summary_stats.py 文件源码

def global_stats(articles: pd.DataFrame):
    """Calculate global stats on article db."""
    print(f'Number of articles: {len(articles):,}')
    num_sources = len(pd.value_counts(articles['base_url'], sort=False))
    print(f'Number of news sources: {num_sources}')
    mean_wc = articles['word_count'].mean()
    print(f'Global mean word count: {mean_wc:.1f}')
    missing_authors = (articles['authors'] == '').sum()
    print(f'Missing authors: {missing_authors:,}')
    missing_titles = (articles['title'] == '').sum()
    print(f'Missing titles: {missing_titles}')
    missing_texts = (articles['text'] == '').sum()
    print(f'Missing texts: {missing_texts:,}')