bagging.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

   * displaying in the explorer/experimenter gui
   */
  public String bagSizePercentTipText() {
    return "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 calcOutOfBagTipText() {
    return "Whether the out-of-bag error is calculated.";
  }

  /**
   * Set whether the out of bag error is calculated.
   *
   * @param calcOutOfBag whether to calculate the out of bag error
   */
  public void setCalcOutOfBag(boolean calcOutOfBag) {

    m_CalcOutOfBag = calcOutOfBag;
  }

  /**
   * Get whether the out of bag error is calculated.
   *
   * @return whether the out of bag error is calculated
   */
  public boolean getCalcOutOfBag() {

    return m_CalcOutOfBag;
  }

  /**
   * Gets the out of bag error that was calculated as the classifier
   * was built.
   *
   * @return the out of bag error 
   */
  public double measureOutOfBagError() {
    
    return m_OutOfBagError;
  }
  
  /**
   * 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("measureOutOfBagError");
    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.equalsIgnoreCase("measureOutOfBagError")) {
      return measureOutOfBagError();
    }
    else {throw new IllegalArgumentException(additionalMeasureName 
					     + " not supported (Bagging)");
    }
  }

  /**
   * Creates a new dataset of the same size using random sampling
   * with replacement according to the given weight vector. The
   * weights of the instances in the new dataset are set to one.
   * The length of the weight vector has to be the same as the
   * number of instances in the dataset, and all weights have to
   * be positive.
   *
   * @param data the data to be sampled from
   * @param random a random number generator
   * @param sampled indicating which instance has been sampled
   * @return the new dataset
   * @throws IllegalArgumentException if the weights array is of the wrong
   * length or contains negative weights.
   */
  public final Instances resampleWithWeights(Instances data,
					     Random random, 
					     boolean[] sampled) {

    double[] weights = new double[data.numInstances()];
    for (int i = 0; i < weights.length; i++) {
      weights[i] = data.instance(i).weight();
    }
    Instances newData = new Instances(data, data.numInstances());
    if (data.numInstances() == 0) {
      return newData;
    }
    double[] probabilities = new double[data.numInstances()];
    double sumProbs = 0, sumOfWeights = Utils.sum(weights);
    for (int i = 0; i < data.numInstances(); i++) {
      sumProbs += random.nextDouble();
      probabilities[i] = sumProbs;
    }
    Utils.normalize(probabilities, sumProbs / sumOfWeights);

    // Make sure that rounding errors don't mess things up
    probabilities[data.numInstances() - 1] = sumOfWeights;
    int k = 0; int l = 0;
    sumProbs = 0;
    while ((k < data.numInstances() && (l < data.numInstances()))) {
      if (weights[l] < 0) {
	throw new IllegalArgumentException("Weights have to be positive.");
      }
      sumProbs += weights[l];
      while ((k < data.numInstances()) &&
	     (probabilities[k] <= sumProbs)) { 
	newData.add(data.instance(l));
	sampled[l] = true;
	newData.instance(k).setWeight(1);
	k++;
      }
      l++;
    }
    return newData;
  }

  /**
   * Bagging method.
   *
   * @param data the training data to be used for generating the
   * bagged classifier.
   * @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();
    
    super.buildClassifier(data);

    if (m_CalcOutOfBag && (m_BagSizePercent != 100)) {
      throw new IllegalArgumentException("Bag size needs to be 100% if " +
					 "out-of-bag error is to be calculated!");
    }

    int bagSize = data.numInstances() * m_BagSizePercent / 100;
    Random random = new Random(m_Seed);
    
    boolean[][] inBag = null;
    if (m_CalcOutOfBag)
      inBag = new boolean[m_Classifiers.length][];
    
    for (int j = 0; j < m_Classifiers.length; j++) {
      Instances bagData = null;

