weka.classifiers.functions.supportVector

Class Kernel

java.lang.Object

weka.classifiers.functions.supportVector.Kernel

All Implemented Interfaces:

java.io.Serializable, CapabilitiesHandler, OptionHandler, RevisionHandler

Direct Known Subclasses:

CachedKernel, PrecomputedKernelMatrixKernel, StringKernel

public abstract class Kernel
extends java.lang.Object
implements java.io.Serializable, OptionHandler, CapabilitiesHandler, RevisionHandler

Abstract kernel. Kernels implementing this class must respect Mercer's condition in order to ensure a correct behaviour of SMOreg.

Version:

$Revision: 9897 $

Author:

Eibe Frank (eibe@cs.waikato.ac.nz), FracPete (fracpete at waikato dot ac dot nz)

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Kernel()

Method Summary

Modifier and Type	Method and Description
void	buildKernel(Instances data) builds the kernel with the given data
java.lang.String	checksTurnedOffTipText() Returns the tip text for this property
abstract void	clean() Frees the memory used by the kernel.
java.lang.String	debugTipText() Returns the tip text for this property
abstract double	eval(int id1, int id2, Instance inst1) Computes the result of the kernel function for two instances.
static Kernel	forName(java.lang.String kernelName, java.lang.String[] options) Creates a new instance of a kernel given it's class name and (optional) arguments to pass to it's setOptions method.
Capabilities	getCapabilities() Returns the Capabilities of this kernel.
boolean	getChecksTurnedOff() Returns whether the checks are turned off or not.
boolean	getDebug() Gets whether debugging output is turned on or not.
java.lang.String[]	getOptions() Gets the current settings of the Kernel.
java.lang.String	getRevision() Returns the revision string.
abstract java.lang.String	globalInfo() Returns a string describing the kernel
java.util.Enumeration	listOptions() Returns an enumeration describing the available options.
static Kernel[]	makeCopies(Kernel model, int num) Creates a given number of deep or shallow (if the kernel implements Copyable) copies of the given kernel using serialization.
static Kernel	makeCopy(Kernel kernel) Creates a shallow copy of the kernel (if it implements Copyable) otherwise a deep copy using serialization.
abstract int	numCacheHits() Returns the number of dot product cache hits.
abstract int	numEvals() Returns the number of kernel evaluation performed.
void	setChecksTurnedOff(boolean value) Disables or enables the checks (which could be time-consuming).
void	setDebug(boolean value) Enables or disables the output of debug information (if the derived kernel supports that)
void	setOptions(java.lang.String[] options) Parses a given list of options.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Kernel

public Kernel()

Method Detail

globalInfo

public abstract java.lang.String globalInfo()

Returns a string describing the kernel

Returns:

a description suitable for displaying in the explorer/experimenter gui

eval

public abstract double eval(int id1,
                            int id2,
                            Instance inst1)
                     throws java.lang.Exception

Computes the result of the kernel function for two instances. If id1 == -1, eval use inst1 instead of an instance in the dataset.

Parameters:

id1 - the index of the first instance in the dataset

id2 - the index of the second instance in the dataset

inst1 - the instance corresponding to id1 (used if id1 == -1)

Returns:

the result of the kernel function

Throws:

java.lang.Exception - if something goes wrong

clean

public abstract void clean()

Frees the memory used by the kernel. (Useful with kernels which use cache.) This function is called when the training is done. i.e. after that, eval will be called with id1 == -1.

numEvals

public abstract int numEvals()

Returns the number of kernel evaluation performed.

Returns:

the number of kernel evaluation performed.

numCacheHits

public abstract int numCacheHits()

Returns the number of dot product cache hits.

Returns:

the number of dot product cache hits, or -1 if not supported by this kernel.

listOptions

public java.util.Enumeration listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

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

Parameters:

options - the list of options as an array of strings

Throws:

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

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the Kernel.

Specified by:

getOptions in interface OptionHandler

Returns:

an array of strings suitable for passing to setOptions

setDebug

public void setDebug(boolean value)

Enables or disables the output of debug information (if the derived kernel supports that)

Parameters:

value - whether to output debugging information

getDebug

public boolean getDebug()

Gets whether debugging output is turned on or not.

Returns:

true if debugging output is produced.

debugTipText

public java.lang.String debugTipText()

Returns the tip text for this property

Returns:

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

setChecksTurnedOff

public void setChecksTurnedOff(boolean value)

Disables or enables the checks (which could be time-consuming). Use with caution!

Parameters:

value - if true turns off all checks

getChecksTurnedOff

public boolean getChecksTurnedOff()

Returns whether the checks are turned off or not.

Returns:

true if the checks are turned off

checksTurnedOffTipText

public java.lang.String checksTurnedOffTipText()

Returns the tip text for this property

Returns:

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

getCapabilities

public Capabilities getCapabilities()

Returns the Capabilities of this kernel. Derived kernels have to override this method to enable capabilities.

Specified by:

getCapabilities in interface CapabilitiesHandler

Returns:

the capabilities of this object

See Also:

Capabilities

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Returns:

the revision

buildKernel

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

builds the kernel with the given data

Parameters:

data - the data to base the kernel on

Throws:

java.lang.Exception - if something goes wrong

makeCopy

public static Kernel makeCopy(Kernel kernel)
                       throws java.lang.Exception

Creates a shallow copy of the kernel (if it implements Copyable) otherwise a deep copy using serialization.

Parameters:

kernel - the kernel to copy

Returns:

a shallow or deep copy of the kernel

Throws:

java.lang.Exception - if an error occurs

makeCopies

public static Kernel[] makeCopies(Kernel model,
                                  int num)
                           throws java.lang.Exception

Creates a given number of deep or shallow (if the kernel implements Copyable) copies of the given kernel using serialization.

Parameters:

model - the kernel to copy

num - the number of kernel copies to create.

Returns:

an array of kernels.

Throws:

java.lang.Exception - if an error occurs

forName

public static Kernel forName(java.lang.String kernelName,
                             java.lang.String[] options)
                      throws java.lang.Exception

Creates a new instance of a kernel given it's class name and (optional) arguments to pass to it's setOptions method.

Parameters:

kernelName - the fully qualified class name of the classifier

options - an array of options suitable for passing to setOptions. May be null.

Returns:

the newly created classifier, ready for use.

Throws:

java.lang.Exception - if the classifier name is invalid, or the options supplied are not acceptable to the classifier