class HierarchicalClassifier(Experiment):
"""Train a single classifier and return performance on a test set."""
def _setup(self):
self.subjective, self.polarity = MultinomialNB(), MultinomialNB()
# self.subjective.top, self.polarity.top = 100000, 100000
# subjective.prior = lambda x: 0.5
# polarity.prior = lambda x: 0.5
def _predict(self, features):
label, probability = self.subjective.classify(features)
if label == 'neutral':
return label, probability
else:
return self.polarity.classify(features)
def _train(self, features, label):
if label != 'neutral':
assert label in set(['positive', 'negative'])
self.polarity.train((features, label))
label = 'subjective'
assert label in set(['neutral', 'subjective'])
if sum(self.subjective._label_count[x] for x in self.subjective._label_count) < 8751:
self.subjective.train((features, label))
def pickle_dumps(self):
pickled = Pickled(self.extractor, (self.subjective, self.polarity))
return pickle.dumps(pickled, pickle.HIGHEST_PROTOCOL)
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()
class SingleClassifier(Experiment):
"""Train a single classifier and return performance on a test set."""
def _setup(self):
self.nb = MultinomialNB()
# self.nb.top = 100000
def _predict(self, features):
return self.nb.classify(features)
def _train(self, features, label):
self.nb.train((features, label))
def pickle_dumps(self):
pickled = Pickled(self.extractor, self.nb)
return pickle.dumps(pickled, pickle.HIGHEST_PROTOCOL)
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
class OldClassifier(Experiment):
def _setup(self):
import old_classify
def extract(x):
old_classify.filter_text(x)
old_classify.regularlize_text(x)
features = old_classify.extract_features(x)
return features
self.extractor.extract = extract
# tokens = old_classify.tokenizer.tokenize(x)
# tokens = old_classify.regularlize_tokens(tokens)
try:
import cPickle as pickle
except ImportError:
import pickle
# twitter-sentiment_classifier.1650000.pickle
# with open(r"R:\_Other\Twitter\TwitterCorpus\results_sentiment\unbalanced_1-gram_stopword\twitter-sentiment_classifier.5000.pickle", mode='rb') as f:
with open(r"R:\_Other\Twitter\TwitterCorpus\results_sentiment\unbalanced_1-gram_stopword\twitter-sentiment_classifier.1650000.pickle", mode='rb') as f:
self.classifier = pickle.load(f)
self.subjective = MultinomialNB()
def _predict(self, features):
label, probability = self.subjective.classify(features)
if label == 'neutral':
return label, probability
sentiment = self.classifier.prob_classify(features)
prob, neg, = sentiment.prob('pos'), sentiment.prob('neg')
if prob > neg:
return 'positive', prob
else:
return 'negative', neg
def _train_func(self, features, label):
if label != 'neutral':
label = 'subjective'
assert label in set(['neutral', 'subjective'])
self.subjective.train((features, label))
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"])