版本修改

This commit is contained in:
王文艳
2026-07-22 16:06:26 +08:00
parent eddb99892a
commit a11383312e
+230 -238
View File
@@ -9,244 +9,8 @@ import logging
log = logging.getLogger(__name__)
server_area_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'server_area')
seaweed_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed')
district_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_stat')
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]
# 昆玉无小区
city_df = city_df[city_df['city'] != '昆玉'].reset_index(drop=True)
seaweed_df = pd.DataFrame(
list(seaweed_conn.find({'cat': 'district', 'status': 0},
{'city': 1, 'region': 1, 'name': 1, 'alias': 1, 'addr_alias': 1})
.batch_size(100000)))
path = "/opt/airflow/dags/repo/dags/business/business/community/data"
aim_path = "/home/airflow/data/stat"
if not os.path.exists(aim_path):
os.makedirs(aim_path)
ret_df = pd.read_excel(path + '/财力评级分布情况20221215.xlsx')
for index, item in city_df.iterrows():
city = item['city']
region_df = seaweed_df[(seaweed_df['city'] == city)].copy()
alias_count = 0
addr_count = 0
seaweed_count = 0
# 楼盘数量
city_df.loc[index, 'community_count'] = len(region_df)
if len(region_df) == 0:
log.error(f"该城市{city}小区数量为0")
for index1, item1 in region_df.iterrows():
flag = True
if type(item1['alias']) == list:
if len(item1['alias']) > 0:
alias_count += len(item1['alias'])
seaweed_count += 1
flag = False
if type(item1['addr_alias']) == list:
if len(item1['addr_alias']) > 0:
addr_count += len(item1['addr_alias'])
if len(item1['addr_alias']) > 0 and flag is True:
seaweed_count += 1
# 楼盘别名总数
city_df.loc[index, 'alias_count'] = alias_count
# 地址别名数量
city_df.loc[index, 'addr_alias_count'] = addr_count
# 有别名小区量【存在楼盘别名或地址别名】
city_df.loc[index, 'exist_alias_community_count'] = seaweed_count
# 【已过期】
# #### 1. 小区数量
# result_df = pd.DataFrame(list(seaweed_conn.aggregate([
# {'$match': {'cat': 'district', 'status': 0}},
# {'$group': {'_id': "$city", 'community_count': {'$sum': 1}}}])))
#
#
# result_df = result_df.rename(columns={'_id': 'city'})
# df = pd.merge(result_df, city_df, how='right', on='city')
# df.fillna(0, inplace=True)
# 有别名小区量 该方式统计不准,可能存在[]情况也算了
# alias_df = pd.DataFrame(list(seaweed_conn.aggregate([
# {'$match': {'cat': 'district', 'status': 0, 'mapping_alias': {'$ne': None}}},
# {'$group': {'_id': "$city", 'alias_count': {'$sum': 1}}}])))
# alias_df = alias_df.rename(columns={'_id': 'city'})
# df = pd.merge(df, alias_df, how='left', on=['city'])
df = city_df.copy()
# 主力户型
main_type_count = pd.DataFrame(list(seaweed_conn.aggregate([
{'$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': "$city", 'estate_type_count': {'$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
# 物业费
df['estate_charge_count'] = None
# 人均消费
df['avg_cost_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 estate_charge>0 "
estate_charge_num = es206_client.search_by_sql(sql)['hits']['total']['value']
df.loc[index, 'estate_charge_count'] = estate_charge_num
sql = f"select count(*) from community_summary where city='{curr_city}' and avg_cost>0 "
avg_cost_count = es206_client.search_by_sql(sql)['hits']['total']['value']
df.loc[index, 'avg_cost_count'] = avg_cost_count
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']
df['estate_charge_coverage'] = df['estate_charge_count'] * 100 / df['community_count']
df['avg_cost_coverage'] = df['avg_cost_count'] * 100 / df['community_count']
##### 2. 近一年成交量
# 小区别名升级为单独df
actions = list()
for index, item in seaweed_df.iterrows():
if type(item['alias']) == list:
for name in item['alias']:
actions.append({'_id': item['_id'], 'city': item['city'], 'name': name, 'region': item['region']})
alias_df = pd.DataFrame(actions)
seaweed_alias_df = pd.concat([seaweed_df[['_id', 'city', 'region', 'name']], alias_df])
deal_price_df = pd.DataFrame(list(deal_price_conn.find(
{'trade_date': {'$gte': dateutils.add_months(dateutils.datetime.datetime.now(), days=-365)}},
