attributeselectedclassifier.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.
 */

/*
 *    AttributeSelectedClassifier.java
 *    Copyright (C) 2000 Mark Hall
 *
 */

package weka.classifiers.meta;

import weka.attributeSelection.ASEvaluation;
import weka.attributeSelection.ASSearch;
import weka.attributeSelection.AttributeSelection;
import weka.classifiers.SingleClassifierEnhancer;
import weka.core.AdditionalMeasureProducer;
import weka.core.Capabilities;
import weka.core.Drawable;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.Utils;
import weka.core.WeightedInstancesHandler;
import weka.core.Capabilities.Capability;

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

/**
 <!-- globalinfo-start -->
 * Dimensionality of training and test data is reduced by attribute selection before being passed on to a classifier.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <pre> -E &lt;attribute evaluator specification&gt;
 *  Full class name of attribute evaluator, followed
 *  by its options.
 *  eg: "weka.attributeSelection.CfsSubsetEval -L"
 *  (default weka.attributeSelection.CfsSubsetEval)</pre>
 * 
 * <pre> -S &lt;search method specification&gt;
 *  Full class name of search method, followed
 *  by its options.
 *  eg: "weka.attributeSelection.BestFirst -D 1"
 *  (default weka.attributeSelection.BestFirst)</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.J48)</pre>
 * 
 * <pre> 
 * Options specific to classifier weka.classifiers.trees.J48:
 * </pre>
 * 
 * <pre> -U
 *  Use unpruned tree.</pre>
 * 
 * <pre> -C &lt;pruning confidence&gt;
 *  Set confidence threshold for pruning.
 *  (default 0.25)</pre>
 * 
 * <pre> -M &lt;minimum number of instances&gt;
 *  Set minimum number of instances per leaf.
 *  (default 2)</pre>
 * 
 * <pre> -R
 *  Use reduced error pruning.</pre>
 * 
 * <pre> -N &lt;number of folds&gt;
 *  Set number of folds for reduced error
 *  pruning. One fold is used as pruning set.
 *  (default 3)</pre>
 * 
 * <pre> -B
 *  Use binary splits only.</pre>
 * 
 * <pre> -S
 *  Don't perform subtree raising.</pre>
 * 
 * <pre> -L
 *  Do not clean up after the tree has been built.</pre>
 * 
 * <pre> -A
 *  Laplace smoothing for predicted probabilities.</pre>
 * 
 * <pre> -Q &lt;seed&gt;
 *  Seed for random data shuffling (default 1).</pre>
 * 
 <!-- options-end -->
 *
 * @author Mark Hall ([e-mail])
 * @version $Revision: 1.24 $
 */
public class AttributeSelectedClassifier 
  extends SingleClassifierEnhancer
  implements OptionHandler, Drawable, AdditionalMeasureProducer,
             WeightedInstancesHandler {

  /** for serialization */
  static final long serialVersionUID = -5951805453487947577L;
  
  /** The attribute selection object */
  protected AttributeSelection m_AttributeSelection = null;

  /** The attribute evaluator to use */
  protected ASEvaluation m_Evaluator = 
    new weka.attributeSelection.CfsSubsetEval();

  /** The search method to use */
  protected ASSearch m_Search = new weka.attributeSelection.BestFirst();

  /** The header of the dimensionally reduced data */
  protected Instances m_ReducedHeader;

  /** The number of class vals in the training data (1 if class is numeric) */
  protected int m_numClasses;

  /** The number of attributes selected by the attribute selection phase */
  protected double m_numAttributesSelected;

  /** The time taken to select attributes in milliseconds */
  protected double m_selectionTime;

  /** The time taken to select attributes AND build the classifier */
  protected double m_totalTime;

  
  /**
   * String describing default classifier.
   * 
   * @return the default classifier classname
   */
  protected String defaultClassifierString() {
    
    return "weka.classifiers.trees.J48";
  }
  
  /**
   * Default constructor.
   */
  public AttributeSelectedClassifier() {
    m_Classifier = new weka.classifiers.trees.J48();
  }

