weka.classifiers.functions
Class PaceRegression

java.lang.Object
  weka.classifiers.Classifier
      weka.classifiers.functions.PaceRegression

All Implemented Interfaces:

java.lang.Cloneable, OptionHandler, java.io.Serializable, WeightedInstancesHandler

public class PaceRegression

extends Classifier

implements OptionHandler, WeightedInstancesHandler

Class for building pace regression linear models and using them for prediction.

Under regularity conditions, pace regression is provably optimal when the number of coefficients tends to infinity. It consists of a group of estimators that are either overall optimal or optimal under certain conditions.

The current work of the pace regression theory, and therefore also this implementation, do not handle:

- missing values
- non-binary nominal attributes
- the case that n - k is small where n is number of instances and k is number of coefficients (the threshold used in this implmentation is 20)

Valid options are:

-D
Produce debugging output.

-E estimator
The estimator can be one of the following:

• eb -- Empirical Bayes estimator for noraml mixture (default)
  
• nested -- Optimal nested model selector for normal mixture
  
• subset -- Optimal subset selector for normal mixture
  
• pace2 -- PACE2 for Chi-square mixture
  
• pace4 -- PACE4 for Chi-square mixture
  
• pace6 -- PACE6 for Chi-square mixture
  
• ols -- Ordinary least squares estimator
  
• aic -- AIC estimator
  
• bic -- BIC estimator
  
• ric -- RIC estimator
  
• olsc -- Ordinary least squares subset selector with a threshold
  

-S Threshold for the olsc estimator

REFERENCES

Wang, Y. (2000). "A new approach to fitting linear models in high dimensional spaces." PhD Thesis. Department of Computer Science, University of Waikato, New Zealand.

Wang, Y. and Witten, I. H. (2002). "Modeling for optimal probability prediction." Proceedings of ICML'2002. Sydney.

Version:

$Revision: 1.1 $

Author:

Yong Wang (yongwang@cs.waikato.ac.nz), Gabi Schmidberger (gabi@cs.waikato.ac.nz)

See Also:

Serialized Form

Field Summary

private static int	aicEstimator
private static int	bicEstimator
private static int	ebEstimator
private int	m_ClassIndex The index of the class attribute
private double[]	m_Coefficients Array for storing coefficients of linear regression.
private boolean	m_Debug True if debug output will be printed
(package private) Instances	m_Model The model used
private static int	nestedEstimator
private static int	olscEstimator
private double	olscThreshold
private static int	olsEstimator
private static int	pace2Estimator
private static int	pace4Estimator
private static int	pace6Estimator
private int	paceEstimator
private static int	ricEstimator
private static int	subsetEstimator
static Tag[]	TAGS_ESTIMATOR

Constructor Summary

PaceRegression()

Method Summary

void	buildClassifier(Instances data) Builds a pace regression model for the given data.
boolean	checkForMissing(Instance instance, Instances model) Checks if an instance has a missing value.
boolean	checkForMissing(Instances data) Checks if instances have a missing value.
boolean	checkForNonBinary(Instances data) Checks if any of the nominal attributes is non-binary.
double	classifyInstance(Instance instance) Classifies the given instance using the linear regression function.
double[]	coefficients() Returns the coefficients for this linear model.
java.lang.String	debugTipText() Returns the tip text for this property
java.lang.String	estimatorTipText() Returns the tip text for this property
boolean	getDebug() Controls whether debugging output will be printed
SelectedTag	getEstimator() Gets the estimator
java.lang.String[]	getOptions() Gets the current settings of the classifier.
double	getThreshold() Gets the threshold for olsc estimator
private double[][]	getTransformedDataMatrix(Instances data, int classIndex) Transforms dataset into a two-dimensional array.
java.lang.String	globalInfo() Returns a string describing this classifier
java.util.Enumeration	listOptions() Returns an enumeration describing the available options.
static void	main(java.lang.String[] argv) Generates a linear regression function predictor.
int	numParameters() Get the number of coefficients used in the model
private double[]	pace(double[][] matrix_X, double[] vector_Y) pace regression
private double	regressionPrediction(Instance transformedInstance, double[] coefficients) Calculate the dependent value for a given instance for a given regression model.
void	setDebug(boolean debug) Controls whether debugging output will be printed
void	setEstimator(SelectedTag estimator) Sets the estimator.
void	setOptions(java.lang.String[] options) Parses a given list of options.
void	setThreshold(double newThreshold) Set threshold for the olsc estimator
java.lang.String	thresholdTipText() Returns the tip text for this property
java.lang.String	toString() Outputs the linear regression model as a string.