      // create the in-bag dataset
      if (m_CalcOutOfBag) {
	inBag[j] = new boolean[data.numInstances()];
	bagData = resampleWithWeights(data, random, inBag[j]);
      } else {
	bagData = data.resampleWithWeights(random);
	if (bagSize < data.numInstances()) {
	  bagData.randomize(random);
	  Instances newBagData = new Instances(bagData, 0, bagSize);
	  bagData = newBagData;
	}
      }
      
      if (m_Classifier instanceof Randomizable) {
	((Randomizable) m_Classifiers[j]).setSeed(random.nextInt());
      }
      
      // build the classifier
      m_Classifiers[j].buildClassifier(bagData);
    }
    
    // calc OOB error?
    if (getCalcOutOfBag()) {
      double outOfBagCount = 0.0;
      double errorSum = 0.0;
      boolean numeric = data.classAttribute().isNumeric();
      
      for (int i = 0; i < data.numInstances(); i++) {
	double vote;
	double[] votes;
	if (numeric)
	  votes = new double[1];
	else
	  votes = new double[data.numClasses()];
	
	// determine predictions for instance
	int voteCount = 0;
	for (int j = 0; j < m_Classifiers.length; j++) {
	  if (!inBag[j][i])
	    continue;
	  
	  voteCount++;
	  double pred = m_Classifiers[j].classifyInstance(data.instance(i));
	  if (numeric)
	    votes[0] += pred;
	  else
	    votes[(int) pred]++;
	}
	
	// "vote"
	if (numeric)
	  vote = votes[0] / voteCount;    // average
	else
	  vote = Utils.maxIndex(votes);   // majority vote
	
	// error for instance
	outOfBagCount += data.instance(i).weight();
	if (numeric) {
	  errorSum += StrictMath.abs(vote - data.instance(i).classValue()) 
	  * data.instance(i).weight();
	}
	else {
	  if (vote != data.instance(i).classValue())
	    errorSum += data.instance(i).weight();
	}
      }
      
      m_OutOfBagError = errorSum / outOfBagCount;
    }
    else {
      m_OutOfBagError = 0;
    }
  }

  /**
   * Calculates the class membership probabilities for the given test
   * instance.
   *
   * @param instance the instance to be classified
   * @return preedicted class probability distribution
   * @throws Exception if distribution can't be computed successfully 
   */
  public double[] distributionForInstance(Instance instance) throws Exception {

    double [] sums = new double [instance.numClasses()], newProbs; 
    
    for (int i = 0; i < m_NumIterations; i++) {
      if (instance.classAttribute().isNumeric() == true) {
	sums[0] += m_Classifiers[i].classifyInstance(instance);
      } else {
	newProbs = m_Classifiers[i].distributionForInstance(instance);
	for (int j = 0; j < newProbs.length; j++)
	  sums[j] += newProbs[j];
      }
    }
    if (instance.classAttribute().isNumeric() == true) {
      sums[0] /= (double)m_NumIterations;
      return sums;
    } else if (Utils.eq(Utils.sum(sums), 0)) {
      return sums;
    } else {
      Utils.normalize(sums);
      return sums;
    }
  }

  /**
   * Returns description of the bagged classifier.
   *
   * @return description of the bagged classifier as a string
   */
  public String toString() {
    
    if (m_Classifiers == null) {
      return "Bagging: No model built yet.";
    }
    StringBuffer text = new StringBuffer();
    text.append("All the base classifiers: \n\n");
    for (int i = 0; i < m_Classifiers.length; i++)
      text.append(m_Classifiers[i].toString() + "\n\n");
    
    if (m_CalcOutOfBag) {
      text.append("Out of bag error: "
		  + Utils.doubleToString(m_OutOfBagError, 4)
		  + "\n\n");
    }

    return text.toString();
  }

  /**
   * Main method for testing this class.
   *
   * @param argv the options
   */
  public static void main(String [] argv) {
    runClassifier(new Bagging(), argv);
  }
}