原创博文,转载请注明出处!

# OneHotEncoder编码

     OneHotEncoder编码称为“哑编码”或“独热编码”,是将表示分类的数据扩维度,由列向量扩展为稀疏矩阵

# OneHotEncoder例子

  1 # -*- coding: utf-8 -*-
2 from sklearn.preprocessing import OneHotEncoder
3 ohe = OneHotEncoder()
4 ohe.fit([[1],[2],[3],[4],[7],[9]])
5 ohe_transform = ohe.transform([[1],[2],[3],[4],[7],[9]]).toarray()
6 print(ohe_transform)
7 """
8 [[ 1. 0. 0. 0. 0. 0.]
9 [ 0. 1. 0. 0. 0. 0.]
10 [ 0. 0. 1. 0. 0. 0.]
11 [ 0. 0. 0. 1. 0. 0.]
12 [ 0. 0. 0. 0. 1. 0.]
13 [ 0. 0. 0. 0. 0. 1.]]
14 """
04-27 04:35