nltk 3.2__zip → 3.3__zip
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {nltk-3.2 → nltk-3.3}/INSTALL.txt +6 -6
- {nltk-3.2 → nltk-3.3}/LICENSE.txt +13 -13
- {nltk-3.2 → nltk-3.3}/MANIFEST.in +6 -6
- {nltk-3.2/nltk.egg-info → nltk-3.3}/PKG-INFO +13 -5
- nltk-3.2/README.txt → nltk-3.3/README.md +49 -48
- nltk-3.3/nltk/VERSION +1 -0
- {nltk-3.2 → nltk-3.3}/nltk/__init__.py +185 -185
- {nltk-3.2 → nltk-3.3}/nltk/app/__init__.py +52 -53
- {nltk-3.2 → nltk-3.3}/nltk/app/chartparser_app.py +2276 -2276
- {nltk-3.2 → nltk-3.3}/nltk/app/chunkparser_app.py +1262 -1264
- {nltk-3.2 → nltk-3.3}/nltk/app/collocations_app.py +347 -350
- {nltk-3.2 → nltk-3.3}/nltk/app/concordance_app.py +568 -570
- {nltk-3.2 → nltk-3.3}/nltk/app/nemo_app.py +156 -155
- {nltk-3.2 → nltk-3.3}/nltk/app/rdparser_app.py +892 -894
- {nltk-3.2 → nltk-3.3}/nltk/app/srparser_app.py +809 -809
- {nltk-3.2 → nltk-3.3}/nltk/app/wordfreq_app.py +32 -32
- {nltk-3.2 → nltk-3.3}/nltk/app/wordnet_app.py +968 -968
- {nltk-3.2 → nltk-3.3}/nltk/book.py +91 -90
- {nltk-3.2 → nltk-3.3}/nltk/ccg/__init__.py +22 -22
- {nltk-3.2 → nltk-3.3}/nltk/ccg/api.py +359 -335
- {nltk-3.2 → nltk-3.3}/nltk/ccg/chart.py +394 -361
- {nltk-3.2 → nltk-3.3}/nltk/ccg/combinator.py +343 -312
- {nltk-3.2 → nltk-3.3}/nltk/ccg/lexicon.py +328 -290
- nltk-3.3/nltk/ccg/logic.py +46 -0
- {nltk-3.2 → nltk-3.3}/nltk/chat/__init__.py +49 -49
- {nltk-3.2 → nltk-3.3}/nltk/chat/eliza.py +244 -244
- {nltk-3.2 → nltk-3.3}/nltk/chat/iesha.py +140 -140
- {nltk-3.2 → nltk-3.3}/nltk/chat/rude.py +92 -92
- {nltk-3.2 → nltk-3.3}/nltk/chat/suntsu.py +117 -117
- {nltk-3.2 → nltk-3.3}/nltk/chat/util.py +122 -120
- {nltk-3.2 → nltk-3.3}/nltk/chat/zen.py +282 -282
- {nltk-3.2 → nltk-3.3}/nltk/chunk/__init__.py +190 -190
- {nltk-3.2 → nltk-3.3}/nltk/chunk/api.py +51 -51
- {nltk-3.2 → nltk-3.3}/nltk/chunk/named_entity.py +331 -331
- {nltk-3.2 → nltk-3.3}/nltk/chunk/regexp.py +1390 -1384
- {nltk-3.2 → nltk-3.3}/nltk/chunk/util.py +600 -600
- {nltk-3.2 → nltk-3.3}/nltk/classify/__init__.py +98 -98
- {nltk-3.2 → nltk-3.3}/nltk/classify/api.py +193 -193
- {nltk-3.2 → nltk-3.3}/nltk/classify/decisiontree.py +295 -295
- {nltk-3.2 → nltk-3.3}/nltk/classify/maxent.py +1510 -1492
- {nltk-3.2 → nltk-3.3}/nltk/classify/megam.py +179 -178
- {nltk-3.2 → nltk-3.3}/nltk/classify/naivebayes.py +245 -242
- {nltk-3.2 → nltk-3.3}/nltk/classify/positivenaivebayes.py +170 -170
- {nltk-3.2 → nltk-3.3}/nltk/classify/rte_classify.py +160 -191
- {nltk-3.2 → nltk-3.3}/nltk/classify/scikitlearn.py +153 -151
- {nltk-3.2 → nltk-3.3}/nltk/classify/senna.py +183 -181
- {nltk-3.2 → nltk-3.3}/nltk/classify/svm.py +15 -15
- {nltk-3.2 → nltk-3.3}/nltk/classify/tadm.py +113 -112
- {nltk-3.2 → nltk-3.3}/nltk/classify/textcat.py +193 -193
- {nltk-3.2 → nltk-3.3}/nltk/classify/util.py +324 -312
- {nltk-3.2 → nltk-3.3}/nltk/classify/weka.py +346 -345
- {nltk-3.2 → nltk-3.3}/nltk/cluster/__init__.py +86 -86
- {nltk-3.2 → nltk-3.3}/nltk/cluster/api.py +74 -70
- {nltk-3.2 → nltk-3.3}/nltk/cluster/em.py +247 -247
- {nltk-3.2 → nltk-3.3}/nltk/cluster/gaac.py +168 -168
- {nltk-3.2 → nltk-3.3}/nltk/cluster/kmeans.py +221 -221
- {nltk-3.2 → nltk-3.3}/nltk/cluster/util.py +304 -289
- nltk-3.3/nltk/collections.py +640 -0
- {nltk-3.2 → nltk-3.3}/nltk/collocations.py +388 -388
- nltk-3.3/nltk/compat.py +365 -0
- {nltk-3.2 → nltk-3.3}/nltk/corpus/__init__.py +341 -320
- {nltk-3.2 → nltk-3.3}/nltk/corpus/europarl_raw.py +44 -44
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/__init__.py +147 -145
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/aligned.py +115 -114
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/api.py +448 -446
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/bnc.py +252 -252
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/bracket_parse.py +227 -227
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/categorized_sents.py +179 -178
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/chasen.py +140 -139
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/childes.py +522 -494
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/chunked.py +212 -212
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/cmudict.py +97 -95
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/comparative_sents.py +280 -278
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/conll.py +528 -521
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/crubadan.py +116 -116
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/dependency.py +101 -101
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/framenet.py +3059 -2093
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ieer.py +112 -111
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/indian.py +85 -86
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ipipan.py +332 -331
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/knbc.py +187 -187
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/lin.py +156 -156
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/mte.py +311 -310
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nkjp.py +429 -428
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nombank.py +421 -421
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nps_chat.py +73 -73
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/opinion_lexicon.py +115 -115
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/panlex_lite.py +165 -165
- nltk-3.3/nltk/corpus/reader/pl196x.py +292 -0
