直接上代码来说明问题:
import pandas as pd
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import LabelBinarizer
from sklearn.preprocessing import MultiLabelBinarizer
# 创建测试数据
testdata=pd.DataFrame({'pet':['cat','dog','dog','fish'],
'age':[4,6,3,3],'salary':[4,5,1,1]})
print(testdata)
输出结果:
#把他们全都二值化,进行 one-hot 编码.
OneHotEncoder(sparse=False).fit_transform(testdata.age) #报错