手把手教你搞定4類數(shù)據(jù)清洗操作

#?檢查數(shù)據(jù)缺失情況
def?check_missing_data(df):
????return?df.isnull().sum().sort_values(ascending?=?False)
check_missing_data(rawdata)
Income????????????1
Age???????????????1
Online?Shopper????0
Region????????????0
dtype:?int64

test1?=?rawdata.copy()#?將更改前的數(shù)據(jù)進(jìn)行備份
test1?=?test1.head(3)#?提取前三行進(jìn)行測試
test1?=?test1.dropna()#?去除數(shù)據(jù)中有缺失值的行
print(test1)
test1
?????name??????toy??????born
0????Andy??????NaN??????NaN
1????Cindy?????Gun??????1998-12-25
2????Wendy?????Gum??????NaN
test1?=?test1.dropna(axis=0)#?去除數(shù)據(jù)中有缺失值的行
?????name??????toy??????born
1????Cindy?????Gun??????1998-12-25
test1?=?test1.dropna(axis='columns')#?去除數(shù)據(jù)中有缺失值的列
?????name
0????Andy
1????Cindy
2????Wendy
test1?=?test1.dropna(how='all')#?去除數(shù)據(jù)完全缺失的行
test1?=?test1.dropna(thresh=2)#?保留行中至少有兩個(gè)值的行
test1?=?test1.dropna(how='any')#?去除數(shù)據(jù)中含有缺失值的行
test1?=?test1.dropna(how='any',subset=['toy'])#?去除toy列中含有缺失值的行
test1.dropna(inplace=True)#?在這個(gè)變量名中直接保存結(jié)果

test1?=?test1.fillna(test1.mean())#?用均值填充缺失值
test1?=?test1.fillna(test1.median())#?用中位數(shù)填充缺失值
test1?=?test1.fillna(test1.mode())#?用眾數(shù)填充缺失值

dataset.isna().sum()??????????#?統(tǒng)計(jì)各列缺失值情況

#?設(shè)定填充方式為平均值填充
imputer?=?SimpleImputer(missing_values=np.nan,?strategy='mean')??
#?選取目標(biāo)列
imputer?=?imputer.fit(rawdata.iloc[:,1:3])?
#?對計(jì)算結(jié)果進(jìn)行填充
rawdata.iloc[:,1:3]?=?imputer.transform(rawdata.iloc[:,1:3])?
#?調(diào)整數(shù)據(jù)
rawdata.iloc[:,1:3]?=?rawdata.iloc[:,1:3].round(0).astype(int)?

rawdata.corr()?????#?相關(guān)性矩陣?

rawdata.cov()??????#?協(xié)方差矩陣