smile.feature

Class WinsorScaler

java.lang.Object

smile.feature.Scaler

smile.feature.WinsorScaler

All Implemented Interfaces:

java.io.Serializable, FeatureTransform

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).

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
WinsorScaler(smile.data.type.StructType schema, double[] lo, double[] hi) Constructor.

Method Summary

Modifier and Type	Method and Description
static WinsorScaler	fit(smile.data.DataFrame data) Learns transformation parameters from a dataset with 5% lower limit and 95% upper limit.
static WinsorScaler	fit(smile.data.DataFrame data, double lower, double upper) Learns transformation parameters from a dataset.
static WinsorScaler	fit(double[][] data) Learns transformation parameters from a dataset.
static WinsorScaler	fit(double[][] data, double lower, double upper) Learns transformation parameters from a dataset.
java.lang.String	toString()

Methods inherited from class smile.feature.Scaler

transform, transform, transform

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface smile.feature.FeatureTransform

transform

Constructor Detail

WinsorScaler

public WinsorScaler(smile.data.type.StructType schema,
                    double[] lo,
                    double[] hi)

Constructor.

Parameters:

schema - the schema of data.

lo - the lower bound.

hi - the upper bound.

Method Detail

fit

public static WinsorScaler fit(smile.data.DataFrame data)

Learns transformation parameters from a dataset with 5% lower limit and 95% upper limit.

Parameters:

data - The training data.

fit

public static WinsorScaler fit(smile.data.DataFrame data,
                               double lower,
                               double upper)

Learns transformation parameters from a dataset.

Parameters:

data - The training data.

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).

fit

public static WinsorScaler fit(double[][] data)

Learns transformation parameters from a dataset.

Parameters:

data - The training data.

fit

public static WinsorScaler fit(double[][] data,
                               double lower,
                               double upper)

Learns transformation parameters from a dataset.

Parameters:

data - The training data.

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).

toString

public java.lang.String toString()

Overrides:

toString in class Scaler