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
@@ -1,565 +1,565 @@
1
- .. Copyright (C) 2001-2015 NLTK Project
2
- .. For license information, see LICENSE.TXT
3
-
4
- ==================================
5
- Examples for Portuguese Processing
6
- ==================================
7
-
8
- This HOWTO contains a variety of examples relating to the Portuguese language.
9
- It is intended to be read in conjunction with the NLTK book
10
- (``http://nltk.org/book``). For instructions on running the Python
11
- interpreter, please see the section *Getting Started with Python*, in Chapter 1.
12
-
13
- --------------------------------------------
14
- Python Programming, with Portuguese Examples
15
- --------------------------------------------
16
-
17
- Chapter 1 of the NLTK book contains many elementary programming examples, all
18
- with English texts. In this section, we'll see some corresponding examples
19
- using Portuguese. Please refer to the chapter for full discussion. *Vamos!*
20
-
21
- >>> from nltk.examples.pt import *
22
- *** Introductory Examples for the NLTK Book ***
23
- Loading ptext1, ... and psent1, ...
24
- Type the name of the text or sentence to view it.
25
- Type: 'texts()' or 'sents()' to list the materials.
26
- ptext1: Memórias Póstumas de Brás Cubas (1881)
27
- ptext2: Dom Casmurro (1899)
28
- ptext3: Gênesis
29
- ptext4: Folha de Sao Paulo (1994)
30
-
31
-
32
- Any time we want to find out about these texts, we just have
33
- to enter their names at the Python prompt:
34
-
35
- >>> ptext2
36
- <Text: Dom Casmurro (1899)>
37
-
38
- Searching Text
39
- --------------
40
-
41
- A concordance permits us to see words in context.
42
-
43
- >>> ptext1.concordance('olhos')
44
- Building index...
45
- Displaying 25 of 138 matches:
46
- De pé , à cabeceira da cama , com os olhos estúpidos , a boca entreaberta , a t
47
- orelhas . Pela minha parte fechei os olhos e deixei - me ir à ventura . Já agor
48
- xões de cérebro enfermo . Como ia de olhos fechados , não via o caminho ; lembr
49
- gelos eternos . Com efeito , abri os olhos e vi que o meu animal galopava numa
50
- me apareceu então , fitando - me uns olhos rutilantes como o sol . Tudo nessa f
51
- mim mesmo . Então , encarei - a com olhos súplices , e pedi mais alguns anos .
52
- ...
53
-
54
- For a given word, we can find words with a similar text distribution:
55
-
56
- >>> ptext1.similar('chegar')
57
- Building word-context index...
58
- acabada acudir aludir avistar bramanismo casamento cheguei com contar
59
- contrário corpo dali deixei desferirem dizer fazer filhos já leitor lhe
60
- >>> ptext3.similar('chegar')
61
- Building word-context index...
62
- achar alumiar arrombar destruir governar guardar ir lavrar passar que
63
- toda tomar ver vir
64
-
65
- We can search for the statistically significant collocations in a text:
66
-
67
- >>> ptext1.collocations()
68
- Building collocations list
69
- Quincas Borba; Lobo Neves; alguma coisa; Brás Cubas; meu pai; dia
70
- seguinte; não sei; Meu pai; alguns instantes; outra vez; outra coisa;
71
- por exemplo; mim mesmo; coisa nenhuma; mesma coisa; não era; dias
72
- depois; Passeio Público; olhar para; das coisas
73
-
74
- We can search for words in context, with the help of *regular expressions*, e.g.:
75
-
76
- >>> ptext1.findall("<olhos> (<.*>)")
77
- estúpidos; e; fechados; rutilantes; súplices; a; do; babavam;
78
- na; moles; se; da; umas; espraiavam; chamejantes; espetados;
79
- ...
80
-
81
- We can automatically generate random text based on a given text, e.g.:
82
-
83
- >>> ptext3.generate() # doctest: +SKIP
84
- No princípio , criou Deus os abençoou , dizendo : Onde { estão } e até
85
- à ave dos céus , { que } será . Disse mais Abrão : Dá - me a mulher
86
- que tomaste ; porque daquele poço Eseque , { tinha .} E disse : Não
87
- poderemos descer ; mas , do campo ainda não estava na casa do teu
88
- pescoço . E viveu Serugue , depois Simeão e Levi { são } estes ? E o
89
- varão , porque habitava na terra de Node , da mão de Esaú : Jeús ,
90
- Jalão e Corá
91
-
92
- Texts as List of Words
93
- ----------------------
94
-
95
- A few sentences have been defined for you.
96
-
97
- >>> psent1
98
- ['o', 'amor', 'da', 'gl\xf3ria', 'era', 'a', 'coisa', 'mais',
99
- 'verdadeiramente', 'humana', 'que', 'h\xe1', 'no', 'homem', ',',
100
- 'e', ',', 'conseq\xfcentemente', ',', 'a', 'sua', 'mais',
101
- 'genu\xedna', 'fei\xe7\xe3o', '.']
102
- >>>
103
-
104
- Notice that the sentence has been *tokenized*. Each token is
105
- represented as a string, represented using quotes, e.g. ``'coisa'``.
106
- Some strings contain special characters, e.g. ``\xf3``,
107
- the internal representation for ó.
108
- The tokens are combined in the form of a *list*. How long is this list?
109
-
110
- >>> len(psent1)
111
- 25
112
- >>>
113
-
114
- What is the vocabulary of this sentence?
115
-
116
- >>> sorted(set(psent1))
117
- [',', '.', 'a', 'amor', 'coisa', 'conseqüentemente', 'da', 'e', 'era',
118
- 'feição', 'genuína', 'glória', 'homem', 'humana', 'há', 'mais', 'no',
119
- 'o', 'que', 'sua', 'verdadeiramente']
120
- >>>
121
-
122
- Let's iterate over each item in ``psent2``, and print information for each:
123
-
124
- >>> for w in psent2:
125
- ... print(w, len(w), w[-1])
126
- ...
127
- Não 3 o
128
- consultes 9 s
129
- dicionários 11 s
130
- . 1 .
131
-
132
- Observe how we make a human-readable version of a string, using ``decode()``.
133
- Also notice that we accessed the last character of a string ``w`` using ``w[-1]``.
134
-
135
- We just saw a ``for`` loop above. Another useful control structure is a
136
- *list comprehension*.
137
-
138
- >>> [w.upper() for w in psent2]
139
- ['N\xc3O', 'CONSULTES', 'DICION\xc1RIOS', '.']
