import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from scipy.stats import pearsonr

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['n_comments'].quantile(0.97)
    sns.catplot(x='type', y='n_comments', kind='box', data=data) \
        .set(title='Commenti in base al tipo di issue') \
        .set(xlabel='tipo') \
        .set(ylabel='numero di commenti') \
        .set(ylim=(0, ylim))
    plt.tight_layout()
    plt.savefig('../src/figures/comments.pdf')

    plt.close()

    ylim = data['words_mean'].quantile(0.97)
    sns.catplot(x='type', y='words_mean', kind='box', data=data) \
        .set(title='Parole medie in un commento') \
        .set(xlabel='tipo') \
        .set(ylabel='parole medie') \
        .set(ylim=(0, ylim))
    plt.tight_layout()
    plt.savefig('../src/figures/words.pdf')