semisupcrossvalidationresultproducer.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

	    // Randomly shuffle stratified training set for fold: added by Sugato
	    train.randomize(new Random(fold));	    

	    Instances test = runInstances.testCV(m_NumFolds, fold);
	    int pointNum = 0;
	    // For each subsample size
	    if (m_PlotPoints != null) {
		m_CurrentSize = plotPoint(0);
	    }
	    else if (m_LowerSize == 0) {
		m_CurrentSize = m_StepSize;
	    } else {
		m_CurrentSize = m_LowerSize;
	    }
	    while (m_CurrentSize <= maxTrainSize()) {
		// Add in some fields to the key like run and fold number, dataset name
		Object [] seKey = m_SplitEvaluator.getKey();
		Object [] key = new Object [seKey.length + numExtraKeys];
		key[0] = Utils.backQuoteChars(m_Instances.relationName());
		key[1] = "" + run;
		key[2] = "" + (fold + 1);
		key[3] = "" + m_CurrentSize;
		if(m_IsFraction) key[4] = "" + m_PlotPoints[pointNum];
		System.arraycopy(seKey, 0, key, numExtraKeys, seKey.length);
		if (m_ResultListener.isResultRequired(this, key)) {
		    try {
			if(m_IsFraction)
			    System.out.println("Run:" + run + " Fold:" + fold + " Size:" + m_CurrentSize + " Fraction:" + m_PlotPoints[pointNum]);
			else
			    System.out.println("Run:" + run + " Fold:" + fold + " Size:" + m_CurrentSize);
			Instances trainSubset = new Instances(train, 0, m_CurrentSize);
			//Begin - PM
			Instances unlabeledSet = new Instances(train, m_CurrentSize, train.numInstances()-m_CurrentSize);
			removeLabels(unlabeledSet);
			Object [] seResults = ((SemiSupSplitEvaluator) m_SplitEvaluator).getResult(trainSubset, unlabeledSet, test);
			//End - PM
			Object [] results = new Object [seResults.length + 1];
			results[0] = getTimestamp();
			System.arraycopy(seResults, 0, results, 1,
					 seResults.length);
			if (m_debugOutput) {
			    String resultName = (""+run+"."+(fold+1)+"."+ m_CurrentSize + "." 
						 + Utils.backQuoteChars(runInstances.relationName())
						 +"."
						 +m_SplitEvaluator.toString()).replace(' ','_');
			    resultName = Utils.removeSubstring(resultName, 
							       "weka.classifiers.");
			    resultName = Utils.removeSubstring(resultName, 
							       "weka.filters.");
			    resultName = Utils.removeSubstring(resultName, 
							       "weka.attributeSelection.");
			    m_ZipDest.zipit(m_SplitEvaluator.getRawResultOutput(), resultName);
			}
			m_ResultListener.acceptResult(this, key, results);
		    } catch (Exception ex) {
			// Save the train and test datasets for debugging purposes?
			throw ex;
		    }
		}
		if (m_PlotPoints != null) {
		    pointNum ++;
		    m_CurrentSize = plotPoint(pointNum);
		}
		else {
		    m_CurrentSize += m_StepSize;
		}
	    }
	}
    }

    /** Determines if the points specified are fractions of the total number of examples */
    protected boolean setIsFraction(){
	if (m_PlotPoints != null){
	    if(!isInteger(m_PlotPoints[0]))//if the first point is not an integer
		m_IsFraction = true;
	    else
		m_IsFraction = false;
	}
	return m_IsFraction;
    }
    
    /** Return the number of training examples for the ith point on the
     * curve for plotPoints as specified.
     */
    protected int plotPoint(int i) {
	// If i beyond number of given plot points return a value greater than maximum training size
	if (i >= m_PlotPoints.length)
	    return maxTrainSize() + 1;
	double point = m_PlotPoints[i];
	// If plot point is an integer (other than a non-initial 1)
	// treat it as a specific number of examples
	if (isInteger(point) && !(Utils.eq(point, 1.0) && i!=0))
	    return (int)point;
	else
	    // Otherwise, treat it as a percentage of the full set
	    return (int)Math.round(point * maxTrainSize());
    }

    /** Return true if the given double represents an integer value */
    protected static boolean isInteger(double val) {
	return Utils.eq(Math.floor(val), Math.ceil(val));
    }

    /**
     * Gets the names of each of the columns produced for a single run.
     * This method should really be static.
     *
     * @return an array containing the name of each column
     */
    public String [] getKeyNames() {

