ridor.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

	    
      return splitData;
    }
	
    /**
     * Whether the instance is covered by this antecedent
     * 
     * @param inst the instance in question
     * @return the boolean value indicating whether the instance is covered 
     *         by this antecedent
     */
    public boolean isCover(Instance inst){
      boolean isCover=false;
      if(!inst.isMissing(att)){
	if(Utils.eq(inst.value(att), value))
	  isCover=true;	    
      }
      return isCover;
    }
	
    /**
     * Prints this antecedent
     *
     * @return a textual description of this antecedent
     */
    public String toString() {
      return (att.name() + " = " +att.value((int)value));
    } 
  }

  /**
   * 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);
    result.enable(Capability.NUMERIC_ATTRIBUTES);
    result.enable(Capability.DATE_ATTRIBUTES);
    result.enable(Capability.MISSING_VALUES);

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

  /**
   * Builds a ripple-down manner rule learner.
   *
   * @param instances the training data
   * @throws Exception if classifier can't be built successfully
   */
  public void buildClassifier(Instances instances) throws Exception {

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

    // remove instances with missing class
    Instances data = new Instances(instances);
    data.deleteWithMissingClass();
    
    int numCl = data.numClasses();
    m_Root = new Ridor_node();
    m_Class = instances.classAttribute();     // The original class label
	
    int index = data.classIndex();
    m_Cover = data.sumOfWeights();
	
    /* Create a binary attribute */
    FastVector binary_values = new FastVector(2);
    binary_values.addElement("otherClasses");
    binary_values.addElement("defClass");
    Attribute attr = new Attribute ("newClass", binary_values);
    data.insertAttributeAt(attr, index);	
    data.setClassIndex(index);                 // The new class label

    /* Partition the data into bags according to their original class values */
    Instances[] dataByClass = new Instances[numCl];
    for(int i=0; i < numCl; i++)
      dataByClass[i] = new Instances(data, data.numInstances()); // Empty bags
    for(int i=0; i < data.numInstances(); i++){ // Partitioning
      Instance inst = data.instance(i);
      inst.setClassValue(0);           // Set new class vaue to be 0
      dataByClass[(int)inst.value(index+1)].add(inst); 
    }	
	
    for(int i=0; i < numCl; i++)    
      dataByClass[i].deleteAttributeAt(index+1);   // Delete original class
	
    m_Root.findRules(dataByClass, 0);
    
  }
    
  /**
   * Classify the test instance with the rule learner 
   *
   * @param datum the instance to be classified
   * @return the classification
   */
  public double classifyInstance(Instance datum){
    return classify(m_Root, datum);
  }
    
  /**
   * Classify the test instance with one node of Ridor 
   *
   * @param node the node of Ridor to classify the test instance
   * @param datum the instance to be classified
   * @return the classification
   */
  private double classify(Ridor_node node, Instance datum){
    double classValue = node.getDefClass();
    RidorRule[] rules = node.getRules();

    if(rules != null){
      Ridor_node[] excepts = node.getExcepts();	
      for(int i=0; i < excepts.length; i++){
	if(rules[i].isCover(datum)){
	  classValue = classify(excepts[i], datum);
	  break;
	}
      }
    }
	
    return classValue;
  }

  /**
   * Returns an enumeration describing the available options
   * Valid options are: <p>
   *
   * -F number <br>
   * Set number of folds for reduced error pruning. One fold is
   * used as the pruning set. (Default: 3) <p>
   *
   * -S number <br>
   * Set number of shuffles for randomization. (Default: 10) <p>
   * 
   * -A <br>
   * Set flag of whether use the error rate of all the data to select
   * the default class in each step. If not set, the learner will only use
   * the error rate in the pruning data <p>
   *
   * -M <br>
   * Set flag of whether use the majority class as the default class
   * in each step instead of choosing default class based on the error rate
   * (if the flag is not set) <p>  
   * 
   * -N number <br>
   * Set the minimal weights of instances within a split.
   * (Default: 2) <p>
   *    
   * @return an enumeration of all the available options
   */
  public Enumeration listOptions() {
    Vector newVector = new Vector(5);
	
    newVector.addElement(new Option("\tSet number of folds for IREP\n" +
				    "\tOne fold is used as pruning set.\n" +
				    "\t(default 3)","F", 1, "-F <number of folds>"));
    newVector.addElement(new Option("\tSet number of shuffles to randomize\n" +
				    "\tthe data in order to get better rule.\n" +
				    "\t(default 10)","S", 1, "-S <number of shuffles>"));
    newVector.addElement(new Option("\tSet flag of whether use the error rate \n"+
				    "\tof all the data to select the default class\n"+
				    "\tin each step. If not set, the learner will only use"+
				    "\tthe error rate in the pruning data","A", 0, "-A"));
    newVector.addElement(new Option("\t Set flag of whether use the majority class as\n"+
				    "\tthe default class in each step instead of \n"+
				    "\tchoosing default class based on the error rate\n"+
				    "\t(if the flag is not set)","M", 0, "-M"));
    newVector.addElement(new Option("\tSet the minimal weights of instances\n" +
				    "\twithin a split.\n" +
				    "\t(default 2.0)","N", 1, "-N <min. weights>"));		
    return newVector.elements();
  }
    
