优化租金均价覆盖率统计

This commit is contained in:
shenjian@fangjia.com
2023-03-29 16:43:38 +08:00
parent 2eecb42410
commit 3f9e8a7528
@@ -2,7 +2,7 @@
小区数量 租金 均价 及 覆盖率统计
"""
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ClickHouseClient, ElasticSearchClient
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ClickHouseClient, ElasticSearchClient, commutils
import pandas as pd
import os
import logging
@@ -184,38 +184,22 @@ df = pd.merge(df, deal_price_half_year_df, how='left', on=['city'])
# #### 2. 均价数量
week_df = pd.DataFrame(list(district_stat_conn.distinct('weekend',
{'weekend': {'$gte': dateutils.add_months(
dateutils.datetime.datetime.now(), days=-60)}})))
week = week_df.loc[len(week_df) - 1, 0]
avg_price_df = commutils.get_avg_price()
rent_price_df = commutils.get_rent_price()
avg_price_df = pd.DataFrame(list(district_stat_conn.aggregate([
{'$match': {'weekend': {'$gte': week}}},
{'$group': {'_id': '$city', 'num': {'$sum': 1}}}
])))
avg_price_df = avg_price_df.rename(columns={'_id': 'city', 'num': 'avg_price_count'})
avg_price_df['avg_price_count'] = avg_price_df.groupby(by=['city']).transform('count')
rent_price_df['sqmetre_rent_count'] = rent_price_df.groupby(by=['city']).transform('count')
avg_price_df = avg_price_df[['city', 'avg_price_count']].drop_duplicates(keep='first')
rent_price_df = rent_price_df[['city', 'sqmetre_rent_count']].drop_duplicates(keep='first')
df = pd.merge(df, avg_price_df, how='left', on=['city'])
df['avg_price_coverage'] = pd.to_numeric(df['avg_price_count'] * 100 / df['community_count'])
df = pd.merge(df, rent_price_df, how='left', on=['city'])
df['avg_price_coverage'] = df['avg_price_count'] * 100 / df['community_count']
df['sqmetre_rent_coverage'] = df['sqmetre_rent_count'] * 100 / df['community_count']
# #### 3.租金数量
week_df = pd.DataFrame(list(sqmetre_rent_conn.distinct('weekend',
{'weekend': {'$gte': dateutils.add_months(dateutils.datetime.datetime.now(), days=-60)}})))
week = week_df.loc[len(week_df) - 1, 0]
sqmetre_rent_df = pd.DataFrame(list(sqmetre_rent_conn.aggregate([
{'$match': {'weekend': {'$gte': week}, 'cat': 'district'}},
{'$group': {'_id': '$city', 'num': {'$sum': 1}}}
])))
sqmetre_rent_df = sqmetre_rent_df.rename(columns={'_id': 'city', 'num': 'sqmetre_rent_count'})
df = pd.merge(df, sqmetre_rent_df, how='left', on=['city'])
df['sqmetre_rent_coverage'] = pd.to_numeric(df['sqmetre_rent_count'] * 100 / df['community_count'])
df.fillna(0, inplace=True)
df['community_count'] = df['community_count'].astype(int)
@@ -228,7 +212,7 @@ df['exist_alias_community_count'] = df['exist_alias_community_count'].astype(int
df = df.round({'avg_price_coverage': 2, 'sqmetre_rent_coverage': 2, 'main_type_coverage': 2, 'main_type_area_coverage': 2, 'total_price_coverage': 2, 'estate_type_coverage': 2,
'finish_building_date_coverage': 2, 'all_area_coverage': 2, 'build_area_coverage': 2, 'consumption_rating_coverage': 2, 'greening_rate_coverage': 2, 'volume_rate_coverage': 2})
df = df[['city', 'community_count', 'city_level', 'avg_price_count', 'avg_price_coverage', 'sqmetre_rent_count', 'sqmetre_rent_coverage', 'alias_count', 'addr_alias_count',
df = df[['city', 'community_count', 'city_level', 'avg_price_coverage', 'sqmetre_rent_coverage', 'alias_count', 'addr_alias_count',
'exist_alias_community_count', 'one_year_deal', 'main_type_coverage', 'main_type_area_coverage', 'total_price_coverage', 'estate_type_coverage',
'finish_building_date_coverage', 'all_area_coverage', 'build_area_coverage', 'consumption_rating_coverage', 'greening_rate_coverage', 'volume_rate_coverage']]