id3.java

数据挖掘分类算法：ID3采用JAVA语言编程实现

/*
 *    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.
 */

/*
 *    Id3.java
 *    Copyright (C) 1999 University of Waikato, Hamilton, New Zealand
 *
 */

package weka.classifiers.trees;

import weka.classifiers.Classifier;
import weka.classifiers.Sourcable;
import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.NoSupportForMissingValuesException;
import weka.core.RevisionUtils;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.Capabilities.Capability;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;

import java.util.Enumeration;

/**
 <!-- globalinfo-start -->
 * Class for constructing an unpruned decision tree based on the ID3 algorithm. Can only deal with nominal attributes. No missing values allowed. Empty leaves may result in unclassified instances. For more information see: <br/>
 * <br/>
 * R. Quinlan (1986). Induction of decision trees. Machine Learning. 1(1):81-106.
 * <p/>
 <!-- globalinfo-end -->
 *
 <!-- technical-bibtex-start -->
 * BibTeX:
 * <pre>
 * &#64;article{Quinlan1986,
 *    author = {R. Quinlan},
 *    journal = {Machine Learning},
 *    number = {1},
 *    pages = {81-106},
 *    title = {Induction of decision trees},
 *    volume = {1},
 *    year = {1986}
 * }
 * </pre>
 * <p/>
 <!-- technical-bibtex-end -->
 *
 <!-- options-start -->
 * Valid options are: <p/>
 * 
 * <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: 1.23 $ 
 */
public class Id3 
  extends Classifier 
  implements TechnicalInformationHandler, Sourcable {

  /** for serialization */
  static final long serialVersionUID = -2693678647096322561L;
  
  /** The node's successors. */ 
  private Id3[] m_Successors;

  /** Attribute used for splitting. */
  private Attribute m_Attribute;

  /** Class value if node is leaf. */
  private double m_ClassValue;

  /** Class distribution if node is leaf. */
  private double[] m_Distribution;

  /** Class attribute of dataset. */
  private Attribute m_ClassAttribute;

  /**
   * Returns a string describing the classifier.
   * @return a description suitable for the GUI.
   */
  public String globalInfo() {

    return  "Class for constructing an unpruned decision tree based on the ID3 "
      + "algorithm. Can only deal with nominal attributes. No missing values "
      + "allowed. Empty leaves may result in unclassified instances. 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, "R. Quinlan");
    result.setValue(Field.YEAR, "1986");
    result.setValue(Field.TITLE, "Induction of decision trees");
    result.setValue(Field.JOURNAL, "Machine Learning");
    result.setValue(Field.VOLUME, "1");
    result.setValue(Field.NUMBER, "1");
    result.setValue(Field.PAGES, "81-106");
    
    return result;
  }

  /**
   * Returns default capabilities of the classifier.
   *
   * @return      the capabilities of this classifier
   */
  public Capabilities getCapabilities() {
    Capabilities result = super.getCapabilities();

    // attributes
    result.enable(Capability.NOMINAL_ATTRIBUTES);

    // class
    result.enable(Capability.NOMINAL_CLASS);
    result.enable(Capability.MISSING_CLASS_VALUES);

    // instances
    result.setMinimumNumberInstances(0);
    
    return result;
  }

  /**
   * Builds Id3 decision tree classifier.
   *
   * @param data the training data
   * @exception Exception if classifier can't be built successfully
   */
  public void buildClassifier(Instances data) throws Exception {

    // can classifier handle the data?
    getCapabilities().testWithFail(data);

    // remove instances with missing class
    data = new Instances(data);
    data.deleteWithMissingClass();
    
    makeTree(data);
  }

  /**
   * Method for building an Id3 tree.
   *
   * @param data the training data
   * @exception Exception if decision tree can't be built successfully
   */
  private void makeTree(Instances data) throws Exception {

    // Check if no instances have reached this node.
    if (data.numInstances() == 0) {
      m_Attribute = null;
      m_ClassValue = Instance.missingValue();
      m_Distribution = new double[data.numClasses()];
      return;
    }

    // Compute attribute with maximum information gain.
    double[] infoGains = new double[data.numAttributes()];
    Enumeration attEnum = data.enumerateAttributes();
    while (attEnum.hasMoreElements()) {
      Attribute att = (Attribute) attEnum.nextElement();
      infoGains[att.index()] = computeInfoGain(data, att);
    }
    m_Attribute = data.attribute(Utils.maxIndex(infoGains));
    
    // Make leaf if information gain is zero. 
    // Otherwise create successors.
    if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
      m_Attribute = null;
      m_Distribution = new double[data.numClasses()];
      Enumeration instEnum = data.enumerateInstances();
      while (instEnum.hasMoreElements()) {
        Instance inst = (Instance) instEnum.nextElement();
        m_Distribution[(int) inst.classValue()]++;
      }
      Utils.normalize(m_Distribution);
      m_ClassValue = Utils.maxIndex(m_Distribution);
      m_ClassAttribute = data.classAttribute();
    } else {
      Instances[] splitData = splitData(data, m_Attribute);
      m_Successors = new Id3[m_Attribute.numValues()];
      for (int j = 0; j < m_Attribute.numValues(); j++) {
        m_Successors[j] = new Id3();
        m_Successors[j].makeTree(splitData[j]);
      }
    }
  }

  /**
   * Classifies a given test instance using the decision tree.
   *
   * @param instance the instance to be classified
   * @return the classification
   * @throws NoSupportForMissingValuesException if instance has missing values
   */
  public double classifyInstance(Instance instance) 
    throws NoSupportForMissingValuesException {

    if (instance.hasMissingValue()) {
      throw new NoSupportForMissingValuesException("Id3: no missing values, "
                                                   + "please.");
    }
    if (m_Attribute == null) {
      return m_ClassValue;
    } else {
      return m_Successors[(int) instance.value(m_Attribute)].
        classifyInstance(instance);
    }
  }

  /**
   * Computes class distribution for instance using decision tree.
   *
   * @param instance the instance for which distribution is to be computed
   * @return the class distribution for the given instance