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/plaintext.py +232 -233
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ppattach.py +96 -95
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/propbank.py +479 -481
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/pros_cons.py +128 -126
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/reviews.py +330 -328
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/rte.py +144 -146
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/semcor.py +256 -256
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/senseval.py +203 -201
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/sentiwordnet.py +137 -137
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/sinica_treebank.py +75 -75
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/string_category.py +60 -59
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/switchboard.py +119 -119
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/tagged.py +295 -294
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/timit.py +452 -450
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/toolbox.py +68 -68
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/twitter.py +155 -157
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/udhr.py +80 -80
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/util.py +804 -800
- nltk-3.3/nltk/corpus/reader/verbnet.py +595 -0
- nltk-3.3/nltk/corpus/reader/wordlist.py +134 -0
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/wordnet.py +2108 -2036
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/xmldocs.py +392 -387
- {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ycoe.py +243 -242
- {nltk-3.2 → nltk-3.3}/nltk/corpus/util.py +144 -127
- {nltk-3.2 → nltk-3.3}/nltk/data.py +1487 -1451
- {nltk-3.2 → nltk-3.3}/nltk/decorators.py +219 -215
- {nltk-3.2 → nltk-3.3}/nltk/downloader.py +2278 -2274
- {nltk-3.2 → nltk-3.3}/nltk/draw/__init__.py +27 -27
- {nltk-3.2 → nltk-3.3}/nltk/draw/cfg.py +774 -777
- {nltk-3.2 → nltk-3.3}/nltk/draw/dispersion.py +58 -58
- {nltk-3.2 → nltk-3.3}/nltk/draw/table.py +1098 -1098
- {nltk-3.2 → nltk-3.3}/nltk/draw/tree.py +963 -966
- {nltk-3.2 → nltk-3.3}/nltk/draw/util.py +2356 -2356
- {nltk-3.2 → nltk-3.3}/nltk/featstruct.py +2617 -2500
- {nltk-3.2 → nltk-3.3}/nltk/grammar.py +1559 -1516
- {nltk-3.2 → nltk-3.3}/nltk/help.py +56 -56
- {nltk-3.2 → nltk-3.3}/nltk/inference/__init__.py +20 -20
- {nltk-3.2 → nltk-3.3}/nltk/inference/api.py +597 -589
- {nltk-3.2 → nltk-3.3}/nltk/inference/discourse.py +612 -608
- {nltk-3.2 → nltk-3.3}/nltk/inference/mace.py +311 -311
- {nltk-3.2 → nltk-3.3}/nltk/inference/nonmonotonic.py +509 -509
- {nltk-3.2 → nltk-3.3}/nltk/inference/prover9.py +431 -431
- {nltk-3.2 → nltk-3.3}/nltk/inference/resolution.py +687 -687
- {nltk-3.2 → nltk-3.3}/nltk/inference/tableau.py +607 -607
- {nltk-3.2 → nltk-3.3}/nltk/internals.py +982 -982
- {nltk-3.2 → nltk-3.3}/nltk/jsontags.py +63 -63
- {nltk-3.2 → nltk-3.3}/nltk/lazyimport.py +142 -142
- {nltk-3.2 → nltk-3.3}/nltk/metrics/__init__.py +30 -29
- {nltk-3.2 → nltk-3.3}/nltk/metrics/agreement.py +421 -401
- nltk-3.3/nltk/metrics/aline.py +607 -0
- {nltk-3.2 → nltk-3.3}/nltk/metrics/association.py +414 -410
- {nltk-3.2 → nltk-3.3}/nltk/metrics/confusionmatrix.py +206 -206
- {nltk-3.2 → nltk-3.3}/nltk/metrics/distance.py +207 -202
- {nltk-3.2 → nltk-3.3}/nltk/metrics/paice.py +381 -381
- {nltk-3.2 → nltk-3.3}/nltk/metrics/scores.py +228 -228
- {nltk-3.2 → nltk-3.3}/nltk/metrics/segmentation.py +231 -232
- {nltk-3.2 → nltk-3.3}/nltk/metrics/spearman.py +69 -69
- {nltk-3.2 → nltk-3.3}/nltk/misc/__init__.py +11 -11
- {nltk-3.2 → nltk-3.3}/nltk/misc/babelfish.py +10 -10
- {nltk-3.2 → nltk-3.3}/nltk/misc/chomsky.py +135 -133
- {nltk-3.2 → nltk-3.3}/nltk/misc/minimalset.py +83 -83
- {nltk-3.2 → nltk-3.3}/nltk/misc/sort.py +157 -157
- {nltk-3.2 → nltk-3.3}/nltk/misc/wordfinder.py +129 -129
- {nltk-3.2 → nltk-3.3}/nltk/parse/__init__.py +81 -80
- {nltk-3.2 → nltk-3.3}/nltk/parse/api.py +66 -66
- {nltk-3.2 → nltk-3.3}/nltk/parse/bllip.py +282 -282
- {nltk-3.2 → nltk-3.3}/nltk/parse/chart.py +1682 -1681
- nltk-3.3/nltk/parse/corenlp.py +780 -0
- {nltk-3.2 → nltk-3.3}/nltk/parse/dependencygraph.py +760 -758
- {nltk-3.2 → nltk-3.3}/nltk/parse/earleychart.py +452 -451
- {nltk-3.2 → nltk-3.3}/nltk/parse/evaluate.py +129 -129
- {nltk-3.2 → nltk-3.3}/nltk/parse/featurechart.py +580 -578
- {nltk-3.2 → nltk-3.3}/nltk/parse/generate.py +87 -76
- {nltk-3.2 → nltk-3.3}/nltk/parse/malt.py +356 -356
- {nltk-3.2 → nltk-3.3}/nltk/parse/nonprojectivedependencyparser.py +783 -783
- {nltk-3.2 → nltk-3.3}/nltk/parse/pchart.py +522 -522
- {nltk-3.2 → nltk-3.3}/nltk/parse/projectivedependencyparser.py +579 -578
- {nltk-3.2 → nltk-3.3}/nltk/parse/recursivedescent.py +655 -656
- {nltk-3.2 → nltk-3.3}/nltk/parse/shiftreduce.py +458 -459
- {nltk-3.2 → nltk-3.3}/nltk/parse/stanford.py +431 -406
- {nltk-3.2 → nltk-3.3}/nltk/parse/transitionparser.py +774 -772
- {nltk-3.2 → nltk-3.3}/nltk/parse/util.py +231 -231
- {nltk-3.2 → nltk-3.3}/nltk/parse/viterbi.py +401 -401
- {nltk-3.2 → nltk-3.3}/nltk/probability.py +2410 -2355
- {nltk-3.2 → nltk-3.3}/nltk/sem/__init__.py +61 -61
- {nltk-3.2 → nltk-3.3}/nltk/sem/boxer.py +1261 -1261
- {nltk-3.2 → nltk-3.3}/nltk/sem/chat80.py +782 -782
- {nltk-3.2 → nltk-3.3}/nltk/sem/cooper_storage.py +118 -118
- {nltk-3.2 → nltk-3.3}/nltk/sem/drt.py +1258 -1257
- {nltk-3.2 → nltk-3.3}/nltk/sem/drt_glue_demo.py +485 -489
