entropybasedsplitcrit.java

一个很好的LIBSVM的JAVA源码。对于要研究和改进SVM算法的学者。可以参考。来自数据挖掘工具YALE工具包。

/*
 *  YALE - Yet Another Learning Environment
 *  Copyright (C) 2001-2004
 *      Simon Fischer, Ralf Klinkenberg, Ingo Mierswa, 
 *          Katharina Morik, Oliver Ritthoff
 *      Artificial Intelligence Unit
 *      Computer Science Department
 *      University of Dortmund
 *      44221 Dortmund,  Germany
 *  email: [e-mail]
 *  web:   http://yale.cs.uni-dortmund.de/
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as 
 *  published by the Free Software Foundation; either version 2 of the
 *  License, or (at your option) any later version. 
 *
 *  This program 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 General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
 *  USA.
 */
package edu.udo.cs.yale.operator.learner.decisiontree.y45.j48;

/**
 * "Abstract" class for computing splitting criteria
 * based on the entropy of a class distribution.
 *
 * @author Eibe Frank ([e-mail])
 * @version $Revision: 1.3 $
 */
public abstract class EntropyBasedSplitCrit extends SplitCriterion{

  /** The log of 2. */
  protected static double log2 = Math.log(2);

  /**
   * Help method for computing entropy.
   */
  public final double logFunc(double num) {

    // Constant hard coded for efficiency reasons
    if (num < 1e-6)
      return 0;
    else
      return num*Math.log(num)/log2;
  }

  /**
   * Computes entropy of distribution before splitting.
   */
  public final double oldEnt(Distribution bags) {

    double returnValue = 0;
    int j;

    for (j=0;j<bags.numClasses();j++)
      returnValue = returnValue+logFunc(bags.perClass(j));
    return logFunc(bags.total())-returnValue; 
  }

  /**
   * Computes entropy of distribution after splitting.
   */
  public final double newEnt(Distribution bags) {
    
    double returnValue = 0;
    int i,j;

    for (i=0;i<bags.numBags();i++){
      for (j=0;j<bags.numClasses();j++)
	returnValue = returnValue+logFunc(bags.perClassPerBag(i,j));
      returnValue = returnValue-logFunc(bags.perBag(i));
    }
    return -returnValue;
  }

  /**
   * Computes entropy after splitting without considering the
   * class values.
   */
  public final double splitEnt(Distribution bags) {

    double returnValue = 0;
    int i;

    for (i=0;i<bags.numBags();i++)
      returnValue = returnValue+logFunc(bags.perBag(i));
    return logFunc(bags.total())-returnValue;
  }
}