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

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

    data['label'] = data['Classification'].apply(lambda x: x.split(';')[0].strip())
    data = data[~data['label'].isin(['?', 'chinese', 'page not found'])]
    data['on_pipe'] = data['label'].apply(lambda x: 'No ML' if x == 'no pipeline' else 'ML')

    g = sns.catplot(x="on_pipe", kind="count", data=data)\
        .set(title='Istanze delle issues in base al tipo')\
        .set(xlabel='tipo')

    ax = g.facet_axis(0, 0)
    for p in ax.patches:
        ax.text(
            p.get_x() + p.get_width() * 0.43,
            p.get_height() + 3,
            p.get_height(),
            color='black', rotation='horizontal', size='large')

    plt.tight_layout()
    plt.savefig('../src/figures/count-type.pdf')
    #plt.show()

    exit()
    plt.close()

    data = data[data['label'] != 'no pipeline']
    g = sns.catplot(y='label', kind='count', data=data, color='green')\
        .set(title='Istanze delle issues in base alla fase') \
        .set(ylabel='fase')

    ax = g.facet_axis(0, 0)
    for p in ax.patches:
        ax.text(
            p.get_width() + 0.25,
            p.get_y() + p.get_height() / 2,
            p.get_width(),
            color='black', rotation='horizontal', size='large')

    plt.tight_layout()
    plt.savefig('../src/figures/count-phases.pdf')