metacost.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

    }

    String cost_matrix= Utils.getOption("cost-matrix", options);
    if (cost_matrix.length() != 0) {
      StringWriter writer = new StringWriter();
      CostMatrix.parseMatlab(cost_matrix).write(writer);
      setCostMatrix(new CostMatrix(new StringReader(writer.toString())));
      setCostMatrixSource(new SelectedTag(MATRIX_SUPPLIED,
                                          TAGS_MATRIX_SOURCE));
    }
    
    super.setOptions(options);
  }

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


    String [] superOptions = super.getOptions();
    String [] options;

    options = new String [superOptions.length + 6];
    int current = 0;

    if (m_MatrixSource == MATRIX_SUPPLIED) {
      if (m_CostFile != null) {
        options[current++] = "-C";
        options[current++] = "" + m_CostFile;
      }
      else {
        options[current++] = "-cost-matrix";
        options[current++] = getCostMatrix().toMatlab();
      }
    } else {
      options[current++] = "-N";
      options[current++] = "" + getOnDemandDirectory();
    }
    options[current++] = "-I"; options[current++] = "" + getNumIterations();
    options[current++] = "-P"; options[current++] = "" + getBagSizePercent();

    System.arraycopy(superOptions, 0, options, current, 
		     superOptions.length);
    return options;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String costMatrixSourceTipText() {
    return "Gets the source location method of the cost matrix. Will "
      + "be one of MATRIX_ON_DEMAND or MATRIX_SUPPLIED.";
  }

  /**
   * Gets the source location method of the cost matrix. Will be one of
   * MATRIX_ON_DEMAND or MATRIX_SUPPLIED.
   *
   * @return the cost matrix source.
   */
  public SelectedTag getCostMatrixSource() {

    return new SelectedTag(m_MatrixSource, TAGS_MATRIX_SOURCE);
  }
  
  /**
   * Sets the source location of the cost matrix. Values other than
   * MATRIX_ON_DEMAND or MATRIX_SUPPLIED will be ignored.
   *
   * @param newMethod the cost matrix location method.
   */
  public void setCostMatrixSource(SelectedTag newMethod) {
    
    if (newMethod.getTags() == TAGS_MATRIX_SOURCE) {
      m_MatrixSource = newMethod.getSelectedTag().getID();
    }
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String onDemandDirectoryTipText() {
    return "Name of directory to search for cost files when loading "
      + "costs on demand.";
  }

  /**
   * Returns the directory that will be searched for cost files when
   * loading on demand.
   *
   * @return The cost file search directory.
   */
  public File getOnDemandDirectory() {

    return m_OnDemandDirectory;
  }

  /**
   * Sets the directory that will be searched for cost files when
   * loading on demand.
   *
   * @param newDir The cost file search directory.
   */
  public void setOnDemandDirectory(File newDir) {

    if (newDir.isDirectory()) {
      m_OnDemandDirectory = newDir;
    } else {
      m_OnDemandDirectory = new File(newDir.getParent());
    }
    m_MatrixSource = MATRIX_ON_DEMAND;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String bagSizePercentTipText() {
    return "The size of each bag, as a percentage of the training set "
      + "size.";
  }

  /**
   * Gets the size of each bag, as a percentage of the training set size.
   *
   * @return the bag size, as a percentage.
   */
  public int getBagSizePercent() {

    return m_BagSizePercent;
  }
  
  /**
   * Sets the size of each bag, as a percentage of the training set size.
   *
   * @param newBagSizePercent the bag size, as a percentage.
   */
  public void setBagSizePercent(int newBagSizePercent) {

    m_BagSizePercent = newBagSizePercent;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String numIterationsTipText() {
    return "The number of bagging iterations.";
  }
  
  /**
   * Sets the number of bagging iterations
   * 
   * @param numIterations the number of iterations to use
   */
  public void setNumIterations(int numIterations) {

    m_NumIterations = numIterations;
  }

  /**
   * Gets the number of bagging iterations
   *
   * @return the maximum number of bagging iterations
   */
  public int getNumIterations() {
    
    return m_NumIterations;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String costMatrixTipText() {
    return "A misclassification cost matrix.";
  }

  /**
   * Gets the misclassification cost matrix.
   *
   * @return the cost matrix
   */
  public CostMatrix getCostMatrix() {
    
    return m_CostMatrix;
  }
  
  /**
   * Sets the misclassification cost matrix.
   *
   * @param newCostMatrix the cost matrix
   */
  public void setCostMatrix(CostMatrix newCostMatrix) {
    
    m_CostMatrix = newCostMatrix;
    m_MatrixSource = MATRIX_SUPPLIED;
  }

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

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

  /**
   * Builds the model of the base learner.
   *
   * @param data the training data
   * @throws Exception if the classifier could not be built successfully
   */
  public void buildClassifier(Instances data) throws Exception {

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

    // remove instances with missing class
    data = new Instances(data);
    data.deleteWithMissingClass();
    
    if (m_MatrixSource == MATRIX_ON_DEMAND) {
      String costName = data.relationName() + CostMatrix.FILE_EXTENSION;
      File costFile = new File(getOnDemandDirectory(), costName);
      if (!costFile.exists()) {
        throw new Exception("On-demand cost file doesn't exist: " + costFile);
      }
      setCostMatrix(new CostMatrix(new BufferedReader(
                                   new FileReader(costFile))));
    }

    // Set up the bagger
    Bagging bagger = new Bagging();
    bagger.setClassifier(getClassifier());
    bagger.setSeed(getSeed());
    bagger.setNumIterations(getNumIterations());
    bagger.setBagSizePercent(getBagSizePercent());
    bagger.buildClassifier(data);
    
    // Use the bagger to reassign class values according to minimum expected
    // cost
    Instances newData = new Instances(data);
    for (int i = 0; i < newData.numInstances(); i++) {
      Instance current = newData.instance(i);
      double [] pred = bagger.distributionForInstance(current);
      int minCostPred = Utils.minIndex(m_CostMatrix.expectedCosts(pred));
      current.setClassValue(minCostPred);
    }

    // Build a classifier using the reassigned data
    m_Classifier.buildClassifier(newData);
  }

  /**
   * Classifies a given instance after filtering.
   *
   * @param instance the instance to be classified
   * @return the class distribution for the given instance
   * @throws Exception if instance could not be classified
   * successfully
   */
  public double[] distributionForInstance(Instance instance) throws Exception {
    return m_Classifier.distributionForInstance(instance);
  }

  /**
   * Gets the classifier specification string, which contains the
   * class name of the classifier and any options to the classifier
   *
   * @return the classifier string.
   */
  protected String getClassifierSpec() {
    
    Classifier c = getClassifier();
    return c.getClass().getName() + " "
      + Utils.joinOptions(((OptionHandler)c).getOptions());
  }

  /**
   * Output a representation of this classifier
   * 
   * @return a string representaiton of the classifier 
   */
  public String toString() {

    if (m_Classifier == null) {
      return "MetaCost: No model built yet.";
    }

    String result = "MetaCost cost sensitive classifier induction";
    result += "\nOptions: " + Utils.joinOptions(getOptions());
    result += "\nBase learner: " + getClassifierSpec()
      + "\n\nClassifier Model\n"
      + m_Classifier.toString()
      + "\n\nCost Matrix\n"
      + m_CostMatrix.toString();
    
    return result;
  }

  /**
   * Main method for testing this class.
   *
   * @param argv should contain the following arguments:
   * -t training file [-T test file] [-c class index]
   */
  public static void main(String [] argv) {
    runClassifier(new MetaCost(), argv);
  }
}