adaboostm1.java

代码是一个分类器的实现,其中使用了部分weka的源代码。可以将项目导入eclipse运行

/*
 *    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.
 */

/*
 *    AdaBoostM1.java
 *    Copyright (C) 1999 Eibe Frank,Len Trigg
 *
 */

package weka.classifiers.meta;

import weka.classifiers.Evaluation;
import weka.classifiers.RandomizableIteratedSingleClassifierEnhancer;
import weka.classifiers.Sourcable;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.Randomizable;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.WeightedInstancesHandler;
import weka.core.Capabilities.Capability;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;

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

/**
 <!-- globalinfo-start -->
 * Class for boosting a nominal class classifier using the Adaboost M1 method. Only nominal class problems can be tackled. Often dramatically improves performance, but sometimes overfits.<br/>
 * <br/>
 * For more information, see<br/>
 * <br/>
 * Yoav Freund, Robert E. Schapire: Experiments with a new boosting algorithm. In: Thirteenth International Conference on Machine Learning, San Francisco, 148-156, 1996.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;inproceedings{Freund1996,
 *    address = {San Francisco},
 *    author = {Yoav Freund and Robert E. Schapire},
 *    booktitle = {Thirteenth International Conference on Machine Learning},
 *    pages = {148-156},
 *    publisher = {Morgan Kaufmann},
 *    title = {Experiments with a new boosting algorithm},
 *    year = {1996}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -P &lt;num&gt;
 *  Percentage of weight mass to base training on.
 *  (default 100, reduce to around 90 speed up)</pre>
 * 
 * <pre> -Q
 *  Use resampling for boosting.</pre>
 * 
 * <pre> -S &lt;num&gt;
 *  Random number seed.
 *  (default 1)</pre>
 * 
 * <pre> -I &lt;num&gt;
 *  Number of iterations.
 *  (default 10)</pre>
 * 
 * <pre> -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console</pre>
 * 
 * <pre> -W
 *  Full name of base classifier.
 *  (default: weka.classifiers.trees.DecisionStump)</pre>
 * 
 * <pre> 
 * Options specific to classifier weka.classifiers.trees.DecisionStump:
 * </pre>
 * 
 * <pre> -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console</pre>
 * 
 <!-- options-end -->
 *
 * Options after -- are passed to the designated classifier.<p>
 *
 * @author Eibe Frank ([e-mail])
 * @author Len Trigg ([e-mail])
 * @version $Revision: 1.34 $ 
 */
public class AdaBoostM1 
  extends RandomizableIteratedSingleClassifierEnhancer 
  implements WeightedInstancesHandler, Sourcable, TechnicalInformationHandler {

  /** for serialization */
  static final long serialVersionUID = -7378107808933117974L;
  
  /** Max num iterations tried to find classifier with non-zero error. */ 
  private static int MAX_NUM_RESAMPLING_ITERATIONS = 10;
  
  /** Array for storing the weights for the votes. */
  protected double [] m_Betas;

  /** The number of successfully generated base classifiers. */
  protected int m_NumIterationsPerformed;

  /** Weight Threshold. The percentage of weight mass used in training */
  protected int m_WeightThreshold = 100;

  /** Use boosting with reweighting? */
  protected boolean m_UseResampling;

  /** The number of classes */
  protected int m_NumClasses;
  
  /**
   * Constructor.
   */
  public AdaBoostM1() {
    
    m_Classifier = new weka.classifiers.trees.DecisionStump();
  }
    
  /**
   * Returns a string describing classifier
   * @return a description suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
 
    return "Class for boosting a nominal class classifier using the Adaboost "
      + "M1 method. Only nominal class problems can be tackled. Often "
      + "dramatically improves performance, but sometimes overfits.\n\n"
      + "For more information, see\n\n"
      + getTechnicalInformation().toString();
  }

