Package si.ijs.kt.clus.ext.semisupervised.confidence.normalization

Class Standardization

java.lang.Object

si.ijs.kt.clus.ext.semisupervised.confidence.normalization.Standardization

All Implemented Interfaces:

Normalization

public class Standardization
extends Object
implements Normalization

Standardizes per-target scores to 0.5 mean and 0.125 standard deviation. This ensures that 99% of values will be in [0,1]. The values greater than 1, or smaller than 0, will be clamped to 1, or 0, respectively.

Author:

jurical

Constructor Summary

Constructors

Constructor	Description
Standardization(int nbTargetAttributes)

Method Summary

Modifier and Type	Method	Description
void	normalize(Map<Integer,double[]> perTargetScores)
void	setIsLessBetter(boolean lessIsBetter)	Set to true if less is better, of false if more is better

Methods inherited from class java.lang.Object

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

Constructor Details

Standardization

public Standardization(int nbTargetAttributes)

Method Details

normalize

public void normalize(Map<Integer,double[]> perTargetScores)

Specified by:

normalize in interface Normalization

Parameters:

perTargetScores - Per-target confidence scores

setIsLessBetter

public void setIsLessBetter(boolean lessIsBetter)

Description copied from interface: Normalization

Set to true if less is better, of false if more is better

Specified by:

setIsLessBetter in interface Normalization