infogainsplitcrit.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 information gain for a given distribution.
 *
 * @author Eibe Frank ([e-mail])
 * @version $Revision: 1.3 $
 */
public final class InfoGainSplitCrit extends EntropyBasedSplitCrit{

  /**
   * This method is a straightforward implementation of the information
   * gain criterion for the given distribution.
   */
  public final double splitCritValue(Distribution bags) {

    double numerator;
        
    numerator = oldEnt(bags)-newEnt(bags);

    // Splits with no gain are useless.
    if (Utils.eq(numerator,0))
      return Double.MAX_VALUE;
        
    // We take the reciprocal value because we want to minimize the
    // splitting criterion's value.
    return bags.total()/numerator;
  }

  /**
   * This method computes the information gain in the same way 
   * C4.5 does.
   *
   * @param distribution the distribution
   * @param totalNoInst weight of ALL instances (including the
   * ones with missing values).
   */
  public final double splitCritValue(Distribution bags,double totalNoInst) {
    
    double numerator;
    double noUnknown;
    double unknownRate;
    int i;
    
    noUnknown = totalNoInst-bags.total();
    unknownRate = noUnknown/totalNoInst;
    numerator = (oldEnt(bags)-newEnt(bags));
    numerator = (1-unknownRate)*numerator;
    
    // Splits with no gain are useless.
    if (Utils.eq(numerator,0))
      return 0;
    
    return numerator/bags.total();
  }

  /**
   * This method computes the information gain in the same way 
   * C4.5 does.
   *
   * @param distribution the distribution
   * @param totalNoInst weight of ALL instances 
   * @param oldEnt entropy with respect to "no-split"-model.
   */
  public final double splitCritValue(Distribution bags,double totalNoInst,
                                     double oldEnt) {
    
    double numerator;
    double noUnknown;
    double unknownRate;
    int i;
    
    noUnknown = totalNoInst-bags.total();
    unknownRate = noUnknown/totalNoInst;
    numerator = (oldEnt-newEnt(bags));
    numerator = (1-unknownRate)*numerator;
    
    // Splits with no gain are useless.
    if (Utils.eq(numerator,0))
      return 0;
    
    return numerator/bags.total();
  }
}