All Downloads are FREE. Search and download functionalities are using the official Maven repository.

weka.classifiers.trees.j48.InfoGainSplitCrit Maven / Gradle / Ivy

Go to download

The Waikato Environment for Knowledge Analysis (WEKA), a machine learning workbench. This version represents the developer version, the "bleeding edge" of development, you could say. New functionality gets added to this version.

There is a newer version: 3.9.6
Show newest version
/*
 *   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 3 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, see .
 */

/*
 *    InfoGainSplitCrit.java
 *    Copyright (C) 1999-2012 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.classifiers.trees.j48;

import weka.core.RevisionUtils;
import weka.core.Utils;

/**
 * Class for computing the information gain for a given distribution.
 * 
 * @author Eibe Frank ([email protected])
 * @version $Revision: 10169 $
 */
public final class InfoGainSplitCrit extends EntropyBasedSplitCrit {

  /** for serialization */
  private static final long serialVersionUID = 4892105020180728499L;

  /**
   * This method is a straightforward implementation of the information gain
   * criterion for the given distribution.
   */
  @Override
  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 bags 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;
    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 bags 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;
    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();
  }

  /**
   * Returns the revision string.
   * 
   * @return the revision
   */
  @Override
  public String getRevision() {
    return RevisionUtils.extract("$Revision: 10169 $");
  }
}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy