weka.classifiers.misc.monotone
Class ZeroOneLossFunction

java.lang.Object
  extended by weka.classifiers.misc.monotone.ZeroOneLossFunction
All Implemented Interfaces:
NominalLossFunction, RevisionHandler

public class ZeroOneLossFunction
extends java.lang.Object
implements NominalLossFunction, RevisionHandler

Class implementing the zero-one loss function, this is an incorrect prediction always accounts for one unit loss.

This implementation is done as part of the master's thesis: "Studie en implementatie van instantie-gebaseerde algoritmen voor gesuperviseerd rangschikken", Stijn Lievens, Ghent University, 2004.

Version:
$Revision: 1.2 $
Author:
Stijn Lievens (stijn.lievens@ugent.be)

Constructor Summary
ZeroOneLossFunction()
           
 
Method Summary
 java.lang.String getRevision()
          Returns the revision string.
 double loss(double actual, double predicted)
          Returns the zero-one loss function between two class values.
 java.lang.String toString()
          Returns a string with the name of the loss function.
 
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Constructor Detail

ZeroOneLossFunction

public ZeroOneLossFunction()
Method Detail

loss

public final double loss(double actual,
                         double predicted)
Returns the zero-one loss function between two class values.

Specified by:
loss in interface NominalLossFunction
Parameters:
actual - the actual class value
predicted - the predicted class value
Returns:
1 if the actual and predicted value differ, 0 otherwise

toString

public java.lang.String toString()
Returns a string with the name of the loss function.

Overrides:
toString in class java.lang.Object
Returns:
a string with the name of the loss function

getRevision

public java.lang.String getRevision()
Returns the revision string.

Specified by:
getRevision in interface RevisionHandler
Returns:
the revision