com.rapidminer.operator.learner.functions.kernel
Class AbstractMySVMLearner

java.lang.Object
  com.rapidminer.tools.AbstractObservable<Operator>
      com.rapidminer.operator.Operator
          com.rapidminer.operator.learner.AbstractLearner
              com.rapidminer.operator.learner.functions.kernel.AbstractKernelBasedLearner
                  com.rapidminer.operator.learner.functions.kernel.AbstractMySVMLearner

All Implemented Interfaces:

ConfigurationListener, PreviewListener, ResourceConsumer, CapabilityProvider, Learner, ParameterHandler, LoggingHandler, Observable<Operator>

Direct Known Subclasses:

JMySVMLearner, MyKLRLearner

public abstract class AbstractMySVMLearner
extends AbstractKernelBasedLearner

This is the abstract superclass for the support vector machine / KLR implementations of Stefan Rüping.

Author:

Ingo Mierswa ingomierswa Exp $

Keywords:

SVM

Field Summary

static int	KERNEL_ANOVA Indicates an anova kernel.
static int	KERNEL_DOT Indicates a linear kernel.
static int	KERNEL_EPANECHNIKOV Indicates a epanechnikov kernel.
static int	KERNEL_GAUSSIAN_COMBINATION Indicates a gaussian combination kernel.
static int	KERNEL_MULTIQUADRIC Indicates a multiquadric kernel.
static int	KERNEL_NEURAL Indicates a neural net kernel.
static int	KERNEL_POLYNOMIAL Indicates a polynomial kernel.
static int	KERNEL_RADIAL Indicates a rbf kernel.
static java.lang.String[]	KERNEL_TYPES The kernels which can be used from RapidMiner for the mySVM / myKLR.
static java.lang.String	PARAMETER_C
static java.lang.String	PARAMETER_CALCULATE_WEIGHTS
static java.lang.String	PARAMETER_CONVERGENCE_EPSILON The parameter name for "Precision on the KKT conditions"
static java.lang.String	PARAMETER_KERNEL_A The parameter name for "The SVM kernel parameter a (neural).
static java.lang.String	PARAMETER_KERNEL_B The parameter name for "The SVM kernel parameter b (neural).
static java.lang.String	PARAMETER_KERNEL_CACHE The parameter name for "Size of the cache for kernel evaluations im MB "
static java.lang.String	PARAMETER_KERNEL_DEGREE The parameter name for "The SVM kernel parameter degree (polynomial, anova, epanechnikov).
static java.lang.String	PARAMETER_KERNEL_GAMMA The parameter name for "The SVM kernel parameter gamma (radial, anova).
static java.lang.String	PARAMETER_KERNEL_SHIFT The parameter name for "The SVM kernel parameter shift (multiquadric).
static java.lang.String	PARAMETER_KERNEL_SIGMA1 The parameter name for "The SVM kernel parameter sigma1 (epanechnikov, gaussian combination, multiquadric).
static java.lang.String	PARAMETER_KERNEL_SIGMA2 The parameter name for "The SVM kernel parameter sigma2 (gaussian combination).
static java.lang.String	PARAMETER_KERNEL_SIGMA3 The parameter name for "The SVM kernel parameter sigma3 (gaussian combination).
static java.lang.String	PARAMETER_KERNEL_TYPE
static java.lang.String	PARAMETER_MAX_ITERATIONS The parameter name for "Stop after this many iterations"
static java.lang.String	PARAMETER_RETURN_OPTIMIZATION_PERFORMANCE The parameter name for "Indicates if final optimization fitness should be returned as performance.
static java.lang.String	PARAMETER_SCALE The parameter name for "Scale the example values and store the scaling parameters for test set.

