natural 0.1.28 → 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 (117) hide show
  1. package/.editorconfig +7 -0
  2. package/.npmignore +4 -11
  3. package/README.md +190 -50
  4. package/bayes_classifier.json +1 -0
  5. package/lib/natural/analyzers/sentence_analyzer.js +8 -5
  6. package/lib/natural/brill_pos_tagger/data/Dutch/README.txt +2 -0
  7. package/lib/natural/brill_pos_tagger/data/Dutch/brill_CONTEXTRULES.jg +285 -0
  8. package/lib/natural/brill_pos_tagger/data/Dutch/brill_LEXICON.jg +11699 -0
  9. package/lib/natural/brill_pos_tagger/data/English/README.txt +8 -0
  10. package/lib/natural/brill_pos_tagger/data/English/lexicon_from_posjs.json +297827 -0
  11. package/lib/natural/brill_pos_tagger/data/English/tr_from_brill_paper.txt +10 -0
  12. package/lib/natural/brill_pos_tagger/data/English/tr_from_posjs.txt +18 -0
  13. package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js +136 -0
  14. package/lib/natural/brill_pos_tagger/lib/Predicate.js +410 -0
  15. package/lib/natural/brill_pos_tagger/lib/TF_Parser.js +717 -0
  16. package/lib/natural/brill_pos_tagger/lib/TF_Parser.pegjs +55 -0
  17. package/lib/natural/brill_pos_tagger/lib/TransformationRule.js +49 -0
  18. package/lib/natural/classifiers/bayes_classifier.js +6 -5
  19. package/lib/natural/classifiers/classifier.js +3 -2
  20. package/lib/natural/classifiers/logistic_regression_classifier.js +9 -5
  21. package/lib/natural/distance/dice_coefficient.js +22 -12
  22. package/lib/natural/distance/jaro-winkler_distance.js +13 -8
  23. package/lib/natural/index.js +6 -0
  24. package/lib/natural/inflectors/present_verb_inflector.js +1 -0
  25. package/lib/natural/ngrams/ngrams.js +6 -0
  26. package/lib/natural/normalizers/normalizer_ja.js +26 -8
  27. package/lib/natural/phonetics/double_metaphone.js +9 -4
  28. package/lib/natural/phonetics/metaphone.js +4 -0
  29. package/lib/natural/phonetics/soundex.js +11 -7
  30. package/lib/natural/spellcheck/spellcheck.js +80 -0
  31. package/lib/natural/stemmers/porter_stemmer.js +90 -62
  32. package/lib/natural/stemmers/porter_stemmer_fr.js +8 -3
  33. package/lib/natural/stemmers/porter_stemmer_pt.js +302 -0
  34. package/lib/natural/stemmers/stemmer.js +31 -6
  35. package/lib/natural/stemmers/stemmer_pt.js +65 -0
  36. package/lib/natural/stemmers/token.js +163 -0
  37. package/lib/natural/tfidf/tfidf.js +49 -18
  38. package/lib/natural/tokenizers/regexp_tokenizer.js +3 -3
  39. package/{examples/inflection/noun.js → lib/natural/tokenizers/sentence_tokenizer.js} +14 -10
  40. package/lib/natural/tokenizers/tokenizer_case.js +58 -0
  41. package/lib/natural/util/bag.js +1 -0
  42. package/lib/natural/util/stopwords_pt.js +136 -0
  43. package/lib/natural/wordnet/wordnet.js +2 -2
  44. package/lib/natural/wordnet/wordnet_file.js +1 -1
  45. package/lr_classifier.json +1 -0
  46. package/package.json +7 -4
  47. package/package.json~ +66 -0
  48. package/benchmarks/index.js +0 -32
  49. package/benchmarks/metaphone.js +0 -27
  50. package/benchmarks/soundex.js +0 -27
  51. package/examples/classification/basic.js +0 -35
  52. package/examples/classification/recall.js +0 -28
  53. package/examples/classification/store.js +0 -37
  54. package/examples/inflection/count.js +0 -35
  55. package/examples/inflection/noun_attach.js +0 -33
  56. package/examples/phonetics/compare.js +0 -39
  57. package/examples/phonetics/sounds_like.js +0 -40
  58. package/examples/phonetics/tokenize_and_phoneticize.js +0 -54
  59. package/examples/stemming/stem_corpus.js +0 -29
