stores a sparse grid not a knot B-spline interpolant in the framework of a respsonse surface for a vector valued objective function (in particular time dependent objective functions, where the return values are the time series) More...

#include <SplineResponseSurfaceVector.hpp>

Inheritance diagram for sgpp::optimization::SplineResponseSurfaceVector:

Public Member Functions
void	distributionAdaptive (size_t maxNumGridPoints, size_t initialLevel, sgpp::base::DistributionsVector pdfs, size_t refinementsNum=3, bool verbose=false)
	creates a distribution adaptive sparse grid intepolant

sgpp::base::DataVector	eval (sgpp::base::DataVector v) override
	evaluates this response surface

sgpp::base::DataVector	evalJacobian (sgpp::base::DataVector v, sgpp::base::DataMatrix &jacobian) override
	evaluates the response surface and its gradient

void	full (size_t level)
	creates a regualar full grid interpolant

sgpp::base::DataMatrix	getCoefficients ()

size_t	getDegree ()

std::shared_ptr< sgpp::base::Grid >	getGrid ()

sgpp::base::DataVector	getIntegrals ()
	return the integrals of the response surface

sgpp::base::DataVector	getLowerBounds ()

sgpp::base::DataVector	getMeans (sgpp::base::DistributionsVector pdfs, size_t quadOrder)
	return the mean of the response surface w.r.t.

size_t	getSize ()

sgpp::base::DataVector	getUpperBounds ()

sgpp::base::DataVector	getVariances (sgpp::base::DistributionsVector pdfs, size_t quadOrder, sgpp::base::DataVector &means, sgpp::base::DataVector &meanSquares)
	return the variance of the response surface w.r.t.

void	nextDistributionAdaptiveGrid (size_t refinementsNum, sgpp::base::DistributionsVector pdfs, bool verbose=false)
	refines the grid distribution adaptive but does not recalculate interpolation coefficients

void	nextSurplusAdaptiveGrid (size_t refinementsNum, bool verbose=false)
	refines the grid surplus adaptive but does not recalculate interpolation coefficients

void	refineDistributionAdaptive (size_t refinementsNum, sgpp::base::DistributionsVector pdfs, bool verbose=false)
	refines the grid distribution adaptive and recalculates the interpoaltion coefficients

void	refineSurplusAdaptive (size_t refinementsNum, bool verbose=false)
	refines the grid surplus adaptive and recalculates the interpoaltion coefficients

void	regular (size_t level)
	creates a regualar sparse grid interpolant

void	regularByPoints (size_t numPoints, bool verbose=false)
	creates a regular grid of the lowest level with more grid points than specified

std::string	serializeGrid ()
	calculates the minimimum with gradient descent

	SplineResponseSurfaceVector (size_t numDim, size_t numRes, sgpp::base::DataVector lb, sgpp::base::DataVector ub, std::string gridFilename, size_t degree, std::string coeffFileName)
	Constructor loading an already calculated response surface from serialized grid and coefficients (gridFile must be created by Grid::serialize, coeff file by DataMatrix::ToFile)

	SplineResponseSurfaceVector (std::shared_ptr< sgpp::base::VectorFunction > objectiveFunc, sgpp::base::DataVector lb, sgpp::base::DataVector ub, sgpp::base::GridType gridType, size_t degree=3)
	Constructor.

void	surplusAdaptive (size_t maxNumGridPoints, size_t initialLevel, size_t refinementsNum=3, bool verbose=false)
	creates a surplus adaptive sparse grid interpolant

	~SplineResponseSurfaceVector () override
	Destructor.

Public Member Functions inherited from sgpp::optimization::ResponseSurfaceVector
sgpp::base::DataVector	averageL2Error (std::shared_ptr< sgpp::base::VectorFunction > objectiveFunc, sgpp::base::DataVector &componentwiseErrors, size_t numMCPoints=1000)
	Calculates the average l2 error between interpolant and objective function.

sgpp::base::DataVector	averageNRMSE (std::shared_ptr< sgpp::base::VectorFunction > objectiveFunc, sgpp::base::DataMatrix &componentwiseErrorData, size_t numMCPoints=1000)
	Calculates the normalized root mean square error between interpolant and objective function at random points.

size_t	getNumDim ()
	Calculates the normalized root mean square error between interpolant and objective function from a precalculated set of test points and according values (this set is usually generated by ResponseSurfaceVector::precalculateErrorTestData)

size_t	getNumRes ()

	ResponseSurfaceVector (size_t numDim, size_t numRes)
	Constructor.

virtual	~ResponseSurfaceVector ()
	Destructor.

