import pandas as pd
from scipy.stats import ranksums
from cliffsDelta import cliffsDelta

def evaluate(feature: str):
    print(f'====={feature}=====')
    print(ranksums(ml_data[feature], no_ml_data[feature]))
    print(cliffsDelta(ml_data[feature], no_ml_data[feature]))

if __name__ == '__main__':
    data = pd.read_csv('commit_analysis.csv')
    ml_data = data[data['is_ml']]
    no_ml_data = data[~data['is_ml']]

    evaluate('file_entropy')
    evaluate('line_entropy')
    evaluate('n_comments')
    evaluate('words_mean')
    evaluate('day_to_fix')