Abstract super class to encapsulate density estimation models such as using offline/-online splitting or conjugate gradients in order to solve the system. More...

#include <ModelFittingDensityEstimation.hpp>

Inheritance diagram for sgpp::datadriven::ModelFittingDensityEstimation:

Public Member Functions
bool	adapt () override
	Improve accuracy of the fit on the given training data by adaptive refinement or coarsening of the grid and recalculate weights.

virtual bool	adapt (size_t newNoPoints, std::vector< size_t > &deletedGridPoints)=0
	Performs refinement and coarsening given the new grid size and the points to coarsened.

double	computeResidual (DataMatrix &validationData) const override=0
	Computes a residual to evaluate the fit of the model.

double	evaluate (const DataVector &sample) override=0
	Evaluate the fitted model at a single data point.

void	evaluate (DataMatrix &samples, DataVector &results) override=0
	Evaluate the fitted model on a set of data points.

virtual void	fit (DataMatrix &dataset)=0
	Fit the grid to the given dataset by determining the surpluses of the initial grid by the SGDE approach.

virtual void	fit (DataMatrix &datasetP, DataMatrix &datasetQ)=0

void	fit (Dataset &dataset) override=0
	Fit the grid to the dataset by determining the weights of an initial grid.

void	fit (Dataset &datasetP, Dataset &datasetQ) override=0

	ModelFittingDensityEstimation ()
	Default constructor.

void	resetTraining () override=0
	Resets any trained representations of the model, but does not reset the entire state.

virtual void	update (DataMatrix &samples)=0
	Updates the model based on new data samples (streaming, batch learning).

virtual void	update (DataMatrix &samplesP, DataMatrix &samplesQ)=0

void	update (Dataset &dataset) override=0
	Train the grid of an existing model with new samples.

void	update (Dataset &datasetP, Dataset &datasetQ) override=0

void	updateRegularization (double lambda) override=0
	Updates the regularization parameter lambda of the underlying model.

Public Member Functions inherited from sgpp::datadriven::ModelFittingBaseSingleGrid
Grid &	getGrid ()
	Get the underlying grid object for the current model.

DataVector &	getSurpluses ()
	Get the surpluses of the current grid.

	ModelFittingBaseSingleGrid ()
	Default constructor.

	ModelFittingBaseSingleGrid (const ModelFittingBaseSingleGrid &rhs)=delete
	Copy constructor - we cannot deep copy all member variables yet.

	ModelFittingBaseSingleGrid (ModelFittingBaseSingleGrid &&rhs)=default
	Move constructor.

ModelFittingBaseSingleGrid &	operator= (const ModelFittingBaseSingleGrid &rhs)=delete
	Copy assign operator - we cannot deep copy all member variables yet.

ModelFittingBaseSingleGrid &	operator= (ModelFittingBaseSingleGrid &&rhs)=default
	Move assign operator.

std::string	storeFitter ()

virtual	~ModelFittingBaseSingleGrid ()=default
	virtual destructor.

Public Member Functions inherited from sgpp::datadriven::ModelFittingBase
Dataset *	getDataset ()

FitterConfiguration &	getFitterConfiguration ()
	Get or set the configuration of the fitter object.

const FitterConfiguration &	getFitterConfiguration () const
	Get the configuration of the fitter object.

virtual std::shared_ptr< BlacsProcessGrid >	getProcessGrid () const

	ModelFittingBase ()
	Default constructor.

	ModelFittingBase (const ModelFittingBase &rhs)=delete
	Copy constructor - we cannot deep copy all member variables yet.

	ModelFittingBase (ModelFittingBase &&rhs)=default
	Move constructor.

ModelFittingBase &	operator= (const ModelFittingBase &rhs)=delete
	Copy assign operator - we cannot deep copy all member variables yet.

ModelFittingBase &	operator= (ModelFittingBase &&rhs)=default
	Move assign operator.

virtual void	reset ()=0
	Resets the state of the entire model.

virtual	~ModelFittingBase ()=default
	virtual destructor.

