66', 'consume-66-1', 'contiguous_location-47.8', 'contiguous_location-47.8-1', 'contiguous_location-47.8-2', 'continue-55.3', 'contribute-13.2', 'contribute-13.2-1', 'contribute-13.2-1-1', 'contribute-13.2-1-1-1', 'contribute-13.2-2', 'contribute-13.2-2-1', 'convert-26.6.2', 'convert-26.6.2-1', 'cooking-45.3', 'cooperate-73', 'cooperate-73-1', 'cooperate-73-2', 'cooperate-73-3', 'cope-83', 'cope-83-1', 'cope-83-1-1', 'correlate-86', 'correspond-36.1', 'correspond-36.1-1', 'correspond-36.1-1-1', 'cost-54.2', 'crane-40.3.2', 'create-26.4', 'create-26.4-1', 'curtsey-40.3.3', 'cut-21.1', 'cut-21.1-1', 'debone-10.8', 'declare-29.4', 'declare-29.4-1', 'declare-29.4-1-1', 'declare-29.4-1-1-1', 'declare-29.4-1-1-2', 'declare-29.4-1-1-3', 'declare-29.4-2', 'dedicate-79', 'defend-85', 'destroy-44', 'devour-39.4', 'devour-39.4-1', 'devour-39.4-2', 'differ-23.4', 'dine-39.5', 'disappearance-48.2', 'disassemble-23.3', 'discover-84', 'discover-84-1', 'discover-84-1-1', 'dress-41.1.1', 'dressing_well-41.3.2', 'drive-11.5', 'drive-11.5-1', 'dub-29.3', 'dub-29.3-1', 'eat-39.1', 'eat-39.1-1', 'eat-39.1-2', 'enforce-63', 'engender-27', 'entity_specific_cos-45.5', 'entity_specific_modes_being-47.2', 'equip-13.4.2', 'equip-13.4.2-1', 'equip-13.4.2-1-1', 'escape-51.1', 'escape-51.1-1', 'escape-51.1-2', 'escape-51.1-2-1', 'exceed-90', 'exchange-13.6', 'exchange-13.6-1', 'exchange-13.6-1-1', 'exhale-40.1.3', 'exhale-40.1.3-1', 'exhale-40.1.3-2', 'exist-47.1', 'exist-47.1-1', 'exist-47.1-1-1', 'feeding-39.7', 'ferret-35.6', 'fill-9.8', 'fill-9.8-1', 'fit-54.3', 'flinch-40.5', 'floss-41.2.1', 'focus-87', 'forbid-67', 'force-59', 'force-59-1', 'free-80', 'free-80-1', 'fulfilling-13.4.1', 'fulfilling-13.4.1-1', 'fulfilling-13.4.1-2', 'funnel-9.3', 'funnel-9.3-1', 'funnel-9.3-2', 'funnel-9.3-2-1', 'future_having-13.3', 'get-13.5.1', 'get-13.5.1-1', 'give-13.1', 'give-13.1-1', 'gobble-39.3', 'gobble-39.3-1', 'gobble-39.3-2', 'gorge-39.6', 'groom-41.1.2', 'grow-26.2', 'help-72', 'help-72-1', 'herd-47.5.2', 'hiccup-40.1.1', 'hit-18.1', 'hit-18.1-1', 'hold-15.1', 'hold-15.1-1', 'hunt-35.1', 'hurt-40.8.3', 'hurt-40.8.3-1', 'hurt-40.8.3-1-1', 'hurt-40.8.3-2', 'illustrate-25.3', 'image_impression-25.1', 'indicate-78', 'indicate-78-1', 'indicate-78-1-1', 'inquire-37.1.2', 'instr_communication-37.4', 'investigate-35.4', 'judgement-33', 'keep-15.2', 'knead-26.5', 'learn-14', 'learn-14-1', 'learn-14-2', 'learn-14-2-1', 'leave-51.2', 'leave-51.2-1', 'lecture-37.11', 'lecture-37.11-1', 'lecture-37.11-1-1', 'lecture-37.11-2', 'light_emission-43.1', 'limit-76', 'linger-53.1', 'linger-53.1-1', 'lodge-46', 'long-32.2', 'long-32.2-1', 'long-32.2-2', 'manner_speaking-37.3', 'marry-36.2', 'marvel-31.3', 'marvel-31.3-1', 'marvel-31.3-2', 'marvel-31.3-3', 'marvel-31.3-4', 'marvel-31.3-5', 'marvel-31.3-6', 'marvel-31.3-7', 'marvel-31.3-8', 'marvel-31.3-9', 'masquerade-29.6', 'masquerade-29.6-1', 'masquerade-29.6-2', 'matter-91', 'meander-47.7', 'meet-36.3', 'meet-36.3-1', 'meet-36.3-2', 'mine-10.9', 'mix-22.1', 'mix-22.1-1', 'mix-22.1-1-1', 'mix-22.1-2', 'mix-22.1-2-1', 'modes_of_being_with_motion-47.3', 'murder-42.1', 'murder-42.1-1', 'neglect-75', 'neglect-75-1', 'neglect-75-1-1', 'neglect-75-2', 'nonvehicle-51.4.2', 