From 70a6904738e19d902c6ddb62c75154ef76d870b8 Mon Sep 17 00:00:00 2001 From: "shenjian@fangjia.com" Date: Tue, 22 Nov 2022 10:59:10 +0800 Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=A2=9E=E8=B4=A2=E5=8A=9B=E8=AF=84?= =?UTF-8?q?=E7=BA=A7=E5=88=86=E5=B8=83=E5=9B=BE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../business/community/consumption.py | 32 ++++++++++++++++++- requirements.txt | 1 - 2 files changed, 31 insertions(+), 2 deletions(-) diff --git a/dags/business/business/community/consumption.py b/dags/business/business/community/consumption.py index e0d5eab..4823992 100644 --- a/dags/business/business/community/consumption.py +++ b/dags/business/business/community/consumption.py @@ -1,19 +1,30 @@ """ 月消费潜力、评级计算 """ -from goojia_utils import ElasticSearchClient, dateutils +from goojia_utils import ElasticSearchClient, dateutils, nextcloudutils, dingutils import pandas as pd import numpy as np import logging +import os +import requests from elasticsearch import helpers from sklearn.mixture import GaussianMixture +from matplotlib import pyplot log = logging.getLogger(__name__) es206_client = ElasticSearchClient(host='192.168.0.206') index_name = "community_summary" path = "/opt/airflow/dags/repo/dags/business/business/community/data" +save_path_prefix = "/home/airflow/data/community" + +save_png_path = save_path_prefix + "/consumption_rating" +if not os.path.exists(save_png_path): + os.makedirs(save_png_path) + +nextcloud_aim_file_path = '共享/财力评级/财力评级分布图' + factor_df = pd.read_excel(path + '/财力评级极值设置.xlsx') factor_dict = dict() @@ -23,6 +34,8 @@ for index, item in factor_df.iterrows(): factor_dict[item['city']] = {'min_total_price': item['min_total_price'], 'max_total_price': item['max_total_price'], 'min_estate_charge': item['min_estate_charge'], 'max_estate_charge': item['max_estate_charge'], \ 'min_avg_cost': item['min_avg_cost'], 'max_avg_cost': item['max_avg_cost']} + + def calc_consumption_potential(city): """ 计算消费潜力 @@ -137,4 +150,21 @@ def sync(city=None): calc_consumption_rating(community_summary_df) +def save_png(city=None): + """ + 生成财力评级图表 + """ + sql = "select id, city, region, name, consumption_rating from community_summary" + if pd.notna(city): + sql += " where city='" + city + "'" + community_summary_df = es206_client.scan_by_sql_to_data_frame(sql) + + for city in community_summary_df['city'].unique(): + community_summary_df[(community_summary_df['consumption_rating'].notna()) & (community_summary_df['city'] == city)]['consumption_rating'].hist(bins=100) + pyplot.savefig(save_png_path + "/" + city + ".png") + + sync() +save_png() +nextcloudutils.up_to_nextcloud(save_png_path, nextcloud_aim_file_path) +dingutils.send_text("【分布图生成完毕】财力评级已完成, 请点击 https://nextcloud.fangjia.com/s/CQdTiH9zW4tFs7T 查看分布图", "c7ac6c86bfbe49a95e30a68616c4d784ae7781c715430dc9c5f6b46d3e6ebd78") diff --git a/requirements.txt b/requirements.txt index 42f474e..71f7665 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,3 @@ -nextcloud-api-wrapper elasticsearch==7.11.0 transbigdata==0.4.15 pykalman==0.9.5