summary_stats.py 文件源码

def calculate_word_count_stats(articles: pd.DataFrame):
    """Calculate aggregate word count statistics on each source's articles."""
    by_source = articles.groupby(['base_url'])['word_count']
    by_source = by_source.agg(['count', 'mean', 'std'])
    by_source.sort_values('count', ascending=False, inplace=True)
    print_full(by_source)

    top_sources = by_source.head(10).index
    top_counts = by_source.reset_index()[by_source.index.isin(top_sources)]
    sns.barplot(x='base_url', y='count', data=top_counts)
    sns.plt.show()
    sns.boxplot(x='base_url', y='word_count',
                data=articles[articles['base_url'].isin(top_sources)])
    sns.plt.show()