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.
Files changed (406) hide show
  1. {nltk-3.2 → nltk-3.3}/INSTALL.txt +6 -6
  2. {nltk-3.2 → nltk-3.3}/LICENSE.txt +13 -13
  3. {nltk-3.2 → nltk-3.3}/MANIFEST.in +6 -6
  4. {nltk-3.2/nltk.egg-info → nltk-3.3}/PKG-INFO +13 -5
  5. nltk-3.2/README.txt → nltk-3.3/README.md +49 -48
  6. nltk-3.3/nltk/VERSION +1 -0
  7. {nltk-3.2 → nltk-3.3}/nltk/__init__.py +185 -185
  8. {nltk-3.2 → nltk-3.3}/nltk/app/__init__.py +52 -53
  9. {nltk-3.2 → nltk-3.3}/nltk/app/chartparser_app.py +2276 -2276
  10. {nltk-3.2 → nltk-3.3}/nltk/app/chunkparser_app.py +1262 -1264
  11. {nltk-3.2 → nltk-3.3}/nltk/app/collocations_app.py +347 -350
  12. {nltk-3.2 → nltk-3.3}/nltk/app/concordance_app.py +568 -570
  13. {nltk-3.2 → nltk-3.3}/nltk/app/nemo_app.py +156 -155
  14. {nltk-3.2 → nltk-3.3}/nltk/app/rdparser_app.py +892 -894
  15. {nltk-3.2 → nltk-3.3}/nltk/app/srparser_app.py +809 -809
  16. {nltk-3.2 → nltk-3.3}/nltk/app/wordfreq_app.py +32 -32
  17. {nltk-3.2 → nltk-3.3}/nltk/app/wordnet_app.py +968 -968
  18. {nltk-3.2 → nltk-3.3}/nltk/book.py +91 -90
  19. {nltk-3.2 → nltk-3.3}/nltk/ccg/__init__.py +22 -22
  20. {nltk-3.2 → nltk-3.3}/nltk/ccg/api.py +359 -335
  21. {nltk-3.2 → nltk-3.3}/nltk/ccg/chart.py +394 -361
  22. {nltk-3.2 → nltk-3.3}/nltk/ccg/combinator.py +343 -312
  23. {nltk-3.2 → nltk-3.3}/nltk/ccg/lexicon.py +328 -290
  24. nltk-3.3/nltk/ccg/logic.py +46 -0
  25. {nltk-3.2 → nltk-3.3}/nltk/chat/__init__.py +49 -49
  26. {nltk-3.2 → nltk-3.3}/nltk/chat/eliza.py +244 -244
  27. {nltk-3.2 → nltk-3.3}/nltk/chat/iesha.py +140 -140
  28. {nltk-3.2 → nltk-3.3}/nltk/chat/rude.py +92 -92
  29. {nltk-3.2 → nltk-3.3}/nltk/chat/suntsu.py +117 -117
  30. {nltk-3.2 → nltk-3.3}/nltk/chat/util.py +122 -120
  31. {nltk-3.2 → nltk-3.3}/nltk/chat/zen.py +282 -282
  32. {nltk-3.2 → nltk-3.3}/nltk/chunk/__init__.py +190 -190
  33. {nltk-3.2 → nltk-3.3}/nltk/chunk/api.py +51 -51
  34. {nltk-3.2 → nltk-3.3}/nltk/chunk/named_entity.py +331 -331
  35. {nltk-3.2 → nltk-3.3}/nltk/chunk/regexp.py +1390 -1384
  36. {nltk-3.2 → nltk-3.3}/nltk/chunk/util.py +600 -600
  37. {nltk-3.2 → nltk-3.3}/nltk/classify/__init__.py +98 -98
  38. {nltk-3.2 → nltk-3.3}/nltk/classify/api.py +193 -193
  39. {nltk-3.2 → nltk-3.3}/nltk/classify/decisiontree.py +295 -295
  40. {nltk-3.2 → nltk-3.3}/nltk/classify/maxent.py +1510 -1492
  41. {nltk-3.2 → nltk-3.3}/nltk/classify/megam.py +179 -178
  42. {nltk-3.2 → nltk-3.3}/nltk/classify/naivebayes.py +245 -242
  43. {nltk-3.2 → nltk-3.3}/nltk/classify/positivenaivebayes.py +170 -170
  44. {nltk-3.2 → nltk-3.3}/nltk/classify/rte_classify.py +160 -191
  45. {nltk-3.2 → nltk-3.3}/nltk/classify/scikitlearn.py +153 -151
  46. {nltk-3.2 → nltk-3.3}/nltk/classify/senna.py +183 -181
  47. {nltk-3.2 → nltk-3.3}/nltk/classify/svm.py +15 -15
  48. {nltk-3.2 → nltk-3.3}/nltk/classify/tadm.py +113 -112
  49. {nltk-3.2 → nltk-3.3}/nltk/classify/textcat.py +193 -193
  50. {nltk-3.2 → nltk-3.3}/nltk/classify/util.py +324 -312
  51. {nltk-3.2 → nltk-3.3}/nltk/classify/weka.py +346 -345
  52. {nltk-3.2 → nltk-3.3}/nltk/cluster/__init__.py +86 -86
  53. {nltk-3.2 → nltk-3.3}/nltk/cluster/api.py +74 -70
  54. {nltk-3.2 → nltk-3.3}/nltk/cluster/em.py +247 -247
  55. {nltk-3.2 → nltk-3.3}/nltk/cluster/gaac.py +168 -168
  56. {nltk-3.2 → nltk-3.3}/nltk/cluster/kmeans.py +221 -221
  57. {nltk-3.2 → nltk-3.3}/nltk/cluster/util.py +304 -289
  58. nltk-3.3/nltk/collections.py +640 -0
  59. {nltk-3.2 → nltk-3.3}/nltk/collocations.py +388 -388
  60. nltk-3.3/nltk/compat.py +365 -0
  61. {nltk-3.2 → nltk-3.3}/nltk/corpus/__init__.py +341 -320
  62. {nltk-3.2 → nltk-3.3}/nltk/corpus/europarl_raw.py +44 -44
  63. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/__init__.py +147 -145
  64. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/aligned.py +115 -114
  65. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/api.py +448 -446
  66. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/bnc.py +252 -252
  67. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/bracket_parse.py +227 -227
  68. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/categorized_sents.py +179 -178
  69. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/chasen.py +140 -139
  70. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/childes.py +522 -494
  71. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/chunked.py +212 -212
  72. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/cmudict.py +97 -95
  73. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/comparative_sents.py +280 -278
  74. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/conll.py +528 -521
  75. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/crubadan.py +116 -116
  76. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/dependency.py +101 -101
  77. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/framenet.py +3059 -2093
  78. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ieer.py +112 -111
  79. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/indian.py +85 -86
  80. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ipipan.py +332 -331
  81. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/knbc.py +187 -187
  82. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/lin.py +156 -156
  83. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/mte.py +311 -310
  84. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nkjp.py +429 -428
  85. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nombank.py +421 -421
  86. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nps_chat.py +73 -73
