Package weka.classifiers.trees.j48

Class SplitCriterion

java.lang.Object

weka.classifiers.trees.j48.SplitCriterion

All Implemented Interfaces:

Serializable, RevisionHandler

Direct Known Subclasses:

EntropyBasedSplitCrit

public abstract class SplitCriterion
extends Object
implements Serializable, RevisionHandler

Abstract class for computing splitting criteria with respect to distributions of class values.

Version:

$Revision: 8034 $

Author:

Eibe Frank (eibe@cs.waikato.ac.nz)

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
SplitCriterion()

Method Summary

Modifier and Type	Method	Description
double	splitCritValue(Distribution bags)	Computes result of splitting criterion for given distribution.
double	splitCritValue(Distribution train, Distribution test)	Computes result of splitting criterion for given training and test distributions.
double	splitCritValue(Distribution train, Distribution test, int noClassesDefault)	Computes result of splitting criterion for given training and test distributions and given number of classes.
double	splitCritValue(Distribution train, Distribution test, Distribution defC)	Computes result of splitting criterion for given training and test distributions and given default distribution.

Methods inherited from class java.lang.Object

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

Methods inherited from interface weka.core.RevisionHandler

getRevision

Constructor Details

SplitCriterion

public SplitCriterion()

Method Details

splitCritValue

public double splitCritValue(Distribution bags)

Computes result of splitting criterion for given distribution.

Returns:

value of splitting criterion. 0 by default

splitCritValue

public double splitCritValue(Distribution train,
 Distribution test)

Computes result of splitting criterion for given training and test distributions.

Returns:

value of splitting criterion. 0 by default

splitCritValue

public double splitCritValue(Distribution train,
 Distribution test,
 int noClassesDefault)

Computes result of splitting criterion for given training and test distributions and given number of classes.

Returns:

value of splitting criterion. 0 by default

splitCritValue

public double splitCritValue(Distribution train,
 Distribution test,
 Distribution defC)

Computes result of splitting criterion for given training and test distributions and given default distribution.

Returns:

value of splitting criterion. 0 by default