From 6c6841988ed4f05a15f7c98fd342ba80973f5990 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B2=88=E5=81=A5?= Date: Fri, 11 Apr 2025 10:02:20 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E5=B0=91=E9=87=8F=E5=9F=8E?= =?UTF-8?q?=E5=B8=82=E8=AF=84=E7=BA=A7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../business/community/consumption.py | 36 +++++++++++-------- 1 file changed, 22 insertions(+), 14 deletions(-) diff --git a/dags/business/business/community/consumption.py b/dags/business/business/community/consumption.py index d9aaa60..7f9d14f 100644 --- a/dags/business/business/community/consumption.py +++ b/dags/business/business/community/consumption.py @@ -37,6 +37,9 @@ reasonable_dict = reasonable_df.set_index('city')['是否合理'].to_dict() def min_max_scale(df, column, target_column, new_min=1, new_max=100): X_min = df[column].min() X_max = df[column].max() + # 如果存在缺失值,则不进行归一化 + if pd.isna(X_min): + return df # 防止分母为零(如果所有值相等) if X_max == X_min: @@ -164,40 +167,45 @@ def calc_consumption_rating(community_summary_df): score_df = gmm_train(total_rate, df.dropna(subset=['total_price_score']), "total_price_score", "total_price_rating") score_df = min_max_scale(score_df, 'total_price_score', 'total_price_score_minmax') df = filter_min_max(df) - df = gmm_train(total_rate, df.dropna(subset=['consumption_potential']), source, target) - # 新增子因子评级 - 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") + if len(df.dropna(subset=['consumption_potential'])) >= total_rate: + df = gmm_train(total_rate, df.dropna(subset=['consumption_potential']), source, target) + # 新增子因子评级 + 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") - # 应用归一化 + # 应用归一化 df = min_max_scale(df, 'consumption_potential', 'consumption_score') 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']) # 填充缺失值 + if 'consumption_rating' not in df.columns: + df["consumption_rating"] = None + if 'consumption_score' not in df.columns: + df["consumption_score"] = None df["consumption_rating"] = df["consumption_rating"].fillna(df["total_price_rating"]) df["consumption_score"] = df["consumption_score"].fillna(df["total_price_score_minmax"]) - # 批量更新 + # 批量更新 如果财力评级与户均总价评级都没有,不更新 for index, item in df.iterrows(): row = dict() _id = str(item["_id"]) - if pd.notna(item['consumption_rating']): + if 'consumption_rating' in item and pd.notna(item['consumption_rating']): row['consumption_rating'] = item['consumption_rating'] - if pd.notna(item['consumption_score']): + if 'consumption_score' in item and pd.notna(item['consumption_score']): row['consumption_score'] = item['consumption_score'] - if pd.notna(item['consumption_potential']): + if 'consumption_potential' in item and pd.notna(item['consumption_potential']): row['consumption_potential'] = item['consumption_potential'] row['m_date'] = dateutils.iso_format() row['sub_factor'] = {} - if pd.notna(item['total_price_rating']): + if 'total_price_rating' in item and pd.notna(item['total_price_rating']): row['sub_factor']['total_price_rating'] = item['total_price_rating'] - if pd.notna(item['estate_charge_rating']): + if 'estate_charge_rating' in item and pd.notna(item['estate_charge_rating']): row['sub_factor']['estate_charge_rating'] = item['estate_charge_rating'] - if pd.notna(item['relative_price_rating']): + if 'relative_price_rating' in item and pd.notna(item['relative_price_rating']): row['sub_factor']['relative_price_rating'] = item['relative_price_rating'] - if pd.notna(item['avg_cost_rating']): + if 'avg_cost_rating' in item and pd.notna(item['avg_cost_rating']): row['sub_factor']['avg_cost_rating'] = item['avg_cost_rating'] action = {'_op_type': 'update', # 操作 index update create delete