  87. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/opinion_lexicon.py +115 -115
  88. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/panlex_lite.py +165 -165
  89. nltk-3.3/nltk/corpus/reader/pl196x.py +292 -0
  90. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/plaintext.py +232 -233
  91. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ppattach.py +96 -95
  92. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/propbank.py +479 -481
  93. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/pros_cons.py +128 -126
  94. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/reviews.py +330 -328
  95. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/rte.py +144 -146
  96. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/semcor.py +256 -256
  97. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/senseval.py +203 -201
  98. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/sentiwordnet.py +137 -137
  99. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/sinica_treebank.py +75 -75
  100. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/string_category.py +60 -59
  101. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/switchboard.py +119 -119
  102. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/tagged.py +295 -294
  103. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/timit.py +452 -450
  104. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/toolbox.py +68 -68
  105. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/twitter.py +155 -157
  106. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/udhr.py +80 -80
  107. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/util.py +804 -800
  108. nltk-3.3/nltk/corpus/reader/verbnet.py +595 -0
  109. nltk-3.3/nltk/corpus/reader/wordlist.py +134 -0
  110. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/wordnet.py +2108 -2036
  111. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/xmldocs.py +392 -387
  112. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ycoe.py +243 -242
  113. {nltk-3.2 → nltk-3.3}/nltk/corpus/util.py +144 -127
  114. {nltk-3.2 → nltk-3.3}/nltk/data.py +1487 -1451
  115. {nltk-3.2 → nltk-3.3}/nltk/decorators.py +219 -215
  116. {nltk-3.2 → nltk-3.3}/nltk/downloader.py +2278 -2274
  117. {nltk-3.2 → nltk-3.3}/nltk/draw/__init__.py +27 -27
  118. {nltk-3.2 → nltk-3.3}/nltk/draw/cfg.py +774 -777
  119. {nltk-3.2 → nltk-3.3}/nltk/draw/dispersion.py +58 -58
  120. {nltk-3.2 → nltk-3.3}/nltk/draw/table.py +1098 -1098
  121. {nltk-3.2 → nltk-3.3}/nltk/draw/tree.py +963 -966
  122. {nltk-3.2 → nltk-3.3}/nltk/draw/util.py +2356 -2356
  123. {nltk-3.2 → nltk-3.3}/nltk/featstruct.py +2617 -2500
  124. {nltk-3.2 → nltk-3.3}/nltk/grammar.py +1559 -1516
  125. {nltk-3.2 → nltk-3.3}/nltk/help.py +56 -56
  126. {nltk-3.2 → nltk-3.3}/nltk/inference/__init__.py +20 -20
  127. {nltk-3.2 → nltk-3.3}/nltk/inference/api.py +597 -589
  128. {nltk-3.2 → nltk-3.3}/nltk/inference/discourse.py +612 -608
  129. {nltk-3.2 → nltk-3.3}/nltk/inference/mace.py +311 -311
  130. {nltk-3.2 → nltk-3.3}/nltk/inference/nonmonotonic.py +509 -509
  131. {nltk-3.2 → nltk-3.3}/nltk/inference/prover9.py +431 -431
  132. {nltk-3.2 → nltk-3.3}/nltk/inference/resolution.py +687 -687
  133. {nltk-3.2 → nltk-3.3}/nltk/inference/tableau.py +607 -607
  134. {nltk-3.2 → nltk-3.3}/nltk/internals.py +982 -982
  135. {nltk-3.2 → nltk-3.3}/nltk/jsontags.py +63 -63
  136. {nltk-3.2 → nltk-3.3}/nltk/lazyimport.py +142 -142
  137. {nltk-3.2 → nltk-3.3}/nltk/metrics/__init__.py +30 -29
  138. {nltk-3.2 → nltk-3.3}/nltk/metrics/agreement.py +421 -401
  139. nltk-3.3/nltk/metrics/aline.py +607 -0
  140. {nltk-3.2 → nltk-3.3}/nltk/metrics/association.py +414 -410
  141. {nltk-3.2 → nltk-3.3}/nltk/metrics/confusionmatrix.py +206 -206
  142. {nltk-3.2 → nltk-3.3}/nltk/metrics/distance.py +207 -202
  143. {nltk-3.2 → nltk-3.3}/nltk/metrics/paice.py +381 -381
  144. {nltk-3.2 → nltk-3.3}/nltk/metrics/scores.py +228 -228
  145. {nltk-3.2 → nltk-3.3}/nltk/metrics/segmentation.py +231 -232
  146. {nltk-3.2 → nltk-3.3}/nltk/metrics/spearman.py +69 -69
  147. {nltk-3.2 → nltk-3.3}/nltk/misc/__init__.py +11 -11
  148. {nltk-3.2 → nltk-3.3}/nltk/misc/babelfish.py +10 -10
  149. {nltk-3.2 → nltk-3.3}/nltk/misc/chomsky.py +135 -133
  150. {nltk-3.2 → nltk-3.3}/nltk/misc/minimalset.py +83 -83
  151. {nltk-3.2 → nltk-3.3}/nltk/misc/sort.py +157 -157
  152. {nltk-3.2 → nltk-3.3}/nltk/misc/wordfinder.py +129 -129
  153. {nltk-3.2 → nltk-3.3}/nltk/parse/__init__.py +81 -80
  154. {nltk-3.2 → nltk-3.3}/nltk/parse/api.py +66 -66
  155. {nltk-3.2 → nltk-3.3}/nltk/parse/bllip.py +282 -282
  156. {nltk-3.2 → nltk-3.3}/nltk/parse/chart.py +1682 -1681
  157. nltk-3.3/nltk/parse/corenlp.py +780 -0
  158. {nltk-3.2 → nltk-3.3}/nltk/parse/dependencygraph.py +760 -758
  159. {nltk-3.2 → nltk-3.3}/nltk/parse/earleychart.py +452 -451
  160. {nltk-3.2 → nltk-3.3}/nltk/parse/evaluate.py +129 -129
  161. {nltk-3.2 → nltk-3.3}/nltk/parse/featurechart.py +580 -578
  162. {nltk-3.2 → nltk-3.3}/nltk/parse/generate.py +87 -76
  163. {nltk-3.2 → nltk-3.3}/nltk/parse/malt.py +356 -356
  164. {nltk-3.2 → nltk-3.3}/nltk/parse/nonprojectivedependencyparser.py +783 -783
  165. {nltk-3.2 → nltk-3.3}/nltk/parse/pchart.py +522 -522
  166. {nltk-3.2 → nltk-3.3}/nltk/parse/projectivedependencyparser.py +579 -578
  167. {nltk-3.2 → nltk-3.3}/nltk/parse/recursivedescent.py +655 -656
  168. {nltk-3.2 → nltk-3.3}/nltk/parse/shiftreduce.py +458 -459
  169. {nltk-3.2 → nltk-3.3}/nltk/parse/stanford.py +431 -406