- {nltk-3.2 → nltk-3.3}/nltk/sem/evaluate.py +790 -784
- {nltk-3.2 → nltk-3.3}/nltk/sem/glue.py +696 -694
- {nltk-3.2 → nltk-3.3}/nltk/sem/hole.py +386 -384
- {nltk-3.2 → nltk-3.3}/nltk/sem/lfg.py +210 -208
- {nltk-3.2 → nltk-3.3}/nltk/sem/linearlogic.py +451 -449
- {nltk-3.2 → nltk-3.3}/nltk/sem/logic.py +1910 -1910
- {nltk-3.2 → nltk-3.3}/nltk/sem/relextract.py +476 -483
- {nltk-3.2 → nltk-3.3}/nltk/sem/skolemize.py +101 -101
- {nltk-3.2 → nltk-3.3}/nltk/sem/util.py +249 -249
- {nltk-3.2 → nltk-3.3}/nltk/sentiment/__init__.py +14 -14
- {nltk-3.2 → nltk-3.3}/nltk/sentiment/sentiment_analyzer.py +229 -229
- {nltk-3.2 → nltk-3.3}/nltk/sentiment/util.py +762 -752
- {nltk-3.2 → nltk-3.3}/nltk/sentiment/vader.py +443 -445
- {nltk-3.2 → nltk-3.3}/nltk/stem/__init__.py +31 -33
- {nltk-3.2 → nltk-3.3}/nltk/stem/api.py +28 -25
- nltk-3.3/nltk/stem/arlstem.py +369 -0
- {nltk-3.2 → nltk-3.3}/nltk/stem/isri.py +345 -345
- {nltk-3.2 → nltk-3.3}/nltk/stem/lancaster.py +337 -310
- nltk-3.3/nltk/stem/porter.py +710 -0
- {nltk-3.2 → nltk-3.3}/nltk/stem/regexp.py +61 -61
- {nltk-3.2 → nltk-3.3}/nltk/stem/rslp.py +142 -142
- {nltk-3.2 → nltk-3.3}/nltk/stem/snowball.py +4236 -3712
- {nltk-3.2 → nltk-3.3}/nltk/stem/util.py +22 -12
- {nltk-3.2 → nltk-3.3}/nltk/stem/wordnet.py +51 -51
- {nltk-3.2 → nltk-3.3}/nltk/tag/__init__.py +152 -127
- {nltk-3.2 → nltk-3.3}/nltk/tag/api.py +86 -81
- {nltk-3.2 → nltk-3.3}/nltk/tag/brill.py +424 -426
- {nltk-3.2 → nltk-3.3}/nltk/tag/brill_trainer.py +608 -608
- {nltk-3.2 → nltk-3.3}/nltk/tag/crf.py +204 -200
- {nltk-3.2 → nltk-3.3}/nltk/tag/hmm.py +1277 -1277
- {nltk-3.2 → nltk-3.3}/nltk/tag/hunpos.py +132 -132
- {nltk-3.2 → nltk-3.3}/nltk/tag/mapping.py +101 -101
- {nltk-3.2 → nltk-3.3}/nltk/tag/perceptron.py +329 -314
- {nltk-3.2 → nltk-3.3}/nltk/tag/senna.py +147 -145
- {nltk-3.2 → nltk-3.3}/nltk/tag/sequential.py +740 -736
- {nltk-3.2 → nltk-3.3}/nltk/tag/stanford.py +219 -196
- {nltk-3.2 → nltk-3.3}/nltk/tag/tnt.py +595 -604
- {nltk-3.2 → nltk-3.3}/nltk/tag/util.py +72 -72
- {nltk-3.2 → nltk-3.3}/nltk/tbl/__init__.py +28 -28
- {nltk-3.2 → nltk-3.3}/nltk/tbl/api.py +1 -1
- {nltk-3.2 → nltk-3.3}/nltk/tbl/demo.py +366 -366
- {nltk-3.2 → nltk-3.3}/nltk/tbl/erroranalysis.py +39 -39
- {nltk-3.2 → nltk-3.3}/nltk/tbl/feature.py +259 -261
- {nltk-3.2 → nltk-3.3}/nltk/tbl/rule.py +321 -321
- {nltk-3.2 → nltk-3.3}/nltk/tbl/template.py +303 -308
- {nltk-3.2 → nltk-3.3}/nltk/test/__init__.py +18 -18
- {nltk-3.2 → nltk-3.3}/nltk/test/all.py +24 -23
- {nltk-3.2 → nltk-3.3}/nltk/test/bleu.doctest +14 -14
- {nltk-3.2 → nltk-3.3}/nltk/test/bnc.doctest +60 -60
- {nltk-3.2 → nltk-3.3}/nltk/test/ccg.doctest +376 -395
- nltk-3.3/nltk/test/ccg_semantics.doctest +553 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/chat80.doctest +234 -234
- {nltk-3.2 → nltk-3.3}/nltk/test/childes.doctest +184 -184
- {nltk-3.2 → nltk-3.3}/nltk/test/childes_fixt.py +14 -13
- {nltk-3.2 → nltk-3.3}/nltk/test/chunk.doctest +373 -373
- {nltk-3.2 → nltk-3.3}/nltk/test/classify.doctest +185 -185
- {nltk-3.2 → nltk-3.3}/nltk/test/classify_fixt.py +11 -10
- nltk-3.3/nltk/test/collections.doctest +20 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/collocations.doctest +276 -276
- {nltk-3.2 → nltk-3.3}/nltk/test/compat.doctest +134 -138
- {nltk-3.2 → nltk-3.3}/nltk/test/compat_fixt.py +9 -8
- nltk-3.3/nltk/test/concordance.doctest +55 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/corpus.doctest +2200 -2212
- {nltk-3.2 → nltk-3.3}/nltk/test/corpus_fixt.py +3 -3
- {nltk-3.2 → nltk-3.3}/nltk/test/crubadan.doctest +65 -65
- {nltk-3.2 → nltk-3.3}/nltk/test/data.doctest +379 -379
- {nltk-3.2 → nltk-3.3}/nltk/test/dependency.doctest +241 -241
- {nltk-3.2 → nltk-3.3}/nltk/test/discourse.doctest +546 -546
- {nltk-3.2 → nltk-3.3}/nltk/test/discourse_fixt.py +14 -13
- {nltk-3.2 → nltk-3.3}/nltk/test/doctest_nose_plugin.py +159 -156
- {nltk-3.2 → nltk-3.3}/nltk/test/drt.doctest +517 -517
- {nltk-3.2 → nltk-3.3}/nltk/test/featgram.doctest +607 -607
- {nltk-3.2 → nltk-3.3}/nltk/test/featstruct.doctest +1229 -1230
- {nltk-3.2 → nltk-3.3}/nltk/test/framenet.doctest +288 -239
- {nltk-3.2 → nltk-3.3}/nltk/test/generate.doctest +67 -67
- {nltk-3.2 → nltk-3.3}/nltk/test/gensim.doctest +140 -141
- {nltk-3.2 → nltk-3.3}/nltk/test/gensim_fixt.py +10 -9
- {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics.doctest +384 -386
- {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics_malt.doctest +68 -68
- {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics_malt_fixt.py +12 -11
- {nltk-3.2 → nltk-3.3}/nltk/test/grammar.doctest +48 -48
- {nltk-3.2 → nltk-3.3}/nltk/test/grammartestsuites.doctest +109 -109
- {nltk-3.2 → nltk-3.3}/nltk/test/index.doctest +100 -100
- {nltk-3.2 → nltk-3.3}/nltk/test/inference.doctest +534 -534
- {nltk-3.2 → nltk-3.3}/nltk/test/inference_fixt.py +12 -11
- {nltk-3.2 → nltk-3.3}/nltk/test/internals.doctest +140 -140
- {nltk-3.2 → nltk-3.3}/nltk/test/japanese.doctest +48 -48
- {nltk-3.2 → nltk-3.3}/nltk/test/logic.doctest +1098 -1098
- {nltk-3.2 → nltk-3.3}/nltk/test/metrics.doctest +270 -270
- {nltk-3.2 → nltk-3.3}/nltk/test/misc.doctest +118 -118
- {nltk-3.2 → nltk-3.3}/nltk/test/nonmonotonic.doctest +286 -286
- {nltk-3.2 → nltk-3.3}/nltk/test/nonmonotonic_fixt.py +12 -11
- {nltk-3.2 → nltk-3.3}/nltk/test/paice.doctest +35 -35
- {nltk-3.2 → nltk-3.3}/nltk/test/parse.doctest +884 -884
- {nltk-3.2 → nltk-3.3}/nltk/test/portuguese_en.doctest +565 -565