	String [] keyNames = m_SplitEvaluator.getKeyNames();
	// Add in the names of our extra key fields
	int numExtraKeys;
	if(m_IsFraction)
	    numExtraKeys = 5;
	else numExtraKeys = 4;
	String [] newKeyNames = new String [keyNames.length + numExtraKeys];
	newKeyNames[0] = DATASET_FIELD_NAME;
	newKeyNames[1] = RUN_FIELD_NAME;
	newKeyNames[2] = FOLD_FIELD_NAME;
	newKeyNames[3] = STEP_FIELD_NAME;
	if(m_IsFraction) newKeyNames[4] = FRACTION_FIELD_NAME;
	System.arraycopy(keyNames, 0, newKeyNames, numExtraKeys, keyNames.length);
	return newKeyNames;
    }

    /**
     * Gets the data types of each of the columns produced for a single run.
     * This method should really be static.
     *
     * @return an array containing objects of the type of each column. The 
     * objects should be Strings, or Doubles.
     */
    public Object [] getKeyTypes() {

	Object [] keyTypes = m_SplitEvaluator.getKeyTypes();
	int numExtraKeys;
	if(m_IsFraction)
	    numExtraKeys = 5;
	else numExtraKeys = 4;
	// Add in the types of our extra fields
	Object [] newKeyTypes = new String [keyTypes.length + numExtraKeys];
	newKeyTypes[0] = new String();
	newKeyTypes[1] = new String();
	newKeyTypes[2] = new String();
	newKeyTypes[3] = new String();
	if(m_IsFraction) newKeyTypes[4] = new String();
	System.arraycopy(keyTypes, 0, newKeyTypes, numExtraKeys, keyTypes.length);
	return newKeyTypes;
    }

    /**
     * Gets the names of each of the columns produced for a single run.
     * This method should really be static.
     *
     * @return an array containing the name of each column
     */
    public String [] getResultNames() {

	String [] resultNames = m_SplitEvaluator.getResultNames();
	// Add in the names of our extra Result fields
	String [] newResultNames = new String [resultNames.length + 1];
	newResultNames[0] = TIMESTAMP_FIELD_NAME;
	System.arraycopy(resultNames, 0, newResultNames, 1, resultNames.length);
	return newResultNames;
    }

    /**
     * Gets the data types of each of the columns produced for a single run.
     * This method should really be static.
     *
     * @return an array containing objects of the type of each column. The 
     * objects should be Strings, or Doubles.
     */
    public Object [] getResultTypes() {

	Object [] resultTypes = m_SplitEvaluator.getResultTypes();
	// Add in the types of our extra Result fields
	Object [] newResultTypes = new Object [resultTypes.length + 1];
	newResultTypes[0] = new Double(0);
	System.arraycopy(resultTypes, 0, newResultTypes, 1, resultTypes.length);
	return newResultTypes;
    }

    /**
     * Gets a description of the internal settings of the result
     * producer, sufficient for distinguishing a ResultProducer
     * instance from another with different settings (ignoring
     * those settings set through this interface). For example,
     * a cross-validation ResultProducer may have a setting for the
     * number of folds. For a given state, the results produced should
     * be compatible. Typically if a ResultProducer is an OptionHandler,
     * this string will represent the command line arguments required
     * to set the ResultProducer to that state.
     *
     * @return the description of the ResultProducer state, or null
     * if no state is defined
     */
    public String getCompatibilityState() {

	String result = "-X " + m_NumFolds + " -S " + getStepSize() + 
	    " -L " + getLowerSize() + " -U " + getUpperSize() + " ";
	if (m_SplitEvaluator == null) {
	    result += "<null SplitEvaluator>";
	} else {
	    result += "-W " + m_SplitEvaluator.getClass().getName();
	}
	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 outputFileTipText() {
	return "Set the destination for saving raw output. If the rawOutput "
	    +"option is selected, then output from the splitEvaluator for "
	    +"individual folds is saved. If the destination is a directory, "
	    +"then each output is saved to an individual gzip file; if the "
	    +"destination is a file, then each output is saved as an entry "
	    +"in a zip file.";
    }

    /**
     * Get the value of OutputFile.
     *
     * @return Value of OutputFile.
     */
    public File getOutputFile() {
    
	return m_OutputFile;
    }
  
    /**
     * Set the value of OutputFile.
     *
     * @param newOutputFile Value to assign to OutputFile.
     */
    public void setOutputFile(File newOutputFile) {
    
	m_OutputFile = newOutputFile;
    }  

    /**
     * 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 "Number of folds to use in cross validation.";
    }

    /**
     * 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 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.
     */