'nonverbal_expression-40.2', 'obtain-13.5.2', 'obtain-13.5.2-1', 'occurrence-48.3', 'order-60', 'order-60-1', 'orphan-29.7', 'other_cos-45.4', 'pain-40.8.1', 'pay-68', 'peer-30.3', 'pelt-17.2', 'performance-26.7', 'performance-26.7-1', 'performance-26.7-1-1', 'performance-26.7-2', 'performance-26.7-2-1', 'pit-10.7', 'pocket-9.10', 'pocket-9.10-1', 'poison-42.2', 'poke-19', 'pour-9.5', 'preparing-26.3', 'preparing-26.3-1', 'preparing-26.3-2', 'price-54.4', 'push-12', 'push-12-1', 'push-12-1-1', 'put-9.1', 'put-9.1-1', 'put-9.1-2', 'put_direction-9.4', 'put_spatial-9.2', 'put_spatial-9.2-1', 'reach-51.8', 'reflexive_appearance-48.1.2', 'refrain-69', 'register-54.1', 'rely-70', 'remove-10.1', 'risk-94', 'risk-94-1', 'roll-51.3.1', 'rummage-35.5', 'run-51.3.2', 'rush-53.2', 'say-37.7', 'say-37.7-1', 'say-37.7-1-1', 'say-37.7-2', 'scribble-25.2', 'search-35.2', 'see-30.1', 'see-30.1-1', 'see-30.1-1-1', 'send-11.1', 'send-11.1-1', 'separate-23.1', 'separate-23.1-1', 'separate-23.1-2', 'settle-89', 'shake-22.3', 'shake-22.3-1', 'shake-22.3-1-1', 'shake-22.3-2', 'shake-22.3-2-1', 'sight-30.2', 'simple_dressing-41.3.1', 'slide-11.2', 'slide-11.2-1-1', 'smell_emission-43.3', 'snooze-40.4', 'sound_emission-43.2', 'sound_existence-47.4', 'spank-18.3', 'spatial_configuration-47.6', 'split-23.2', 'spray-9.7', 'spray-9.7-1', 'spray-9.7-1-1', 'spray-9.7-2', 'stalk-35.3', 'steal-10.5', 'stimulus_subject-30.4', 'stop-55.4', 'stop-55.4-1', 'substance_emission-43.4', 'succeed-74', 'succeed-74-1', 'succeed-74-1-1', 'succeed-74-2', 'suffocate-40.7', 'suspect-81', 'swarm-47.5.1', 'swarm-47.5.1-1', 'swarm-47.5.1-2', 'swarm-47.5.1-2-1', 'swat-18.2', 'talk-37.5', 'tape-22.4', 'tape-22.4-1', 'tell-37.2', 'throw-17.1', 'throw-17.1-1', 'throw-17.1-1-1', 'tingle-40.8.2', 'touch-20', 'touch-20-1', 'transcribe-25.4', 'transfer_mesg-37.1.1', 'transfer_mesg-37.1.1-1', 'transfer_mesg-37.1.1-1-1', 'try-61', 'turn-26.6.1', 'turn-26.6.1-1', 'urge-58', 'vehicle-51.4.1', 'vehicle-51.4.1-1', 'waltz-51.5', 'want-32.1', 'want-32.1-1', 'want-32.1-1-1', 'weather-57', 'weekend-56', 'wink-40.3.1', 'wink-40.3.1-1', 'wipe_instr-10.4.2', 'wipe_instr-10.4.2-1', 'wipe_manner-10.4.1', 'wipe_manner-10.4.1-1', 'wish-62', 'withdraw-82', 'withdraw-82-1', 'withdraw-82-2', 'withdraw-82-3']
+
 The primary object in the lexicon is a class record, which is stored
 as an ElementTree xml object.  The class record for a given class
 identifier is returned by the `vnclass()` method:
@@ -1061,18 +1023,42 @@ concise form.  The simplest such method is `pprint()`:
         * Theme[+concrete +force]
       Frames:
         Intransitive (Expletive Subject)
+          Example: It's raining.
           Syntax: LEX[it] LEX[[+be]] VERB
           Semantics:
             * weather(during(E), Weather_type, ?Theme)
         NP (Expletive Subject, Theme Object)
+          Example: It's raining cats and dogs.
           Syntax: LEX[it] LEX[[+be]] VERB NP[Theme]
           Semantics:
             * weather(during(E), Weather_type, Theme)
         PP (Expletive Subject, Theme-PP)
+          Example: It was pelting with rain.
           Syntax: LEX[it[+be]] VERB PREP[with] NP[Theme]
           Semantics:
             * weather(during(E), Weather_type, Theme)
 
