`Imputer`后$X$少了一列

很有可能某一列是全是NaN，所以自动删除了。 对的，count一下就好了。

其他不想管的问题。

---

BTW, if I use train_fea_imputed = imp.fit_transform(train_fea), the code works fine, but train_fea_imputed return an array with 1 dimension less than train_fea

• python - sklearn Imputer() returned features does not fit in fit function - Stack Overflow

修改axis = 1

In [3]: Imputer?
axis : integer, optional (default=0)
    The axis along which to impute.

    - If `axis=0`, then impute along columns.

跟这个问题不想管。

• python - How to prevent sklearn Imputer(missing_values=“NaN”, strategy=“mean”, axis=0).fit_transform(data) from removing columns with only NA in them - Bioinformatics Stack Exchange 未解决。

• python - Know feature names after imputation - Stack Overflow 未解决。