140
- >>> [w for w in psent1 if w.endswith('a')]
141
- ['da', 'gl\xf3ria', 'era', 'a', 'coisa', 'humana', 'a', 'sua', 'genu\xedna']
142
- >>> [w for w in ptext4 if len(w) > 15]
143
- [u'norte-irlandeses', u'pan-nacionalismo', u'predominatemente', u'primeiro-ministro',
144
- u'primeiro-ministro', u'irlandesa-americana', u'responsabilidades', u'significativamente']
145
-
146
- We can examine the relative frequency of words in a text, using ``FreqDist``:
147
-
148
- >>> fd1 = FreqDist(ptext1)
149
- >>> fd1
150
- <FreqDist with 10848 samples and 77098 outcomes>
151
- >>> fd1['olhos']
152
- 137
153
- >>> fd1.max()
154
- u','
155
- >>> fd1.samples()[:100]
156
- [u',', u'.', u'a', u'que', u'de', u'e', u'-', u'o', u';', u'me', u'um', u'n\xe3o',
157
- u'\x97', u'se', u'do', u'da', u'uma', u'com', u'os', u'\xe9', u'era', u'as', u'eu',
158
- u'lhe', u'ao', u'em', u'para', u'mas', u'...', u'!', u'\xe0', u'na', u'mais', u'?',
159
- u'no', u'como', u'por', u'N\xe3o', u'dos', u'ou', u'ele', u':', u'Virg\xedlia',
160
- u'meu', u'disse', u'minha', u'das', u'O', u'/', u'A', u'CAP\xcdTULO', u'muito',
161
- u'depois', u'coisa', u'foi', u'sem', u'olhos', u'ela', u'nos', u'tinha', u'nem',
162
- u'E', u'outro', u'vida', u'nada', u'tempo', u'menos', u'outra', u'casa', u'homem',
163
- u'porque', u'quando', u'mim', u'mesmo', u'ser', u'pouco', u'estava', u'dia',
164
- u't\xe3o', u'tudo', u'Mas', u'at\xe9', u'D', u'ainda', u's\xf3', u'alguma',
165
- u'la', u'vez', u'anos', u'h\xe1', u'Era', u'pai', u'esse', u'lo', u'dizer', u'assim',
166
- u'ent\xe3o', u'dizia', u'aos', u'Borba']
167
-
168
- ---------------
169
- Reading Corpora
170
- ---------------
171
-
172
- Accessing the Machado Text Corpus
173
- ---------------------------------
174
-
175
- NLTK includes the complete works of Machado de Assis.
176
-
177
- >>> from nltk.corpus import machado
178
- >>> machado.fileids()
179
- ['contos/macn001.txt', 'contos/macn002.txt', 'contos/macn003.txt', ...]
180
-
181
- Each file corresponds to one of the works of Machado de Assis. To see a complete
182
- list of works, you can look at the corpus README file: ``print machado.readme()``.
183
- Let's access the text of the *Posthumous Memories of Brás Cubas*.
184
-
185
- We can access the text as a list of characters, and access 200 characters starting
186
- from position 10,000.
187
-
188
- >>> raw_text = machado.raw('romance/marm05.txt')
189
- >>> raw_text[10000:10200]
190
- u', primou no\nEstado, e foi um dos amigos particulares do vice-rei Conde
191
- da Cunha.\n\nComo este apelido de Cubas lhe\ncheirasse excessivamente a
192
- tanoaria, alegava meu pai, bisneto de Dami\xe3o, que o\ndito ape'
193
-
194
- However, this is not a very useful way to work with a text. We generally think
195
- of a text as a sequence of words and punctuation, not characters:
196
-
197
- >>> text1 = machado.words('romance/marm05.txt')
198
- >>> text1
199
- ['Romance', ',', 'Mem\xf3rias', 'P\xf3stumas', 'de', ...]
200
- >>> len(text1)
201
- 77098
202
- >>> len(set(text1))
203
- 10848
204
-
205
- Here's a program that finds the most common ngrams that contain a
206
- particular target word.
207
-
208
- >>> from nltk import ngrams, FreqDist
209
- >>> target_word = 'olhos'
210
- >>> fd = FreqDist(ng
211
- ... for ng in ngrams(text1, 5)
212
- ... if target_word in ng)
213
- >>> for hit in fd.samples():
214
- ... print(' '.join(hit))
215
- ...
216
- , com os olhos no
217
- com os olhos no ar
218
- com os olhos no chão
219
- e todos com os olhos
220
- me estar com os olhos
221
- os olhos estúpidos , a
222
- os olhos na costura ,
223
- os olhos no ar ,
224
- , com os olhos espetados
225
- , com os olhos estúpidos
226
- , com os olhos fitos
227
- , com os olhos naquele
228
- , com os olhos para
229
-
230
-
231
- Accessing the MacMorpho Tagged Corpus
232
- -------------------------------------
233
-
234
- NLTK includes the MAC-MORPHO Brazilian Portuguese POS-tagged news text,
235
- with over a million words of
236
- journalistic texts extracted from ten sections of
237
- the daily newspaper *Folha de Sao Paulo*, 1994.
238
-
239
- We can access this corpus as a sequence of words or tagged words as follows:
240
- >>> import nltk.corpus
241
- >>> nltk.corpus.mac_morpho.words()
242
- ['Jersei', 'atinge', 'm\xe9dia', 'de', 'Cr$', '1,4', ...]
243
- >>> nltk.corpus.mac_morpho.sents() # doctest: +NORMALIZE_WHITESPACE
244
- [['Jersei', 'atinge', 'm\xe9dia', 'de', 'Cr$', '1,4', 'milh\xe3o',
245
- 'em', 'a', 'venda', 'de', 'a', 'Pinhal', 'em', 'S\xe3o', 'Paulo'],
246
- ['Programe', 'sua', 'viagem', 'a', 'a', 'Exposi\xe7\xe3o', 'Nacional',
247
- 'do', 'Zebu', ',', 'que', 'come\xe7a', 'dia', '25'], ...]
248
- >>> nltk.corpus.mac_morpho.tagged_words()
249
- [('Jersei', 'N'), ('atinge', 'V'), ('m\xe9dia', 'N'), ...]
250
-
251
- We can also access it in sentence chunks.
252
-
253
- >>> nltk.corpus.mac_morpho.tagged_sents() # doctest: +NORMALIZE_WHITESPACE
254
- [[('Jersei', 'N'), ('atinge', 'V'), ('m\xe9dia', 'N'), ('de', 'PREP'),
255
- ('Cr$', 'CUR'), ('1,4', 'NUM'), ('milh\xe3o', 'N'), ('em', 'PREP|+'),
256
- ('a', 'ART'), ('venda', 'N'), ('de', 'PREP|+'), ('a', 'ART'),
257
- ('Pinhal', 'NPROP'), ('em', 'PREP'), ('S\xe3o', 'NPROP'),
258
- ('Paulo', 'NPROP')],
259
- [('Programe', 'V'), ('sua', 'PROADJ'), ('viagem', 'N'), ('a', 'PREP|+'),
260
- ('a', 'ART'), ('Exposi\xe7\xe3o', 'NPROP'), ('Nacional', 'NPROP'),
261
- ('do', 'NPROP'), ('Zebu', 'NPROP'), (',', ','), ('que', 'PRO-KS-REL'),
262
- ('come\xe7a', 'V'), ('dia', 'N'), ('25', 'N|AP')], ...]
263
-
264
- This data can be used to train taggers (examples below for the Floresta treebank).
265
-
266
- Accessing the Floresta Portuguese Treebank
267
- ------------------------------------------
268
-
269
- The NLTK data distribution includes the
270
- "Floresta Sinta(c)tica Corpus" version 7.4, available from
271
- ``http://www.linguateca.pt/Floresta/``.
272
-
273
- We can access this corpus as a sequence of words or tagged words as follows:
274
-
275
- >>> from nltk.corpus import floresta
276
- >>> floresta.words()
277
- ['Um', 'revivalismo', 'refrescante', 'O', '7_e_Meio', ...]
278
- >>> floresta.tagged_words()
279
- [('Um', '>N+art'), ('revivalismo', 'H+n'), ...]
