diff --git a/dags/business/business/community/data/财力评级物业费等级情况20221213.xlsx b/dags/business/business/community/data/财力评级物业费等级情况20221213.xlsx new file mode 100644 index 0000000..535ad3d Binary files /dev/null and b/dags/business/business/community/data/财力评级物业费等级情况20221213.xlsx differ diff --git a/dags/business/business/community/estate_charge_ranking.py b/dags/business/business/community/estate_charge_ranking.py index e68f74d..fcb5f2f 100644 --- a/dags/business/business/community/estate_charge_ranking.py +++ b/dags/business/business/community/estate_charge_ranking.py @@ -34,9 +34,17 @@ for index, item in factor_df.iterrows(): 'min_avg_cost': item['min_avg_cost'], 'max_avg_cost': item['max_avg_cost']} +reasonable_df = pd.read_excel(path + '/财力评级物业费等级情况20221213.xlsx') +reasonable_dict = reasonable_df.set_index('city')['是否合理'].to_dict() + + def gmm_train(total_rate, consumption_df, source, target): # 高斯混合模型 - gmm = GaussianMixture(n_components=total_rate).fit(consumption_df[[source]]) + city_info = consumption_df.loc[0, 'city'] + if city_info in reasonable_dict and reasonable_dict[city_info] == '不合理': + gmm = GaussianMixture(n_components=total_rate, max_iter=200, n_init=5).fit(consumption_df[[source]]) + else: + gmm = GaussianMixture(n_components=total_rate).fit(consumption_df[[source]]) consumption_df['cluster'] = gmm.predict(consumption_df[[source]]) consumption_df['price_mean_cluster'] = consumption_df.groupby('cluster')[source].transform('mean') consumption_df[target] = consumption_df['price_mean_cluster'].rank(method='dense', ascending=False).astype(int) @@ -124,7 +132,8 @@ def sync_by_city(city_now): def sync(city=None): if pd.isna(city): - for city_now in factor_df['city'].unique(): + for city_now in reasonable_df['city'].unique(): + #if reasonable_dict[city_now] == '不合理': sync_by_city(city_now) else: sync_by_city(city)