entropysplitcrit.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;

import weka.core.*;

/**
 * Class for computing the entropy for a given distribution.
 *
 * @author Eibe Frank ([e-mail])
 * @version $Revision: 1.3 $
 */
public final class EntropySplitCrit extends EntropyBasedSplitCrit {

  /**
   * Computes entropy for given distribution.
   */
  public final double splitCritValue(Distribution bags) {
    
    return newEnt(bags);
  }

  /**
   * Computes entropy of test distribution with respect to training distribution.
   */
  public final double splitCritValue(Distribution train, Distribution test) {

    double result = 0;
    int numClasses = 0;
    int i, j;
    
    // Find out relevant number of classes
    for (j = 0; j < test.numClasses(); j++)
      if (Utils.gr(train.perClass(j), 0) || Utils.gr(test.perClass(j), 0))
	numClasses++;

    // Compute entropy of test data with respect to training data
    for (i = 0; i < test.numBags(); i++)
      if (Utils.gr(test.perBag(i),0)) {
	for (j = 0; j < test.numClasses(); j++)
	  if (Utils.gr(test.perClassPerBag(i, j), 0))
	    result -= test.perClassPerBag(i, j)*
	      Math.log(train.perClassPerBag(i, j) + 1);
	result += test.perBag(i) * Math.log(train.perBag(i) + numClasses);
      }
  
    return result / log2;
  }
}