def get_optimal_polarity_classifier():
"""
Trains and returns the optimal polarity classifier.
"""
tweets = utils.get_pickles(3)
tweets, targets = utils.make_polarity_targets(tweets)
vect_options = {
'ngram_range': (1,1),
'max_df': 0.5
}
tfidf_options = {
'sublinear_tf': False,
'use_idf': True,
'smooth_idf': True,
}
clf = SVM(tweets, targets, vect_options, tfidf_options)
clf.set_feature_set('PC2', features.get_google_sentiment_values(3))
clf.train_on_feature_set()
return clf
def perform_grid_search_on_featureset_SA_and_PA():
datasetnr = 3
tweets = utils.get_pickles(datasetnr)
sentimentvalues = feat_utils.get_sentiment_values(datasetnr)
tweets = preprocessing.remove_link_classes(tweets)
tweets = preprocessing.lower_case(tweets)
tweets = preprocessing.remove_specialchars_round2(tweets)
train_tweets, train_targets, test_tweets, test_targets, train_sentimentvalues, test_sentimentvalues = utils.make_subjectivity_train_and_test_and_targets(
tweets, sentimentvalues
)
clf = SVM(train_tweets, train_targets, None)
clf.set_feature_set("SA", None)
clf.grid_search_on_text_features(file_postfix="subjectivity")
clf = NB(train_tweets, train_targets, None)
clf.set_feature_set("SA", None)
clf.grid_search_on_text_features(file_postfix="subjectivity")
clf = ME(train_tweets, train_targets, None)
clf.set_feature_set("SA", None)
clf.grid_search_on_text_features(file_postfix="subjectivity")
train_tweets, train_targets, test_tweets, test_targets, train_sentimentvalues, test_sentimentvalues = utils.make_polarity_train_and_test_and_targets(
tweets, sentimentvalues
)
clf = SVM(train_tweets, train_targets, None)
clf.set_feature_set("PA", None)
clf.grid_search_on_text_features(file_postfix="polarity")
clf = NB(train_tweets, train_targets, None)
clf.set_feature_set("PA", None)
clf.grid_search_on_text_features(file_postfix="polarity")
clf = ME(train_tweets, train_targets, None)
clf.set_feature_set("PA", None)
clf.grid_search_on_text_features(file_postfix="polarity")