{'city': 1, 'region': 1, 'district_name': 1, '_id': 0}).batch_size(10000)))
deal_price_df = deal_price_df.rename(columns={'district_name': 'name'})
deal_price_seaweed_df = pd.merge(deal_price_df, seaweed_alias_df, how='left', on=['city', 'region', 'name'])
# 剔除没有配到的小区
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(df, deal_price_half_year_df, how='left', on=['city'])
# #### 2. 均价数量
avg_price_df = commutils.get_avg_price()
rent_price_df = commutils.get_rent_price()
avg_price_df['avg_price_count'] = avg_price_df.groupby(by=['city'])['_id'].transform('count')
rent_price_df['sqmetre_rent_count'] = rent_price_df.groupby(by=['city'])['_id'].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 = 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']
df.fillna(0, inplace=True)
df['community_count'] = df['community_count'].astype(int)
df['avg_price_count'] = df['avg_price_count'].astype(int)
df['sqmetre_rent_count'] = df['sqmetre_rent_count'].astype(int)
df['one_year_deal'] = df['one_year_deal'].astype(int)
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, '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, 'estate_charge_coverage': 2, 'avg_cost_coverage': 2, 'consumption_rating_coverage': 2, 'greening_rate_coverage': 2, 'volume_rate_coverage': 2})
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', 'estate_charge_coverage', 'avg_cost_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
clickHouseClient.execute(
"ALTER TABLE fangjia_stat.community_coverage_stat DELETE WHERE weekend = toDate('" + dateutils.format_date(dateutils.datetime.datetime.now(), '%Y-%m-%d') + "')")
clickHouseClient.to_sql(df, table='community_coverage_stat', if_exists='insert', order_by='weekend')
# 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",
'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', 'estate_charge_coverage': '物业费覆盖率', 'avg_cost_coverage': '人均消费覆盖率', '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)
# https://nextcloud.fangjia.com/s/3aw663fy9BbiBeLji'bie
# ================== 辅助上传函数(全局定义,供 main 调用) ==================
def up_to_nextcloud():
"""
@@ -256,8 +20,236 @@ def up_to_nextcloud():
NEXTCLOUD_URL = "https://nextcloud.fangjia.com"
NEXTCLOUD_USERNAME = "shenjian@fangjia.com"
NEXTCLOUD_PASSWORD = "goojia123456"
# 使用运行时生成的 output_date 和 aim_file_name 全局变量
aim_file_path = '共享/统计/常用覆盖率统计' + output_date + '.xlsx'
nxc = NextCloud(endpoint=NEXTCLOUD_URL, user=NEXTCLOUD_USERNAME, password=NEXTCLOUD_PASSWORD, json_output=True)
nxc.upload_file(aim_file_name, aim_file_path)
up_to_nextcloud()
# ================== 🛡️ 安全运行入口 ==================
if __name__ == "__main__":
# 1. 延迟初始化数据库连接(避开 Airflow 进程的加载期)
server_area_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'server_area')
seaweed_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed')
district_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_stat')
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')
# 2. 读取城市列表与清洗
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]
# 昆玉无小区
city_df = city_df[city_df['city'] != '昆玉'].reset_index(drop=True)
# 3. 巨量 MongoDB 查询与路径准备
seaweed_df = pd.DataFrame(
list(seaweed_conn.find({'cat': 'district', 'status': 0},
{'city': 1, 'region': 1, 'name': 1, 'alias': 1, 'addr_alias': 1})
.batch_size(100000)))
path = "/opt/airflow/dags/repo/dags/business/business/community/data"
aim_path = "/home/airflow/data/stat"
if not os.path.exists(aim_path):
os.makedirs(aim_path)
ret_df = pd.read_excel(path + '/财力评级分布情况20221215.xlsx')
# 4. 双层大循环处理小区与别名
for index, item in city_df.iterrows():
city = item['city']
region_df = seaweed_df[(seaweed_df['city'] == city)].copy()
alias_count = 0
addr_count = 0
seaweed_count = 0
# 楼盘数量
city_df.loc[index, 'community_count'] = len(region_df)
if len(region_df) == 0:
log.error(f"该城市{city}小区数量为0")
for index1, item1 in region_df.iterrows():
flag = True
if type(item1['alias']) == list:
if len(item1['alias']) > 0:
alias_count += len(item1['alias'])
seaweed_count += 1
flag = False
