npm - natural - Versions diffs - 0.5.4 → 0.6.1 - Mend

natural 0.5.4 → 0.6.1

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 (82) hide show

package/.dockerignore +2 -0
package/.npmignore +1 -0
package/.travis.yml +1 -1
package/README.md +412 -89
package/bayes_classifier.json +1 -1
package/classifier.json +418 -0
package/data/kata-dasar.txt +29933 -0
package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js +8 -9
package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tester.js +5 -5
package/lib/natural/brill_pos_tagger/lib/Brill_POS_Trainer.js +10 -6
package/lib/natural/brill_pos_tagger/lib/Corpus.js +21 -16
package/lib/natural/brill_pos_tagger/lib/Lexicon.js +22 -13
package/lib/natural/brill_pos_tagger/lib/Predicate.js +2 -2
package/lib/natural/brill_pos_tagger/lib/RuleTemplate.js +2 -2
package/lib/natural/brill_pos_tagger/lib/RuleTemplates.js +132 -146
package/lib/natural/brill_pos_tagger/lib/Sentence.js +41 -0
package/lib/natural/brill_pos_tagger/lib/TF_Parser.js +83 -76
package/lib/natural/brill_pos_tagger/lib/TF_Parser.pegjs +19 -4
package/lib/natural/brill_pos_tagger/lib/TransformationRule.js +10 -11
package/lib/natural/classifiers/classifier.js +15 -8
package/lib/natural/classifiers/maxent/Classifier.js +125 -0
package/lib/natural/classifiers/maxent/Context.js +33 -0
package/lib/natural/classifiers/maxent/Distribution.js +145 -0
package/lib/natural/classifiers/maxent/Element.js +34 -0
package/lib/natural/classifiers/maxent/Feature.js +88 -0
package/lib/natural/classifiers/maxent/FeatureSet.js +67 -0
package/lib/natural/classifiers/maxent/GISScaler.js +148 -0
package/lib/natural/classifiers/maxent/POS/ME_Corpus.js +56 -0
package/lib/natural/classifiers/maxent/POS/ME_Sentence.js +73 -0
package/lib/natural/classifiers/maxent/POS/POS_Element.js +172 -0
package/lib/natural/classifiers/maxent/Sample.js +141 -0
package/lib/natural/classifiers/maxent/SimpleExample/SE_Element.js +49 -0
package/lib/natural/distance/hamming_distance.js +52 -0
package/lib/natural/distance/jaro-winkler_distance.js +16 -6
package/lib/natural/distance/levenshtein_distance.js +164 -11
package/lib/natural/index.js +26 -5
package/lib/natural/inflectors/noun_inflector.js +15 -13
package/lib/natural/ngrams/ngrams.js +83 -25
package/lib/natural/normalizers/normalizer_sv.js +41 -0
package/lib/natural/sentiment/Basque/senticon_eu.json +21557 -0
package/lib/natural/sentiment/Catalan/senticon_ca.json +36352 -0
package/lib/natural/sentiment/Dutch/negations_du.json +3 -0
package/lib/natural/sentiment/Dutch/pattern-sentiment-nl.json +39650 -0
package/lib/natural/sentiment/English/negations_en.json +3 -0
package/lib/natural/sentiment/English/pattern-sentiment-en.json +16024 -0
package/lib/natural/sentiment/English/senticon_en.json +124197 -0
package/lib/natural/sentiment/French/pattern-sentiment-fr.json +40906 -0
package/lib/natural/sentiment/Galician/senticon_gl.json +24427 -0
package/lib/natural/sentiment/Italian/pattern-sentiment-it.json +24522 -0
package/lib/natural/sentiment/SentimentAnalyzer.js +116 -0
package/lib/natural/sentiment/Spanish/afinnShortSortedSpanish.json +1655 -0
package/lib/natural/sentiment/Spanish/negations_es.json +3 -0
package/lib/natural/sentiment/Spanish/senticon_es.json +56722 -0
package/lib/natural/sentiment/tools/README.md +31 -0
package/lib/natural/sentiment/tools/XmlParser4PatternData.js +31 -0
package/lib/natural/sentiment/tools/sentimentXmlParser.js +30 -0
package/lib/natural/stemmers/indonesian/base_stemmer_id.js +86 -0
package/lib/natural/stemmers/indonesian/prefix_rules.js +1027 -0
package/lib/natural/stemmers/indonesian/removal.js +49 -0
package/lib/natural/stemmers/indonesian/stemmer_id.js +307 -0
package/lib/natural/stemmers/indonesian/suffix_rules.js +75 -0
package/lib/natural/stemmers/porter_stemmer_es.js +265 -199
package/lib/natural/stemmers/porter_stemmer_fr.js +1 -1
package/lib/natural/stemmers/porter_stemmer_nl.js +362 -0
package/lib/natural/stemmers/porter_stemmer_sv.js +99 -0
package/lib/natural/stemmers/stemmer_es.js +18 -12
package/lib/natural/stemmers/stemmer_nl.js +64 -0
package/lib/natural/stemmers/stemmer_sv.js +61 -0
package/lib/natural/tfidf/tfidf.js +27 -4
package/lib/natural/tokenizers/aggressive_tokenizer_id.js +44 -0
package/lib/natural/tokenizers/aggressive_tokenizer_sv.js +40 -0
package/lib/natural/tokenizers/aggressive_tokenizer_vi.js +37 -0
package/lib/natural/tokenizers/orthography_matchers.js +33 -0
package/lib/natural/tokenizers/regexp_tokenizer.js +23 -3
package/lib/natural/tokenizers/sentence_tokenizer.js +1 -1
package/lib/natural/util/stopwords_id.js +119 -0
package/lib/natural/util/stopwords_no.js +1 -1
package/lib/natural/util/stopwords_sv.js +70 -0
package/lib/natural/wordnet/wordnet_file.js +7 -1
package/lr_classifier.json +1 -1
package/package-lock.json +378 -0
package/package.json +29 -21