Protected Member Functions
std::unique_ptr< sgpp::base::CoarseningFunctor >	getCoarseningFunctor ()
	Returns the refinement functor suitable for the model settings.

std::unique_ptr< sgpp::base::RefinementFunctor >	getRefinementFunctor ()
	Returns the refinement functor suitable for the model settings.

virtual bool	isRefinable ()=0
	Function that indicates whether a model is refinable at all (certain on/off settings do not allow for refinement)

Protected Member Functions inherited from sgpp::datadriven::ModelFittingBase
Grid *	buildGrid (const sgpp::base::GeneralGridConfiguration &gridConfig) const
	Factory member function that generates a grid from configuration.

Grid *	buildGrid (const sgpp::base::GeneralGridConfiguration &gridConfig, const GeometryConfiguration &geometryConfig) const
	Factory member function that generates a grid from configuration.

SLESolver *	buildSolver (const SLESolverConfiguration &config) const
	Factory member function to build the solver for the least squares regression problem according to the config.

std::set< std::set< size_t > >	getInteractions (const GeometryConfiguration &geometryConfig)

void	reconfigureSolver (SLESolver &solver, const SLESolverConfiguration &config) const
	Configure solver based on the desired configuration.

Protected Attributes
size_t	initialGridSize
	Initial number of grid points.

size_t	refinementsPerformed
	Count the amount of refinement operations performed on the current dataset.

Protected Attributes inherited from sgpp::datadriven::ModelFittingBaseSingleGrid
DataVector	alpha
	hierarchical surpluses of the grid.

std::unique_ptr< Grid >	grid
	the sparse grid that approximates the data.

Protected Attributes inherited from sgpp::datadriven::ModelFittingBase
std::unique_ptr< FitterConfiguration >	config
	Configuration object for the fitter.

Dataset *	dataset
	Pointer to sgpp::datadriven::Dataset.

Dataset *	extraDataset

std::unique_ptr< std::set< std::set< size_t > > >	interactions

std::unique_ptr< SLESolver >	solver
	Solver for the learning problem.

Additional Inherited Members
Public Attributes inherited from sgpp::datadriven::ModelFittingBase
bool	verboseSolver
	Whether the Solver produces output or not.

Detailed Description

Abstract super class to encapsulate density estimation models such as using offline/-online splitting or conjugate gradients in order to solve the system.

Constructor & Destructor Documentation

◆ ModelFittingDensityEstimation()

sgpp::datadriven::ModelFittingDensityEstimation::ModelFittingDensityEstimation ( )

Default constructor.

Member Function Documentation

◆ adapt() [1/2]

bool sgpp::datadriven::ModelFittingDensityEstimation::adapt ( )

overridevirtual

Improve accuracy of the fit on the given training data by adaptive refinement or coarsening of the grid and recalculate weights.

Returns: true if refinement or coarsening could be performed based on the refinement configuration, else false.

Implements sgpp::datadriven::ModelFittingBase.

Reimplemented in sgpp::datadriven::ModelFittingDensityEstimationCombi.

References adapt(), sgpp::datadriven::ModelFittingBase::config, getCoarseningFunctor(), sgpp::datadriven::GridFactory::getInteractions(), getRefinementFunctor(), sgpp::datadriven::ModelFittingBaseSingleGrid::grid, initialGridSize, isRefinable(), refinementsPerformed, and sgpp::datadriven::GeometryConfiguration::stencils_.

Referenced by adapt().

◆ adapt() [2/2]

virtual bool sgpp::datadriven::ModelFittingDensityEstimation::adapt	(	size_t	newNoPoints,
		std::vector< size_t > &	deletedGridPoints
	)

pure virtual

Performs refinement and coarsening given the new grid size and the points to coarsened.