+Verbnet gives us frames that link the syntax and semantics using an example.
+These frames are part of the corpus and we can use `frames()` to get a frame
+for a given verbnet class.
+
+    >>> frame = verbnet.frames('57')
+    >>> frame == [{'semantics': [{'arguments': [{'value': 'during(E)', 'type': 'Event'}, {'value': 'Weather_type', 'type': 'VerbSpecific'}, {'value': '?Theme', 'type': 'ThemRole'}], 'predicate_value': 'weather'}], 'example': "It's raining.", 'syntax': [{'pos_tag': 'LEX', 'modifiers': {'value': 'it', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'LEX', 'modifiers': {'value': '[+be]', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'VERB', 'modifiers': {'value': '', 'synrestrs': [], 'selrestrs': []}}], 'description': {'primary': 'Intransitive', 'secondary': 'Expletive Subject'}}, {'semantics': [{'arguments': [{'value': 'during(E)', 'type': 'Event'}, {'value': 'Weather_type', 'type': 'VerbSpecific'}, {'value': 'Theme', 'type': 'ThemRole'}], 'predicate_value': 'weather'}], 'example': "It's raining cats and dogs.", 'syntax': [{'pos_tag': 'LEX', 'modifiers': {'value': 'it', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'LEX', 'modifiers': {'value': '[+be]', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'VERB', 'modifiers': {'value': '', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'NP', 'modifiers': {'value': 'Theme', 'synrestrs': [], 'selrestrs': []}}], 'description': {'primary': 'NP', 'secondary': 'Expletive Subject, Theme Object'}}, {'semantics': [{'arguments': [{'value': 'during(E)', 'type': 'Event'}, {'value': 'Weather_type', 'type': 'VerbSpecific'}, {'value': 'Theme', 'type': 'ThemRole'}], 'predicate_value': 'weather'}], 'example': 'It was pelting with rain.', 'syntax': [{'pos_tag': 'LEX', 'modifiers': {'value': 'it[+be]', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'VERB', 'modifiers': {'value': '', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'PREP', 'modifiers': {'value': 'with', 'synrestrs': [], 'selrestrs': []}}, {'pos_tag': 'NP', 'modifiers': {'value': 'Theme', 'synrestrs': [], 'selrestrs': []}}], 'description': {'primary': 'PP', 'secondary': 'Expletive Subject, Theme-PP'}}]
+    True
+
+Verbnet corpus lets us access thematic roles individually using `themroles()`.
+
+    >>> themroles = verbnet.themroles('57')
+    >>> themroles == [{'modifiers': [{'type': 'concrete', 'value': '+'}, {'type': 'force', 'value': '+'}], 'type': 'Theme'}]
+    True
+
+Verbnet classes may also have subclasses sharing similar syntactic and semantic properties
+while having differences with the superclass. The Verbnet corpus allows us to access these
+subclasses using `subclasses()`.
+
+    >>> print(verbnet.subclasses('9.1')) #Testing for 9.1 since '57' does not have subclasses
+    ['put-9.1-1', 'put-9.1-2']
+
 
