decorate.java

MacroWeka扩展了著名数据挖掘工具weka

/*
 *    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., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 *    Decorate.java
 *    Copyright (C) 2002 Prem Melville
 *
 */

package weka.classifiers.meta;
import weka.classifiers.*;
import java.util.*;
import weka.core.*;
import weka.experiment.*;

/**
 * DECORATE is a meta-learner for building diverse ensembles of
 * classifiers by using specially constructed artificial training
 * examples. Comprehensive experiments have demonstrated that this
 * technique is consistently more accurate than the base classifier, 
 * Bagging and Random Forests. Decorate also obtains higher accuracy than
 * Boosting on small training sets, and achieves comparable performance
 * on larger training sets.  For more
 * details see: <p>
 *
 * Prem Melville and Raymond J. Mooney. <i>Constructing diverse
 * classifier ensembles using artificial training examples.</i>
 * Proceedings of the Seventeeth International Joint Conference on
 * Artificial Intelligence 2003.<p>
 *
 * Prem Melville and Raymond J. Mooney. <i>Creating diversity in ensembles using artificial data.</i>
 * Submitted.<BR><BR>
 *
 * Valid options are:<p>
 *
 * -D <br>
 * Turn on debugging output.<p>
 *
 * -W classname <br>
 * Specify the full class name of a weak classifier as the basis for 
 * Decorate (default weka.classifiers.trees.J48()).<p>
 *
 * -E num <br>
 * Specify the desired size of the committee (default 10). <p>
 *
 * -I iterations <br>
 * Set the maximum number of Decorate iterations (default 10). <p>
 *
 * -S seed <br>
 * Seed for random number generator. (default 0).<p>
 *
 * -R factor <br>
 * Factor that determines number of artificial examples to generate. <p>
 *
 * Options after -- are passed to the designated classifier.<p>
 *
 * @author Prem Melville ([e-mail])
 * @version $Revision: 1.1 $ */
public class Decorate extends RandomizableIteratedSingleClassifierEnhancer {
      
    /** Vector of classifiers that make up the committee/ensemble. */
    protected Vector m_Committee = null;
    
    /** The desired ensemble size. */
    protected int m_DesiredSize = 10;
    
    /** Amount of artificial/random instances to use - specified as a
        fraction of the training data size. */
    protected double m_ArtSize = 1.0 ;

    /** The random number generator. */
    protected Random m_Random = new Random(0);
    
    /** Attribute statistics - used for generating artificial examples. */
    protected Vector m_AttributeStats = null;

    
  /**
   * Constructor.
   */
  public Decorate() {
    
    m_Classifier = new weka.classifiers.trees.J48();
  }

  /**
   * String describing default classifier.
   */
  protected String defaultClassifierString() {
    
    return "weka.classifiers.trees.J48";
  }
    
    /**
     * Returns an enumeration describing the available options
     *
     * @return an enumeration of all the available options
     */
    public Enumeration listOptions() {
	Vector newVector = new Vector(8);

	newVector.addElement(new Option(
              "\tDesired size of ensemble.\n" 
              + "\t(default 10)",
              "E", 1, "-E"));
	newVector.addElement(new Option(
 	    "\tFactor that determines number of artificial examples to generate.\n"
           +"\tSpecified proportional to training set size.\n" 
          + "\t(default 1.0)",
	    "R", 1, "-R"));

        Enumeration enu = super.listOptions();
        while (enu.hasMoreElements()) {
          newVector.addElement(enu.nextElement());
        }
        return newVector.elements();
    }

    
    /**
     * Parses a given list of options. Valid options are:<p>
     *   
     * -D <br>
     * Turn on debugging output.<p>
     *    
     * -W classname <br>
     * Specify the full class name of a weak classifier as the basis for 
     * Decorate (required).<p>
     *
     * -E num <br>
     * Specify the desired size of the committee (default 10). <p>
     *
     * -I iterations <br>
     * Set the maximum number of Decorate iterations (default 10). <p>
     *
     * -S seed <br>
     * Seed for random number generator. (default 0).<p>
     *
     * -R factor <br>
     * Factor that determines number of artificial examples to generate. <p>
     *
     * Options after -- are passed to the designated classifier.<p>
     *
     * @param options the list of options as an array of strings
     * @exception Exception if an option is not supported
     */
    public void setOptions(String[] options) throws Exception {

