美团中间表改造

This commit is contained in:
shenjian@fangjia.com
2023-03-20 11:38:48 +08:00
parent 11d76204a7
commit 7c99f1b0ac
6 changed files with 82 additions and 14 deletions
+44
View File
@@ -0,0 +1,44 @@
CREATE TABLE tmp.mt_community
(
id String COMMENT '小区ID',
city String COMMENT '城市',
region String COMMENT '区域',
name String COMMENT '名称',
alias String COMMENT '别名',
address String COMMENT '地址',
addr_alias String COMMENT '地址别名',
avg_price Nullable(INT) COMMENT '均价',
rent_price Nullable(INT) COMMENT '平米租金',
lng Nullable(Float32) COMMENT '经度',
lat Nullable(Float32) COMMENT '纬度',
estate_type2 String COMMENT '物业类型',
block String COMMENT '板块',
loop_line_info String COMMENT '环线',
business_quarter String COMMENT '商圈',
households String COMMENT '户数',
property_fee String COMMENT '物业费',
car_site_count String COMMENT '停车位',
property_life String COMMENT '产权年限',
house_property String COMMENT '产权性质',
all_area String COMMENT '占地面积',
build_area String COMMENT '建筑面积',
plot_ratio String COMMENT '容积率',
landscaping_ratio String COMMENT '绿化率',
property_type String COMMENT '物业类型',
build_type String COMMENT '建筑类型',
build_structure String COMMENT '建筑结构',
finish_building_date String COMMENT '建成年代',
developer String COMMENT '开发商',
house_type String COMMENT '户型',
house_area String COMMENT '房型建筑面积',
deal_num Nullable(INT) COMMENT '近一年成交量',
district_facilitys String COMMENT '周边配套数量字段',
school Nullable(INT) COMMENT '学校数量',
market Nullable(INT) COMMENT '商场数量',
subway Nullable(INT) COMMENT '地铁数量',
bank Nullable(INT) COMMENT '银行数量',
hospital Nullable(INT) COMMENT '医院数量',
status INT COMMENT '0 正常 1 删除',
m_date DateTime('Asia/Shanghai') default now() COMMENT '更新时间'
) ENGINE ReplacingMergeTree(m_date)
PARTITION BY city PRIMARY KEY (city, region, name) ORDER BY (city, region, name);
+8 -3
View File
@@ -1,13 +1,14 @@
"""
小区属性导出
"""
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, commutils
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, commutils, ClickHouseClient
import pandas as pd
import datetime
import os
import sys
seaweed_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed')
tmp_ck = ClickHouseClient(database='tmp')
path = "/home/airflow/data/mt"
if not os.path.exists(path):
@@ -74,5 +75,9 @@ seaweed_new_result_df = seaweed_new_result_df.rename(columns={'_id': 'id', 'mapp
'cubage_percent' : 'plot_ratio', 'virescence_percent': 'landscaping_ratio', 'estate_type2': 'property_type',
'main_type': 'house_type', 'main_type_area': 'house_area'})
seaweed_new_result_df.to_csv(path + '/FJW_COMM_' + output_date + '.csv',
sep='@', encoding='utf-8', index=False)
seaweed_new_result_df.to_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8', index=False)
ck_delete_sql = "ALTER TABLE tmp.mt_community DELETE WHERE 1=1 "
tmp_ck.execute(ck_delete_sql)
tmp_ck.to_sql_plus(seaweed_new_result_df, 'mt_community')
+2 -1
View File
@@ -10,11 +10,12 @@ import requests
path = "/home/airflow/data/mt"
clickhouse_client = ClickHouseClient(database='fangjia_stat')
tmp_ck = ClickHouseClient(database='tmp')
output_date = sys.argv[1] if len(sys.argv) > 1 else dateutils.format_date(datetime.datetime.now(), '%Y%m')
print("输出日期" + output_date)
result_df = pd.read_csv(path + '/FJW_COMM_' + output_date + ".csv", sep='@', encoding='utf-8')
result_df = tmp_ck.read_sql_query("select * from tmp.mt_community")
city_df = pd.read_excel('/opt/airflow/dags/repo/dags/mt/supply/data/美团88城市列表.xlsx')
cities = city_df['城市列表'].values.tolist()
+10 -3
View File
@@ -1,7 +1,7 @@
"""
每个小区近一年成交统计
"""
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ElasticSearchClient
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ElasticSearchClient, ClickHouseClient
import pandas as pd
import datetime
import logging
@@ -11,6 +11,7 @@ import sys
es45_client = ElasticSearchClient(host='192.168.0.45')
deal_price_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'deal_price')
district_facilitys_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'district_facilitys')
