#semisuppairactivecurvecvresultproducer.java#

wekaUT是 university texas austin 开发的基于weka的半指导学习(semi supervised learning)的分类器

  public String lowerSizeTipText() {
    return "Set the minimum number of instances in a training set. Setting zero "
	  + "here will actually use <stepSize> number of instances at the first "
	  + "step (since performance at zero instances is predictable)";
  }

  /**
   * Get the value of LowerSize.
   *
   * @return Value of LowerSize.
   */
  public int getLowerSize() {
    
    return m_LowerSize;
  }
  
  /**
   * Set the value of LowerSize.
   *
   * @param newLowerSize Value to assign to
   * LowerSize.
   */
  public void setLowerSize(int newLowerSize) {
    
    m_LowerSize = newLowerSize;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String upperSizeTipText() {
	return "Set the maximum number of instances in a training set. Setting -1 "
	  + "sets no upper limit (other than the total number of instances "
	  + "in the full training set)";
  }

  /**
   * Get the value of UpperSize.
   *
   * @return Value of UpperSize.
   */
  public int getUpperSize() {
    
    return m_UpperSize;
  }
  
  /**
   * Set the value of UpperSize.
   *
   * @param newUpperSize Value to assign to
   * UpperSize.
   */
  public void setUpperSize(int newUpperSize) {
    
    m_UpperSize = newUpperSize;
  }


  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String stepSizeTipText() {
    return "Set the number of instances to add to the training data at each step.";
  }

  /**
   * Get the value of StepSize.
   *
   * @return Value of StepSize.
   */
  public int getStepSize() {
    
    return m_StepSize;
  }
  
  /**
   * Set the value of StepSize.
   *
   * @param newStepSize Value to assign to
   * StepSize.
   */
  public void setStepSize(int newStepSize) {
    
    m_StepSize = newStepSize;
  }


  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String plotPointsTipText() {
    return "A list of specific points to plot as a string of numbers separated by commas or spaces. "+
      "Whole numbers indicate a specific number of examples, "+
      "decimal fractions indicate a fraction of the total training set. "+
      "Specifying plot points overrides step size, lower size, and upper size parameters.";
  }
  
  /**
   * Get the value of PlotPoints.
   *
   * @return Value of PlotPoints.
   */
  public String getPlotPoints() {
    StringBuffer buf = new StringBuffer();
    if (m_PlotPoints != null) 
      for (int i=0; i < m_PlotPoints.length; i++) {
		buf.append(m_PlotPoints[i]);
		if (i != (m_PlotPoints.length -1)) 
		  buf.append(" ");
      }
    return buf.toString();
  }
  
  /**
   * Set the value of PlotPoints.
   *
   * @param plotPoints Value to assign to
   * PlotPoints.
   */
  public void setPlotPoints(String plotPoints) {
    m_PlotPoints = parsePlotPoints(plotPoints);
    setIsFraction();
  }
  
  /** 
   * Parse a string of doubles separated by commas or spaces into a sorted array of doubles
   */
  protected double[] parsePlotPoints(String plotPoints) {
    StringTokenizer tokenizer = new StringTokenizer(plotPoints," ,\t");
    double[] result = null;
    int count = tokenizer.countTokens();
    if (count > 0)
      result = new double[count];
    else
      return null;
    int i = 0;
    while(tokenizer.hasMoreTokens()) {
      result[i] = Double.parseDouble(tokenizer.nextToken());
      i++;
    }
    Arrays.sort(result);
    return result;
  }
  
  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String rawOutputTipText() {
    return "Save raw output (useful for debugging). If set, then output is "
      +"sent to the destination specified by outputFile";
  }

  /**
   * Get if raw split evaluator output is to be saved
   * @return true if raw split evalutor output is to be saved
   */
  public boolean getRawOutput() {
    return m_debugOutput;
  }
  
  /**
   * Set to true if raw split evaluator output is to be saved
   * @param d true if output is to be saved
   */
  public void setRawOutput(boolean d) {
    m_debugOutput = d;
  }

  /**
   * Returns the tip text for this property
   * @return tip text for this property suitable for
   * displaying in the explorer/experimenter gui
   */
  public String splitEvaluatorTipText() {
    return "The clusterer to apply to the cross validation folds.";
  }
 
  /**
   * Get the SplitEvaluator.
   *
   * @return the SplitEvaluator.
   */
  public SplitEvaluator getSplitEvaluator() {
    
    return m_SplitEvaluator;
  }
  
  /**
   * Set the SplitEvaluator.
   *
   * @param newSplitEvaluator new SplitEvaluator to use.
   */
  public void setSplitEvaluator(SplitEvaluator newSplitEvaluator) {
    
    m_SplitEvaluator = newSplitEvaluator;
    m_SplitEvaluator.setAdditionalMeasures(m_AdditionalMeasures);
  }

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

    Vector newVector = new Vector(7);

    newVector.addElement(new Option(
									"\tThe number of folds to use for the cross-validation.\n"
									+"\t(default 10)", 
									"X", 1, 
									"-X <number of folds>"));

    newVector.addElement(new Option(
									"\tThe number of instances to add at each step on the learning curve.",
									"S", 1, 
									"-S <step size>"));

    newVector.addElement(new Option(
									"\tThe minmum number of instances in a training set. Setting zero"
									+ "\there will actually use <stepSize> number of instances at the first"
									+ "\tstep (since performance at zero instances is predictable)",
									"L", 1, 
									"-L <lower bound>"));

    newVector.addElement(new Option(
									"\tThe maximum number of instances in a training set. Setting -1 "
									+ "\tsets no upper limit (other than the total number of instances "
									+ "\tin the full training set)",
									"U", 1, 
									"-U <upper bound>"));