280
-
281
- The tags consist of some syntactic information, followed by a plus sign,
282
- followed by a conventional part-of-speech tag. Let's strip off the material before
283
- the plus sign:
284
-
285
- >>> def simplify_tag(t):
286
- ... if "+" in t:
287
- ... return t[t.index("+")+1:]
288
- ... else:
289
- ... return t
290
- >>> twords = floresta.tagged_words()
291
- >>> twords = [(w.lower(), simplify_tag(t)) for (w,t) in twords]
292
- >>> twords[:10]
293
- [('um', 'art'), ('revivalismo', 'n'), ('refrescante', 'adj'), ('o', 'art'), ('7_e_meio', 'prop'),
294
- ('\xe9', 'v-fin'), ('um', 'art'), ('ex-libris', 'n'), ('de', 'prp'), ('a', 'art')]
295
-
296
- Pretty printing the tagged words:
297
-
298
- >>> print(' '.join(word + '/' + tag for (word, tag) in twords[:10]))
299
- um/art revivalismo/n refrescante/adj o/art 7_e_meio/prop é/v-fin um/art ex-libris/n de/prp a/art
300
-
301
- Count the word tokens and types, and determine the most common word:
302
-
303
- >>> words = floresta.words()
304
- >>> len(words)
305
- 211852
306
- >>> fd = nltk.FreqDist(words)
307
- >>> len(fd)
308
- 29421
309
- >>> fd.max()
310
- 'de'
311
-
312
- List the 20 most frequent tags, in order of decreasing frequency:
313
-
314
- >>> tags = [simplify_tag(tag) for (word,tag) in floresta.tagged_words()]
315
- >>> fd = nltk.FreqDist(tags)
316
- >>> fd.keys()[:20] # doctest: +NORMALIZE_WHITESPACE
317
- ['n', 'prp', 'art', 'v-fin', ',', 'prop', 'adj', 'adv', '.',
318
- 'conj-c', 'v-inf', 'pron-det', 'v-pcp', 'num', 'pron-indp',
319
- 'pron-pers', '\xab', '\xbb', 'conj-s', '}']
320
-
321
- We can also access the corpus grouped by sentence:
322
-
323
- >>> floresta.sents() # doctest: +NORMALIZE_WHITESPACE
324
- [['Um', 'revivalismo', 'refrescante'],
325
- ['O', '7_e_Meio', '\xe9', 'um', 'ex-libris', 'de', 'a', 'noite',
326
- 'algarvia', '.'], ...]
327
- >>> floresta.tagged_sents() # doctest: +NORMALIZE_WHITESPACE
328
- [[('Um', '>N+art'), ('revivalismo', 'H+n'), ('refrescante', 'N<+adj')],
329
- [('O', '>N+art'), ('7_e_Meio', 'H+prop'), ('\xe9', 'P+v-fin'),
330
- ('um', '>N+art'), ('ex-libris', 'H+n'), ('de', 'H+prp'),
331
- ('a', '>N+art'), ('noite', 'H+n'), ('algarvia', 'N<+adj'), ('.', '.')],
332
- ...]
333
- >>> floresta.parsed_sents() # doctest: +NORMALIZE_WHITESPACE +ELLIPSIS
334
- [Tree('UTT+np', [Tree('>N+art', ['Um']), Tree('H+n', ['revivalismo']),
335
- Tree('N<+adj', ['refrescante'])]),
336
- Tree('STA+fcl',
337
- [Tree('SUBJ+np', [Tree('>N+art', ['O']),
338
- Tree('H+prop', ['7_e_Meio'])]),
339
- Tree('P+v-fin', ['\xe9']),
340
- Tree('SC+np',
341
- [Tree('>N+art', ['um']),
342
- Tree('H+n', ['ex-libris']),
343
- Tree('N<+pp', [Tree('H+prp', ['de']),
344
- Tree('P<+np', [Tree('>N+art', ['a']),
345
- Tree('H+n', ['noite']),
346
- Tree('N<+adj', ['algarvia'])])])]),
347
- Tree('.', ['.'])]), ...]
348
-
349
- To view a parse tree, use the ``draw()`` method, e.g.:
350
-
351
- >>> psents = floresta.parsed_sents()
352
- >>> psents[5].draw() # doctest: +SKIP
353
-
354
- Character Encodings
355
- -------------------
356
-
357
- Python understands the common character encoding used for Portuguese, ISO 8859-1 (ISO Latin 1).
358
-
359
- >>> import os, nltk.test
360
- >>> testdir = os.path.split(nltk.test.__file__)[0]
361
- >>> text = open(os.path.join(testdir, 'floresta.txt'), 'rb').read().decode('ISO 8859-1')
362
- >>> text[:60]
363
- 'O 7 e Meio \xe9 um ex-libris da noite algarvia.\n\xc9 uma das mais '
364
- >>> print(text[:60])
365
- O 7 e Meio é um ex-libris da noite algarvia.
366
- É uma das mais
367
-
368
- For more information about character encodings and Python, please see section 3.3 of the book.
369
-
370
- ----------------
371
- Processing Tasks
372
- ----------------
373
-
374
-
375
- Simple Concordancing
376
- --------------------
377
-
378
- Here's a function that takes a word and a specified amount of context (measured
379
- in characters), and generates a concordance for that word.
380
-
381
- >>> def concordance(word, context=30):
382
- ... for sent in floresta.sents():
383
- ... if word in sent:
384
- ... pos = sent.index(word)
385
- ... left = ' '.join(sent[:pos])
386
- ... right = ' '.join(sent[pos+1:])
387
- ... print('%*s %s %-*s' %
388
- ... (context, left[-context:], word, context, right[:context]))
389
-
390
- >>> concordance("dar") # doctest: +SKIP
391
- anduru , foi o suficiente para dar a volta a o resultado .
392
- 1. O P?BLICO veio dar a a imprensa di?ria portuguesa
393
- A fartura de pensamento pode dar maus resultados e n?s n?o quer
394
- Come?a a dar resultados a pol?tica de a Uni
395
- ial come?ar a incorporar- lo e dar forma a um ' site ' que tem se
396
- r com Constantino para ele lhe dar tamb?m os pap?is assinados .
397
- va a brincar , pois n?o lhe ia dar procura??o nenhuma enquanto n?
398
- ?rica como o ant?doto capaz de dar sentido a o seu enorme poder .
399
- . . .
400
- >>> concordance("vender") # doctest: +SKIP
401
- er recebido uma encomenda para vender 4000 blindados a o Iraque .
402
- m?rico_Amorim caso conseguisse vender o lote de ac??es de o empres?r
403
- mpre ter jovens simp?ticos a ? vender ? chega ! }
404
- Disse que o governo vai vender ? desde autom?vel at? particip
405
- ndiciou ontem duas pessoas por vender carro com ?gio .
406
- A inten??o de Fleury ? vender as a??es para equilibrar as fi
407
-
408
- Part-of-Speech Tagging
409
- ----------------------
410
-
411
- Let's begin by getting the tagged sentence data, and simplifying the tags
412
- as described earlier.
413
-
414
- >>> from nltk.corpus import floresta
415
- >>> tsents = floresta.tagged_sents()
416
- >>> tsents = [[(w.lower(),simplify_tag(t)) for (w,t) in sent] for sent in tsents if sent]
417
- >>> train = tsents[100:]
418
- >>> test = tsents[:100]
419
-
420
- We already know that ``n`` is the most common tag, so we can set up a
421
- default tagger that tags every word as a noun, and see how well it does:
422
-
423
- >>> tagger0 = nltk.DefaultTagger('n')
424
- >>> nltk.tag.accuracy(tagger0, test)
425
- 0.17697228144989338
426
-
427
- Evidently, about one in every six words is a noun. Let's improve on this by
428
- training a unigram tagger:
429
-
430
- >>> tagger1 = nltk.UnigramTagger(train, backoff=tagger0)
431
- >>> nltk.tag.accuracy(tagger1, test)
432
- 0.87029140014214645
433
-
434
- Next a bigram tagger:
435
-
436
- >>> tagger2 = nltk.BigramTagger(train, backoff=tagger1)
437
- >>> nltk.tag.accuracy(tagger2, test)
438
- 0.89019189765458417
439
-
440
-
441
- Sentence Segmentation
442
- ---------------------
443
-
444
- Punkt is a language-neutral sentence segmentation tool. We
445
-
446
- >>> sent_tokenizer=nltk.data.load('tokenizers/punkt/portuguese.pickle')
447
- >>> raw_text = machado.raw('romance/marm05.txt')
448
- >>> sentences = sent_tokenizer.tokenize(raw_text)
449
- >>> for sent in sentences[1000:1005]:
450
- ... print("<<", sent, ">>")
451
- ...
