naivebayes.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.
 */

/*
 *    NaiveBayes.java
 *    Copyright (C) 1999 Eibe Frank,Len Trigg
 *
 */

package weka.classifiers.bayes;

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

import weka.classifiers.Classifier;
import weka.classifiers.Evaluation;
import weka.core.Attribute;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.Option;
import weka.core.OptionHandler;
import weka.core.UnsupportedAttributeTypeException;
import weka.core.UnsupportedClassTypeException;
import weka.core.Utils;
import weka.core.WeightedInstancesHandler;
import weka.estimators.DiscreteEstimator;
import weka.estimators.Estimator;
import weka.estimators.KernelEstimator;
import weka.estimators.NormalEstimator;

/**
 * Class for a Naive Bayes classifier using estimator classes. Numeric 
 * estimator precision values are chosen based on analysis of the 
 * training data. For this reason, the classifier is not an 
 * UpdateableClassifier (which in typical usage are initialized with zero 
 * training instances) -- if you need the UpdateableClassifier functionality,
 * use the NaiveBayesUpdateable classifier. The NaiveBayesUpdateable
 * classifier will  use a default precision of 0.1 for numeric attributes
 * when buildClassifier is called with zero training instances.
 * <p>
 * For more information on Naive Bayes classifiers, see<p>
 *
 * George H. John and Pat Langley (1995). <i>Estimating
 * Continuous Distributions in Bayesian Classifiers</i>. Proceedings
 * of the Eleventh Conference on Uncertainty in Artificial
 * Intelligence. pp. 338-345. Morgan Kaufmann, San Mateo.<p>
 *
 * Valid options are:<p>
 *
 * -K <br>
 * Use kernel estimation for modelling numeric attributes rather than
 * a single normal distribution.<p>
 *
 * -D <br>
 * Use supervised discretization to process numeric attributes.<p>
 *
 * @author Len Trigg ([e-mail])
 * @author Eibe Frank ([e-mail])
 * @version $Revision$
 */
public class NaiveBayes extends Classifier 
  implements OptionHandler, WeightedInstancesHandler {

  /**
	 * 
	 */
	private static final long serialVersionUID = 5995231201785697655L;

/** The attribute estimators. */
  protected Estimator [][] m_Distributions;
  
  /** The class estimator. */
  protected Estimator m_ClassDistribution;

  /**
   * Whether to use kernel density estimator rather than normal distribution
   * for numeric attributes
   */
  protected boolean m_UseKernelEstimator = false;

  /**
   * Whether to use discretization than normal distribution
   * for numeric attributes
   */
  protected boolean m_UseDiscretization = false;

  /** The number of classes (or 1 for numeric class) */
  protected int m_NumClasses;

  /**
   * The dataset header for the purposes of printing out a semi-intelligible 
   * model 
   */
  protected Instances m_Instances;

  /*** The precision parameter used for numeric attributes */
  protected static final double DEFAULT_NUM_PRECISION = 0.01;

  /**
   * The discretization filter.
   */
  protected weka.filters.supervised.attribute.Discretize m_Disc = null;

  /**
   * Returns a string describing this classifier
   * @return a description of the classifier suitable for
   * displaying in the explorer/experimenter gui
   */
  public String globalInfo() {
    return "Class for a Naive Bayes classifier using estimator classes. Numeric"
      +" estimator precision values are chosen based on analysis of the "
      +" training data. For this reason, the classifier is not an"
      +" UpdateableClassifier (which in typical usage are initialized with zero"
      +" training instances) -- if you need the UpdateableClassifier functionality,"
      +" use the NaiveBayesUpdateable classifier. The NaiveBayesUpdateable"
      +" classifier will  use a default precision of 0.1 for numeric attributes"
      +" when buildClassifier is called with zero training instances.\n\n"
      +"For more information on Naive Bayes classifiers, see\n\n"
      +"George H. John and Pat Langley (1995). Estimating"
      + " Continuous Distributions in Bayesian Classifiers. Proceedings"
      +" of the Eleventh Conference on Uncertainty in Artificial"
      +" Intelligence. pp. 338-345. Morgan Kaufmann, San Mateo.";
  }

