natural 0.2.1 → 0.4.0

package/spec/aggressive_tokenizer_es_spec.js

@@ -1,36 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this softwé and associated documentation files (the "Softwé"), to deal
-in the Softwé without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Softwé, and to permit persons to whom the Softwé is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Softwé.
-
-THE SOFTWé IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWé OR THE USE OR OTHER DEALINGS IN
-THE SOFTWé.
-*/
-
-var Tokenizer = require('../lib/natural/tokenizers/aggressive_tokenizer_es'),
-    tokenizer = new Tokenizer();
-
-describe('aggressive_tokenizer_es', function() {
-  it('should tokenize strings', function() {
-    expect(tokenizer.tokenize('hola yo me llamo eduardo y esudié ingeniería')).toEqual(['hola', 'yo', 'me', 'llamo', 'eduardo', 'y', 'esudié', 'ingeniería']);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect('hola yo me llamo eduardo y esudié ingeniería'.tokenize()).toEqual(['hola', 'yo', 'me', 'llamo', 'eduardo', 'y', 'esudié', 'ingeniería']);
-  });
-
-});

package/spec/aggressive_tokenizer_fr_spec.js

@@ -1,101 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this softwé and associated documentation files (the "Softwé"), to deal
-in the Softwé without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Softwé, and to permit persons to whom the Softwé is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Softwé.
-
-THE SOFTWé IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWé OR THE USE OR OTHER DEALINGS IN
-THE SOFTWé.
-*/
-
-var Tokenizer = require('../lib/natural/tokenizers/aggressive_tokenizer_fr'),
-    tokenizer = new Tokenizer();
-
-var text = "Affectueusement surnommé « Gabo » dans toute l'Amérique latine, le Colombien Gabriel Garcia Marquez, prix Nobel de littérature 1982, l'un des plus grands écrivains du XXe siècle, est mort À son domicile de Mexico jeudi 17 avril. Il était âgé de 87 ans. Son Œuvre a été traduite dans toutes les langues ou presque, et vendue à quelque 50 millions d'exemplaires.";
-
-var tokenized = [ 'Affectueusement',
-  'surnommé',
-  'Gabo',
-  'dans',
-  'toute',
-  'l',
-  'Amérique',
-  'latine',
-  'le',
-  'Colombien',
-  'Gabriel',
-  'Garcia',
-  'Marquez',
-  'prix',
-  'Nobel',
-  'de',
-  'littérature',
-  '1982',
-  'l',
-  'un',
-  'des',
-  'plus',
-  'grands',
-  'écrivains',
-  'du',
-  'XXe',
-  'siècle',
-  'est',
-  'mort',
-  'À',
-  'son',
-  'domicile',
-  'de',
-  'Mexico',
-  'jeudi',
-  '17',
-  'avril',
-  'Il',
-  'était',
-  'âgé',
-  'de',
-  '87',
-  'ans',
-  'Son',
-  'Œuvre',
-  'a',
-  'été',
-  'traduite',
-  'dans',
-  'toutes',
-  'les',
-  'langues',
-  'ou',
-  'presque',
-  'et',
-  'vendue',
-  'à',
-  'quelque',
-  '50',
-  'millions',
-  'd',
-  'exemplaires' ];
-
-describe('aggressive_tokenizer_fr', function() {
-  it('should tokenize strings', function() {
-    expect(tokenizer.tokenize(text)).toEqual(tokenized);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect(text.tokenize()).toEqual(tokenized);
-  });
-
-});

package/spec/aggressive_tokenizer_nl_spec.js

@@ -1,36 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel, Martijn de Boer
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this softwé and associated documentation files (the "Softwé"), to deal
-in the Softwé without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Softwé, and to permit persons to whom the Softwé is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Softwé.
-
-THE SOFTWé IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWé OR THE USE OR OTHER DEALINGS IN
-THE SOFTWé.
-*/
-
-var Tokenizer = require('../lib/natural/tokenizers/aggressive_tokenizer_nl'),
-    tokenizer = new Tokenizer();
-
-describe('aggressive_tokenizer_nl', function() {
-  it('should tokenize strings', function() {
-    expect(tokenizer.tokenize('\'s Morgens is het nog erg koud, vertelde de weerman over een van de radio\'s')).toEqual(['\'s','Morgens','is','het','nog','erg','koud','vertelde','de','weerman','over','een','van','de','radio\'s']);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect('\'s Morgens is het nog erg koud, vertelde de weerman over een van de radio\'s'.tokenize()).toEqual(['\'s','Morgens','is','het','nog','erg','koud','vertelde','de','weerman','over','een','van','de','radio\'s']);
-  });
-
-});