452
- << Em verdade, parecia ainda mais mulher do que era;
453
- seria criança nos seus folgares de moça; mas assim quieta, impassível, tinha a
454
- compostura da mulher casada. >>
455
- << Talvez essa circunstância lhe diminuía um pouco da
456
- graça virginal. >>
457
- << Depressa nos familiarizamos; a mãe fazia-lhe grandes elogios, eu
458
- escutava-os de boa sombra, e ela sorria com os olhos fúlgidos, como se lá dentro
459
- do cérebro lhe estivesse a voar uma borboletinha de asas de ouro e olhos de
460
- diamante... >>
461
- << Digo lá dentro, porque cá fora o
462
- que esvoaçou foi uma borboleta preta, que subitamente penetrou na varanda, e
463
- começou a bater as asas em derredor de D. Eusébia. >>
464
- << D. Eusébia deu um grito,
465
- levantou-se, praguejou umas palavras soltas: - T'esconjuro!... >>
466
-
467
- The sentence tokenizer can be trained and evaluated on other text.
468
- The source text (from the Floresta Portuguese Treebank) contains one sentence per line.
469
- We read the text, split it into its lines, and then join these lines together using
470
- spaces. Now the information about sentence breaks has been discarded. We split this
471
- material into training and testing data:
472
-
473
- >>> import os, nltk.test
474
- >>> testdir = os.path.split(nltk.test.__file__)[0]
475
- >>> text = open(os.path.join(testdir, 'floresta.txt'), 'rb').read().decode('ISO-8859-1')
476
- >>> lines = text.split('\n')
477
- >>> train = ' '.join(lines[10:])
478
- >>> test = ' '.join(lines[:10])
479
-
480
- Now we train the sentence segmenter (or sentence tokenizer) and use it on our test sentences:
481
-
482
- >>> stok = nltk.PunktSentenceTokenizer(train)
483
- >>> print(stok.tokenize(test))
484
- ['O 7 e Meio \xe9 um ex-libris da noite algarvia.',
485
- '\xc9 uma das mais antigas discotecas do Algarve, situada em Albufeira,
486
- que continua a manter os tra\xe7os decorativos e as clientelas de sempre.',
487
- '\xc9 um pouco a vers\xe3o de uma esp\xe9cie de \xaboutro lado\xbb da noite,
488
- a meio caminho entre os devaneios de uma fauna perif\xe9rica, seja de Lisboa,
489
- Londres, Dublin ou Faro e Portim\xe3o, e a postura circunspecta dos fi\xe9is da casa,
490
- que dela esperam a m\xfasica \xabgeracionista\xbb dos 60 ou dos 70.',
491
- 'N\xe3o deixa de ser, nos tempos que correm, um certo \xabvery typical\xbb algarvio,
492
- cabe\xe7a de cartaz para os que querem fugir a algumas movimenta\xe7\xf5es nocturnas
493
- j\xe1 a caminho da ritualiza\xe7\xe3o de massas, do g\xe9nero \xabvamos todos ao
494
- Calypso e encontramo-nos na Locomia\xbb.',
495
- 'E assim, aos 2,5 milh\xf5es que o Minist\xe9rio do Planeamento e Administra\xe7\xe3o
496
- do Territ\xf3rio j\xe1 gasta no pagamento do pessoal afecto a estes organismos,
497
- v\xeam juntar-se os montantes das obras propriamente ditas, que os munic\xedpios,
498
- j\xe1 com projectos na m\xe3o, v\xeam reivindicar junto do Executivo, como salienta
499
- aquele membro do Governo.',
500
- 'E o dinheiro \xabn\xe3o falta s\xf3 \xe0s c\xe2maras\xbb, lembra o secret\xe1rio de Estado,
501
- que considera que a solu\xe7\xe3o para as autarquias \xe9 \xabespecializarem-se em
502
- fundos comunit\xe1rios\xbb.',
503
- 'Mas como, se muitas n\xe3o disp\xf5em, nos seus quadros, dos t\xe9cnicos necess\xe1rios?',
504
- '\xabEncomendem-nos a projectistas de fora\xbb porque, se as obras vierem a ser financiadas,
505
- eles at\xe9 saem de gra\xe7a, j\xe1 que, nesse caso, \xabos fundos comunit\xe1rios pagam
506
- os projectos, o mesmo n\xe3o acontecendo quando eles s\xe3o feitos pelos GAT\xbb,
507
- dado serem organismos do Estado.',
508
- 'Essa poder\xe1 vir a ser uma hip\xf3tese, at\xe9 porque, no terreno, a capacidade dos GAT
509
- est\xe1 cada vez mais enfraquecida.',
510
- 'Alguns at\xe9 j\xe1 desapareceram, como o de Castro Verde, e outros t\xeam vindo a perder quadros.']
511
-
512
- NLTK's data collection includes a trained model for Portuguese sentence
513
- segmentation, which can be loaded as follows. It is faster to load a trained model than
514
- to retrain it.
515
-
516
- >>> stok = nltk.data.load('tokenizers/punkt/portuguese.pickle')
517
-
518
- Stemming
519
- --------
520
-
521
- NLTK includes the RSLP Portuguese stemmer. Here we use it to stem some Portuguese text:
522
-
523
- >>> stemmer = nltk.stem.RSLPStemmer()
524
- >>> stemmer.stem("copiar")
525
- 'copi'
526
- >>> stemmer.stem("paisagem")
527
- 'pais'
528
-
529
-
530
- Stopwords
531
- ---------
532
-
533
- NLTK includes Portuguese stopwords:
534
-
535
- >>> stopwords = nltk.corpus.stopwords.words('portuguese')
536
- >>> stopwords[:10]
537
- ['a', 'ao', 'aos', 'aquela', 'aquelas', 'aquele', 'aqueles', 'aquilo', 'as', 'at\xe9']
538
-
539
- Now we can use these to filter text. Let's find the most frequent words (other than stopwords)
540
- and print them in descending order of frequency:
541
-
542
- >>> fd = nltk.FreqDist(w.lower() for w in floresta.words() if w not in stopwords)
543
- >>> for word in list(fd.keys())[:20]:
544
- ... print(word, fd[word])
545
- , 13444
546
- . 7725
547
- « 2369
548
- » 2310
549
- é 1305
550
- o 1086
551
- } 1047
552
- { 1044
553
- a 897
554
- ; 633
555
- em 516
556
- ser 466
557
- sobre 349
558
- os 313
559
- anos 301
560
- ontem 292
561
- ainda 279
562
- segundo 256
563
- ter 249
564
- dois 231
565
-
1
+ .. Copyright (C) 2001-2018 NLTK Project
2
+ .. For license information, see LICENSE.TXT
3
+
4
+ ==================================
5
+ Examples for Portuguese Processing
6
+ ==================================
7
+
8
+ This HOWTO contains a variety of examples relating to the Portuguese language.
9
+ It is intended to be read in conjunction with the NLTK book
10
+ (``http://nltk.org/book``). For instructions on running the Python
11
+ interpreter, please see the section *Getting Started with Python*, in Chapter 1.
