美团均价获取方式改变

This commit is contained in:
shenjian@fangjia.com
2022-11-08 11:12:33 +08:00
parent 063bc39324
commit 12d3023738
+21 -15
View File
@@ -9,7 +9,9 @@ import logging
import sys
import numpy as np
district_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_stat')
#district_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_stat')
# 月度均价表
district_sell_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_sell_stat')
sqmetre_rent_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'sqmetre_rent')
@@ -25,6 +27,7 @@ if 'avg_price' in seaweed_new_result_df:
seaweed_new_result_df = seaweed_new_result_df.drop(columns=['avg_price', 'rent_price'])
month_start = dateutils.format_date(dateutils.add_months(dateutils.parse_date(output_date, '%Y%m'), months=-1), '%Y%m') + '01'
year_month = month_start[0:6]
curr_month_start = output_date + '01'
logging.info("日期信息:" + month_start + ' ' + curr_month_start)
@@ -44,21 +47,24 @@ for index, item in threshold_df.iterrows():
min_price[item['城市']] = item['均价最小值']
max_price[item['城市']] = item['均价最大值']
avg_df = pd.DataFrame()
for city in cities:
# 求当月均价均值
temp_df = pd.DataFrame(list(district_stat_conn.find(
{'weekend': {'$gt': month_start_date, '$lte': curr_month_start_date}, 'city': city},
{'city': 1, 'region': 1, 'district_name': 1, 'avg_price': 1, 'weekend': 1}).batch_size(10000)))
temp_df['avg_price_mean'] = temp_df.groupby(by=['city', 'region', 'district_name'])['avg_price'].transform('mean').astype(int)
temp_df = temp_df[['city', 'region', 'district_name', 'avg_price_mean']]
temp_df = temp_df.drop_duplicates(subset=['city', 'region', 'district_name'], keep='first')
# 过滤阈值
if city in min_price:
temp_df = temp_df[(temp_df['avg_price_mean'] >= min_price[city]) & (temp_df['avg_price_mean'] <= max_price[city])]
avg_df = pd.concat([avg_df, temp_df])
# 已过期 20221108 改为从月度均价表获取【该表已控制每月涨跌幅】
# avg_df = pd.DataFrame()
# for city in cities:
# # 求当月均价均值
# temp_df = pd.DataFrame(list(district_stat_conn.find(
# {'weekend': {'$gt': month_start_date, '$lte': curr_month_start_date}, 'city': city},
# {'city': 1, 'region': 1, 'district_name': 1, 'avg_price': 1, 'weekend': 1}).batch_size(10000)))
# temp_df['avg_price_mean'] = temp_df.groupby(by=['city', 'region', 'district_name'])['avg_price'].transform('mean').astype(int)
# temp_df = temp_df[['city', 'region', 'district_name', 'avg_price_mean']]
# temp_df = temp_df.drop_duplicates(subset=['city', 'region', 'district_name'], keep='first')
# # 过滤阈值
# if city in min_price:
# temp_df = temp_df[(temp_df['avg_price_mean'] >= min_price[city]) & (temp_df['avg_price_mean'] <= max_price[city])]
# avg_df = pd.concat([avg_df, temp_df])
# avg_df = avg_df.rename(columns={'district_name': 'name', 'avg_price_mean': 'avg_price'})
avg_df = avg_df.rename(columns={'district_name': 'name', 'avg_price_mean': 'avg_price'})
avg_df = pd.DataFrame(list(district_sell_conn.find({'date': int(year_month)}, {'city': 1, 'region': 1, 'district_name': 1, 'avg_price': 1}).batch_size(100000)))
avg_df = avg_df.rename(columns={'district_name': 'name'})
rent_df = pd.DataFrame()
for city in cities: