diff --git a/dags/business/business/community/consumption.py b/dags/business/business/community/consumption.py index 68cdfee..31f5816 100644 --- a/dags/business/business/community/consumption.py +++ b/dags/business/business/community/consumption.py @@ -181,8 +181,17 @@ def calc_consumption_rating(community_summary_df): df = gmm_train(total_rate, df, "relative_price_ranking_score", "relative_price_rating") df = gmm_train(total_rate, df, "avg_cost_score", "avg_cost_rating") - # 应用归一化 - df['robust_potential'] = scaler.fit_transform(df[['consumption_potential']]) + # 计算四分位数和IQR + Q1 = df['consumption_potential'].quantile(0.15) + Q3 = df['consumption_potential'].quantile(0.85) + IQR = Q3 - Q1 + + # 定义上下临界点 + upper_bound = Q3 + 1.5 * IQR + + # 将超过上临界点的值替换为临界值 + df['robust_potential'] = df['consumption_potential'].clip(upper=upper_bound) + df = min_max_scale(df, 'robust_potential', 'consumption_score') # 再映射到 [1, 100] #df = min_max_scale(df, 'consumption_potential', 'consumption_score') if len(score_df) > 0: