import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

if __name__ == '__main__':
    data = pd.read_csv('commit_analysis.csv')

    data['type'] = data['is_ml'].apply(lambda x: 'ML' if x else 'No ML')

    ylim = data['file_entropy'].quantile(0.95)
    sns.catplot(x='type', y='file_entropy', kind='box', data=data) \
        .set(title='Entropia del cambiamento calcolata sui file') \
        .set(xlabel='tipo') \
        .set(ylabel='entropia') \
        .set(ylim=(0, ylim))
    plt.tight_layout()
    plt.savefig('../src/figures/files-entropy.pdf')

    plt.close()

    ylim = data['line_entropy'].quantile(0.95)
    sns.catplot(x='type', y='line_entropy', kind='box', data=data) \
        .set(title='Entropia del cambiamento calcolata sulle linee') \
        .set(xlabel='tipo') \
        .set(ylabel='entropia') \
        .set(ylim=(0, ylim))
    plt.tight_layout()
    plt.savefig('../src/figures/lines-entropy.pdf')