package/bayes_classifier.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"classifier":{"classFeatures":{"computing":{"0":2,"1":2,"2":2,"3":3,"4":2,"5":2},"literature":{"2":2,"6":4,"7":2,"8":2}},"classTotals":{"computing":4,"literature":4},"totalExamples":7,"smoothing":1},"docs":[{"label":"computing","text":["fix","box"]},{"label":"computing","text":["write","code"]},{"label":"computing","text":["nasti","script","code"]},{"label":"literature","text":["write","book"]},{"label":"literature","text":["read","book"]},{"label":"literature","text":["studi","book"]}],"features":{"fix":1,"box":1,"write":2,"code":2,"nasti":1,"script":1,"book":3,"read":1,"studi":1},"stemmer":{},"lastAdded":6,"events":{"~~domain":null,"~~_events":{},"_eventsCount":0}}
1	+ {"classifier":{"classFeatures":{"computing":{"0":2,"1":2,"2":2,"3":3,"4":2,"5":2},"literature":{"2":2,"6":4,"7":2,"8":2}},"classTotals":{"computing":4,"literature":4},"totalExamples":7,"smoothing":1},"docs":[{"label":"computing","text":["fix","box"]},{"label":"computing","text":["write","code"]},{"label":"computing","text":["nasti","script","code"]},{"label":"literature","text":["write","book"]},{"label":"literature","text":["read","book"]},{"label":"literature","text":["studi","book"]}],"features":{"fix":1,"box":1,"write":2,"code":2,"nasti":1,"script":1,"book":3,"read":1,"studi":1},"stemmer":{},"lastAdded":6,"events":{"_events":{},"_eventsCount":0}}

