机器学习-记录错误

编码出错原因

ordinal_encoder = OrdinalEncoder()
housing_cat_encoded = ordinal_encoder.fit_transform(housing.ocean_proximity)
housing_cat_encoded[:10]

提示出错

array=['INLAND' 'NEAR OCEAN' 'INLAND' ... '<1H OCEAN' '<1H OCEAN' 'INLAND'].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

原因

sklearn 的新版本中，OrdinalEncoder 的输入必须是 2D array，而 housing_cat 返回的 是 1D array。改正方法：

ordinal_encoder = OrdinalEncoder()
housing_cat_encoded = ordinal_encoder.fit_transform(housing[['ocean_proximity']])
housing_cat_encoded[:10]

输出结果

0,1.0
1,4.0
2,1.0
3,4.0
4,0.0
5,3.0
6,0.0
7,0.0
8,0.0
9,0.0