com.rapidminer.operator.performance
Class BinaryClassificationPerformance

java.lang.Object
  com.rapidminer.operator.AbstractIOObject
      com.rapidminer.operator.ResultObjectAdapter
          com.rapidminer.tools.math.Averagable
              com.rapidminer.operator.performance.PerformanceCriterion
                  com.rapidminer.operator.performance.MeasuredPerformance
                      com.rapidminer.operator.performance.BinaryClassificationPerformance

All Implemented Interfaces:

IOObject, ResultObject, Saveable, Readable, Reportable, Tableable, LoggingHandler, java.io.Serializable, java.lang.Cloneable, java.lang.Comparable<PerformanceCriterion>

public class BinaryClassificationPerformance
extends MeasuredPerformance
implements Tableable

This class encapsulates the well known binary classification criteria precision and recall. Furthermore it can be used to calculate the fallout, the equally weighted f-measure (f1-measure), the lift, and the values for TRUE_POSITIVE, FALSE_POSITIVE, TRUE_NEGATIVE, and FALSE_NEGATIVE. With "positive" we refer to the first class and with "negative" we refer to the second.

Author:

Ingo Mierswa, Simon Fischer ingomierswa Exp $

See Also:

Serialized Form

Field Summary

static java.lang.String[]	DESCRIPTIONS
static int	F_MEASURE
static int	FALLOUT
static int	FALSE_NEGATIVE
static int	FALSE_POSITIVE
static int	LIFT
static java.lang.String[]	NAMES
static int	NEGATIVE_PREDICTIVE_VALUE
static int	POSITIVE_PREDICTIVE_VALUE
static int	PRECISION
static int	PSEP
static int	RECALL
static int	SENSITIVITY
static int	SPECIFICITY
static int	TRUE_NEGATIVE
static int	TRUE_POSITIVE
static int	YOUDEN

Constructor Summary

BinaryClassificationPerformance()

BinaryClassificationPerformance(BinaryClassificationPerformance o)

BinaryClassificationPerformance(int type)

BinaryClassificationPerformance(int type, double[][] counter)
For test cases only.

Method Summary

void	buildSingleAverage(Averagable performance) This method should build the average of this and another averagable of the same type.
void	countExample(Example example) Counts a single example, e.g. by summing up errors.
void	finishReporting()
boolean	formatPercent() Indicates wether or not percentage format should be used in the Averagable.toString() method.
java.lang.String	getCell(int row, int column)
java.lang.String	getColumnName(int columnIndex)
int	getColumnNumber()
java.lang.String	getDescription() Returns a description of the performance criterion.
double	getExampleCount() Returns the number of data points which was used to determine the criterion value.
double	getFitness() Returns the fitness depending on the value.
double	getMaxFitness() Returns the maximum fitness.
double	getMikroAverage() Returns the (current) value of the averagable (the average itself).
double	getMikroVariance() Returns the variance of the averagable.
java.lang.String	getName() Returns the name of this averagable.
int	getRowNumber()
java.awt.Component	getVisualizationComponent(IOContainer ioContainer) This implementation returns a confusion matrix viewer based on a JTable.
boolean	isFirstColumnHeader()
boolean	isFirstLineHeader()
static BinaryClassificationPerformance	newInstance(java.lang.String name)
void	prepareReporting()
void	startCounting(ExampleSet eSet, boolean useExampleWeights) Initializes the criterion.
java.lang.String	toString()

Methods inherited from class com.rapidminer.operator.performance.MeasuredPerformance

startCounting

Methods inherited from class com.rapidminer.operator.performance.PerformanceCriterion

compareTo

Methods inherited from class com.rapidminer.tools.math.Averagable

buildAverage, clone, cloneAveragable, getAverage, getAverageCount, getExtension, getFileDescription, getMakroAverage, getMakroStandardDeviation, getMakroVariance, getMikroStandardDeviation, getStandardDeviation, getVariance, setAverageCount

Methods inherited from class com.rapidminer.operator.ResultObjectAdapter

addAction, getActions, getResultIcon, isSavable, log, logError, logNote, logWarning, save, toHTML, toResultString

Methods inherited from class com.rapidminer.operator.AbstractIOObject

copy, getLog, getSource, initWriting, read, setLoggingHandler, setSource, write

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.rapidminer.operator.IOObject

copy, getLog, getSource, setLoggingHandler, setSource, write

Field Detail

PRECISION

public static final int PRECISION

See Also:

Constant Field Values

RECALL

public static final int RECALL

See Also:

Constant Field Values

LIFT

public static final int LIFT

See Also:

Constant Field Values

FALLOUT

public static final int FALLOUT

See Also:

Constant Field Values

F_MEASURE

public static final int F_MEASURE

See Also:

Constant Field Values

FALSE_POSITIVE

public static final int FALSE_POSITIVE

See Also:

Constant Field Values

FALSE_NEGATIVE

public static final int FALSE_NEGATIVE

See Also:

Constant Field Values

TRUE_POSITIVE

public static final int TRUE_POSITIVE

See Also:

Constant Field Values

TRUE_NEGATIVE

public static final int TRUE_NEGATIVE

See Also:

Constant Field Values

SENSITIVITY

public static final int SENSITIVITY

See Also:

Constant Field Values

SPECIFICITY

public static final int SPECIFICITY

See Also:

Constant Field Values

YOUDEN

public static final int YOUDEN

See Also:

Constant Field Values

POSITIVE_PREDICTIVE_VALUE

public static final int POSITIVE_PREDICTIVE_VALUE

See Also:

Constant Field Values

NEGATIVE_PREDICTIVE_VALUE

public static final int NEGATIVE_PREDICTIVE_VALUE

See Also:

Constant Field Values

PSEP

public static final int PSEP

See Also:

Constant Field Values

NAMES

public static final java.lang.String[] NAMES

DESCRIPTIONS

public static final java.lang.String[] DESCRIPTIONS

Constructor Detail

BinaryClassificationPerformance

public BinaryClassificationPerformance()

BinaryClassificationPerformance

public BinaryClassificationPerformance(BinaryClassificationPerformance o)

BinaryClassificationPerformance

public BinaryClassificationPerformance(int type)

BinaryClassificationPerformance

public BinaryClassificationPerformance(int type,
                                       double[][] counter)

For test cases only.

