out_f.write(','.join(feature_builder.feature_names) + '\n')
for a in articles:
features = feature_builder.get_article_features(a)
save_features(features, a.source, out_f)
def print_data(articles, feature_builder):
print(','.join(feature_builder.feature_names))
for a in articles:
features = feature_builder.get_article_features(a)
print_features(features, a.source)
if __name__ == '__main__':
dr = DataReader(sys.argv[1:])
articles = dr._make_data()
articles.normalize()
sent_feature_builder = SentimentFeatureBuilder()
testing, training = articles.make_sets()
# Print the features to STDOUT to be used as training data?
# save_data(training, sent_feature_builder, "training.txt")
# save_data(testing, sent_feature_builder, "testing.txt")
# Try to use a linear SVC to fit?
model = svm.LinearSVC()
df_training = pd.read_csv("training.txt")
df_testing = pd.read_csv("testing.txt")
training_data = df_training.loc[:, df_training.columns != 'label']
training_label = df_training['label']
