weka.classifiers.bayes.NaiveBayesMultinomial Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of weka-dev Show documentation
The Waikato Environment for Knowledge Analysis (WEKA), a machine learning workbench. This version represents the developer version, the "bleeding edge" of development, you could say. New functionality gets added to this version.
There is a newer version: 3.9.6
Show newest version
/*
 *   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 3 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, see .
 */

/*
 * NaiveBayesMultinomial.java
 * Copyright (C) 2003-2012 University of Waikato, Hamilton, New Zealand
 */

package weka.classifiers.bayes;

import weka.classifiers.AbstractClassifier;
import weka.core.Capabilities;
import weka.core.Capabilities.Capability;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.RevisionUtils;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.WeightedInstancesHandler;

/**
 
 * Class for building and using a multinomial Naive Bayes classifier. For more information see,

 * 

 * Andrew Mccallum, Kamal Nigam: A Comparison of Event Models for Naive Bayes Text Classification. In: AAAI-98 Workshop on 'Learning for Text Categorization', 1998.

 * 

 * The core equation for this classifier:

 * 

 * P[Ci|D] = (P[D|Ci] x P[Ci]) / P[D] (Bayes rule)

 * 

 * where Ci is class i and D is a document.
 * 
 
 *
 
 * BibTeX:
 * 
 * @inproceedings{Mccallum1998,
 *    author = {Andrew Mccallum and Kamal Nigam},
 *    booktitle = {AAAI-98 Workshop on 'Learning for Text Categorization'},
 *    title = {A Comparison of Event Models for Naive Bayes Text Classification},
 *    year = {1998}
 * }
 * 
 * 
 
 *
 
 * Valid options are: 

 * 
 * 
 -D
 *  If set, classifier is run in debug mode and
 *  may output additional info to the console
 * 
 
 *
 * @author Andrew Golightly ([email protected])
 * @author Bernhard Pfahringer ([email protected])
 * @version $Revision: 11301 $ 
 */
public class NaiveBayesMultinomial 
  extends AbstractClassifier 
  implements WeightedInstancesHandler,TechnicalInformationHandler {
  
  /** for serialization */
  static final long serialVersionUID = 5932177440181257085L;
  
  /**
   * probability that a word (w) exists in a class (H) (i.e. Pr[w|H])
   * The matrix is in the this format: probOfWordGivenClass[class][wordAttribute]
   * NOTE: the values are actually the log of Pr[w|H]
   */
  protected double[][] m_probOfWordGivenClass;
    
  /** the probability of a class (i.e. Pr[H]) */
  protected double[] m_probOfClass;
    
  /** number of unique words */
  protected int m_numAttributes;
    
  /** number of class values */
  protected int m_numClasses;
    
  /** cache lnFactorial computations */
  protected double[] m_lnFactorialCache = new double[]{0.0,0.0};
    
  /** copy of header information for use in toString method */
  protected Instances m_headerInfo;

  /**
   * 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 building and using a multinomial Naive Bayes classifier. "
      + "For more information see,\n\n"
      + getTechnicalInformation().toString() + "\n\n"
      + "The core equation for this classifier:\n\n"
      + "P[Ci|D] = (P[D|Ci] x P[Ci]) / P[D] (Bayes rule)\n\n"
      + "where Ci is class i and D is a document.";
  }

  /**
   * 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.INPROCEEDINGS);
    result.setValue(Field.AUTHOR, "Andrew Mccallum and Kamal Nigam");
    result.setValue(Field.YEAR, "1998");
    result.setValue(Field.TITLE, "A Comparison of Event Models for Naive Bayes Text Classification");
    result.setValue(Field.BOOKTITLE, "AAAI-98 Workshop on 'Learning for Text Categorization'");
    
    return result;
  }

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

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

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

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

    // remove instances with missing class
    instances = new Instances(instances);
    instances.deleteWithMissingClass();
    
    m_headerInfo = new Instances(instances, 0);
    m_numClasses = instances.numClasses();
    m_numAttributes = instances.numAttributes();
    m_probOfWordGivenClass = new double[m_numClasses][];
	
    /*
      initialising the matrix of word counts
      NOTE: Laplace estimator introduced in case a word that does not appear for a class in the 
      training set does so for the test set
    */
    for(int c = 0; c enumInsts = instances.enumerateInstances();
    while (enumInsts.hasMoreElements()) 
      {
	instance = (Instance) enumInsts.nextElement();
	classIndex = (int)instance.value(instance.classIndex());
	docsPerClass[classIndex] += instance.weight();
		
	for(int a = 0; a