""" 周边配套数量统计 """ from goojia_utils import MAIN_MONGO_CLIENT, dateutils import pandas as pd import datetime import logging district_facilitys_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'district_facilitys') city_df = pd.read_excel('/opt/airflow/dags/repo/dags/mt/supply/data/美团19城市列表.xlsx') cities = city_df['城市列表'].values.tolist() # 1. 获取「今天」 today = datetime.date.today() # 2. 获取当前月的第一天 first = today.replace(day=1) # 3. 减一天,得到上个月的最后一天 last_month = first - datetime.timedelta(days=1) month_start = last_month.strftime("%Y%m") + '01' curr_month_start = dateutils.format_date(datetime.datetime.now(), '%Y%m') + '01' logging.info(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') path = "/home/airflow/data/mt" district_facilitys_df = pd.DataFrame() district_facilitys_school_df = pd.DataFrame(list(district_facilitys_conn.aggregate([ {'$match': {'school': {'$ne': None}}}, {'$project': {'city': '$city', 'region': '$region', 'district_name': '$district_name', 'school': {'$size': '$school'}}} ]).batch_size(10000))) district_facilitys_school_df = district_facilitys_school_df.drop(columns=['_id']) district_facilitys_supermarket_df = pd.DataFrame(list(district_facilitys_conn.aggregate([ {'$match': {'supermarket': {'$ne': None}}}, {'$project': {'city': '$city', 'region': '$region', 'district_name': '$district_name', 'supermarket': {'$size': '$supermarket'}}} ]).batch_size(10000))) district_facilitys_supermarket_df = district_facilitys_supermarket_df.drop(columns=['_id']) district_facilitys_subway_df = pd.DataFrame(list(district_facilitys_conn.aggregate([ {'$match': {'subway': {'$ne': None}}}, {'$project': {'city': '$city', 'region': '$region', 'district_name': '$district_name', 'subway': {'$size': '$subway'}}} ]).batch_size(10000))) district_facilitys_subway_df = district_facilitys_subway_df.drop(columns=['_id']) district_facilitys_bank_df = pd.DataFrame(list(district_facilitys_conn.aggregate([ {'$match': {'bank': {'$ne': None}}}, {'$project': {'city': '$city', 'region': '$region', 'district_name': '$district_name', 'bank': {'$size': '$bank'}}} ]).batch_size(10000))) district_facilitys_bank_df = district_facilitys_bank_df.drop(columns=['_id']) district_facilitys_hospital_df = pd.DataFrame(list(district_facilitys_conn.aggregate([ {'$match': {'hospital': {'$ne': None}}}, {'$project': {'city': '$city', 'region': '$region', 'district_name': '$district_name', 'hospital': {'$size': '$hospital'}}} ]).batch_size(10000))) district_facilitys_hospital_df = district_facilitys_hospital_df.drop(columns=['_id']) district_facilitys_df = pd.merge(district_facilitys_school_df,district_facilitys_supermarket_df, how='left', on=['city', 'region', 'district_name']) district_facilitys_df = pd.merge(district_facilitys_df,district_facilitys_subway_df, how='left', on=['city', 'region', 'district_name']) district_facilitys_df = pd.merge(district_facilitys_df,district_facilitys_bank_df, how='left', on=['city', 'region', 'district_name']) district_facilitys_df = pd.merge(district_facilitys_df,district_facilitys_hospital_df, how='left', on=['city', 'region', 'district_name']) district_facilitys_new_df = district_facilitys_df[['city', 'region', 'district_name', 'school', 'bank', 'hospital', 'supermarket', 'subway']] 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(subsets=['city', 'region', 'name'], keep='first') result_df = pd.read_csv(path + '/FJW_COMM_' + dateutils.format_date(datetime.datetime.now(), '%Y%m') + '.csv', sep='@', encoding='utf-8') result_df = pd.merge(result_df, district_facilitys_new_df, how='left', on=['city', 'region', 'name']) result_df.loc[:, 'district_facilitys'] = '学校、商场、地铁、银行、医院' # 剔除特别大的 def format_facilitys(x): if type(x['school']) is not int: x.school = None if type(x['bank']) is not int: x.bank = None if type(x['hospital']) is not int: x.hospital = None if type(x['market']) is not int: x.market = None if type(x['subway']) is not int: x.subway = None if x['school'] > 10: x.school = None if x['market'] > 15: x.market = None if x['subway'] > 5: x.subway = None if x['bank'] > 30: x.bank = None if x['hospital'] > 10: x.hospital = None return x result_df = result_df.apply(lambda x: format_facilitys(x), axis=1) result_df.to_csv(path + '/FJW_COMM_' + dateutils.format_date(datetime.datetime.now(), '%Y%m') + '.csv', sep='@', encoding='utf-8', index=False)