Parameters

newNoPoints	the grid size after refinement and coarsening
deletedGridPoints	a list of indexes for grid points that will be removed

Returns: if the grid was refined (true)

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

◆ computeResidual()

double sgpp::datadriven::ModelFittingDensityEstimation::computeResidual ( DataMatrix & validationData ) const

overridepure virtual

Computes a residual to evaluate the fit of the model.

This is useful for density estimation, because other Scores cannot be used as there are no targets.

Parameters

validationData Matrix for validation data

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

◆ evaluate() [1/2]

double sgpp::datadriven::ModelFittingDensityEstimation::evaluate ( const DataVector & sample )

overridepure virtual

Evaluate the fitted model at a single data point.

Parameters

sample vector with the coordinates in all dimensions of that sample.

Returns: evaluation of the model.

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

◆ evaluate() [2/2]

void sgpp::datadriven::ModelFittingDensityEstimation::evaluate	(	DataMatrix &	samples,
		DataVector &	results
	)

overridepure virtual

Evaluate the fitted model on a set of data points.

Parameters

samples	matrix where each row represents a sample and the columns contain the coordinates in all dimensions of that sample.
results	vector where each row will contain the evaluation of the respective sample on the current model.

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

◆ fit() [1/4]

virtual void sgpp::datadriven::ModelFittingDensityEstimation::fit ( DataMatrix & dataset )

pure virtual

Fit the grid to the given dataset by determining the surpluses of the initial grid by the SGDE approach.

Requires only data samples and no targets (since those are irrelevant for the density estimation whatsoever)

Parameters

dataset the training dataset that is used to fit the model.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel, and sgpp::datadriven::ModelFittingDensityEstimationCombi.

◆ fit() [2/4]

virtual void sgpp::datadriven::ModelFittingDensityEstimation::fit	(	DataMatrix &	datasetP,
		DataMatrix &	datasetQ
	)

pure virtual

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel, and sgpp::datadriven::ModelFittingDensityEstimationCombi.

◆ fit() [3/4]

void sgpp::datadriven::ModelFittingDensityEstimation::fit ( Dataset & dataset )

overridepure virtual

Fit the grid to the dataset by determining the weights of an initial grid.

Parameters

dataset the training dataset that is used to fit the model.

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel, and sgpp::datadriven::ModelFittingDensityEstimationCombi.

◆ fit() [4/4]

void sgpp::datadriven::ModelFittingDensityEstimation::fit	(	Dataset &	datasetP,
		Dataset &	datasetQ
	)

overridepure virtual

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel, and sgpp::datadriven::ModelFittingDensityEstimationCombi.

◆ getCoarseningFunctor()

std::unique_ptr< CoarseningFunctor > sgpp::datadriven::ModelFittingDensityEstimation::getCoarseningFunctor ( )

protected

Returns the refinement functor suitable for the model settings.

Returns: pointer to a coarsening functor that suits the model settings

References adaptivityConfig, sgpp::datadriven::ModelFittingBaseSingleGrid::alpha, sgpp::base::AdaptivityConfiguration::coarseningFunctorType_, and sgpp::datadriven::ModelFittingBase::config.

Referenced by adapt().

◆ getRefinementFunctor()

std::unique_ptr< RefinementFunctor > sgpp::datadriven::ModelFittingDensityEstimation::getRefinementFunctor ( )

protected

Returns the refinement functor suitable for the model settings.

Returns: pointer to a refinement functor that suits the model settings

References sgpp::datadriven::ModelFittingBaseSingleGrid::alpha, sgpp::datadriven::ModelFittingBase::config, and sgpp::base::AdaptivityConfiguration::refinementFunctorType_.

Referenced by adapt().

◆ isRefinable()

virtual bool sgpp::datadriven::ModelFittingDensityEstimation::isRefinable ( )

protectedpure virtual

Function that indicates whether a model is refinable at all (certain on/off settings do not allow for refinement)

Returns: whether the model is refinable

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

Referenced by adapt().

