diff --git a/dags/mt/supply/comm.py b/dags/mt/supply/comm.py index a18d34d..1802cf6 100644 --- a/dags/mt/supply/comm.py +++ b/dags/mt/supply/comm.py @@ -5,6 +5,7 @@ from goojia_utils import MAIN_MONGO_CLIENT, dateutils, commutils import pandas as pd import datetime import os +import re seaweed_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed') @@ -37,6 +38,7 @@ def format_seaweed(x): """ try: if str(x.mapping_alias) != 'nan' and x.mapping_alias != None: + # 过滤映射别名,防止含有主名 if x.name in x.mapping_alias: x.mapping_alias.remove(x.name) x.mapping_alias = ','.join(x.mapping_alias) @@ -50,6 +52,25 @@ def format_seaweed(x): x.lng = commutils.format_lat_lng(x.lng) x.lat = commutils.format_lat_lng(x.lat) x.cubage_percent = commutils.format_plot_ratio(x.cubage_percent) + # 过滤房型,大于5房过滤,剔除厅卫 + if 'house_type' in x and str(x['house_type']) != 'nan': + if re.match('[1-6]室', x['house_type']) is None: + x.house_type = None + x.house_area = None + else: + x.house_type = re.sub('(\d+厅)?(\d+厨)?(\d+卫)?', '', x.house_type) + if '1室' in x.house_type: + if x.house_area > 125 or x.house_area < 20: + x.house_area = None + if '2室' in x.house_type: + if x.house_area > 200 or x.house_area < 30: + x.house_area = None + if '3室' in x.house_type: + if x.house_area > 260 or x.house_area < 60: + x.house_area = None + if '4室' in x.house_type: + if x.house_area > 260 or x.house_area < 90: + x.house_area = None if type(x.alias) == str and '@' in x.alias: x.alias = None diff --git a/dags/mt/supply/facilitys.py b/dags/mt/supply/facilitys.py index e4a2e12..5949c0a 100644 --- a/dags/mt/supply/facilitys.py +++ b/dags/mt/supply/facilitys.py @@ -28,53 +28,55 @@ curr_month_start_date = dateutils.parse_date(curr_month_start, '%Y%m%d') path = "/home/airflow/data/mt" district_facilitys_df = pd.DataFrame() -for city in cities: - temp_df = pd.DataFrame( - list(district_facilitys_conn.find({'city': city}, {'city': 1, 'region': 1, 'district_name': 1, 'school': 1, - 'supermarket': 1, 'subway': 1, 'bank': 1, 'hospital': 1}).batch_size(10000))) - district_facilitys_df = pd.concat([district_facilitys_df, temp_df]) +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']) -def count_facilitys(x): - ret = x - try: - if 'school' in x and x['school'] is not None and str(x['school']) != 'nan': - for item in x['school']: - if item is not None: - ret.school = len(item) - if 'supermarket' in x and x['supermarket'] is not None and str(x['supermarket']) != 'nan': - for item in x['supermarket']: - if item is not None: - ret.supermarket = len(item) - if 'subway' in x and x['subway'] is not None and str(x['subway']) != 'nan': - for item in x['subway']: - if item is not None: - ret.subway = len(item) - if 'bank' in x and x['bank'] is not None and str(x['bank']) != 'nan': - for item in x['bank']: - if item is not None: - ret.bank = len(item) - if 'hospital' in x and x['hospital'] is not None and str(x['hospital']) != 'nan': - for item in x['hospital']: - if item is not None: - ret.hospital = len(item) - return ret - except Exception as e: - print(e) - print(x) - return None +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_new_df = district_facilitys_df.apply(lambda x: count_facilitys(x), axis=1) +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_new_df = district_facilitys_new_df[['city', 'region', 'district_name', 'school', 'bank', 'hospital', 'supermarket', 'subway']] +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 @@ -86,6 +88,16 @@ def format_facilitys(x): 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