weka.knowledgeflow.steps

Class ClassifierPerformanceEvaluator

java.lang.Object

weka.knowledgeflow.steps.BaseStep

weka.knowledgeflow.steps.ClassifierPerformanceEvaluator

All Implemented Interfaces:

java.io.Serializable, BaseStepExtender, Step

@KFStep(name="ClassifierPerformanceEvaluator",
        category="Evaluation",
        toolTipText="Evaluates batch classifiers",
        iconPath="weka/gui/knowledgeflow/icons/ClassifierPerformanceEvaluator.gif")
public class ClassifierPerformanceEvaluator
extends BaseStep

Step that implements batch classifier evaluation

Version:

$Revision: $

Author:

Mark Hall (mhall{[at]}pentaho{[dot]}com)

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ClassifierPerformanceEvaluator() Constructor

Method Summary

Modifier and Type	Method and Description
boolean	getCollectPredictionsForVisAndAUC()
java.lang.String	getCostMatrixString() Get the cost matrix to use as a string
java.lang.String	getCustomEditorForStep() Return the fully qualified name of a custom editor component (JComponent) to use for editing the properties of the step.
boolean	getErrorPlotPointSizeProportionalToMargin() Get whether the size of plot data points will be proportional to the prediction margin
boolean	getEvaluateWithRespectToCosts() Get whether to evaluate with respoect to costs
java.lang.String	getEvaluationMetricsToOutput() Get the evaluation metrics to output (as a comma-separated list).
java.util.List<java.lang.String>	getIncomingConnectionTypes() Get a list of incoming connection types that this step can accept.
java.util.List<java.lang.String>	getOutgoingConnectionTypes() Get a list of outgoing connection types that this step can produce.
boolean	getOutputConfusionMatrix()
boolean	getOutputEntropyMetrics()
boolean	getOutputPerClassStats()
void	processIncoming(Data data) Process an incoming data payload (if the step accepts incoming connections)
void	setCollectPredictionsForVisAndAUC(boolean collectPredictionsForVisAndAUC)
void	setCostMatrixString(java.lang.String cms) Set the cost matrix to use as a string
void	setErrorPlotPointSizeProportionalToMargin(boolean e) Set whether the size of plot data points will be proportional to the prediction margin
void	setEvaluateWithRespectToCosts(boolean useCosts) Set whether to evaluate with respoect to costs
void	setEvaluationMetricsToOutput(java.lang.String m) Set the evaluation metrics to output (as a comma-separated list).
void	setOutputConfusionMatrix(boolean outputConfusionMatrix)
void	setOutputEntropyMetrics(boolean outputEntropyMetrics)
void	setOutputPerClassStats(boolean perClassStats)
void	stepInit() Initialize the step.
void	stop() Request that processing be stopped.

Methods inherited from class weka.knowledgeflow.steps.BaseStep

environmentSubstitute, getDefaultSettings, getInteractiveViewers, getInteractiveViewersImpls, getName, getStepManager, globalInfo, isResourceIntensive, isStopRequested, outputStructureForConnectionType, outputStructureForConnectionType, setName, setStepIsResourceIntensive, setStepManager, setStepMustRunSingleThreaded, start, stepMustRunSingleThreaded

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ClassifierPerformanceEvaluator

public ClassifierPerformanceEvaluator()

Constructor

Method Detail

setOutputPerClassStats

public void setOutputPerClassStats(boolean perClassStats)

getOutputPerClassStats

@OptionMetadata(displayName="Output per-class stats",
                description="Output precision/recall and true/false positives for each class",
                displayOrder=1)
public boolean getOutputPerClassStats()

setOutputConfusionMatrix

@OptionMetadata(displayName="Output confusion matrix",
                description="Output the matrix containing class confusions",
                displayOrder=2)
public void setOutputConfusionMatrix(boolean outputConfusionMatrix)

getOutputConfusionMatrix

public boolean getOutputConfusionMatrix()

setOutputEntropyMetrics

@OptionMetadata(displayName="Output entropy evaluation measures",
                description="Output entropy-based evaluation measures",
                displayOrder=3)
public void setOutputEntropyMetrics(boolean outputEntropyMetrics)

