SG++-Doxygen-Documentation
|
#include <RosenblattTransformation.hpp>
Public Member Functions | |
LearnerSGDE | createSGDELearner (size_t dim, RosenblattTransformationConfig config) |
Helper function It configures and creates a SGDE learner with meaningful parameters. More... | |
Dataset * | doInverseTransformation (Dataset *dataset) override |
Wrapper for Rosenblatt inverse transformation. More... | |
Dataset * | doTransformation (Dataset *dataset) override |
Wrapper for Rosenblatt transformation. More... | |
void | initialize (Dataset *dataset, DataTransformationConfig config) override |
Initializes a transformation by approximating probability density function (PDF), calculates grid and alpha for numSamples samples of a dataset. More... | |
RosenblattTransformation () | |
Default constructor. More... | |
Public Member Functions inherited from sgpp::datadriven::DataTransformation | |
DataTransformation ()=default | |
Default constructor. More... | |
virtual | ~DataTransformation ()=default |
Virtual destructor. More... | |
sgpp::datadriven::RosenblattTransformation::RosenblattTransformation | ( | ) |
Default constructor.
sgpp::datadriven::LearnerSGDE sgpp::datadriven::RosenblattTransformation::createSGDELearner | ( | size_t | dim, |
RosenblattTransformationConfig | config | ||
) |
Helper function It configures and creates a SGDE learner with meaningful parameters.
References adaptConfig, sgpp::solver::CG, chess::dim, sgpp::base::GeneralGridConfiguration::dim_, sgpp::datadriven::CrossvalidationConfiguration::enable_, sgpp::solver::SLESolverConfiguration::eps_, sgpp::datadriven::RosenblattTransformationConfig::gridLevel, sgpp::datadriven::Laplace, sgpp::base::GeneralGridConfiguration::level_, sgpp::base::Linear, sgpp::solver::SLESolverConfiguration::maxIterations_, sgpp::base::AdaptivityConfiguration::numRefinements_, sgpp::datadriven::RosenblattTransformationConfig::solverEps, sgpp::datadriven::RosenblattTransformationConfig::solverMaxIterations, sgpp::datadriven::RosenblattTransformationConfig::solverThreshold, sgpp::solver::SLESolverConfiguration::threshold_, sgpp::datadriven::RegularizationConfiguration::type_, sgpp::solver::SLESolverConfiguration::type_, and sgpp::base::GeneralGridConfiguration::type_.
Referenced by initialize().
|
overridevirtual |
Wrapper for Rosenblatt inverse transformation.
Can be called from an initialized DataTransformation (with DataTransformationType::ROSENBLATT)
dataset | pointer to the dataset to be Rosenblatt inverse transformed |
Implements sgpp::datadriven::DataTransformation.
References sgpp::op_factory::createOperationInverseRosenblattTransformation(), sgpp::datadriven::OperationInverseRosenblattTransformation::doTransformation(), sgpp::datadriven::Dataset::getData(), sgpp::datadriven::Dataset::getDimension(), and sgpp::datadriven::Dataset::getNumberInstances().
|
overridevirtual |
Wrapper for Rosenblatt transformation.
Can be called from an initialized DataTransformation (with DataTransformationType::ROSENBLATT)
dataset | pointer to the dataset to be Rosenblatt transformed |
Implements sgpp::datadriven::DataTransformation.
References sgpp::op_factory::createOperationRosenblattTransformation(), sgpp::datadriven::OperationRosenblattTransformation::doTransformation(), sgpp::datadriven::Dataset::getData(), sgpp::datadriven::Dataset::getDimension(), and sgpp::datadriven::Dataset::getNumberInstances().
|
overridevirtual |
Initializes a transformation by approximating probability density function (PDF), calculates grid and alpha for numSamples samples of a dataset.
dataset | pointer to the dataset to be initialized |
config | configuration containing parameters for initalization |
Implements sgpp::datadriven::DataTransformation.
References createSGDELearner(), chess::dim, sgpp::datadriven::Dataset::getData(), sgpp::datadriven::Dataset::getDimension(), sgpp::datadriven::Dataset::getNumberInstances(), sgpp::base::DataMatrix::getRow(), sgpp::datadriven::LearnerSGDE::getSharedGrid(), sgpp::datadriven::LearnerSGDE::getSharedSurpluses(), python.statsfileInfo::i, sgpp::datadriven::LearnerSGDE::initialize(), sgpp::datadriven::RosenblattTransformationConfig::numSamples, sgpp::datadriven::DataTransformationConfig::rosenblattConfig, parabolasimple::samples, and sgpp::datadriven::LearnerSGDE::train().