def rebuild_features(self):
print 'Parsing tweets...'
tweetparser.parse_all_files(self.parser_options)
print 'Building features...'
# build features for training data
training_labels = read_labels(TRAINING)
training_tweets = pickle.load(open(TRAINING_TWEETS, 'rb'))
unigram_features = buildfeatures.build_unigram_feature_dict(training_tweets, training_labels)
training_data = buildfeatures.get_feature_vectors(training_tweets, unigram_features)
# save training data
np.savetxt(TRAINING_DATA_FILE, training_data, delimiter=',')
# build features for testing data
testing_tweets = pickle.load(open(TESTING_TWEETS, 'rb'))
testing_data = buildfeatures.get_feature_vectors(testing_tweets, unigram_features)
np.savetxt(TESTING_DATA_FILE, testing_data, delimiter=',')
# build features for development data
development_tweets = pickle.load(open(DEVELOPMENT_TWEETS, 'rb'))
development_data = buildfeatures.get_feature_vectors(development_tweets, unigram_features)
np.savetxt(DEVELOPMENT_DATA_FILE, development_data, delimiter=',')
# save unigram features processed
pickle.dump(unigram_features, open(UNIGRAM_FEATURES_FILE, 'wb'), -1)
def classify_custom_tweets(self, custom_filename):
if not os.path.exists(custom_filename):
print 'The file ' + custom_filename + ' does not exist.'
return
try:
print 'Parsing tweets...'
custom_tweets = []
def collect(tweet):
custom_tweets.append(tweet)
tweetparser._parse_tweets(custom_filename, collect)
labels = read_labels(custom_filename)
topics = read_topics(custom_filename)
print 'Building features...'
unigram_features = pickle.load(open(UNIGRAM_FEATURES_FILE, 'rb'))
data = buildfeatures.get_feature_vectors(custom_tweets, unigram_features)
print 'Predicting labels...'
labels = read_labels(custom_filename)
topics = read_topics(custom_filename)
print 'Results: ' + str(self.classifier.predict_testing_data(custom_tweets, data, topics, labels, RESULTS_FILE))
print 'See labels at: ' + RESULTS_FILE
except:
print 'Something went wrong. File may be in wrong format.'