  /**
   * Returns an instance of a TechnicalInformation object, containing 
   * detailed information about the technical background of this class,
   * e.g., paper reference or book this class is based on.
   * 
   * @return the technical information about this class
   */
  public TechnicalInformation getTechnicalInformation() {
    TechnicalInformation 	result;
    
    result = new TechnicalInformation(Type.INPROCEEDINGS);
    result.setValue(Field.AUTHOR, "Yoav Freund and Robert E. Schapire");
    result.setValue(Field.TITLE, "Experiments with a new boosting algorithm");
    result.setValue(Field.BOOKTITLE, "Thirteenth International Conference on Machine Learning");
    result.setValue(Field.YEAR, "1996");
    result.setValue(Field.PAGES, "148-156");
    result.setValue(Field.PUBLISHER, "Morgan Kaufmann");
    result.setValue(Field.ADDRESS, "San Francisco");
    
    return result;
  }

  /**
   * String describing default classifier.
   * 
   * @return the default classifier classname
   */
  protected String defaultClassifierString() {
    
    return "weka.classifiers.trees.DecisionStump";
  }

  /**
   * Select only instances with weights that contribute to 
   * the specified quantile of the weight distribution
   *
   * @param data the input instances
   * @param quantile the specified quantile eg 0.9 to select 
   * 90% of the weight mass
   * @return the selected instances
   */
  protected Instances selectWeightQuantile(Instances data, double quantile) { 

    int numInstances = data.numInstances();
    Instances trainData = new Instances(data, numInstances);
    double [] weights = new double [numInstances];

    double sumOfWeights = 0;
    for(int i = 0; i < numInstances; i++) {
      weights[i] = data.instance(i).weight();
      sumOfWeights += weights[i];
    }
    double weightMassToSelect = sumOfWeights * quantile;
    int [] sortedIndices = Utils.sort(weights);

    // Select the instances
    sumOfWeights = 0;
    for(int i = numInstances - 1; i >= 0; i--) {
      Instance instance = (Instance)data.instance(sortedIndices[i]).copy();
      trainData.add(instance);
      sumOfWeights += weights[sortedIndices[i]];
      if ((sumOfWeights > weightMassToSelect) && 
	  (i > 0) && 
	  (weights[sortedIndices[i]] != weights[sortedIndices[i - 1]])) {
	break;
      }
    }
    if (m_Debug) {
      System.err.println("Selected " + trainData.numInstances()
			 + " out of " + numInstances);
    }
    return trainData;
  }

  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {

    Vector newVector = new Vector();

    newVector.addElement(new Option(
	"\tPercentage of weight mass to base training on.\n"
	+"\t(default 100, reduce to around 90 speed up)",
	"P", 1, "-P <num>"));
    
    newVector.addElement(new Option(
	"\tUse resampling for boosting.",
	"Q", 0, "-Q"));

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


  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -P &lt;num&gt;
   *  Percentage of weight mass to base training on.
   *  (default 100, reduce to around 90 speed up)</pre>
   * 
   * <pre> -Q
   *  Use resampling for boosting.</pre>
   * 
   * <pre> -S &lt;num&gt;
   *  Random number seed.
   *  (default 1)</pre>
   * 
   * <pre> -I &lt;num&gt;
   *  Number of iterations.
   *  (default 10)</pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   * <pre> -W
   *  Full name of base classifier.
   *  (default: weka.classifiers.trees.DecisionStump)</pre>
   * 
   * <pre> 
   * Options specific to classifier weka.classifiers.trees.DecisionStump:
   * </pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   <!-- options-end -->
   *
   * Options after -- are passed to the designated classifier.<p>
   *
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {

    String thresholdString = Utils.getOption('P', options);
    if (thresholdString.length() != 0) {
      setWeightThreshold(Integer.parseInt(thresholdString));
    } else {
      setWeightThreshold(100);
    }
      
    setUseResampling(Utils.getFlag('Q', options));

    super.setOptions(options);
  }

  /**
   * Gets the current settings of the Classifier.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {
    Vector        result;
    String[]      options;
    int           i;
    
    result  = new Vector();

    options = super.getOptions();
    for (i = 0; i < options.length; i++)
      result.add(options[i]);

    if (getUseResampling())
      result.add("-Q");

    result.add("-P");
    result.add("" + getWeightThreshold());
    
    return (String[]) result.toArray(new String[result.size()]);
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String weightThresholdTipText() {
    return "Weight threshold for weight pruning.";
  }

  /**
   * Set weight threshold
   *
   * @param threshold the percentage of weight mass used for training
   */
  public void setWeightThreshold(int threshold) {

    m_WeightThreshold = threshold;
  }

  /**
   * Get the degree of weight thresholding
   *
   * @return the percentage of weight mass used for training
   */
  public int getWeightThreshold() {

    return m_WeightThreshold;