naivebayes.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

      attIndex++;
    }

    // Compute counts
    Enumeration enumInsts = m_Instances.enumerateInstances();
    while (enumInsts.hasMoreElements()) {
      Instance instance = 
	(Instance) enumInsts.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 enumAtts = m_Instances.enumerateAttributes();
      int attIndex = 0;
      while (enumAtts.hasMoreElements()) {
	Attribute attribute = (Attribute) enumAtts.nextElement();
	if (!instance.isMissing(attribute)) {
	  m_Distributions[attIndex][(int)instance.classValue()].
	    addValue(instance.value(attribute), instance.weight());
	}
	attIndex++;
      }
      m_ClassDistribution.addValue(instance.classValue(),
				   instance.weight());
    }
  }


  /**
   * Calculates the class membership probabilities for the given test 
   * instance.
   *
   * @param instance the instance to be classified
   * @return predicted class probability distribution
   * @exception Exception if there is a problem generating the prediction
   */
  public double [] distributionForInstance(Instance instance) 
  throws Exception { 
    
    if (m_UseDiscretization) {
      m_Disc.input(instance);
      instance = m_Disc.output();
    }
    double [] probs = new double[m_NumClasses];
    for (int j = 0; j < m_NumClasses; j++) {
      probs[j] = m_ClassDistribution.getProbability(j);
    }
    Enumeration enumAtts = instance.enumerateAttributes();
    int attIndex = 0;
    while (enumAtts.hasMoreElements()) {
      Attribute attribute = (Attribute) enumAtts.nextElement();
      if (!instance.isMissing(attribute)) {
	double temp, max = 0;
	for (int j = 0; j < m_NumClasses; j++) {
	  temp = Math.max(1e-75, m_Distributions[attIndex][j].
	  getProbability(instance.value(attribute)));
	  probs[j] *= temp;
	  if (probs[j] > max) {
	    max = probs[j];
	  }
	  if (Double.isNaN(probs[j])) {
	    throw new Exception("NaN returned from estimator for attribute "
				+ attribute.name() + ":\n"
				+ m_Distributions[attIndex][j].toString());
	  }
	}
	if ((max > 0) && (max < 1e-75)) { // Danger of probability underflow
	  for (int j = 0; j < m_NumClasses; j++) {
	    probs[j] *= 1e75;
	  }
	}
      }
      attIndex++;
    }

    // Display probabilities
    Utils.normalize(probs);
    return probs;
  }

  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {

    Vector newVector = new Vector(2);

    newVector.addElement(
    new Option("\tUse kernel density estimator rather than normal\n"
	       +"\tdistribution for numeric attributes",
	       "K", 0,"-K"));
    newVector.addElement(
    new Option("\tUse supervised discretization to process numeric attributes\n",
	       "D", 0,"-D"));
    return newVector.elements();
  }

  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -K
   *  Use kernel density estimator rather than normal
   *  distribution for numeric attributes</pre>
   * 
   * <pre> -D
   *  Use supervised discretization to process numeric attributes
   * </pre>
   * 
   <!-- options-end -->
   *
   * @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 {
    
    boolean k = Utils.getFlag('K', options);
    boolean d = Utils.getFlag('D', options);
    if (k && d) {
      throw new IllegalArgumentException("Can't use both kernel density " +
					 "estimation and discretization!");
    }
    setUseSupervisedDiscretization(d);
    setUseKernelEstimator(k);
    Utils.checkForRemainingOptions(options);
  }

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

    String [] options = new String [2];
    int current = 0;

    if (m_UseKernelEstimator) {
      options[current++] = "-K";
    }

    if (m_UseDiscretization) {
      options[current++] = "-D";
    }

    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }

  /**
   * Returns a description of the classifier.
   *
   * @return a description of the classifier as a string.
   */
  public String toString() {
    
    StringBuffer text = new StringBuffer();

    text.append("Naive Bayes Classifier");
    if (m_Instances == null) {
      text.append(": No model built yet.");
    } else {
      try {
	for (int i = 0; i < m_Distributions[0].length; i++) {
	  text.append("\n\nClass " + m_Instances.classAttribute().value(i) +
		      ": Prior probability = " + Utils.
		      doubleToString(m_ClassDistribution.getProbability(i),
				     4, 2) + "\n\n");
	  Enumeration enumAtts = m_Instances.enumerateAttributes();
	  int attIndex = 0;
	  while (enumAtts.hasMoreElements()) {
	    Attribute attribute = (Attribute) enumAtts.nextElement();
	    text.append(attribute.name() + ":  " 
			+ m_Distributions[attIndex][i]);
	    attIndex++;
	  }
	}
      } catch (Exception ex) {
	text.append(ex.getMessage());
      }
    }

    return text.toString();
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String useKernelEstimatorTipText() {
    return "Use a kernel estimator for numeric attributes rather than a "
      +"normal distribution.";
  }
  /**
   * Gets if kernel estimator is being used.
   *
   * @return Value of m_UseKernelEstimatory.
   */
  public boolean getUseKernelEstimator() {
    
    return m_UseKernelEstimator;
  }
  
  /**
   * Sets if kernel estimator is to be used.
   *
   * @param v  Value to assign to m_UseKernelEstimatory.
   */
  public void setUseKernelEstimator(boolean v) {
    
    m_UseKernelEstimator = v;
    if (v) {
      setUseSupervisedDiscretization(false);
    }
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String useSupervisedDiscretizationTipText() {
    return "Use supervised discretization to convert numeric attributes to nominal "
      +"ones.";
  }

  /**
   * Get whether supervised discretization is to be used.
   *
   * @return true if supervised discretization is to be used.
   */
  public boolean getUseSupervisedDiscretization() {
    
    return m_UseDiscretization;
  }
  
  /**
   * Set whether supervised discretization is to be used.
   *
   * @param newblah true if supervised discretization is to be used.
   */
  public void setUseSupervisedDiscretization(boolean newblah) {
    
    m_UseDiscretization = newblah;
    if (newblah) {
      setUseKernelEstimator(false);
    }
  }
  
  /**
   * Main method for testing this class.
   *
   * @param argv the options
   */
  public static void main(String [] argv) {
    runClassifier(new NaiveBayes(), argv);
  }
}