diff --git a/dags/business/business/community/estate_charge_ranking.py b/dags/business/business/community/estate_charge_ranking.py index cf7adf3..46549a6 100644 --- a/dags/business/business/community/estate_charge_ranking.py +++ b/dags/business/business/community/estate_charge_ranking.py @@ -15,6 +15,13 @@ es206_client = ElasticSearchClient(host='192.168.0.206') index_name = "community_summary" path = "/opt/airflow/dags/repo/dags/business/business/community/data" +factor_df = pd.read_excel(path + '/财力评级极值设置.xlsx') +factor_dict = dict() +for index, item in factor_df.iterrows(): + if pd.isna(item['min_total_price']): + continue + factor_dict[item['city']] = {'min_total_price': item['min_total_price'], 'max_total_price': item['max_total_price'], 'min_estate_charge': item['min_estate_charge'], 'max_estate_charge': item['max_estate_charge'], \ + 'min_avg_cost': item['min_avg_cost'], 'max_avg_cost': item['max_avg_cost']} def gmm_train(total_rate, consumption_df, source, target): @@ -73,7 +80,11 @@ def sync(city=None): sql = "select id, city, region, name, estate_charge from community_summary" if pd.notna(city): sql += " where city='" + city + "'" + ### 极值设置 community_summary_df = es206_client.scan_by_sql_to_data_frame(sql) + if city in factor_dict: + community_summary_df.loc[community_summary_df['estate_charge'] < factor_dict[city]['min_estate_charge'], 'estate_charge'] = factor_dict[city]['min_estate_charge'] + community_summary_df.loc[community_summary_df['estate_charge'] > factor_dict[city]['max_estate_charge'], 'estate_charge'] = factor_dict[city]['max_estate_charge'] calc_estate_charge_rating(community_summary_df) -sync() +sync('上海')