箱体处理异常值
转载自：https://blog.csdn.net/zhuiqiuuuu/article/details/82721935

import pandas as pd
import numpy as np
from collections import Counter

def detect_outliers(df,n,features):    
	print("开始处理异常值")    
	outlier_indices = []    
	for col in features:        
		Q1 = np.percentile(df[col], 25)        
		Q3 = np.percentile(df[col],75)        
		IQR = Q3 - Q1        
		outlier_step = 1.5 * IQR        
		outlier_list_col = df[(df[col] < Q1 - outlier_step) | (df[col] > Q3 + outlier_step )].index     
   		outlier_indices.extend(outlier_list_col)    
	
	outlier_indices = Counter(outlier_indices)
	multiple_outliers = list( k for k, v in outlier_indices.items() if v > n )    
	return multiple_outliers   

Outliers_to_drop = detect_outliers(data,0,['target_Kwh'])
data = data.drop(Outliers_to_drop,axis=0).reset_index(drop=True)

代码中n表示行异常的次数，即检查的行中，异常的column次数大于n，才被选定。