	String desiredSize = Utils.getOption('E', options);
	if (desiredSize.length() != 0) {
	    setDesiredSize(Integer.parseInt(desiredSize));
	} else {
	    setDesiredSize(10);
	}
	
	String artSize = Utils.getOption('R', options);
	if (artSize.length() != 0) {
	    setArtificialSize(Double.parseDouble(artSize));
	} else {
	    setArtificialSize(1.0);
	}

        super.setOptions(options);
    }
    
    /**
     * Gets the current settings of the Classifier.
     *
     * @return an array of strings suitable for passing to setOptions
     */
    public String [] getOptions() {

      String [] superOptions = super.getOptions();
      String [] options = new String [superOptions.length + 4];
      
      int current = 0;
      options[current++] = "-E"; options[current++] = "" + getDesiredSize();
      options[current++] = "-R"; options[current++] = "" + getArtificialSize();
      
      System.arraycopy(superOptions, 0, options, current, 
                       superOptions.length);
      
      current += superOptions.length;
      while (current < options.length) {
        options[current++] = "";
      }
      return options;
    }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String desiredSizeTipText() {
      return "the desired number of member classifiers in the Decorate ensemble. Decorate may terminate "
	+"before this size is reached (depending on the value of numIterations). "
	+"Larger ensemble sizes usually lead to more accurate models, but increases "
	+"training time and model complexity.";
  }
    
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String numIterationsTipText() {
    return "the maximum number of Decorate iterations to run. Each iteration generates a classifier, "
	+"but does not necessarily add it to the ensemble. Decorate stops when the desired ensemble "
	+"size is reached. This parameter should be greater than "
	+"equal to the desiredSize. If the desiredSize is not being reached it may help to "
	+"increase this value.";
  }
    
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String artificialSizeTipText() {
    return "determines the number of artificial examples to use during training. Specified as "
	+"a proportion of the training data. Higher values can increase ensemble diversity.";
  }

  /**
   * Returns a string describing classifier
   * @return a description suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
      return "DECORATE is a meta-learner for building diverse ensembles of "
	  +"classifiers by using specially constructed artificial training "
	  +"examples. Comprehensive experiments have demonstrated that this "
	  +"technique is consistently more accurate than the base classifier, Bagging and Random Forests."
	  +"Decorate also obtains higher accuracy than Boosting on small training sets, and achieves "
	  +"comparable performance on larger training sets. "
	  +"For more details see: P. Melville & R. J. Mooney. Constructing diverse classifier ensembles "
	  +"using artificial training examples (IJCAI 2003).\n"
	  +"P. Melville & R. J. Mooney. Creating diversity in ensembles using artificial data (submitted).";
  }

    /**
     * Factor that determines number of artificial examples to generate.
     *
     * @return factor that determines number of artificial examples to generate
     */
    public double getArtificialSize() {
	return m_ArtSize;
    }
  
    /**
     * Sets factor that determines number of artificial examples to generate.
     *
     * @param newwArtSize factor that determines number of artificial examples to generate
     */
    public void setArtificialSize(double newArtSize) {
	m_ArtSize = newArtSize;
    }
    
    /**
     * Gets the desired size of the committee.
     *
     * @return the desired size of the committee
     */
    public int getDesiredSize() {
	return m_DesiredSize;
    }
    
    /**
     * Sets the desired size of the committee.
     *
     * @param newDesiredSize the desired size of the committee
     */
    public void setDesiredSize(int newDesiredSize) {
	m_DesiredSize = newDesiredSize;
    }

    /**
     * Build Decorate classifier
     *
     * @param data the training data to be used for generating the classifier
     * @exception Exception if the classifier could not be built successfully
     */
    public void buildClassifier(Instances data) throws Exception {
	if(m_Classifier == null) {
	    throw new Exception("A base classifier has not been specified!");
	}
	if(data.checkForStringAttributes()) {
	    throw new UnsupportedAttributeTypeException("Cannot handle string attributes!");
	}