  170. {nltk-3.2 → nltk-3.3}/nltk/parse/transitionparser.py +774 -772
  171. {nltk-3.2 → nltk-3.3}/nltk/parse/util.py +231 -231
  172. {nltk-3.2 → nltk-3.3}/nltk/parse/viterbi.py +401 -401
  173. {nltk-3.2 → nltk-3.3}/nltk/probability.py +2410 -2355
  174. {nltk-3.2 → nltk-3.3}/nltk/sem/__init__.py +61 -61
  175. {nltk-3.2 → nltk-3.3}/nltk/sem/boxer.py +1261 -1261
  176. {nltk-3.2 → nltk-3.3}/nltk/sem/chat80.py +782 -782
  177. {nltk-3.2 → nltk-3.3}/nltk/sem/cooper_storage.py +118 -118
  178. {nltk-3.2 → nltk-3.3}/nltk/sem/drt.py +1258 -1257
  179. {nltk-3.2 → nltk-3.3}/nltk/sem/drt_glue_demo.py +485 -489
  180. {nltk-3.2 → nltk-3.3}/nltk/sem/evaluate.py +790 -784
  181. {nltk-3.2 → nltk-3.3}/nltk/sem/glue.py +696 -694
  182. {nltk-3.2 → nltk-3.3}/nltk/sem/hole.py +386 -384
  183. {nltk-3.2 → nltk-3.3}/nltk/sem/lfg.py +210 -208
  184. {nltk-3.2 → nltk-3.3}/nltk/sem/linearlogic.py +451 -449
  185. {nltk-3.2 → nltk-3.3}/nltk/sem/logic.py +1910 -1910
  186. {nltk-3.2 → nltk-3.3}/nltk/sem/relextract.py +476 -483
  187. {nltk-3.2 → nltk-3.3}/nltk/sem/skolemize.py +101 -101
  188. {nltk-3.2 → nltk-3.3}/nltk/sem/util.py +249 -249
  189. {nltk-3.2 → nltk-3.3}/nltk/sentiment/__init__.py +14 -14
  190. {nltk-3.2 → nltk-3.3}/nltk/sentiment/sentiment_analyzer.py +229 -229
  191. {nltk-3.2 → nltk-3.3}/nltk/sentiment/util.py +762 -752
  192. {nltk-3.2 → nltk-3.3}/nltk/sentiment/vader.py +443 -445
  193. {nltk-3.2 → nltk-3.3}/nltk/stem/__init__.py +31 -33
  194. {nltk-3.2 → nltk-3.3}/nltk/stem/api.py +28 -25
  195. nltk-3.3/nltk/stem/arlstem.py +369 -0
  196. {nltk-3.2 → nltk-3.3}/nltk/stem/isri.py +345 -345
  197. {nltk-3.2 → nltk-3.3}/nltk/stem/lancaster.py +337 -310
  198. nltk-3.3/nltk/stem/porter.py +710 -0
  199. {nltk-3.2 → nltk-3.3}/nltk/stem/regexp.py +61 -61
  200. {nltk-3.2 → nltk-3.3}/nltk/stem/rslp.py +142 -142
  201. {nltk-3.2 → nltk-3.3}/nltk/stem/snowball.py +4236 -3712
  202. {nltk-3.2 → nltk-3.3}/nltk/stem/util.py +22 -12
  203. {nltk-3.2 → nltk-3.3}/nltk/stem/wordnet.py +51 -51
  204. {nltk-3.2 → nltk-3.3}/nltk/tag/__init__.py +152 -127
  205. {nltk-3.2 → nltk-3.3}/nltk/tag/api.py +86 -81
  206. {nltk-3.2 → nltk-3.3}/nltk/tag/brill.py +424 -426
  207. {nltk-3.2 → nltk-3.3}/nltk/tag/brill_trainer.py +608 -608
  208. {nltk-3.2 → nltk-3.3}/nltk/tag/crf.py +204 -200
  209. {nltk-3.2 → nltk-3.3}/nltk/tag/hmm.py +1277 -1277
  210. {nltk-3.2 → nltk-3.3}/nltk/tag/hunpos.py +132 -132
  211. {nltk-3.2 → nltk-3.3}/nltk/tag/mapping.py +101 -101
  212. {nltk-3.2 → nltk-3.3}/nltk/tag/perceptron.py +329 -314
  213. {nltk-3.2 → nltk-3.3}/nltk/tag/senna.py +147 -145
  214. {nltk-3.2 → nltk-3.3}/nltk/tag/sequential.py +740 -736
  215. {nltk-3.2 → nltk-3.3}/nltk/tag/stanford.py +219 -196
  216. {nltk-3.2 → nltk-3.3}/nltk/tag/tnt.py +595 -604
  217. {nltk-3.2 → nltk-3.3}/nltk/tag/util.py +72 -72
  218. {nltk-3.2 → nltk-3.3}/nltk/tbl/__init__.py +28 -28
  219. {nltk-3.2 → nltk-3.3}/nltk/tbl/api.py +1 -1
  220. {nltk-3.2 → nltk-3.3}/nltk/tbl/demo.py +366 -366
  221. {nltk-3.2 → nltk-3.3}/nltk/tbl/erroranalysis.py +39 -39
  222. {nltk-3.2 → nltk-3.3}/nltk/tbl/feature.py +259 -261
  223. {nltk-3.2 → nltk-3.3}/nltk/tbl/rule.py +321 -321
  224. {nltk-3.2 → nltk-3.3}/nltk/tbl/template.py +303 -308
  225. {nltk-3.2 → nltk-3.3}/nltk/test/__init__.py +18 -18
  226. {nltk-3.2 → nltk-3.3}/nltk/test/all.py +24 -23
  227. {nltk-3.2 → nltk-3.3}/nltk/test/bleu.doctest +14 -14
  228. {nltk-3.2 → nltk-3.3}/nltk/test/bnc.doctest +60 -60
  229. {nltk-3.2 → nltk-3.3}/nltk/test/ccg.doctest +376 -395
  230. nltk-3.3/nltk/test/ccg_semantics.doctest +553 -0
  231. {nltk-3.2 → nltk-3.3}/nltk/test/chat80.doctest +234 -234
  232. {nltk-3.2 → nltk-3.3}/nltk/test/childes.doctest +184 -184
  233. {nltk-3.2 → nltk-3.3}/nltk/test/childes_fixt.py +14 -13
  234. {nltk-3.2 → nltk-3.3}/nltk/test/chunk.doctest +373 -373
  235. {nltk-3.2 → nltk-3.3}/nltk/test/classify.doctest +185 -185
  236. {nltk-3.2 → nltk-3.3}/nltk/test/classify_fixt.py +11 -10
  237. nltk-3.3/nltk/test/collections.doctest +20 -0
  238. {nltk-3.2 → nltk-3.3}/nltk/test/collocations.doctest +276 -276
  239. {nltk-3.2 → nltk-3.3}/nltk/test/compat.doctest +134 -138
  240. {nltk-3.2 → nltk-3.3}/nltk/test/compat_fixt.py +9 -8
  241. nltk-3.3/nltk/test/concordance.doctest +55 -0
  242. {nltk-3.2 → nltk-3.3}/nltk/test/corpus.doctest +2200 -2212
  243. {nltk-3.2 → nltk-3.3}/nltk/test/corpus_fixt.py +3 -3
  244. {nltk-3.2 → nltk-3.3}/nltk/test/crubadan.doctest +65 -65
  245. {nltk-3.2 → nltk-3.3}/nltk/test/data.doctest +379 -379
  246. {nltk-3.2 → nltk-3.3}/nltk/test/dependency.doctest +241 -241
  247. {nltk-3.2 → nltk-3.3}/nltk/test/discourse.doctest +546 -546
  248. {nltk-3.2 → nltk-3.3}/nltk/test/discourse_fixt.py +14 -13
  249. {nltk-3.2 → nltk-3.3}/nltk/test/doctest_nose_plugin.py +159 -156
  250. {nltk-3.2 → nltk-3.3}/nltk/test/drt.doctest +517 -517
  251. {nltk-3.2 → nltk-3.3}/nltk/test/featgram.doctest +607 -607
  252. {nltk-3.2 → nltk-3.3}/nltk/test/featstruct.doctest +1229 -1230
  253. {nltk-3.2 → nltk-3.3}/nltk/test/framenet.doctest +288 -239
  254. {nltk-3.2 → nltk-3.3}/nltk/test/generate.doctest +67 -67
  255. {nltk-3.2 → nltk-3.3}/nltk/test/gensim.doctest +140 -141
  256. {nltk-3.2 → nltk-3.3}/nltk/test/gensim_fixt.py +10 -9
  257. {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics.doctest +384 -386
  258. {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics_malt.doctest +68 -68
  259. {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics_malt_fixt.py +12 -11
  260. {nltk-3.2 → nltk-3.3}/nltk/test/grammar.doctest +48 -48