if type(item1['addr_alias']) == list:
if len(item1['addr_alias']) > 0:
addr_count += len(item1['addr_alias'])
if len(item1['addr_alias']) > 0 and flag is True:
seaweed_count += 1
# 楼盘别名总数
city_df.loc[index, 'alias_count'] = alias_count
# 地址别名数量
city_df.loc[index, 'addr_alias_count'] = addr_count
# 有别名小区量【存在楼盘别名或地址别名】
city_df.loc[index, 'exist_alias_community_count'] = seaweed_count
df = city_df.copy()
# 5. 主力属性的多项重度 MongoDB Aggregation 统计
# 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_type_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']
# 6. 人均/财力等 Elasticsearch 批量循环查询
df['total_price_count'] = None
df['estate_charge_count'] = None
df['avg_cost_count'] = None
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 estate_charge>0 "
estate_charge_num = es206_client.search_by_sql(sql)['hits']['total']['value']
df.loc[index, 'estate_charge_count'] = estate_charge_num
sql = f"select count(*) from community_summary where city='{curr_city}' and avg_cost>0 "
avg_cost_count = es206_client.search_by_sql(sql)['hits']['total']['value']
df.loc[index, 'avg_cost_count'] = avg_cost_count
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']
df['estate_charge_coverage'] = df['estate_charge_count'] * 100 / df['community_count']
df['avg_cost_coverage'] = df['avg_cost_count'] * 100 / df['community_count']
# 7. 近一年成交量 MongoDB 加载
actions = list()
for index, item in seaweed_df.iterrows():
if type(item['alias']) == list:
for name in item['alias']:
actions.append({'_id': item['_id'], 'city': item['city'], 'name': name, 'region': item['region']})
alias_df = pd.DataFrame(actions)
seaweed_alias_df = pd.concat([seaweed_df[['_id', 'city', 'region', 'name']], alias_df])
deal_price_df = pd.DataFrame(list(deal_price_conn.find(
{'trade_date': {'$gte': dateutils.add_months(dateutils.datetime.datetime.now(), days=-365)}},
{'city': 1, 'region': 1, 'district_name': 1, '_id': 0}).batch_size(10000)))
deal_price_df = deal_price_df.rename(columns={'district_name': 'name'})
deal_price_seaweed_df = pd.merge(deal_price_df, seaweed_alias_df, how='left', on=['city', 'region', 'name'])
# 剔除没有配到的小区
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(df, deal_price_half_year_df, how='left', on=['city'])
# 8. 均价租金统计
avg_price_df = commutils.get_avg_price()
rent_price_df = commutils.get_rent_price()
avg_price_df['avg_price_count'] = avg_price_df.groupby(by=['city'])['_id'].transform('count')
rent_price_df['sqmetre_rent_count'] = rent_price_df.groupby(by=['city'])['_id'].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 = 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']
df.fillna(0, inplace=True)
df['community_count'] = df['community_count'].astype(int)
df['avg_price_count'] = df['avg_price_count'].astype(int)
df['sqmetre_rent_count'] = df['sqmetre_rent_count'].astype(int)
df['one_year_deal'] = df['one_year_deal'].astype(int)
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, '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, 'estate_charge_coverage': 2, 'avg_cost_coverage': 2, 'consumption_rating_coverage': 2, 'greening_rate_coverage': 2, 'volume_rate_coverage': 2})
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', 'estate_charge_coverage', 'avg_cost_coverage', 'consumption_rating_coverage', 'greening_rate_coverage', 'volume_rate_coverage']]
# 9. ClickHouse 写入与去重操作
df['weekend'] = dateutils.datetime.datetime.now()
clickHouseClient.execute(
"ALTER TABLE fangjia_stat.community_coverage_stat DELETE WHERE weekend = toDate('" + dateutils.format_date(dateutils.datetime.datetime.now(), '%Y-%m-%d') + "')")
clickHouseClient.to_sql(df, table='community_coverage_stat', if_exists='insert', order_by='weekend')
# 10. 文件输出与 NextCloud 上传
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",
'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', 'estate_charge_coverage': '物业费覆盖率', 'avg_cost_coverage': '人均消费覆盖率', '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)
up_to_nextcloud()