stacking.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.
 */

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

package weka.classifiers.meta;

import weka.classifiers.Classifier;
import weka.classifiers.RandomizableMultipleClassifiersCombiner;
import weka.classifiers.rules.ZeroR;
import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.FastVector;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;

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

/**
 <!-- globalinfo-start -->
 * Combines several classifiers using the stacking method. Can do classification or regression.<br/>
 * <br/>
 * For more information, see<br/>
 * <br/>
 * David H. Wolpert (1992). Stacked generalization. Neural Networks. 5:241-259.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;article{Wolpert1992,
 *    author = {David H. Wolpert},
 *    journal = {Neural Networks},
 *    pages = {241-259},
 *    publisher = {Pergamon Press},
 *    title = {Stacked generalization},
 *    volume = {5},
 *    year = {1992}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -M &lt;scheme specification&gt;
 *  Full name of meta classifier, followed by options.
 *  (default: "weka.classifiers.rules.Zero")</pre>
 * 
 * <pre> -X &lt;number of folds&gt;
 *  Sets the number of cross-validation folds.</pre>
 * 
 * <pre> -S &lt;num&gt;
 *  Random number seed.
 *  (default 1)</pre>
 * 
 * <pre> -B &lt;classifier specification&gt;
 *  Full class name of classifier to include, followed
 *  by scheme options. May be specified multiple times.
 *  (default: "weka.classifiers.rules.ZeroR")</pre>
 * 
 * <pre> -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console</pre>
 * 
 <!-- options-end -->
 *
 * @author Eibe Frank ([e-mail])
 * @version $Revision: 1.30 $ 
 */
public class Stacking 
  extends RandomizableMultipleClassifiersCombiner
  implements TechnicalInformationHandler {

  /** for serialization */
  static final long serialVersionUID = 5134738557155845452L;
  
  /** The meta classifier */
  protected Classifier m_MetaClassifier = new ZeroR();
 
  /** Format for meta data */
  protected Instances m_MetaFormat = null;

  /** Format for base data */
  protected Instances m_BaseFormat = null;

  /** Set the number of folds for the cross-validation */
  protected int m_NumFolds = 10;
    
  /**
   * Returns a string describing classifier
   * @return a description suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {

    return "Combines several classifiers using the stacking method. "
      + "Can do classification or regression.\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, "David H. Wolpert");
    result.setValue(Field.YEAR, "1992");
    result.setValue(Field.TITLE, "Stacked generalization");
    result.setValue(Field.JOURNAL, "Neural Networks");
    result.setValue(Field.VOLUME, "5");
    result.setValue(Field.PAGES, "241-259");
    result.setValue(Field.PUBLISHER, "Pergamon Press");
    
    return result;
  }
  
  /**
   * 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(
	      metaOption(),
	      "M", 0, "-M <scheme specification>"));
    newVector.addElement(new Option(
	      "\tSets the number of cross-validation folds.",
	      "X", 1, "-X <number of folds>"));

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

  /**
   * String describing option for setting meta classifier
   * 
   * @return the string describing the option
   */
  protected String metaOption() {

    return "\tFull name of meta classifier, followed by options.\n" +
      "\t(default: \"weka.classifiers.rules.Zero\")";
  }

  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -M &lt;scheme specification&gt;
   *  Full name of meta classifier, followed by options.
   *  (default: "weka.classifiers.rules.Zero")</pre>
   * 
   * <pre> -X &lt;number of folds&gt;
   *  Sets the number of cross-validation folds.</pre>
   * 
   * <pre> -S &lt;num&gt;
   *  Random number seed.
   *  (default 1)</pre>
   * 
   * <pre> -B &lt;classifier specification&gt;
   *  Full class name of classifier to include, followed
   *  by scheme options. May be specified multiple times.
   *  (default: "weka.classifiers.rules.ZeroR")</pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   <!-- options-end -->
   *
   * @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 numFoldsString = Utils.getOption('X', options);
    if (numFoldsString.length() != 0) {
      setNumFolds(Integer.parseInt(numFoldsString));
    } else {
      setNumFolds(10);
    }
    processMetaOptions(options);
    super.setOptions(options);
  }

  /**
   * Process options setting meta classifier.
   * 
   * @param options the options to parse
   * @throws Exception if the parsing fails
   */
  protected void processMetaOptions(String[] options) throws Exception {

    String classifierString = Utils.getOption('M', options);
    String [] classifierSpec = Utils.splitOptions(classifierString);
    String classifierName;
    if (classifierSpec.length == 0) {
      classifierName = "weka.classifiers.rules.ZeroR";
    } else {
      classifierName = classifierSpec[0];
      classifierSpec[0] = "";
    }
    setMetaClassifier(Classifier.forName(classifierName, classifierSpec));
  }

  /**
   * 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++] = "-X"; options[current++] = "" + getNumFolds();
    options[current++] = "-M";
    options[current++] = getMetaClassifier().getClass().getName() + " "
      + Utils.joinOptions(((OptionHandler)getMetaClassifier()).getOptions());