 nps_chat
 --------
@@ -1486,9 +1472,12 @@ constructor will first call its base class's constructor, and then
 store the customizable parameters.  For example, the
 `ConllChunkCorpusReader`\ 's constructor is defined as follows:
 
-    >>> def __init__(self, root, files, chunk_types):
-    ...     CorpusReader.__init__(self, root, files)
-    ...     self.chunk_types = tuple(chunk_types)
+    def __init__(self, root, fileids, chunk_types, encoding='utf8',
+                 tagset=None, separator=None):
+        ConllCorpusReader.__init__(
+                self, root, fileids, ('words', 'pos', 'chunk'),
+                chunk_types=chunk_types, encoding=encoding,
+                tagset=tagset, separator=separator)
 
 If your corpus reader does not implement any customization parameters,
 then you can often just inherit the base class's constructor.

{nltk-3.2.1 → nltk-3.3}/nltk/test/crubadan.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 Crubadan Corpus Reader

{nltk-3.2.1 → nltk-3.3}/nltk/test/data.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 =========================================

{nltk-3.2.1 → nltk-3.3}/nltk/test/dependency.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ===================

{nltk-3.2.1 → nltk-3.3}/nltk/test/discourse.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==================

{nltk-3.2.1 → nltk-3.3}/nltk/test/discourse_fixt.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
+
 # FIXME: the entire discourse.doctest is skipped if Prover9/Mace4 is
 # not installed, but there are pure-python parts that don't need Prover9.
 def setup_module(module):

{nltk-3.2.1 → nltk-3.3}/nltk/test/doctest_nose_plugin.py

@@ -12,6 +12,7 @@ from nose.plugins.doctests import Doctest, log, DocFileCase
 
 ALLOW_UNICODE = doctest.register_optionflag('ALLOW_UNICODE')
 
+
 class _UnicodeOutputChecker(doctest.OutputChecker):
     _literal_re = re.compile(r"(\W|^)[uU]([rR]?[\'\"])", re.UNICODE)
 
@@ -31,8 +32,10 @@ class _UnicodeOutputChecker(doctest.OutputChecker):
         res = doctest.OutputChecker.check_output(self, cleaned_want, cleaned_got, optionflags)
         return res
 
+
 _checker = _UnicodeOutputChecker()
 
+
 class DoctestPluginHelper(object):
     """
     This mixin adds print_function future import to all test cases.
@@ -69,7 +72,7 @@ class DoctestPluginHelper(object):
                     log.debug(
                         "Could not import %s: %s (%s)", fixt_mod, e, sys.path)
                 log.debug("Fixture module %s resolved to %s",
-                    fixt_mod, fixture_context)
+                          fixt_mod, fixture_context)
                 if hasattr(fixture_context, 'globs'):
                     globs = fixture_context.globs(globs)
             parser = doctest.DocTestParser()
@@ -88,7 +91,7 @@ class DoctestPluginHelper(object):
                 else:
                     yield case
             else:
-                yield False # no tests to load
+                yield False  # no tests to load
 
     def loadTestsFromFile(self, filename):
 
@@ -123,7 +126,7 @@ class DoctestPluginHelper(object):
         self.fixtures = options.doctestFixtures
         self.finder = doctest.DocTestFinder()
 
-        #super(DoctestPluginHelper, self).configure(options, config)
+        # super(DoctestPluginHelper, self).configure(options, config)
         self.optionflags = 0
         self.options = {}
 
@@ -138,13 +141,13 @@ class DoctestPluginHelper(object):
                         self.optionflags &= ~doctest.OPTIONFLAGS_BY_NAME[stroption[1:]]
                         continue
                     try:
-                        key,value=stroption.split('=')
+                        key, value = stroption.split('=')
                     except ValueError:
                         pass
                     else:
                         if not key in self.OPTION_BY_NAME:
                             raise ValueError()
-                        self.options[key]=value
+                        self.options[key] = value
                         continue
                 except (AttributeError, ValueError, KeyError):
                     raise ValueError("Unknown doctest option {}".format(stroption))