package/spec/aggressive_tokenizer_pt_spec.js

@@ -1,56 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this softwé and associated documentation files (the "Softwé"), to deal
-in the Softwé without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Softwé, and to permit persons to whom the Softwé is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Softwé.
-
-THE SOFTWé IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWé OR THE USE OR OTHER DEALINGS IN
-THE SOFTWé.
-*/
-
-var Tokenizer = require('../lib/natural/tokenizers/aggressive_tokenizer_pt'),
-    tokenizer = new Tokenizer();
-
-describe('aggressive_tokenizer_pt', function() {
-  it('should tokenize strings', function() {
-    expect(tokenizer.tokenize('isso é coração')).toEqual(['isso', 'é', 'coração']);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect('isso é coração'.tokenize()).toEqual(['isso', 'é', 'coração']);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect('isso é coração'.tokenize()).toEqual(['isso', 'é', 'coração']);
-  });
-
-  it('should swollow punctuation', function() {
-    expect(tokenizer.tokenize('isso é coração, no')).toEqual(['isso', 'é', 'coração', 'no']);
-  });
-
-  it('should swollow final punctuation', function() {
-    expect(tokenizer.tokenize('isso é coração, no?')).toEqual(['isso', 'é', 'coração', 'no']);
-  });
-
-  it('should swollow initial punctuation', function() {
-    expect(tokenizer.tokenize('.isso é coração, no')).toEqual(['isso', 'é', 'coração', 'no']);
-  });
-
-  it('should swollow duplicate punctuation', function() {
-    expect(tokenizer.tokenize('eu vou... pause')).toEqual(['eu', 'vou', 'pause']);
-  });
-});

package/spec/aggressive_tokenizer_spec.js

@@ -1,56 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
-*/
-
-var Tokenizer = require('../lib/natural/tokenizers/aggressive_tokenizer'),
-    tokenizer = new Tokenizer();
-
-describe('aggressive_tokenizer', function() {
-  it('should tokenize strings', function() {
-    expect(tokenizer.tokenize('these are things')).toEqual(['these', 'are', 'things']);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect('these are things'.tokenize()).toEqual(['these', 'are', 'things']);
-  });
-
-  it('should tokenize strings via attached string method', function() {
-    tokenizer.attach();
-    expect('these are things'.tokenize()).toEqual(['these', 'are', 'things']);
-  });
-
-  it('should swollow punctuation', function() {
-    expect(tokenizer.tokenize('these are things, no')).toEqual(['these', 'are', 'things', 'no']);
-  });
-
-  it('should swollow final punctuation', function() {
-    expect(tokenizer.tokenize('these are things, no?')).toEqual(['these', 'are', 'things', 'no']);
-  });
-
-  it('should swollow initial punctuation', function() {
-    expect(tokenizer.tokenize('.these are things, no')).toEqual(['these', 'are', 'things', 'no']);
-  });
-
-  it('should swollow duplicate punctuation', function() {
-    expect(tokenizer.tokenize('i shal... pause')).toEqual(['i', 'shal', 'pause']);
-  });  
-});

