stacking.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

    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 numFoldsTipText() {
    return "The number of folds used for cross-validation.";
  }

  /** 
   * Gets the number of folds for the cross-validation.
   *
   * @return the number of folds for the cross-validation
   */
  public int getNumFolds() {

    return m_NumFolds;
  }

  /**
   * Sets the number of folds for the cross-validation.
   *
   * @param numFolds the number of folds for the cross-validation
   * @throws Exception if parameter illegal
   */
  public void setNumFolds(int numFolds) throws Exception {
    
    if (numFolds < 0) {
      throw new IllegalArgumentException("Stacking: Number of cross-validation " +
					 "folds must be positive.");
    }
    m_NumFolds = numFolds;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String metaClassifierTipText() {
    return "The meta classifiers to be used.";
  }

  /**
   * Adds meta classifier
   *
   * @param classifier the classifier with all options set.
   */
  public void setMetaClassifier(Classifier classifier) {

    m_MetaClassifier = classifier;
  }
  
  /**
   * Gets the meta classifier.
   *
   * @return the meta classifier
   */
  public Classifier getMetaClassifier() {
    
    return m_MetaClassifier;
  }

  /**
   * Returns combined capabilities of the base classifiers, i.e., the
   * capabilities all of them have in common.
   *
   * @return      the capabilities of the base classifiers
   */
  public Capabilities getCapabilities() {
    Capabilities      result;
    
    result = super.getCapabilities();
    result.setMinimumNumberInstances(getNumFolds());

    return result;
  }

  /**
   * Buildclassifier selects a classifier from the set of classifiers
   * by minimising error on the training data.
   *
   * @param data the training data to be used for generating the
   * boosted classifier.
   * @throws Exception if the classifier could not be built successfully
   */
  public void buildClassifier(Instances data) throws Exception {

    if (m_MetaClassifier == null) {
      throw new IllegalArgumentException("No meta classifier has been set");
    }

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

    // remove instances with missing class
    Instances newData = new Instances(data);
    m_BaseFormat = new Instances(data, 0);
    newData.deleteWithMissingClass();
    
    Random random = new Random(m_Seed);
    newData.randomize(random);
    if (newData.classAttribute().isNominal()) {
      newData.stratify(m_NumFolds);
    }

    // Create meta level
    generateMetaLevel(newData, random);

    // Rebuilt all the base classifiers on the full training data
    for (int i = 0; i < m_Classifiers.length; i++) {
      getClassifier(i).buildClassifier(newData);
    }
  }

  /**
   * Generates the meta data
   * 
   * @param newData the data to work on
   * @param random the random number generator to use for cross-validation
   * @throws Exception if generation fails
   */
  protected void generateMetaLevel(Instances newData, Random random) 
    throws Exception {

    Instances metaData = metaFormat(newData);
    m_MetaFormat = new Instances(metaData, 0);
    for (int j = 0; j < m_NumFolds; j++) {
      Instances train = newData.trainCV(m_NumFolds, j, random);

      // Build base classifiers
      for (int i = 0; i < m_Classifiers.length; i++) {
	getClassifier(i).buildClassifier(train);
      }

      // Classify test instances and add to meta data
      Instances test = newData.testCV(m_NumFolds, j);
      for (int i = 0; i < test.numInstances(); i++) {
	metaData.add(metaInstance(test.instance(i)));
      }
    }

    m_MetaClassifier.buildClassifier(metaData);
  }

  /**
   * Returns class probabilities.
   *
   * @param instance the instance to be classified
   * @return the distribution
   * @throws Exception if instance could not be classified
   * successfully
   */
  public double[] distributionForInstance(Instance instance) throws Exception {

    return m_MetaClassifier.distributionForInstance(metaInstance(instance));
  }

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

    if (m_Classifiers.length == 0) {
      return "Stacking: No base schemes entered.";
    }
    if (m_MetaClassifier == null) {
      return "Stacking: No meta scheme selected.";
    }
    if (m_MetaFormat == null) {
      return "Stacking: No model built yet.";
    }
    String result = "Stacking\n\nBase classifiers\n\n";
    for (int i = 0; i < m_Classifiers.length; i++) {
      result += getClassifier(i).toString() +"\n\n";
    }
   
    result += "\n\nMeta classifier\n\n";
    result += m_MetaClassifier.toString();

    return result;
  }

  /**
   * Makes the format for the level-1 data.
   *
   * @param instances the level-0 format
   * @return the format for the meta data
   * @throws Exception if the format generation fails
   */
  protected Instances metaFormat(Instances instances) throws Exception {

    FastVector attributes = new FastVector();
    Instances metaFormat;

    for (int k = 0; k < m_Classifiers.length; k++) {
      Classifier classifier = (Classifier) getClassifier(k);
      String name = classifier.getClass().getName();
      if (m_BaseFormat.classAttribute().isNumeric()) {
	attributes.addElement(new Attribute(name));
      } else {
	for (int j = 0; j < m_BaseFormat.classAttribute().numValues(); j++) {
	  attributes.addElement(new Attribute(name + ":" + 
					      m_BaseFormat
					      .classAttribute().value(j)));
	}
      }
    }
    attributes.addElement(m_BaseFormat.classAttribute().copy());
    metaFormat = new Instances("Meta format", attributes, 0);
    metaFormat.setClassIndex(metaFormat.numAttributes() - 1);
    return metaFormat;
  }

  /**
   * Makes a level-1 instance from the given instance.
   * 
   * @param instance the instance to be transformed
   * @return the level-1 instance
   * @throws Exception if the instance generation fails
   */
  protected Instance metaInstance(Instance instance) throws Exception {

    double[] values = new double[m_MetaFormat.numAttributes()];
    Instance metaInstance;
    int i = 0;
    for (int k = 0; k < m_Classifiers.length; k++) {
      Classifier classifier = getClassifier(k);
      if (m_BaseFormat.classAttribute().isNumeric()) {
	values[i++] = classifier.classifyInstance(instance);
      } else {
	double[] dist = classifier.distributionForInstance(instance);
	for (int j = 0; j < dist.length; j++) {
	  values[i++] = dist[j];
	}
      }
    }
    values[i] = instance.classValue();
    metaInstance = new Instance(1, values);
    metaInstance.setDataset(m_MetaFormat);
    return metaInstance;
  }

  /**
   * 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 Stacking(), argv);
  }
}