def test_init_no_training(self):
classifier = MultinomialNB()
assert classifier.vocabulary == set()
assert classifier.labels == set()
classifier.train(*self.training_docs)
self.test_labels()
self.test_vocabulary()
def setup(self):
self.training_docs = [('Chinese Bejing Chinese', 'yes'),
('Chinese Chinese Shanghai', 'yes'),
('Chinese Macao', 'yes'),
('Tokyo Japan Chinese', 'no')]
self.training_docs = [(x.split(), y) for x, y in self.training_docs]
self.classifier = MultinomialNB(*self.training_docs)
self.make_snapshot()
def test_top_features(self):
docs = [(['happy', 'joy', 'smile'], 'positive'),
(['happy', 'joy', 'frown'], 'positive'),
(['sad', 'frown', 'tired'], 'negative'),
(['sad', 'tired', 'bored'], 'negative')]
classifier = MultinomialNB()
classifier.top_features = 2
classifier.train(*docs)
result = classifier._most_common['positive'].store
assert result == {'happy': 2, 'joy': 2}
result = classifier._most_common['negative'].store
assert result == {'sad': 2, 'tired': 2}
first = classifier.prob_all(['happy', 'smile'])
second = classifier.prob_all(['happy', 'smile', 'smile'])
assert first == second, classifier._most_common
first = classifier.prob_all(['sad', 'tired'])['negative']
second = classifier.prob_all(['sad', 'tired', 'frown'])['negative']
assert first == second, classifier._most_common
def test_ngrams_multinomialnb(self):
# Integration test with Naive Bayes classifier.
classifier = MultinomialNB()
self.extractor.min_n, self.extractor.max_n = 1, 3
features = self.extractor.extract(self.document)
classifier.train([features, 'positive'])
def test_train_many_document(self):
documents = [(['one', 'document', 'already', 'tokenized'], 'label')
] * 5
classifier = MultinomialNB(*documents)
expected = set(['one', 'document', 'already', 'tokenized'])
assert classifier.vocabulary == expected
