de.jstacs.classifiers.performanceMeasures
Class MaximumFMeasure

java.lang.Object
  de.jstacs.parameters.ParameterSet
      de.jstacs.classifiers.performanceMeasures.AbstractPerformanceMeasure
          de.jstacs.classifiers.performanceMeasures.TwoClassAbstractPerformanceMeasure
              de.jstacs.classifiers.performanceMeasures.MaximumNumericalTwoClassMeasure
                  de.jstacs.classifiers.performanceMeasures.MaximumFMeasure

All Implemented Interfaces:

NumericalPerformanceMeasure, GalaxyConvertible, Storable, Cloneable

public class MaximumFMeasure
extends MaximumNumericalTwoClassMeasure

Computes the maximum of the general F-measure given a positive real parameter . The F-measure is defined as , where PPV denotes the positive predictive value and Sn denotes sensitivity. For it is equal to the traditional F1-measure.

Author:

Jens Keilwagen

See Also:

PositivePredictiveValueForFixedSensitivity, SensitivityForFixedSpecificity

Nested Class Summary

Nested classes/interfaces inherited from class de.jstacs.parameters.ParameterSet

ParameterSet.ParameterList

Field Summary

Fields inherited from class de.jstacs.parameters.ParameterSet

errorMessage, parameters, parent

Constructor Summary

MaximumFMeasure()
Constructs a new instance of the performance measure MaximumFMeasure with empty parameters.

MaximumFMeasure(double beta)
Constructs a new instance of the performance measure MaximumFMeasure with given beta.

MaximumFMeasure(StringBuffer xml)
The standard constructor for the interface Storable.

Method Summary

protected double	getMeasure(double tp, double fp, double fn, double tn) This measure compute the measure for a given confusion matrix
protected String	getMeasureName() This method returns a short name of the measure without any parameters.
protected String	getSpecificName() This method returns a specific name of the measure including any parameters.

Methods inherited from class de.jstacs.classifiers.performanceMeasures.MaximumNumericalTwoClassMeasure

compute, compute, getName

Methods inherited from class de.jstacs.classifiers.performanceMeasures.TwoClassAbstractPerformanceMeasure

getAllowedNumberOfClasses

Methods inherited from class de.jstacs.classifiers.performanceMeasures.AbstractPerformanceMeasure

getCollectionOfAllMeasures

Methods inherited from class de.jstacs.parameters.ParameterSet

clone, fromGalaxy, fromXML, getAllParameterNames, getComment, getComment, getErrorMessage, getIndex, getName, getName, getNumberOfParameters, getParameterAt, getParameterForName, getParent, hasDefaultOrIsSet, initParameterList, initParameterList, isAtomic, isComparable, parametersLoaded, reset, setParent, toGalaxy, toXML

Methods inherited from class java.lang.Object

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

Constructor Detail

MaximumFMeasure

public MaximumFMeasure()

Constructs a new instance of the performance measure MaximumFMeasure with empty parameters.

MaximumFMeasure

public MaximumFMeasure(double beta)
                throws Exception

Constructs a new instance of the performance measure MaximumFMeasure with given beta.

Parameters:

beta - the beta for which the maximum F-measure should be computed

Throws:

Exception - if the internal parameters can not be created or the value can not be set

MaximumFMeasure

public MaximumFMeasure(StringBuffer xml)
                throws NonParsableException

The standard constructor for the interface Storable. Constructs a MaximumFMeasure out of an XML representation.

Parameters:

xml - the XML representation as StringBuffer

Throws:

NonParsableException - if the MaximumFMeasure could not be reconstructed out of the StringBuffer xml

Method Detail

getMeasureName

protected String getMeasureName()

Description copied from class: MaximumNumericalTwoClassMeasure

This method returns a short name of the measure without any parameters.

Specified by:

getMeasureName in class MaximumNumericalTwoClassMeasure

Returns:

a short name of the measure without any parameters

getSpecificName

protected String getSpecificName()

Description copied from class: MaximumNumericalTwoClassMeasure

This method returns a specific name of the measure including any parameters.

Specified by:

getSpecificName in class MaximumNumericalTwoClassMeasure

Returns:

a specific name of the measure including any parameters

getMeasure

protected double getMeasure(double tp,
                            double fp,
                            double fn,
                            double tn)

Description copied from class: MaximumNumericalTwoClassMeasure

This measure compute the measure for a given confusion matrix

Specified by:

getMeasure in class MaximumNumericalTwoClassMeasure

Parameters:

tp - true positives

fp - false positives

fn - false negatives

tn - true negative

Returns:

the value of the measure