From 452334f320fcaee3ac520c700afe07a7cf58e78a Mon Sep 17 00:00:00 2001 From: "shenjian@fangjia.com" Date: Wed, 14 Dec 2022 14:10:30 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E7=89=A9=E4=B8=9A=E8=B4=B9?= =?UTF-8?q?=E8=AF=84=E7=BA=A7=E4=B8=AD=E4=B8=8D=E5=90=88=E7=90=86?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../business/community/estate_charge_ranking.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/dags/business/business/community/estate_charge_ranking.py b/dags/business/business/community/estate_charge_ranking.py index fcb5f2f..db6489a 100644 --- a/dags/business/business/community/estate_charge_ranking.py +++ b/dags/business/business/community/estate_charge_ranking.py @@ -1,13 +1,12 @@ """ 物业费等级计算 """ -from goojia_utils import ElasticSearchClient, nextcloudutils, dingutils, areautils +from goojia_utils import ElasticSearchClient, nextcloudutils import pandas as pd import logging import os from elasticsearch import helpers import matplotlib.pyplot as plt -import numpy as np from sklearn.mixture import GaussianMixture from sklearn.preprocessing import QuantileTransformer @@ -42,7 +41,7 @@ def gmm_train(total_rate, consumption_df, source, target): # 高斯混合模型 city_info = consumption_df.loc[0, 'city'] if city_info in reasonable_dict and reasonable_dict[city_info] == '不合理': - gmm = GaussianMixture(n_components=total_rate, max_iter=200, n_init=5).fit(consumption_df[[source]]) + gmm = GaussianMixture(n_components=total_rate, covariance_type='tied', max_iter=200, n_init=10).fit(consumption_df[[source]]) else: gmm = GaussianMixture(n_components=total_rate).fit(consumption_df[[source]]) consumption_df['cluster'] = gmm.predict(consumption_df[[source]]) @@ -83,8 +82,10 @@ def calc_estate_charge_rating(community_summary_df): count = 0 if len(df) < 5: - return [] - df = gmm_train(5, df, source, target) + # 对于样本低于5的直接排名 + df[target] = df['estate_charge'].rank(method='dense', ascending=False).astype(int) + else: + df = gmm_train(5, df, source, target) # 批量更新 for index, item in df.iterrows(): row = dict()