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

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

    help_df = pd.DataFrame(columns=['project', 'tipo', 'files/dirs', 'value'])

    for i, row in data.iterrows():
        project = row['project']

        help_df = help_df.append(
            {'project': project, 'tipo': 'No ML', 'files/dirs': 'Files', 'value': row['no_ml_files_ratio']},
            ignore_index=True
        )
        help_df = help_df.append(
            {'project': project, 'tipo': 'ML', 'files/dirs': 'Files', 'value': row['ml_files_ratio']},
            ignore_index=True
        )
        help_df = help_df.append(
            {'project': project, 'tipo': 'No ML', 'files/dirs': 'Directories', 'value': row['no_ml_dirs_ratio']},
            ignore_index=True
        )
        help_df = help_df.append(
            {'project': project, 'tipo': 'ML', 'files/dirs': 'Directories', 'value': row['ml_dirs_ratio']},
            ignore_index=True
        )

    plot = sns.boxplot(x='files/dirs', y='value', hue='tipo', data=help_df)
    plot.set_title('Percentuali di files e directories modificate')
    plot.set_ylabel('')

    plt.tight_layout()
    plt.savefig('../src/figures/files-and-directories.pdf')