  60. package/examples/stemming/stem_word.js +0 -26
  61. package/examples/tfidf/array_example.js +0 -34
  62. package/examples/tfidf/multiple_terms.js +0 -33
  63. package/examples/tfidf/tfidf_example.js +0 -44
  64. package/io_spec/test_data/tfidf/one +0 -1
  65. package/io_spec/test_data/tfidf/two +0 -1
  66. package/io_spec/tfidf_spec.js +0 -50
  67. package/io_spec/wordnet_spec.js +0 -81
  68. package/spec/aggressive_tokenizer_es_spec.js +0 -36
  69. package/spec/aggressive_tokenizer_fr_spec.js +0 -101
  70. package/spec/aggressive_tokenizer_nl_spec.js +0 -36
  71. package/spec/aggressive_tokenizer_pt_spec.js +0 -56
  72. package/spec/aggressive_tokenizer_spec.js +0 -56
  73. package/spec/bayes_classifier_spec.js +0 -173
  74. package/spec/classifier_spec.js +0 -91
  75. package/spec/count_inflector_fr_spec.js +0 -44
  76. package/spec/count_inflector_spec.js +0 -73
  77. package/spec/dice_coefficient_spec.js +0 -26
  78. package/spec/double_metaphone_spec.js +0 -743
  79. package/spec/jaro-winkler_spec.js +0 -53
  80. package/spec/lancaster_stemmer_spec.js +0 -73
  81. package/spec/levenshtein_spec.js +0 -66
  82. package/spec/logistic_regression_classifier_spec.js +0 -122
  83. package/spec/longest_path_tree_spec.js +0 -102
  84. package/spec/metaphone_spec.js +0 -247
  85. package/spec/ngram_spec.js +0 -130
  86. package/spec/ngram_zh_spec.js +0 -122
  87. package/spec/normalizer_ja_spec.js +0 -154
  88. package/spec/normalizer_no_spec.js +0 -111
  89. package/spec/normalizer_spec.js +0 -118
  90. package/spec/noun_inflector_fr_spec.js +0 -476
  91. package/spec/noun_inflector_ja_spec.js +0 -112
  92. package/spec/noun_inflector_spec.js +0 -270
  93. package/spec/porter_stemmer_fr_spec.js +0 -101
  94. package/spec/porter_stemmer_it_spec.js +0 -44
  95. package/spec/porter_stemmer_no_spec.js +0 -143
  96. package/spec/porter_stemmer_ru_spec.js +0 -63
  97. package/spec/porter_stemmer_spec.js +0 -137
  98. package/spec/present_verb_inflector_spec.js +0 -125
  99. package/spec/sentence_analyzer_spec.js +0 -29
  100. package/spec/shortest_path_tree_spec.js +0 -132
  101. package/spec/soundex_spec.js +0 -154
  102. package/spec/stemmer_ja_spec.js +0 -66
  103. package/spec/test_data/snowball_fr.txt +0 -20402
  104. package/spec/test_data/snowball_it.txt +0 -35482
  105. package/spec/test_data/snowball_no.txt +0 -20628
  106. package/spec/test_data/tfdif_testcorpus.txt +0 -7
  107. package/spec/test_data/tfidf_document1.txt +0 -1
  108. package/spec/test_data/tfidf_document2.txt +0 -1
  109. package/spec/test_data/tfidf_document3.txt +0 -1
  110. package/spec/test_data/tfidf_document4.txt +0 -1
  111. package/spec/test_data/tfidf_teststopwords.txt +0 -1
  112. package/spec/test_data/wordnet_mini.sql +0 -95
  113. package/spec/tfidf_spec.js +0 -198
  114. package/spec/tokenizer_ja_spec.js +0 -58
  115. package/spec/transliterator_ja_spec.js +0 -103
  116. package/spec/treebank_word_tokenizer_spec.js +0 -36
  117. package/spec/trie_spec.js +0 -206
@@ -0,0 +1,8 @@
1
+ The tranformation rules in tr_from_brill_paper.txt are from this article:
2
+ A simple rule-based part of speech tagger, Eric Brill, Published in: Proceeding ANLC '92 Proceedings of the third conference on Applied natural language processing, Pages 152-155. http://dl.acm.org/citation.cfm?id=974526
3
+
4
+ The lexicon in lexicon_from_posjs.json is from:
5
+ https://github.com/dariusk/pos-js
6
+
7
+ The transformation rules in tr_from_posj.txt are derived from Javascript code in:
8
+ BrillTransformationRules.js from https://github.com/dariusk/pos-js/