def classifyTest(self,test, classifier, feature_extractor):
testClassifies = []
for doc,lbl in test:
tmpLbl = classifier.classify(feature_extractor(movie_reviews.words(fileids=[doc])))
x = (doc,tmpLbl)
testClassifies.append(x)
return testClassifies
def classifyTest(self, test, classifier, feature_extractor):
testClassifies = []
for doc, lbl in test:
tmpLbl = classifier.classify(
feature_extractor(movie_reviews.words(fileids=[doc])))
x = (doc, tmpLbl)
testClassifies.append(x)
return testClassifies
print(nb_classifier.classify(posfeat))
print(accuracy(nb_classifier, test_feats))
probs = nb_classifier.prob_classify(test_feats[0][0])
print(probs.samples())
print(probs.max())
print(probs.prob('pos'))
print(probs.prob('neg'))
print(nb_classifier.most_informative_features(n=5))
print("############################################################################")
print(nb_classifier.show_most_informative_features(n=5))
print("############################################################################")
nb_classifier = NaiveBayesClassifier.train(train_feats, estimator=LaplaceProbDist)
print("Accuracy: " + str(accuracy(nb_classifier, test_feats)))
# Accuracy: 0.76
label_probdist = DictionaryProbDist({'pos': 0.5, 'neg': 0.5})
true_probdist = DictionaryProbDist({True: 1})
feature_probdist = {('pos', 'yes'): true_probdist, ('neg', 'no'): true_probdist}
classifier = NaiveBayesClassifier(label_probdist, feature_probdist)
print(classifier.classify({'yes': True}))
print(classifier.classify({'no': True}))
def hasNegativeSent(text):
#take in raw text, not tokens
return nb_classifier.classify(word_features(text))
def test(self): testArr= self.matched[100:] random.shuffle(testArr) for item in testArr: classified = NaiveBayesClassifier.classify(self.model,item)
def batchClassify(self, model): for item in self.unmatched: classified = NaiveBayesClassifier.classify(model, item.featurize())
def classify(self, model, item): _name = self.convertItem(item) tokens = _name.getNameDes() classified = NaiveBayesClassifier.classify(model, _name.input_featurize(tokens)) return classified
def nameobj_classify(self, model, _name): tokens = _name.name + name.brand classified = NaiveBayesClassifier.classify(model, _name.input_featurize(tokens)) return classified
labeled=False)
# Build the test set
_test_X = analyzer.apply_features([
mark_negation(word_tokenize(unidecode(clean_text(instance))))
for instance in test_X
],
labeled=False)
print "Vader Classifier:"
print vader.polarity_scores(train_X[0])
print vader_polarity(train_X[0]), train_y[0] # 0 1
print vader_polarity(train_X[1]), train_y[1] # 0 0
print vader_polarity(train_X[2]), train_y[2] # 1 1
print vader_polarity(train_X[3]), train_y[3] # 0 1
print vader_polarity(train_X[4]), train_y[4] # 0 0
pred_y = [vader_polarity(text) for text in test_X]
print "Vader Accuracy:", accuracy_score(test_y, pred_y) # 0.6892
print "Vader Precision:", precision_score(test_y, pred_y, average='binary')
print "Vader Recall:", recall_score(test_y, pred_y, average='binary')
trainer = NaiveBayesClassifier.train
classifier = analyzer.train(trainer, zip(_train_X, train_y[:TRAINING_COUNT]))
score = analyzer.evaluate(zip(_test_X, test_y))
print score
print "NB Accuracy: ", score['Accuracy'] # 0.8064 for TRAINING_COUNT=5000
classifyed = NaiveBayesClassifier.classify(_test_X)
print classifyed
