simplelogistic.java

MacroWeka扩展了著名数据挖掘工具weka

		
	options[current++] = "-I"; 
	options[current++] = ""+getNumBoostingIterations();
	
	if (!getUseCrossValidation()) {
	    options[current++] = "-S";
	} 

	if (getErrorOnProbabilities()) {
	    options[current++] = "-P";
	} 

	options[current++] = "-M"; 
	options[current++] = ""+getMaxBoostingIterations();
	
	options[current++] = "-H"; 
	options[current++] = ""+getHeuristicStop();

	while (current < options.length) {
	    options[current++] = "";
	} 
	return options;
    } 

    /**
     * Get the value of numBoostingIterations.
     */
    public int getNumBoostingIterations(){
	return m_numBoostingIterations;
    }
    /**
     * Get the value of useCrossValidation.
     */
    public boolean getUseCrossValidation(){
	return m_useCrossValidation;
    }

    /**
     * Get the value of errorOnProbabilities.
     */
    public boolean getErrorOnProbabilities(){
	return m_errorOnProbabilities;
    }
    
    /**
     * Get the value of maxBoostingIterations.
     */
    public int getMaxBoostingIterations(){
	return m_maxBoostingIterations;
    }

    /**
     * Get the value of heuristicStop.
     */
    public int getHeuristicStop(){
	return m_heuristicStop;
    }
    
    /**
     * Set the value of numBoostingIterations.
     */
    public void setNumBoostingIterations(int n){
	m_numBoostingIterations = n;
    }

    /**
     * Set the value of useCrossValidation.
     */
    public void setUseCrossValidation(boolean l){
	m_useCrossValidation = l;
    }

    /**
     * Set the value of errorOnProbabilities.
     */
    public void setErrorOnProbabilities(boolean l){
	m_errorOnProbabilities = l;
    }

    /**
     * Set the value of maxBoostingIterations.
     */
    public void setMaxBoostingIterations(int n){
	m_maxBoostingIterations = n;
    } 

    /**
     * Set the value of heuristicStop.
     */
    public void setHeuristicStop(int n){
	if (n == 0) m_heuristicStop = m_maxBoostingIterations; else m_heuristicStop = n;
    }

    /**
     * Get the number of LogitBoost iterations performed (= the number of regression functions fit by LogitBoost).
     */
    public int getNumRegressions(){
	return m_boostedModel.getNumRegressions();
    }

    /**
     * Returns a description of the logistic model (attributes/coefficients).
     */
    public String toString(){
	if (m_boostedModel == null) return "No model built";
	return "SimpleLogistic:\n" + m_boostedModel.toString();
    }

    /**
     * Returns the fraction of all attributes in the data that are used in the logistic model (in percent).
     * An attribute is used in the model if it is used in any of the models for the different classes.
     */
    public double measureAttributesUsed(){
	return m_boostedModel.percentAttributesUsed();
    }
       
     /**
     * Returns an enumeration of the additional measure names
     * @return an enumeration of the measure names
     */
    public Enumeration enumerateMeasures() {
	Vector newVector = new Vector(3);
	newVector.addElement("measureAttributesUsed");
	newVector.addElement("measureNumIterations");
	return newVector.elements();
    }
    
    /**
     * Returns the value of the named measure
     * @param additionalMeasureName the name of the measure to query for its value
     * @return the value of the named measure
     * @exception IllegalArgumentException if the named measure is not supported
     */
    public double getMeasure(String additionalMeasureName) {
	if (additionalMeasureName.compareToIgnoreCase("measureAttributesUsed") == 0) {
	    return measureAttributesUsed();
      	} else if(additionalMeasureName.compareToIgnoreCase("measureNumIterations") == 0){
	    return getNumRegressions();
	} else {
	    throw new IllegalArgumentException(additionalMeasureName 
					       + " not supported (SimpleLogistic)");
	}
    }    


    /**
     * Returns a string describing classifier
     * @return a description suitable for
     * displaying in the explorer/experimenter gui
     */
    public String globalInfo() {
	return "Classifier for building linear logistic regression models. LogitBoost with simple regression "
	    +"functions as base learners is used for fitting the logistic models. The optimal number of LogitBoost "
	    +"iterations to perform is cross-validated, which leads to automatic attribute selection. "
	    +"For more information see: N.Landwehr, M.Hall, E. Frank 'Logistic Model Trees' (ECML 2003).";	    
    }

    /**
     * Returns the tip text for this property
     * @return tip text for this property suitable for
     * displaying in the explorer/experimenter gui
     */
    public String numBoostingIterationsTipText() {
	return "Set fixed number of iterations for LogitBoost. If >= 0, this sets the number of LogitBoost iterations "
	    +"to perform. If < 0, the number is cross-validated or a stopping criterion on the training set is used "
	    +"(depending on the value of useCrossValidation).";
    }

    /**
     * Returns the tip text for this property
     * @return tip text for this property suitable for
     * displaying in the explorer/experimenter gui
     */
    public String useCrossValidationTipText() {
	return "Sets whether the number of LogitBoost iterations is to be cross-validated or the stopping criterion "
	    +"on the training set should be used. If not set (and no fixed number of iterations was given), "
	    +"the number of LogitBoost iterations is used that minimizes the error on the training set "
	    +"(misclassification error or error on probabilities depending on errorOnProbabilities).";
    }

    /**
     * Returns the tip text for this property
     * @return tip text for this property suitable for
     * displaying in the explorer/experimenter gui
     */
    public String errorOnProbabilitiesTipText() {
	return "Use error on the probabilties as error measure when determining the best number of LogitBoost iterations. "
	    +"If set, the number of LogitBoost iterations is chosen that minimizes the root mean squared error "
	    +"(either on the training set or in the cross-validation, depending on useCrossValidation).";
    }

    /**
     * Returns the tip text for this property
     * @return tip text for this property suitable for
     * displaying in the explorer/experimenter gui
     */
    public String maxBoostingIterationsTipText() {
	return "Sets the maximum number of iterations for LogitBoost. Default value is 500, for very small/large "
	    +"datasets a lower/higher value might be preferable.";
    }

    /**
     * Returns the tip text for this property
     * @return tip text for this property suitable for
     * displaying in the explorer/experimenter gui
     */
    public String heuristicStopTipText() {
	return "If heuristicStop > 0, the heuristic for greedy stopping while cross-validating the number of "
	    +"LogitBoost iterations is enabled. This means LogitBoost is stopped if no new error minimum "
	    +"has been reached in the last heuristicStop iterations. It is recommended to use this heuristic, "
	    +"it gives a large speed-up especially on small datasets. The default value is 50.";
    }    

    /**
     * Main method for testing this class
     *
     * @param String options 
     */
    public static void main(String[] argv) {	
	try {
	    System.out.println(Evaluation.evaluateModel(new SimpleLogistic(), argv));
	} catch (Exception e) {
	    e.printStackTrace();
	    System.err.println(e.getMessage());
	}
    }

}