diff --git a/dags/stat/community/community_rate.py b/dags/stat/community/community_rate.py index 3928d5b..746b969 100644 --- a/dags/stat/community/community_rate.py +++ b/dags/stat/community/community_rate.py @@ -201,7 +201,7 @@ def gmm_train(total_rate, data, source, target): def load_comms(city): query = {"cat": "district", "status": 0, "city": city} fields = {"city": 1, "region": 1, "name": 1, "address": 1, "lng": 1, "lat": 1, "estate_type2": 1, "create_year": 1, - "cubage_percent": 1, "virescence_percent": 1, "estate_charge": 1, "business_quarter": 1} + "cubage_percent": 1, "virescence_percent": 1, "estate_charge": 1, "business_quarter": 1, "business_quarter": 1} seaweed = pd.DataFrame(list(seaweed_client.find(query, fields))) seaweed = seaweed.dropna(subset=['lng', 'lat']) seaweed['_id'] = seaweed['_id'].apply(lambda x: str(x)) @@ -403,7 +403,7 @@ def comms_rating(data): data[f'{score_factor}_level'] = data[f'{score_factor}_level'].map(COMM_RATING_LEVEL_NAMES) for score_factor in ['total_score', 'community_quality_score', 'community_price_score', 'location_advantage_score', 'flowability_score', 'living_facilities_score', 'education_score', 'hospital_score']: - data[f'{score_factor}'] = data[f'{score_factor}'].apply(lambda x: int(x * 100)) + data[f'{score_factor}'] = data[f'{score_factor}'].apply(lambda x: round(x * 100, 6)) return data # ## 按照城市加载楼盘评级数据宽表 @@ -442,7 +442,7 @@ if __name__ == '__main__': else: cities = [city for city in args.city.split(',')] - db_fields = ["comm_id", "city", "region", "name", "total_score", "community_quality_score", "community_price_score", + db_fields = ["comm_id", "city", "region", 'business_quarter', "name", "total_score", "community_quality_score", "community_price_score", "location_advantage_score", "flowability_score", "living_facilities_score", "education_score", "hospital_score", "total_score_level", "community_quality_score_level", "community_price_score_level", "location_advantage_score_level", "flowability_score_level", "living_facilities_score_level", @@ -454,6 +454,37 @@ if __name__ == '__main__': data = comms_rating(data) data["comm_id"] = data['_id'] db_df = data[db_fields] + df_simple = db_df.copy() + for factor_score_field in ['total_score', 'community_quality_score', 'community_price_score', + 'location_advantage_score', 'flowability_score', 'living_facilities_score', + 'education_score', 'hospital_score']: + key = "_" + if factor_score_field != "total_score": + key = f"_{factor_score_field.replace('_score', '')}" + + df_simple[f'city{key}rank'] = df_simple.groupby('city')[factor_score_field].rank(method='dense', + ascending=False).astype( + int) + df_simple[f'city{key}total_rank'] = df_simple[f'city{key}rank'].max() + df_simple[f'region{key}rank'] = df_simple.groupby(['city', 'region'])[factor_score_field].rank( + method='dense', ascending=False).astype(int) + df_simple[f'region{key}total_rank'] = df_simple[f'region{key}rank'].max() + # 处理bis为None的情况 - 只对非空bis值计算排名 + df_simple[f'business_quarter{key}_total_rank'] = None + df_simple[f'business_quarter{key}_rank'] = None + # 对bis不为None的记录计算商圈排名 + bis_not_null = df_simple['business_quarter'].notna() + if bis_not_null.any(): + df_simple.loc[bis_not_null, f'business_quarter{key}_rank'] = \ + df_simple.loc[bis_not_null].groupby(['city', 'region', 'business_quarter'])[ + factor_score_field].rank(method='dense', ascending=False).astype(int) + df_simple.loc[bis_not_null, f'business_quarter{key}_total_rank'] = df_simple.loc[bis_not_null][ + f'business_quarter{key}_rank'].max() + for score_factor in ['total_score', 'community_quality_score', 'community_price_score', + 'location_advantage_score', 'flowability_score', 'living_facilities_score', + 'education_score', 'hospital_score']: + df_simple[f'{score_factor}'] = df_simple[f'{score_factor}'].apply(lambda x: round(x * 100, 2)) + updater = MongoDataFrameUpdater(community_rate_client) updater.bulk_insert_or_update_by_id(db_df, id_fields=['comm_id']) logger.info(f"楼盘评级计算结束:{city}")