features_generator.py 文件源码

def load_brand_comment_ratio(end_date = '2016-04-01 00:00:00'):
    '''
    ?????
    '''
    dump_path = './cache/brand_comment_ratio_{0}.pkl'.format(end_date[:10])
    if os.path.exists(dump_path):
        with open(dump_path, 'rb') as f:
            df = pickle.load(f)
    else:
        item_feat = load_base_item_feat(end_date = end_date)
        item_feat = item_feat[['sku_id', 'bad_comment_rate']]
        brands = get_action_data(start_date = '2016-02-01 00:00:00', end_date = end_date, field=['sku_id', 'brand'])
        brands = brands.drop_duplicates()
        df = pd.merge(item_feat, brands, on=['sku_id'], how='left')
        df = df[['brand', 'bad_comment_rate']]
        df = df.groupby(['brand'], as_index=False).mean()
        df.columns = ['brand', 'brand_bad_comment_rate']
        with open(dump_path, 'wb') as f:
            pickle.dump(df, f)

    return df