Fields inherited from interface com.rapidminer.operator.learner.CapabilityProvider

PROPERTY_RAPIDMINER_GENERAL_CAPABILITIES_WARN

Constructor Summary

AbstractMySVMLearner(OperatorDescription description)

Method Summary

boolean	canCalculateWeights() Returns true if this learner is capable of computing attribute weights.
static Kernel	createKernel(int kernelType) Creates a new kernel of the given type.
abstract SVMInterface	createSVM(Attribute label, Kernel kernel, SVMExamples svmExamples, ExampleSet rapidMinerExamples) Creates a new SVM according to the given label.
abstract AbstractMySVMModel	createSVMModel(ExampleSet exampleSet, SVMExamples svmExamples, Kernel kernel, int kernelType) Creates a new SVM model from the given data.
protected Kernel	getKernel() Returns the kernel of this SVM.
PerformanceVector	getOptimizationPerformance() Returns the optimization performance of the best result.
java.util.List<ParameterType>	getParameterTypes() Returns a list of ParameterTypes describing the parameters of this operator.
protected SVMInterface	getSVM() Returns the used SVM.
MetaDataError	getWeightCalculationError(OutputPort weightPort)
AttributeWeights	getWeights(ExampleSet exampleSet) Returns the weights for all features.
Model	learn(ExampleSet exampleSet) Trains a model.
boolean	shouldCalculateWeights() Returns true if the user has specified that weights should be calculated.
boolean	shouldDeliverOptimizationPerformance() Returns the value of the corresponding parameter.
boolean	supportsCapability(OperatorCapability lc) Checks for Learner capabilities.

Methods inherited from class com.rapidminer.operator.learner.functions.kernel.AbstractKernelBasedLearner

getModelClass

Methods inherited from class com.rapidminer.operator.learner.AbstractLearner

canEstimatePerformance, doWork, doWork, getEstimatedPerformance, getExampleSetInputPort, getWeights, onlyWarnForNonSufficientCapabilities, shouldAutoConnect, shouldEstimatePerformance

Methods inherited from class com.rapidminer.operator.Operator

acceptsInput, addError, addError, addValue, addWarning, apply, apply, assumePreconditionsSatisfied, checkAll, checkAllExcludingMetaData, checkDeprecations, checkForStop, checkIO, checkProperties, clear, clearErrorList, cloneOperator, collectErrors, createExperimentTree, createExperimentTree, createFromXML, createFromXML, createFromXML, createMarkedExperimentTree, createMarkedProcessTree, createProcessTree, createProcessTree, disconnectPorts, execute, fireUpdate, freeMemory, getAddOnlyAdditionalOutput, getApplyCount, getCompatibilityLevel, getDeliveredOutputClasses, getDeprecationInfo, getDesiredInputClasses, getDOMRepresentation, getEncoding, getErrorList, getExecutionUnit, getExperiment, getIncompatibleVersionChanges, getInput, getInput, getInput, getInputClasses, getInputDescription, getInputPorts, getIODescription, getLog, getLogger, getName, getNumberOfBreakpoints, getOperatorClassName, getOperatorDescription, getOutputClasses, getOutputPorts, getParameter, getParameterAsBoolean, getParameterAsChar, getParameterAsColor, getParameterAsDouble, getParameterAsFile, getParameterAsFile, getParameterAsInputStream, getParameterAsInt, getParameterAsMatrix, getParameterAsRepositoryLocation, getParameterAsString, getParameterHandler, getParameterList, getParameters, getParameterTupel, getParameterType, getParent, getPortOwner, getProcess, getResourceConsumptionEstimator, getRoot, getStartTime, getTransformer, getUserDescription, getValue, getValues, getXML, getXML, getXML, hasBreakpoint, hasBreakpoint, hasInput, inApplyLoop, isDebugMode, isDirty, isEnabled, isExpanded, isParallel, isParameterSet, isRunning, log, log, logError, logNote, logWarning, lookupOperator, makeDirty, makeDirtyOnUpdate, notifyRenaming, performAdditionalChecks, preAutoWire, processFinished, processStarts, producesOutput, propagateDirtyness, register, registerOperator, remove, removeAndKeepConnections, rename, resume, setBreakpoint, setCompatibilityLevel, setEnabled, setEnclosingProcess, setExpanded, setInput, setListParameter, setPairParameter, setParameter, setParameters, setUserDescription, shouldAutoConnect, shouldStopStandaloneExecution, toString, transformMetaData, unregisterOperator, updateExecutionOrder, walk, writeXML, writeXML

Methods inherited from class com.rapidminer.tools.AbstractObservable

addObserver, addObserverAsFirst, fireUpdate, removeObserver

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.rapidminer.operator.learner.Learner

getName

Field Detail

PARAMETER_KERNEL_GAMMA

public static final java.lang.String PARAMETER_KERNEL_GAMMA

The parameter name for "The SVM kernel parameter gamma (radial, anova)."

