weighted_pagerank.py 文件源码

def pickle_correlations_zeros_january():
    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 from link_features', conn)
    print 'loaded links'
    df2 = pd.read_sql('select prev_id, curr_id, counts from clickstream_derived_en_201501  where link_type_derived= "internal-link";',  conn)
    print 'loaded counts'
    result = pd.merge(df, df2, how='left', left_on = ['source_article_id', 'target_article_id'], right_on = ['prev_id', 'curr_id'])
    print 'merged counts'
    print result
    article_counts = result.groupby(by=["target_article_id"])['counts'].sum().reset_index()
    article_counts['counts'].fillna(0.0, inplace=True)
    print article_counts
    print 'write to file'
    article_counts[["target_article_id","counts"]].to_csv(TMP+'january_article_counts.tsv', sep='\t', index=False)