package/spec/bayes_classifier_spec.js

@@ -1,173 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
-*/
-
-var natural = require('../lib/natural');
-
-describe('bayes classifier', function() {
-    describe('classifier', function() {
-        it('should classify with arrays', function() {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument(['fix', 'box'], 'computing');
-            classifier.addDocument(['write', 'code'], 'computing');
-            classifier.addDocument(['script', 'code'], 'computing');
-            classifier.addDocument(['write', 'book'], 'literature');
-            classifier.addDocument(['read', 'book'], 'literature');
-            classifier.addDocument(['study', 'book'], 'literature');
-
-            classifier.train();
-            
-            expect(classifier.classify(['bug', 'code'])).toBe('computing');
-            expect(classifier.classify(['read', 'thing'])).toBe('literature');
-        });
-
-        it('should provide all classification scores', function() {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument(['fix', 'box'], 'computing');
-            classifier.addDocument(['write', 'code'], 'computing');
-            classifier.addDocument(['script', 'code'], 'computing');
-            classifier.addDocument(['write', 'book'], 'literature');
-            classifier.addDocument(['read', 'book'], 'literature');
-            classifier.addDocument(['study', 'book'], 'literature');
-
-            classifier.train();
-            
-	    expect(classifier.getClassifications('i write code')[0].label).toBe('computing');
-	    expect(classifier.getClassifications('i write code')[1].label).toBe('literature');
-        });
-
-        it('should classify with strings', function() {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument('i fixed the box', 'computing');
-            classifier.addDocument('i write code', 'computing');
-            classifier.addDocument('nasty script code', 'computing');
-            classifier.addDocument('write a book', 'literature');
-            classifier.addDocument('read a book', 'literature');
-            classifier.addDocument('study the books', 'literature');
-
-            classifier.train();
-            
-            expect(classifier.classify('a bug in the code')).toBe('computing');
-            expect(classifier.classify('read all the books')).toBe('literature');
-        });
-
-        it('should classify and re-classify after document-removal', function() {
-            var classifier = new natural.BayesClassifier()
-              , arr
-              , item
-              , classifications = {};
-
-            // Add some good/bad docs and train
-            classifier.addDocument('foo bar baz', 'good');
-            classifier.addDocument('qux zooby', 'bad');
-            classifier.addDocument('asdf qwer', 'bad');
-            classifier.train();
-
-            expect(classifier.classify('foo')).toBe('good');
-            expect(classifier.classify('qux')).toBe('bad');
-
-            // Remove one of the bad docs, retrain
-            classifier.removeDocument('qux zooby', 'bad');
-            classifier.retrain();
-
-            // Simple `classify` will still return a single result, even if
-            // ratio for each side is equal -- have to compare actual values in
-            // the classifications, should be equal since qux is unclassified
-            arr = classifier.getClassifications('qux');
-            for (var i = 0, ii = arr.length; i < ii; i++) {
-              item = arr[i];
-              classifications[item.label] = item.value;
-            }
-            expect(classifications.good).toEqual(classifications.bad);
-
-            // Re-classify as good, retrain
-            classifier.addDocument('qux zooby', 'good');
-            classifier.retrain();
-
-            // Should now be good, original docs should be unaffected
-            expect(classifier.classify('foo')).toBe('good');
-            expect(classifier.classify('qux')).toBe('good');
-        });
-
-        it('should serialize and deserialize a working classifier', function() {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument('i fixed the box', 'computing');
-            classifier.addDocument('i write code', 'computing');
-            classifier.addDocument('nasty script code', 'computing');
-            classifier.addDocument('write a book', 'literature');
-            classifier.addDocument('read a book', 'literature');
-            classifier.addDocument('study the books', 'literature');
-           
-	    var obj = JSON.stringify(classifier);
-	    var newClassifier = natural.BayesClassifier.restore(JSON.parse(obj));
-
-            newClassifier.addDocument('kick a ball', 'sports');
-            newClassifier.addDocument('hit some balls', 'sports');
-            newClassifier.addDocument('kick and punch', 'sports');
-
-            newClassifier.train();
-
-            expect(newClassifier.classify('a bug in the code')).toBe('computing');
-            expect(newClassifier.classify('read all the books')).toBe('literature');
-            expect(newClassifier.classify('kick butt')).toBe('sports');
-        });
-
-	it('should save and load a working classifier', function() {
-            var classifier = new natural.BayesClassifier();
-	    classifier.addDocument('i fixed the box', 'computing');
-	    classifier.addDocument('i write code', 'computing');
-	    classifier.addDocument('nasty script code', 'computing');
-	    classifier.addDocument('write a book', 'literature');
-	    classifier.addDocument('read a book', 'literature');
-	    classifier.addDocument('study the books', 'literature');
-
-	    classifier.train();  
-      
-            classifier.save('bayes_classifier.json', function(err) {
-		natural.BayesClassifier.load('bayes_classifier.json', null,
-		  function(err, newClassifier){
-		      newClassifier.addDocument('kick a ball', 'sports');
-		      newClassifier.addDocument('hit some balls', 'sports');
-		      newClassifier.addDocument('kick and punch', 'sports');
-						      
-		      newClassifier.train();
-
-		      expect(newClassifier.classify('a bug in the code')).toBe('computing');
-		      expect(newClassifier.classify('read all the books')).toBe('literature');
-		      expect(newClassifier.classify('kick butt')).toBe('sports');
-		      asyncSpecDone();
-		  });
-            });
-	});
-
-
-        it('should accept an optional smoothing parameter for the Bayesian estimates', function() {
-            var defaultClassifier = new natural.BayesClassifier();
-            var PorterStemmer = require('../lib/natural/stemmers/porter_stemmer');
-            var newClassifier1 = new natural.BayesClassifier(PorterStemmer);
-            var newClassifier2 = new natural.BayesClassifier(PorterStemmer, 0.1);
-
-            expect(defaultClassifier.classifier.smoothing).toBe(1.0);
-            expect(newClassifier1.classifier.smoothing).toBe(1.0);
-            expect(newClassifier2.classifier.smoothing).toBe(0.1);
-        });
-    });
-});

