metacost.java

wekaUT是 university texas austin 开发的基于weka的半指导学习(semi supervised learning)的分类器

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

  /**
   * 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 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;
  }

  
  /**
   * Sets the distribution classifier
   *
   * @param classifier the distribution classifier with all options set.
   */
  public void setClassifier(Classifier classifier) {

    m_Classifier = classifier;
  }

  /**
   * Gets the distribution classifier used.
   *
   * @return the classifier
   */
  public Classifier getClassifier() {

    return m_Classifier;
  }
  

  /**
   * 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();
    if (c instanceof OptionHandler) {
      return c.getClass().getName() + " "
	+ Utils.joinOptions(((OptionHandler)c).getOptions());
    }
    return c.getClass().getName();
  }


  /**
   * 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;
  }
  
  /**
   * Sets the number of bagging iterations
   */
  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;
  }


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

    m_Seed = seed;
  }

  /**
   * Get seed for resampling.
   *
   * @return the seed for resampling
   */
  public int getSeed() {

    return m_Seed;
  }


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

    if (m_Classifier == null) {
      throw new Exception("No base classifier has been set!");
    }
    if (!data.classAttribute().isNominal()) {
      throw new UnsupportedClassTypeException("Class attribute must be nominal!");
    }
    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 test instance.
   *
   * @param instance the instance to be classified
   * @exception Exception if instance could not be classified
   * successfully
   */
  public double classifyInstance(Instance instance) throws Exception {

    return m_Classifier.classifyInstance(instance);
  }

  /**
   * Output a representation of this 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) {

    try {
      System.out.println(Evaluation
			 .evaluateModel(new MetaCost(),
					argv));
    } catch (Exception e) {
      System.err.println(e.getMessage());
    }
  }

}