12
+
13
+ --------------------------------------------
14
+ Python Programming, with Portuguese Examples
15
+ --------------------------------------------
16
+
17
+ Chapter 1 of the NLTK book contains many elementary programming examples, all
18
+ with English texts. In this section, we'll see some corresponding examples
19
+ using Portuguese. Please refer to the chapter for full discussion. *Vamos!*
20
+
21
+ >>> from nltk.examples.pt import *
22
+ *** Introductory Examples for the NLTK Book ***
23
+ Loading ptext1, ... and psent1, ...
24
+ Type the name of the text or sentence to view it.
25
+ Type: 'texts()' or 'sents()' to list the materials.
26
+ ptext1: Memórias Póstumas de Brás Cubas (1881)
27
+ ptext2: Dom Casmurro (1899)
28
+ ptext3: Gênesis
29
+ ptext4: Folha de Sao Paulo (1994)
30
+
31
+
32
+ Any time we want to find out about these texts, we just have
33
+ to enter their names at the Python prompt:
34
+
35
+ >>> ptext2
36
+ <Text: Dom Casmurro (1899)>
37
+
38
+ Searching Text
39
+ --------------
40
+
41
+ A concordance permits us to see words in context.
42
+
43
+ >>> ptext1.concordance('olhos')
44
+ Building index...
45
+ Displaying 25 of 138 matches:
46
+ De pé , à cabeceira da cama , com os olhos estúpidos , a boca entreaberta , a t
47
+ orelhas . Pela minha parte fechei os olhos e deixei - me ir à ventura . Já agor
48
+ xões de cérebro enfermo . Como ia de olhos fechados , não via o caminho ; lembr
49
+ gelos eternos . Com efeito , abri os olhos e vi que o meu animal galopava numa
50
+ me apareceu então , fitando - me uns olhos rutilantes como o sol . Tudo nessa f
51
+ mim mesmo . Então , encarei - a com olhos súplices , e pedi mais alguns anos .
52
+ ...
53
+
54
+ For a given word, we can find words with a similar text distribution:
55
+
56
+ >>> ptext1.similar('chegar')
57
+ Building word-context index...
58
+ acabada acudir aludir avistar bramanismo casamento cheguei com contar
59
+ contrário corpo dali deixei desferirem dizer fazer filhos já leitor lhe
60
+ >>> ptext3.similar('chegar')
61
+ Building word-context index...
62
+ achar alumiar arrombar destruir governar guardar ir lavrar passar que
63
+ toda tomar ver vir
64
+
65
+ We can search for the statistically significant collocations in a text:
66
+
67
+ >>> ptext1.collocations()
68
+ Building collocations list
69
+ Quincas Borba; Lobo Neves; alguma coisa; Brás Cubas; meu pai; dia
70
+ seguinte; não sei; Meu pai; alguns instantes; outra vez; outra coisa;
71
+ por exemplo; mim mesmo; coisa nenhuma; mesma coisa; não era; dias
72
+ depois; Passeio Público; olhar para; das coisas
73
+
74
+ We can search for words in context, with the help of *regular expressions*, e.g.:
75
+
76
+ >>> ptext1.findall("<olhos> (<.*>)")
77
+ estúpidos; e; fechados; rutilantes; súplices; a; do; babavam;
78
+ na; moles; se; da; umas; espraiavam; chamejantes; espetados;
79
+ ...
80
+
81
+ We can automatically generate random text based on a given text, e.g.:
82
+
83
+ >>> ptext3.generate() # doctest: +SKIP
84
+ No princípio , criou Deus os abençoou , dizendo : Onde { estão } e até
85
+ à ave dos céus , { que } será . Disse mais Abrão : Dá - me a mulher
86
+ que tomaste ; porque daquele poço Eseque , { tinha .} E disse : Não
87
+ poderemos descer ; mas , do campo ainda não estava na casa do teu
88
+ pescoço . E viveu Serugue , depois Simeão e Levi { são } estes ? E o
89
+ varão , porque habitava na terra de Node , da mão de Esaú : Jeús ,
90
+ Jalão e Corá
91
+
92
+ Texts as List of Words
93
+ ----------------------
94
+
95
+ A few sentences have been defined for you.
96
+
97
+ >>> psent1
98
+ ['o', 'amor', 'da', 'gl\xf3ria', 'era', 'a', 'coisa', 'mais',
99
+ 'verdadeiramente', 'humana', 'que', 'h\xe1', 'no', 'homem', ',',
100
+ 'e', ',', 'conseq\xfcentemente', ',', 'a', 'sua', 'mais',
101
+ 'genu\xedna', 'fei\xe7\xe3o', '.']
102
+ >>>
103
+
104
+ Notice that the sentence has been *tokenized*. Each token is
105
+ represented as a string, represented using quotes, e.g. ``'coisa'``.
106
+ Some strings contain special characters, e.g. ``\xf3``,
107
+ the internal representation for ó.
108
+ The tokens are combined in the form of a *list*. How long is this list?
109
+
110
+ >>> len(psent1)
111
+ 25
112
+ >>>
113
+
114
+ What is the vocabulary of this sentence?
115
+
116
+ >>> sorted(set(psent1))
117
+ [',', '.', 'a', 'amor', 'coisa', 'conseqüentemente', 'da', 'e', 'era',
118
+ 'feição', 'genuína', 'glória', 'homem', 'humana', 'há', 'mais', 'no',
119
+ 'o', 'que', 'sua', 'verdadeiramente']
120
+ >>>
121
+
122
+ Let's iterate over each item in ``psent2``, and print information for each:
123
+
124
+ >>> for w in psent2:
125
+ ... print(w, len(w), w[-1])
126
+ ...
127
+ Não 3 o
128
+ consultes 9 s
129
+ dicionários 11 s
130
+ . 1 .
131
+
132
+ Observe how we make a human-readable version of a string, using ``decode()``.
133
+ Also notice that we accessed the last character of a string ``w`` using ``w[-1]``.
134
+
135
+ We just saw a ``for`` loop above. Another useful control structure is a
136
+ *list comprehension*.
137
+
138
+ >>> [w.upper() for w in psent2]
139
+ ['N\xc3O', 'CONSULTES', 'DICION\xc1RIOS', '.']
140
+ >>> [w for w in psent1 if w.endswith('a')]
141
+ ['da', 'gl\xf3ria', 'era', 'a', 'coisa', 'humana', 'a', 'sua', 'genu\xedna']
142
+ >>> [w for w in ptext4 if len(w) > 15]
143
+ [u'norte-irlandeses', u'pan-nacionalismo', u'predominatemente', u'primeiro-ministro',
144
+ u'primeiro-ministro', u'irlandesa-americana', u'responsabilidades', u'significativamente']
145
+
146
+ We can examine the relative frequency of words in a text, using ``FreqDist``:
147
+
148
+ >>> fd1 = FreqDist(ptext1)
149
+ >>> fd1
150
+ <FreqDist with 10848 samples and 77098 outcomes>
151
+ >>> fd1['olhos']
152
+ 137
153
+ >>> fd1.max()
154
+ u','
155
+ >>> fd1.samples()[:100]
156
+ [u',', u'.', u'a', u'que', u'de', u'e', u'-', u'o', u';', u'me', u'um', u'n\xe3o',
157
+ u'\x97', u'se', u'do', u'da', u'uma', u'com', u'os', u'\xe9', u'era', u'as', u'eu',
158
+ u'lhe', u'ao', u'em', u'para', u'mas', u'...', u'!', u'\xe0', u'na', u'mais', u'?',
159
+ u'no', u'como', u'por', u'N\xe3o', u'dos', u'ou', u'ele', u':', u'Virg\xedlia',
160
+ u'meu', u'disse', u'minha', u'das', u'O', u'/', u'A', u'CAP\xcdTULO', u'muito',
161
+ u'depois', u'coisa', u'foi', u'sem', u'olhos', u'ela', u'nos', u'tinha', u'nem',
162
+ u'E', u'outro', u'vida', u'nada', u'tempo', u'menos', u'outra', u'casa', u'homem',
163
+ u'porque', u'quando', u'mim', u'mesmo', u'ser', u'pouco', u'estava', u'dia',
164
+ u't\xe3o', u'tudo', u'Mas', u'at\xe9', u'D', u'ainda', u's\xf3', u'alguma',
165
+ u'la', u'vez', u'anos', u'h\xe1', u'Era', u'pai', u'esse', u'lo', u'dizer', u'assim',
166
+ u'ent\xe3o', u'dizia', u'aos', u'Borba']
167
+
168
+ ---------------
169
+ Reading Corpora
170
+ ---------------
171
+
172
+ Accessing the Machado Text Corpus
173
+ ---------------------------------
174
+
175
+ NLTK includes the complete works of Machado de Assis.