- {nltk-3.2 → nltk-3.3}/nltk/test/portuguese_en_fixt.py +16 -16
- {nltk-3.2 → nltk-3.3}/nltk/test/probability.doctest +304 -304
- {nltk-3.2 → nltk-3.3}/nltk/test/probability_fixt.py +13 -12
- {nltk-3.2 → nltk-3.3}/nltk/test/propbank.doctest +176 -176
- {nltk-3.2 → nltk-3.3}/nltk/test/relextract.doctest +263 -263
- {nltk-3.2 → nltk-3.3}/nltk/test/resolution.doctest +221 -221
- {nltk-3.2 → nltk-3.3}/nltk/test/runtests.py +86 -64
- {nltk-3.2 → nltk-3.3}/nltk/test/segmentation_fixt.py +10 -10
- {nltk-3.2 → nltk-3.3}/nltk/test/semantics.doctest +665 -665
- {nltk-3.2 → nltk-3.3}/nltk/test/semantics_fixt.py +7 -7
- {nltk-3.2 → nltk-3.3}/nltk/test/sentiment.doctest +233 -233
- {nltk-3.2 → nltk-3.3}/nltk/test/sentiwordnet.doctest +41 -41
- {nltk-3.2 → nltk-3.3}/nltk/test/simple.doctest +85 -85
- {nltk-3.2 → nltk-3.3}/nltk/test/stem.doctest +78 -78
- {nltk-3.2 → nltk-3.3}/nltk/test/tag.doctest +33 -33
- {nltk-3.2 → nltk-3.3}/nltk/test/tokenize.doctest +273 -166
- {nltk-3.2 → nltk-3.3}/nltk/test/toolbox.doctest +307 -307
- {nltk-3.2 → nltk-3.3}/nltk/test/translate.doctest +242 -242
- {nltk-3.2 → nltk-3.3}/nltk/test/translate_fixt.py +3 -3
- {nltk-3.2 → nltk-3.3}/nltk/test/tree.doctest +1101 -1101
- {nltk-3.2 → nltk-3.3}/nltk/test/treeprettyprinter.doctest +127 -127
- {nltk-3.2 → nltk-3.3}/nltk/test/treetransforms.doctest +156 -156
- nltk-3.3/nltk/test/unit/test_2x_compat.py +63 -0
- nltk-3.3/nltk/test/unit/test_aline.py +52 -0
- nltk-3.3/nltk/test/unit/test_chunk.py +56 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_classify.py +55 -53
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_collocations.py +88 -79
- nltk-3.3/nltk/test/unit/test_concordance.py +98 -0
- nltk-3.3/nltk/test/unit/test_corenlp.py +1000 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_corpora.py +200 -183
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_corpus_views.py +45 -45
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_hmm.py +88 -88
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_json2csv_corpus.py +188 -187
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_naivebayes.py +26 -26
- nltk-3.3/nltk/test/unit/test_rte_classify.py +86 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_seekable_unicode_stream_reader.py +124 -124
- nltk-3.3/nltk/test/unit/test_senna.py +74 -0
- nltk-3.3/nltk/test/unit/test_stem.py +121 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_tag.py +20 -20
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_tgrep.py +628 -626
- nltk-3.3/nltk/test/unit/test_tokenize.py +168 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_twitter_auth.py +185 -185
- nltk-3.3/nltk/test/unit/test_wordnet.py +134 -0
- nltk-3.3/nltk/test/unit/translate/test_bleu.py +244 -0
- nltk-3.3/nltk/test/unit/translate/test_gdfa.py +57 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm1.py +75 -75
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm2.py +87 -87
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm3.py +105 -105
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm4.py +126 -126
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm5.py +166 -166
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm_model.py +270 -270
- nltk-3.3/nltk/test/unit/translate/test_nist.py +37 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_stack_decoder.py +300 -300
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/utils.py +41 -41
- {nltk-3.2 → nltk-3.3}/nltk/test/util.doctest +48 -48
- {nltk-3.2 → nltk-3.3}/nltk/test/wordnet.doctest +595 -581
- {nltk-3.2 → nltk-3.3}/nltk/test/wordnet_fixt.py +7 -6
- {nltk-3.2 → nltk-3.3}/nltk/test/wordnet_lch.doctest +53 -53
- {nltk-3.2 → nltk-3.3}/nltk/test/wsd.doctest +68 -68
- {nltk-3.2 → nltk-3.3}/nltk/text.py +663 -610
- {nltk-3.2 → nltk-3.3}/nltk/tgrep.py +938 -937
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/__init__.py +130 -107
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/api.py +77 -78
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/casual.py +343 -342
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/mwe.py +120 -120
- nltk-3.3/nltk/tokenize/nist.py +173 -0
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/punkt.py +1620 -1601
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/regexp.py +208 -202
- nltk-3.3/nltk/tokenize/repp.py +151 -0
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/sexpr.py +140 -142
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/simple.py +138 -136
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/stanford.py +117 -113
- nltk-3.3/nltk/tokenize/stanford_segmenter.py +246 -0
- {nltk-3.2 → nltk-3.3}/nltk/tokenize/texttiling.py +458 -460
- nltk-3.3/nltk/tokenize/toktok.py +155 -0
- nltk-3.3/nltk/tokenize/treebank.py +363 -0
- nltk-3.3/nltk/tokenize/util.py +261 -0
- {nltk-3.2 → nltk-3.3}/nltk/toolbox.py +499 -497
- {nltk-3.2 → nltk-3.3}/nltk/translate/__init__.py +24 -24
- {nltk-3.2 → nltk-3.3}/nltk/translate/api.py +331 -321
- {nltk-3.2 → nltk-3.3}/nltk/translate/bleu_score.py +615 -556
- nltk-3.3/nltk/translate/chrf_score.py +137 -0
- {nltk-3.2 → nltk-3.3}/nltk/translate/gale_church.py +248 -235
- {nltk-3.2 → nltk-3.3}/nltk/translate/gdfa.py +135 -131
- nltk-3.3/nltk/translate/gleu_score.py +193 -0
- {nltk-3.2 → nltk-3.3}/nltk/translate/ibm1.py +250 -241
- {nltk-3.2 → nltk-3.3}/nltk/translate/ibm2.py +308 -308
- {nltk-3.2 → nltk-3.3}/nltk/translate/ibm3.py +337 -337
- {nltk-3.2 → nltk-3.3}/nltk/translate/ibm4.py +467 -467
- {nltk-3.2 → nltk-3.3}/nltk/translate/ibm5.py +639 -639
