dagging.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

   *  Random number seed.
   *  (default 1)</pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   * <pre> -W
   *  Full name of base classifier.
   *  (default: weka.classifiers.functions.SMO)</pre>
   * 
   * <pre> 
   * Options specific to classifier weka.classifiers.functions.SMO:
   * </pre>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   * <pre> -no-checks
   *  Turns off all checks - use with caution!
   *  Turning them off assumes that data is purely numeric, doesn't
   *  contain any missing values, and has a nominal class. Turning them
   *  off also means that no header information will be stored if the
   *  machine is linear. Finally, it also assumes that no instance has
   *  a weight equal to 0.
   *  (default: checks on)</pre>
   * 
   * <pre> -C &lt;double&gt;
   *  The complexity constant C. (default 1)</pre>
   * 
   * <pre> -N
   *  Whether to 0=normalize/1=standardize/2=neither. (default 0=normalize)</pre>
   * 
   * <pre> -L &lt;double&gt;
   *  The tolerance parameter. (default 1.0e-3)</pre>
   * 
   * <pre> -P &lt;double&gt;
   *  The epsilon for round-off error. (default 1.0e-12)</pre>
   * 
   * <pre> -M
   *  Fit logistic models to SVM outputs. </pre>
   * 
   * <pre> -V &lt;double&gt;
   *  The number of folds for the internal
   *  cross-validation. (default -1, use training data)</pre>
   * 
   * <pre> -W &lt;double&gt;
   *  The random number seed. (default 1)</pre>
   * 
   * <pre> -K &lt;classname and parameters&gt;
   *  The Kernel to use.
   *  (default: weka.classifiers.functions.supportVector.PolyKernel)</pre>
   * 
   * <pre> 
   * Options specific to kernel weka.classifiers.functions.supportVector.PolyKernel:
   * </pre>
   * 
   * <pre> -D
   *  Enables debugging output (if available) to be printed.
   *  (default: off)</pre>
   * 
   * <pre> -no-checks
   *  Turns off all checks - use with caution!
   *  (default: checks on)</pre>
   * 
   * <pre> -C &lt;num&gt;
   *  The size of the cache (a prime number).
   *  (default: 250007)</pre>
   * 
   * <pre> -E &lt;num&gt;
   *  The Exponent to use.
   *  (default: 1.0)</pre>
   * 
   * <pre> -L
   *  Use lower-order terms.
   *  (default: no)</pre>
   * 
   <!-- options-end -->
   *
   * Options after -- are passed to the designated classifier.<p>
   *
   * @param options the list of options as an array of strings
   * @throws Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {
    String        tmpStr;

    tmpStr = Utils.getOption('F', options);
    if (tmpStr.length() != 0)
      setNumFolds(Integer.parseInt(tmpStr));
    else
      setNumFolds(10);
    
    setVerbose(Utils.getFlag("verbose", options));
    
    super.setOptions(options);
  }

  /**
   * Gets the current settings of the Classifier.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String[] getOptions() {
    Vector        result;
    String[]      options;
    int           i;
    
    result  = new Vector();

    result.add("-F");
    result.add("" + getNumFolds());
    
    if (getVerbose())
      result.add("-verbose");
    
    options = super.getOptions();
    for (i = 0; i < options.length; i++)
      result.add(options[i]);
    
    return (String[]) result.toArray(new String[result.size()]);
  }

  /**
   * Gets the number of folds to use for splitting the training set.
   *
   * @return the number of folds
   */
  public int getNumFolds() {
    return m_NumFolds;
  }
  
  /**
   * Sets the number of folds to use for splitting the training set.
   *
   * @param value     the new number of folds
   */
  public void setNumFolds(int value) {
    if (value > 0)
      m_NumFolds = value;
    else
      System.out.println(
          "At least 1 fold is necessary (provided: " + value + ")!");
  }

  /**
   * 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 to use for splitting the training set into smaller chunks for the base classifier.";
  }
  
  /**
   * Set the verbose state.
   *
   * @param value the verbose state
   */
  public void setVerbose(boolean value) {
    m_Verbose = value;
  }
  
  /**
   * Gets the verbose state
   *
   * @return the verbose state
   */
  public boolean getVerbose() {
    return m_Verbose;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String verboseTipText() {
    return "Whether to ouput some additional information during building.";
  }

  /**
   * 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 {
    Classifier[]        base;
    int                 i;
    int                 n;
    int                 fromIndex;
    int                 toIndex;
    Instances           train;
    double              chunkSize;
    
    // can classifier handle the data?
    getCapabilities().testWithFail(data);

    // remove instances with missing class
    data = new Instances(data);
    data.deleteWithMissingClass();
    
    m_Vote    = new Vote();
    base      = new Classifier[getNumFolds()];
    chunkSize = (double) data.numInstances() / (double) getNumFolds();
    
    // stratify data
    if (getNumFolds() > 1)
      data.stratify(getNumFolds());

    // generate <folds> classifiers
    for (i = 0; i < getNumFolds(); i++) {
      base[i] = makeCopy(getClassifier());

      // generate training data
      if (getNumFolds() > 1) {
        // some progress information
        if (getVerbose())
          System.out.print(".");
        
        train     = new Instances(data, 0);
        fromIndex = (int) ((double) i * chunkSize);
        toIndex   = (int) (((double) i + 1) * chunkSize) - 1;
        if (i == getNumFolds() - 1)
          toIndex = data.numInstances() - 1;
        for (n = fromIndex; n < toIndex; n++)
          train.add(data.instance(n));
      }
      else {
        train = data;
      }

      // train classifier
      base[i].buildClassifier(train);
    }
    
    // init vote
    m_Vote.setClassifiers(base);
    
    if (getVerbose())
      System.out.println();
  }

  /**
   * 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 {
    return m_Vote.distributionForInstance(instance);
  }

  /**
   * Returns description of the classifier.
   *
   * @return description of the classifier as a string
   */
  public String toString() {
    if (m_Vote == null)
      return this.getClass().getName().replaceAll(".*\\.", "") 
             + ": No model built yet.";
    else
      return m_Vote.toString();
  }

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