176
+
177
+ >>> from nltk.corpus import machado
178
+ >>> machado.fileids()
179
+ ['contos/macn001.txt', 'contos/macn002.txt', 'contos/macn003.txt', ...]
180
+
181
+ Each file corresponds to one of the works of Machado de Assis. To see a complete
182
+ list of works, you can look at the corpus README file: ``print machado.readme()``.
183
+ Let's access the text of the *Posthumous Memories of Brás Cubas*.
184
+
185
+ We can access the text as a list of characters, and access 200 characters starting
186
+ from position 10,000.
187
+
188
+ >>> raw_text = machado.raw('romance/marm05.txt')
189
+ >>> raw_text[10000:10200]
190
+ u', primou no\nEstado, e foi um dos amigos particulares do vice-rei Conde
191
+ da Cunha.\n\nComo este apelido de Cubas lhe\ncheirasse excessivamente a
192
+ tanoaria, alegava meu pai, bisneto de Dami\xe3o, que o\ndito ape'
193
+
194
+ However, this is not a very useful way to work with a text. We generally think
195
+ of a text as a sequence of words and punctuation, not characters:
196
+
197
+ >>> text1 = machado.words('romance/marm05.txt')
198
+ >>> text1
199
+ ['Romance', ',', 'Mem\xf3rias', 'P\xf3stumas', 'de', ...]
200
+ >>> len(text1)
201
+ 77098
202
+ >>> len(set(text1))
203
+ 10848
204
+
205
+ Here's a program that finds the most common ngrams that contain a
206
+ particular target word.
207
+
208
+ >>> from nltk import ngrams, FreqDist
209
+ >>> target_word = 'olhos'
210
+ >>> fd = FreqDist(ng
211
+ ... for ng in ngrams(text1, 5)
212
+ ... if target_word in ng)
213
+ >>> for hit in fd.samples():
214
+ ... print(' '.join(hit))
215
+ ...
216
+ , com os olhos no
217
+ com os olhos no ar
218
+ com os olhos no chão
219
+ e todos com os olhos
220
+ me estar com os olhos
221
+ os olhos estúpidos , a
222
+ os olhos na costura ,
223
+ os olhos no ar ,
224
+ , com os olhos espetados
225
+ , com os olhos estúpidos
226
+ , com os olhos fitos
227
+ , com os olhos naquele
228
+ , com os olhos para
229
+
230
+
231
+ Accessing the MacMorpho Tagged Corpus
232
+ -------------------------------------
233
+
234
+ NLTK includes the MAC-MORPHO Brazilian Portuguese POS-tagged news text,
235
+ with over a million words of
236
+ journalistic texts extracted from ten sections of
237
+ the daily newspaper *Folha de Sao Paulo*, 1994.
238
+
239
+ We can access this corpus as a sequence of words or tagged words as follows:
240
+ >>> import nltk.corpus
241
+ >>> nltk.corpus.mac_morpho.words()
242
+ ['Jersei', 'atinge', 'm\xe9dia', 'de', 'Cr$', '1,4', ...]
243
+ >>> nltk.corpus.mac_morpho.sents() # doctest: +NORMALIZE_WHITESPACE
244
+ [['Jersei', 'atinge', 'm\xe9dia', 'de', 'Cr$', '1,4', 'milh\xe3o',
245
+ 'em', 'a', 'venda', 'de', 'a', 'Pinhal', 'em', 'S\xe3o', 'Paulo'],
246
+ ['Programe', 'sua', 'viagem', 'a', 'a', 'Exposi\xe7\xe3o', 'Nacional',
247
+ 'do', 'Zebu', ',', 'que', 'come\xe7a', 'dia', '25'], ...]
248
+ >>> nltk.corpus.mac_morpho.tagged_words()
249
+ [('Jersei', 'N'), ('atinge', 'V'), ('m\xe9dia', 'N'), ...]
250
+
251
+ We can also access it in sentence chunks.
252
+
253
+ >>> nltk.corpus.mac_morpho.tagged_sents() # doctest: +NORMALIZE_WHITESPACE
254
+ [[('Jersei', 'N'), ('atinge', 'V'), ('m\xe9dia', 'N'), ('de', 'PREP'),
255
+ ('Cr$', 'CUR'), ('1,4', 'NUM'), ('milh\xe3o', 'N'), ('em', 'PREP|+'),
256
+ ('a', 'ART'), ('venda', 'N'), ('de', 'PREP|+'), ('a', 'ART'),
257
+ ('Pinhal', 'NPROP'), ('em', 'PREP'), ('S\xe3o', 'NPROP'),
258
+ ('Paulo', 'NPROP')],
259
+ [('Programe', 'V'), ('sua', 'PROADJ'), ('viagem', 'N'), ('a', 'PREP|+'),
260
+ ('a', 'ART'), ('Exposi\xe7\xe3o', 'NPROP'), ('Nacional', 'NPROP'),
261
+ ('do', 'NPROP'), ('Zebu', 'NPROP'), (',', ','), ('que', 'PRO-KS-REL'),
262
+ ('come\xe7a', 'V'), ('dia', 'N'), ('25', 'N|AP')], ...]
263
+
264
+ This data can be used to train taggers (examples below for the Floresta treebank).
265
+
266
+ Accessing the Floresta Portuguese Treebank
267
+ ------------------------------------------
268
+
269
+ The NLTK data distribution includes the
270
+ "Floresta Sinta(c)tica Corpus" version 7.4, available from
271
+ ``http://www.linguateca.pt/Floresta/``.
272
+
273
+ We can access this corpus as a sequence of words or tagged words as follows:
274
+
275
+ >>> from nltk.corpus import floresta
276
+ >>> floresta.words()
277
+ ['Um', 'revivalismo', 'refrescante', 'O', '7_e_Meio', ...]
278
+ >>> floresta.tagged_words()
279
+ [('Um', '>N+art'), ('revivalismo', 'H+n'), ...]