Additional Inherited Members
Protected Member Functions inherited from sgpp::optimization::ResponseSurfaceVector
double	domainVolume ()
	calculates the volume of the tensor product domain given by lb and ub

void	transformPoint (sgpp::base::DataVector &v, sgpp::base::DataVector lBounds, sgpp::base::DataVector uBounds, sgpp::base::DataVector newlBounds, sgpp::base::DataVector newuBounds)
	transforms a point in hyper-rectangle [lBounds,rBounds] to the hyper-rectangle [newlBounds,newuBounds]

Protected Attributes inherited from sgpp::optimization::ResponseSurfaceVector
std::shared_ptr< sgpp::base::VectorFunctionGradient >	interpolantGradients

std::shared_ptr< sgpp::base::VectorFunction >	interpolants

sgpp::base::DataVector	lb

size_t	numDim

size_t	numRes

sgpp::base::DataVector	ub

Detailed Description

stores a sparse grid not a knot B-spline interpolant in the framework of a respsonse surface for a vector valued objective function (in particular time dependent objective functions, where the return values are the time series)

Constructor & Destructor Documentation

◆ SplineResponseSurfaceVector() [1/2]

sgpp::optimization::SplineResponseSurfaceVector::SplineResponseSurfaceVector	(	std::shared_ptr< sgpp::base::VectorFunction >	objectiveFunc,
		sgpp::base::DataVector	lb,
		sgpp::base::DataVector	ub,
		sgpp::base::GridType	gridType,
		size_t	degree = `3`
	)

inline

Constructor.

Parameters

objectiveFunc	objective Function
lb	lower parameter boundaries
ub	upper parameter boundaries
gridType	type of the interpolants grid/basis
degree	degree of the interpolants basis

References sgpp::base::Bspline, sgpp::base::BsplineBoundary, sgpp::base::BsplineClenshawCurtis, sgpp::base::FundamentalSpline, sgpp::optimization::ResponseSurfaceVector::lb, sgpp::base::ModBspline, sgpp::base::ModFundamentalSpline, sgpp::base::ModNakBspline, sgpp::base::NakBspline, sgpp::base::NakBsplineBoundary, sgpp::base::NakBsplineExtended, sgpp::base::NakPBspline, sgpp::optimization::ResponseSurfaceVector::numDim, sgpp::optimization::ResponseSurfaceVector::numRes, sgpp::base::DataMatrix::resize(), sgpp::base::DataMatrix::setColumn(), and sgpp::optimization::ResponseSurfaceVector::ub.

◆ SplineResponseSurfaceVector() [2/2]

sgpp::optimization::SplineResponseSurfaceVector::SplineResponseSurfaceVector	(	size_t	numDim,
		size_t	numRes,
		sgpp::base::DataVector	lb,
		sgpp::base::DataVector	ub,
		std::string	gridFilename,
		size_t	degree,
		std::string	coeffFileName
	)

inline

Constructor loading an already calculated response surface from serialized grid and coefficients (gridFile must be created by Grid::serialize, coeff file by DataMatrix::ToFile)

Parameters

numDim	input dimensionality
numRes	output dimensionality
lb	lower parameter boundaries
ub	upper parameter boundaries
gridFilename	path to the file with stored grid data
degree	basis degree
coeffFileName	path to the file with stored coefficients

References sgpp::base::BsplineBoundary, sgpp::base::DataMatrix::fromFile(), sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::interpolants, sgpp::optimization::ResponseSurfaceVector::lb, sgpp::base::NakBsplineBoundary, sgpp::optimization::ResponseSurfaceVector::numDim, sgpp::optimization::ResponseSurfaceVector::numRes, sgpp::base::DataMatrix::resize(), sgpp::base::DataMatrix::setColumn(), sgpp::optimization::ResponseSurfaceVector::ub, and sgpp::base::Grid::unserializeFromFile().

◆ ~SplineResponseSurfaceVector()

sgpp::optimization::SplineResponseSurfaceVector::~SplineResponseSurfaceVector ( )

inlineoverride

Destructor.

Member Function Documentation

◆ distributionAdaptive()

void sgpp::optimization::SplineResponseSurfaceVector::distributionAdaptive	(	size_t	maxNumGridPoints,
		size_t	initialLevel,
		sgpp::base::DistributionsVector	pdfs,
		size_t	refinementsNum = `3`,
		bool	verbose = `false`
	)

creates a distribution adaptive sparse grid intepolant

Parameters

maxNumGridPoints	maximum number of grid points of the interpolants grid
initialLevel	first a regular grid of initialLevel is created.
pdfs	the probability density functions 'distributions'
refinementsNum	max number of grid points, added in each refinement step
verbose	print extra info

References sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::interpolants, refineDistributionAdaptive(), and regular().

◆ eval()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::eval ( sgpp::base::DataVector v )

overridevirtual

evaluates this response surface

Parameters

v	point to evaluate in

Returns: the evaluation

Reimplemented from sgpp::optimization::ResponseSurfaceVector.

