moa.classifiers.trees

Class HoeffdingAdaptiveTree

java.lang.Object

moa.AbstractMOAObject

moa.options.AbstractOptionHandler

moa.classifiers.AbstractClassifier

moa.classifiers.trees.HoeffdingTree

moa.classifiers.trees.HoeffdingAdaptiveTree

All Implemented Interfaces:

Serializable, Classifier, AWTRenderable, MOAObject, OptionHandler

public class HoeffdingAdaptiveTree
extends HoeffdingTree

Hoeffding Adaptive Tree for evolving data streams.

This adaptive Hoeffding Tree uses ADWIN to monitor performance of branches on the tree and to replace them with new branches when their accuracy decreases if the new branches are more accurate.

See details in:

Adaptive Learning from Evolving Data Streams. Albert Bifet, Ricard Gavaldà. IDA 2009

• Same parameters as HoeffdingTreeNBAdaptive
• -l : Leaf prediction to use: MajorityClass (MC), Naive Bayes (NB) or NaiveBayes adaptive (NBAdaptive).

Version:

$Revision: 7 $

Author:

Albert Bifet (abifet at cs dot waikato dot ac dot nz)

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	HoeffdingAdaptiveTree.AdaLearningNode
static class	HoeffdingAdaptiveTree.AdaSplitNode
static interface	HoeffdingAdaptiveTree.NewNode

Nested classes/interfaces inherited from class moa.classifiers.trees.HoeffdingTree

HoeffdingTree.ActiveLearningNode, HoeffdingTree.FoundNode, HoeffdingTree.InactiveLearningNode, HoeffdingTree.LearningNode, HoeffdingTree.LearningNodeNB, HoeffdingTree.LearningNodeNBAdaptive, HoeffdingTree.Node, HoeffdingTree.SplitNode

Field Summary

Fields

Modifier and Type	Field and Description
protected int	alternateTrees
protected int	prunedAlternateTrees
protected int	switchedAlternateTrees

Fields inherited from class moa.classifiers.trees.HoeffdingTree

activeLeafByteSizeEstimate, activeLeafNodeCount, binarySplitsOption, byteSizeEstimateOverheadFraction, decisionNodeCount, gracePeriodOption, growthAllowed, inactiveLeafByteSizeEstimate, inactiveLeafNodeCount, leafpredictionOption, maxByteSizeOption, memoryEstimatePeriodOption, nbThresholdOption, nominalEstimatorOption, noPrePruneOption, numericEstimatorOption, removePoorAttsOption, splitConfidenceOption, splitCriterionOption, stopMemManagementOption, tieThresholdOption, treeRoot

Fields inherited from class moa.classifiers.AbstractClassifier

classifierRandom, modelContext, randomSeed, randomSeedOption, trainingWeightSeenByModel

Fields inherited from class moa.options.AbstractOptionHandler

classOptionNamesToPreparedObjects, options

Constructor Summary

Constructors

Constructor and Description
HoeffdingAdaptiveTree()

Method Summary

Methods

Modifier and Type	Method and Description
HoeffdingTree.FoundNode[]	filterInstanceToLeaves(weka.core.Instance inst, HoeffdingTree.SplitNode parent, int parentBranch, boolean updateSplitterCounts)
String	getPurposeString() Gets the purpose of this object
double[]	getVotesForInstance(weka.core.Instance inst) Predicts the class memberships for a given instance.
protected HoeffdingTree.LearningNode	newLearningNode(double[] initialClassObservations)
protected HoeffdingTree.SplitNode	newSplitNode(InstanceConditionalTest splitTest, double[] classObservations)
protected HoeffdingTree.SplitNode	newSplitNode(InstanceConditionalTest splitTest, double[] classObservations, int size)
void	trainOnInstanceImpl(weka.core.Instance inst) Trains this classifier incrementally using the given instance. The reason for ...Impl methods: ease programmer burden by not requiring them to remember calls to super in overridden methods.

