weka.classifiers.trees.j48
Class EntropyBasedSplitCrit

java.lang.Object
  |
  +--weka.classifiers.trees.j48.SplitCriterion
        |
        +--weka.classifiers.trees.j48.EntropyBasedSplitCrit

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

EntropySplitCrit, GainRatioSplitCrit, InfoGainSplitCrit

public abstract class EntropyBasedSplitCrit

extends SplitCriterion

"Abstract" class for computing splitting criteria based on the entropy of a class distribution.

Version:

$Revision: 1.5 $

Author:

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

See Also:

Serialized Form

Constructor Summary

EntropyBasedSplitCrit()

Method Summary

double	logFunc(double num) Help method for computing entropy.
double	newEnt(Distribution bags) Computes entropy of distribution after splitting.
double	oldEnt(Distribution bags) Computes entropy of distribution before splitting.
double	splitEnt(Distribution bags) Computes entropy after splitting without considering the class values.

Methods inherited from class weka.classifiers.trees.j48.SplitCriterion

splitCritValue, splitCritValue, splitCritValue, splitCritValue

Methods inherited from class java.lang.Object

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

Constructor Detail

EntropyBasedSplitCrit

public EntropyBasedSplitCrit()

Method Detail

logFunc

public final double logFunc(double num)

Help method for computing entropy.

oldEnt

public final double oldEnt(Distribution bags)

Computes entropy of distribution before splitting.

newEnt

public final double newEnt(Distribution bags)

Computes entropy of distribution after splitting.

splitEnt

public final double splitEnt(Distribution bags)

Computes entropy after splitting without considering the class values.