mismo.java

Java 编写的多种数据挖掘算法 包括聚类、分类、预处理等

    else
      m_numFolds = -1;

    tmpStr = Utils.getOption('W', options);
    if (tmpStr.length() != 0)
      setRandomSeed(Integer.parseInt(tmpStr));
    else
      setRandomSeed(1);

    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]);

    if (getChecksTurnedOff())
      result.add("-no-checks");

    result.add("-C"); 
    result.add("" + getC());
    
    result.add("-L");
    result.add("" + getToleranceParameter());
    
    result.add("-P");
    result.add("" + getEpsilon());
    
    result.add("-N");
    result.add("" + m_filterType);
    
    if (getMinimax())
      result.add("-I");

    if (getBuildLogisticModels())
      result.add("-M");
    
    result.add("-V");
    result.add("" + getNumFolds());
    
    result.add("-W");
    result.add("" + getRandomSeed());
    
    result.add("-K");
    result.add("" + getKernel().getClass().getName() + " " + Utils.joinOptions(getKernel().getOptions()));
    
    return (String[]) result.toArray(new String[result.size()]);	  
  }

  /**
   * Disables or enables the checks (which could be time-consuming). Use with
   * caution!
   * 
   * @param value	if true turns off all checks
   */
  public void setChecksTurnedOff(boolean value) {
    if (value)
      turnChecksOff();
    else
      turnChecksOn();
  }
  
  /**
   * Returns whether the checks are turned off or not.
   * 
   * @return		true if the checks are turned off
   */
  public boolean getChecksTurnedOff() {
    return m_checksTurnedOff;
  }

  /**
   * Returns the tip text for this property
   * 
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String checksTurnedOffTipText() {
    return "Turns time-consuming checks off - use with caution.";
  }
  
  /**
   * 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 kernel
   */
  public void setKernel(Kernel value) {
    if (!(value instanceof MultiInstanceCapabilitiesHandler))
      throw new IllegalArgumentException(
	  "Kernel must be able to handle multi-instance data!\n"
	  + "(This one does not implement " + MultiInstanceCapabilitiesHandler.class.getName() + ")");
    
    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 cTipText() {
    return "The complexity parameter C.";
  }

  /**
   * Get the value of C.
   *
   * @return Value of C.
   */
  public double getC() {

    return m_C;
  }

  /**
   * Set the value of C.
   *
   * @param v  Value to assign to C.
   */
  public void setC(double v) {

    m_C = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String toleranceParameterTipText() {
    return "The tolerance parameter (shouldn't be changed).";
  }

  /**
   * Get the value of tolerance parameter.
   * @return Value of tolerance parameter.
   */
  public double getToleranceParameter() {

    return m_tol;
  }

  /**
   * Set the value of tolerance parameter.
   * @param v  Value to assign to tolerance parameter.
   */
  public void setToleranceParameter(double v) {

    m_tol = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String epsilonTipText() {
    return "The epsilon for round-off error (shouldn't be changed).";
  }

  /**
   * Get the value of epsilon.
   * @return Value of epsilon.
   */
  public double getEpsilon() {

    return m_eps;
  }

  /**
   * Set the value of epsilon.
   * @param v  Value to assign to epsilon.
   */
  public void setEpsilon(double v) {

    m_eps = v;
  }

  /**
   * 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.
   *
   * @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 minimaxTipText() {
    return "Whether the MIMinimax feature space is to be used.";
  }

  /**
   * Check if the MIMinimax feature space is to be used.
   * @return true if minimax
   */
  public boolean getMinimax() {

    return m_minimax;
  }

  /**
   * Set if the MIMinimax feature space is to be used.
   * @param v  true if RBF
   */
  public void setMinimax(boolean v) {
    m_minimax = v;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String buildLogisticModelsTipText() {
    return "Whether to fit logistic models to the outputs (for proper "
      + "probability estimates).";
  }

  /**
   * Get the value of buildLogisticModels.
   *
   * @return Value of buildLogisticModels.
   */
  public boolean getBuildLogisticModels() {

    return m_fitLogisticModels;
  }

  /**
   * Set the value of buildLogisticModels.
   *
   * @param newbuildLogisticModels Value to assign to buildLogisticModels.
   */
  public void setBuildLogisticModels(boolean newbuildLogisticModels) {

    m_fitLogisticModels = newbuildLogisticModels;
  }

  /**
   * 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 for cross-validation used to generate "
      + "training data for logistic models (-1 means use training data).";
  }

  /**
   * Get the value of numFolds.
   *
   * @return Value of numFolds.
   */
  public int getNumFolds() {

    return m_numFolds;
  }

  /**
   * Set the value of numFolds.
   *
   * @param newnumFolds Value to assign to numFolds.
   */
  public void setNumFolds(int newnumFolds) {

    m_numFolds = newnumFolds;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String randomSeedTipText() {
    return "Random number seed for the cross-validation.";
  }

  /**
   * Get the value of randomSeed.
   *
   * @return Value of randomSeed.
   */
  public int getRandomSeed() {

    return m_randomSeed;
  }

  /**
   * Set the value of randomSeed.
   *
   * @param newrandomSeed Value to assign to randomSeed.
   */
  public void setRandomSeed(int newrandomSeed) {

    m_randomSeed = newrandomSeed;
  }

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

    StringBuffer text = new StringBuffer();

    if ((m_classAttribute == null)) {
      return "SMO: No model built yet.";
    }
    try {
      text.append("SMO\n\n");
      for (int i = 0; i < m_classAttribute.numValues(); i++) {
        for (int j = i + 1; j < m_classAttribute.numValues(); j++) {
          text.append("Classifier for classes: " + 
              m_classAttribute.value(i) + ", " +
              m_classAttribute.value(j) + "\n\n");
          text.append(m_classifiers[i][j]);
          if (m_fitLogisticModels) {
            text.append("\n\n");
            if ( m_classifiers[i][j].m_logistic == null) {
              text.append("No logistic model has been fit.\n");
            } else {
              text.append(m_classifiers[i][j].m_logistic);
            }
          }
          text.append("\n\n");
        }
      }
    } catch (Exception e) {
      return "Can't print SMO 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 MISMO();
      System.out.println(Evaluation.evaluateModel(scheme, argv));
    } catch (Exception e) {
      e.printStackTrace();
      System.err.println(e.getMessage());
    }
  }
}