attributeselectedclassifier.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

/*
 *    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 java.util.Enumeration;
import java.util.Vector;

import weka.attributeSelection.ASEvaluation;
import weka.attributeSelection.ASSearch;
import weka.attributeSelection.AttributeSelection;
import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;
import weka.core.AdditionalMeasureProducer;
import weka.core.Drawable;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.Utils;

/**
 * Class for running an arbitrary classifier on data that has been reduced
 * through attribute selection. <p>
 *
 * Valid options from the command line are:<p>
 *
 * -W classifierstring <br>
 * Classifierstring should contain the full class name of a classifier
 * followed by options to the classifier.
 * (required).<p>
 *
 * -E evaluatorstring <br>
 * Evaluatorstring should contain the full class name of an attribute
 * evaluator followed by any options.
 * (required).<p>
 *
 * -S searchstring <br>
 * Searchstring should contain the full class name of a search method
 * followed by any options.
 * (required). <p>
 *
 * @author Mark Hall ([e-mail])
 * @version $Revision$
 */
public class AttributeSelectedClassifier extends Classifier 
  implements OptionHandler, Drawable, AdditionalMeasureProducer {

  /** The classifier */
  protected Classifier m_Classifier = new weka.classifiers.rules.ZeroR();

  /** 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;
 
  /**
   * 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 classifier to use, followed\n"
	      + "\tby scheme options. (required)\n"
	      + "\teg: \"weka.classifiers.bayes.NaiveBayes -D\"",
	      "W", 1, "-W <classifier specification>"));
    
    newVector.addElement(new Option(
	      "\tFull class name of attribute evaluator, followed\n"
	      + "\tby its options. (required)\n"
	      + "\teg: \"weka.attributeSelection.CfsSubsetEval -L\"",
	      "E", 1, "-E <attribute evaluator specification>"));

    newVector.addElement(new Option(
	      "\tFull class name of search method, followed\n"
	      + "\tby its options. (required)\n"
	      + "\teg: \"weka.attributeSelection.BestFirst -D 1\"",
	      "S", 1, "-S <search method specification>"));
    return newVector.elements();
  }

  /**
   * Parses a given list of options. Valid options are:<p>
   *
   * -W classifierstring <br>
   * Classifierstring should contain the full class name of a classifier
   * followed by options to the classifier.
   * (required).<p>
   *
   * -E evaluatorstring <br>
   * Evaluatorstring should contain the full class name of an attribute
   * evaluator followed by any options.
   * (required).<p>
   *
   * -S searchstring <br>
   * Searchstring should contain the full class name of a search method
   * followed by any options.
   * (required). <p>
   *
   * @param options the list of options as an array of strings
   * @exception Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {

    String classifierString = Utils.getOption('W', options);
    if (classifierString.length() == 0) {
      throw new Exception("A classifier must be specified"
			  + " with the -W option.");
    }
    String [] classifierSpec = Utils.splitOptions(classifierString);
    if (classifierSpec.length == 0) {
      throw new Exception("Invalid classifier specification string");
    }
    String classifierName = classifierSpec[0];
    classifierSpec[0] = "";
    setClassifier(Classifier.forName(classifierName, classifierSpec));

    // same for attribute evaluator
     String evaluatorString = Utils.getOption('E', options);
    if (evaluatorString.length() == 0) {
      throw new Exception("An attribute evaluator must be specified"
			  + " with the -E option.");
    }
    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) {
      throw new Exception("A search method must be specified"
			  + " with the -S option.");
    }
    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));
  }

  /**
   * Gets the current settings of the Classifier.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {

    String [] options = new String [6];
    int current = 0;

    options[current++] = "-W";
    options[current++] = "" + getClassifierSpec();

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

    while (current < options.length) {
      options[current++] = "";
    }
    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 classifierTipText() {
    return "Set the classifier to use";
  }

  /**
   * Sets the classifier
   *
   * @param classifier the classifier with all options set.
   */
  public void setClassifier(Classifier classifier) {

    m_Classifier = classifier;
  }

  /**
   * Gets the classifier used.
   *
   * @return the classifier
   */
  public Classifier getClassifier() {

    return m_Classifier;
  }

  /**
   * Gets the classifier specification string, which contains the class name of
   * the classifier and any options to the classifier
   *
   * @return the classifier string.
   */
  protected String getClassifierSpec() {
    
    Classifier c = getClassifier();
    if (c instanceof OptionHandler) {
      return c.getClass().getName() + " "
	+ Utils.joinOptions(((OptionHandler)c).getOptions());
    }
    return c.getClass().getName();
  }

  /**
   * 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.";