280
+
281
+ The tags consist of some syntactic information, followed by a plus sign,
282
+ followed by a conventional part-of-speech tag. Let's strip off the material before
283
+ the plus sign:
284
+
285
+ >>> def simplify_tag(t):
286
+ ... if "+" in t:
287
+ ... return t[t.index("+")+1:]
288
+ ... else:
289
+ ... return t
290
+ >>> twords = floresta.tagged_words()
291
+ >>> twords = [(w.lower(), simplify_tag(t)) for (w,t) in twords]
292
+ >>> twords[:10]
293
+ [('um', 'art'), ('revivalismo', 'n'), ('refrescante', 'adj'), ('o', 'art'), ('7_e_meio', 'prop'),
294
+ ('\xe9', 'v-fin'), ('um', 'art'), ('ex-libris', 'n'), ('de', 'prp'), ('a', 'art')]
295
+
296
+ Pretty printing the tagged words:
297
+
298
+ >>> print(' '.join(word + '/' + tag for (word, tag) in twords[:10]))
299
+ um/art revivalismo/n refrescante/adj o/art 7_e_meio/prop é/v-fin um/art ex-libris/n de/prp a/art
300
+
301
+ Count the word tokens and types, and determine the most common word:
302
+
303
+ >>> words = floresta.words()
304
+ >>> len(words)
305
+ 211852
306
+ >>> fd = nltk.FreqDist(words)
307
+ >>> len(fd)
308
+ 29421
309
+ >>> fd.max()
310
+ 'de'
311
+
312
+ List the 20 most frequent tags, in order of decreasing frequency:
313
+
314
+ >>> tags = [simplify_tag(tag) for (word,tag) in floresta.tagged_words()]
315
+ >>> fd = nltk.FreqDist(tags)
316
+ >>> fd.keys()[:20] # doctest: +NORMALIZE_WHITESPACE
317
+ ['n', 'prp', 'art', 'v-fin', ',', 'prop', 'adj', 'adv', '.',
318
+ 'conj-c', 'v-inf', 'pron-det', 'v-pcp', 'num', 'pron-indp',
319
+ 'pron-pers', '\xab', '\xbb', 'conj-s', '}']
320
+
321
+ We can also access the corpus grouped by sentence:
322
+
323
+ >>> floresta.sents() # doctest: +NORMALIZE_WHITESPACE
324
+ [['Um', 'revivalismo', 'refrescante'],
325
+ ['O', '7_e_Meio', '\xe9', 'um', 'ex-libris', 'de', 'a', 'noite',
326
+ 'algarvia', '.'], ...]
327
+ >>> floresta.tagged_sents() # doctest: +NORMALIZE_WHITESPACE
328
+ [[('Um', '>N+art'), ('revivalismo', 'H+n'), ('refrescante', 'N<+adj')],
329
+ [('O', '>N+art'), ('7_e_Meio', 'H+prop'), ('\xe9', 'P+v-fin'),
330
+ ('um', '>N+art'), ('ex-libris', 'H+n'), ('de', 'H+prp'),
331
+ ('a', '>N+art'), ('noite', 'H+n'), ('algarvia', 'N<+adj'), ('.', '.')],
332
+ ...]
333
+ >>> floresta.parsed_sents() # doctest: +NORMALIZE_WHITESPACE +ELLIPSIS
334
+ [Tree('UTT+np', [Tree('>N+art', ['Um']), Tree('H+n', ['revivalismo']),
335
+ Tree('N<+adj', ['refrescante'])]),
336
+ Tree('STA+fcl',
337
+ [Tree('SUBJ+np', [Tree('>N+art', ['O']),
338
+ Tree('H+prop', ['7_e_Meio'])]),
339
+ Tree('P+v-fin', ['\xe9']),
340
+ Tree('SC+np',
341
+ [Tree('>N+art', ['um']),
342
+ Tree('H+n', ['ex-libris']),
343
+ Tree('N<+pp', [Tree('H+prp', ['de']),
344
+ Tree('P<+np', [Tree('>N+art', ['a']),
345
+ Tree('H+n', ['noite']),
346
+ Tree('N<+adj', ['algarvia'])])])]),
347
+ Tree('.', ['.'])]), ...]
348
+
349
+ To view a parse tree, use the ``draw()`` method, e.g.:
350
+
351
+ >>> psents = floresta.parsed_sents()
352
+ >>> psents[5].draw() # doctest: +SKIP
353
+
354
+ Character Encodings
355
+ -------------------
356
+
357
+ Python understands the common character encoding used for Portuguese, ISO 8859-1 (ISO Latin 1).
358
+
359
+ >>> import os, nltk.test
360
+ >>> testdir = os.path.split(nltk.test.__file__)[0]
361
+ >>> text = open(os.path.join(testdir, 'floresta.txt'), 'rb').read().decode('ISO 8859-1')
362
+ >>> text[:60]
363
+ 'O 7 e Meio \xe9 um ex-libris da noite algarvia.\n\xc9 uma das mais '
364
+ >>> print(text[:60])
365
+ O 7 e Meio é um ex-libris da noite algarvia.
366
+ É uma das mais
367
+
368
+ For more information about character encodings and Python, please see section 3.3 of the book.
369
+
370
+ ----------------
371
+ Processing Tasks
372
+ ----------------
373
+
374
+
375
+ Simple Concordancing
376
+ --------------------
377
+
378
+ Here's a function that takes a word and a specified amount of context (measured
379
+ in characters), and generates a concordance for that word.
380
+
381
+ >>> def concordance(word, context=30):
382
+ ... for sent in floresta.sents():
383
+ ... if word in sent:
384
+ ... pos = sent.index(word)
385
+ ... left = ' '.join(sent[:pos])
386
+ ... right = ' '.join(sent[pos+1:])
387
+ ... print('%*s %s %-*s' %
388
+ ... (context, left[-context:], word, context, right[:context]))
389
+
390
+ >>> concordance("dar") # doctest: +SKIP
391
+ anduru , foi o suficiente para dar a volta a o resultado .
392
+ 1. O P?BLICO veio dar a a imprensa di?ria portuguesa
393
+ A fartura de pensamento pode dar maus resultados e n?s n?o quer
394
+ Come?a a dar resultados a pol?tica de a Uni
395
+ ial come?ar a incorporar- lo e dar forma a um ' site ' que tem se
396
+ r com Constantino para ele lhe dar tamb?m os pap?is assinados .
397
+ va a brincar , pois n?o lhe ia dar procura??o nenhuma enquanto n?
398
+ ?rica como o ant?doto capaz de dar sentido a o seu enorme poder .
399
+ . . .
400
+ >>> concordance("vender") # doctest: +SKIP
401
+ er recebido uma encomenda para vender 4000 blindados a o Iraque .
402
+ m?rico_Amorim caso conseguisse vender o lote de ac??es de o empres?r
403
+ mpre ter jovens simp?ticos a ? vender ? chega ! }
404
+ Disse que o governo vai vender ? desde autom?vel at? particip
405
+ ndiciou ontem duas pessoas por vender carro com ?gio .
406
+ A inten??o de Fleury ? vender as a??es para equilibrar as fi
407
+
408
+ Part-of-Speech Tagging
409
+ ----------------------
410
+
411
+ Let's begin by getting the tagged sentence data, and simplifying the tags
412
+ as described earlier.
413
+
414
+ >>> from nltk.corpus import floresta
415
+ >>> tsents = floresta.tagged_sents()
416
+ >>> tsents = [[(w.lower(),simplify_tag(t)) for (w,t) in sent] for sent in tsents if sent]
417
+ >>> train = tsents[100:]
418
+ >>> test = tsents[:100]
419
+
420
+ We already know that ``n`` is the most common tag, so we can set up a
421
+ default tagger that tags every word as a noun, and see how well it does:
422
+
423
+ >>> tagger0 = nltk.DefaultTagger('n')
424
+ >>> nltk.tag.accuracy(tagger0, test)
425
+ 0.17697228144989338
426
+
427
+ Evidently, about one in every six words is a noun. Let's improve on this by
428
+ training a unigram tagger:
429
+
430
+ >>> tagger1 = nltk.UnigramTagger(train, backoff=tagger0)
431
+ >>> nltk.tag.accuracy(tagger1, test)
432
+ 0.87029140014214645
433
+
434
+ Next a bigram tagger:
435
+
436
+ >>> tagger2 = nltk.BigramTagger(train, backoff=tagger1)
437
+ >>> nltk.tag.accuracy(tagger2, test)
438
+ 0.89019189765458417
439
+
440
+
441
+ Sentence Segmentation
442
+ ---------------------
443
+
444
+ Punkt is a language-neutral sentence segmentation tool. We
445
+
446
+ >>> sent_tokenizer=nltk.data.load('tokenizers/punkt/portuguese.pickle')
447
+ >>> raw_text = machado.raw('romance/marm05.txt')
448
+ >>> sentences = sent_tokenizer.tokenize(raw_text)
449
+ >>> for sent in sentences[1000:1005]:
450
+ ... print("<<", sent, ">>")
451
+ ...
