edu.udo.cs.yale.operator.performance
Class MultiClassificationPerformance

java.lang.Object
  edu.udo.cs.yale.operator.AbstractIOObject
      edu.udo.cs.yale.operator.ResultObjectAdapter
          edu.udo.cs.yale.tools.math.Averagable
              edu.udo.cs.yale.operator.performance.PerformanceCriterion
                  edu.udo.cs.yale.operator.performance.MeasuredPerformance
                      edu.udo.cs.yale.operator.performance.MultiClassificationPerformance

All Implemented Interfaces:

IOObject, ResultObject, java.lang.Cloneable, java.lang.Comparable<Averagable>

public class MultiClassificationPerformance
extends MeasuredPerformance

Measures the accuracy and classification error for both binary classification problems and multi class problems. Additionally, this performance criterion can also compute the kappa statistics for multi class problems. This is calculated as k = (P(A) - P(E)) / (1 - P(E)) with P(A) = (diagonal sum / number of examples) and P(E) = sum over i of ((sum of i-th row * sum of i-th column) / n to the power of the number of classes).

Version:

$Id: MultiClassificationPerformance.java,v 2.16 2006/03/21 15:35:50 ingomierswa Exp $

Author:

Ingo Mierswa

Field Summary

static int	ACCURACY Indicates accuracy.
private java.lang.String[]	classNames The class names of the label.
private int[][]	counter The counter for true labels and the prediction.
static java.lang.String[]	DESCRIPTION The descriptions of the criteria.
static int	ERROR Indicates classification error.
static int	KAPPA Indicates kappa statistics.
static java.lang.String[]	NAME The names of the criteria.
private int	type The type of this performance: accuracy or classification error.
static int	UNDEFINED Indicates an undefined type (should not happen).

Constructor Summary

MultiClassificationPerformance()
Creates a MultiClassificationPerformance with undefined type.

MultiClassificationPerformance(int type)
Creates a MultiClassificationPerformance with the given type.

Method Summary

void	buildSingleAverage(Averagable performance) This method should build the average of this and another averagables of the same type.
protected void	cloneAveragable(Averagable newPC) Must be implemented by subclasses such that it copies all values of other to this.
void	countExample(Example example) Increases the prediction value in the matrix.
boolean	formatPercent() Returns true.
java.lang.String	getDescription() Returns the description.
int	getExampleCount() Returns the number of data points which was used to determine the criterion value.
double	getFitness() Returns the accuracy or 1 - error.
double	getMaxFitness() Returns 1.
double	getMikroAverage() Returns either the accuracy or the classification error.
double	getMikroVariance() Returns the variance of the averagable.
java.lang.String	getName() Returns the name.
static MultiClassificationPerformance	newInstance(java.lang.String name) Creates a MultiClassificationPerformance with the given type.
void	readCriterionData(java.io.BufferedReader in) Reads the performance data from the given reader.
void	startCounting(ExampleSet eSet) Initializes the criterion and sets the label.
java.lang.String	toHTML() Returns a HTML table for the confusion matrix.
java.lang.String	toString()
void	writeCriterionData(java.io.PrintWriter out) Writes the performance criterion into the given writer.

Methods inherited from class edu.udo.cs.yale.operator.performance.PerformanceCriterion

compareTo, readPerformanceCriterion, writePerformanceCriterion

Methods inherited from class edu.udo.cs.yale.tools.math.Averagable

buildAverage, clone, formatDeviation, formatValue, getAverage, getMakroAverage, getMakroStandardDeviation, getMakroVariance, getMikroStandardDeviation, getStandardDeviation, getVariance

Methods inherited from class edu.udo.cs.yale.operator.ResultObjectAdapter

addAction, getActions, getVisualisationComponent, toHTML, toResultString

Methods inherited from class edu.udo.cs.yale.operator.AbstractIOObject

copy, read, read, read, write, write

Methods inherited from class java.lang.Object

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

Methods inherited from interface edu.udo.cs.yale.operator.IOObject

copy, write, write

Field Detail

UNDEFINED

public static final int UNDEFINED

Indicates an undefined type (should not happen).

