优化物业费评级中不合理
This commit is contained in:
@@ -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()
|
||||
|
||||
Reference in New Issue
Block a user