bagging.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.
 */

/*
 *    Bagging.java
 *    Copyright (C) 1999 Eibe Frank
 *
 */

package weka.classifiers.meta;

import weka.classifiers.RandomizableIteratedSingleClassifierEnhancer;
import weka.core.AdditionalMeasureProducer;
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.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;

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

/**
 <!-- globalinfo-start -->
 * Class for bagging a classifier to reduce variance. Can do classification and regression depending on the base learner. <br/>
 * <br/>
 * For more information, see<br/>
 * <br/>
 * Leo Breiman (1996). Bagging predictors. Machine Learning. 24(2):123-140.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;article{Breiman1996,
 *    author = {Leo Breiman},
 *    journal = {Machine Learning},
 *    number = {2},
 *    pages = {123-140},
 *    title = {Bagging predictors},
 *    volume = {24},
 *    year = {1996}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -P
 *  Size of each bag, as a percentage of the
 *  training set size. (default 100)</pre>
 * 
 * <pre> -O
 *  Calculate the out of bag error.</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.REPTree)</pre>
 * 
 * <pre> 
 * Options specific to classifier weka.classifiers.trees.REPTree:
 * </pre>
 * 
 * <pre> -M &lt;minimum number of instances&gt;
 *  Set minimum number of instances per leaf (default 2).</pre>
 * 
 * <pre> -V &lt;minimum variance for split&gt;
 *  Set minimum numeric class variance proportion
 *  of train variance for split (default 1e-3).</pre>
 * 
 * <pre> -N &lt;number of folds&gt;
 *  Number of folds for reduced error pruning (default 3).</pre>
 * 
 * <pre> -S &lt;seed&gt;
 *  Seed for random data shuffling (default 1).</pre>
 * 
 * <pre> -P
 *  No pruning.</pre>
 * 
 * <pre> -L
 *  Maximum tree depth (default -1, no maximum)</pre>
 * 
 <!-- options-end -->
 *
 * Options after -- are passed to the designated classifier.<p>
 *
 * @author Eibe Frank ([e-mail])
 * @author Len Trigg ([e-mail])
 * @author Richard Kirkby ([e-mail])
 * @version $Revision: 1.37 $
 */
public class Bagging
  extends RandomizableIteratedSingleClassifierEnhancer 
  implements WeightedInstancesHandler, AdditionalMeasureProducer,
             TechnicalInformationHandler {

  /** for serialization */
  static final long serialVersionUID = -505879962237199703L;
  
  /** The size of each bag sample, as a percentage of the training size */
  protected int m_BagSizePercent = 100;

  /** Whether to calculate the out of bag error */
  protected boolean m_CalcOutOfBag = false;

  /** The out of bag error that has been calculated */
  protected double m_OutOfBagError;  
    
  /**
   * Constructor.
   */
  public Bagging() {
    
    m_Classifier = new weka.classifiers.trees.REPTree();
  }
  
  /**
   * Returns a string describing classifier
   * @return a description suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
 
    return "Class for bagging a classifier to reduce variance. Can do classification "
      + "and regression depending on the base learner. \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.ARTICLE);
    result.setValue(Field.AUTHOR, "Leo Breiman");
    result.setValue(Field.YEAR, "1996");
    result.setValue(Field.TITLE, "Bagging predictors");
    result.setValue(Field.JOURNAL, "Machine Learning");
    result.setValue(Field.VOLUME, "24");
    result.setValue(Field.NUMBER, "2");
    result.setValue(Field.PAGES, "123-140");
    
    return result;
  }

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

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

    Vector newVector = new Vector(2);

    newVector.addElement(new Option(
              "\tSize of each bag, as a percentage of the\n" 
              + "\ttraining set size. (default 100)",
              "P", 1, "-P"));
    newVector.addElement(new Option(
              "\tCalculate the out of bag error.",
              "O", 0, "-O"));

    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
   *  Size of each bag, as a percentage of the
   *  training set size. (default 100)</pre>
   * 
   * <pre> -O
   *  Calculate the out of bag error.</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.REPTree)</pre>
   * 
   * <pre> 
   * Options specific to classifier weka.classifiers.trees.REPTree:
   * </pre>
   * 
   * <pre> -M &lt;minimum number of instances&gt;
   *  Set minimum number of instances per leaf (default 2).</pre>
   * 
   * <pre> -V &lt;minimum variance for split&gt;
   *  Set minimum numeric class variance proportion
   *  of train variance for split (default 1e-3).</pre>
   * 
   * <pre> -N &lt;number of folds&gt;
   *  Number of folds for reduced error pruning (default 3).</pre>
   * 
   * <pre> -S &lt;seed&gt;
   *  Seed for random data shuffling (default 1).</pre>
   * 
   * <pre> -P
   *  No pruning.</pre>
   * 
   * <pre> -L
   *  Maximum tree depth (default -1, no maximum)</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 bagSize = Utils.getOption('P', options);
    if (bagSize.length() != 0) {
      setBagSizePercent(Integer.parseInt(bagSize));
    } else {
      setBagSizePercent(100);
    }

    setCalcOutOfBag(Utils.getFlag('O', options));

    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 + 3];

    int current = 0;
    options[current++] = "-P"; 
    options[current++] = "" + getBagSizePercent();

    if (getCalcOutOfBag()) { 
      options[current++] = "-O";
    }

    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