natural 0.2.1 → 0.4.0

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 (106) hide show
  1. package/.npmignore +4 -11
  2. package/README.md +156 -41
  3. package/bayes_classifier.json +1 -0
  4. package/lib/natural/brill_pos_tagger/data/Dutch/README.txt +2 -0
  5. package/lib/natural/brill_pos_tagger/data/Dutch/brill_CONTEXTRULES.jg +285 -0
  6. package/lib/natural/brill_pos_tagger/data/Dutch/brill_LEXICON.jg +11699 -0
  7. package/lib/natural/brill_pos_tagger/data/English/README.txt +8 -0
  8. package/lib/natural/brill_pos_tagger/data/English/lexicon_from_posjs.json +297827 -0
  9. package/lib/natural/brill_pos_tagger/data/English/tr_from_brill_paper.txt +10 -0
  10. package/lib/natural/brill_pos_tagger/data/English/tr_from_posjs.txt +18 -0
  11. package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js +136 -0
  12. package/lib/natural/brill_pos_tagger/lib/Predicate.js +410 -0
  13. package/lib/natural/brill_pos_tagger/lib/TF_Parser.js +717 -0
  14. package/lib/natural/brill_pos_tagger/lib/TF_Parser.pegjs +55 -0
  15. package/lib/natural/brill_pos_tagger/lib/TransformationRule.js +49 -0
  16. package/lib/natural/classifiers/bayes_classifier.js +6 -5
  17. package/lib/natural/classifiers/classifier.js +3 -2
  18. package/lib/natural/classifiers/logistic_regression_classifier.js +9 -5
  19. package/lib/natural/distance/dice_coefficient.js +22 -12
  20. package/lib/natural/index.js +6 -0
  21. package/lib/natural/ngrams/ngrams.js +4 -0
  22. package/lib/natural/stemmers/stemmer.js +31 -6
  23. package/lib/natural/tokenizers/regexp_tokenizer.js +3 -3
  24. package/{examples/inflection/noun.js → lib/natural/tokenizers/sentence_tokenizer.js} +14 -10
  25. package/lib/natural/tokenizers/tokenizer_case.js +58 -0
  26. package/lib/natural/util/bag.js +1 -0
  27. package/lib/natural/wordnet/wordnet.js +2 -2
  28. package/lib/natural/wordnet/wordnet_file.js +1 -1
  29. package/lr_classifier.json +1 -0
  30. package/package.json +6 -3
  31. package/package.json~ +66 -0
  32. package/benchmarks/index.js +0 -32
  33. package/benchmarks/metaphone.js +0 -27
  34. package/benchmarks/soundex.js +0 -27
  35. package/examples/classification/basic.js +0 -35
  36. package/examples/classification/recall.js +0 -28
  37. package/examples/classification/store.js +0 -37
  38. package/examples/inflection/count.js +0 -35
  39. package/examples/inflection/noun_attach.js +0 -33
  40. package/examples/phonetics/compare.js +0 -39
  41. package/examples/phonetics/sounds_like.js +0 -40
  42. package/examples/phonetics/tokenize_and_phoneticize.js +0 -54
  43. package/examples/stemming/stem_corpus.js +0 -29
  44. package/examples/stemming/stem_word.js +0 -26
  45. package/examples/tfidf/array_example.js +0 -34
  46. package/examples/tfidf/multiple_terms.js +0 -33
  47. package/examples/tfidf/tfidf_example.js +0 -44
  48. package/io_spec/test_data/tfidf/one +0 -1
  49. package/io_spec/test_data/tfidf/two +0 -1
  50. package/io_spec/tfidf_spec.js +0 -50
  51. package/io_spec/wordnet_spec.js +0 -81
  52. package/spec/aggressive_tokenizer_es_spec.js +0 -36
  53. package/spec/aggressive_tokenizer_fr_spec.js +0 -101
  54. package/spec/aggressive_tokenizer_nl_spec.js +0 -36
  55. package/spec/aggressive_tokenizer_pt_spec.js +0 -56
  56. package/spec/aggressive_tokenizer_spec.js +0 -56
  57. package/spec/bayes_classifier_spec.js +0 -173
  58. package/spec/classifier_spec.js +0 -175
  59. package/spec/count_inflector_fr_spec.js +0 -44
  60. package/spec/count_inflector_spec.js +0 -73
  61. package/spec/dice_coefficient_spec.js +0 -26
  62. package/spec/double_metaphone_spec.js +0 -752
  63. package/spec/jaro-winkler_spec.js +0 -53
  64. package/spec/lancaster_stemmer_spec.js +0 -73
  65. package/spec/levenshtein_spec.js +0 -66
  66. package/spec/logistic_regression_classifier_spec.js +0 -122
  67. package/spec/longest_path_tree_spec.js +0 -102
  68. package/spec/metaphone_spec.js +0 -252
  69. package/spec/ngram_spec.js +0 -130
  70. package/spec/ngram_zh_spec.js +0 -122
  71. package/spec/normalizer_ja_spec.js +0 -160
  72. package/spec/normalizer_no_spec.js +0 -111
  73. package/spec/normalizer_spec.js +0 -140
  74. package/spec/noun_inflector_fr_spec.js +0 -476
  75. package/spec/noun_inflector_ja_spec.js +0 -112
  76. package/spec/noun_inflector_spec.js +0 -270
  77. package/spec/porter_stemmer_fr_spec.js +0 -101
  78. package/spec/porter_stemmer_it_spec.js +0 -44
  79. package/spec/porter_stemmer_no_spec.js +0 -143
  80. package/spec/porter_stemmer_pt_spec.js +0 -50
  81. package/spec/porter_stemmer_ru_spec.js +0 -63
  82. package/spec/porter_stemmer_spec.js +0 -182
  83. package/spec/present_verb_inflector_spec.js +0 -128
  84. package/spec/remove_diacritics_spec.js +0 -31
  85. package/spec/sentence_analyzer_spec.js +0 -277
  86. package/spec/shortest_path_tree_spec.js +0 -132
  87. package/spec/soundex_spec.js +0 -158
  88. package/spec/spellcheck_spec.js +0 -92
  89. package/spec/stemmer_ja_spec.js +0 -66
  90. package/spec/stemmer_token_spec.js +0 -161
  91. package/spec/test_data/snowball_fr.txt +0 -20402
  92. package/spec/test_data/snowball_it.txt +0 -35482
  93. package/spec/test_data/snowball_no.txt +0 -20628
  94. package/spec/test_data/snowball_pt.txt +0 -32016
  95. package/spec/test_data/tfdif_testcorpus.txt +0 -7
  96. package/spec/test_data/tfidf_document1.txt +0 -1
  97. package/spec/test_data/tfidf_document2.txt +0 -1
  98. package/spec/test_data/tfidf_document3.txt +0 -1
  99. package/spec/test_data/tfidf_document4.txt +0 -1
  100. package/spec/test_data/tfidf_teststopwords.txt +0 -1
  101. package/spec/test_data/wordnet_mini.sql +0 -95
  102. package/spec/tfidf_spec.js +0 -323
  103. package/spec/tokenizer_ja_spec.js +0 -58
  104. package/spec/transliterator_ja_spec.js +0 -103
  105. package/spec/treebank_word_tokenizer_spec.js +0 -36
  106. package/spec/trie_spec.js +0 -206

There are too many changes on this page to be displayed.


The amount of changes on this page would crash your brower.

You can still verify the content by downloading the package file manually.