gaussianprocesses.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

      m_Filter.input(inst);
      m_Filter.batchFinished();
      inst = m_Filter.output();
    }

    // Build K vector

    weka.core.matrix.Matrix k = new weka.core.matrix.Matrix(m_data.numInstances(),1);
    for (int i = 0; i < m_data.numInstances(); i++) 
      k.set(i,0,m_kernel.eval(-1,i,inst));
      
    double result = k.transpose().times(m_t).get(0,0)+m_avg_target;

    return result;

  }

  /**
   * Predicts a confidence interval for the given instance and confidence level.
   *
   * @param inst the instance to make the prediction for
   * @param confidenceLevel the percentage of cases the interval should cover
   * @return a 1*2 array that contains the boundaries of the interval
   * @throws Exception if interval could not be estimated
   * successfully
   */
  public double[][] predictInterval(Instance inst, double confidenceLevel) throws Exception {

    // Filter instance
    if (!m_checksTurnedOff) {
      m_Missing.input(inst);
      m_Missing.batchFinished();
      inst = m_Missing.output();
    }

    if (m_NominalToBinary != null) {
      m_NominalToBinary.input(inst);
      m_NominalToBinary.batchFinished();
      inst = m_NominalToBinary.output();
    }
	
    if (m_Filter != null) {
      m_Filter.input(inst);
      m_Filter.batchFinished();
      inst = m_Filter.output();
    }

    // Build K vector (and Kappa)

    weka.core.matrix.Matrix k = new weka.core.matrix.Matrix(m_data.numInstances(),1);
    for (int i = 0; i < m_data.numInstances(); i++) 
      k.set(i,0,m_kernel.eval(-1,i,inst));
      
    double kappa = m_kernel.eval(-1,-1,inst) + m_delta*m_delta;
      
    double estimate = k.transpose().times(m_t).get(0,0)+m_avg_target;

    double sigma = Math.sqrt(kappa - k.transpose().times(m_C).times(k).get(0,0));

    confidenceLevel = 1.0 - ((1.0 - confidenceLevel)/2.0);

    double z = Statistics.normalInverse(confidenceLevel);
    
    double[][] interval = new double[1][2];

    interval[0][0] = estimate - z * sigma;
    interval[0][1] = estimate + z * sigma;

    return interval;
    
  }
  
  /**
   * Gives the variance of the prediction at the given instance
   *
   * @param inst the instance to get the variance for
   * @return tha variance
   * @throws Exception if computation fails
   */
    public double getStandardDeviation(Instance inst) throws Exception {

    // Filter instance
    if (!m_checksTurnedOff) {
      m_Missing.input(inst);
      m_Missing.batchFinished();
      inst = m_Missing.output();
    }

    if (m_NominalToBinary != null) {
      m_NominalToBinary.input(inst);m_Alin = 1.0;
      m_Blin = 0.0;

      m_NominalToBinary.batchFinished();
      inst = m_NominalToBinary.output();
    }
	
    if (m_Filter != null) {
      m_Filter.input(inst);
      m_Filter.batchFinished();
      inst = m_Filter.output();
    }

    weka.core.matrix.Matrix k = new weka.core.matrix.Matrix(m_data.numInstances(),1);
    for (int i = 0; i < m_data.numInstances(); i++) 
      k.set(i,0,m_kernel.eval(-1,i,inst));
      
    double kappa = m_kernel.eval(-1,-1,inst) + m_delta*m_delta;
    
    double var = kappa - k.transpose().times(m_C).times(k).get(0,0);

    if (var < 0) System.out.println("Aiaiai: variance is negative (" + var + ")!!!");
  
    double sigma = Math.sqrt(var);

    return sigma;
    }

  /**
   * Returns an enumeration describing the available options.
   *
   * @return an enumeration of all the available options.
   */
  public Enumeration listOptions() {
	
    Vector result = new Vector();

    Enumeration enm = super.listOptions();
    while (enm.hasMoreElements())
      result.addElement(enm.nextElement());

    result.addElement(new Option(
	"\tLevel of Gaussian Noise."
	+ " (default 0.1)",
	"L", 1, "-L <double>"));
    
    result.addElement(new Option(
	"\tWhether to 0=normalize/1=standardize/2=neither. " +
	"(default 0=normalize)",
	"N", 1, "-N"));
    
    result.addElement(new Option(
	"\tThe Kernel to use.\n"
	+ "\t(default: weka.classifiers.functions.supportVector.PolyKernel)",
	"K", 1, "-K <classname and parameters>"));

    result.addElement(new Option(
	"",
	"", 0, "\nOptions specific to kernel "
	+ getKernel().getClass().getName() + ":"));
    
    enm = ((OptionHandler) getKernel()).listOptions();
    while (enm.hasMoreElements())
      result.addElement(enm.nextElement());

    return result.elements();
  }
    
    
  /**
   * Parses a given list of options. <p/>
   *
   <!-- options-start -->
   * Valid options are: <p/>
   * 
   * <pre> -D
   *  If set, classifier is run in debug mode and
   *  may output additional info to the console</pre>
   * 
   * <pre> -L &lt;double&gt;
   *  Level of Gaussian Noise. (default 0.1)</pre>
   * 
   * <pre> -N
   *  Whether to 0=normalize/1=standardize/2=neither. (default 0=normalize)</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.RBFKernel:
   * </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> -G &lt;num&gt;
   *  The Gamma parameter.
   *  (default: 0.01)</pre>
   * 
   <!-- options-end -->
   * 
   * @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;
    String[]	tmpOptions;
    
