新增评级总分100
This commit is contained in:
@@ -127,7 +127,7 @@ def calc_consumption_rating(community_summary_df):
|
||||
count = 0
|
||||
|
||||
# 总评级
|
||||
total_rate = 100
|
||||
total_rate = 6
|
||||
if len(df) < total_rate:
|
||||
# 对于样本低于5的直接排名
|
||||
df[target] = df['consumption_potential'].rank(method='dense', ascending=False).astype(int)
|
||||
@@ -144,11 +144,23 @@ def calc_consumption_rating(community_summary_df):
|
||||
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")
|
||||
|
||||
# 总分数
|
||||
total_score = 100
|
||||
if len(df) < total_score:
|
||||
# 对于样本低于5的直接排名
|
||||
df["consumption_score"] = df['consumption_potential'].rank(method='dense', ascending=False).astype(int)
|
||||
else:
|
||||
# 极值设置
|
||||
df = filter_min_max(df)
|
||||
df = gmm_train(total_rate, df, source, "consumption_score")
|
||||
|
||||
# 批量更新
|
||||
for index, item in df.iterrows():
|
||||
row = dict()
|
||||
_id = str(item["_id"])
|
||||
row['consumption_rating'] = item['consumption_rating']
|
||||
row['consumption_score'] = item['consumption_score']
|
||||
row['consumption_potential'] = item['consumption_potential']
|
||||
row['m_date'] = dateutils.iso_format()
|
||||
row['sub_factor'] = {
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
import sys
|
||||
|
||||
from goojia_utils import ElasticSearchClient, MAIN_MONGO_CLIENT, dateutils, areautils
|
||||
import numpy as np
|
||||
from pymongo import UpdateOne
|
||||
from datetime import datetime
|
||||
import logging
|
||||
import pandas as pd
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
es_client = ElasticSearchClient(host='192.168.0.206')
|
||||
shop_rent_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'shop_rent_stat')
|
||||
|
||||
|
||||
def calc(city, year_month):
|
||||
if len(str(year_month)) != 6:
|
||||
raise Exception('年月格式错误yyyyMM')
|
||||
shop = es_client.scan_by_sql_to_data_frame(
|
||||
"select * from latest_seawater where cat='shop_rent' and city='" + city + "' and p_date>=" + str(
|
||||
year_month) + "01 and p_date<=" + str(year_month) + "31 ")
|
||||
if len(shop) > 0:
|
||||
shop['day_avg_price'] = shop['day_rent_price']
|
||||
# 计算总价的Z-score
|
||||
shop['Z_Score'] = (shop['day_avg_price'] - shop['day_avg_price'].mean()) / shop['day_avg_price'].std()
|
||||
# 剔除Z-score超过0.1的异常值
|
||||
shop_cleaned = shop[np.abs(shop['Z_Score']) < 0.1]
|
||||
# 至少样本数大于等于10
|
||||
if len(shop_cleaned['day_avg_price']) >= 10:
|
||||
city_price = round(shop_cleaned['day_avg_price'].median(), 2)
|
||||
region_median_count_prices = shop_cleaned.groupby(shop_cleaned['region'])['day_avg_price'].agg(['median', 'count']).to_dict()
|
||||
else:
|
||||
city_price = None
|
||||
region_median_count_prices = {'median': {}, 'count': {}}
|
||||
else:
|
||||
city_price = None
|
||||
region_median_count_prices = {'median': {}, 'count': {}}
|
||||
|
||||
actions = list()
|
||||
|
||||
last_month = int(
|
||||
dateutils.format_date(dateutils.add_months(dateutils.parse_date(str(year_month), '%Y%m'), months=-1), '%Y%m'))
|
||||
if pd.isna(city_price):
|
||||
# 处理均价为空情况,用上月均价替代
|
||||
stat = shop_rent_stat_conn.find_one({'city': city, 'cat': 'city', 'date': last_month})
|
||||
if pd.isna(stat):
|
||||
return False
|
||||
last_month_city_price = stat['avg_price']
|
||||
if pd.isna(last_month_city_price):
|
||||
return False
|
||||
city_price = last_month_city_price
|
||||
|
||||
# 写入MONGODB
|
||||
action = UpdateOne({'city': city, 'cat': 'city', 'date': year_month},
|
||||
{'$set': {'city': city, 'cat': 'city', 'date': year_month, 'avg_price': city_price,
|
||||
'updated_date': datetime.now()}},
|
||||
upsert=True)
|
||||
|
||||
actions.append(action)
|
||||
for region in areautils.get_all_districts(city):
|
||||
region_avg_prices = region_median_count_prices['median']
|
||||
region_count = region_median_count_prices['count']
|
||||
if region in region_avg_prices and region_count[region] >= 10:
|
||||
avg_price = region_avg_prices[region]
|
||||
else:
|
||||
# 处理均价为空情况,用上月均价替代
|
||||
district_stat = shop_rent_stat_conn.find_one({'city': city, 'cat': 'district', 'date': last_month, 'district': region})
|
||||
if pd.isna(district_stat):
|
||||
continue
|
||||
last_month_region_price = district_stat['avg_price']
|
||||
if pd.isna(last_month_region_price):
|
||||
continue
|
||||
avg_price = last_month_region_price
|
||||
|
||||
action = UpdateOne({'city': city, 'cat': 'district', 'date': year_month, 'district': region},
|
||||
{'$set': {'city': city, 'cat': 'district', 'date': year_month, 'district': region,
|
||||
'avg_price': round(avg_price, 2), 'updated_date': datetime.now()}},
|
||||
upsert=True)
|
||||
actions.append(action)
|
||||
shop_rent_stat_conn.bulk_write(actions)
|
||||
log.info(f"{city} {year_month} 均价计算完毕!")
|
||||
|
||||
|
||||
yearmonth = sys.argv[1] if len(sys.argv) > 1 else ''
|
||||
|
||||
if yearmonth == '':
|
||||
date = dateutils.add_months(datetime.today(), months=-1)
|
||||
yearmonth = int(dateutils.format_date(date, '%Y%m'))
|
||||
try:
|
||||
for city in areautils.get_all_cities():
|
||||
calc(city, yearmonth)
|
||||
except Exception as e:
|
||||
log.error(e)
|
||||
|
||||
# # 初始化从2024年9月
|
||||
# 创建从2024年9月到2024年12月的日期范围
|
||||
# date_range = pd.date_range(start='2024-09-01', end='2025-01-31', freq='M')
|
||||
#
|
||||
# # 创建一个包含这些日期的DataFrame
|
||||
# df = pd.DataFrame({'date': date_range, 'value': range(1, len(date_range) + 1)})
|
||||
#
|
||||
# # 将日期设置为索引
|
||||
# df.set_index('date', inplace=True)
|
||||
#
|
||||
# # 遍历DataFrame
|
||||
# for city in areautils.get_all_cities():
|
||||
# for date, row in df.iterrows():
|
||||
# try:
|
||||
# date_format = int(dateutils.format_date(date, '%Y%m'))
|
||||
# calc(city, date_format)
|
||||
# except Exception as e:
|
||||
# log.error(e)
|
||||
Reference in New Issue
Block a user