  /**
   * Generates the classifier.
   *
   * @param instances set of instances serving as training data 
   * @exception Exception if the classifier has not been generated 
   * successfully
   */
  public void buildClassifier(Instances instances) throws Exception {

    if (instances.checkForStringAttributes()) {
      throw new UnsupportedAttributeTypeException("Cannot handle string attributes!");
    }
    if (instances.classAttribute().isNumeric()) {
      throw new UnsupportedClassTypeException("Naive Bayes: Class is numeric!");
    }
    m_NumClasses = instances.numClasses();
    if (m_NumClasses < 0) {
      throw new Exception ("Dataset has no class attribute");
    }

    // Copy the instances
    m_Instances = new Instances(instances);

    // Discretize instances if required
    if (m_UseDiscretization) {
      m_Disc = new weka.filters.supervised.attribute.Discretize();
      m_Disc.setInputFormat(m_Instances);
      m_Instances = weka.filters.Filter.useFilter(m_Instances, m_Disc);
    } else {
      m_Disc = null;
    }

    // Reserve space for the distributions
    m_Distributions = new Estimator[m_Instances.numAttributes() - 1]
    [m_Instances.numClasses()];
    m_ClassDistribution = new DiscreteEstimator(m_Instances.numClasses(), 
						true);
    int attIndex = 0;
    Enumeration em = m_Instances.emerateAttributes();
    while (em.hasMoreElements()) {
      Attribute attribute = (Attribute) em.nextElement();

      // If the attribute is numeric, determine the estimator 
      // numeric precision from differences between adjacent values
      double numPrecision = DEFAULT_NUM_PRECISION;
      if (attribute.type() == Attribute.NUMERIC) {
	m_Instances.sort(attribute);
	if ((m_Instances.numInstances() > 0)
	    && !m_Instances.instance(0).isMissing(attribute)) {
	  double lastVal = m_Instances.instance(0).value(attribute);
	  double currentVal, deltaSum = 0;
	  int distinct = 0;
	  for (int i = 1; i < m_Instances.numInstances(); i++) {
	    Instance currentInst = m_Instances.instance(i);
	    if (currentInst.isMissing(attribute)) {
	      break;
	    }
	    currentVal = currentInst.value(attribute);
	    if (currentVal != lastVal) {
	      deltaSum += currentVal - lastVal;
	      lastVal = currentVal;
	      distinct++;
	    }
	  }
	  if (distinct > 0) {
	    numPrecision = deltaSum / distinct;
	  }
	}
      }


      for (int j = 0; j < m_Instances.numClasses(); j++) {
	switch (attribute.type()) {
	case Attribute.NUMERIC: 
	  if (m_UseKernelEstimator) {
	    m_Distributions[attIndex][j] = 
	    new KernelEstimator(numPrecision);
	  } else {
	    m_Distributions[attIndex][j] = 
	    new NormalEstimator(numPrecision);
	  }
	  break;
	case Attribute.NOMINAL:
	  m_Distributions[attIndex][j] = 
	  new DiscreteEstimator(attribute.numValues(), true);
	  break;
	default:
	  throw new Exception("Attribute type unknown to NaiveBayes");
	}
      }
      attIndex++;
    }

    // Compute counts
    Enumeration emInsts = m_Instances.emerateInstances();
    while (emInsts.hasMoreElements()) {
      Instance instance = 
	(Instance) emInsts.nextElement();
      updateClassifier(instance);
    }

    // Save space
    m_Instances = new Instances(m_Instances, 0);
  }


  /**
   * Updates the classifier with the given instance.
   *
   * @param instance the new training instance to include in the model 
   * @exception Exception if the instance could not be incorporated in
   * the model.
   */
  public void updateClassifier(Instance instance) throws Exception {

    if (!instance.classIsMissing()) {
      Enumeration emAtts = m_Instances.emerateAttributes();
      int attIndex = 0;
      while (emAtts.hasMoreElements()) {
	Attribute attribute = (Attribute) emAtts.nextElement();
	if (!instance.isMissing(attribute)) {
	  m_Distributions[attIndex][(int)instance.classValue()].
	    addValue(instance.value(attribute), instance.weight());