distributionclassifier.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.classifiers.evaluation;

/**
 * <p>Title: The Data Miner prototype</p>
 * <p>Description: A prototype for the DataMiner (DM), the Agent Academy (AA) module responsible for performing data mining on the contents of the Agent Use Repository (AUR). The extracted knowledge is to be sent back to the AUR in the form of a PMML document.</p>
 * <p>Copyright: Copyright (c) 2002</p>
 * <p>Company: CERTH</p>
 * @author asymeon
 * @version 0.3
 */

import  org.agentacademy.modules.dataminer.core.*;

/**
 * Abstract classification model that produces (for each test instance)
 * an estimate of the membership in each class
 * (ie. a probability distribution).
 *
 */
public abstract class DistributionClassifier extends Classifier {

  /**
   * Predicts the class memberships for a given instance. If
   * an instance is unclassified, the returned array elements
   * must be all zero. If the class is numeric, the array
   * must consist of only one element, which contains the
   * predicted value.
   *
   * @param instance the instance to be classified
   * @return an array containing the estimated membership
   * probabilities of the test instance in each class (this
   * should sum to at most 1)
   * @exception Exception if distribution could not be
   * computed successfully
   */
  public abstract double[] distributionForInstance(Instance instance)
       throws Exception;

  /**
   * Classifies the given test instance. The instance has to belong to a
   * dataset when it's being classified.
   *
   * @param instance the instance to be classified
   * @return the predicted most likely class for the instance or
   * Instance.missingValue() if no prediction is made
   * @exception Exception if an error occurred during the prediction
   */
  public double classifyInstance(Instance instance) throws Exception {

    double [] dist = distributionForInstance(instance);
    if (dist == null) {
      throw new Exception("Null distribution predicted");
    }
    switch (instance.classAttribute().type()) {
    case Attribute.NOMINAL:
      double max = 0;
      int maxIndex = 0;

      for (int i = 0; i < dist.length; i++) {
	if (dist[i] > max) {
	  maxIndex = i;
	  max = dist[i];
	}
      }
      if (max > 0) {
	return maxIndex;
      } else {
	return Instance.missingValue();
      }
    case Attribute.NUMERIC:
      return dist[0];
    default:
      return Instance.missingValue();
    }
  }
}