    newVector.addElement(new Option(
									"Save raw split evaluator output.",
									"D",0,"-D"));

    newVector.addElement(new Option(
									"\tThe filename where raw output will be stored.\n"
									+"\tIf a directory name is specified then then individual\n"
									+"\toutputs will be gzipped, otherwise all output will be\n"
									+"\tzipped to the named file. Use in conjuction with -D."
									+"\t(default splitEvalutorOut.zip)", 
									"O", 1, 
									"-O <file/directory name/path>"));

    newVector.addElement(new Option(
									"\tThe full class name of a SplitEvaluator.\n"
									+"\teg: weka.experiment.ClustererSplitEvaluator", 
									"W", 1, 
									"-W <class name>"));

    if ((m_SplitEvaluator != null) &&
		(m_SplitEvaluator instanceof OptionHandler)) {
      newVector.addElement(new Option(
									  "",
									  "", 0, "\nOptions specific to split evaluator "
									  + m_SplitEvaluator.getClass().getName() + ":"));
      Enumeration enum = ((OptionHandler)m_SplitEvaluator).listOptions();
      while (enum.hasMoreElements()) {
		newVector.addElement(enum.nextElement());
      }
    }
    return newVector.elements();
  }

  /**
   * Parses a given list of options. Valid options are:<p>
   *
   * -X num_folds <br>
   * The number of folds to use for the cross-validation. <p>
   *
   * -D <br>
   * Specify that raw split evaluator output is to be saved. <p>
   *
   * -O file/directory name <br>
   * Specify the file or directory to which raw split evaluator output
   * is to be saved. If a directory is specified, then each output string
   * is saved as an individual gzip file. If a file is specified, then
   * each output string is saved as an entry in a zip file. <p>
   *
   * -W classname <br>
   * Specify the full class name of the split evaluator. <p>
   *
   * All option after -- will be passed to the split evaluator.
   *
   * @param options the list of options as an array of strings
   * @exception Exception if an option is not supported
   */
  public void setOptions(String[] options) throws Exception {
    
    setRawOutput(Utils.getFlag('D', options));

    String fName = Utils.getOption('O', options);
    if (fName.length() != 0) {
      setOutputFile(new File(fName));
    }

    String numFolds = Utils.getOption('X', options);
    if (numFolds.length() != 0) {
      setNumFolds(Integer.parseInt(numFolds));
    } else {
      setNumFolds(10);
    }

    String stepSize = Utils.getOption('S', options);
    if (stepSize.length() != 0) {
      setStepSize(Integer.parseInt(stepSize));
    } else {
      setStepSize(10);
    }

    String lowerSize = Utils.getOption('L', options);
    if (lowerSize.length() != 0) {
      setLowerSize(Integer.parseInt(lowerSize));
    } else {
      setLowerSize(0);
    }
    
    String upperSize = Utils.getOption('U', options);
    if (upperSize.length() != 0) {
      setUpperSize(Integer.parseInt(upperSize));
    } else {
      setUpperSize(-1);
    }

    String seName = Utils.getOption('W', options);
    if (seName.length() == 0) {
      throw new Exception("A SplitEvaluator must be specified with"
						  + " the -W option.");
    }
    // Do it first without options, so if an exception is thrown during
    // the option setting, listOptions will contain options for the actual
    // SE.
    setSplitEvaluator((SemiSupClustererSplitEvaluator)Utils.forName(
																	SplitEvaluator.class,
																	seName,
																	null));
    if (getSplitEvaluator() instanceof OptionHandler) {
      ((OptionHandler) getSplitEvaluator())
		.setOptions(Utils.partitionOptions(options));
    }
  }

  /**
   * Gets the current settings of the result producer.
   *
   * @return an array of strings suitable for passing to setOptions
   */
  public String [] getOptions() {

    String [] seOptions = new String [0];
    if ((m_SplitEvaluator != null) && 
		(m_SplitEvaluator instanceof OptionHandler)) {
      seOptions = ((OptionHandler)m_SplitEvaluator).getOptions();
    }
    
    String [] options = new String [seOptions.length + 16];
    int current = 0;

    options[current++] = "-X"; options[current++] = "" + getNumFolds();

    if (getRawOutput()) {
      options[current++] = "-D";
    }

    options[current++] = "-O"; 
    options[current++] = getOutputFile().getName();
    
    options[current++] = "-S";
    options[current++] = "" + getStepSize();
    options[current++] = "-L";
    options[current++] = "" + getLowerSize();
    options[current++] = "-U";
    options[current++] = "" + getUpperSize();

	if (m_fractionMustLinks != -1) { 
	  options[current++] = "-fraction";
	  options[current++] = "" + m_fractionMustLinks;
	} 

    if (getSplitEvaluator() != null) {
      options[current++] = "-W";
      options[current++] = getSplitEvaluator().getClass().getName();
    }
    options[current++] = "--";

    System.arraycopy(seOptions, 0, options, current, 
					 seOptions.length);
    current += seOptions.length;
    while (current < options.length) {
      options[current++] = "";
    }
    return options;
  }

  /**
   * Gets a text descrption of the result producer.
   *
   * @return a text description of the result producer.
   */
  public String toString() {

    String result = "SemiSupPairActiveCurveCVResultProducer: ";
    result += getCompatibilityState();
    if (m_Instances == null) {
      result += ": <null Instances>";
    } else {
      result += ": " +  Utils.backQuoteChars(m_Instances.relationName());
    }
    return result;
  }

    
  // Quick test of timestamp
  public static void main(String [] args) {
    
    System.err.println(Utils.doubleToString(getTimestamp().doubleValue(), 4));
  }
} //  SemiSupPairActiveCurveCVResultProducer

// Note: 1. Every pair has an ordering: index(first) < index(second)
//       2. Order of points: labeled train + unlabeled train + test