Method Detail

newInstance

public static BinaryClassificationPerformance newInstance(java.lang.String name)

getExampleCount

public double getExampleCount()

Description copied from class: PerformanceCriterion

Returns the number of data points which was used to determine the criterion value. If the criterion does not use example weights (or no weight was given) then the returned value will be an integer. Otherwise, the returned value is the sum of all example weights.

Specified by:

getExampleCount in class PerformanceCriterion

startCounting

public void startCounting(ExampleSet eSet,
                          boolean useExampleWeights)
                   throws OperatorException

Description copied from class: MeasuredPerformance

Initializes the criterion. The default implementation does nothing.

Overrides:

startCounting in class MeasuredPerformance

Throws:

OperatorException

countExample

public void countExample(Example example)

Description copied from class: MeasuredPerformance

Counts a single example, e.g. by summing up errors.

Specified by:

countExample in class MeasuredPerformance

getMikroAverage

public double getMikroAverage()

Description copied from class: Averagable

Returns the (current) value of the averagable (the average itself). If the method Averagable.buildSingleAverage(Averagable) was used, this method must return the micro average from both (or more) criteria. This is usually achieved by correctly implementing Averagable.buildSingleAverage(Averagable).

Specified by:

getMikroAverage in class Averagable

getFitness

public double getFitness()

Description copied from class: PerformanceCriterion

Returns the fitness depending on the value. The fitness values will be used for all optimization purposes (feature space transformations, parameter optimizations...) and must always be maximized. Hence, if your criterion is better the smaller the value is you should return something like (-1 * value) or (1 / value).

Subclasses should use Averagable.getAverage() instead of Averagable.getMikroAverage() in this method since usually the makro average (if available) should be optmized instead of the mikro average. The mikro average should only be used in the (rare) cases where no makro average is available but this is automatically done returned by Averagable.getAverage() in these cases.

Specified by:

getFitness in class PerformanceCriterion

getMaxFitness

public double getMaxFitness()

Description copied from class: PerformanceCriterion

Returns the maximum fitness. The default implementation resturns POSITIVE_INFINITY, subclasses may override this to allow feature operators to end the optimization if the maximum was reached.

Overrides:

getMaxFitness in class PerformanceCriterion

getMikroVariance

public double getMikroVariance()

Description copied from class: Averagable

Returns the variance of the averagable. The returned value must not be negative. If the averagable does not define a variance this method should return Double.NaN.

Specified by:

getMikroVariance in class Averagable

getName

public java.lang.String getName()

Description copied from class: Averagable

Returns the name of this averagable. The returned string should only contain lowercase letters and underscore (RapidMiner parameter format) since the names will be automatically used for GUI purposes.

Specified by:

getName in interface ResultObject

Specified by:

getName in class Averagable

getDescription

public java.lang.String getDescription()

Description copied from class: PerformanceCriterion

Returns a description of the performance criterion. This description is used for GUI purposes and automatic parameter type creation for the PerformanceEvaluator operator.

Specified by:

getDescription in class PerformanceCriterion

formatPercent

public boolean formatPercent()

Description copied from class: Averagable

Indicates wether or not percentage format should be used in the Averagable.toString() method. The default implementation returns false.

Overrides:

formatPercent in class Averagable

buildSingleAverage

public void buildSingleAverage(Averagable performance)

Description copied from class: Averagable

This method should build the average of this and another averagable of the same type. The next invocation of Averagable.getMikroAverage() should return the average of this and the given averagable. Hence, this method is used to build the actual micro average value of two criteria. Please refer to SimpleCriterion for a simple implementation example.

Specified by:

buildSingleAverage in class Averagable

toString

public java.lang.String toString()

Specified by:

toString in interface Readable

Overrides:

toString in class Averagable

getVisualizationComponent

public java.awt.Component getVisualizationComponent(IOContainer ioContainer)

This implementation returns a confusion matrix viewer based on a JTable.

Specified by:

getVisualizationComponent in interface ResultObject

Overrides:

getVisualizationComponent in class Averagable

prepareReporting

public void prepareReporting()

Specified by:

prepareReporting in interface Tableable

finishReporting

public void finishReporting()

Specified by:

finishReporting in interface Tableable

getColumnName

public java.lang.String getColumnName(int columnIndex)

Specified by:

getColumnName in interface Tableable

getCell

public java.lang.String getCell(int row,
                                int column)

Specified by:

getCell in interface Tableable

getColumnNumber

public int getColumnNumber()

Specified by:

getColumnNumber in interface Tableable

getRowNumber

public int getRowNumber()

Specified by:

getRowNumber in interface Tableable

isFirstLineHeader

public boolean isFirstLineHeader()

Specified by:

isFirstLineHeader in interface Tableable

isFirstColumnHeader

public boolean isFirstColumnHeader()

Specified by:

isFirstColumnHeader in interface Tableable