新增字段统计

This commit is contained in:
shenjian@fangjia.com
2023-03-29 15:02:18 +08:00
parent 9abc7a5676
commit 98017d34f0
2 changed files with 112 additions and 11 deletions
@@ -0,0 +1,25 @@
create table fangjia_stat.community_coverage_stat
(
city String,
city_level Int32,
community_count Int32,
avg_price_count Int32,
avg_price_coverage Float32,
sqmetre_rent_count Int32,
sqmetre_rent_coverage Float32,
weekend Date,
alias_count Nullable(Int32),
addr_alias_count Nullable(Int32),
one_year_deal Nullable(Int32),
exist_alias_community_count Nullable(Int32),
main_type_coverage Nullable(Float32),
main_type_area_coverage Nullable(Float32),
estate_charge_coverage Nullable(Float32),
finish_building_date_coverage Nullable(Float32),
all_area_coverage Nullable(Float32),
build_area_coverage Nullable(Float32),
greening_rate_coverage Nullable(Float32),
volume_rate_coverage Nullable(Float32),
consumption_rating_coverage Nullable(Float32)
)
engine = Memory;
@@ -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
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ClickHouseClient, ElasticSearchClient
import pandas as pd
import os
@@ -13,6 +13,8 @@ sqmetre_rent_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'sqmetre_rent')
clickHouseClient = ClickHouseClient(host="192.168.0.216", database='fangjia_stat')
deal_price_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'deal_price')
es206_client = ElasticSearchClient(host='192.168.0.206')
city_df = pd.DataFrame(list(server_area_conn.find({}, {'city_grade': 1, 'display': 1})))
city_df = city_df.rename(columns={'city_grade': 'city_level', 'display': 'city'})
city_df = city_df[city_df['city_level'] != 0]
@@ -74,12 +76,82 @@ for index, item in city_df.iterrows():
# alias_df = alias_df.rename(columns={'_id': 'city'})
# df = pd.merge(df, alias_df, how='left', on=['city'])
# 有地址别名小区量
# addr_alias_count = pd.DataFrame(list(seaweed_conn.aggregate([
# {'$match': {'cat': 'district', 'status': 0, 'addr_alias': {'$ne': None}}},
# {'$group': {'_id': "$city", 'addr_alias_count': {'$sum': 1}}}])))
# addr_alias_count = addr_alias_count.rename(columns={'_id': 'city'})
# df = pd.merge(df, addr_alias_count, how='left', on=['city'])
df = city_df.copy()
# 主力户型
main_type_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'main_type': {'$ne': None}}},
{'$group': {'_id': "$city", 'main_type_count': {'$sum': 1}}}])))
main_type_count = main_type_count.rename(columns={'_id': 'city'})
df = pd.merge(df, main_type_count, how='left', on=['city'])
df['main_type_coverage'] = df['main_type_count'] * 100 / df['community_count']
# 主力面积
main_type_area_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'main_type_area': {'$ne': None}}},
{'$group': {'_id': "$city", 'main_type_area_count': {'$sum': 1}}}])))
main_type_area_count = main_type_area_count.rename(columns={'_id': 'city'})
df = pd.merge(df, main_type_area_count, how='left', on=['city'])
df['main_type_area_coverage'] = df['main_type_area_count'] * 100 / df['community_count']
# 物业类型
estate_type_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'estate_type2': {'$ne': None}}},
{'$group': {'_id': "$city", 'estate_charge_count': {'$sum': 1}}}])))
estate_type_count = estate_type_count.rename(columns={'_id': 'city'})
df = pd.merge(df, estate_type_count, how='left', on=['city'])
df['estate_type_coverage'] = df['estate_type_count'] * 100 / df['community_count']
# 建成年代
finish_building_date_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'finish_building_date': {'$ne': None}}},
{'$group': {'_id': "$city", 'finish_building_date_count': {'$sum': 1}}}])))
finish_building_date_count = finish_building_date_count.rename(columns={'_id': 'city'})
df = pd.merge(df, finish_building_date_count, how='left', on=['city'])
df['finish_building_date_coverage'] = df['finish_building_date_count'] * 100 / df['community_count']
# 占地面积
all_area_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'all_area': {'$ne': None}}},
{'$group': {'_id': "$city", 'all_area_count': {'$sum': 1}}}])))
all_area_count = all_area_count.rename(columns={'_id': 'city'})
df = pd.merge(df, all_area_count, how='left', on=['city'])
df['all_area_coverage'] = df['all_area_count'] * 100 / df['community_count']
