Yeo-Johnson变换

1 为什么要进行Yeo-Johnson变换

To better meet the assumptions of normality and homogenous variances

Yeo-Johnson transformation provides a powerful way of reducing skewness and can be applied to variables that include negative values【1】

参考文献：【1】Global effects of soil and climate on leaf photosynthetic traits and rates 

备注：

help(preprocessing.scale)

scale(X, axis=0, with_mean=True, with_std=True, copy=True)

axis=0:默认是按照每一个特征(即按照列)进行标准化；

axis=1:则为行，按照样本进本进行标准化

代码：

import numpyas np

from sklearn.preprocessingimport PowerTransformer

pt =PowerTransformer(method='yeo-johnson', standardize=True, copy=True)

data = [[1, 2], [3, 2], [4, 5]]

print(pt.fit(data))

PowerTransformer()

print(pt.lambdas_)

print(pt.transform(data))