  261. {nltk-3.2 → nltk-3.3}/nltk/test/grammartestsuites.doctest +109 -109
  262. {nltk-3.2 → nltk-3.3}/nltk/test/index.doctest +100 -100
  263. {nltk-3.2 → nltk-3.3}/nltk/test/inference.doctest +534 -534
  264. {nltk-3.2 → nltk-3.3}/nltk/test/inference_fixt.py +12 -11
  265. {nltk-3.2 → nltk-3.3}/nltk/test/internals.doctest +140 -140
  266. {nltk-3.2 → nltk-3.3}/nltk/test/japanese.doctest +48 -48
  267. {nltk-3.2 → nltk-3.3}/nltk/test/logic.doctest +1098 -1098
  268. {nltk-3.2 → nltk-3.3}/nltk/test/metrics.doctest +270 -270
  269. {nltk-3.2 → nltk-3.3}/nltk/test/misc.doctest +118 -118
  270. {nltk-3.2 → nltk-3.3}/nltk/test/nonmonotonic.doctest +286 -286
  271. {nltk-3.2 → nltk-3.3}/nltk/test/nonmonotonic_fixt.py +12 -11
  272. {nltk-3.2 → nltk-3.3}/nltk/test/paice.doctest +35 -35
  273. {nltk-3.2 → nltk-3.3}/nltk/test/parse.doctest +884 -884
  274. {nltk-3.2 → nltk-3.3}/nltk/test/portuguese_en.doctest +565 -565
  275. {nltk-3.2 → nltk-3.3}/nltk/test/portuguese_en_fixt.py +16 -16
  276. {nltk-3.2 → nltk-3.3}/nltk/test/probability.doctest +304 -304
  277. {nltk-3.2 → nltk-3.3}/nltk/test/probability_fixt.py +13 -12
  278. {nltk-3.2 → nltk-3.3}/nltk/test/propbank.doctest +176 -176
  279. {nltk-3.2 → nltk-3.3}/nltk/test/relextract.doctest +263 -263
  280. {nltk-3.2 → nltk-3.3}/nltk/test/resolution.doctest +221 -221
  281. {nltk-3.2 → nltk-3.3}/nltk/test/runtests.py +86 -64
  282. {nltk-3.2 → nltk-3.3}/nltk/test/segmentation_fixt.py +10 -10
  283. {nltk-3.2 → nltk-3.3}/nltk/test/semantics.doctest +665 -665
  284. {nltk-3.2 → nltk-3.3}/nltk/test/semantics_fixt.py +7 -7
  285. {nltk-3.2 → nltk-3.3}/nltk/test/sentiment.doctest +233 -233
  286. {nltk-3.2 → nltk-3.3}/nltk/test/sentiwordnet.doctest +41 -41
  287. {nltk-3.2 → nltk-3.3}/nltk/test/simple.doctest +85 -85
  288. {nltk-3.2 → nltk-3.3}/nltk/test/stem.doctest +78 -78
  289. {nltk-3.2 → nltk-3.3}/nltk/test/tag.doctest +33 -33
  290. {nltk-3.2 → nltk-3.3}/nltk/test/tokenize.doctest +273 -166
  291. {nltk-3.2 → nltk-3.3}/nltk/test/toolbox.doctest +307 -307
  292. {nltk-3.2 → nltk-3.3}/nltk/test/translate.doctest +242 -242
  293. {nltk-3.2 → nltk-3.3}/nltk/test/translate_fixt.py +3 -3
  294. {nltk-3.2 → nltk-3.3}/nltk/test/tree.doctest +1101 -1101
  295. {nltk-3.2 → nltk-3.3}/nltk/test/treeprettyprinter.doctest +127 -127
  296. {nltk-3.2 → nltk-3.3}/nltk/test/treetransforms.doctest +156 -156
  297. nltk-3.3/nltk/test/unit/test_2x_compat.py +63 -0
  298. nltk-3.3/nltk/test/unit/test_aline.py +52 -0
  299. nltk-3.3/nltk/test/unit/test_chunk.py +56 -0
  300. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_classify.py +55 -53
  301. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_collocations.py +88 -79
  302. nltk-3.3/nltk/test/unit/test_concordance.py +98 -0
  303. nltk-3.3/nltk/test/unit/test_corenlp.py +1000 -0
  304. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_corpora.py +200 -183
  305. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_corpus_views.py +45 -45
  306. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_hmm.py +88 -88
  307. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_json2csv_corpus.py +188 -187
  308. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_naivebayes.py +26 -26
  309. nltk-3.3/nltk/test/unit/test_rte_classify.py +86 -0
  310. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_seekable_unicode_stream_reader.py +124 -124
  311. nltk-3.3/nltk/test/unit/test_senna.py +74 -0
  312. nltk-3.3/nltk/test/unit/test_stem.py +121 -0
  313. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_tag.py +20 -20
  314. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_tgrep.py +628 -626
  315. nltk-3.3/nltk/test/unit/test_tokenize.py +168 -0
  316. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_twitter_auth.py +185 -185
  317. nltk-3.3/nltk/test/unit/test_wordnet.py +134 -0
  318. nltk-3.3/nltk/test/unit/translate/test_bleu.py +244 -0
  319. nltk-3.3/nltk/test/unit/translate/test_gdfa.py +57 -0
  320. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm1.py +75 -75
  321. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm2.py +87 -87
  322. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm3.py +105 -105
  323. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm4.py +126 -126
  324. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm5.py +166 -166
  325. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm_model.py +270 -270
  326. nltk-3.3/nltk/test/unit/translate/test_nist.py +37 -0
  327. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_stack_decoder.py +300 -300
  328. {nltk-3.2 → nltk-3.3}/nltk/test/unit/utils.py +41 -41
  329. {nltk-3.2 → nltk-3.3}/nltk/test/util.doctest +48 -48
  330. {nltk-3.2 → nltk-3.3}/nltk/test/wordnet.doctest +595 -581
  331. {nltk-3.2 → nltk-3.3}/nltk/test/wordnet_fixt.py +7 -6
  332. {nltk-3.2 → nltk-3.3}/nltk/test/wordnet_lch.doctest +53 -53
  333. {nltk-3.2 → nltk-3.3}/nltk/test/wsd.doctest +68 -68
  334. {nltk-3.2 → nltk-3.3}/nltk/text.py +663 -610
  335. {nltk-3.2 → nltk-3.3}/nltk/tgrep.py +938 -937
  336. {nltk-3.2 → nltk-3.3}/nltk/tokenize/__init__.py +130 -107
  337. {nltk-3.2 → nltk-3.3}/nltk/tokenize/api.py +77 -78
  338. {nltk-3.2 → nltk-3.3}/nltk/tokenize/casual.py +343 -342
  339. {nltk-3.2 → nltk-3.3}/nltk/tokenize/mwe.py +120 -120
  340. nltk-3.3/nltk/tokenize/nist.py +173 -0
  341. {nltk-3.2 → nltk-3.3}/nltk/tokenize/punkt.py +1620 -1601
  342. {nltk-3.2 → nltk-3.3}/nltk/tokenize/regexp.py +208 -202
  343. nltk-3.3/nltk/tokenize/repp.py +151 -0
  344. {nltk-3.2 → nltk-3.3}/nltk/tokenize/sexpr.py +140 -142
