diff --git a/dags/business/business/community/consumption.py b/dags/business/business/community/consumption.py index fa3c5b8..2480399 100644 --- a/dags/business/business/community/consumption.py +++ b/dags/business/business/community/consumption.py @@ -84,7 +84,7 @@ def gmm_train(total_rate, consumption_df, source, target): gmm = GaussianMixture(n_components=total_rate).fit(consumption_df[[source]]) consumption_df.loc[:, 'cluster'] = gmm.predict(consumption_df[[source]]) consumption_df.loc[:, 'price_mean_cluster'] = consumption_df.groupby('cluster')[source].transform('mean') - consumption_df.loc[:, target] = consumption_df['price_mean_cluster'].rank(method='dense').astype(int) + consumption_df.loc[:, target] = consumption_df['price_mean_cluster'].rank(method='dense', ascending=False).astype(int) consumption_df = consumption_df.drop(columns=['cluster', 'price_mean_cluster'], axis=1) return consumption_df @@ -103,9 +103,9 @@ def calc_consumption_rating(community_summary_df): for city in cities: df = consumption_aim_df[consumption_aim_df['city'] == city].copy() - if len(df) < 10: + if len(df) < 5: continue - df = gmm_train(10, df, source, target) + df = gmm_train(5, df, source, target) # 批量更新 for index, item in df.iterrows(): row = dict()