moa.classifiers.rules

Class AbstractAMRules

java.lang.Object

moa.AbstractMOAObject

moa.options.AbstractOptionHandler

moa.classifiers.AbstractClassifier

moa.classifiers.rules.AbstractAMRules

All Implemented Interfaces:

Serializable, Classifier, AWTRenderable, MOAObject, OptionHandler

Direct Known Subclasses:

AMRulesRegressor

public abstract class AbstractAMRules
extends AbstractClassifier

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
IntOption	anomalyNumInstThresholdOption
protected Rule	defaultRule
FlagOption	DriftDetectionOption
IntOption	gracePeriodOption
FloatOption	multivariateAnomalyProbabilityThresholdOption
FlagOption	noAnomalyDetectionOption
static double	NORMAL_CONSTANT
ClassOption	numericObserverOption
FloatOption	pageHinckleyAlphaOption
IntOption	pageHinckleyThresholdOption
protected int	ruleNumberID
protected RuleSet	ruleSet
FloatOption	splitConfidenceOption
protected double[]	statistics
FloatOption	tieThresholdOption
FloatOption	univariateAnomalyprobabilityThresholdOption
FlagOption	unorderedRulesOption
IntOption	VerbosityOption

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
AbstractAMRules()

Method Summary

Methods

Modifier and Type	Method and Description
protected void	debug(String string, int level) Print to console
int	getModelAttIndexToInstanceAttIndex(int index, weka.core.Instance inst)
void	getModelDescription(StringBuilder out, int indent) print GUI learn model
protected Measurement[]	getModelMeasurementsImpl() print GUI evaluate model
double[]	getVotesForInstance(weka.core.Instance instance) getVotesForInstance extension of the instance method getVotesForInstance in moa.classifier.java returns the prediction of the instance.
abstract boolean	isRandomizable() description of the Methods used.
static int	modelAttIndexToInstanceAttIndex(int index, weka.core.Instance inst) Gets the index of the attribute in the instance, given the index of the attribute in the learner.
abstract ErrorWeightedVote	newErrorWeightedVote()
protected abstract Rule	newRule(int ID, RuleActiveLearningNode learningNode, double[] statistics) Rule.Builder() to build an object with the parameters.
abstract RuleActiveLearningNode	newRuleActiveLearningNode(double[] initialClassObservations)
abstract RuleActiveLearningNode	newRuleActiveLearningNode(Rule.Builder builder)
void	PrintRuleSet()
void	resetLearningImpl() Resets this classifier.
void	trainOnInstanceImpl(weka.core.Instance instance) 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.
protected void	VerboseToConsole(weka.core.Instance inst)

Methods inherited from class moa.classifiers.AbstractClassifier

contextIsCompatible, copy, correctlyClassifies, getAttributeNameString, getAWTRenderer, getClassLabelString, getClassNameString, getDescription, getModelContext, getModelMeasurements, getNominalValueString, getPurposeString, getSubClassifiers, 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, 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

Methods inherited from interface moa.MOAObject

measureByteSize

Field Detail

ruleSet

protected RuleSet ruleSet

defaultRule

protected Rule defaultRule

ruleNumberID

protected int ruleNumberID

statistics

protected double[] statistics

NORMAL_CONSTANT

public static final double NORMAL_CONSTANT

splitConfidenceOption

public FloatOption splitConfidenceOption

tieThresholdOption

public FloatOption tieThresholdOption

gracePeriodOption

public IntOption gracePeriodOption

DriftDetectionOption

public FlagOption DriftDetectionOption

pageHinckleyAlphaOption

public FloatOption pageHinckleyAlphaOption

pageHinckleyThresholdOption

public IntOption pageHinckleyThresholdOption

noAnomalyDetectionOption

public FlagOption noAnomalyDetectionOption

multivariateAnomalyProbabilityThresholdOption

public FloatOption multivariateAnomalyProbabilityThresholdOption

univariateAnomalyprobabilityThresholdOption

public FloatOption univariateAnomalyprobabilityThresholdOption

anomalyNumInstThresholdOption

public IntOption anomalyNumInstThresholdOption

unorderedRulesOption

public FlagOption unorderedRulesOption

VerbosityOption

public IntOption VerbosityOption

numericObserverOption

public ClassOption numericObserverOption

Constructor Detail

AbstractAMRules

public AbstractAMRules()

Method Detail

isRandomizable

public abstract boolean isRandomizable()

description of the Methods used. isRandomizable resetLearningImpl newRule // to build an object with the parameters. trainOnInstanceImpl isAnomaly getVotesForInstance getModelMeasurementsImpl getModelDescription // to printout to MOA GUI debug // use debug('string') to printout to console

Returns:

true if the classifier needs a random seed.

newRule

protected abstract Rule newRule(int ID,
           RuleActiveLearningNode learningNode,
           double[] statistics)

Rule.Builder() to build an object with the parameters. If you have an algorithm with many parameters, especially if some of them are optional, it can be beneficial to define an object that represents all of the parameters.

Returns:

trainOnInstanceImpl

public void trainOnInstanceImpl(weka.core.Instance instance)

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.

Specified by:

trainOnInstanceImpl in class AbstractClassifier

Parameters:

instance - the instance to be used for training

getVotesForInstance

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

getVotesForInstance extension of the instance method getVotesForInstance in moa.classifier.java returns the prediction of the instance. Called in EvaluateModelRegression

Parameters:

instance - the instance to be classified

Returns:

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

getModelMeasurementsImpl

protected Measurement[] getModelMeasurementsImpl()

print GUI evaluate model

Specified by:

getModelMeasurementsImpl in class AbstractClassifier

Returns:

an array of measurements to be used in evaluation tasks

getModelDescription

public void getModelDescription(StringBuilder out,
                       int indent)

print GUI learn model

Specified by:

getModelDescription in class AbstractClassifier

Parameters:

out - the stringbuilder to add the description

indent - the number of characters to indent

debug

protected void debug(String string,
         int level)

Print to console

Parameters:

string -

VerboseToConsole

protected void VerboseToConsole(weka.core.Instance inst)

PrintRuleSet

public void PrintRuleSet()

newRuleActiveLearningNode

public abstract RuleActiveLearningNode newRuleActiveLearningNode(Rule.Builder builder)

newRuleActiveLearningNode

public abstract RuleActiveLearningNode newRuleActiveLearningNode(double[] initialClassObservations)

getModelAttIndexToInstanceAttIndex

public int getModelAttIndexToInstanceAttIndex(int index,
                                     weka.core.Instance inst)

resetLearningImpl

public void resetLearningImpl()

Description copied from class: AbstractClassifier

Resets this classifier. It must be similar to starting a new classifier from scratch.

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.

Specified by:

resetLearningImpl in class AbstractClassifier

modelAttIndexToInstanceAttIndex

public static int modelAttIndexToInstanceAttIndex(int index,
                                  weka.core.Instance inst)

Gets the index of the attribute in the instance, given the index of the attribute in the learner.

Parameters:

index - the index of the attribute in the learner

inst - the instance

Returns:

the index in the instance

newErrorWeightedVote

public abstract ErrorWeightedVote newErrorWeightedVote()