""" 小区周边1公里交通地铁入库业务逻辑 """ import datetime import logging import pandas as pd from goojia_utils import MAIN_MONGO_CLIENT from goojia_utils import dateutils from sklearn.mixture import GaussianMixture from pymongo import InsertOne, DeleteMany, ReplaceOne, UpdateOne logger = logging.getLogger(__name__) district_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_stat') district_analy_data_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_analy_data') server_area_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'server_area') weekend = list(district_stat_conn.find().sort([("weekend", -1)]).limit(1))[0]['weekend'] level_map = {"1": "S", "2": "A", "3": "B", "4": "C", "5": "D"} logger.info(f"开始计算楼盘评级 weekend:{dateutils.format_date(weekend, '%Y-%m-%d')}") for server_area in server_area_conn.find({'display': {'$ne': '全国'}}, {"display": 1}): city = server_area["display"] data = pd.DataFrame( district_stat_conn.find({"city": city, "weekend": weekend}, {"_id": 0, "region": 1, "district_name": 1, "avg_price": 1})) if "avg_price" not in data or len(data['avg_price'].unique()) < 5: continue data['city'] = city logger.info(f"开始计算{city}楼盘评级 weekend:{dateutils.format_date(weekend, '%Y-%m-%d')}") # 高斯混合模型 gmm = GaussianMixture(n_components=5, covariance_type='tied', max_iter=200, n_init=10).fit( data[["avg_price"]]) data.loc[:, 'cluster'] = gmm.predict(data[["avg_price"]]) data.loc[:, 'price_mean_cluster'] = data.groupby('cluster')["avg_price"].transform('mean') data.loc[:, "target"] = data['price_mean_cluster'].rank(method='dense', ascending=False).astype(int) data = data.drop(columns=['cluster', 'price_mean_cluster'], axis=1) data["community_rating"] = data['target'].apply(lambda x: level_map[str(x)]) opts = [] for item in data.to_dict('records'): opts.append(UpdateOne({"city": city, "region": item["region"], "district_name": item["district_name"]}, {"$set": {"community_rating": item["community_rating"]}}, upsert=True )) # 按照每 1000 条分割 updates 列表 batch_size = 1000 batches = [opts[i:i + batch_size] for i in range(0, len(opts), batch_size)] # 逐个批次执行批量更新操作 cnt = 0 for batch in batches: cnt = cnt + 1 logger.info(f"{city}楼盘评级更新数据库, 进度:{cnt}/{len(batches)}") result = district_analy_data_conn.bulk_write(batch) print(f"当前批次更新的文档数量: {result.modified_count}") logger.info(f"楼盘评级计算结束{dateutils.format_date(datetime.datetime.utcnow(), '%Y-%m-%d')}")