  /**
   * Parses a given list of options. <p/>
   * 
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -F &lt;number of folds&gt;
   *  Set number of folds for IREP
   *  One fold is used as pruning set.
   *  (default 3)</pre>
   * 
   * <pre> -S &lt;number of shuffles&gt;
   *  Set number of shuffles to randomize
   *  the data in order to get better rule.
   *  (default 10)</pre>
   * 
   * <pre> -A
   *  Set flag of whether use the error rate 
   *  of all the data to select the default class
   *  in each step. If not set, the learner will only use the error rate in the pruning data</pre>
   * 
   * <pre> -M
   *   Set flag of whether use the majority class as
   *  the default class in each step instead of 
   *  choosing default class based on the error rate
   *  (if the flag is not set)</pre>
   * 
   * <pre> -N &lt;min. weights&gt;
   *  Set the minimal weights of instances
   *  within a split.
   *  (default 2.0)</pre>
   * 
   <!-- options-end -->
   *
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {
	
    String numFoldsString = Utils.getOption('F', options);
    if (numFoldsString.length() != 0) 
      m_Folds = Integer.parseInt(numFoldsString);
    else 
      m_Folds = 3;
	
    String numShuffleString = Utils.getOption('S', options);
    if (numShuffleString.length() != 0) 
      m_Shuffle = Integer.parseInt(numShuffleString);
    else 
      m_Shuffle = 1;

    String seedString = Utils.getOption('s', options);
    if (seedString.length() != 0) 
      m_Seed = Integer.parseInt(seedString);
    else 
      m_Seed = 1;
	
    String minNoString = Utils.getOption('N', options);
    if (minNoString.length() != 0) 
      m_MinNo = Double.parseDouble(minNoString);
    else 
      m_MinNo = 2.0;
	
    m_IsAllErr = Utils.getFlag('A', options);
    m_IsMajority = Utils.getFlag('M', 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 [8];
    int current = 0;
    options[current++] = "-F"; options[current++] = "" + m_Folds;
    options[current++] = "-S"; options[current++] = "" + m_Shuffle;
    options[current++] = "-N"; options[current++] = "" + m_MinNo;
	
    if(m_IsAllErr)
      options[current++] = "-A";
    if(m_IsMajority)
      options[current++] = "-M";	
    while (current < options.length) 
      options[current++] = "";
    return options;
  }
    
  /** Set and get members for parameters */

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String foldsTipText() {
    return "Determines the amount of data used for pruning. One fold is used for "
      + "pruning, the rest for growing the rules.";
  }

  public void setFolds(int fold){ m_Folds = fold; }
  public int getFolds(){ return m_Folds; }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String shuffleTipText() {
    return "Determines how often the data is shuffled before a rule "
      + "is chosen. If > 1, a rule is learned multiple times and the "
      + "most accurate rule is chosen.";
  }

  public void setShuffle(int sh){ m_Shuffle = sh; }
  public int getShuffle(){ return m_Shuffle; }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String seedTipText() {
    return "The seed used for randomizing the data.";
  }

  public void setSeed(int s){ m_Seed = s; }
  public int getSeed(){ return m_Seed; }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String wholeDataErrTipText() {
    return "Whether worth of rule is computed based on all the data "
      + "or just based on data covered by rule.";
  }

  public void setWholeDataErr(boolean a){ m_IsAllErr = a; }
  public boolean getWholeDataErr(){ return m_IsAllErr; }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String majorityClassTipText() {
    return "Whether the majority class is used as default.";
  }
  public void setMajorityClass(boolean m){ m_IsMajority = m; }
  public boolean getMajorityClass(){ return m_IsMajority; }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String minNoTipText() {
    return "The minimum total weight of the instances in a rule.";
  }

  public void setMinNo(double m){  m_MinNo = m; }
  public double getMinNo(){ return m_MinNo; }
    
  /**
   * Returns an enumeration of the additional measure names
   * @return an enumeration of the measure names
   */
  public Enumeration enumerateMeasures() {
    Vector newVector = new Vector(1);
    newVector.addElement("measureNumRules");
    return newVector.elements();
  }
    
  /**
   * Returns the value of the named measure
   * @param additionalMeasureName the name of the measure to query for its value
   * @return the value of the named measure
   * @throws IllegalArgumentException if the named measure is not supported
   */
  public double getMeasure(String additionalMeasureName) {
    if (additionalMeasureName.compareToIgnoreCase("measureNumRules") == 0) 
      return numRules();
    else 
      throw new IllegalArgumentException(additionalMeasureName+" not supported (Ripple down rule learner)");
  }  
    
  /**
   * Measure the number of rules in total in the model
   *
   * @return the number of rules
   */  
  private double numRules(){
    int size = 0;
    if(m_Root != null)
      size = m_Root.size();
	
    return (double)(size+1); // Add the default rule
  }
   
  /**
   * Prints the all the rules of the rule learner.
   *
   * @return a textual description of the classifier
   */
  public String toString() {
    if (m_Root == null) 
      return "RIpple DOwn Rule Learner(Ridor): No model built yet.";
	
    return ("RIpple DOwn Rule Learner(Ridor) rules\n"+
	    "--------------------------------------\n\n" + 
	    m_Root.toString() +
	    "\nTotal number of rules (incl. the default rule): " + (int)numRules());
  }
    
  /**
   * Main method.
   *
   * @param args the options for the classifier
   */
  public static void main(String[] args) {	
    runClassifier(new Ridor(), args);
  }
}