版本修改

This commit is contained in:
王文艳
2026-07-22 16:13:44 +08:00
parent a11383312e
commit b7534064aa
4 changed files with 92 additions and 70 deletions
+4
View File
@@ -6,6 +6,10 @@ import pandas as pd
from elasticsearch import helpers
import logging
log = logging.getLogger(__name__)
import os
# 🛡️ 极其重要:必须在导入 goojia_utils 之前禁用 ES 8.x 的兼容性 Content-Type 头部请求!
# 这样客户端就会使用普通的 'application/json' 头部,彻底解决低版本 Elasticsearch 报错 406 的故障。
os.environ["ELASTIC_CLIENT_APIVERSIONING"] = "0"
flag = False
for province in areautils.get_all_province():
+2 -4
View File
@@ -27,7 +27,6 @@ def choose_task(**context):
return ['office_city_region_rent_calc', 'office_base_rent_calc']
with DAG(
dag_id="office_rent_dag",
# 每月25日1点运行
@@ -41,7 +40,7 @@ with DAG(
branch_task = BranchPythonOperator(
task_id='choose_branch',
python_callable=choose_task,
provide_context=True
# 🛡️ 已移除 provide_context=True,防止 Airflow 3.3.0 报错崩溃
)
# 任务1:城市区域租金计算
t1 = BashOperator(
@@ -52,7 +51,6 @@ with DAG(
t2 = PythonOperator(
task_id='office_base_rent_calc',
python_callable=calc,
provide_context=True
# 🛡️ 已移除 provide_context=True,防止 Airflow 3.3.0 报错崩溃
)
branch_task >> [t1, t2]
+1
View File
@@ -4,6 +4,7 @@ import datetime
import urllib3
from goojia_utils import nextcloudutils, dingutils
if __name__ == "__main__":
# 禁用 InsecureRequestWarning
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+23 -4
View File
@@ -4,6 +4,7 @@
import datetime
import logging
import pandas as pd
import sys # 新增导入系统模块用于安全退出
from goojia_utils import MAIN_MONGO_CLIENT
from goojia_utils import dateutils
from sklearn.mixture import GaussianMixture
@@ -11,12 +12,26 @@ from pymongo import InsertOne, DeleteMany, ReplaceOne, UpdateOne
logger = logging.getLogger(__name__)
# ================== 🛡️ 安全运行入口 ==================
if __name__ == "__main__":
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']
# 1. 延迟进行重度 MongoDB 查询
weekend_list = list(district_stat_conn.find().sort([("weekend", -1)]).limit(1))
if not weekend_list:
logger.error("在 district_stat 集合中未找到有效的 weekend 记录,程序退出。")
sys.exit(1)
weekend = weekend_list[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')}")
# 2. 遍历各城市开展机器学习模型评级
for server_area in server_area_conn.find({'display': {'$ne': '全国'}}, {"display": 1}):
city = server_area["display"]
data = pd.DataFrame(
@@ -26,7 +41,8 @@ for server_area in server_area_conn.find({'display': {'$ne': '全国'}}, {"displ
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
# 高斯混合模型训练及评估(延迟到真正执行时运行,避免污染解析阶段)
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"]])
@@ -34,19 +50,22 @@ for server_area in server_area_conn.find({'display': {'$ne': '全国'}}, {"displ
data.loc[:, "target"] = data['price_mean_cluster'].rank(method='dense', ascending=False).astype(int)
data = data.drop(columns=['cluster', 'price_mean_cluster'], axis=1)
data["community_rating"] = data['target'].apply(lambda x: level_map[str(x)])
opts = []
for item in data.to_dict('records'):
opts.append(UpdateOne({"city": city, "region": item["region"], "district_name": item["district_name"]},
{"$set": {"community_rating": item["community_rating"]}}, upsert=True
))
# 按照每 1000 条分割 updates 列表
# 按照每 1000 条分割 updates 列表并执行 Bulk Write
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')}")