edu.udo.cs.yale.tools.math
Class Averagable

java.lang.Object
  edu.udo.cs.yale.operator.AbstractIOObject
      edu.udo.cs.yale.operator.ResultObjectAdapter
          edu.udo.cs.yale.tools.math.Averagable

All Implemented Interfaces:

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

Direct Known Subclasses:

AttributeWeight, PerformanceCriterion

public abstract class Averagable
extends ResultObjectAdapter
implements java.lang.Cloneable, java.lang.Comparable<Averagable>

Superclass for all objects which can be averaged. Averagable objects can be stored in a average vector.

Version:

$Id: Averagable.java,v 1.18 2006/08/03 14:39:34 ingomierswa Exp $

Author:

Ingo Mierswa

Field Summary

private int	averageCount Counts the number of times, build average was executed.
private double	meanSquaredSum The squared averages are summed up each time buildAverage is called.
private double	meanSum The averages are summed up each time buildAverage is called.

Constructor Summary

Averagable()

Method Summary

void	buildAverage(Averagable averagable) This method builds the makro average of two averagables of the same type.
protected abstract void	buildSingleAverage(Averagable averagable) This method should build the average of this and another averagables of the same type.
java.lang.Object	clone() Returns a (deep) clone of this averagable.
protected abstract void	cloneAveragable(Averagable other) Must be implemented by subclasses such that it copies all values of other to this.
protected java.lang.String	formatDeviation(double dev) Formats the standard deviation for the toString() method.
boolean	formatPercent() Indicates wether or not percentage format should be used in the toString() method.
protected java.lang.String	formatValue(double value) Formats the value for the toString() method.
double	getAverage() This method returns the makro average if it was defined and the mikro average (the current value) otherwise.
double	getMakroAverage() Returns the average value of all performance criteria average by using the buildAverage(Averagable) method.
double	getMakroStandardDeviation() Returns the standard deviation of all performance criteria average by using the buildAverage(Averagable) method.
double	getMakroVariance() Returns the variance of all performance criteria average by using the buildAverage(Averagable) method.
abstract double	getMikroAverage() Returns the (current) value of the averagable (the average itself).
double	getMikroStandardDeviation() Returns the standard deviation of the performance criterion.
abstract double	getMikroVariance() Returns the variance of the averagable.
abstract java.lang.String	getName() Returns the name of this averagable.
double	getStandardDeviation() This method returns the makro standard deviation if it was defined and the mikro standard deviation otherwise.
double	getVariance() This method returns the makro variance if it was defined and the mikro variance otherwise.
java.lang.String	toHTML() Returns a HTML result string.
java.lang.String	toString()

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 java.lang.Comparable

compareTo

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

copy, write, write

Field Detail

meanSum

private double meanSum

The averages are summed up each time buildAverage is called.

meanSquaredSum

private double meanSquaredSum

The squared averages are summed up each time buildAverage is called.

averageCount

private int averageCount

Counts the number of times, build average was executed.

Constructor Detail

Averagable

public Averagable()

Method Detail

getName

public abstract java.lang.String getName()

Returns the name of this averagable.

Specified by:

getName in interface ResultObject

Overrides:

getName in class ResultObjectAdapter

getMikroAverage

public abstract double getMikroAverage()

Returns the (current) value of the averagable (the average itself).

getMikroVariance

public abstract double getMikroVariance()

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.

cloneAveragable

protected abstract void cloneAveragable(Averagable other)

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.

buildSingleAverage

protected abstract void buildSingleAverage(Averagable 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.

buildAverage

public final void buildAverage(Averagable averagable)

This method builds the makro average of two averagables of the same type. First this method checks if the classes of this and performance are the same and if the getName() methods return the same String. Otherwise a RuntimeException is thrown.
The value of averagable.getMikroAverage() is added to meanSum, its square is added to meanSquaredSum and averageCount is increased by one. These values are used in the getMakroAverage() and getMakroVariance() methods.
Subclasses should implement the method buildSingleAverage() to build the mikro (weighted) average of this averagable and the given averagable. They must be weighted by the number of examples used for calculating the averagables.

getAverage

public final double getAverage()

This method returns the makro average if it was defined and the mikro average (the current value) otherwise. This method should be used instead of for optimization purposes, i.e. by methods like getFitness() of performance criteria.

getVariance

public final double getVariance()

This method returns the makro variance if it was defined and the mikro variance otherwise.

getStandardDeviation

public final double getStandardDeviation()

This method returns the makro standard deviation if it was defined and the mikro standard deviation otherwise.

getMikroStandardDeviation

public final double getMikroStandardDeviation()

Returns the standard deviation of the performance criterion.

getMakroAverage

public final double getMakroAverage()

Returns the average value of all performance criteria average by using the buildAverage(Averagable) method.

getMakroVariance

public final double getMakroVariance()

Returns the variance of all performance criteria average by using the buildAverage(Averagable) method.

getMakroStandardDeviation

public final double getMakroStandardDeviation()

Returns the standard deviation of all performance criteria average by using the buildAverage(Averagable) method.

clone

public java.lang.Object clone()

Returns a (deep) clone of this averagable.

Overrides:

clone in class java.lang.Object

formatPercent

public boolean formatPercent()

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

formatValue

protected java.lang.String formatValue(double value)

Formats the value for the toString() method.

formatDeviation

protected java.lang.String formatDeviation(double dev)

Formats the standard deviation for the toString() method.

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

toHTML

public java.lang.String toHTML()

Returns a HTML result string. Default implementation returns toString().