response_stats.py 文件源码

def show_domain_stats(log, output, top=50):
    log['Domain'] = log['url'].apply(get_domain)
    by_domain = log.groupby('Domain')
    top_domains = (
        by_domain.count().sort_values('url', ascending=False)['url'].index)
    stats_by_domain = pd.DataFrame(index=top_domains)
    stats_by_domain['Pages'] = by_domain.count()['url']
    stats_by_domain['Total Score'] = by_domain.sum()['score'].astype(int)
    stats_by_domain['Mean Score'] = by_domain.mean()['score']
    stats_by_domain['Max Depth'] = by_domain.max()['depth']
    stats_by_domain['Median Depth'] = by_domain.median()['depth'].astype(int)
    print()
    pages = stats_by_domain['Pages']
    print('Top {} domains stats (covering {:.1%} pages)'
          .format(top, pages[:top].sum() / pages.sum()))
    pd.set_option('display.width', 1000)
    print(stats_by_domain[:top])
    if output:
        filename = '{}-by-domain.csv'.format(output)
        stats_by_domain.to_csv(filename)
        print()
        print('Saved domain stats to {}'.format(filename))