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


def get(project, series) -> int:
    try:
        return series[(project, True)]
    except Exception:
        return 0


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

    total_files = data.groupby('project').size()
    ml = data.groupby(['project', 'is_ml']).size()
    ml_strict = data.groupby(['project', 'is_ml_strict']).size()

    help_df = pd.DataFrame(columns=['project', 'type', 'value'])

    for project in data['project'].unique():
        tot_files = total_files[project]

        help_df = help_df.append(
            {'project': project, 'type': 'all', 'value': get(project, ml)/tot_files},
            ignore_index=True
        )
        help_df = help_df.append(
            {'project': project, 'type': 'wo_pandas_numpy_scipy', 'value': get(project, ml_strict) / tot_files},
            ignore_index=True
        )

    colors = ['#cab2d6', '#6a3d9a']
    sns.set_palette(sns.color_palette(colors))

    sns.catplot(x='type', y='value', kind='box', data=help_df)\
        .set(title='Percentuale di file con import di ML') \
        .set(xlabel='Librerie ML') \
        .set(ylabel='')
    plt.tight_layout()
    plt.savefig('../src/figures/imports.pdf')
    #plt.show()