clusterer.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.clusterers;

/**
 * <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 java.io.Serializable;
import org.agentacademy.modules.dataminer.core.*;

/**
 * Abstract clusterer.
 *
 */
public abstract class Clusterer implements Cloneable, Serializable {

  // ===============
  // Public methods.
  // ===============

  /**
   * Generates a clusterer. Has to initialize all fields of the clusterer
   * that are not being set via options.
   *
   * @param data set of instances serving as training data
   * @exception Exception if the clusterer has not been
   * generated successfully
   */
  public abstract void buildClusterer(Instances data) throws Exception;

  /**
   * Classifies a given instance.
   *
   * @param instance the instance to be assigned to a cluster
   * @return the number of the assigned cluster as an interger
   * if the class is enumerated, otherwise the predicted value
   * @exception Exception if instance could not be classified
   * successfully
   */
  public abstract int clusterInstance(Instance instance) throws Exception;

  /**
   * Returns the number of clusters.
   *
   * @return the number of clusters generated for a training dataset.
   * @exception Exception if number of clusters could not be returned
   * successfully
   */
  public abstract int numberOfClusters() throws Exception;

  /**
   * Creates a new instance of a clusterer given it's class name and
   * (optional) arguments to pass to it's setOptions method. If the
   * clusterer implements OptionHandler and the options parameter is
   * non-null, the clusterer will have it's options set.
   *
   * @param searchName the fully qualified class name of the clusterer
   * @param options an array of options suitable for passing to setOptions. May
   * be null.
   * @return the newly created search object, ready for use.
   * @exception Exception if the clusterer class name is invalid, or the
   * options supplied are not acceptable to the clusterer.
   */
  public static Clusterer forName(String clustererName,
				  String [] options) throws Exception
  {
    return (Clusterer)Utils.forName(Clusterer.class,
				    clustererName,
				    options);
  }

  /**
   * Creates copies of the current clusterer. Note that this method
   * now uses Serialization to perform a deep copy, so the Clusterer
   * object must be fully Serializable. Any currently built model will
   * now be copied as well.
   *
   * @param model an example clusterer to copy
   * @param num the number of clusterer copies to create.
   * @return an array of clusterers.
   * @exception Exception if an error occurs
   */
  public static Clusterer [] makeCopies(Clusterer model,
					int num) throws Exception {
     if (model == null) {
      throw new Exception("No model clusterer set");
    }
    Clusterer [] clusterers = new Clusterer [num];
    SerializedObject so = new SerializedObject(model);
    for(int i = 0; i < clusterers.length; i++) {
      clusterers[i] = (Clusterer) so.getObject();
    }
    return clusterers;
  }
}