  345. {nltk-3.2 → nltk-3.3}/nltk/tokenize/simple.py +138 -136
  346. {nltk-3.2 → nltk-3.3}/nltk/tokenize/stanford.py +117 -113
  347. nltk-3.3/nltk/tokenize/stanford_segmenter.py +246 -0
  348. {nltk-3.2 → nltk-3.3}/nltk/tokenize/texttiling.py +458 -460
  349. nltk-3.3/nltk/tokenize/toktok.py +155 -0
  350. nltk-3.3/nltk/tokenize/treebank.py +363 -0
  351. nltk-3.3/nltk/tokenize/util.py +261 -0
  352. {nltk-3.2 → nltk-3.3}/nltk/toolbox.py +499 -497
  353. {nltk-3.2 → nltk-3.3}/nltk/translate/__init__.py +24 -24
  354. {nltk-3.2 → nltk-3.3}/nltk/translate/api.py +331 -321
  355. {nltk-3.2 → nltk-3.3}/nltk/translate/bleu_score.py +615 -556
  356. nltk-3.3/nltk/translate/chrf_score.py +137 -0
  357. {nltk-3.2 → nltk-3.3}/nltk/translate/gale_church.py +248 -235
  358. {nltk-3.2 → nltk-3.3}/nltk/translate/gdfa.py +135 -131
  359. nltk-3.3/nltk/translate/gleu_score.py +193 -0
  360. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm1.py +250 -241
  361. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm2.py +308 -308
  362. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm3.py +337 -337
  363. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm4.py +467 -467
  364. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm5.py +639 -639
  365. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm_model.py +536 -533
  366. {nltk-3.2 → nltk-3.3}/nltk/translate/metrics.py +40 -40
  367. nltk-3.3/nltk/translate/nist_score.py +178 -0
  368. {nltk-3.2 → nltk-3.3}/nltk/translate/phrase_based.py +175 -175
  369. {nltk-3.2 → nltk-3.3}/nltk/translate/ribes_score.py +325 -325
  370. {nltk-3.2 → nltk-3.3}/nltk/translate/stack_decoder.py +499 -495
  371. {nltk-3.2 → nltk-3.3}/nltk/tree.py +1605 -1603
  372. {nltk-3.2 → nltk-3.3}/nltk/treeprettyprinter.py +564 -564
  373. {nltk-3.2 → nltk-3.3}/nltk/treetransforms.py +309 -309
  374. {nltk-3.2 → nltk-3.3}/nltk/twitter/__init__.py +28 -28
  375. {nltk-3.2 → nltk-3.3}/nltk/twitter/api.py +141 -136
  376. {nltk-3.2 → nltk-3.3}/nltk/twitter/common.py +264 -258
  377. {nltk-3.2 → nltk-3.3}/nltk/twitter/twitter_demo.py +288 -288
  378. {nltk-3.2 → nltk-3.3}/nltk/twitter/twitterclient.py +530 -530
  379. {nltk-3.2 → nltk-3.3}/nltk/twitter/util.py +147 -146
  380. nltk-3.3/nltk/util.py +751 -0
  381. {nltk-3.2 → nltk-3.3}/nltk/wsd.py +53 -53
  382. {nltk-3.2 → nltk-3.3/nltk.egg-info}/PKG-INFO +13 -5
  383. {nltk-3.2 → nltk-3.3}/nltk.egg-info/SOURCES.txt +26 -3
  384. nltk-3.3/nltk.egg-info/requires.txt +31 -0
  385. {nltk-3.2 → nltk-3.3}/setup.cfg +0 -1
  386. {nltk-3.2 → nltk-3.3}/setup.py +102 -75
  387. nltk-3.2/nltk/VERSION +0 -1
  388. nltk-3.2/nltk/compat.py +0 -680
  389. nltk-3.2/nltk/corpus/reader/pl196x.py +0 -278
  390. nltk-3.2/nltk/corpus/reader/verbnet.py +0 -408
  391. nltk-3.2/nltk/corpus/reader/wordlist.py +0 -37
  392. nltk-3.2/nltk/sentiment/vader_lexicon.txt +0 -7517
  393. nltk-3.2/nltk/six.py +0 -868
  394. nltk-3.2/nltk/stem/porter.py +0 -692
  395. nltk-3.2/nltk/test/unit/test_2x_compat.py +0 -26
  396. nltk-3.2/nltk/test/unit/test_stem.py +0 -36
  397. nltk-3.2/nltk/test/unit/test_tokenize.py +0 -23
  398. nltk-3.2/nltk/test/unit/translate/test_bleu.py +0 -84
  399. nltk-3.2/nltk/tokenize/treebank.py +0 -124
  400. nltk-3.2/nltk/tokenize/util.py +0 -90
  401. nltk-3.2/nltk/util.py +0 -1364
  402. {nltk-3.2 → nltk-3.3}/nltk/test/unit/__init__.py +0 -0
  403. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/__init__.py +0 -0
  404. {nltk-3.2 → nltk-3.3}/nltk.egg-info/dependency_links.txt +0 -0
  405. {nltk-3.2 → nltk-3.3}/nltk.egg-info/not-zip-safe +0 -0
  406. {nltk-3.2 → nltk-3.3}/nltk.egg-info/top_level.txt +0 -0
@@ -1,311 +1,311 @@
1
- # Natural Language Toolkit: Interface to the Mace4 Model Builder
2
- #
3
- # Author: Dan Garrette <dhgarrette@gmail.com>
4
- # Ewan Klein <ewan@inf.ed.ac.uk>
5
-
6
- # URL: <http://nltk.org/>
7
- # For license information, see LICENSE.TXT
8
-
9
- """
10
- A model builder that makes use of the external 'Mace4' package.
11
- """
12
- from __future__ import print_function
13
-
14
- import os
15
- import tempfile
16
-
17
- from nltk.sem.logic import is_indvar
18
- from nltk.sem import Valuation, Expression
19
-
20
- from nltk.inference.api import ModelBuilder, BaseModelBuilderCommand
21
- from nltk.inference.prover9 import Prover9CommandParent, Prover9Parent
22
-
23
-
24
- class MaceCommand(Prover9CommandParent, BaseModelBuilderCommand):
25
- """
26
- A ``MaceCommand`` specific to the ``Mace`` model builder. It contains
27
- a print_assumptions() method that is used to print the list
28
- of assumptions in multiple formats.
29
- """
30
- _interpformat_bin = None
31
-
32
- def __init__(self, goal=None, assumptions=None, max_models=500, model_builder=None):
33
- """
34
- :param goal: Input expression to prove
35
- :type goal: sem.Expression
36
- :param assumptions: Input expressions to use as assumptions in
37
- the proof.
38
- :type assumptions: list(sem.Expression)
39
- :param max_models: The maximum number of models that Mace will try before
40
- simply returning false. (Use 0 for no maximum.)
41
- :type max_models: int
42
- """
43
- if model_builder is not None:
44
- assert isinstance(model_builder, Mace)
45
- else:
46
- model_builder = Mace(max_models)
47
-
48
- BaseModelBuilderCommand.__init__(self, model_builder, goal, assumptions)
49
-
50
- @property
51
- def valuation(mbc): return mbc.model('valuation')
52
-
53
- def _convert2val(self, valuation_str):
54
- """
55
- Transform the output file into an NLTK-style Valuation.
56
-
57
- :return: A model if one is generated; None otherwise.
