""" 统计小区数量、近半年第三方均价、近半年成交信息 """ import logging from goojia_utils import MAIN_MONGO_CLIENT, ElasticSearchClient, dateutils import pandas as pd import datetime import os import sys log = logging.getLogger(__name__) city_num = sys.argv[1] if len(sys.argv) > 1 else None if city_num is not None: log.info("输出参数" + city_num) df = pd.DataFrame() if city_num is not None and int(city_num) == 92: df = pd.read_excel('/opt/airflow/dags/repo/dags/stat/evaluate/data/估值92城市数据统计.xlsx') else: df = pd.read_excel('/opt/airflow/dags/repo/dags/stat/evaluate/data/估值数据统计.xlsx') year_month_day = dateutils.format_date(datetime.datetime.now()) path = "/home/airflow/data/evaluate" aim_file_name = path + '/估值数据统计结果' + year_month_day + '.xlsx' if not os.path.exists(path): os.makedirs(path) seaweed_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed') es206_client = ElasticSearchClient(host='192.168.0.206') district_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'district_stat') # 成交 average_statistics_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'average_statistics') # 第三方均价 deal_price_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'deal_price') seaweed_df = pd.DataFrame( list(seaweed_conn.find({'cat': 'district', 'status': 0}, {'city': 1, 'region': 1, 'name': 1, 'mapping_alias': 1}) .batch_size(10000))) seaweed_df = seaweed_df.rename(columns={'mapping_alias': 'alias'}) cities = df[['城市']].drop_duplicates(keep='first')['城市'].values.tolist() def count_stat(): """ 统计小区数量 """ result_df = pd.DataFrame(seaweed_conn.aggregate([ {'$match': {'cat': 'district', 'status': 0}}, {'$group': {'_id': '$city', 'community_count': {'$sum': 1}}} ])) result_rename_df = result_df.rename(columns={'_id': '城市', 'community_count': '小区量'}) new_df = pd.merge(df, result_rename_df, how='left', on=['城市']) new_df.to_excel(aim_file_name, index=False) def third_avg_stat(): """ 近半年有第三方均价小区数量及占比 """ new_df = pd.read_excel(aim_file_name) s_date = dateutils.format_date(dateutils.add_months(dateutils.datetime.datetime.now(), days=-180), fm='%Y%m') average_statistics_df = pd.DataFrame( list(average_statistics_conn.find({'s_date': {'$gte': int(s_date)}, 'category': 'district'}).batch_size(10000))) average_statistics_new_df = average_statistics_df[ ['city', 'name', 'region', '58tc_esf_price', 'cityhouse_esf_price', 'soufang_esf_price', 'lianjia_esf_price', '5i5j_esf_price', 'maitian_esf_price', '365house_esf_price', 'beike_esf_price', 'qfang_esf_price', 'fangtan_esf_price', 'tuboshi_esf_price', 'zhugezhaofang_esf_price', 'zhongyuan_esf_price', 'jiwu_esf_price', 'anjuke_esf_price']] average_statistics_new_df.loc[:, 'has_esf_price'] = average_statistics_new_df['58tc_esf_price'] \ .combine_first(average_statistics_new_df['cityhouse_esf_price']) \ .combine_first(average_statistics_new_df['soufang_esf_price']) \ .combine_first(average_statistics_new_df['lianjia_esf_price']) \ .combine_first(average_statistics_new_df['5i5j_esf_price']) \ .combine_first(average_statistics_new_df['maitian_esf_price']) \ .combine_first(average_statistics_new_df['365house_esf_price']) \ .combine_first(average_statistics_new_df['beike_esf_price']) \ .combine_first(average_statistics_new_df['qfang_esf_price']) \ .combine_first(average_statistics_new_df['fangtan_esf_price']) \ .combine_first(average_statistics_new_df['tuboshi_esf_price']) \ .combine_first(average_statistics_new_df['zhugezhaofang_esf_price']) \ .combine_first(average_statistics_new_df['zhongyuan_esf_price']) \ .combine_first(average_statistics_new_df['jiwu_esf_price']) \ .combine_first(average_statistics_new_df['anjuke_esf_price']) average_statistics_new_df.fillna(0, inplace=True) average_statistics_new_df.loc[:, ['flag']] = average_statistics_new_df['has_esf_price'].apply( lambda x: True if x > 0 else False) average_statistics_new_df = average_statistics_new_df[average_statistics_new_df['flag'] == True] average_statistics_new_df = average_statistics_new_df[['city', 'region', 'name']] average_statistics_new_df = average_statistics_new_df.drop_duplicates(keep='first') average_statistics_new_df['近半年有第三方均价小区数量'] = average_statistics_new_df.groupby('city')['city'].transform('size') average_statistics_new_df = average_statistics_new_df[['city', '近半年有第三方均价小区数量']].drop_duplicates(keep='first') average_statistics_new_df = average_statistics_new_df.rename(columns={'city': '城市'}) new_df = pd.merge(new_df, average_statistics_new_df, how='left', on=['城市']) new_df['近半年有第三方均价小区占比'] = round(new_df['近半年有第三方均价小区数量'] * 100 / new_df['小区量'], 2) new_df.to_excel(aim_file_name, index=False) def deal_stat(): """ 近半年成交量及小区数量统计 """ new_df = pd.read_excel(aim_file_name) # 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=-180)}}, {'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[:, '近半年成交数据量'] = deal_price_seaweed_notnull_df.groupby(['city'])[ 'city'].transform('size') deal_price_half_year_df = deal_price_seaweed_notnull_df[['city', '近半年成交数据量']].drop_duplicates(keep='first') deal_price_half_year_df = deal_price_half_year_df.rename(columns={'city': '城市'}) new_df = pd.merge(new_df, deal_price_half_year_df, how='left', on=['城市']) seaweed_half_year_df = deal_price_seaweed_notnull_df[['city', '_id']] seaweed_half_year_df = seaweed_half_year_df.drop_duplicates(subset=['city', '_id'], keep='first') seaweed_half_year_df['近半年有成交小区数量'] = seaweed_half_year_df.groupby(['city'])['city'].transform('size') seaweed_half_year_rename_df = seaweed_half_year_df[['city', '近半年有成交小区数量']].rename(columns={'city': '城市'}) seaweed_half_year_rename_df = seaweed_half_year_rename_df.drop_duplicates(keep='first') new_df = pd.merge(new_df, seaweed_half_year_rename_df, how='left', on=['城市']) new_df.to_excel(aim_file_name, index=False) log.info("开始统计小区数量、近半年第三方均价、近半年成交信息") count_stat() # third_avg_stat() deal_stat() log.info("完成统计小区数量、近半年第三方均价、近半年成交信息")