- class ray.data.preprocessors.PowerTransformer(columns: List[str], power: float, method: str = 'yeo-johnson')[source]#
Apply a power transform to make your data more normally distributed.
Some models expect data to be normally distributed. By making your data more Gaussian-like, you might be able to improve your model’s performance.
This preprocessor supports the following transformations:
Box-Cox requires all data to be positive.
You need to manually specify the transform’s power parameter. If you choose a bad value, the transformation might not work well.
columns – The columns to separately transform.
power – A parameter that determines how your data is transformed. Practioners typically set
powerbetween \(-2.5\) and \(2.5\), although you may need to try different values to find one that works well.
method – A string representing which transformation to apply. Supports
"box-cox". If you choose
"box-cox", your data needs to be positive. Defaults to
PublicAPI (alpha): This API is in alpha and may change before becoming stable.