References sgpp::optimization::ResponseSurfaceVector::interpolants, sgpp::optimization::ResponseSurfaceVector::lb, sgpp::optimization::ResponseSurfaceVector::transformPoint(), and sgpp::optimization::ResponseSurfaceVector::ub.

Referenced by python.uq.analysis.asgc.ASGCAnalysis.ASGCAnalysis::estimateDensity().

◆ evalJacobian()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::evalJacobian	(	sgpp::base::DataVector	v,
		sgpp::base::DataMatrix &	jacobian
	)

overridevirtual

evaluates the response surface and its gradient

Parameters

v	point to evaluate in
jacobian	reference to return the repsonse surfaces jacobian matrix evaluted in v

Returns: the evaluation

Implements sgpp::optimization::ResponseSurfaceVector.

References sgpp::base::DataMatrix::componentwise_div(), sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::lb, sgpp::optimization::ResponseSurfaceVector::transformPoint(), and sgpp::optimization::ResponseSurfaceVector::ub.

◆ full()

void sgpp::optimization::SplineResponseSurfaceVector::full ( size_t level )

creates a regualar full grid interpolant

Parameters

level level of the regular full grid

References sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::interpolants, and level.

◆ getCoefficients()

sgpp::base::DataMatrix sgpp::optimization::SplineResponseSurfaceVector::getCoefficients ( )

inline

Returns: the interpolation coefficients

◆ getDegree()

size_t sgpp::optimization::SplineResponseSurfaceVector::getDegree ( )

inline

Returns: the degree of the B-splines

◆ getGrid()

std::shared_ptr< sgpp::base::Grid > sgpp::optimization::SplineResponseSurfaceVector::getGrid ( )

inline

Returns: the interpolation grid

Referenced by python.uq.analysis.asgc.ASGCKnowledge.ASGCKnowledge::getSparseGridFunction(), python.uq.learner.SimulationLearner.SimulationLearner::learnData(), python.uq.learner.SimulationLearner.SimulationLearner::learnDataWithFolding(), python.uq.learner.SimulationLearner.SimulationLearner::learnDataWithTest(), and python.uq.learner.SimulationLearner.SimulationLearner::refineGrid().

◆ getIntegrals()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::getIntegrals ( )

return the integrals of the response surface

References sgpp::op_factory::createOperationQuadrature(), sgpp::optimization::ResponseSurfaceVector::domainVolume(), sgpp::base::OperationQuadrature::doQuadrature(), sgpp::base::DataMatrix::getColumn(), and sgpp::optimization::ResponseSurfaceVector::numRes.

◆ getLowerBounds()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::getLowerBounds ( )

inline

Returns: the lower bounds of the domain

References sgpp::optimization::ResponseSurfaceVector::lb.

◆ getMeans()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::getMeans	(	sgpp::base::DistributionsVector	pdfs,
		size_t	quadOrder
	)

return the mean of the response surface w.r.t.

a probability density function

Parameters

pdfs	the probability density function
quadOrder	order of the Gauss Legendre quadrature

Returns: vector containing the means

References sgpp::op_factory::createOperationWeightedQuadrature(), sgpp::base::OperationWeightedQuadrature::doWeightedQuadrature(), sgpp::base::DataMatrix::getColumn(), sgpp::optimization::ResponseSurfaceVector::numRes, and sgpp::base::DataVector::resizeZero().

Referenced by getVariances().

◆ getSize()

size_t sgpp::optimization::SplineResponseSurfaceVector::getSize ( )

inline

Returns: the number of grid points

Referenced by python.uq.uq_setting.UQSetting.UQSetting::convert(), python.uq.uq_setting.UQSetting.UQSetting::getTimeDependentResults(), python.uq.uq_setting.UQSetting.UQSetting::runSamples(), and python.uq.uq_setting.UQSetting.UQSetting::runSamples_withoutDistribution().

◆ getUpperBounds()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::getUpperBounds ( )

inline

Returns: the upper bounds of the domain

References sgpp::optimization::ResponseSurfaceVector::ub.

◆ getVariances()

sgpp::base::DataVector sgpp::optimization::SplineResponseSurfaceVector::getVariances	(	sgpp::base::DistributionsVector	pdfs,
		size_t	quadOrder,
		sgpp::base::DataVector &	means,
		sgpp::base::DataVector &	meanSquares
	)

return the variance of the response surface w.r.t.

a probability density function

Parameters

pdfs	the probability density function
quadOrder	order of the Gauss Legendre quadrature
means	reference to return the means used to calculate the variances
meanSquares	reference to return the meanSquares used to calculate the variances

Returns: vector containing the variances

References sgpp::op_factory::createOperationWeightedSecondMoment(), sgpp::base::OperationWeightedSecondMoment::doWeightedQuadrature(), sgpp::base::DataMatrix::getColumn(), getMeans(), sgpp::optimization::ResponseSurfaceVector::numRes, and sgpp::base::DataVector::resizeZero().

