def test_names_nltk(self):
"""Classify names using NLTK features"""
train, dev, test = self.split_names_corpus()
classifier = MaxEnt()
classifier.labels = ['female', 'male']
classifier.vocab = self.get_names_vocab(train)
classifier.feature_vectors(train + dev + test)
classifier.train(train, dev)
acc = accuracy(classifier, test)
self.assertGreater(acc, 0.70)
def test_reviews_bag(self):
"""Classify sentiment using bag-of-words"""
train, dev, test = self.split_review_corpus(BagOfWords)
classifier = MaxEnt()
classifier.labels = ['positive', 'negative', 'neutral']
classifier.vocab = self.get_review_vocab(train)
print('...creating sparse feature vectors...')
classifier.feature_vectors(train + dev + test)
print('...training...')
classifier.train(train, dev)
self.assertGreater(accuracy(classifier, test), 0.55)