tmp_ck = ClickHouseClient(database='tmp')
city_df = pd.read_excel('/opt/airflow/dags/repo/dags/mt/supply/data/美团88城市列表.xlsx')
cities = city_df['城市列表'].values.tolist()
@@ -26,7 +27,7 @@ logging.info("日期信息:" + month_start + ' ' + curr_month_start)
month_start_date = dateutils.parse_date(month_start, '%Y%m%d')
curr_month_start_date = dateutils.parse_date(curr_month_start, '%Y%m%d')
result_df = pd.read_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8')
result_df = tmp_ck.read_sql_query("select * from mt_community")
if 'deal_num' in result_df.columns:
result_df = result_df.drop(columns=['deal_num'])
@@ -93,4 +94,10 @@ columns = ['id', 'city', 'region', 'name', 'alias', 'address', 'addr_alias', 'av
'build_structure', 'finish_building_date',
'developer', 'house_type', 'house_area', 'deal_num', 'district_facilitys', 'school', 'market', 'subway',
'bank', 'hospital', 'status']
result_df.to_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8', index=False, columns=columns)
result_save_df = result_df[columns]
ck_delete_sql = "ALTER TABLE tmp.mt_community DELETE WHERE 1=1 "
tmp_ck.execute(ck_delete_sql)
tmp_ck.to_sql_plus(result_save_df, 'mt_community')
+8 -3
View File
@@ -1,13 +1,14 @@
"""
周边配套数量统计
"""
from goojia_utils import MAIN_MONGO_CLIENT, dateutils
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ClickHouseClient
import pandas as pd
import datetime
import logging
import sys
district_facilitys_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'district_facilitys')
tmp_ck = ClickHouseClient(database='tmp')
city_df = pd.read_excel('/opt/airflow/dags/repo/dags/mt/supply/data/美团88城市列表.xlsx')
cities = city_df['城市列表'].values.tolist()
@@ -73,7 +74,8 @@ district_facilitys_new_df = district_facilitys_df[
district_facilitys_new_df = district_facilitys_new_df.rename(columns={'district_name': 'name', 'supermarket': 'market'})
district_facilitys_new_df = district_facilitys_new_df.drop_duplicates(subset=['city', 'region', 'name'], keep='first')
result_df = pd.read_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8')
result_df = tmp_ck.read_sql_query("select * from mt_community")
if 'school' in result_df.columns:
result_df = result_df.drop(columns=['school', 'bank', 'hospital', 'market', 'subway'])
@@ -141,4 +143,7 @@ result_df['bank'].fillna(0, inplace=True)
result_df['hospital'].fillna(0, inplace=True)
result_df['subway'].fillna(0, inplace=True)
result_df.to_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8', index=False)
ck_delete_sql = "ALTER TABLE tmp.mt_community DELETE WHERE 1=1 "
tmp_ck.execute(ck_delete_sql)
tmp_ck.to_sql_plus(result_df, 'mt_community')
+10 -4
View File
@@ -2,17 +2,17 @@
租金、均价导出
"""
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, commutils
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, commutils, ClickHouseClient
import pandas as pd
import datetime
import logging
import sys
import numpy as np
#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')
tmp_ck = ClickHouseClient(database='tmp')
city_df = pd.read_excel('/opt/airflow/dags/repo/dags/mt/supply/data/美团88城市列表.xlsx')
@@ -22,7 +22,8 @@ path = "/home/airflow/data/mt"
output_date = sys.argv[1] if len(sys.argv) > 1 else dateutils.format_date(datetime.datetime.now(), '%Y%m')
seaweed_new_result_df = pd.read_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8')
seaweed_new_result_df = tmp_ck.read_sql_query("select * from mt_community")
if 'avg_price' in seaweed_new_result_df:
seaweed_new_result_df = seaweed_new_result_df.drop(columns=['avg_price', 'rent_price'])
@@ -111,4 +112,9 @@ result_df['ignore_comm'] = None
result_df = result_df.apply(lambda x: format_rent(x), axis=1)
result_df = result_df[result_df['ignore_comm'] != 1]
result_df.to_csv(path + '/FJW_COMM_' + output_date + '.csv', sep='@', encoding='utf-8', index=False)
del result_df['ignore_comm']
ck_delete_sql = "ALTER TABLE tmp.mt_community DELETE WHERE 1=1 "
tmp_ck.execute(ck_delete_sql)
tmp_ck.to_sql_plus(result_df, 'mt_community')