- {nltk-3.2 → nltk-3.3}/nltk/translate/ibm_model.py +536 -533
- {nltk-3.2 → nltk-3.3}/nltk/translate/metrics.py +40 -40
- nltk-3.3/nltk/translate/nist_score.py +178 -0
- {nltk-3.2 → nltk-3.3}/nltk/translate/phrase_based.py +175 -175
- {nltk-3.2 → nltk-3.3}/nltk/translate/ribes_score.py +325 -325
- {nltk-3.2 → nltk-3.3}/nltk/translate/stack_decoder.py +499 -495
- {nltk-3.2 → nltk-3.3}/nltk/tree.py +1605 -1603
- {nltk-3.2 → nltk-3.3}/nltk/treeprettyprinter.py +564 -564
- {nltk-3.2 → nltk-3.3}/nltk/treetransforms.py +309 -309
- {nltk-3.2 → nltk-3.3}/nltk/twitter/__init__.py +28 -28
- {nltk-3.2 → nltk-3.3}/nltk/twitter/api.py +141 -136
- {nltk-3.2 → nltk-3.3}/nltk/twitter/common.py +264 -258
- {nltk-3.2 → nltk-3.3}/nltk/twitter/twitter_demo.py +288 -288
- {nltk-3.2 → nltk-3.3}/nltk/twitter/twitterclient.py +530 -530
- {nltk-3.2 → nltk-3.3}/nltk/twitter/util.py +147 -146
- nltk-3.3/nltk/util.py +751 -0
- {nltk-3.2 → nltk-3.3}/nltk/wsd.py +53 -53
- {nltk-3.2 → nltk-3.3/nltk.egg-info}/PKG-INFO +13 -5
- {nltk-3.2 → nltk-3.3}/nltk.egg-info/SOURCES.txt +26 -3
- nltk-3.3/nltk.egg-info/requires.txt +31 -0
- {nltk-3.2 → nltk-3.3}/setup.cfg +0 -1
- {nltk-3.2 → nltk-3.3}/setup.py +102 -75
- nltk-3.2/nltk/VERSION +0 -1
- nltk-3.2/nltk/compat.py +0 -680
- nltk-3.2/nltk/corpus/reader/pl196x.py +0 -278
- nltk-3.2/nltk/corpus/reader/verbnet.py +0 -408
- nltk-3.2/nltk/corpus/reader/wordlist.py +0 -37
- nltk-3.2/nltk/sentiment/vader_lexicon.txt +0 -7517
- nltk-3.2/nltk/six.py +0 -868
- nltk-3.2/nltk/stem/porter.py +0 -692
- nltk-3.2/nltk/test/unit/test_2x_compat.py +0 -26
- nltk-3.2/nltk/test/unit/test_stem.py +0 -36
- nltk-3.2/nltk/test/unit/test_tokenize.py +0 -23
- nltk-3.2/nltk/test/unit/translate/test_bleu.py +0 -84
- nltk-3.2/nltk/tokenize/treebank.py +0 -124
- nltk-3.2/nltk/tokenize/util.py +0 -90
- nltk-3.2/nltk/util.py +0 -1364
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/__init__.py +0 -0
- {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/__init__.py +0 -0
- {nltk-3.2 → nltk-3.3}/nltk.egg-info/dependency_links.txt +0 -0
- {nltk-3.2 → nltk-3.3}/nltk.egg-info/not-zip-safe +0 -0
- {nltk-3.2 → nltk-3.3}/nltk.egg-info/top_level.txt +0 -0
|
@@ -1,350 +1,347 @@
|
|
|
1
|
-
# Natural Language Toolkit: Collocations Application
|
|
2
|
-
# Much of the GUI code is imported from concordance.py; We intend to merge these tools together
|
|
3
|
-
# Copyright (C) 2001-
|
|
4
|
-
# Author: Sumukh Ghodke <sghodke@csse.unimelb.edu.au>
|
|
5
|
-
# URL: <http://nltk.org/>
|
|
6
|
-
# For license information, see LICENSE.TXT
|
|
7
|
-
#
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
from __future__ import division
|
|
11
|
-
|
|
12
|
-
import
|
|
13
|
-
|
|
14
|
-
import
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
from nltk.
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
self.
|
|
76
|
-
self.
|
|
77
|
-
self.top
|
|
78
|
-
self.
|
|
79
|
-
self.
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
top.
|
|
86
|
-
top.
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
self.
|
|
93
|
-
self.
|
|
94
|
-
self.
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
innerframe =
|
|
101
|
-
|
|
102
|
-
self.
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
om
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
self.
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
rescntmenu
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
|
|
135
|
-
|
|
136
|
-
|
|
137
|
-
self.
|
|
138
|
-
|
|
139
|
-
def
|
|
140
|
-
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
|
|
150
|
-
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
|
|
154
|
-
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
innerframe
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
self.
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
self.
|
|
172
|
-
|
|
173
|
-
def
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
|
|
180
|
-
|
|
181
|
-
|
|
182
|
-
|
|
183
|
-
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
self.
|
|
187
|
-
|
|
188
|
-
|
|
189
|
-
self.
|
|
190
|
-
self.
|
|
191
|
-
|
|
192
|
-
|
|
193
|
-
self.
|
|
194
|
-
|
|
195
|
-
|
|
196
|
-
self.
|
|
197
|
-
self.
|
|
198
|
-
self.
|
|
199
|
-
self.
|
|
200
|
-
|
|
201
|
-
|
|
202
|
-
|
|
203
|
-
self.
|
|
204
|
-
|
|
205
|
-
|
|
206
|
-
|
|
207
|
-
self.
|
|
208
|
-
|
|
209
|
-
|
|
210
|
-
self.
|
|
211
|
-
|
|
212
|
-
self.
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
self.
|
|
216
|
-
|
|
217
|
-
|
|
218
|
-
self.
|
|
219
|
-
|
|
220
|
-
self.
|
|
221
|
-
|
|
222
|
-
|
|
223
|
-
self.
|
|
224
|
-
|
|
225
|
-
|
|
226
|
-
|
|
227
|
-
|
|
228
|
-
|
|
229
|
-
|
|
230
|
-
|
|
231
|
-
|
|
232
|
-
|
|
233
|
-
self.
|
|
234
|
-
|
|
235
|
-
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
|
|
240
|
-
|
|
241
|
-
|
|
242
|
-
self.top
|
|
243
|
-
|
|
244
|
-
|
|
245
|
-
|
|
246
|
-
|
|
247
|
-
|
|
248
|
-
|
|
249
|
-
|
|
250
|
-
|
|
251
|
-
|
|
252
|
-
self.
|
|
253
|
-
|
|
254
|
-
def
|
|
255
|
-
self.
|
|
256
|
-
|
|
257
|
-
|
|
258
|
-
|
|
259
|
-
|
|
260
|
-
|
|
261
|
-
|
|
262
|
-
|
|
263
|
-
|
|
264
|
-
|
|
265
|
-
|
|
266
|
-
|
|
267
|
-
|
|
268
|
-
|
|
269
|
-
|
|
270
|
-
|
|
271
|
-
|
|
272
|
-
|
|
273
|
-
|
|
274
|
-
|
|
275
|
-
|
|
276
|
-
|
|
277
|
-
self.
|
|
278
|
-
self.
|
|
279
|
-
self.
|
|
280
|
-
self.
|
|
281
|
-
|
|
282
|
-
|
|
283
|
-
self.
|
|
284
|
-
|
|
285
|
-
|
|
286
|
-
|
|
287
|
-
self.
|
|
288
|
-
|
|
289
|
-
|
|
290
|
-
|
|
291
|
-
self.