{nltk-3.2.1 → nltk-3.3}/nltk/test/drt.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ================================

{nltk-3.2.1 → nltk-3.3}/nltk/test/featgram.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 =========================

{nltk-3.2.1 → nltk-3.3}/nltk/test/featstruct.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==================================
@@ -334,7 +334,7 @@ base value types that have custom unification methods.  For example,
 the following feature value type encodes a range, and defines
 unification as taking the intersection on the ranges:
 
-    >>> from nltk.compat import total_ordering
+    >>> from functools import total_ordering
     >>> from nltk.featstruct import CustomFeatureValue, UnificationFailure
     >>> @total_ordering
     ... class Range(CustomFeatureValue):
@@ -1227,4 +1227,3 @@ is present.)
 
 ..
     >>> del fs1, fs2 # clean-up
-

{nltk-3.2.1 → nltk-3.3}/nltk/test/framenet.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ========
@@ -69,30 +69,45 @@ To get a list of all of the Frames in FrameNet, you can use the
 that pattern:
 
     >>> from pprint import pprint
+    >>> from operator import itemgetter
     >>> from nltk.corpus import framenet as fn
-    >>> len(fn.frames())
-    1019
-    >>> pprint(fn.frames(r'(?i)medical'))
-    [<frame ID=256 name=Medical_specialties>, <frame ID=257 name=Medical_instruments>, ...]
+    >>> from nltk.corpus.reader.framenet import PrettyList
+    >>> x = fn.frames(r'(?i)crim')
+    >>> x.sort(key=itemgetter('ID'))
+    >>> x
+    [<frame ID=200 name=Criminal_process>, <frame ID=500 name=Criminal_investigation>, ...]
+    >>> PrettyList(sorted(x, key=itemgetter('ID')))
+    [<frame ID=200 name=Criminal_process>, <frame ID=500 name=Criminal_investigation>, ...]
 
 To get the details of a particular Frame, you can use the `frame()`
 function passing in the frame number:
 
     >>> from pprint import pprint
     >>> from nltk.corpus import framenet as fn
-    >>> f = fn.frame(256)
+    >>> f = fn.frame(202)
     >>> f.ID
-    256
+    202
     >>> f.name
-    'Medical_specialties'
+    'Arrest'
     >>> f.definition # doctest: +ELLIPSIS
-    "This frame includes words that name ..."
+    "Authorities charge a Suspect, who is under suspicion of having committed a crime..."
     >>> len(f.lexUnit)
-    29
+    11
     >>> pprint(sorted([x for x in f.FE]))
-    ['Affliction', 'Body_system', 'Specialty', 'Type']
+    ['Authorities',
+     'Charges',
+     'Co-participant',
+     'Manner',
+     'Means',
+     'Offense',
+     'Place',
+     'Purpose',
+     'Source_of_legal_authority',
+     'Suspect',
+     'Time',
+     'Type']
     >>> pprint(f.frameRelations)
-    [<Parent=Cure -- Using -> Child=Medical_specialties>]
+    [<Parent=Intentionally_affect -- Inheritance -> Child=Arrest>, <Complex=Criminal_process -- Subframe -> Component=Arrest>, ...]
 
 The `frame()` function shown above returns a dict object containing
 detailed information about the Frame. See the documentation on the
@@ -105,9 +120,8 @@ expression. Note that LU names are composed of "lemma.POS", where the
 "lemma" part can be made up of either a single lexeme (e.g. 'run') or
 multiple lexemes (e.g. 'a little') (see below).
 
-    >>> from nltk.corpus import framenet as fn
-    >>> fn.frames_by_lemma(r'(?i)a little')
-    [<frame ID=189 name=Quantity>, <frame ID=2001 name=Degree>]
+    >>> PrettyList(sorted(fn.frames_by_lemma(r'(?i)a little'), key=itemgetter('ID'))) # doctest: +ELLIPSIS
+    [<frame ID=189 name=Quanti...>, <frame ID=2001 name=Degree>]
 
 -------------
 Lexical Units
@@ -175,11 +189,8 @@ Details for a specific lexical unit can be obtained using this class's
 pattern that will be matched against the name of the lexical unit:
 
     >>> from pprint import pprint
-    >>> from nltk.corpus import framenet as fn
-    >>> len(fn.lus())
-    11829
-    >>> pprint(fn.lus(r'(?i)a little'))
-    [<lu ID=14744 name=a little bit.adv>, <lu ID=14733 name=a little.n>, ...]
+    >>> PrettyList(sorted(fn.lus(r'(?i)a little'), key=itemgetter('ID')))
+    [<lu ID=14733 name=a little.n>, <lu ID=14743 name=a little.adv>, ...]
 