58
- :rtype: sem.Valuation
59
- """
60
- valuation_standard_format = self._transform_output(valuation_str, 'standard')
61
-
62
- val = []
63
- for line in valuation_standard_format.splitlines(False):
64
- l = line.strip()
65
-
66
- if l.startswith('interpretation'):
67
- # find the number of entities in the model
68
- num_entities = int(l[l.index('(')+1:l.index(',')].strip())
69
-
70
- elif l.startswith('function') and l.find('_') == -1:
71
- # replace the integer identifier with a corresponding alphabetic character
72
- name = l[l.index('(')+1:l.index(',')].strip()
73
- if is_indvar(name):
74
- name = name.upper()
75
- value = int(l[l.index('[')+1:l.index(']')].strip())
76
- val.append((name, MaceCommand._make_model_var(value)))
77
-
78
- elif l.startswith('relation'):
79
- l = l[l.index('(')+1:]
80
- if '(' in l:
81
- #relation is not nullary
82
- name = l[:l.index('(')].strip()
83
- values = [int(v.strip()) for v in l[l.index('[')+1:l.index(']')].split(',')]
84
- val.append((name, MaceCommand._make_relation_set(num_entities, values)))
85
- else:
86
- #relation is nullary
87
- name = l[:l.index(',')].strip()
88
- value = int(l[l.index('[')+1:l.index(']')].strip())
89
- val.append((name, value == 1))
90
-
91
- return Valuation(val)
92
-
93
- @staticmethod
94
- def _make_relation_set(num_entities, values):
95
- """
96
- Convert a Mace4-style relation table into a dictionary.
97
-
98
- :param num_entities: the number of entities in the model; determines the row length in the table.
99
- :type num_entities: int
100
- :param values: a list of 1's and 0's that represent whether a relation holds in a Mace4 model.
101
- :type values: list of int
102
- """
103
- r = set()
104
- for position in [pos for (pos,v) in enumerate(values) if v == 1]:
105
- r.add(tuple(MaceCommand._make_relation_tuple(position, values, num_entities)))
106
- return r
107
-
108
- @staticmethod
109
- def _make_relation_tuple(position, values, num_entities):
110
- if len(values) == 1:
111
- return []
112
- else:
113
- sublist_size = len(values) // num_entities
114
- sublist_start = position // sublist_size
115
- sublist_position = int(position % sublist_size)
116
-
117
- sublist = values[sublist_start*sublist_size:(sublist_start+1)*sublist_size]
118
- return [MaceCommand._make_model_var(sublist_start)] + \
119
- MaceCommand._make_relation_tuple(sublist_position,
120
- sublist,
121
- num_entities)
122
-
123
- @staticmethod
124
- def _make_model_var(value):
125
- """
126
- Pick an alphabetic character as identifier for an entity in the model.
127
-
128
- :param value: where to index into the list of characters
129
- :type value: int
130
- """
131
- letter = ['a','b','c','d','e','f','g','h','i','j','k','l','m','n',
132
- 'o','p','q','r','s','t','u','v','w','x','y','z'][value]
133
- num = value // 26
134
- return (letter + str(num) if num > 0 else letter)
135
-
136
- def _decorate_model(self, valuation_str, format):
137
- """
138
- Print out a Mace4 model using any Mace4 ``interpformat`` format.
139
- See http://www.cs.unm.edu/~mccune/mace4/manual/ for details.
140
-
141
- :param valuation_str: str with the model builder's output
142
- :param format: str indicating the format for displaying
143
- models. Defaults to 'standard' format.
144
- :return: str
145
- """
146
- if not format:
147
- return valuation_str
148
- elif format == 'valuation':
149
- return self._convert2val(valuation_str)
150
- else:
151
- return self._transform_output(valuation_str, format)
152
-
153
- def _transform_output(self, valuation_str, format):
154
- """
155
- Transform the output file into any Mace4 ``interpformat`` format.
156
-
157
- :param format: Output format for displaying models.
158
- :type format: str
159
- """
160
- if format in ['standard', 'standard2', 'portable', 'tabular',
161
- 'raw', 'cooked', 'xml', 'tex']:
162
- return self._call_interpformat(valuation_str, [format])[0]
163
- else:
164
- raise LookupError("The specified format does not exist")
165
-
166
- def _call_interpformat(self, input_str, args=[], verbose=False):
167
- """
168
- Call the ``interpformat`` binary with the given input.
169
-
170
- :param input_str: A string whose contents are used as stdin.
171
- :param args: A list of command-line arguments.
172
- :return: A tuple (stdout, returncode)
173
- :see: ``config_prover9``
174
- """
175
- if self._interpformat_bin is None:
176
- self._interpformat_bin = self._modelbuilder._find_binary(
177
- 'interpformat', verbose)
178
-
179
- return self._modelbuilder._call(input_str, self._interpformat_bin,
180
- args, verbose)
181
-
182
-
183
- class Mace(Prover9Parent, ModelBuilder):
184
- _mace4_bin = None
185
-
186
- def __init__(self, end_size=500):
187
- self._end_size = end_size
188
- """The maximum model size that Mace will try before
189
- simply returning false. (Use -1 for no maximum.)"""
190
-
191
- def _build_model(self, goal=None, assumptions=None, verbose=False):
192
- """
193
- Use Mace4 to build a first order model.
194
-
195
- :return: ``True`` if a model was found (i.e. Mace returns value of 0),
196
- else ``False``
197
- """
198
- if not assumptions:
199
- assumptions = []
200
-
201
- stdout, returncode = self._call_mace4(self.prover9_input(goal, assumptions),
202
- verbose=verbose)
203
- return (returncode == 0, stdout)
204
-
205
- def _call_mace4(self, input_str, args=[], verbose=False):
206
- """
207
- Call the ``mace4`` binary with the given input.
208
-
209
- :param input_str: A string whose contents are used as stdin.
210
- :param args: A list of command-line arguments.
211
- :return: A tuple (stdout, returncode)
212
- :see: ``config_prover9``
213
- """
214
- if self._mace4_bin is None:
215
- self._mace4_bin = self._find_binary('mace4', verbose)
216
-
217
- updated_input_str = ''
218
- if self._end_size > 0:
219
- updated_input_str += 'assign(end_size, %d).\n\n' % self._end_size
220
- updated_input_str += input_str
221
-
222
- return self._call(updated_input_str, self._mace4_bin, args, verbose)
223
-
224
-
225
- def spacer(num=30):
226
- print('-' * num)
227
-
228
- def decode_result(found):
229
- """
230
- Decode the result of model_found()
231
-
232
- :param found: The output of model_found()
233
- :type found: bool
234
- """
235
- return {True: 'Countermodel found', False: 'No countermodel found', None: 'None'}[found]
236
-
237
- def test_model_found(arguments):
238
- """
239
- Try some proofs and exhibit the results.
240
- """
241
- for (goal, assumptions) in arguments:
242
- g = Expression.fromstring(goal)
243
- alist = [lp.parse(a) for a in assumptions]
244
- m = MaceCommand(g, assumptions=alist, max_models=50)
245
- found = m.build_model()
246
- for a in alist:
247
- print(' %s' % a)
248
- print('|- %s: %s\n' % (g, decode_result(found)))
249
-
250
-
251
- def test_build_model(arguments):
252
- """
253
- Try to build a ``nltk.sem.Valuation``.
