jrip.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

    m_UsePruning = !Utils.getFlag('P', 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 [11];
    int current = 0;
    options[current++] = "-F"; options[current++] = "" + m_Folds;
    options[current++] = "-N"; options[current++] = "" + m_MinNo;
    options[current++] = "-O"; options[current++] = "" + m_Optimizations;
    options[current++] = "-S"; options[current++] = "" + m_Seed;
	
    if(m_Debug)
      options[current++] = "-D";

    if(!m_CheckErr)
      options[current++] = "-E";
	
    if(!m_UsePruning)
      options[current++] = "-P";
	
    while(current < options.length)
      options[current++] = "";
	
    return options;
  }

  /**
   * 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 m_Ruleset.size();
    else 
      throw new IllegalArgumentException(additionalMeasureName+" not supported (RIPPER)");
  }  

  /**
   * 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.";
  }

  /**
   * Sets the number of folds to use
   * 
   * @param fold the number of folds
   */
  public void setFolds(int fold) { 
    m_Folds = fold; 
  }
  
  /**
   * Gets the number of folds
   * 
   * @return the number of folds
   */
  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 minNoTipText() {
    return "The minimum total weight of the instances in a rule.";
  }

  /**
   * Sets the minimum total weight of the instances in a rule
   * 
   * @param m the minimum total weight of the instances in a rule
   */
  public void setMinNo(double m) {
    m_MinNo = m;
  }
  
  /**
   * Gets the minimum total weight of the instances in a rule
   * 
   * @return the minimum total weight of the instances in a rule
   */
  public double getMinNo(){ 
    return m_MinNo;
  }

  /**
   * 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.";
  }

  /**
   * Sets the seed value to use in randomizing the data
   * 
   * @param s the new seed value
   */
  public void setSeed(long s) {
    m_Seed = s;
  }
  
  /**
   * Gets the current seed value to use in randomizing the data
   * 
   * @return the seed value
   */
  public long 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 optimizationsTipText() {
    return "The number of optimization runs.";
  }

  /**
   * Sets the number of optimization runs
   * 
   * @param run the number of optimization runs
   */
  public void setOptimizations(int run) {
    m_Optimizations = run;
  }
  
  /**
   * Gets the the number of optimization runs
   * 
   * @return the number of optimization runs
   */
  public int getOptimizations() {
    return m_Optimizations;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String debugTipText() {
    return "Whether debug information is output to the console.";
  }

  /**
   * Sets whether debug information is output to the console
   * 
   * @param d whether debug information is output to the console
   */
  public void setDebug(boolean d) {
    m_Debug = d;
  }
  
  /**
   * Gets whether debug information is output to the console
   * 
   * @return whether debug information is output to the console
   */
  public boolean getDebug(){
    return m_Debug;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String checkErrorRateTipText() {
    return "Whether check for error rate >= 1/2 is included" +
      " in stopping criterion.";
  }

  /**
   * Sets whether to check for error rate is in stopping criterion
   * 
   * @param d whether to check for error rate is in stopping criterion
   */
  public void setCheckErrorRate(boolean d) { 
    m_CheckErr = d;
  }
  
  /**
   * Gets whether to check for error rate is in stopping criterion
   * 
   * @return true if checking for error rate is in stopping criterion
   */
  public boolean getCheckErrorRate(){ 
    return m_CheckErr; 
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String usePruningTipText() {
    return "Whether pruning is performed.";
  }

  /**
   * Sets whether pruning is performed
   * 
   * @param d Whether pruning is performed
   */
  public void setUsePruning(boolean d) { 
    m_UsePruning = d;
  }
  
  /**
   * Gets whether pruning is performed
   * 
   * @return true if pruning is performed
   */
  public boolean getUsePruning(){ 
    return m_UsePruning; 
  }
    
  /** 
   * Get the ruleset generated by Ripper 
   *
   * @return the ruleset
   */
  public FastVector getRuleset(){ return m_Ruleset; }

