lwl.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.
 */

/*
 *    LWL.java
 *    Copyright (C) 1999, 2002, 2003 Len Trigg, Eibe Frank, Ashraf M. Kibriya
 *
 */

package weka.classifiers.lazy;

import weka.classifiers.SingleClassifierEnhancer;
import weka.classifiers.UpdateableClassifier;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.LinearNN;
import weka.core.NearestNeighbourSearch;
import weka.core.Option;
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.Vector;

/**
 <!-- globalinfo-start -->
 * Locally weighted learning. Uses an instance-based algorithm to assign instance weights which are then used by a specified WeightedInstancesHandler.<br/>
 * Can do classification (e.g. using naive Bayes) or regression (e.g. using linear regression).<br/>
 * <br/>
 * For more info, see<br/>
 * <br/>
 * Eibe Frank, Mark Hall, Bernhard Pfahringer: Locally Weighted Naive Bayes. In: 19th Conference in Uncertainty in Artificial Intelligence, 249-256, 2003.<br/>
 * <br/>
 * C. Atkeson, A. Moore, S. Schaal (1996). Locally weighted learning. AI Review..
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;inproceedings{Frank2003,
 *    author = {Eibe Frank and Mark Hall and Bernhard Pfahringer},
 *    booktitle = {19th Conference in Uncertainty in Artificial Intelligence},
 *    pages = {249-256},
 *    publisher = {Morgan Kaufmann},
 *    title = {Locally Weighted Naive Bayes},
 *    year = {2003}
 * }
 * 
 * &#64;article{Atkeson1996,
 *    author = {C. Atkeson and A. Moore and S. Schaal},
 *    journal = {AI Review},
 *    title = {Locally weighted learning},
 *    year = {1996}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -A
 *  The nearest neighbour search algorithm to use (default: LinearNN).
 * </pre>
 * 
 * <pre> -K &lt;number of neighbours&gt;
 *  Set the number of neighbours used to set the kernel bandwidth.
 *  (default all)</pre>
 * 
 * <pre> -U &lt;number of weighting method&gt;
 *  Set the weighting kernel shape to use. 0=Linear, 1=Epanechnikov,
 *  2=Tricube, 3=Inverse, 4=Gaussian.
 *  (default 0 = Linear)</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 -->
 *
 * @author Len Trigg ([e-mail])
 * @author Eibe Frank ([e-mail])
 * @author Ashraf M. Kibriya ([e-mail])
 * @version $Revision: 1.18 $ 
 */
public class LWL 
  extends SingleClassifierEnhancer
  implements UpdateableClassifier, WeightedInstancesHandler, 
             TechnicalInformationHandler {

  /** for serialization */
  static final long serialVersionUID = 1979797405383665815L;

  /** The training instances used for classification. */
  protected Instances m_Train;
    
  /** The number of neighbours used to select the kernel bandwidth */
  protected int m_kNN = -1;

  /** The weighting kernel method currently selected */
  protected int m_WeightKernel = LINEAR;

  /** True if m_kNN should be set to all instances */
  protected boolean m_UseAllK = true;
  
  /** The nearest neighbour search algorithm to use. (Default: LinearNN) */
  protected NearestNeighbourSearch m_NNSearch = new LinearNN();
  
  /** The available kernel weighting methods */
  protected static final int LINEAR       = 0;
  protected static final int EPANECHNIKOV = 1;
  protected static final int TRICUBE      = 2;  
  protected static final int INVERSE      = 3;
  protected static final int GAUSS        = 4;
  protected static final int CONSTANT     = 5;