package/spec/classifier_spec.js

@@ -1,175 +0,0 @@
-/*
-Copyright (c) 2011, Chris Umbel
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
-*/
-
-var natural = require('lib/natural');
-var baseClassifier = require('lib/natural/classifiers/classifier.js');
-var fs = require('fs');
-
-describe('classifier', function () {
-
-    describe('addDocument', function () {
-
-        it('should ignore an empty document', function () {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument('', 'philosophy');
-            expect(classifier.docs.length).toBe(0);
-        });
-    });
-
-    describe('events emitters', function () {
-
-        it('should be emitted when a document is classified', function () {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument('i fixed the box', 'computing');
-            classifier.addDocument('i write code', 'computing');
-            classifier.addDocument('nasty script code', 'computing');
-            classifier.addDocument('write a book', 'literature');
-            classifier.addDocument('read a book', 'literature');
-            classifier.addDocument('study the books', 'literature');
-
-            classifier.train();
-
-            var pushedEvents = [];
-
-            function eventRegister(obj) {
-                pushedEvents.push(obj);
-            };
-
-            function assertEventResults() {
-                teardown();
-                expect(pushedEvents[0].index).toBe(0);
-                expect(pushedEvents[0].total).toBe(6);
-                expect(pushedEvents.length).toBe(6);
-            }
-
-            function teardown() {
-                classifier.events.removeListener('trainedWithDocument', eventRegister);
-                classifier.events.removeListener('doneTraining', assertEventResults);
-            }
-
-            classifier.events.on('trainedWithDocument', eventRegister);
-            classifier.events.on('doneTraining', assertEventResults);
-        });
-
-        it('should emit events only on an instance of Classifier', function () {
-            var classifier = new natural.BayesClassifier();
-            classifier.addDocument('i fixed the box', 'computing');
-            classifier.addDocument('i write code', 'computing');
-            classifier.addDocument('write a book', 'literature');
-            classifier.addDocument('study the books', 'literature');
-
-            var pushedEvents = [];
-
-            function eventRegister(obj) {
-                pushedEvents.push(obj);
-            };
-
-            function assertEventResults() {
-                teardown();
-                expect(pushedEvents.length).toBe(0);
-            }
-
-            function teardown() {
-                classifier.events.removeListener('trainedWithDocument', eventRegister);
-                classifier.events.removeListener('doneTraining', assertEventResults);
-            }
-
-            var classifier2 = new natural.BayesClassifier();
-            classifier2.events.on('trainedWithDocument', eventRegister);
-            classifier.events.on('doneTraining', assertEventResults);
-            classifier.train();
-        });
-
-    });
-
-    describe('removeDocument', function () {
-
-        var classifier;
-        beforeEach(function () {
-            classifier = new natural.BayesClassifier();
-            classifier.addDocument('i fixed the box', 'computing');
-            classifier.addDocument('i write code', 'computing');
-            classifier.addDocument('write a book', 'literature');
-            classifier.addDocument('study the books', 'literature');
-        });
-
-        it('should do nothing if text is not a string', function () {
-            expect(classifier.docs.length).toBe(4);
-            classifier.removeDocument(['write a book'], 'literature');
-            classifier.removeDocument(['study the books'], 'literature');
-            expect(classifier.docs.length).toBe(4);
-        });
-
-        it('should do nothing if text is not a match', function () {
-            expect(classifier.docs.length).toBe(4);
-            classifier.removeDocument('something else', 'literature');
-            classifier.removeDocument('another thing', 'literature');
-            expect(classifier.docs.length).toBe(4);
-        });
-    });
-
-    describe('save', function () {
-
-        var tmpFilename = '/spec/test_data/deleteMe';
-        var nonExistentFilename = '/nonExistentDir/deleteMe';
-        var classifier;
-
-        beforeEach(function () {
-            classifier = new natural.BayesClassifier();
-            classifier.addDocument('I went to see the doctor of', 'philosophy');
-        });
-
-        afterEach(function () {
-            if (fs.existsSync(tmpFilename)) {
-                fs.unlinkSync(tmpFilename);
-                fs.unlinkSync(nonExistentFilename);
-            }
-        });
-
-        it('does nothing if called without a callback', function () {
-            classifier.save(tmpFilename);
-            expect(fs.existsSync(tmpFilename)).toBe(false);
-        });
-
-        it('fails if writing to a file fails', function () {
-            classifier.save(nonExistentFilename, function (err) {
-                expect(err).toBe.ok;
-                expect(fs.existsSync(tmpFilename)).toBe(false);
-            });
-        });
-    });
-
-    describe('load', function () {
-
-        it('does nothing if called without a callback', function () {
-            result = baseClassifier.load('/spec/test_data/tfidf_document1.txt');
-            expect(result).not.toBe.ok;
-        });
-
-        it('does nothing if called without a callback', function () {
-            result = baseClassifier.load('/nonexistentFilename', function (err, newClassifier){
-                expect(err).toBe.ok;
-                expect(newClassifier).not.toBe.ok;
-            });
-        });
-    });
-});