if __name__ == "__main__":
# Load trining data
training_encoded_data_path = "./Dataset/encoded_training_data_4362.json"
X_train, y_train = FeatureTransformer.load_encoded_data(training_encoded_data_path)
# Load test data
test_data_path = "./Dataset/valid_data_1091.json"
test_data = utils.load_data(test_data_path)
df = pd.DataFrame(test_data)
X_test = df.content.values
y_test = df.label.values
# Transform test data
ft = FeatureTransformer()
X_test = ft.fit_transform(X_test, y_train, vocab_path=VOCAB_PATH)
# Define models
mnb = MultinomialNB(alpha=0.004)
rf = RandomForestClassifier(
max_features=0.8,
n_estimators=20,
max_depth=80,
class_weight="balanced",
n_jobs=-1,
random_state=RANDOM_STATE)
etree = ExtraTreesClassifier(
n_estimators=50,
def __init__(self, scoring, vocab_path, cv=3):
self.cv = cv
self.scoring = scoring
self.models = {}
self.vocab_path = vocab_path
self.feature_transformer = FeatureTransformer()