edu.umass.cs.mallet.base.classify

Class C45Trainer

java.lang.Object

edu.umass.cs.mallet.base.classify.ClassifierTrainer

edu.umass.cs.mallet.base.classify.C45Trainer

All Implemented Interfaces:

Boostable

public class C45Trainer
extends ClassifierTrainer
implements Boostable

A C4.5 decision tree learner, approximtely. Currently treats all features as continuous-valued, and has no notion of missing values.

This implementation uses MDL for pruning.

J. R. Quinlan
"Improved Use of Continuous Attributes in C4.5"
ftp://ftp.cs.cmu.edu/project/jair/volume4/quinlan96a.ps

J. R. Quinlan and R. L. Rivest
"Inferring Decision Trees Using Minimum Description Length Principle"

Author:

Gary Huang ghuang@cs.umass.edu

Constructor Summary

Constructors

Constructor and Description
C45Trainer() Uses default values: not depth limited tree with a minimum of 2 instances in each leaf node
C45Trainer(boolean doPruning)
C45Trainer(int maxDepth) Construct a depth-limited tree with the given depth limit
C45Trainer(int maxDepth, boolean doPruning)

Method Summary

Modifier and Type	Method and Description
boolean	getDepthLimited()
boolean	getDoPruning()
int	getMaxDepth()
int	getMinNumInsts()
void	setDepthLimited(boolean depthLimited)
void	setDoPruning(boolean doPruning)
void	setMaxDepth(int maxDepth)
void	setMinNumInsts(int minNumInsts)
protected void	splitTree(C45.Node node, int depth)
Classifier	train(InstanceList trainingList, InstanceList validationList, InstanceList testSet, ClassifierEvaluating evaluator, Classifier initialClassifier) Return a new classifier tuned using the three arguments.

Methods inherited from class edu.umass.cs.mallet.base.classify.ClassifierTrainer

main, toString, train, train, train, train

Methods inherited from class java.lang.Object

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

Constructor Detail

C45Trainer

public C45Trainer()

Uses default values: not depth limited tree with a minimum of 2 instances in each leaf node

C45Trainer

public C45Trainer(int maxDepth)

Construct a depth-limited tree with the given depth limit

C45Trainer

public C45Trainer(boolean doPruning)

C45Trainer

public C45Trainer(int maxDepth,
                  boolean doPruning)

Method Detail

setDoPruning

public void setDoPruning(boolean doPruning)

getDoPruning

public boolean getDoPruning()

setDepthLimited

public void setDepthLimited(boolean depthLimited)

getDepthLimited

public boolean getDepthLimited()

setMaxDepth

public void setMaxDepth(int maxDepth)

getMaxDepth

public int getMaxDepth()

setMinNumInsts

public void setMinNumInsts(int minNumInsts)

getMinNumInsts

public int getMinNumInsts()

splitTree

protected void splitTree(C45.Node node,
                         int depth)

train

public Classifier train(InstanceList trainingList,
                        InstanceList validationList,
                        InstanceList testSet,
                        ClassifierEvaluating evaluator,
                        Classifier initialClassifier)

Description copied from class: ClassifierTrainer

Return a new classifier tuned using the three arguments.

Specified by:

train in class ClassifierTrainer

Parameters:

trainingList - examples used to set parameters.

validationList - examples used to tune meta-parameters. May be null.

testSet - examples not examined at all for training, but passed on to diagnostic routines. May be null.

initialClassifier - training process may start from here. The parameters of the initialClassifier are not modified. May be null.