See Also:

Constant Field Values

ACCURACY

public static final int ACCURACY

Indicates accuracy.

See Also:

Constant Field Values

ERROR

public static final int ERROR

Indicates classification error.

See Also:

Constant Field Values

KAPPA

public static final int KAPPA

Indicates kappa statistics.

See Also:

Constant Field Values

NAME

public static final java.lang.String[] NAME

The names of the criteria.

DESCRIPTION

public static final java.lang.String[] DESCRIPTION

The descriptions of the criteria.

counter

private int[][] counter

The counter for true labels and the prediction. First: true label, second: predicted label.

classNames

private java.lang.String[] classNames

The class names of the label. Used for logging and result display.

type

private int type

The type of this performance: accuracy or classification error.

Constructor Detail

MultiClassificationPerformance

public MultiClassificationPerformance()

Creates a MultiClassificationPerformance with undefined type.

MultiClassificationPerformance

public MultiClassificationPerformance(int type)

Creates a MultiClassificationPerformance with the given type.

Method Detail

newInstance

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

Creates a MultiClassificationPerformance with the given type.

writeCriterionData

public void writeCriterionData(java.io.PrintWriter out)
                        throws java.io.IOException

Description copied from class: PerformanceCriterion

Writes the performance criterion into the given writer. Please note that the criterion must be written in a human readable format!

Specified by:

writeCriterionData in class PerformanceCriterion

Throws:

java.io.IOException

readCriterionData

public void readCriterionData(java.io.BufferedReader in)
                       throws java.io.IOException

Description copied from class: PerformanceCriterion

Reads the performance data from the given reader.

Specified by:

readCriterionData in class PerformanceCriterion

Throws:

java.io.IOException

getExampleCount

public int getExampleCount()

Description copied from class: PerformanceCriterion

Returns the number of data points which was used to determine the criterion value.

Specified by:

getExampleCount in class PerformanceCriterion

startCounting

public void startCounting(ExampleSet eSet)

Initializes the criterion and sets the label.

Overrides:

startCounting in class MeasuredPerformance

countExample

public void countExample(Example example)

Increases the prediction value in the matrix.

Specified by:

countExample in class MeasuredPerformance

getMikroAverage

public double getMikroAverage()

Returns either the accuracy or the classification error.

Specified by:

getMikroAverage in class Averagable

formatPercent

public boolean formatPercent()

Returns true.

Overrides:

formatPercent in class Averagable

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()

Returns the name.

Specified by:

getName in interface ResultObject

Specified by:

getName in class Averagable

getDescription

public java.lang.String getDescription()

Returns the description.

Specified by:

getDescription in class MeasuredPerformance

getFitness

public double getFitness()

Returns the accuracy or 1 - error.

Specified by:

getFitness in class PerformanceCriterion

getMaxFitness

public double getMaxFitness()

Returns 1.

Overrides:

getMaxFitness in class PerformanceCriterion

cloneAveragable

protected void cloneAveragable(Averagable newPC)

Description copied from class: Averagable

Must be implemented by subclasses such that it copies all values of other to this. When this method is called, it is guaranteed, that other is a subclass of the class of the object it is called on.

Specified by:

cloneAveragable in class Averagable

buildSingleAverage

public void buildSingleAverage(Averagable performance)

Description copied from class: Averagable

This method should build the average of this and another averagables of the same type. The next invocation of getValue() should return the average of this and the given averagable. Please refer to SimpleCriterion for a simple implementation example.

Specified by:

buildSingleAverage in class Averagable

toString

public java.lang.String toString()

Overrides:

toString in class Averagable

toHTML

public java.lang.String toHTML()

Returns a HTML table for the confusion matrix.

Overrides:

toHTML in class Averagable