Methods inherited from class moa.classifiers.trees.HoeffdingTree

activateLearningNode, attemptToSplit, calcByteSize, computeHoeffdingBound, deactivateAllLeaves, deactivateLearningNode, enforceTrackerLimit, estimateModelByteSizes, findLearningNodes, findLearningNodes, getModelDescription, getModelMeasurementsImpl, isRandomizable, measureByteSize, measureTreeDepth, newLearningNode, newNominalClassObserver, newNumericClassObserver, resetLearningImpl

Methods inherited from class moa.classifiers.AbstractClassifier

contextIsCompatible, copy, correctlyClassifies, getAttributeNameString, getAWTRenderer, getClassLabelString, getClassNameString, getDescription, getModelContext, getModelMeasurements, getNominalValueString, getSubClassifiers, modelAttIndexToInstanceAttIndex, modelAttIndexToInstanceAttIndex, prepareForUseImpl, resetLearning, setModelContext, setRandomSeed, trainingHasStarted, trainingWeightSeenByModel, trainOnInstance

Methods inherited from class moa.options.AbstractOptionHandler

discoverOptionsViaReflection, getCLICreationString, getOptions, getPreparedClassOption, getPreparedClassOption, prepareClassOptions, prepareForUse, prepareForUse

Methods inherited from class moa.AbstractMOAObject

copy, measureByteSize, toString

Methods inherited from class java.lang.Object

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

Methods inherited from interface moa.options.OptionHandler

getCLICreationString, getOptions, prepareForUse, prepareForUse

Field Detail

alternateTrees

protected int alternateTrees

prunedAlternateTrees

protected int prunedAlternateTrees

switchedAlternateTrees

protected int switchedAlternateTrees

Constructor Detail

HoeffdingAdaptiveTree

public HoeffdingAdaptiveTree()

Method Detail

getPurposeString

public String getPurposeString()

Description copied from interface: OptionHandler

Gets the purpose of this object

Specified by:

getPurposeString in interface OptionHandler

Overrides:

getPurposeString in class HoeffdingTree

Returns:

the string with the purpose of this object

newLearningNode

protected HoeffdingTree.LearningNode newLearningNode(double[] initialClassObservations)

Overrides:

newLearningNode in class HoeffdingTree

newSplitNode

protected HoeffdingTree.SplitNode newSplitNode(InstanceConditionalTest splitTest,
                                   double[] classObservations)

Overrides:

newSplitNode in class HoeffdingTree

newSplitNode

protected HoeffdingTree.SplitNode newSplitNode(InstanceConditionalTest splitTest,
                                   double[] classObservations,
                                   int size)

Overrides:

newSplitNode in class HoeffdingTree

trainOnInstanceImpl

public void trainOnInstanceImpl(weka.core.Instance inst)

Description copied from class: AbstractClassifier

Trains this classifier incrementally using the given instance.

The reason for ...Impl methods: ease programmer burden by not requiring them to remember calls to super in overridden methods. Note that this will produce compiler errors if not overridden.

Overrides:

trainOnInstanceImpl in class HoeffdingTree

Parameters:

inst - the instance to be used for training

filterInstanceToLeaves

public HoeffdingTree.FoundNode[] filterInstanceToLeaves(weka.core.Instance inst,
                                               HoeffdingTree.SplitNode parent,
                                               int parentBranch,
                                               boolean updateSplitterCounts)

getVotesForInstance

public double[] getVotesForInstance(weka.core.Instance inst)

Description copied from interface: Classifier

Predicts the class memberships for a given instance. If an instance is unclassified, the returned array elements must be all zero.

Specified by:

getVotesForInstance in interface Classifier

Overrides:

getVotesForInstance in class HoeffdingTree

Parameters:

inst - the instance to be classified

Returns:

an array containing the estimated membership probabilities of the test instance in each class