|
|
292
|
-
|
|
293
|
-
|
|
294
|
-
|
|
295
|
-
|
|
296
|
-
|
|
297
|
-
copy
|
|
298
|
-
copy
|
|
299
|
-
|
|
300
|
-
|
|
301
|
-
|
|
302
|
-
|
|
303
|
-
|
|
304
|
-
|
|
305
|
-
|
|
306
|
-
|
|
307
|
-
|
|
308
|
-
|
|
309
|
-
|
|
310
|
-
|
|
311
|
-
|
|
312
|
-
|
|
313
|
-
|
|
314
|
-
|
|
315
|
-
|
|
316
|
-
|
|
317
|
-
|
|
318
|
-
|
|
319
|
-
|
|
320
|
-
|
|
321
|
-
|
|
322
|
-
|
|
323
|
-
|
|
324
|
-
|
|
325
|
-
|
|
326
|
-
|
|
327
|
-
|
|
328
|
-
|
|
329
|
-
|
|
330
|
-
|
|
331
|
-
|
|
332
|
-
|
|
333
|
-
|
|
334
|
-
|
|
335
|
-
self.model.queue.put(
|
|
336
|
-
|
|
337
|
-
|
|
338
|
-
|
|
339
|
-
|
|
340
|
-
|
|
341
|
-
|
|
342
|
-
|
|
343
|
-
|
|
344
|
-
|
|
345
|
-
|
|
346
|
-
|
|
347
|
-
|
|
348
|
-
app()
|
|
349
|
-
|
|
350
|
-
__all__ = ['app']
|
|
1
|
+
# Natural Language Toolkit: Collocations Application
|
|
2
|
+
# Much of the GUI code is imported from concordance.py; We intend to merge these tools together
|
|
3
|
+
# Copyright (C) 2001-2018 NLTK Project
|
|
4
|
+
# Author: Sumukh Ghodke <sghodke@csse.unimelb.edu.au>
|
|
5
|
+
# URL: <http://nltk.org/>
|
|
6
|
+
# For license information, see LICENSE.TXT
|
|
7
|
+
#
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
from __future__ import division
|
|
11
|
+
|
|
12
|
+
import threading
|
|
13
|
+
|
|
14
|
+
from six.moves import queue as q
|
|
15
|
+
from six.moves.tkinter_font import Font
|
|
16
|
+
from six.moves.tkinter import (Button, END, Frame, IntVar, LEFT, Label, Menu,
|
|
17
|
+
OptionMenu, SUNKEN, Scrollbar, StringVar,
|
|
18
|
+
Text, Tk)
|
|
19
|
+
|
|
20
|
+
from nltk.corpus import (cess_cat, brown, nps_chat, treebank, sinica_treebank, alpino,
|
|
21
|
+
indian, floresta, mac_morpho, machado, cess_esp)
|
|
22
|
+
from nltk.util import in_idle
|
|
23
|
+
from nltk.probability import FreqDist
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
CORPUS_LOADED_EVENT = '<<CL_EVENT>>'
|
|
27
|
+
ERROR_LOADING_CORPUS_EVENT = '<<ELC_EVENT>>'
|
|
28
|
+
POLL_INTERVAL = 100
|
|
29
|
+
|
|
30
|
+
_DEFAULT = 'English: Brown Corpus (Humor)'
|
|
31
|
+
_CORPORA = {
|
|
32
|
+
'Catalan: CESS-CAT Corpus':
|
|
33
|
+
lambda: cess_cat.words(),
|
|
34
|
+
'English: Brown Corpus':
|
|
35
|
+
lambda: brown.words(),
|
|
36
|
+
'English: Brown Corpus (Press)':
|
|
37
|
+
lambda: brown.words(categories=['news', 'editorial', 'reviews']),
|
|
38
|
+
'English: Brown Corpus (Religion)':
|
|
39
|
+
lambda: brown.words(categories='religion'),
|
|
40
|
+
'English: Brown Corpus (Learned)':
|
|
41
|
+
lambda: brown.words(categories='learned'),
|
|
42
|
+
'English: Brown Corpus (Science Fiction)':
|
|
43
|
+
lambda: brown.words(categories='science_fiction'),
|
|
44
|
+
'English: Brown Corpus (Romance)':
|
|
45
|
+
lambda: brown.words(categories='romance'),
|
|
46
|
+
'English: Brown Corpus (Humor)':
|
|
47
|
+
lambda: brown.words(categories='humor'),
|
|
48
|
+
'English: NPS Chat Corpus':
|
|
49
|
+
lambda: nps_chat.words(),
|
|
50
|
+
'English: Wall Street Journal Corpus':
|
|
51
|
+
lambda: treebank.words(),
|
|
52
|
+
'Chinese: Sinica Corpus':
|
|
53
|
+
lambda: sinica_treebank.words(),
|
|
54
|
+
'Dutch: Alpino Corpus':
|
|
55
|
+
lambda: alpino.words(),
|
|
56
|
+
'Hindi: Indian Languages Corpus':
|
|
57
|
+
lambda: indian.words(files='hindi.pos'),
|
|
58
|
+
'Portuguese: Floresta Corpus (Portugal)':
|
|
59
|
+
lambda: floresta.words(),
|
|
60
|
+
'Portuguese: MAC-MORPHO Corpus (Brazil)':
|
|
61
|
+
lambda: mac_morpho.words(),
|
|
62
|
+
'Portuguese: Machado Corpus (Brazil)':
|
|
63
|
+
lambda: machado.words(),
|
|
64
|
+
'Spanish: CESS-ESP Corpus':
|
|
65
|
+
lambda: cess_esp.words()
|
|
66
|
+
}
|
|
67
|
+
|
|
68
|
+
class CollocationsView:
|
|
69
|
+
_BACKGROUND_COLOUR='#FFF' #white
|
|
70
|
+
|
|
71
|
+
def __init__(self):
|
|
72
|
+
self.queue = q.Queue()
|
|
73
|
+
self.model = CollocationsModel(self.queue)
|
|
74
|
+
self.top = Tk()
|
|
75
|
+
self._init_top(self.top)
|
|
76
|
+
self._init_menubar()
|
|
77
|
+
self._init_widgets(self.top)
|
|
78
|
+
self.load_corpus(self.model.DEFAULT_CORPUS)
|
|
79
|
+
self.after = self.top.after(POLL_INTERVAL, self._poll)
|
|
80
|
+
|
|
81
|
+
def _init_top(self, top):
|
|
82
|
+
top.geometry('550x650+50+50')
|
|
83
|
+
top.title('NLTK Collocations List')
|
|
84
|
+
top.bind('<Control-q>', self.destroy)
|
|
85
|
+
top.protocol('WM_DELETE_WINDOW', self.destroy)
|
|
86
|
+
top.minsize(550,650)
|
|
87
|
+
|
|
88
|
+
def _init_widgets(self, parent):
|
|
89
|
+
self.main_frame = Frame(parent, dict(background=self._BACKGROUND_COLOUR, padx=1, pady=1, border=1))
|
|
90
|
+
self._init_corpus_select(self.main_frame)
|
|
91
|
+
self._init_results_box(self.main_frame)
|
|
92
|
+
self._init_paging(self.main_frame)
|
|
93
|
+
self._init_status(self.main_frame)
|
|
94
|
+
self.main_frame.pack(fill='both', expand=True)
|
|
95
|
+
|
|
96
|
+
def _init_corpus_select(self, parent):
|
|
97
|
+
innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
|
|
98
|
+
self.var = StringVar(innerframe)
|
|
99
|
+
self.var.set(self.model.DEFAULT_CORPUS)
|
|
100
|
+
Label(innerframe, justify=LEFT, text=' Corpus: ', background=self._BACKGROUND_COLOUR, padx = 2, pady = 1, border = 0).pack(side='left')
|
|
101
|
+
|
|
102
|
+
other_corpora = list(self.model.CORPORA.keys()).remove(self.model.DEFAULT_CORPUS)
|
|
103
|
+
om = OptionMenu(innerframe, self.var, self.model.DEFAULT_CORPUS, command=self.corpus_selected, *self.model.non_default_corpora())
|
|
104
|
+
om['borderwidth'] = 0
|
|
105
|
+
om['highlightthickness'] = 1
|
|
106
|
+
om.pack(side='left')
|
|
107
|
+
innerframe.pack(side='top', fill='x', anchor='n')
|
|
108
|
+
|
|
109
|
+
def _init_status(self, parent):