package/classifier.json ADDED Viewed

@@ -0,0 +1,418 @@
+{
+  "features": {
+    "features": [
+      {
+        "name": "isZero",
+        "parameters": [
+          "0"
+        ],
+        "parametersKey": "0",
+        "observedExpect": 0.3
+      },
+      {
+        "name": "isOne",
+        "parameters": [
+          "1"
+        ],
+        "parametersKey": "1",
+        "observedExpect": 0.3
+      },
+      {
+        "name": "Correction feature",
+        "parameters": [],
+        "parametersKey": "",
+        "observedExpect": 0.4
+      }
+    ],
+    "map": {
+      "isZero | 0": true,
+      "isOne | 1": true,
+      "Correction feature | ": true
+    }
+  },
+  "sample": {
+    "frequencyOfContext": {
+      "\"0\"": 6,
+      "\"1\"": 4
+    },
+    "frequency": {
+      "x\"0\"": 3,
+      "y\"0\"": 3,
+      "x\"1\"": 1,
+      "y\"1\"": 3
+    },
+    "classes": [
+      "x",
+      "y"
+    ],
+    "elements": [
+      {
+        "a": "x",
+        "b": {
+          "data": "0",
+          "key": "\"0\""
+        },
+        "key": "x\"0\""
+      },
+      {
+        "a": "x",
+        "b": {
+          "data": "0",
+          "key": "\"0\""
+        },
+        "key": "x\"0\""
+      },
+      {
+        "a": "x",
+        "b": {
+          "data": "0",
+          "key": "\"0\""
+        },
+        "key": "x\"0\""
+      },
+      {
+        "a": "y",
+        "b": {
+          "data": "0",
+          "key": "\"0\""
+        },
+        "key": "y\"0\""
+      },
+      {
+        "a": "y",
+        "b": {
+          "data": "0",
+          "key": "\"0\""
+        },
+        "key": "y\"0\""
+      },
+      {
+        "a": "y",
+        "b": {
+          "data": "0",
+          "key": "\"0\""
+        },
+        "key": "y\"0\""
+      },
+      {
+        "a": "x",
+        "b": {
+          "data": "1",
+          "key": "\"1\""
+        },
+        "key": "x\"1\""
+      },
+      {
+        "a": "y",
+        "b": {
+          "data": "1",
+          "key": "\"1\""
+        },
+        "key": "y\"1\""
+      },
+      {
+        "a": "y",
+        "b": {
+          "data": "1",
+          "key": "\"1\""
+        },
+        "key": "y\"1\""
+      },
+      {
+        "a": "y",
+        "b": {
+          "data": "1",
+          "key": "\"1\""
+        },
+        "key": "y\"1\""
+      }
+    ]
+  },
+  "scaler": {
+    "featureSet": {
+      "features": [
+        {
+          "name": "isZero",
+          "parameters": [
+            "0"
+          ],
+          "parametersKey": "0",
+          "observedExpect": 0.3
+        },
+        {
+          "name": "isOne",
+          "parameters": [
+            "1"
+          ],
+          "parametersKey": "1",
+          "observedExpect": 0.3
+        },
+        {
+          "name": "Correction feature",
+          "parameters": [],
+          "parametersKey": "",
+          "observedExpect": 0.4
+        }
+      ],
+      "map": {
+        "isZero | 0": true,
+        "isOne | 1": true,
+        "Correction feature | ": true
+      }
+    },
+    "sample": {
+      "frequencyOfContext": {
+        "\"0\"": 6,
+        "\"1\"": 4
+      },
+      "frequency": {
+        "x\"0\"": 3,
+        "y\"0\"": 3,
+        "x\"1\"": 1,
+        "y\"1\"": 3
+      },
+      "classes": [
+        "x",
+        "y"
+      ],
+      "elements": [
+        {
+          "a": "x",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "x\"0\""
+        },
+        {
+          "a": "x",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "x\"0\""
+        },
+        {
+          "a": "x",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "x\"0\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "y\"0\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "y\"0\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "y\"0\""
+        },
+        {
+          "a": "x",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "x\"1\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "y\"1\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "y\"1\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "y\"1\""
+        }
+      ]
+    },
+    "iteration": 3,
+    "improvement": 0.008269762368828815,
+    "C": 1,
+    "featureSums": {
+      "x\"0\"": 1,
+      "y\"0\"": 0,
+      "x\"1\"": 0,
+      "y\"1\"": 1
+    }
+  },
+  "p": {
+    "alpha": [
+      0.8442857142857142,
+      1.8851785714285711,
+      0.777505117061545
+    ],
+    "featureSet": {
+      "features": [
+        {
+          "name": "isZero",
+          "parameters": [
+            "0"
+          ],
+          "parametersKey": "0",
+          "observedExpect": 0.3
+        },
+        {
+          "name": "isOne",
+          "parameters": [
+            "1"
+          ],
+          "parametersKey": "1",
+          "observedExpect": 0.3
+        },
+        {
+          "name": "Correction feature",
+          "parameters": [],
+          "parametersKey": "",
+          "observedExpect": 0.4
+        }
+      ],
+      "map": {
+        "isZero | 0": true,
+        "isOne | 1": true,
+        "Correction feature | ": true
+      }
+    },
+    "sample": {
+      "frequencyOfContext": {
+        "\"0\"": 6,
+        "\"1\"": 4
+      },
+      "frequency": {
+        "x\"0\"": 3,
+        "y\"0\"": 3,
+        "x\"1\"": 1,
+        "y\"1\"": 3
+      },
+      "classes": [
+        "x",
+        "y"
+      ],
+      "elements": [
+        {
+          "a": "x",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "x\"0\""
+        },
+        {
+          "a": "x",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "x\"0\""
+        },
+        {
+          "a": "x",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "x\"0\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "y\"0\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "y\"0\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "0",
+            "key": "\"0\""
+          },
+          "key": "y\"0\""
+        },
+        {
+          "a": "x",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "x\"1\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "y\"1\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "y\"1\""
+        },
+        {
+          "a": "y",
+          "b": {
+            "data": "1",
+            "key": "\"1\""
+          },
+          "key": "y\"1\""
+        }
+      ]
+    },
+    "aPriorisBeforeNormalisation": {
+      "x\"0\"": 0.8442857142857142,
+      "y\"0\"": 0.777505117061545,
+      "x\"1\"": 0.777505117061545,
+      "y\"1\"": 1.8851785714285711
+    },
+    "aPrioriNormalisationConstant": 11.298413325389037,
+    "aPosterioriNormalisationConstants": {
+      "\"0\"": 1.6217908313472593,
+      "\"1\"": 2.662683688490116
+    }
+  }
+}