weka.classifiers.functions.loss

Class ApproximateAbsoluteError

java.lang.Object

weka.classifiers.functions.loss.ApproximateAbsoluteError

All Implemented Interfaces:

java.io.Serializable, LossFunction, weka.core.OptionHandler

public class ApproximateAbsoluteError
extends java.lang.Object
implements LossFunction, weka.core.OptionHandler

Approximate absolute error for MLPRegressor and MLPClassifier:
loss(a, b) = sqrt((a-b)^2+epsilon)

Valid options are:

 -E <double>
  Epsilon to be added (default: 0.01).

Version:

$Revision: 10949 $

Author:

Eibe Frank (eibe@cs.waikato.ac.nz)

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ApproximateAbsoluteError()

Method Summary

Modifier and Type	Method and Description
double	derivative(double pred, double actual) The derivative of the loss with respect to the predicted value
java.lang.String	epsilonTipText()
double	getEpsilon() Returns the value of the epsilon parameter.
java.lang.String[]	getOptions() Gets the current settings of the loss function.
java.lang.String	globalInfo() This will return a string describing the classifier.
java.util.Enumeration<weka.core.Option>	listOptions() Returns an enumeration describing the available options.
double	loss(double pred, double actual) Returns the loss.
void	setEpsilon(double epsilon) Sets the value of the epsilon parameter.
void	setOptions(java.lang.String[] options) Parses a given list of options.

Methods inherited from class java.lang.Object

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

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

ApproximateAbsoluteError

public ApproximateAbsoluteError()

Method Detail

globalInfo

public java.lang.String globalInfo()

This will return a string describing the classifier.

Returns:

The string.

loss

public double loss(double pred,
                   double actual)

Returns the loss.

Specified by:

loss in interface LossFunction

Parameters:

pred - predicted target value

actual - actual target value

Returns:

the loss

derivative

public double derivative(double pred,
                         double actual)

The derivative of the loss with respect to the predicted value

Specified by:

derivative in interface LossFunction

Parameters:

pred - predicted target value

actual - actual target value

Returns:

the value of the derivative

epsilonTipText

public java.lang.String epsilonTipText()

Returns:

a string to describe the option

getEpsilon

public double getEpsilon()

Returns the value of the epsilon parameter.

Returns:

the value of the epsilon parameter.

setEpsilon

public void setEpsilon(double epsilon)

Sets the value of the epsilon parameter.

Parameters:

epsilon - the value of the epsilon parameter.

listOptions

public java.util.Enumeration<weka.core.Option> listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface weka.core.OptionHandler

Returns:

an enumeration of all the available options.

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Valid options are:

 -E <double>
  Epsilon to be added (default: 0.01).

Specified by:

setOptions in interface weka.core.OptionHandler

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the loss function.

Specified by:

getOptions in interface weka.core.OptionHandler

Returns:

an array of strings suitable for passing to setOptions