1from sklearn.preprocessing import PowerTransformer
2# power transform the raw data
3power = PowerTransformer(method='yeo-johnson', standardize=True)
4data_trans = power.fit_transform(data)
5
6
7========================ADDITIONAL INFORMATION==================================
8## Few Important things to keep in mind
9There are two popular approaches(method) for such automatic power transforms;
10* method='box-cox'
11 It is a power transform that assumes the values of the input variable
12 to which it is applied are strictly positive. That means 0 and negative
13 values are not supported.
14* method='yeo-johnson'
15 Unlike the Box-Cox transform, it does not require the values
16 for each input variable to be strictly positive. It supports
17 zero values and negative values. This means we can apply it to
18 our dataset without scaling it first.