  /**
   * Returns a string describing this search method
   * @return a description of the search method suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return "Dimensionality of training and test data is reduced by "
      +"attribute selection before being passed on to a classifier.";
  }

  /**
   * 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(
	      "\tFull class name of attribute evaluator, followed\n"
	      + "\tby its options.\n"
	      + "\teg: \"weka.attributeSelection.CfsSubsetEval -L\"\n"
	      + "\t(default weka.attributeSelection.CfsSubsetEval)",
	      "E", 1, "-E <attribute evaluator specification>"));

    newVector.addElement(new Option(
	      "\tFull class name of search method, followed\n"
	      + "\tby its options.\n"
	      + "\teg: \"weka.attributeSelection.BestFirst -D 1\"\n"
	      + "\t(default weka.attributeSelection.BestFirst)",
	      "S", 1, "-S <search method specification>"));
    
    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> -E &lt;attribute evaluator specification&gt;
   *  Full class name of attribute evaluator, followed
   *  by its options.
   *  eg: "weka.attributeSelection.CfsSubsetEval -L"
   *  (default weka.attributeSelection.CfsSubsetEval)</pre>
   * 
   * <pre> -S &lt;search method specification&gt;
   *  Full class name of search method, followed
   *  by its options.
   *  eg: "weka.attributeSelection.BestFirst -D 1"
   *  (default weka.attributeSelection.BestFirst)</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.J48)</pre>
   * 
   * <pre> 
   * Options specific to classifier weka.classifiers.trees.J48:
   * </pre>
   * 
   * <pre> -U
   *  Use unpruned tree.</pre>
   * 
   * <pre> -C &lt;pruning confidence&gt;
   *  Set confidence threshold for pruning.
   *  (default 0.25)</pre>
   * 
   * <pre> -M &lt;minimum number of instances&gt;
   *  Set minimum number of instances per leaf.
   *  (default 2)</pre>
   * 
   * <pre> -R
   *  Use reduced error pruning.</pre>
   * 
   * <pre> -N &lt;number of folds&gt;
   *  Set number of folds for reduced error
   *  pruning. One fold is used as pruning set.
   *  (default 3)</pre>
   * 
   * <pre> -B
   *  Use binary splits only.</pre>
   * 
   * <pre> -S
   *  Don't perform subtree raising.</pre>
   * 
   * <pre> -L
   *  Do not clean up after the tree has been built.</pre>
   * 
   * <pre> -A
   *  Laplace smoothing for predicted probabilities.</pre>
   * 
   * <pre> -Q &lt;seed&gt;
   *  Seed for random data shuffling (default 1).</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 {

    // same for attribute evaluator
    String evaluatorString = Utils.getOption('E', options);
    if (evaluatorString.length() == 0)
      evaluatorString = weka.attributeSelection.CfsSubsetEval.class.getName();
    String [] evaluatorSpec = Utils.splitOptions(evaluatorString);
    if (evaluatorSpec.length == 0) {
      throw new Exception("Invalid attribute evaluator specification string");
    }
    String evaluatorName = evaluatorSpec[0];
    evaluatorSpec[0] = "";
    setEvaluator(ASEvaluation.forName(evaluatorName, evaluatorSpec));

    // same for search method
    String searchString = Utils.getOption('S', options);
    if (searchString.length() == 0)
      searchString = weka.attributeSelection.BestFirst.class.getName();
    String [] searchSpec = Utils.splitOptions(searchString);
    if (searchSpec.length == 0) {
      throw new Exception("Invalid search specification string");
    }
    String searchName = searchSpec[0];
    searchSpec[0] = "";
    setSearch(ASSearch.forName(searchName, searchSpec));

    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 + 4];

    int current = 0;

    // same attribute evaluator
    options[current++] = "-E";
    options[current++] = "" +getEvaluatorSpec();
    
    // same for search
    options[current++] = "-S";
    options[current++] = "" + getSearchSpec();

    System.arraycopy(superOptions, 0, options, current, 
		     superOptions.length);
    
    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 evaluatorTipText() {
    return "Set the attribute evaluator to use. This evaluator is used "
      +"during the attribute selection phase before the classifier is "
      +"invoked.";