rdg1.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

    tmpStr = Utils.getOption('I', options);
    if (tmpStr.length() != 0)
      setNumIrrelevant(Integer.parseInt(tmpStr));
    else
      setNumIrrelevant(defaultNumIrrelevant());

    if ((getNumAttributes() - getNumIrrelevant()) < getMinRuleSize())
       throw new Exception("Possible rule size is below minimal rule size.");

    tmpStr = Utils.getOption('N', options);
    if (tmpStr.length() != 0)
      setNumNumeric(Integer.parseInt(tmpStr));
    else
      setNumNumeric(defaultNumNumeric());

    setVoteFlag(Utils.getFlag('V', options));
  }

  /**
   * Gets the current settings of the datagenerator RDG1.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String[] getOptions() {
    Vector        result;
    String[]      options;
    int           i;
    
    result  = new Vector();
    options = super.getOptions();
    for (i = 0; i < options.length; i++)
      result.add(options[i]);
    
    result.add("-a");
    result.add("" + getNumAttributes());
    
    result.add("-c");
    result.add("" + getNumClasses());

    result.add("-N"); 
    result.add("" + getNumNumeric());
    
    result.add("-I"); 
    result.add("" + getNumIrrelevant());
    
    result.add("-M"); 
    result.add("" + getMinRuleSize());
    
    result.add("-R"); 
    result.add("" + getMaxRuleSize());
    
    if (getVoteFlag())
      result.add("-V"); 

    return (String[]) result.toArray(new String[result.size()]);
  }

  /**
   * returns the default number of attributes
   * 
   * @return the default number of attributes
   */
  protected int defaultNumAttributes() {
    return 10;
  }

  /**
   * Sets the number of attributes the dataset should have.
   * @param numAttributes the new number of attributes
   */
  public void setNumAttributes(int numAttributes) {
    m_NumAttributes = numAttributes;
  }

  /**
   * Gets the number of attributes that should be produced.
   * @return the number of attributes that should be produced
   */
  public int getNumAttributes() { 
    return m_NumAttributes; 
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String numAttributesTipText() {
    return "The number of attributes the generated data will contain.";
  }

  /**
   * returns the default number of classes
   * 
   * @return the default number of classes
   */
  protected int defaultNumClasses() {
    return 2;
  }

  /**
   * Sets the number of classes the dataset should have.
   * @param numClasses the new number of classes
   */
  public void setNumClasses(int numClasses) { 
    m_NumClasses = numClasses; 
  }

  /**
   * Gets the number of classes the dataset should have.
   * @return the number of classes the dataset should have
   */
  public int getNumClasses() { 
    return m_NumClasses; 
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String numClassesTipText() {
    return "The number of classes to generate.";
  }

  /**
   * returns the default max size of rules
   * 
   * @return the default max size of rules
   */
  protected int defaultMaxRuleSize() {
    return 10;
  }

  /**
   * Gets the maximum number of tests in rules.
   *
   * @return the maximum number of tests allowed in rules
   */
  public int getMaxRuleSize() { 
    return m_MaxRuleSize; 
  }
  
  /**
   * Sets the maximum number of tests in rules.
   *
   * @param newMaxRuleSize new maximum number of tests allowed in rules.
   */
  public void setMaxRuleSize(int newMaxRuleSize) {
    m_MaxRuleSize = newMaxRuleSize;
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String maxRuleSizeTipText() {
    return "The maximum number of tests in rules.";
  }

  /**
   * returns the default min size of rules
   * 
   * @return the default min size of rules
   */
  protected int defaultMinRuleSize() {
    return 1;
  }

  /**
   * Gets the minimum number of tests in rules.
   *
   * @return the minimum number of tests allowed in rules
   */
  public int getMinRuleSize() { 
    return m_MinRuleSize; 
  }
  
  /**
   * Sets the minimum number of tests in rules.
   *
   * @param newMinRuleSize new minimum number of test in rules.
   */
  public void setMinRuleSize(int newMinRuleSize) {
    m_MinRuleSize = newMinRuleSize;
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String minRuleSizeTipText() {
    return "The minimum number of tests in rules.";
  }

  /**
   * returns the default number of irrelevant attributes
   * 
   * @return the default number of irrelevant attributes
   */
  protected int defaultNumIrrelevant() {
    return 0;
  }

