sgpp::datadriven::PrimalDualSVM Class Reference

Implementation of a support vector machine in primal formulation which additionally stores support vectors. More...

#include <PrimalDualSVM.hpp>

Public Member Functions
void	add (sgpp::base::Grid &grid, sgpp::base::DataVector &x, double alpha, size_t dataDim)
	Adds a data point to the set of support vectors. More...
void	multiply (double scalar)
	Scales the normal vector w. More...
int	predict (sgpp::base::Grid &grid, sgpp::base::DataVector &x, size_t dataDim)
	Class prediction for a given data point and grid. More...
double	predictRaw (sgpp::base::Grid &grid, sgpp::base::DataVector &x, size_t dataDim, bool trans=false)
	Raw prediction for a given data point and grid. More...
	PrimalDualSVM (size_t dim, size_t inputDim, size_t budget, bool useBias)
	Constructor. More...
	~PrimalDualSVM ()
	Destructor. More...

Public Attributes
base::DataVector	alphas
base::DataVector	norms
base::DataMatrix	svs
base::DataVector	w
base::DataVector	w2

Protected Attributes
double	bias
size_t	budget
bool	useBias

Detailed Description

Implementation of a support vector machine in primal formulation which additionally stores support vectors.

For non-linear classification, sparse grid kernels are applied.

Constructor & Destructor Documentation

PrimalDualSVM()

sgpp::datadriven::PrimalDualSVM::PrimalDualSVM	(	size_t	dim,
		size_t	inputDim,
		size_t	budget,
		bool	useBias
	)

Constructor.

Parameters

dim	The dimension of the feature space (i.e. grid size)
inputDim	The dimension of the data
budget	The max number of support vectors
useBias	Indicates whether bias should be used

References sgpp::base::DataMatrix::reserveAdditionalRows(), and svs.

~PrimalDualSVM()

sgpp::datadriven::PrimalDualSVM::~PrimalDualSVM

(

)

Destructor.

Member Function Documentation

add()

void sgpp::datadriven::PrimalDualSVM::add	(	sgpp::base::Grid &	grid,
		sgpp::base::DataVector &	x,
		double	alpha,
		size_t	dataDim
	)

Adds a data point to the set of support vectors.

Parameters

grid	The sparse grid which defines the transformation
x	The data point
alpha	The corresponding weight
dataDim	Dimension of x

References sgpp::base::DataVector::add(), alpha, alphas, sgpp::base::DataVector::append(), sgpp::base::DataMatrix::appendRow(), bias, budget, sgpp::op_factory::createOperationMultipleEval(), sgpp::base::DataMatrix::getNrows(), sgpp::base::Grid::getSize(), sgpp::base::DataVector::mult(), norms, svs, useBias, w, and w2.

multiply()

void sgpp::datadriven::PrimalDualSVM::multiply

(

double

scalar

)

Scales the normal vector w.

Parameters

scalar

The scaling factor

References alphas, bias, sgpp::base::DataVector::getSize(), sgpp::base::DataVector::mult(), useBias, w, and w2.

predict()

int sgpp::datadriven::PrimalDualSVM::predict	(	sgpp::base::Grid &	grid,
		sgpp::base::DataVector &	x,
		size_t	dataDim
	)

Class prediction for a given data point and grid.

Parameters

grid	The sparse grid which defines the transformation
x	The data point
dataDim	Dimension of x

Returns

The predicted class label (-1 or 1)

References predictRaw().

predictRaw()

double sgpp::datadriven::PrimalDualSVM::predictRaw	(	sgpp::base::Grid &	grid,
		sgpp::base::DataVector &	x,
		size_t	dataDim,
		bool	trans = false
	)

Raw prediction for a given data point and grid.

Parameters

grid	The sparse grid which defines the transformation
x	The data point
dataDim	Dimension of x
trans	Indicates whether x is already transformed into feature space

Returns

The raw prediction value

References bias, sgpp::op_factory::createOperationMultipleEval(), sgpp::base::DataVector::dotProduct(), sgpp::base::Grid::getSize(), sgpp::base::DataMatrix::setRow(), useBias, and w.

Referenced by predict().

Member Data Documentation

alphas

base::DataVector sgpp::datadriven::PrimalDualSVM::alphas

Referenced by add(), and multiply().

bias

double sgpp::datadriven::PrimalDualSVM::bias

protected

Referenced by add(), multiply(), and predictRaw().

budget

size_t sgpp::datadriven::PrimalDualSVM::budget

protected

Referenced by add().

norms

base::DataVector sgpp::datadriven::PrimalDualSVM::norms

Referenced by add().

svs

base::DataMatrix sgpp::datadriven::PrimalDualSVM::svs

Referenced by add(), and PrimalDualSVM().

useBias

bool sgpp::datadriven::PrimalDualSVM::useBias

protected

Referenced by add(), multiply(), and predictRaw().

w

base::DataVector sgpp::datadriven::PrimalDualSVM::w

Referenced by add(), multiply(), and predictRaw().

w2

base::DataVector sgpp::datadriven::PrimalDualSVM::w2

Referenced by add(), and multiply().

---

The documentation for this class was generated from the following files:

• datadriven/src/sgpp/datadriven/application/PrimalDualSVM.hpp
• datadriven/src/sgpp/datadriven/application/PrimalDualSVM.cpp