452
+ << Em verdade, parecia ainda mais mulher do que era;
453
+ seria criança nos seus folgares de moça; mas assim quieta, impassível, tinha a
454
+ compostura da mulher casada. >>
455
+ << Talvez essa circunstância lhe diminuía um pouco da
456
+ graça virginal. >>
457
+ << Depressa nos familiarizamos; a mãe fazia-lhe grandes elogios, eu
458
+ escutava-os de boa sombra, e ela sorria com os olhos fúlgidos, como se lá dentro
459
+ do cérebro lhe estivesse a voar uma borboletinha de asas de ouro e olhos de
460
+ diamante... >>
461
+ << Digo lá dentro, porque cá fora o
462
+ que esvoaçou foi uma borboleta preta, que subitamente penetrou na varanda, e
463
+ começou a bater as asas em derredor de D. Eusébia. >>
464
+ << D. Eusébia deu um grito,
465
+ levantou-se, praguejou umas palavras soltas: - T'esconjuro!... >>
466
+
467
+ The sentence tokenizer can be trained and evaluated on other text.
468
+ The source text (from the Floresta Portuguese Treebank) contains one sentence per line.
469
+ We read the text, split it into its lines, and then join these lines together using
470
+ spaces. Now the information about sentence breaks has been discarded. We split this
471
+ material into training and testing data:
472
+
473
+ >>> import os, nltk.test
474
+ >>> testdir = os.path.split(nltk.test.__file__)[0]
475
+ >>> text = open(os.path.join(testdir, 'floresta.txt'), 'rb').read().decode('ISO-8859-1')
476
+ >>> lines = text.split('\n')
477
+ >>> train = ' '.join(lines[10:])
478
+ >>> test = ' '.join(lines[:10])
479
+
480
+ Now we train the sentence segmenter (or sentence tokenizer) and use it on our test sentences:
481
+
482
+ >>> stok = nltk.PunktSentenceTokenizer(train)
483
+ >>> print(stok.tokenize(test))
484
+ ['O 7 e Meio \xe9 um ex-libris da noite algarvia.',
485
+ '\xc9 uma das mais antigas discotecas do Algarve, situada em Albufeira,
486
+ que continua a manter os tra\xe7os decorativos e as clientelas de sempre.',
487
+ '\xc9 um pouco a vers\xe3o de uma esp\xe9cie de \xaboutro lado\xbb da noite,
488
+ a meio caminho entre os devaneios de uma fauna perif\xe9rica, seja de Lisboa,
489
+ Londres, Dublin ou Faro e Portim\xe3o, e a postura circunspecta dos fi\xe9is da casa,
490
+ que dela esperam a m\xfasica \xabgeracionista\xbb dos 60 ou dos 70.',
491
+ 'N\xe3o deixa de ser, nos tempos que correm, um certo \xabvery typical\xbb algarvio,
492
+ cabe\xe7a de cartaz para os que querem fugir a algumas movimenta\xe7\xf5es nocturnas
493
+ j\xe1 a caminho da ritualiza\xe7\xe3o de massas, do g\xe9nero \xabvamos todos ao
494
+ Calypso e encontramo-nos na Locomia\xbb.',
495
+ 'E assim, aos 2,5 milh\xf5es que o Minist\xe9rio do Planeamento e Administra\xe7\xe3o
496
+ do Territ\xf3rio j\xe1 gasta no pagamento do pessoal afecto a estes organismos,
497
+ v\xeam juntar-se os montantes das obras propriamente ditas, que os munic\xedpios,
498
+ j\xe1 com projectos na m\xe3o, v\xeam reivindicar junto do Executivo, como salienta
499
+ aquele membro do Governo.',
500
+ 'E o dinheiro \xabn\xe3o falta s\xf3 \xe0s c\xe2maras\xbb, lembra o secret\xe1rio de Estado,
501
+ que considera que a solu\xe7\xe3o para as autarquias \xe9 \xabespecializarem-se em
502
+ fundos comunit\xe1rios\xbb.',
503
+ 'Mas como, se muitas n\xe3o disp\xf5em, nos seus quadros, dos t\xe9cnicos necess\xe1rios?',
504
+ '\xabEncomendem-nos a projectistas de fora\xbb porque, se as obras vierem a ser financiadas,
505
+ eles at\xe9 saem de gra\xe7a, j\xe1 que, nesse caso, \xabos fundos comunit\xe1rios pagam
506
+ os projectos, o mesmo n\xe3o acontecendo quando eles s\xe3o feitos pelos GAT\xbb,
507
+ dado serem organismos do Estado.',
508
+ 'Essa poder\xe1 vir a ser uma hip\xf3tese, at\xe9 porque, no terreno, a capacidade dos GAT
509
+ est\xe1 cada vez mais enfraquecida.',
510
+ 'Alguns at\xe9 j\xe1 desapareceram, como o de Castro Verde, e outros t\xeam vindo a perder quadros.']
511
+
512
+ NLTK's data collection includes a trained model for Portuguese sentence
513
+ segmentation, which can be loaded as follows. It is faster to load a trained model than
514
+ to retrain it.
515
+
516
+ >>> stok = nltk.data.load('tokenizers/punkt/portuguese.pickle')
517
+
518
+ Stemming
519
+ --------
520
+
521
+ NLTK includes the RSLP Portuguese stemmer. Here we use it to stem some Portuguese text:
522
+
523
+ >>> stemmer = nltk.stem.RSLPStemmer()
524
+ >>> stemmer.stem("copiar")
525
+ 'copi'
526
+ >>> stemmer.stem("paisagem")
527
+ 'pais'
528
+
529
+
530
+ Stopwords
531
+ ---------
532
+
533
+ NLTK includes Portuguese stopwords:
534
+
535
+ >>> stopwords = nltk.corpus.stopwords.words('portuguese')
536
+ >>> stopwords[:10]
537
+ ['a', 'ao', 'aos', 'aquela', 'aquelas', 'aquele', 'aqueles', 'aquilo', 'as', 'at\xe9']
538
+
539
+ Now we can use these to filter text. Let's find the most frequent words (other than stopwords)
540
+ and print them in descending order of frequency:
541
+
542
+ >>> fd = nltk.FreqDist(w.lower() for w in floresta.words() if w not in stopwords)
543
+ >>> for word in list(fd.keys())[:20]:
544
+ ... print(word, fd[word])
545
+ , 13444
546
+ . 7725
547
+ « 2369
548
+ » 2310
549
+ é 1305
550
+ o 1086
551
+ } 1047
552
+ { 1044
553
+ a 897
554
+ ; 633
555
+ em 516
556
+ ser 466
557
+ sobre 349
558
+ os 313
559
+ anos 301
560
+ ontem 292
561
+ ainda 279
562
+ segundo 256
563
+ ter 249
564
+ dois 231
565
+