From e3579708e4257bb14d8fbbb2bdf59e4529f514b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B2=88=E5=81=A5?= Date: Wed, 5 Mar 2025 11:01:49 +0800 Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=A2=9E=E5=AD=90=E8=AF=84=E7=BA=A7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- dags/business/business/community/consumption.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/dags/business/business/community/consumption.py b/dags/business/business/community/consumption.py index 284a905..8a06f64 100644 --- a/dags/business/business/community/consumption.py +++ b/dags/business/business/community/consumption.py @@ -99,7 +99,7 @@ def calc_consumption_potential(city): community_summary_df['avg_cost_score'] = 0 community_summary_df['consumption_potential'] = community_summary_df['total_price_score'] + community_summary_df[ - 'estate_charge_score'] + community_summary_df['relative_price_ranking_score'] + community_summary_df['avg_cost_score'] + community_summary_df['avg_cost_score'] + 4099.978248 + 'estate_charge_score'] + community_summary_df['relative_price_ranking_score'] + community_summary_df['avg_cost_score'] + 4099.978248 return community_summary_df @@ -117,7 +117,7 @@ def calc_consumption_rating(community_summary_df): """ 计算消费等级 """ - df = community_summary_df[['_id', 'city', 'consumption_potential']] + df = community_summary_df[['_id', 'city', 'consumption_potential', 'total_price_score', 'estate_charge_score', 'relative_price_ranking_score', 'avg_cost_score']] df = df.dropna(subset=['consumption_potential']) source = "normal_consumption_potential" target = "consumption_rating" @@ -133,6 +133,11 @@ def calc_consumption_rating(community_summary_df): # 极值设置 df = filter_min_max(df) df = gmm_train(total_rate, df, source, target) + # 新增子因子评级 + df = gmm_train(total_rate, df, "total_price_score", "total_price_rating") + df = gmm_train(total_rate, df, "estate_charge_score", "estate_charge_rating") + 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") # 批量更新 for index, item in df.iterrows(): row = dict() @@ -140,6 +145,12 @@ def calc_consumption_rating(community_summary_df): row['consumption_rating'] = item['consumption_rating'] row['consumption_potential'] = item['consumption_potential'] row['m_date'] = dateutils.iso_format() + row['sub_factor'] = { + "total_price_rating": item['total_price_rating'], + "estate_charge_rating": item['estate_charge_rating'], + "relative_price_rating": item['relative_price_rating'], + "avg_cost_rating": item['avg_cost_rating'] + } action = {'_op_type': 'update', # 操作 index update create delete '_index': index_name, # index