Methods inherited from class weka.classifiers.Classifier

distributionForInstance, forName, makeCopies

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

m_Model

Instances m_Model

The model used

m_Coefficients

private double[] m_Coefficients

Array for storing coefficients of linear regression.

m_ClassIndex

private int m_ClassIndex

The index of the class attribute

m_Debug

private boolean m_Debug

True if debug output will be printed

olsEstimator

private static final int olsEstimator

See Also:

Constant Field Values

ebEstimator

private static final int ebEstimator

See Also:

Constant Field Values

nestedEstimator

private static final int nestedEstimator

See Also:

Constant Field Values

subsetEstimator

private static final int subsetEstimator

See Also:

Constant Field Values

pace2Estimator

private static final int pace2Estimator

See Also:

Constant Field Values

pace4Estimator

private static final int pace4Estimator

See Also:

Constant Field Values

pace6Estimator

private static final int pace6Estimator

See Also:

Constant Field Values

olscEstimator

private static final int olscEstimator

See Also:

Constant Field Values

aicEstimator

private static final int aicEstimator

See Also:

Constant Field Values

bicEstimator

private static final int bicEstimator

See Also:

Constant Field Values

ricEstimator

private static final int ricEstimator

See Also:

Constant Field Values

TAGS_ESTIMATOR

public static final Tag[] TAGS_ESTIMATOR

paceEstimator

private int paceEstimator

olscThreshold

private double olscThreshold

Constructor Detail

PaceRegression

public PaceRegression()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing this classifier

Returns:

a description of the classifier suitable for displaying in the explorer/experimenter gui

buildClassifier

public void buildClassifier(Instances data)
                     throws java.lang.Exception

Builds a pace regression model for the given data.

Specified by:

buildClassifier in class Classifier

Parameters:

data - the training data to be used for generating the linear regression function

Throws:

java.lang.Exception - if the classifier could not be built successfully

pace

private double[] pace(double[][] matrix_X,
                      double[] vector_Y)

pace regression

Parameters:

matrix_X - matrix with observations

vector_Y - vektor with class values

Returns:

vector with coefficients

Throws:

java.lang.Exception - if pace regression cannot be done successfully

checkForMissing

public boolean checkForMissing(Instances data)

Checks if instances have a missing value.

Parameters:

data - the data set

Returns:

true if missing value is present in data set

checkForMissing

public boolean checkForMissing(Instance instance,
                               Instances model)

Checks if an instance has a missing value.

Parameters:

instance - the instance

Returns:

true if missing value is present

checkForNonBinary

public boolean checkForNonBinary(Instances data)

Checks if any of the nominal attributes is non-binary.

Parameters:

data - the data set

Returns:

true if non binary attribute is present

getTransformedDataMatrix

private double[][] getTransformedDataMatrix(Instances data,
                                            int classIndex)

Transforms dataset into a two-dimensional array.

Parameters:

data - dataset

classIndex - index of the class attribute

classifyInstance

public double classifyInstance(Instance instance)
                        throws java.lang.Exception

Classifies the given instance using the linear regression function.

Overrides:

classifyInstance in class Classifier

Parameters:

instance - the test instance

Returns:

the classification

Throws:

java.lang.Exception - if classification can't be done successfully

toString

public java.lang.String toString()

Outputs the linear regression model as a string.

listOptions

public java.util.Enumeration listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

Overrides:

listOptions in class Classifier

Returns:

an enumeration of all the available options.

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Specified by:

setOptions in interface OptionHandler

Overrides:

setOptions in class Classifier

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

coefficients

public double[] coefficients()

Returns the coefficients for this linear model.

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the classifier.

Specified by:

getOptions in interface OptionHandler

Overrides:

getOptions in class Classifier

Returns:

an array of strings suitable for passing to setOptions

numParameters

public int numParameters()

Get the number of coefficients used in the model

Returns:

the number of coefficients

debugTipText

public java.lang.String debugTipText()

Returns the tip text for this property

Overrides:

debugTipText in class Classifier

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setDebug

public void setDebug(boolean debug)

Controls whether debugging output will be printed

Overrides:

setDebug in class Classifier

Parameters:

debug - true if debugging output should be printed

getDebug

public boolean getDebug()

Controls whether debugging output will be printed

Overrides:

getDebug in class Classifier

Returns:

true if debugging output is on

estimatorTipText

public java.lang.String estimatorTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

getEstimator

public SelectedTag getEstimator()

Gets the estimator

Returns:

the estimator

setEstimator

public void setEstimator(SelectedTag estimator)

Sets the estimator.

Parameters:

estimator - the new estimator

thresholdTipText

public java.lang.String thresholdTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setThreshold

public void setThreshold(double newThreshold)

Set threshold for the olsc estimator

getThreshold

public double getThreshold()

Gets the threshold for olsc estimator

Returns:

the threshold

regressionPrediction

private double regressionPrediction(Instance transformedInstance,
                                    double[] coefficients)
                             throws java.lang.Exception

Calculate the dependent value for a given instance for a given regression model.

Parameters:

transformedInstance - the input instance

coefficients - an array of coefficients for the regression model

Returns:

the regression value for the instance.

Throws:

java.lang.Exception - if the class attribute of the input instance is not assigned

main

public static void main(java.lang.String[] argv)

Generates a linear regression function predictor.