◆ nextDistributionAdaptiveGrid()

void sgpp::optimization::SplineResponseSurfaceVector::nextDistributionAdaptiveGrid	(	size_t	refinementsNum,
		sgpp::base::DistributionsVector	pdfs,
		bool	verbose = `false`
	)

refines the grid distribution adaptive but does not recalculate interpolation coefficients

Parameters

refinementsNum	number of grid points which should be refined
pdfs	the probability density functions 'distributions'
verbose	print information on the refine points

Referenced by refineDistributionAdaptive().

◆ nextSurplusAdaptiveGrid()

void sgpp::optimization::SplineResponseSurfaceVector::nextSurplusAdaptiveGrid	(	size_t	refinementsNum,
		bool	verbose = `false`
	)

refines the grid surplus adaptive but does not recalculate interpolation coefficients

Parameters

refinementsNum	number of grid points which should be refined
verbose	print information on the refine points

Referenced by refineSurplusAdaptive().

◆ refineDistributionAdaptive()

void sgpp::optimization::SplineResponseSurfaceVector::refineDistributionAdaptive	(	size_t	refinementsNum,
		sgpp::base::DistributionsVector	pdfs,
		bool	verbose = `false`
	)

refines the grid distribution adaptive and recalculates the interpoaltion coefficients

Parameters

refinementsNum	number of grid points which should be refined
pdfs	the probability density functions 'distributions'
verbose	print information on the refine points

References nextDistributionAdaptiveGrid().

Referenced by distributionAdaptive().

◆ refineSurplusAdaptive()

void sgpp::optimization::SplineResponseSurfaceVector::refineSurplusAdaptive	(	size_t	refinementsNum,
		bool	verbose = `false`
	)

refines the grid surplus adaptive and recalculates the interpoaltion coefficients

Parameters

refinementsNum	number of grid points which should be refined
verbose	print information on the refine points

References nextSurplusAdaptiveGrid().

Referenced by surplusAdaptive().

◆ regular()

void sgpp::optimization::SplineResponseSurfaceVector::regular ( size_t level )

creates a regualar sparse grid interpolant

Parameters

level level of the regular sparse grid

References sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::interpolants, and level.

Referenced by distributionAdaptive(), and surplusAdaptive().

◆ regularByPoints()

void sgpp::optimization::SplineResponseSurfaceVector::regularByPoints	(	size_t	numPoints,
		bool	verbose = `false`
	)

creates a regular grid of the lowest level with more grid points than specified

Parameters

numPoints	desired number of grid points
verbose	print extra info

References sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::interpolants, and level.

◆ serializeGrid()

std::string sgpp::optimization::SplineResponseSurfaceVector::serializeGrid ( )

calculates the minimimum with gradient descent

Returns: argmin of the response surface Serialize the grid for storing and later usage; string of the serialized grid

◆ surplusAdaptive()

void sgpp::optimization::SplineResponseSurfaceVector::surplusAdaptive	(	size_t	maxNumGridPoints,
		size_t	initialLevel,
		size_t	refinementsNum = `3`,
		bool	verbose = `false`
	)

creates a surplus adaptive sparse grid interpolant

Parameters

maxNumGridPoints	maximum number of grid points of the interpolants grid
initialLevel	first a regular grid of initialLevel is created.
refinementsNum	max number of grid points, added in each refinement step
verbose	print extra info

References sgpp::optimization::ResponseSurfaceVector::interpolantGradients, sgpp::optimization::ResponseSurfaceVector::interpolants, refineSurplusAdaptive(), and regular().

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

optimization/src/sgpp/optimization/function/vector/SplineResponseSurfaceVector.hpp
optimization/src/sgpp/optimization/function/vector/SplineResponseSurfaceVector.cpp

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ SplineResponseSurfaceVector() [1/2]

◆ SplineResponseSurfaceVector() [2/2]

◆ ~SplineResponseSurfaceVector()

Member Function Documentation

◆ distributionAdaptive()

◆ eval()

◆ evalJacobian()

◆ full()

◆ getCoefficients()

◆ getDegree()

◆ getGrid()

◆ getIntegrals()

◆ getLowerBounds()

◆ getMeans()

◆ getSize()

◆ getUpperBounds()

◆ getVariances()

◆ nextDistributionAdaptiveGrid()

◆ nextSurplusAdaptiveGrid()

◆ refineDistributionAdaptive()

◆ refineSurplusAdaptive()

◆ regular()

◆ regularByPoints()

◆ serializeGrid()

◆ surplusAdaptive()