254
- """
255
- g = Expression.fromstring('all x.man(x)')
256
- alist = [Expression.fromstring(a) for a in ['man(John)',
257
- 'man(Socrates)',
258
- 'man(Bill)',
259
- 'some x.(-(x = John) & man(x) & sees(John,x))',
260
- 'some x.(-(x = Bill) & man(x))',
261
- 'all x.some y.(man(x) -> gives(Socrates,x,y))']]
262
-
263
- m = MaceCommand(g, assumptions=alist)
264
- m.build_model()
265
- spacer()
266
- print("Assumptions and Goal")
267
- spacer()
268
- for a in alist:
269
- print(' %s' % a)
270
- print('|- %s: %s\n' % (g, decode_result(m.build_model())))
271
- spacer()
272
- #print m.model('standard')
273
- #print m.model('cooked')
274
- print("Valuation")
275
- spacer()
276
- print(m.valuation, '\n')
277
-
278
- def test_transform_output(argument_pair):
279
- """
280
- Transform the model into various Mace4 ``interpformat`` formats.
281
- """
282
- g = Expression.fromstring(argument_pair[0])
283
- alist = [lp.parse(a) for a in argument_pair[1]]
284
- m = MaceCommand(g, assumptions=alist)
285
- m.build_model()
286
- for a in alist:
287
- print(' %s' % a)
288
- print('|- %s: %s\n' % (g, m.build_model()))
289
- for format in ['standard', 'portable', 'xml', 'cooked']:
290
- spacer()
291
- print("Using '%s' format" % format)
292
- spacer()
293
- print(m.model(format=format))
294
-
295
- def test_make_relation_set():
296
- print(MaceCommand._make_relation_set(num_entities=3, values=[1,0,1]) == set([('c',), ('a',)]))
297
- print(MaceCommand._make_relation_set(num_entities=3, values=[0,0,0,0,0,0,1,0,0]) == set([('c', 'a')]))
298
- print(MaceCommand._make_relation_set(num_entities=2, values=[0,0,1,0,0,0,1,0]) == set([('a', 'b', 'a'), ('b', 'b', 'a')]))
299
-
300
- arguments = [
301
- ('mortal(Socrates)', ['all x.(man(x) -> mortal(x))', 'man(Socrates)']),
302
- ('(not mortal(Socrates))', ['all x.(man(x) -> mortal(x))', 'man(Socrates)'])
303
- ]
304
-
305
- def demo():
306
- test_model_found(arguments)
307
- test_build_model(arguments)
308
- test_transform_output(arguments[1])
309
-
310
- if __name__ == '__main__':
311
- demo()
1
+ # Natural Language Toolkit: Interface to the Mace4 Model Builder
2
+ #
3
+ # Author: Dan Garrette <dhgarrette@gmail.com>
4
+ # Ewan Klein <ewan@inf.ed.ac.uk>
5
+
6
+ # URL: <http://nltk.org/>
7
+ # For license information, see LICENSE.TXT
8
+
9
+ """
10
+ A model builder that makes use of the external 'Mace4' package.
11
+ """
12
+ from __future__ import print_function
13
+
14
+ import os
15
+ import tempfile
16
+
17
+ from nltk.sem.logic import is_indvar
18
+ from nltk.sem import Valuation, Expression
19
+
20
+ from nltk.inference.api import ModelBuilder, BaseModelBuilderCommand
21
+ from nltk.inference.prover9 import Prover9CommandParent, Prover9Parent
22
+
23
+
24
+ class MaceCommand(Prover9CommandParent, BaseModelBuilderCommand):
25
+ """
26
+ A ``MaceCommand`` specific to the ``Mace`` model builder. It contains
27
+ a print_assumptions() method that is used to print the list
28
+ of assumptions in multiple formats.
29
+ """
30
+ _interpformat_bin = None
31
+
32
+ def __init__(self, goal=None, assumptions=None, max_models=500, model_builder=None):
33
+ """
34
+ :param goal: Input expression to prove
35
+ :type goal: sem.Expression
36
+ :param assumptions: Input expressions to use as assumptions in
37
+ the proof.
38
+ :type assumptions: list(sem.Expression)
39
+ :param max_models: The maximum number of models that Mace will try before
40
+ simply returning false. (Use 0 for no maximum.)
41
+ :type max_models: int
42
+ """
43
+ if model_builder is not None:
44
+ assert isinstance(model_builder, Mace)
45
+ else:
46
+ model_builder = Mace(max_models)
47
+
48
+ BaseModelBuilderCommand.__init__(self, model_builder, goal, assumptions)
49
+
50
+ @property
51
+ def valuation(mbc): return mbc.model('valuation')
52
+
53
+ def _convert2val(self, valuation_str):
54
+ """
55
+ Transform the output file into an NLTK-style Valuation.
56
+
57
+ :return: A model if one is generated; None otherwise.
58
+ :rtype: sem.Valuation
59
+ """
60
+ valuation_standard_format = self._transform_output(valuation_str, 'standard')
61
+
62
+ val = []
63
+ for line in valuation_standard_format.splitlines(False):
64
+ l = line.strip()
65
+
66
+ if l.startswith('interpretation'):
67
+ # find the number of entities in the model
68
+ num_entities = int(l[l.index('(')+1:l.index(',')].strip())
69
+
70
+ elif l.startswith('function') and l.find('_') == -1:
71
+ # replace the integer identifier with a corresponding alphabetic character
72
+ name = l[l.index('(')+1:l.index(',')].strip()
73
+ if is_indvar(name):
74
+ name = name.upper()
75
+ value = int(l[l.index('[')+1:l.index(']')].strip())
76
+ val.append((name, MaceCommand._make_model_var(value)))
77
+
78
+ elif l.startswith('relation'):
79
+ l = l[l.index('(')+1:]
80
+ if '(' in l:
81
+ #relation is not nullary
82
+ name = l[:l.index('(')].strip()
83
+ values = [int(v.strip()) for v in l[l.index('[')+1:l.index(']')].split(',')]
84
+ val.append((name, MaceCommand._make_relation_set(num_entities, values)))
85
+ else:
86
+ #relation is nullary
87
+ name = l[:l.index(',')].strip()
88
+ value = int(l[l.index('[')+1:l.index(']')].strip())
89
+ val.append((name, value == 1))
90
+
91
+ return Valuation(val)
92
+
93
+ @staticmethod
94
+ def _make_relation_set(num_entities, values):
95
+ """
96
+ Convert a Mace4-style relation table into a dictionary.
97
+
98
+ :param num_entities: the number of entities in the model; determines the row length in the table.
99
+ :type num_entities: int
100
+ :param values: a list of 1's and 0's that represent whether a relation holds in a Mace4 model.
101
+ :type values: list of int
102
+ """
103
+ r = set()
104
+ for position in [pos for (pos,v) in enumerate(values) if v == 1]:
105
+ r.add(tuple(MaceCommand._make_relation_tuple(position, values, num_entities)))
106
+ return r
107
+
108
+ @staticmethod
109
+ def _make_relation_tuple(position, values, num_entities):
110
+ if len(values) == 1:
111
+ return []
112
+ else:
113
+ sublist_size = len(values) // num_entities
114
+ sublist_start = position // sublist_size
115
+ sublist_position = int(position % sublist_size)
116
+
117
+ sublist = values[sublist_start*sublist_size:(sublist_start+1)*sublist_size]
118
+ return [MaceCommand._make_model_var(sublist_start)] + \
119
+ MaceCommand._make_relation_tuple(sublist_position,
120
+ sublist,
121
+ num_entities)
122
+
123
+ @staticmethod
124
+ def _make_model_var(value):
125
+ """
126
+ Pick an alphabetic character as identifier for an entity in the model.
