From 027ba5ef1fdf35fdef3163415da9b27b8d1c19c0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B2=88=E5=81=A5?= Date: Mon, 14 Apr 2025 11:10:25 +0800 Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=A2=9E=E5=AD=90=E5=9B=A0=E5=AD=90?= =?UTF-8?q?=E8=AF=84=E5=88=86?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../business/community/consumption.py | 25 ++++++++++--------- 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/dags/business/business/community/consumption.py b/dags/business/business/community/consumption.py index 763103d..0ab13d3 100644 --- a/dags/business/business/community/consumption.py +++ b/dags/business/business/community/consumption.py @@ -190,19 +190,11 @@ 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") - # 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] + # 新增子因子评分 df = min_max_scale(df, 'consumption_potential', 'consumption_score') + df = min_max_scale(df, 'estate_charge_score', 'estate_charge_score_minmax') + df = min_max_scale(df, 'relative_price_ranking_score', 'relative_price_ranking_score_minmax') + df = min_max_scale(df, 'avg_cost_score', 'avg_cost_score_minmax') if len(score_df) > 0: # 补充财力评级 df = pd.merge(score_df[['_id', 'total_price_rating', 'total_price_score_minmax']], df, how='left', on=['_id']) @@ -235,6 +227,15 @@ def calc_consumption_rating(community_summary_df): if 'avg_cost_rating' in item and pd.notna(item['avg_cost_rating']): row['sub_factor']['avg_cost_rating'] = item['avg_cost_rating'] + if 'total_price_score_minmax' in item and pd.notna(item['total_price_score_minmax']): + row['sub_factor']['total_price_score'] = item['total_price_score_minmax'] + if 'estate_charge_score_minmax' in item and pd.notna(item['estate_charge_score_minmax']): + row['sub_factor']['estate_charge_score'] = item['estate_charge_score_minmax'] + if 'relative_price_ranking_score_minmax' in item and pd.notna(item['relative_price_ranking_score_minmax']): + row['sub_factor']['relative_price_score'] = item['relative_price_ranking_score_minmax'] + if 'avg_cost_score_minmax' in item and pd.notna(item['avg_cost_score_minmax']): + row['sub_factor']['avg_cost_score'] = item['avg_cost_score_minmax'] + action = {'_op_type': 'update', # 操作 index update create delete '_index': index_name, # index '_id': _id, # 请勿忘记ID