|
|
110
|
+
self.status = Label(parent, justify=LEFT, relief=SUNKEN, background=self._BACKGROUND_COLOUR, border=0, padx = 1, pady = 0)
|
|
111
|
+
self.status.pack(side='top', anchor='sw')
|
|
112
|
+
|
|
113
|
+
def _init_menubar(self):
|
|
114
|
+
self._result_size = IntVar(self.top)
|
|
115
|
+
menubar = Menu(self.top)
|
|
116
|
+
|
|
117
|
+
filemenu = Menu(menubar, tearoff=0, borderwidth=0)
|
|
118
|
+
filemenu.add_command(label='Exit', underline=1,
|
|
119
|
+
command=self.destroy, accelerator='Ctrl-q')
|
|
120
|
+
menubar.add_cascade(label='File', underline=0, menu=filemenu)
|
|
121
|
+
|
|
122
|
+
editmenu = Menu(menubar, tearoff=0)
|
|
123
|
+
rescntmenu = Menu(editmenu, tearoff=0)
|
|
124
|
+
rescntmenu.add_radiobutton(label='20', variable=self._result_size,
|
|
125
|
+
underline=0, value=20, command=self.set_result_size)
|
|
126
|
+
rescntmenu.add_radiobutton(label='50', variable=self._result_size,
|
|
127
|
+
underline=0, value=50, command=self.set_result_size)
|
|
128
|
+
rescntmenu.add_radiobutton(label='100', variable=self._result_size,
|
|
129
|
+
underline=0, value=100, command=self.set_result_size)
|
|
130
|
+
rescntmenu.invoke(1)
|
|
131
|
+
editmenu.add_cascade(label='Result Count', underline=0, menu=rescntmenu)
|
|
132
|
+
|
|
133
|
+
menubar.add_cascade(label='Edit', underline=0, menu=editmenu)
|
|
134
|
+
self.top.config(menu=menubar)
|
|
135
|
+
|
|
136
|
+
def set_result_size(self, **kwargs):
|
|
137
|
+
self.model.result_count = self._result_size.get()
|
|
138
|
+
|
|
139
|
+
def _init_results_box(self, parent):
|
|
140
|
+
innerframe = Frame(parent)
|
|
141
|
+
i1 = Frame(innerframe)
|
|
142
|
+
i2 = Frame(innerframe)
|
|
143
|
+
vscrollbar = Scrollbar(i1, borderwidth=1)
|
|
144
|
+
hscrollbar = Scrollbar(i2, borderwidth=1, orient='horiz')
|
|
145
|
+
self.results_box = Text(i1,
|
|
146
|
+
font=Font(family='courier', size='16'),
|
|
147
|
+
state='disabled', borderwidth=1,
|
|
148
|
+
yscrollcommand=vscrollbar.set,
|
|
149
|
+
xscrollcommand=hscrollbar.set, wrap='none', width='40', height = '20', exportselection=1)
|
|
150
|
+
self.results_box.pack(side='left', fill='both', expand=True)
|
|
151
|
+
vscrollbar.pack(side='left', fill='y', anchor='e')
|
|
152
|
+
vscrollbar.config(command=self.results_box.yview)
|
|
153
|
+
hscrollbar.pack(side='left', fill='x', expand=True, anchor='w')
|
|
154
|
+
hscrollbar.config(command=self.results_box.xview)
|
|
155
|
+
#there is no other way of avoiding the overlap of scrollbars while using pack layout manager!!!
|
|
156
|
+
Label(i2, text=' ', background=self._BACKGROUND_COLOUR).pack(side='left', anchor='e')
|
|
157
|
+
i1.pack(side='top', fill='both', expand=True, anchor='n')
|
|
158
|
+
i2.pack(side='bottom', fill='x', anchor='s')
|
|
159
|
+
innerframe.pack(side='top', fill='both', expand=True)
|
|
160
|
+
|
|
161
|
+
def _init_paging(self, parent):
|
|
162
|
+
innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
|
|
163
|
+
self.prev = prev = Button(innerframe, text='Previous', command=self.previous, width='10', borderwidth=1, highlightthickness=1, state='disabled')
|
|
164
|
+
prev.pack(side='left', anchor='center')
|
|
165
|
+
self.next = next = Button(innerframe, text='Next', command=self.__next__, width='10', borderwidth=1, highlightthickness=1, state='disabled')
|
|
166
|
+
next.pack(side='right', anchor='center')
|
|
167
|
+
innerframe.pack(side='top', fill='y')
|
|
168
|
+
self.reset_current_page()
|
|
169
|
+
|
|
170
|
+
def reset_current_page(self):
|
|
171
|
+
self.current_page = -1
|
|
172
|
+
|
|
173
|
+
def _poll(self):
|
|
174
|
+
try:
|
|
175
|
+
event = self.queue.get(block=False)
|
|
176
|
+
except q.Empty:
|
|
177
|
+
pass
|
|
178
|
+
else:
|
|
179
|
+
if event == CORPUS_LOADED_EVENT:
|
|
180
|
+
self.handle_corpus_loaded(event)
|
|
181
|
+
elif event == ERROR_LOADING_CORPUS_EVENT:
|
|
182
|
+
self.handle_error_loading_corpus(event)
|
|
183
|
+
self.after = self.top.after(POLL_INTERVAL, self._poll)
|
|
184
|
+
|
|
185
|
+
def handle_error_loading_corpus(self, event):
|
|
186
|
+
self.status['text'] = 'Error in loading ' + self.var.get()
|
|
187
|
+
self.unfreeze_editable()
|
|
188
|
+
self.clear_results_box()
|
|
189
|
+
self.freeze_editable()
|
|
190
|
+
self.reset_current_page()
|
|
191
|
+
|
|
192
|
+
def handle_corpus_loaded(self, event):
|
|
193
|
+
self.status['text'] = self.var.get() + ' is loaded'
|
|
194
|
+
self.unfreeze_editable()
|
|
195
|
+
self.clear_results_box()
|
|
196
|
+
self.reset_current_page()
|
|
197
|
+
#self.next()
|
|
198
|
+
collocations = self.model.next(self.current_page + 1)
|
|
199
|
+
self.write_results(collocations)
|
|
200
|
+
self.current_page += 1
|
|
201
|
+
|
|
202
|
+
def corpus_selected(self, *args):
|
|
203
|
+
new_selection = self.var.get()
|
|
204
|
+
self.load_corpus(new_selection)
|
|
205
|
+
|
|
206
|
+
def previous(self):
|
|
207
|
+
self.freeze_editable()
|
|
208
|
+
collocations = self.model.prev(self.current_page - 1)
|
|
209
|
+
self.current_page= self.current_page - 1
|
|
210
|
+
self.clear_results_box()
|
|
211
|
+
self.write_results(collocations)
|
|
212
|
+
self.unfreeze_editable()
|
|
213
|
+
|
|
214
|
+
def __next__(self):
|
|
215
|
+
self.freeze_editable()
|
|
216
|
+
collocations = self.model.next(self.current_page + 1)
|
|
217
|
+
self.clear_results_box()
|
|
218
|
+
self.write_results(collocations)
|
|
219
|
+
self.current_page += 1
|
|
220
|
+
self.unfreeze_editable()
|
|
221
|
+
|
|
222
|
+
def load_corpus(self, selection):
|
|
223
|
+
if self.model.selected_corpus != selection:
|
|
224
|
+
self.status['text'] = 'Loading ' + selection + '...'