    tmpStr = Utils.getOption('L', options);
    if (tmpStr.length() != 0)
      setNoise(Double.parseDouble(tmpStr));
    else
      setNoise(0.1);

    tmpStr = Utils.getOption('N', options);
    if (tmpStr.length() != 0)
      setFilterType(new SelectedTag(Integer.parseInt(tmpStr), TAGS_FILTER));
    else
      setFilterType(new SelectedTag(FILTER_NORMALIZE, TAGS_FILTER));

    tmpStr     = Utils.getOption('K', options);
    tmpOptions = Utils.splitOptions(tmpStr);
    if (tmpOptions.length != 0) {
      tmpStr        = tmpOptions[0];
      tmpOptions[0] = "";
      setKernel(Kernel.forName(tmpStr, tmpOptions));
    }
    
    super.setOptions(options);
  }

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

    result = new Vector();
    options = super.getOptions();
    for (i = 0; i < options.length; i++)
      result.add(options[i]);

    result.add("-L");
    result.add("" + getNoise());
    
    result.add("-N");
    result.add("" + m_filterType);
    
    result.add("-K");
    result.add("" + m_kernel.getClass().getName() + " " + Utils.joinOptions(m_kernel.getOptions()));
    
    return (String[]) result.toArray(new String[result.size()]);	  
  }

  /**
   * Returns the tip text for this property
   * 
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String kernelTipText() {
    return "The kernel to use.";
  }

  /**
   * Gets the kernel to use.
   *
   * @return 		the kernel
   */
  public Kernel getKernel() {
    return m_kernel;
  }
    
  /**
   * Sets the kernel to use.
   *
   * @param value	the new kernel
   */
  public void setKernel(Kernel value) {
    m_kernel = value;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String filterTypeTipText() {
    return "Determines how/if the data will be transformed.";
  }

  /**
   * Gets how the training data will be transformed. Will be one of
   * FILTER_NORMALIZE, FILTER_STANDARDIZE, FILTER_NONE.2200Instances
   *
   * @return the filtering mode
   */
  public SelectedTag getFilterType() {
	
    return new SelectedTag(m_filterType, TAGS_FILTER);
  }
    
  /**
   * Sets how the training data will be transformed. Should be one of
   * FILTER_NORMALIZE, FILTER_STANDARDIZE, FILTER_NONE.
   *
   * @param newType the new filtering mode
   */
  public void setFilterType(SelectedTag newType) {
	
    if (newType.getTags() == TAGS_FILTER) {
      m_filterType = newType.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 noiseTipText() {
    return "The level of Gaussian Noise (added to the diagonal of the Covariance Matrix).";
  }
  
  /**
   * Get the value of noise. 
   *
   * @return Value of noise.
   */
  public double getNoise() {
    return m_delta;
  }
  
  /**
   * Set the level of Gaussian Noise. 
   *
   * @param v  Value to assign to noise.
   */
  public void setNoise(double v) {
    m_delta = v;
  }

  /**
   * Prints out the classifier.
   *
   * @return a description of the classifier as a string
   */
  public String toString() {

    StringBuffer text = new StringBuffer();

    if (m_t == null)
      return "Gaussian Processes: No model built yet.";

    try {

      text.append("Gaussian Processes\n\n");
      text.append("Kernel used:\n  " + m_kernel.toString() + "\n\n");

      text.append("Average Target Value : " + m_avg_target + "\n");

      text.append("Inverted Covariance Matrix:\n");
      double min = m_C.get(0,0);
      double max = m_C.get(0,0);
      for (int i = 0; i < m_data.numInstances(); i++)
	for (int j = 0; j < m_data.numInstances(); j++) {
	    if (m_C.get(i,j) < min) min = m_C.get(i,j);
	    else if (m_C.get(i,j) > max) max = m_C.get(i,j);
	}
      text.append("    Lowest Value = " + min + "\n");
      text.append("    Highest Value = " + max + "\n");
      text.append("Inverted Covariance Matrix * Target-value Vector:\n");
      min = m_t.get(0,0);
      max = m_t.get(0,0);
      for (int i = 0; i < m_data.numInstances(); i++) {
	    if (m_t.get(i,0) < min) min = m_t.get(i,0);
	    else if (m_t.get(i,0) > max) max = m_t.get(i,0);
	}
      text.append("    Lowest Value = " + min + "\n");
      text.append("    Highest Value = " + max + "\n \n");   
      
    } catch (Exception e) {
      return "Can't print the classifier.";
    }

    return text.toString();
  }
 
 /**
   * Main method for testing this class.
   * 
   * @param argv the commandline parameters
   */
  public static void main(String[] argv) {
	
    Classifier scheme;
    try {
      scheme = new GaussianProcesses();
      System.out.println(Evaluation.evaluateModel(scheme, argv));
    } catch (Exception e) {
      e.printStackTrace();
      System.err.println(e.getMessage());
    }
  }
}