See Also:

Constant Field Values

PARAMETER_KERNEL_SIGMA1

public static final java.lang.String PARAMETER_KERNEL_SIGMA1

The parameter name for "The SVM kernel parameter sigma1 (epanechnikov, gaussian combination, multiquadric)."

See Also:

Constant Field Values

PARAMETER_KERNEL_SIGMA2

public static final java.lang.String PARAMETER_KERNEL_SIGMA2

The parameter name for "The SVM kernel parameter sigma2 (gaussian combination)."

See Also:

Constant Field Values

PARAMETER_KERNEL_SIGMA3

public static final java.lang.String PARAMETER_KERNEL_SIGMA3

The parameter name for "The SVM kernel parameter sigma3 (gaussian combination)."

See Also:

Constant Field Values

PARAMETER_KERNEL_SHIFT

public static final java.lang.String PARAMETER_KERNEL_SHIFT

The parameter name for "The SVM kernel parameter shift (multiquadric)."

See Also:

Constant Field Values

PARAMETER_KERNEL_DEGREE

public static final java.lang.String PARAMETER_KERNEL_DEGREE

The parameter name for "The SVM kernel parameter degree (polynomial, anova, epanechnikov)."

See Also:

Constant Field Values

PARAMETER_KERNEL_A

public static final java.lang.String PARAMETER_KERNEL_A

The parameter name for "The SVM kernel parameter a (neural)."

See Also:

Constant Field Values

PARAMETER_KERNEL_B

public static final java.lang.String PARAMETER_KERNEL_B

The parameter name for "The SVM kernel parameter b (neural)."

See Also:

Constant Field Values

PARAMETER_KERNEL_CACHE

public static final java.lang.String PARAMETER_KERNEL_CACHE

The parameter name for "Size of the cache for kernel evaluations im MB "

See Also:

Constant Field Values

PARAMETER_CONVERGENCE_EPSILON

public static final java.lang.String PARAMETER_CONVERGENCE_EPSILON

The parameter name for "Precision on the KKT conditions"

See Also:

Constant Field Values

PARAMETER_MAX_ITERATIONS

public static final java.lang.String PARAMETER_MAX_ITERATIONS

The parameter name for "Stop after this many iterations"

See Also:

Constant Field Values

PARAMETER_SCALE

public static final java.lang.String PARAMETER_SCALE

The parameter name for "Scale the example values and store the scaling parameters for test set."

See Also:

Constant Field Values

PARAMETER_RETURN_OPTIMIZATION_PERFORMANCE

public static final java.lang.String PARAMETER_RETURN_OPTIMIZATION_PERFORMANCE

The parameter name for "Indicates if final optimization fitness should be returned as performance."

See Also:

Constant Field Values

PARAMETER_C

public static final java.lang.String PARAMETER_C

See Also:

Constant Field Values

PARAMETER_KERNEL_TYPE

public static final java.lang.String PARAMETER_KERNEL_TYPE

See Also:

Constant Field Values

PARAMETER_CALCULATE_WEIGHTS

public static final java.lang.String PARAMETER_CALCULATE_WEIGHTS

See Also:

Constant Field Values

KERNEL_TYPES

public static final java.lang.String[] KERNEL_TYPES

The kernels which can be used from RapidMiner for the mySVM / myKLR.

KERNEL_DOT

public static final int KERNEL_DOT

Indicates a linear kernel.

See Also:

Constant Field Values

KERNEL_RADIAL

public static final int KERNEL_RADIAL

Indicates a rbf kernel.

See Also:

Constant Field Values

KERNEL_POLYNOMIAL

public static final int KERNEL_POLYNOMIAL

Indicates a polynomial kernel.

See Also:

Constant Field Values

KERNEL_NEURAL

public static final int KERNEL_NEURAL

Indicates a neural net kernel.