◆ resetTraining()

void sgpp::datadriven::ModelFittingDensityEstimation::resetTraining ( )

overridepure virtual

Resets any trained representations of the model, but does not reset the entire state.

The decomposition from the offline phase is kept so that it can be reused.

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

◆ update() [1/4]

virtual void sgpp::datadriven::ModelFittingDensityEstimation::update ( DataMatrix & samples )

pure virtual

Updates the model based on new data samples (streaming, batch learning).

Requires only the data samples and no targets (since those are irrelevant for the density estimation whatsoever)

Parameters

samples the new data samples

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

Referenced by python.uq.refinement.RefinementStrategy.Ranking::rank(), and python.learner.LearnedKnowledge.LearnedKnowledge::setMemento().

◆ update() [2/4]

virtual void sgpp::datadriven::ModelFittingDensityEstimation::update	(	DataMatrix &	samplesP,
		DataMatrix &	samplesQ
	)

pure virtual

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

Referenced by python.uq.refinement.RefinementStrategy.Ranking::rank(), and python.learner.LearnedKnowledge.LearnedKnowledge::setMemento().

◆ update() [3/4]

void sgpp::datadriven::ModelFittingDensityEstimation::update ( Dataset & dataset )

overridepure virtual

Train the grid of an existing model with new samples.

Parameters

dataset the training dataset that is used to fit the model.

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

Referenced by python.uq.refinement.RefinementStrategy.Ranking::rank(), and python.learner.LearnedKnowledge.LearnedKnowledge::setMemento().

◆ update() [4/4]

void sgpp::datadriven::ModelFittingDensityEstimation::update	(	Dataset &	datasetP,
		Dataset &	datasetQ
	)

overridepure virtual

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

Referenced by python.uq.refinement.RefinementStrategy.Ranking::rank(), and python.learner.LearnedKnowledge.LearnedKnowledge::setMemento().

◆ updateRegularization()

void sgpp::datadriven::ModelFittingDensityEstimation::updateRegularization ( double lambda )

overridepure virtual

Updates the regularization parameter lambda of the underlying model.

Parameters

lambda the new lambda parameter

Implements sgpp::datadriven::ModelFittingBase.

Implemented in sgpp::datadriven::ModelFittingDensityDifferenceEstimationCG, sgpp::datadriven::ModelFittingDensityDifferenceEstimationOnOff, sgpp::datadriven::ModelFittingDensityEstimationCG, sgpp::datadriven::ModelFittingDensityEstimationCombi, sgpp::datadriven::ModelFittingDensityEstimationOnOff, and sgpp::datadriven::ModelFittingDensityEstimationOnOffParallel.

Member Data Documentation

◆ initialGridSize

size_t sgpp::datadriven::ModelFittingDensityEstimation::initialGridSize

protected

Initial number of grid points.

Referenced by adapt().

◆ refinementsPerformed

size_t sgpp::datadriven::ModelFittingDensityEstimation::refinementsPerformed

protected

Count the amount of refinement operations performed on the current dataset.

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

datadriven/src/sgpp/datadriven/datamining/modules/fitting/ModelFittingDensityEstimation.hpp
datadriven/src/sgpp/datadriven/datamining/modules/fitting/ModelFittingDensityEstimation.cpp

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ ModelFittingDensityEstimation()

Member Function Documentation

◆ adapt() [1/2]

◆ adapt() [2/2]

◆ computeResidual()

◆ evaluate() [1/2]

◆ evaluate() [2/2]

◆ fit() [1/4]

◆ fit() [2/4]

◆ fit() [3/4]

◆ fit() [4/4]

◆ getCoarseningFunctor()

◆ getRefinementFunctor()

◆ isRefinable()

◆ resetTraining()

◆ update() [1/4]

◆ update() [2/4]

◆ update() [3/4]

◆ update() [4/4]

◆ updateRegularization()

Member Data Documentation

◆ initialGridSize

◆ refinementsPerformed