pandas缺失值的均值填充

pandas缺失值的均值填充

读入数据

import pandas as pd
import numpy as np

bj_data = pd.read_csv("北京地区信息.csv",encoding='GBK')

缺失值填充

# bj_data.head(15)
#检测是否有重复行并删除
bj_data.drop_duplicates(keep='first',inplace=True)
#检测是否有缺失值并按均值填充
for column in list(bj_data.columns[bj_data.isnull().sum() > 0]):
    mean_val = bj_data[column].mean()
    bj_data[column].fillna(mean_val, inplace=True)
bj_data