# 建筑面积
build_area_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'build_area': {'$ne': None}}},
{'$group': {'_id': "$city", 'build_area_count': {'$sum': 1}}}])))
build_area_count = build_area_count.rename(columns={'_id': 'city'})
df = pd.merge(df, build_area_count, how='left', on=['city'])
df['build_area_coverage'] = df['build_area_count'] * 100 / df['community_count']
# 绿化率
greening_rate_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'virescence_percent': {'$ne': None}}},
{'$group': {'_id': "$city", 'greening_rate_count': {'$sum': 1}}}])))
greening_rate_count = greening_rate_count.rename(columns={'_id': 'city'})
df = pd.merge(df, greening_rate_count, how='left', on=['city'])
df['greening_rate_coverage'] = df['greening_rate_count'] * 100 / df['community_count']
# 容积率
volume_rate_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$match': {'cat': 'district', 'status': 0, 'cubage_percent': {'$ne': None}}},
{'$group': {'_id': "$city", 'volume_rate_count': {'$sum': 1}}}])))
volume_rate_count = volume_rate_count.rename(columns={'_id': 'city'})
df = pd.merge(df, volume_rate_count, how='left', on=['city'])
df['volume_rate_coverage'] = df['volume_rate_count'] * 100 / df['community_count']
# 户均总价
df['total_price_count'] = None
# 财力评级
df['consumption_rating_count'] = None
for index, item in df.iterrows():
curr_city = item['city']
sql = f"select count(*) from community_summary where city='{curr_city}' and total_price>0 "
num = es206_client.search_by_sql(sql)['hits']['total']['value']
df.loc[index, 'total_price_count'] = num
sql = f"select count(*) from community_summary where city='{curr_city}' and consumption_rating>0 "
consumption_rating_num = es206_client.search_by_sql(sql)['hits']['total']['value']
df.loc[index, 'consumption_rating_count'] = consumption_rating_num
df['total_price_coverage'] = df['total_price_count'] * 100 / df['community_count']
df['consumption_rating_coverage'] = df['consumption_rating_count'] * 100 / df['community_count']
##### 2. 近一年成交量
@@ -101,7 +173,7 @@ deal_price_seaweed_notnull_df = deal_price_seaweed_df.dropna(subset=['_id'])
deal_price_seaweed_notnull_df.loc[:, 'one_year_deal'] = deal_price_seaweed_notnull_df.groupby(['city'])[
'city'].transform('size')
deal_price_half_year_df = deal_price_seaweed_notnull_df[['city', 'one_year_deal']].drop_duplicates(keep='first')
df = pd.merge(city_df, deal_price_half_year_df, how='left', on=['city'])
df = pd.merge(df, deal_price_half_year_df, how='left', on=['city'])
# #### 2. 均价数量
@@ -147,8 +219,11 @@ df['alias_count'] = df['alias_count'].astype(int)
df['addr_alias_count'] = df['addr_alias_count'].astype(int)
df['exist_alias_community_count'] = df['exist_alias_community_count'].astype(int)
df = df.round({'avg_price_coverage': 2, 'sqmetre_rent_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', 'exist_alias_community_count', 'one_year_deal']]
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',
'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']]
df['weekend'] = dateutils.datetime.datetime.now()
# 删除本日生成的重复数据,防止手工点击生成
@@ -159,7 +234,8 @@ clickHouseClient.to_sql(df, table='community_coverage_stat', if_exists='insert',
# 上传至nextcloud
ret_df = pd.merge(ret_df, df, how='left', on=['city'])
del ret_df['是否合理']
ret_df = ret_df.rename(columns={'city': '城市', 'city_level': '城市级别', 'community_count': "楼盘数量", "alias_count": "别名数量", "addr_alias_count": "地址别名数量", "exist_alias_community_count": "有别名覆盖小区数量"})
ret_df = ret_df.rename(columns={'city': '城市', 'city_level': '城市级别', 'community_count': "楼盘数量", "alias_count": "别名数量", "addr_alias_count": "地址别名数量", "exist_alias_community_count": "有别名覆盖小区数量",
'estate_type_coverage': '物业类型覆盖率', 'avg_price_coverage': '均价覆盖率', 'sqmetre_rent_coverage': '平米租金覆盖率', 'total_price_coverage': '户均总价覆盖率', 'main_type_coverage': '主力户型覆盖率', 'main_type_area_coverage': '主力面积覆盖率', 'finish_building_date_coverage': '建成年代覆盖率', 'all_area_coverage': '占地面积覆盖率', 'build_area_coverage': '建筑面积覆盖率', 'consumption_rating_coverage': '财力评级覆盖率', 'greening_rate_coverage': '绿化率覆盖率', 'volume_rate_coverage': '容积率覆盖率'})
output_date = dateutils.format_date(dateutils.datetime.datetime.now())
aim_file_name = aim_path + "/" + output_date + '覆盖率统计.xlsx'
ret_df.to_excel(aim_file_name, index=False)