diff --git a/dags/business/business/community/avg_cost.py b/dags/business/business/community/avg_cost.py index f4cd669..8a3198a 100644 --- a/dags/business/business/community/avg_cost.py +++ b/dags/business/business/community/avg_cost.py @@ -101,22 +101,23 @@ def update_status(new_df): def sync(city=None): log.info("开始同步消费数据...") - query_sql = "select id, city, tag, type, price from bd_poi where price > 0 and tag in('美食;中餐厅', '美食;外国餐厅') " - if pd.notna(city): - query_sql += " and city='" + areautils.get_city_display(city) + "'" - df = es206_client.scan_by_sql_to_data_frame(query_sql) - - # 按百分位5-95筛选数据 - cities = df['city'].unique() - for city_now in cities: - df.loc[df['city'] == city_now, 'minPrice5'] = np.percentile(a=df[df['city'] == city_now]['price'], q=5, axis=0) - df.loc[df['city'] == city_now, 'minPrice95'] = np.percentile(a=df[df['city'] == city_now]['price'], q=95, axis=0) - - new_df = df[(df['price'] >= df['minPrice5']) & (df['price'] <= df['minPrice95'])] - new_df['new_mean'] = new_df.groupby(by=['city'])['price'].transform(np.mean) - - # 按最新的百分位更新库中价格状态 - update_status(new_df) + # 暂时注释 + # query_sql = "select id, city, tag, type, price from bd_poi where price > 0 and tag in('美食;中餐厅', '美食;外国餐厅') " + # if pd.notna(city): + # query_sql += " and city='" + areautils.get_city_display(city) + "'" + # df = es206_client.scan_by_sql_to_data_frame(query_sql) + # + # # 按百分位5-95筛选数据 + # cities = df['city'].unique() + # for city_now in cities: + # df.loc[df['city'] == city_now, 'minPrice5'] = np.percentile(a=df[df['city'] == city_now]['price'], q=5, axis=0) + # df.loc[df['city'] == city_now, 'minPrice95'] = np.percentile(a=df[df['city'] == city_now]['price'], q=95, axis=0) + # + # new_df = df[(df['price'] >= df['minPrice5']) & (df['price'] <= df['minPrice95'])] + # new_df['new_mean'] = new_df.groupby(by=['city'])['price'].transform(np.mean) + # + # # 按最新的百分位更新库中价格状态 + # update_status(new_df) seaweed_df = pd.read_csv(path + '/seaweed.csv', sep='@', encoding='UTF-8') if pd.notna(city):