weighted_pagerank.py 文件源码

def pickle_correlations_zeros():
    db = MySQLDatabase(DATABASE_HOST, DATABASE_USER, DATABASE_PASSWORD, DATABASE_NAME)
    conn = db._create_connection()

    print 'read'
    df = pd.read_sql('select source_article_id, target_article_id, IFNULL(counts, 0) as counts from link_features group by source_article_id, target_article_id', conn)
    print 'group'
    article_counts = df.groupby(by=["target_article_id"])['counts'].sum().reset_index()
    print 'write to file'
    article_counts[["target_article_id","counts"]].to_csv(TMP+'article_counts.tsv', sep='\t', index=False)