|
|
225
|
+
self.freeze_editable()
|
|
226
|
+
self.model.load_corpus(selection)
|
|
227
|
+
|
|
228
|
+
def freeze_editable(self):
|
|
229
|
+
self.prev['state'] = 'disabled'
|
|
230
|
+
self.next['state'] = 'disabled'
|
|
231
|
+
|
|
232
|
+
def clear_results_box(self):
|
|
233
|
+
self.results_box['state'] = 'normal'
|
|
234
|
+
self.results_box.delete("1.0", END)
|
|
235
|
+
self.results_box['state'] = 'disabled'
|
|
236
|
+
|
|
237
|
+
def fire_event(self, event):
|
|
238
|
+
#Firing an event so that rendering of widgets happen in the mainloop thread
|
|
239
|
+
self.top.event_generate(event, when='tail')
|
|
240
|
+
|
|
241
|
+
def destroy(self, *e):
|
|
242
|
+
if self.top is None: return
|
|
243
|
+
self.top.after_cancel(self.after)
|
|
244
|
+
self.top.destroy()
|
|
245
|
+
self.top = None
|
|
246
|
+
|
|
247
|
+
def mainloop(self, *args, **kwargs):
|
|
248
|
+
if in_idle(): return
|
|
249
|
+
self.top.mainloop(*args, **kwargs)
|
|
250
|
+
|
|
251
|
+
def unfreeze_editable(self):
|
|
252
|
+
self.set_paging_button_states()
|
|
253
|
+
|
|
254
|
+
def set_paging_button_states(self):
|
|
255
|
+
if self.current_page == -1 or self.current_page == 0:
|
|
256
|
+
self.prev['state'] = 'disabled'
|
|
257
|
+
else:
|
|
258
|
+
self.prev['state'] = 'normal'
|
|
259
|
+
if self.model.is_last_page(self.current_page):
|
|
260
|
+
self.next['state'] = 'disabled'
|
|
261
|
+
else:
|
|
262
|
+
self.next['state'] = 'normal'
|
|
263
|
+
|
|
264
|
+
def write_results(self, results):
|
|
265
|
+
self.results_box['state'] = 'normal'
|
|
266
|
+
row = 1
|
|
267
|
+
for each in results:
|
|
268
|
+
self.results_box.insert(str(row) + '.0', each[0] + " " + each[1] + "\n")
|
|
269
|
+
row += 1
|
|
270
|
+
self.results_box['state'] = 'disabled'
|
|
271
|
+
|
|
272
|
+
class CollocationsModel:
|
|
273
|
+
def __init__(self, queue):
|
|
274
|
+
self.result_count = None
|
|
275
|
+
self.selected_corpus = None
|
|
276
|
+
self.collocations = None
|
|
277
|
+
self.CORPORA = _CORPORA
|
|
278
|
+
self.DEFAULT_CORPUS = _DEFAULT
|
|
279
|
+
self.queue = queue
|
|
280
|
+
self.reset_results()
|
|
281
|
+
|
|
282
|
+
def reset_results(self):
|
|
283
|
+
self.result_pages = []
|
|
284
|
+
self.results_returned = 0
|
|
285
|
+
|
|
286
|
+
def load_corpus(self, name):
|
|
287
|
+
self.selected_corpus = name
|
|
288
|
+
self.collocations = None
|
|
289
|
+
runner_thread = self.LoadCorpus(name, self)
|
|
290
|
+
runner_thread.start()
|
|
291
|
+
self.reset_results()
|
|
292
|
+
|
|
293
|
+
def non_default_corpora(self):
|
|
294
|
+
copy = []
|
|
295
|
+
copy.extend(list(self.CORPORA.keys()))
|
|
296
|
+
copy.remove(self.DEFAULT_CORPUS)
|
|
297
|
+
copy.sort()
|
|
298
|
+
return copy
|
|
299
|
+
|
|
300
|
+
def is_last_page(self, number):
|
|
301
|
+
if number < len(self.result_pages):
|
|
302
|
+
return False
|
|
303
|
+
return self.results_returned + (number - len(self.result_pages)) * self.result_count >= len(self.collocations)
|
|
304
|
+
|
|
305
|
+
def next(self, page):
|
|
306
|
+
if (len(self.result_pages) - 1) < page:
|
|
307
|
+
for i in range(page - (len(self.result_pages) - 1)):
|
|
308
|
+
self.result_pages.append(self.collocations[self.results_returned:self.results_returned+self.result_count])
|
|
309
|
+
self.results_returned += self.result_count
|
|
310
|
+
return self.result_pages[page]
|
|
311
|
+
|
|
312
|
+
def prev(self, page):
|
|
313
|
+
if page == -1:
|
|
314
|
+
return []
|
|
315
|
+
return self.result_pages[page]
|
|
316
|
+
|
|
317
|
+
class LoadCorpus(threading.Thread):
|
|
318
|
+
def __init__(self, name, model):
|
|
319
|
+
threading.Thread.__init__(self)
|
|
320
|
+
self.model, self.name = model, name
|
|
321
|
+
|
|
322
|
+
def run(self):
|
|
323
|
+
try:
|
|
324
|
+
words = self.model.CORPORA[self.name]()
|
|
325
|
+
from operator import itemgetter
|
|
326
|
+
text = [w for w in words if len(w) > 2]
|
|
327
|
+
fd = FreqDist(tuple(text[i:i+2]) for i in range(len(text)-1))
|
|
328
|
+
vocab = FreqDist(text)
|
|
329
|
+
scored = [((w1,w2), fd[(w1,w2)] ** 3 / (vocab[w1] * vocab[w2])) for w1, w2 in fd]
|
|
330
|
+
scored.sort(key=itemgetter(1), reverse=True)
|
|
331
|
+
self.model.collocations = list(map(itemgetter(0), scored))
|
|
332
|
+
self.model.queue.put(CORPUS_LOADED_EVENT)
|
|
333
|
+
except Exception as e:
|
|
334
|
+
print(e)
|
|
335
|
+
self.model.queue.put(ERROR_LOADING_CORPUS_EVENT)
|
|
336
|
+
|
|
337
|
+
#def collocations():
|
|
338
|
+
# colloc_strings = [w1 + ' ' + w2 for w1, w2 in self._collocations[:num]]
|
|
339
|
+
|
|
340
|
+
def app():
|
|
341
|
+
c = CollocationsView()
|
|
342
|
+
c.mainloop()
|
|
343
|
+
|
|
344
|
+
if __name__ == '__main__':
|
|
345
|
+
app()
|
|
346
|
+
|
|
347
|
+
__all__ = ['app']
|