decorate.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

/*
 *    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 java.util.Enumeration;
import java.util.Random;
import java.util.Vector;

import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.UnsupportedAttributeTypeException;
import weka.core.UnsupportedClassTypeException;
import weka.core.Utils;

/**
 * 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>
 *
 * -I num <br>
 * Specify the desired size of the committee (default 15). <p>
 *
 * -M iterations <br>
 * Set the maximum number of Decorate iterations (default 50). <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 $Revision$ */
public class Decorate extends Classifier implements OptionHandler{

    /** Set to true to get debugging output. */
    protected boolean m_Debug = false;

    /** The model base classifier to use. */
    protected Classifier m_Classifier = new weka.classifiers.trees.J48();
      
    /** Vector of classifiers that make up the committee/ensemble. */
    protected Vector m_Committee = null;
    
    /** The desired ensemble size. */
    protected int m_DesiredSize = 15;

    /** The maximum number of Decorate iterations to run. */
    protected int m_NumIterations = 50;
    
    /** The seed for random number generation. */
    protected int m_Seed = 0;
    
    /** 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;

    
    /**
     * 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(
	      "\tTurn on debugging output.",
	      "D", 0, "-D"));
	newVector.addElement(new Option(
              "\tDesired size of ensemble.\n" 
              + "\t(default 15)",
              "I", 1, "-I"));
	newVector.addElement(new Option(
	      "\tMaximum number of Decorate iterations.\n"
	      + "\t(default 50)",
	      "M", 1, "-M"));
	newVector.addElement(new Option(
	      "\tFull name of base classifier.\n"
	      + "\t(default weka.classifiers.trees.J48)",
	      "W", 1, "-W"));
	newVector.addElement(new Option(
              "\tSeed for random number generator.\n"
	      +"\tIf set to -1, use a random seed.\n"
              + "\t(default 0)",
              "S", 1, "-S"));
	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"));
    
	if ((m_Classifier != null) &&
	    (m_Classifier instanceof OptionHandler)) {
	    newVector.addElement(new Option(
					    "",
					    "", 0, "\nOptions specific to classifier "
					    + m_Classifier.getClass().getName() + ":"));
	    Enumeration em = ((OptionHandler)m_Classifier).listOptions();
	    while (em.hasMoreElements()) {
		newVector.addElement(em.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>
     *
     * -I num <br>
     * Specify the desired size of the committee (default 15). <p>
     *
     * -M iterations <br>
     * Set the maximum number of Decorate iterations (default 50). <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 {
	setDebug(Utils.getFlag('D', options));

	String desiredSize = Utils.getOption('I', options);
	if (desiredSize.length() != 0) {
	    setDesiredSize(Integer.parseInt(desiredSize));
	} else {
	    setDesiredSize(15);
	}

	String maxIterations = Utils.getOption('M', options);
	if (maxIterations.length() != 0) {
	    setNumIterations(Integer.parseInt(maxIterations));
	} else {
	    setNumIterations(50);
	}
	
	String seed = Utils.getOption('S', options);
	if (seed.length() != 0) {
	    setSeed(Integer.parseInt(seed));
	} else {
	    setSeed(0);
	}
	
	String artSize = Utils.getOption('R', options);
	if (artSize.length() != 0) {
	    setArtificialSize(Double.parseDouble(artSize));
	} else {
	    setArtificialSize(1.0);
	}
	
	String classifierName = Utils.getOption('W', options);
	if (classifierName.length() != 0) {
	  setClassifier(Classifier.forName(classifierName,
					   Utils.partitionOptions(options)));
	}
    }
    
    /**
     * Gets the current settings of the Classifier.
     *
     * @return an array of strings suitable for passing to setOptions
     */
    public String [] getOptions() {
	String [] classifierOptions = new String [0];
	if ((m_Classifier != null) && 
	    (m_Classifier instanceof OptionHandler)) {
	    classifierOptions = ((OptionHandler)m_Classifier).getOptions();
	}
	String [] options = new String [classifierOptions.length + 12];
	int current = 0;
	if (getDebug()) {
	    options[current++] = "-D";
	}
	options[current++] = "-S"; options[current++] = "" + getSeed();
	options[current++] = "-I"; options[current++] = "" + getDesiredSize();
	options[current++] = "-M"; options[current++] = "" + getNumIterations();
	options[current++] = "-R"; options[current++] = "" + getArtificialSize();
	
	if (getClassifier() != null) {
	    options[current++] = "-W";
	    options[current++] = getClassifier().getClass().getName();
	}
	options[current++] = "--";
	System.arraycopy(classifierOptions, 0, options, current, 
			 classifierOptions.length);
	current += classifierOptions.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 the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String seedTipText() {
    return "seed for random number generator used for creating artificial data."
	+" Set to -1 to use a random seed.";
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
b   */
  public String classifierTipText() {
    return "the desired base learner for the ensemble.";
  }

  /**
   * 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).";
  }

    
    /**
     * Set debugging mode
     *
     * @param debug true if debug output should be printed
     */
    public void setDebug(boolean debug) {
	m_Debug = debug;
    }
    
    /**
     * Get whether debugging is turned on
     *
     * @return true if debugging output is on
     */
    public boolean getDebug() {
	return m_Debug;
    }
    
    /**
     * Set the base classifier for Decorate.
     *
     * @param newClassifier the Classifier to use.
     */
    public void setClassifier(Classifier newClassifier) {
	m_Classifier = newClassifier;
    }

    /**
     * Get the classifier used as the base classifier
     *
     * @return the classifier used as the classifier
     */
    public Classifier getClassifier() {
	return m_Classifier;
    }

    /**
     * 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;
    }
  
    /**