  /**
   * Returns a string describing classifier
   * @return a description suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return 
        "Locally weighted learning. Uses an instance-based algorithm to "
      + "assign instance weights which are then used by a specified "
      + "WeightedInstancesHandler.\n"
      + "Can do classification (e.g. using naive Bayes) or regression "
      + "(e.g. using linear regression).\n\n"
      + "For more info, 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;
    TechnicalInformation 	additional;
    
    result = new TechnicalInformation(Type.INPROCEEDINGS);
    result.setValue(Field.AUTHOR, "Eibe Frank and Mark Hall and Bernhard Pfahringer");
    result.setValue(Field.YEAR, "2003");
    result.setValue(Field.TITLE, "Locally Weighted Naive Bayes");
    result.setValue(Field.BOOKTITLE, "19th Conference in Uncertainty in Artificial Intelligence");
    result.setValue(Field.PAGES, "249-256");
    result.setValue(Field.PUBLISHER, "Morgan Kaufmann");
    
    additional = result.add(Type.ARTICLE);
    additional.setValue(Field.AUTHOR, "C. Atkeson and A. Moore and S. Schaal");
    additional.setValue(Field.YEAR, "1996");
    additional.setValue(Field.TITLE, "Locally weighted learning");
    additional.setValue(Field.JOURNAL, "AI Review");
    
    return result;
  }
    
  /**
   * Constructor.
   */
  public LWL() {
    
    m_Classifier = new weka.classifiers.trees.DecisionStump();
  }

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

  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {
    
    Vector newVector = new Vector(3);
    newVector.addElement(new Option("\tThe nearest neighbour search " +
                                    "algorithm to use (default: LinearNN).\n",
                                    "A", 0, "-A"));
    newVector.addElement(new Option("\tSet the number of neighbours used to set"
				    +" the kernel bandwidth.\n"
				    +"\t(default all)",
				    "K", 1, "-K <number of neighbours>"));
    newVector.addElement(new Option("\tSet the weighting kernel shape to use."
				    +" 0=Linear, 1=Epanechnikov,\n"
				    +"\t2=Tricube, 3=Inverse, 4=Gaussian.\n"
				    +"\t(default 0 = Linear)",
				    "U", 1,"-U <number of weighting method>"));
    
    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> -A
   *  The nearest neighbour search algorithm to use (default: LinearNN).
   * </pre>
   * 
   * <pre> -K &lt;number of neighbours&gt;
   *  Set the number of neighbours used to set the kernel bandwidth.
   *  (default all)</pre>
   * 
   * <pre> -U &lt;number of weighting method&gt;
   *  Set the weighting kernel shape to use. 0=Linear, 1=Epanechnikov,
   *  2=Tricube, 3=Inverse, 4=Gaussian.
   *  (default 0 = Linear)</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 -->
   *
   * @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 knnString = Utils.getOption('K', options);
    if (knnString.length() != 0) {
      setKNN(Integer.parseInt(knnString));
    } else {
      setKNN(-1);
    }

    String weightString = Utils.getOption('U', options);
    if (weightString.length() != 0) {
      setWeightingKernel(Integer.parseInt(weightString));
    } else {
      setWeightingKernel(LINEAR);
    }
    
    String nnSearchClass = Utils.getOption('A', options);
    if(nnSearchClass.length() != 0) {
      String nnSearchClassSpec[] = Utils.splitOptions(nnSearchClass);
      if(nnSearchClassSpec.length == 0) { 
        throw new Exception("Invalid NearestNeighbourSearch algorithm " +
                            "specification string."); 
      }
      String className = nnSearchClassSpec[0];
      nnSearchClassSpec[0] = "";

      setNearestNeighbourSearchAlgorithm( (NearestNeighbourSearch)
                  Utils.forName( NearestNeighbourSearch.class, 
                                 className, 
                                 nnSearchClassSpec)
                                        );
    }
    else 
      this.setNearestNeighbourSearchAlgorithm(new LinearNN());

    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 + 6];

    int current = 0;

    options[current++] = "-U"; options[current++] = "" + getWeightingKernel();
    if ( (getKNN() == 0) && m_UseAllK) {
      options[current++] = "-K"; options[current++] = "-1";
    }
    else {
      options[current++] = "-K"; options[current++] = "" + getKNN();
    }
    options[current++] = "-A";
    options[current++] = m_NNSearch.getClass().getName()+" "+Utils.joinOptions(m_NNSearch.getOptions()); 

    System.arraycopy(superOptions, 0, options, current,
                     superOptions.length);