 You can obtain detailed information on a particular LU by calling the
 `lu()` function and passing in an LU's 'ID' number:
@@ -221,19 +232,57 @@ Annotated Documents
 -------------------
 
 The FrameNet corpus contains a small set of annotated documents. A list
-of these documents can be obtained by calling the `documents()` function:
+of these documents can be obtained by calling the `docs()` function:
 
     >>> from pprint import pprint
     >>> from nltk.corpus import framenet as fn
-    >>> docs = fn.documents()
-    >>> len(docs)
-    78
-    >>> pprint(sorted(docs[0].keys()))
-    ['ID', 'corpid', 'corpname', 'description', 'filename']
-
-Detailed information about each sentence contained in each document can
-be obtained by calling the `annotated_document()` function and supplying
-the 'ID' number of the document. For detailed information about the info
-that is for each document, see the documentation on the
-`annotated_document()` function.
-
+    >>> d = fn.docs('BellRinging')[0]
+    >>> d.corpname
+    'PropBank'
+    >>> d.sentence[49] # doctest: +ELLIPSIS
+    full-text sentence (...) in BellRinging:
+    <BLANKLINE>
+    <BLANKLINE>
+    [POS] 17 tags
+    <BLANKLINE>
+    [POS_tagset] PENN
+    <BLANKLINE>
+    [text] + [annotationSet]
+    <BLANKLINE>
+    `` I live in hopes that the ringers themselves will be drawn into
+                 *****          *******                    *****
+                 Desir          Cause_t                    Cause
+                 [1]            [3]                        [2]
+    <BLANKLINE>
+     that fuller life .
+          ******
+          Comple
+          [4]
+     (Desir=Desiring, Cause_t=Cause_to_make_noise, Cause=Cause_motion, Comple=Completeness)
+    <BLANKLINE>
+
+    >>> d.sentence[49].annotationSet[1] # doctest: +ELLIPSIS
+    annotation set (...):
+    <BLANKLINE>
+    [status] MANUAL
+    <BLANKLINE>
+    [LU] (6605) hope.n in Desiring
+    <BLANKLINE>
+    [frame] (366) Desiring
+    <BLANKLINE>
+    [GF] 2 relations
+    <BLANKLINE>
+    [PT] 2 phrases
+    <BLANKLINE>
+    [text] + [Target] + [FE] + [Noun]
+    <BLANKLINE>
+    `` I live in hopes that the ringers themselves will be drawn into
+       - ^^^^ ^^ ***** ----------------------------------------------
+       E supp su       Event
+    <BLANKLINE>
+     that fuller life .
+    -----------------
+    <BLANKLINE>
+     (E=Experiencer, su=supp)
+    <BLANKLINE>
+    <BLANKLINE>

{nltk-3.2.1 → nltk-3.3}/nltk/test/generate.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ===============================================

{nltk-3.2.1 → nltk-3.3}/nltk/test/gensim.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 =======================================
@@ -35,7 +35,7 @@ For example, to compute the cosine similarity between 2 words:
 
     >>> new_model.similarity('university','school') > 0.3
     True
-	
+
 ---------------------------
 Using the pre-trained model
 ---------------------------
@@ -45,8 +45,8 @@ The full model is from https://code.google.com/p/word2vec/ (about 3 GB).
 
     >>> from nltk.data import find
     >>> word2vec_sample = str(find('models/word2vec_sample/pruned.word2vec.txt'))
-    >>> model = gensim.models.Word2Vec.load_word2vec_format(word2vec_sample, binary=False)
-	
+    >>> model = gensim.models.KeyedVectors.load_word2vec_format(word2vec_sample, binary=False)
+
 We pruned the model to only include the most common words (~44k words).
 
