weka.attributeSelection
Class HoldOutSubsetEvaluator

java.lang.Object
  extended byweka.attributeSelection.ASEvaluation
      extended byweka.attributeSelection.SubsetEvaluator
          extended byweka.attributeSelection.HoldOutSubsetEvaluator
All Implemented Interfaces:
java.io.Serializable
Direct Known Subclasses:
ClassifierSubsetEval

public abstract class HoldOutSubsetEvaluator
extends SubsetEvaluator

Abstract attribute subset evaluator capable of evaluating subsets with respect to a data set that is distinct from that used to initialize/ train the subset evaluator.

Version:
$Revision: 1.3 $
Author:
Mark Hall (mhall@cs.waikato.ac.nz)
See Also:
Serialized Form

Constructor Summary
HoldOutSubsetEvaluator()
           
 
Method Summary
abstract  double evaluateSubset(java.util.BitSet subset, Instance holdOut, boolean retrain)
          Evaluates a subset of attributes with respect to a single instance.
abstract  double evaluateSubset(java.util.BitSet subset, Instances holdOut)
          Evaluates a subset of attributes with respect to a set of instances.
 
Methods inherited from class weka.attributeSelection.SubsetEvaluator
evaluateSubset
 
Methods inherited from class weka.attributeSelection.ASEvaluation
buildEvaluator, forName, makeCopies, postProcess
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

HoldOutSubsetEvaluator

public HoldOutSubsetEvaluator()
Method Detail

evaluateSubset

public abstract double evaluateSubset(java.util.BitSet subset,
                                      Instances holdOut)
                               throws java.lang.Exception
Evaluates a subset of attributes with respect to a set of instances.

Parameters:
subset - a bitset representing the attribute subset to be evaluated
holdOut - a set of instances (possibly seperate and distinct from those use to build/train the evaluator) with which to evaluate the merit of the subset
Returns:
the "merit" of the subset on the holdOut data
Throws:
java.lang.Exception - if the subset cannot be evaluated

evaluateSubset

public abstract double evaluateSubset(java.util.BitSet subset,
                                      Instance holdOut,
                                      boolean retrain)
                               throws java.lang.Exception
Evaluates a subset of attributes with respect to a single instance.

Parameters:
subset - a bitset representing the attribute subset to be evaluated
holdOut - a single instance (possibly not one of those used to build/train the evaluator) with which to evaluate the merit of the subset
retrain - true if the classifier should be retrained with respect to the new subset before testing on the holdOut instance.
Returns:
the "merit" of the subset on the holdOut instance
Throws:
java.lang.Exception - if the subset cannot be evaluated