getOutputEntropyMetrics

public boolean getOutputEntropyMetrics()

setCollectPredictionsForVisAndAUC

@OptionMetadata(displayName="Collect test data and predictions for visualization",
                description="Collect data and predictions in order to output visualizableError and thresholdData data",
                displayOrder=4)
public void setCollectPredictionsForVisAndAUC(boolean collectPredictionsForVisAndAUC)

getCollectPredictionsForVisAndAUC

public boolean getCollectPredictionsForVisAndAUC()

getErrorPlotPointSizeProportionalToMargin

@OptionMetadata(displayName="Error plot point size proportional to margin",
                description="Set the point size proportional to the prediction margin for classification error plots")
public boolean getErrorPlotPointSizeProportionalToMargin()

Get whether the size of plot data points will be proportional to the prediction margin

Returns:

true if plot data points will be rendered proportional to the size of the prediction margin

setErrorPlotPointSizeProportionalToMargin

public void setErrorPlotPointSizeProportionalToMargin(boolean e)

Set whether the size of plot data points will be proportional to the prediction margin

Parameters:

e - true if plot data points will be rendered proportional to the size of the prediction margin

getEvaluationMetricsToOutput

@ProgrammaticProperty
public java.lang.String getEvaluationMetricsToOutput()

Get the evaluation metrics to output (as a comma-separated list).

Returns:

the evaluation metrics to output

setEvaluationMetricsToOutput

public void setEvaluationMetricsToOutput(java.lang.String m)

Set the evaluation metrics to output (as a comma-separated list).

Parameters:

m - the evaluation metrics to output

setEvaluateWithRespectToCosts

@ProgrammaticProperty
public void setEvaluateWithRespectToCosts(boolean useCosts)

Set whether to evaluate with respoect to costs

Parameters:

useCosts - true to use cost-sensitive evaluation

getEvaluateWithRespectToCosts

public boolean getEvaluateWithRespectToCosts()

Get whether to evaluate with respoect to costs

Returns:

true to use cost-sensitive evaluation

setCostMatrixString

@ProgrammaticProperty
public void setCostMatrixString(java.lang.String cms)

Set the cost matrix to use as a string

Parameters:

cms - the cost matrix to use

getCostMatrixString

public java.lang.String getCostMatrixString()

Get the cost matrix to use as a string

Returns:

the cost matrix

getIncomingConnectionTypes

public java.util.List<java.lang.String> getIncomingConnectionTypes()

Get a list of incoming connection types that this step can accept. Ideally (and if appropriate), this should take into account the state of the step and any existing incoming connections. E.g. a step might be able to accept one (and only one) incoming batch data connection.

Returns:

a list of incoming connections that this step can accept given its current state

getOutgoingConnectionTypes

public java.util.List<java.lang.String> getOutgoingConnectionTypes()

Get a list of outgoing connection types that this step can produce. Ideally (and if appropriate), this should take into account the state of the step and the incoming connections. E.g. depending on what incoming connection is present, a step might be able to produce a trainingSet output, a testSet output or neither, but not both.

Returns:

a list of outgoing connections that this step can produce

stepInit

public void stepInit()
              throws WekaException

Description copied from interface: Step

Initialize the step.

Throws:

WekaException - if a problem occurs during initialization

stop

public void stop()

Description copied from class: BaseStep

Request that processing be stopped. Subclasses should call isStopRequested() periodically to see if they should stop processing.

Specified by:

stop in interface Step

Overrides:

stop in class BaseStep

processIncoming

public void processIncoming(Data data)
                     throws WekaException

Process an incoming data payload (if the step accepts incoming connections)

Specified by:

processIncoming in interface BaseStepExtender

Specified by:

processIncoming in interface Step

Overrides:

processIncoming in class BaseStep

Parameters:

data - the payload to process

Throws:

WekaException - if a problem occurs

getCustomEditorForStep

public java.lang.String getCustomEditorForStep()

Return the fully qualified name of a custom editor component (JComponent) to use for editing the properties of the step. This method can return null, in which case the system will dynamically generate an editor using the GenericObjectEditor

Specified by:

getCustomEditorForStep in interface Step

Overrides:

getCustomEditorForStep in class BaseStep

Returns:

the fully qualified name of a step editor component