     >>> len(model.vocab)
@@ -56,12 +56,12 @@ Each word is represented in the space of 300 dimensions:
 
     >>> len(model['university'])
     300
- 	
+
 Finding the top n words that are similar to a target word is simple. The result is the list of n words with the score.
 
     >>> model.most_similar(positive=['university'], topn = 3)
     [(u'universities', 0.70039...), (u'faculty', 0.67809...), (u'undergraduate', 0.65870...)]
- 	
+
 Finding a word that is not in a list is also supported, although, implementing this by yourself is simple.
 
     >>> model.doesnt_match('breakfast cereal dinner lunch'.split())
@@ -138,4 +138,3 @@ We use this code to get the `word2vec_sample` model.
 |        f.write('{} {}\n'.format(word, ' '.join(str(value) for value in model[word])))
 |
 |    f.close()
-

{nltk-3.2.1 → nltk-3.3}/nltk/test/gensim_fixt.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
+
 def setup_module(module):
     from nose import SkipTest
     try:

{nltk-3.2.1 → nltk-3.3}/nltk/test/gluesemantics.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==============================================================================
@@ -343,13 +343,12 @@ Dependency Graph to Glue Formulas
     ... 4	dog	_	NN	NN	_	2	OBJ	_	_
     ... """)
     >>> gfl = GlueDict('nltk:grammars/sample_grammars/glue.semtype').to_glueformula_list(depgraph)
-    >>> for gf in sorted(gfl):
-    ...     print(gf)
-    \P Q.exists x.(P(x) & Q(x)) : ((fv -o fr) -o ((f -o F2) -o F2))
-    \P Q.exists x.(P(x) & Q(x)) : ((iv -o ir) -o ((i -o I5) -o I5))
-    \x y.sees(x,y) : (f -o (i -o g))
-    \x.John(x) : (fv -o fr)
-    \x.dog(x) : (iv -o ir)
+    >>> print(gfl) # doctest: +SKIP
+    [\x y.sees(x,y) : (f -o (i -o g)),
+     \x.dog(x) : (iv -o ir),
+     \P Q.exists x.(P(x) & Q(x)) : ((iv -o ir) -o ((i -o I3) -o I3)),
+     \P Q.exists x.(P(x) & Q(x)) : ((fv -o fr) -o ((f -o F4) -o F4)),
+     \x.John(x) : (fv -o fr)]
     >>> glue = Glue()
     >>> for r in sorted([r.simplify().normalize() for r in glue.get_readings(glue.gfl_to_compiled(gfl))], key=str):
     ...     print(r)
@@ -375,12 +374,11 @@ Dependency Graph to LFG f-structure
 ---------------------------------
 LFG f-structure to Glue
 ---------------------------------
-    >>> for gf in sorted(fstruct.to_glueformula_list(GlueDict('nltk:grammars/sample_grammars/glue.semtype'))):
-    ...     print(gf)
-    \P Q.exists x.(P(x) & Q(x)) : ((gv -o gr) -o ((g -o G5) -o G5))
-    \P Q.exists x.(P(x) & Q(x)) : ((iv -o ir) -o ((i -o I2) -o I2))
-    \x y.sees(x,y) : (i -o (g -o f))
-    \x.John(x) : (iv -o ir)
-    \x.dog(x) : (gv -o gr)
+    >>> fstruct.to_glueformula_list(GlueDict('nltk:grammars/sample_grammars/glue.semtype')) # doctest: +SKIP
+    [\x y.sees(x,y) : (i -o (g -o f)),
+     \x.dog(x) : (gv -o gr),
+     \P Q.exists x.(P(x) & Q(x)) : ((gv -o gr) -o ((g -o G3) -o G3)),
+     \P Q.exists x.(P(x) & Q(x)) : ((iv -o ir) -o ((i -o I4) -o I4)),
+     \x.John(x) : (iv -o ir)]
 
 .. see gluesemantics_malt.doctest for more

{nltk-3.2.1 → nltk-3.3}/nltk/test/gluesemantics_malt.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 .. see also: gluesemantics.doctest

{nltk-3.2.1 → nltk-3.3}/nltk/test/gluesemantics_malt_fixt.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
+
 def setup_module(module):
     from nose import SkipTest
     from nltk.parse.malt import MaltParser

{nltk-3.2.1 → nltk-3.3}/nltk/test/grammar.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ===============