All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Class weka.classifiers.BVDecompose

java.lang.Object
   |
   +----weka.classifiers.BVDecompose

public class BVDecompose

extends Object

implements OptionHandler

R. Kohavi & D. Wolpert (1996), Bias plus variance decomposition for zero-one loss functions, in Proc. of the Thirteenth International Machine Learning Conference (ICML96) download postscript.

Valid options are:

-D
Turn on debugging output.

-W classname
Specify the full class name of a learner to perform the decomposition on (required).

-t filename
Set the arff file to use for the decomposition (required).

-T num
Specify the number of instances in the training pool (default 100).

-c num
Specify the index of the class attribute (default last).

-x num
Set the number of train iterations (default 50).

-s num
Set the seed for the dataset randomisation (default 1).

Options after -- are passed to the designated sub-learner.

Version:

$Revision: 1.4 $

Author:

Len Trigg (trigg@cs.waikato.ac.nz)

BVDecompose()

decompose()

Carry out the bias-variance decomposition

getBias()

Get the calculated bias squared

getClassifier()

Gets the name of the classifier being analysed

getClassIndex()

Get the index (starting from 1) of the attribute used as the class.

getDataFileName()

Get the name of the data file used for the decomposition

getDebug()

Gets whether debugging is turned on

getError()

Get the calculated error rate

getOptions()

Gets the current settings of the CheckClassifier.

getSeed()

Gets the random number seed

getSigma()

Get the calculated sigma squared

getTrainIterations()

Gets the maximum number of boost iterations

getTrainPoolSize()

Get the number of instances in the training pool.

getVariance()

Get the calculated variance

listOptions()

Returns an enumeration describing the available options

main(String[])

Test method for this class

setClassifier(Classifier)

Set the classifiers being analysed

setClassIndex(int)

Sets index of attribute to discretize on

setDataFileName(String)

Sets the maximum number of boost iterations

setDebug(boolean)

Sets debugging mode

setOptions(String[])

Parses a given list of options.

setSeed(int)

Sets the random number seed

setTrainIterations(int)

Sets the maximum number of boost iterations

setTrainPoolSize(int)

Set the number of instances in the training pool.

toString()

Returns description of the bias-variance decomposition results.

 public BVDecompose()

 public Enumeration listOptions()

Returns an enumeration describing the available options

Returns:

an enumeration of all the available options

 public void setOptions(String options[]) throws Exception

Parses a given list of options. Valid options are:

-D
Turn on debugging output.

-W classname
Specify the full class name of a learner to perform the decomposition on (required).

-t filename
Set the arff file to use for the decomposition (required).

-T num
Specify the number of instances in the training pool (default 100).

-c num
Specify the index of the class attribute (default last).

-x num
Set the number of train iterations (default 50).

-s num
Set the seed for the dataset randomisation (default 1).

Options after -- are passed to the designated sub-learner.

Parameters:

options - the list of options as an array of strings

Throws: Exception

if an option is not supported

 public String[] getOptions()

Gets the current settings of the CheckClassifier.

Returns:

an array of strings suitable for passing to setOptions

 public int getTrainPoolSize()

Get the number of instances in the training pool.

Returns:

number of instances in the training pool.

 public void setTrainPoolSize(int numTrain)

Set the number of instances in the training pool.

Parameters:

numTrain - number of instances in the training pool.

 public void setClassifier(Classifier newClassifier)

Set the classifiers being analysed

Parameters:

newClassifier - the Classifier to use.

 public Classifier getClassifier()

Gets the name of the classifier being analysed

Returns:

the classifier being analysed.

 public void setDebug(boolean debug)

Sets debugging mode

Parameters:

debug - true if debug output should be printed

 public boolean getDebug()

Gets whether debugging is turned on

Returns:

true if debugging output is on

 public void setSeed(int seed)

Sets the random number seed

 public int getSeed()

Gets the random number seed

Returns:

the random number seed

 public void setTrainIterations(int trainIterations)

Sets the maximum number of boost iterations

 public int getTrainIterations()

Gets the maximum number of boost iterations

Returns:

the maximum number of boost iterations

 public void setDataFileName(String dataFileName)

Sets the maximum number of boost iterations

 public String getDataFileName()

Get the name of the data file used for the decomposition

Returns:

the name of the data file

 public int getClassIndex()

Get the index (starting from 1) of the attribute used as the class.

Returns:

the index of the class attribute

 public void setClassIndex(int classIndex)

Sets index of attribute to discretize on

Parameters:

index - the index (starting from 1) of the class attribute

 public double getBias()

Get the calculated bias squared

Returns:

the bias squared

 public double getVariance()

Get the calculated variance

Returns:

the variance

 public double getSigma()

Get the calculated sigma squared

Returns:

the sigma squared

 public double getError()

Get the calculated error rate

Returns:

the error rate

 public void decompose() throws Exception

Carry out the bias-variance decomposition

Throws: Exception

if the decomposition couldn't be carried out

 public String toString()

Returns description of the bias-variance decomposition results.

Returns:

the bias-variance decomposition results as a string

Overrides:

toString in class Object

 public static void main(String args[])

Test method for this class

Parameters:

args - the command line arguments

All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home