holdoutsubsetevaluator.java

一个数据挖掘系统的源码

/**
 *   
 *   AgentAcademy - an open source Data Mining framework for
 *   training intelligent agents
 *
 *   Copyright (C)   2001-2003 AA Consortium.
 *
 *   This library is open source software; you can redistribute it 
 *   and/or modify it under the terms of the GNU Lesser General 
 *   Public License as published by the Free Software Foundation;   
 *   either version 2.0 of the License, or (at your option) any later 
 *   version.
 *
 *   This library is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the    
 *   GNU General Public License for more details.
 *
 *   You should have received a copy of the GNU Lesser General Public
 *   License along with this library; if not, write to the Free 
 *   Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, 
 *   MA  02111-1307 USA
 * 
 */

package org.agentacademy.modules.dataminer.attributeSelection;

import java.util.BitSet;

import org.agentacademy.modules.dataminer.core.Instance;
import org.agentacademy.modules.dataminer.core.Instances;

/** 
 * 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.
 *
 * @author Mark Hall ([e-mail])
 * @version $Revision: 1.2 $
 */
public abstract class HoldOutSubsetEvaluator extends SubsetEvaluator {

  /**
   * Evaluates a subset of attributes with respect to a set of instances.
   * @param subset a bitset representing the attribute subset to be
   * evaluated
   * @param 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
   * @return the "merit" of the subset on the holdOut data
   * @exception Exception if the subset cannot be evaluated
   */
  public abstract double evaluateSubset(BitSet subset, Instances holdOut)
    throws Exception;

  /**
   * Evaluates a subset of attributes with respect to a single instance.
   * @param subset a bitset representing the attribute subset to be
   * evaluated
   * @param holdOut a single instance (possibly not one of those used to
   * build/train the evaluator) with which to evaluate the merit of the subset
   * @param retrain true if the classifier should be retrained with respect
   * to the new subset before testing on the holdOut instance.
   * @return the "merit" of the subset on the holdOut instance
   * @exception Exception if the subset cannot be evaluated
   */
  public abstract double evaluateSubset(BitSet subset, 
					Instance holdOut,
					boolean retrain)
    throws Exception;
}