cc.mallet.classify
Class C45Trainer

java.lang.Object
  cc.mallet.classify.ClassifierTrainer<C45>
      cc.mallet.classify.C45Trainer

All Implemented Interfaces:

Boostable

public class C45Trainer
extends ClassifierTrainer<C45>
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

Nested Class Summary

Nested classes/interfaces inherited from class cc.mallet.classify.ClassifierTrainer

ClassifierTrainer.ByActiveLearning<C extends Classifier>, ClassifierTrainer.ByIncrements<C extends Classifier>, ClassifierTrainer.ByInstanceIncrements<C extends Classifier>, ClassifierTrainer.ByOptimization<C extends Classifier>, ClassifierTrainer.Factory<CT extends ClassifierTrainer<? extends Classifier>>

Field Summary

Fields inherited from class cc.mallet.classify.ClassifierTrainer

finishedTraining, validationSet

Constructor Summary

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

C45	getClassifier()
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)
C45	train(InstanceList trainingList)

Methods inherited from class cc.mallet.classify.ClassifierTrainer

getValidationInstances, isFinishedTraining, setValidationInstances

Methods inherited from class java.lang.Object

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

getClassifier

public C45 getClassifier()

Specified by:

getClassifier in class ClassifierTrainer<C45>

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 C45 train(InstanceList trainingList)

Specified by:

train in class ClassifierTrainer<C45>