javax.datamining.algorithm.svm.regression
Interface SVMRegressionSettings

All Superinterfaces:

AlgorithmSettings, SupervisedAlgorithmSettings

public interface SVMRegressionSettings

extends SupervisedAlgorithmSettings

A SVMRegressionSettings object supports function settings specific to the SVM regression mining algorithm.

Author:

JSR-73 Java Data Mining Expert Group

See Also:

AlgorithmSettings, SupervisedAlgorithmSettings

Method Summary

double	getComplexityFactor() Returns the complexity factor, either set by the user or the default value.
double	getCStrategy() Returns the C strategy value, either set by the user or the default value.
double	getEpsilon() Returns the value of the interval of the allowed error in epsilon-insensitive regression, either set by the user or the default value.
int	getKernelCacheSize() Returns the kernel cache size in bytes to be used for storing computed kernels during the build operation.
KernelFunction	getKernelFunction() Returns the kernel function to be used to transform the input data into a high dimensional feature space.
int	getPolynomialDegree() Returns the degree of polynomial kernel function, either set by the user or the default value.
double	getStandardDeviation() Returns the standard deviation value (also known as radius) to be used when the kernel function is Gaussian.
double	getTolerance() Returns the tolerance value allowed before termination, either set by the user or the default value.
void	setComplexityFactor(double factor) Sets the complexity factor that is a parameter trading off complexity for prediction loss.
void	setCStrategy(double cValue) Sets the C strategy value.
void	setEpsilon(double epsilon) Sets the value of the interval of the allowed error in epsilon-insensitive regression.
void	setKernelCacheSize(int cacheSize) Sets the kernel cache size in bytes to be used for storing computed kernels during the build operation.
void	setKernelFunction(KernelFunction kernelFunction) Sets the kernel function to be used to transform the input data into a high dimensional feature space.
void	setPolynomialDegree(int degree) Sets the degree of the polynomial kernel function.
void	setStandardDeviation(double stdDeviation) Sets the standard deviation value to be used with Gaussian kernel function.
void	setTolerance(double tolerance) Sets the tolerance value allowed before termination.

Methods inherited from interface javax.datamining.base.AlgorithmSettings

getMiningAlgorithm, verify

Method Detail

getComplexityFactor

public double getComplexityFactor()

Returns the complexity factor, either set by the user or the default value. The complexity factor is a parameter trading off complexity for prediction loss.

Returns:

double

getCStrategy

public double getCStrategy()

Returns the C strategy value, either set by the user or the default value.

Returns:

double

getEpsilon

public double getEpsilon()

Returns the value of the interval of the allowed error in epsilon-insensitive regression, either set by the user or the default value.

Returns:

double

getKernelCacheSize

public int getKernelCacheSize()

Returns the kernel cache size in bytes to be used for storing computed kernels during the build operation. The returned value is either set by the user or the default value.

Returns:

int

getKernelFunction

public KernelFunction getKernelFunction()

Returns the kernel function to be used to transform the input data into a high dimensional feature space. The kernel function is either set by the user or the default kernel function.

Returns:

KernelFunction

getPolynomialDegree

public int getPolynomialDegree()

Returns the degree of polynomial kernel function, either set by the user or the default value.

Returns:

int

getStandardDeviation

public double getStandardDeviation()

Returns the standard deviation value (also known as radius) to be used when the kernel function is Gaussian.

Returns:

double

getTolerance

public double getTolerance()

Returns the tolerance value allowed before termination, either set by the user or the default value.

Returns:

double

setComplexityFactor

public void setComplexityFactor(double factor)

Sets the complexity factor that is a parameter trading off complexity for prediction loss. The factor must be a non-negative number.

Parameters:

factor - The complexity factor to be used.

Returns:

void

setCStrategy

public void setCStrategy(double cValue)

Sets the C strategy value. If not specified by the user, the system chooses the default value.

Parameters:

cValue - The C strategy value to be used.

Returns:

void

setEpsilon

public void setEpsilon(double epsilon)

Sets the value of the interval of the allowed error in epsilon-insensitive regression. The value must be between 0 and 1, noted as [0,1) where 1 is excluded.

Parameters:

epsilon - The epsilon value to be used.

Returns:

void

setKernelCacheSize

public void setKernelCacheSize(int cacheSize)

Sets the kernel cache size in bytes to be used for storing computed kernels during the build operation. The value must be a positive integer.

Parameters:

cacheSize - The kernel cache size in bytes.

Returns:

void

setKernelFunction

public void setKernelFunction(KernelFunction kernelFunction)

Sets the kernel function to be used to transform the input data into a high dimensional feature space. If null is specified, the default kernel function is used.

Parameters:

kernelFunction - The kernel function to be used.

Returns:

void

setPolynomialDegree

public void setPolynomialDegree(int degree)

Sets the degree of the polynomial kernel function. The value must be greater than 0.

Parameters:

degree - The degree of the polynomial kernel function.

Returns:

void

setStandardDeviation

public void setStandardDeviation(double stdDeviation)

Sets the standard deviation value to be used with Gaussian kernel function. The value must be a positive number.

Parameters:

stdDeviation - The standard deviation value for Gaussian kernel function.

Returns:

void

setTolerance

public void setTolerance(double tolerance)

Sets the tolerance value allowed before termination. The value must be between 0 and 1.

Parameters:

tolerance - The tolerance value.

Returns:

void