  /**
   * Gets the number of irrelevant attributes.
   *
   * @return the number of irrelevant attributes
   */
  public int getNumIrrelevant() { 
    return m_NumIrrelevant; 
  }
  
  /**
   * Sets the number of irrelevant attributes.
   *
   * @param newNumIrrelevant the number of irrelevant attributes.
   */
  public void setNumIrrelevant(int newNumIrrelevant) {
    m_NumIrrelevant = newNumIrrelevant;
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String numIrrelevantTipText() {
    return "The number of irrelevant attributes.";
  }

  /**
   * returns the default number of numeric attributes
   * 
   * @return the default number of numeric attributes
   */
  protected int defaultNumNumeric() {
    return 0;
  }

  /**
   * Gets the number of numerical attributes.
   *
   * @return the number of numerical attributes.
   */
  public int getNumNumeric() { 
    return m_NumNumeric; 
  }
  
  /**
   * Sets the number of numerical attributes.
   *
   * @param newNumNumeric the number of numerical attributes.
   */
  public void setNumNumeric(int newNumNumeric) { 
    m_NumNumeric = newNumNumeric;
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String numNumericTipText() {
    return "The number of numerical attributes.";
  }

  /**
   * Gets the vote flag.
   *
   * @return voting flag.
   */
  public boolean getVoteFlag() { 
    return m_VoteFlag; 
  }
  
  /**
   * Sets the vote flag.
   *
   * @param newVoteFlag boolean with the new setting of the vote flag.
   */
  public void setVoteFlag(boolean newVoteFlag) { 
    m_VoteFlag = newVoteFlag; 
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String voteFlagTipText() {
    return "Whether to use voting or not.";
  }

  /**
   * Gets the single mode flag.
   *
   * @return true if methode generateExample can be used.
   */
  public boolean getSingleModeFlag() { 
    return (!getVoteFlag()); 
  }

  /**
   * Gets the array that defines which of the attributes
   * are seen to be irrelevant.
   *
   * @return the array that defines the irrelevant attributes
   */
  public boolean[] getAttList_Irr() { 
    return m_AttList_Irr; 
  }
  
  /**
   * Sets the array that defines which of the attributes
   * are seen to be irrelevant.
   *
   * @param newAttList_Irr array that defines the irrelevant attributes.
   */
  public void setAttList_Irr(boolean[] newAttList_Irr) {
    m_AttList_Irr = newAttList_Irr;
  }
  
  /**
   * Returns the tip text for this property
   * 
   * @return tip text for this property suitable for
   *         displaying in the explorer/experimenter gui
   */
  public String attList_IrrTipText() {
    return "The array with the indices of the irrelevant attributes.";
  }

  /**
   * Initializes the format for the dataset produced. 
   *
   * @return the output data format
   * @throws Exception data format could not be defined 
   */
  public Instances defineDataFormat() throws Exception {
    Instances dataset;
    Random random = new Random (getSeed());
    setRandom(random);

    m_DecisionList = new FastVector();

    // number of examples is the same as given per option
    setNumExamplesAct(getNumExamples());

    // define dataset
    dataset = defineDataset(random);
    return dataset; 
  }

  /**
   * Generate an example of the dataset dataset. 
   * @return the instance generated
   * @throws Exception if format not defined or generating <br/>
   * examples one by one is not possible, because voting is chosen
   */
  public Instance generateExample() throws Exception {
    Random random = getRandom();
    Instances format = getDatasetFormat();

    if (format == null) 
      throw new Exception("Dataset format not defined.");
    if (getVoteFlag()) 
      throw new Exception("Examples cannot be generated one by one.");

    // generate values for all attributes
    format = generateExamples(1, random, format);

    return format.lastInstance();
  }

  /**
   * Generate all examples of the dataset. 
   * @return the instance generated
   * @throws Exception if format not defined or generating <br/>
   * examples one by one is not possible, because voting is chosen
   */
  public Instances generateExamples() throws Exception {
    Random random = getRandom();
    Instances format = getDatasetFormat();
    if (format == null) 
      throw new Exception("Dataset format not defined.");

    // generate values for all attributes
    format = generateExamples(getNumExamplesAct(), random, format);

    // vote all examples, and set new class value
    if (getVoteFlag())
      format = voteDataset(format);