See Also:

Constant Field Values

KERNEL_ANOVA

public static final int KERNEL_ANOVA

Indicates an anova kernel.

See Also:

Constant Field Values

KERNEL_EPANECHNIKOV

public static final int KERNEL_EPANECHNIKOV

Indicates a epanechnikov kernel.

See Also:

Constant Field Values

KERNEL_GAUSSIAN_COMBINATION

public static final int KERNEL_GAUSSIAN_COMBINATION

Indicates a gaussian combination kernel.

See Also:

Constant Field Values

KERNEL_MULTIQUADRIC

public static final int KERNEL_MULTIQUADRIC

Indicates a multiquadric kernel.

See Also:

Constant Field Values

Constructor Detail

AbstractMySVMLearner

public AbstractMySVMLearner(OperatorDescription description)

Method Detail

getWeightCalculationError

public MetaDataError getWeightCalculationError(OutputPort weightPort)

Overrides:

getWeightCalculationError in class AbstractLearner

createSVM

public abstract SVMInterface createSVM(Attribute label,
                                       Kernel kernel,
                                       SVMExamples svmExamples,
                                       ExampleSet rapidMinerExamples)
                                throws OperatorException

Creates a new SVM according to the given label.

Throws:

OperatorException

createSVMModel

public abstract AbstractMySVMModel createSVMModel(ExampleSet exampleSet,
                                                  SVMExamples svmExamples,
                                                  Kernel kernel,
                                                  int kernelType)

Creates a new SVM model from the given data.

getKernel

protected Kernel getKernel()

Returns the kernel of this SVM.

getSVM

protected SVMInterface getSVM()

Returns the used SVM.

shouldDeliverOptimizationPerformance

public boolean shouldDeliverOptimizationPerformance()

Returns the value of the corresponding parameter.

Overrides:

shouldDeliverOptimizationPerformance in class AbstractLearner

getOptimizationPerformance

public PerformanceVector getOptimizationPerformance()

Returns the optimization performance of the best result. This method must be called after training, not before.

Overrides:

getOptimizationPerformance in class AbstractLearner

shouldCalculateWeights

public boolean shouldCalculateWeights()

Returns true if the user has specified that weights should be calculated.

Specified by:

shouldCalculateWeights in interface Learner

Overrides:

shouldCalculateWeights in class AbstractLearner

canCalculateWeights

public boolean canCalculateWeights()

Description copied from class: AbstractLearner

Returns true if this learner is capable of computing attribute weights. If this method returns true, also override AbstractLearner.getWeights(ExampleSet)

Overrides:

canCalculateWeights in class AbstractLearner

getWeights

public AttributeWeights getWeights(ExampleSet exampleSet)
                            throws OperatorException

Returns the weights for all features.

Specified by:

getWeights in interface Learner

Overrides:

getWeights in class AbstractLearner

Throws:

OperatorException

learn

public Model learn(ExampleSet exampleSet)
            throws OperatorException

Description copied from interface: Learner

Trains a model. This method should be called by apply() and is implemented by subclasses.

Throws:

OperatorException

createKernel

public static Kernel createKernel(int kernelType)

Creates a new kernel of the given type. The kernel type has to be one out of KERNEL_DOT, KERNEL_RADIAL, KERNEL_POLYNOMIAL, KERNEL_NEURAL, KERNEL_EPANECHNIKOV, KERNEL_GAUSSIAN_COMBINATION, or KERNEL_MULTIQUADRIC.

supportsCapability

public boolean supportsCapability(OperatorCapability lc)

Description copied from interface: CapabilityProvider

Checks for Learner capabilities. Should return true if the given capability is supported.

getParameterTypes

public java.util.List<ParameterType> getParameterTypes()

Description copied from class: Operator

Returns a list of ParameterTypes describing the parameters of this operator. The default implementation returns an empty list if no input objects can be retained and special parameters for those input objects which can be prevented from being consumed. ATTENTION! This will create new parameterTypes. For calling already existing parameter types use getParameters().getParameterTypes();

Specified by:

getParameterTypes in interface ParameterHandler

Overrides:

getParameterTypes in class Operator