127
+
128
+ :param value: where to index into the list of characters
129
+ :type value: int
130
+ """
131
+ letter = ['a','b','c','d','e','f','g','h','i','j','k','l','m','n',
132
+ 'o','p','q','r','s','t','u','v','w','x','y','z'][value]
133
+ num = value // 26
134
+ return (letter + str(num) if num > 0 else letter)
135
+
136
+ def _decorate_model(self, valuation_str, format):
137
+ """
138
+ Print out a Mace4 model using any Mace4 ``interpformat`` format.
139
+ See http://www.cs.unm.edu/~mccune/mace4/manual/ for details.
140
+
141
+ :param valuation_str: str with the model builder's output
142
+ :param format: str indicating the format for displaying
143
+ models. Defaults to 'standard' format.
144
+ :return: str
145
+ """
146
+ if not format:
147
+ return valuation_str
148
+ elif format == 'valuation':
149
+ return self._convert2val(valuation_str)
150
+ else:
151
+ return self._transform_output(valuation_str, format)
152
+
153
+ def _transform_output(self, valuation_str, format):
154
+ """
155
+ Transform the output file into any Mace4 ``interpformat`` format.
156
+
157
+ :param format: Output format for displaying models.
158
+ :type format: str
159
+ """
160
+ if format in ['standard', 'standard2', 'portable', 'tabular',
161
+ 'raw', 'cooked', 'xml', 'tex']:
162
+ return self._call_interpformat(valuation_str, [format])[0]
163
+ else:
164
+ raise LookupError("The specified format does not exist")
165
+
166
+ def _call_interpformat(self, input_str, args=[], verbose=False):
167
+ """
168
+ Call the ``interpformat`` binary with the given input.
169
+
170
+ :param input_str: A string whose contents are used as stdin.
171
+ :param args: A list of command-line arguments.
172
+ :return: A tuple (stdout, returncode)
173
+ :see: ``config_prover9``
174
+ """
175
+ if self._interpformat_bin is None:
176
+ self._interpformat_bin = self._modelbuilder._find_binary(
177
+ 'interpformat', verbose)
178
+
179
+ return self._modelbuilder._call(input_str, self._interpformat_bin,
180
+ args, verbose)
181
+
182
+
183
+ class Mace(Prover9Parent, ModelBuilder):
184
+ _mace4_bin = None
185
+
186
+ def __init__(self, end_size=500):
187
+ self._end_size = end_size
188
+ """The maximum model size that Mace will try before
189
+ simply returning false. (Use -1 for no maximum.)"""
190
+
191
+ def _build_model(self, goal=None, assumptions=None, verbose=False):
192
+ """
193
+ Use Mace4 to build a first order model.
194
+
195
+ :return: ``True`` if a model was found (i.e. Mace returns value of 0),
196
+ else ``False``
197
+ """
198
+ if not assumptions:
199
+ assumptions = []
200
+
201
+ stdout, returncode = self._call_mace4(self.prover9_input(goal, assumptions),
202
+ verbose=verbose)
203
+ return (returncode == 0, stdout)
204
+
205
+ def _call_mace4(self, input_str, args=[], verbose=False):
206
+ """
207
+ Call the ``mace4`` binary with the given input.
208
+
209
+ :param input_str: A string whose contents are used as stdin.
210
+ :param args: A list of command-line arguments.
211
+ :return: A tuple (stdout, returncode)
212
+ :see: ``config_prover9``
213
+ """
214
+ if self._mace4_bin is None:
215
+ self._mace4_bin = self._find_binary('mace4', verbose)
216
+
217
+ updated_input_str = ''
218
+ if self._end_size > 0:
219
+ updated_input_str += 'assign(end_size, %d).\n\n' % self._end_size
220
+ updated_input_str += input_str
221
+
222
+ return self._call(updated_input_str, self._mace4_bin, args, verbose)
223
+
224
+
225
+ def spacer(num=30):
226
+ print('-' * num)
227
+
228
+ def decode_result(found):
229
+ """
230
+ Decode the result of model_found()
231
+
232
+ :param found: The output of model_found()
233
+ :type found: bool
234
+ """
235
+ return {True: 'Countermodel found', False: 'No countermodel found', None: 'None'}[found]
236
+
237
+ def test_model_found(arguments):
238
+ """
239
+ Try some proofs and exhibit the results.
240
+ """
241
+ for (goal, assumptions) in arguments:
242
+ g = Expression.fromstring(goal)
243
+ alist = [lp.parse(a) for a in assumptions]
244
+ m = MaceCommand(g, assumptions=alist, max_models=50)
245
+ found = m.build_model()
246
+ for a in alist:
247
+ print(' %s' % a)
248
+ print('|- %s: %s\n' % (g, decode_result(found)))
249
+
250
+
251
+ def test_build_model(arguments):
252
+ """
253
+ Try to build a ``nltk.sem.Valuation``.
254
+ """
255
+ g = Expression.fromstring('all x.man(x)')
256
+ alist = [Expression.fromstring(a) for a in ['man(John)',
257
+ 'man(Socrates)',
258
+ 'man(Bill)',
259
+ 'some x.(-(x = John) & man(x) & sees(John,x))',
260
+ 'some x.(-(x = Bill) & man(x))',
261
+ 'all x.some y.(man(x) -> gives(Socrates,x,y))']]
262
+
263
+ m = MaceCommand(g, assumptions=alist)
264
+ m.build_model()
265
+ spacer()
266
+ print("Assumptions and Goal")
267
+ spacer()
268
+ for a in alist:
269
+ print(' %s' % a)
270
+ print('|- %s: %s\n' % (g, decode_result(m.build_model())))
271
+ spacer()
272
+ #print m.model('standard')
273
+ #print m.model('cooked')
274
+ print("Valuation")
275
+ spacer()
276
+ print(m.valuation, '\n')
277
+
278
+ def test_transform_output(argument_pair):
279
+ """
280
+ Transform the model into various Mace4 ``interpformat`` formats.
281
+ """
282
+ g = Expression.fromstring(argument_pair[0])
283
+ alist = [lp.parse(a) for a in argument_pair[1]]
284
+ m = MaceCommand(g, assumptions=alist)
285
+ m.build_model()
286
+ for a in alist:
287
+ print(' %s' % a)
288
+ print('|- %s: %s\n' % (g, m.build_model()))
289
+ for format in ['standard', 'portable', 'xml', 'cooked']:
290
+ spacer()
291
+ print("Using '%s' format" % format)
292
+ spacer()
293
+ print(m.model(format=format))
294
+
295
+ def test_make_relation_set():
296
+ print(MaceCommand._make_relation_set(num_entities=3, values=[1,0,1]) == set([('c',), ('a',)]))
297
+ print(MaceCommand._make_relation_set(num_entities=3, values=[0,0,0,0,0,0,1,0,0]) == set([('c', 'a')]))
298
+ print(MaceCommand._make_relation_set(num_entities=2, values=[0,0,1,0,0,0,1,0]) == set([('a', 'b', 'a'), ('b', 'b', 'a')]))
299
+
300
+ arguments = [
301
+ ('mortal(Socrates)', ['all x.(man(x) -> mortal(x))', 'man(Socrates)']),
302
+ ('(not mortal(Socrates))', ['all x.(man(x) -> mortal(x))', 'man(Socrates)'])
303
+ ]
304
+
305
+ def demo():
306
+ test_model_found(arguments)
307
+ test_build_model(arguments)
308
+ test_transform_output(arguments[1])
309
+
310
+ if __name__ == '__main__':
311
+ demo()