com.rapidminer.operator.learner.tree
Class AbstractTreeLearner

java.lang.Object
  com.rapidminer.tools.AbstractObservable<Operator>
      com.rapidminer.operator.Operator
          com.rapidminer.operator.learner.AbstractLearner
              com.rapidminer.operator.learner.tree.AbstractTreeLearner

All Implemented Interfaces:

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

Direct Known Subclasses:

DecisionStumpLearner, DecisionTreeLearner, ID3Learner, ID3NumericalLearner

public abstract class AbstractTreeLearner
extends AbstractLearner

This is the abstract super class for all decision tree learners. The actual type of the tree is determined by the criterion, e.g. using gain_ratio or Gini for CART / C4.5 and chi_squared for CHAID.

Author:

Sebastian Land, Ingo Mierswa

Field Summary

static java.lang.Class[]	CRITERIA_CLASSES
static java.lang.String[]	CRITERIA_NAMES
static int	CRITERION_ACCURACY
static int	CRITERION_GAIN_RATIO
static int	CRITERION_GINI_INDEX
static int	CRITERION_INFO_GAIN
static java.lang.String	PARAMETER_CRITERION The parameter name for "Specifies the used criterion for selecting attributes and numerical splits.
static java.lang.String	PARAMETER_MINIMAL_GAIN The parameter name for the minimal gain.
static java.lang.String	PARAMETER_MINIMAL_LEAF_SIZE The parameter name for "The minimal size of all leaves.
static java.lang.String	PARAMETER_MINIMAL_SIZE_FOR_SPLIT The parameter name for "The minimal size of all leaves.

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

PROPERTY_RAPIDMINER_GENERAL_CAPABILITIES_WARN

Constructor Summary

AbstractTreeLearner(OperatorDescription description)

Method Summary

protected Criterion	createCriterion(double minimalGain)
java.lang.Class<? extends PredictionModel>	getModelClass() This method might be overridden from subclasses in order to specify exactly which model class they use.
java.util.List<ParameterType>	getParameterTypes() Returns a list of ParameterTypes describing the parameters of this operator.
abstract Pruner	getPruner() Returns the pruner for this tree learner.
SplitPreprocessing	getSplitPreprocessing() The split preprocessing is applied before each new split The default implementation does nothing and simply returns the given example set.
abstract java.util.List<Terminator>	getTerminationCriteria(ExampleSet exampleSet) Returns all termination criteria.
protected abstract TreeBuilder	getTreeBuilder(ExampleSet exampleSet)
Model	learn(ExampleSet eSet) Trains a model.

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

canCalculateWeights, canEstimatePerformance, doWork, doWork, getEstimatedPerformance, getExampleSetInputPort, getOptimizationPerformance, getWeightCalculationError, getWeights, getWeights, onlyWarnForNonSufficientCapabilities, shouldAutoConnect, shouldCalculateWeights, shouldDeliverOptimizationPerformance, 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

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

supportsCapability

Field Detail

PARAMETER_CRITERION

public static final java.lang.String PARAMETER_CRITERION

The parameter name for "Specifies the used criterion for selecting attributes and numerical splits."

See Also:

Constant Field Values

PARAMETER_MINIMAL_SIZE_FOR_SPLIT

public static final java.lang.String PARAMETER_MINIMAL_SIZE_FOR_SPLIT

The parameter name for "The minimal size of all leaves."

See Also:

Constant Field Values

PARAMETER_MINIMAL_LEAF_SIZE

public static final java.lang.String PARAMETER_MINIMAL_LEAF_SIZE

The parameter name for "The minimal size of all leaves."

See Also:

Constant Field Values

PARAMETER_MINIMAL_GAIN

public static final java.lang.String PARAMETER_MINIMAL_GAIN

The parameter name for the minimal gain.

See Also:

Constant Field Values

CRITERIA_NAMES

public static final java.lang.String[] CRITERIA_NAMES

CRITERIA_CLASSES

public static final java.lang.Class[] CRITERIA_CLASSES

CRITERION_GAIN_RATIO

public static final int CRITERION_GAIN_RATIO

See Also:

Constant Field Values

CRITERION_INFO_GAIN

public static final int CRITERION_INFO_GAIN

See Also:

Constant Field Values

CRITERION_GINI_INDEX

public static final int CRITERION_GINI_INDEX

See Also:

Constant Field Values

CRITERION_ACCURACY

public static final int CRITERION_ACCURACY

See Also:

Constant Field Values

Constructor Detail

AbstractTreeLearner

public AbstractTreeLearner(OperatorDescription description)

Method Detail

getModelClass

public java.lang.Class<? extends PredictionModel> getModelClass()

Description copied from class: AbstractLearner

This method might be overridden from subclasses in order to specify exactly which model class they use. This is to ensure the proper postprocessing of some models like KernelModels (SupportVectorCounter) or TreeModels (Rule generation)

Overrides:

getModelClass in class AbstractLearner

getTerminationCriteria

public abstract java.util.List<Terminator> getTerminationCriteria(ExampleSet exampleSet)
                                                           throws OperatorException

Returns all termination criteria.

Throws:

OperatorException

getPruner

public abstract Pruner getPruner()
                          throws OperatorException

Returns the pruner for this tree learner. If this method returns null, pruning will be disabled.

Throws:

OperatorException

getSplitPreprocessing

public SplitPreprocessing getSplitPreprocessing()

The split preprocessing is applied before each new split The default implementation does nothing and simply returns the given example set. Subclasses might want to override this in order to perform some data preprocessing like random subset selections.

learn

public Model learn(ExampleSet eSet)
            throws OperatorException

Description copied from interface: Learner

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

Throws:

OperatorException

getTreeBuilder

protected abstract TreeBuilder getTreeBuilder(ExampleSet exampleSet)
                                       throws OperatorException

Throws:

OperatorException

createCriterion

protected Criterion createCriterion(double minimalGain)
                             throws OperatorException

Throws:

OperatorException

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