smile.feature

Class WinsorScaler

java.lang.Object

smile.feature.FeatureTransform

smile.feature.Scaler

smile.feature.WinsorScaler

public class WinsorScaler
extends Scaler

Scales all numeric variables into the range [0, 1]. If the dataset has outliers, normalization will certainly scale the "normal" data to a very small interval. In this case, the Winsorization procedure should be applied: values greater than the specified upper limit are replaced with the upper limit, and those below the lower limit are replace with the lower limit. Often, the specified range is indicate in terms of percentiles of the original distribution (like the 5th and 95th percentile).

Constructor Summary

Constructors

Constructor and Description
WinsorScaler(double lower, double upper) Constructor.
WinsorScaler(double lower, double upper, boolean copy) Constructor.

Method Summary

Modifier and Type	Method and Description
void	learn(Attribute[] attributes, double[][] data) Learns transformation parameters from a dataset.
java.lang.String	toString()

Methods inherited from class smile.feature.Scaler

transform

Methods inherited from class smile.feature.FeatureTransform

learn, transform

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

WinsorScaler

public WinsorScaler(double lower,
                    double upper)

Constructor. Inplace transformation.

Parameters:

lower - the lower limit in terms of percentiles of the original distribution (say 5th percentile).

upper - the upper limit in terms of percentiles of the original distribution (say 95th percentile).

WinsorScaler

public WinsorScaler(double lower,
                    double upper,
                    boolean copy)

Constructor.

Parameters:

lower - the lower limit in terms of percentiles of the original distribution (say 5th percentile).

upper - the upper limit in terms of percentiles of the original distribution (say 95th percentile).

copy - If false, try to avoid a copy and do inplace scaling instead.

Method Detail

learn

public void learn(Attribute[] attributes,
                  double[][] data)

Description copied from class: FeatureTransform

Learns transformation parameters from a dataset.

Overrides:

learn in class Scaler

Parameters:

attributes - The variable attributes. Of which, numeric variables will be standardized.

data - The training data to learn scaling parameters. The data will not be modified.

toString

public java.lang.String toString()

Overrides:

toString in class Scaler