class InterestAnalyzer:
def __init__(self):
self.feature_builder = FeatureBuilder()
def rebuild_features(self):
print 'Parsing Facebook...'
fbparser.parse({'in': TRAINING_DIRECTORIES['fb'], 'out': TRAINING_FILES['fb']})
print 'Parsing Twitter...'
tweetparser.parse({'in': TRAINING_DIRECTORIES['tweets'], 'out': TRAINING_FILES['tweets']})
print 'Parsing LinkedIn...'
linkedinparser.parse({'in': TRAINING_DIRECTORIES['linkedin'], 'out': TRAINING_FILES['linkedin']})
print 'Building features...'
# build features for training data
self.feature_builder.create_feature_vectors(TRAINING_FILES['linkedin'], TRAINING_FEATURE_FILES['linkedin'], 'linkedin')
self.feature_builder.create_feature_vectors(TRAINING_FILES['tweets'], TRAINING_FEATURE_FILES['tweets'], 'tweets')
self.feature_builder.create_feature_vectors(TRAINING_FILES['fb'], TRAINING_FEATURE_FILES['fb'], 'fb')
def retrain_classifier(self):
print 'Training classifier...'
self.classifier = Classifier()
def save_classifier(self):
pickle.dump(self.classifier, open(CLASSIFIER_FILE, 'wb'))
def load_classifier(self):
self.classifier = pickle.load(open(CLASSIFIER_FILE, 'rb'))
def classifier_predict(self):
print 'Parsing Facebook...'
fbparser.parse({'in': TESTING_DIRECTORIES['fb'], 'out': TESTING_FILES['fb']})
print 'Parsing Twitter...'
tweetparser.parse({'in': TESTING_DIRECTORIES['tweets'], 'out': TESTING_FILES['tweets']})
print 'Parsing LinkedIn...'
linkedinparser.parse({'in': TESTING_DIRECTORIES['linkedin'], 'out': TESTING_FILES['linkedin']})
print 'Building features...'
self.feature_builder.create_feature_vectors(TESTING_FILES['linkedin'], TESTING_FEATURE_FILES['linkedin'], 'linkedin')
self.feature_builder.create_feature_vectors(TESTING_FILES['tweets'], TESTING_FEATURE_FILES['tweets'], 'tweets')
self.feature_builder.create_feature_vectors(TESTING_FILES['fb'], TESTING_FEATURE_FILES['fb'], 'fb')
linkedin_testing_features = np.loadtxt(TESTING_FEATURE_FILES['linkedin'], delimiter=',')
tweets_testing_features = np.loadtxt(TESTING_FEATURE_FILES['tweets'], delimiter=',')
fb_testing_features = np.loadtxt(TESTING_FEATURE_FILES['fb'], delimiter=',')
print 'Predicting labels...'
print 'LinkedIn classifier:'
print self.classifier.predict_testing_data('linkedin', linkedin_testing_features, TESTING_LABELS_FILE, 'results_l.txt')
print 'Twitter classifier:'
print self.classifier.predict_testing_data('tweets', tweets_testing_features, TESTING_LABELS_FILE, 'results_t.txt')
tweets_result_labels = np.loadtxt('results_t.txt', delimiter=',')
linkedin_result_labels = np.loadtxt('results_l.txt', delimiter=',')
print 'Late fusion classifier:'
print self.classifier.predict_late_fusion_testing_data([tweets_result_labels, linkedin_result_labels], TESTING_LABELS_FILE, 'result.txt')