  /** 
   * Get the statistics of the ruleset in the given position
   *
   * @param pos the position of the stats, assuming correct
   * @return the statistics of the ruleset in the given position
   */
  public RuleStats getRuleStats(int pos) {
    return (RuleStats)m_RulesetStats.elementAt(pos);
  }
    
  /** 
   * The single antecedent in the rule, which is composed of an attribute and 
   * the corresponding value.  There are two inherited classes, namely NumericAntd
   * and NominalAntd in which the attributes are numeric and nominal respectively.
   */    
  private abstract class Antd 
    implements WeightedInstancesHandler, Copyable, Serializable {
	
    /** The attribute of the antecedent */
    protected Attribute att;
	
    /** The attribute value of the antecedent.  
       For numeric attribute, value is either 0(1st bag) or 1(2nd bag) */
    protected double value; 
	
    /** The maximum infoGain achieved by this antecedent test 
     * in the growing data */
    protected double maxInfoGain;
	
    /** The accurate rate of this antecedent test on the growing data */
    protected double accuRate;
	
    /** The coverage of this antecedent in the growing data */
    protected double cover;
	
    /** The accurate data for this antecedent in the growing data */
    protected double accu;
	
    /** 
     * Constructor
     */
    public Antd(Attribute a){
      att=a;
      value=Double.NaN; 
      maxInfoGain = 0;
      accuRate = Double.NaN;
      cover = Double.NaN;
      accu = Double.NaN;
    }
	
    /* The abstract members for inheritance */
    public abstract Instances[] splitData(Instances data, double defAcRt, 
					  double cla);
    public abstract boolean covers(Instance inst);
    public abstract String toString();
	
    /** 
     * Implements Copyable
     * 
     * @return a copy of this object
     */
    public abstract Object copy(); 
	   
    /* Get functions of this antecedent */
    public Attribute getAttr(){ return att; }
    public double getAttrValue(){ return value; }
    public double getMaxInfoGain(){ return maxInfoGain; }
    public double getAccuRate(){ return accuRate; } 
    public double getAccu(){ return accu; } 
    public double getCover(){ return cover; } 
  }
    
  /** 
   * The antecedent with numeric attribute
   */
  private class 
    NumericAntd extends Antd {
    
    /** for serialization */
    static final long serialVersionUID = 5699457269983735442L;
	
    /** The split point for this numeric antecedent */
    private double splitPoint;
    
    /** 
     * Constructor
     */
    public NumericAntd(Attribute a){ 
      super(a);
      splitPoint = Double.NaN;
    }    
	
    /** 
     * Get split point of this numeric antecedent
     * 
     * @return the split point of this numeric antecedent
     */
    public double getSplitPoint(){ 
      return splitPoint;
    }
	
    /** 
     * Implements Copyable
     * 
     * @return a copy of this object
     */
    public Object copy(){ 
      NumericAntd na = new NumericAntd(getAttr());
      na.value = this.value;
      na.splitPoint = this.splitPoint;
      return na;
    }
	
    /**
     * Implements the splitData function.  
     * This procedure is to split the data into two bags according 
     * to the information gain of the numeric attribute value
     * The maximum infoGain is also calculated.  
     * 
     * @param insts the data to be split
     * @param defAcRt the default accuracy rate for data
     * @param cl the class label to be predicted
     * @return the array of data after split
     */
    public Instances[] splitData(Instances insts, double defAcRt, 
				 double cl){
	Instances data = insts;
      int total=data.numInstances();// Total number of instances without 
      // missing value for att
	    
      int split=1;                  // Current split position
      int prev=0;                   // Previous split position
      int finalSplit=split;         // Final split position
      maxInfoGain = 0;
      value = 0;	
	    
      double fstCover=0, sndCover=0, fstAccu=0, sndAccu=0;
	    
      data.sort(att);
      // Find the las instance without missing value 
      for(int x=0; x<data.numInstances(); x++){
	Instance inst = data.instance(x);
	if(inst.isMissing(att)){
	  total = x;
	  break;
	}
		
	sndCover += inst.weight();
	if(Utils.eq(inst.classValue(), cl))