English Français

Documentation / Developer's manual

Available modules

Calibration,  DataServer,  Launcher,  MetaModelOptim,  Modeler,  Optimizer,  ReLauncher,  Reliability,  ReOptimizer,  Sampler,  Sensitivity,  UncertModeler,  XmlProblem,   Uranie / Modeler: URANIE::Modeler::TGPCostFunction Class Reference
Uranie / Modeler v4.9.0
/* @license-end */
URANIE::Modeler::TGPCostFunction Class Referenceabstract

Description of the class TGPCostFunction. More...

#include <TGPCostFunction.h>

Inheritance diagram for URANIE::Modeler::TGPCostFunction:
Collaboration diagram for URANIE::Modeler::TGPCostFunction:

Public Member Functions

Constructor and Destructor
 TGPCostFunction (TGPBuilder *gpb)
 Standard constructor.
 
virtual ~TGPCostFunction ()
 Default destructor.
 
Get and Set methods
TGPBuildergetBuilder ()
 Return a pointer to the GP Builder.
 
Double_t * getCovarianceMatrix ()
 Return a pointer to the GP Builder covariance matrix.
 
Double_t * getCorrelationMatrix ()
 Return a pointer to the GP Builder correlation matrix.
 
Double_t * getObservationVector ()
 Return a pointer to the observations outputs.
 
Int_t getNObs ()
 Return the number of observations.
 
void setBuilder (TGPBuilder *gpb)
 
Estimate
virtual Int_t eval (Double_t *theta, Double_t *res, int=0)=0
 Evaluate the cost function (implemented in the children classes)
 
Printing Log
void setLog ()
 
void unsetLog ()
 
void changeLog ()
 
Bool_t getLog ()
 
virtual void printLog (Option_t *option="")
 

Public Attributes

Bool_t _blog
 Boolean to decide if the log information is shown or not.
 
TGPBuildergpBuilder
 pointer to a gaussian process builder object.
 

Protected Attributes

Double_t * _H
 pointer to the deterministic trend matrix (size: _n * _p)
 
Double_t * _K
 pointer to the covariance matrix (size: _n * _n)
 
Double_t * _C
 pointer to the correlation matrix (size: _n * _n)
 
Double_t * _yObs
 pointer to the vector of observations outputs (size: _n)
 
Int_t _n
 number of observations
 
Int_t _p
 number of deterministic trend coefficients
 

Detailed Description

Description of the class TGPCostFunction.

This class defines a cost function used to select the optimal hyper-parameters of a Gaussian Process (correlation lengths, variance, etc.). Its children are wrappers to the various cost functions provided by the "gaussian process Library" (gpLib), by Jean-Marc Martinez.

Constructor & Destructor Documentation

◆ TGPCostFunction()

URANIE::Modeler::TGPCostFunction::TGPCostFunction ( TGPBuilder gpb)

Standard constructor.

A TGPCostFunction object need to be associated with a TGPBuilder object which will provide the covariance matrix and the observations.

Parameters
gpb(TGPBuilder*): pointer to a Gaussian Process Builder object.

Referenced by ClassImp().

◆ ~TGPCostFunction()

virtual URANIE::Modeler::TGPCostFunction::~TGPCostFunction ( )
virtual

Default destructor.

Referenced by ClassImp().

Member Function Documentation

◆ changeLog()

void URANIE::Modeler::TGPCostFunction::changeLog ( )
inline

References _blog.

◆ eval()

virtual Int_t URANIE::Modeler::TGPCostFunction::eval ( Double_t *  theta,
Double_t *  res,
int  = 0 
)
pure virtual

Evaluate the cost function (implemented in the children classes)

Implemented in URANIE::Modeler::TGPLooCostFunction, URANIE::Modeler::TGPMLCostFunction, and URANIE::Modeler::TGPReMLCostFunction.

◆ getBuilder()

TGPBuilder * URANIE::Modeler::TGPCostFunction::getBuilder ( )
inline

Return a pointer to the GP Builder.

References gpBuilder.

◆ getCorrelationMatrix()

Double_t * URANIE::Modeler::TGPCostFunction::getCorrelationMatrix ( )
inline

Return a pointer to the GP Builder correlation matrix.

References _C.

◆ getCovarianceMatrix()

Double_t * URANIE::Modeler::TGPCostFunction::getCovarianceMatrix ( )
inline

Return a pointer to the GP Builder covariance matrix.

References _K.

◆ getLog()

Bool_t URANIE::Modeler::TGPCostFunction::getLog ( )
inline

References _blog.

◆ getNObs()

Int_t URANIE::Modeler::TGPCostFunction::getNObs ( )
inline

Return the number of observations.

References _n.

◆ getObservationVector()

Double_t * URANIE::Modeler::TGPCostFunction::getObservationVector ( )
inline

Return a pointer to the observations outputs.

References _yObs.

◆ printLog()

virtual void URANIE::Modeler::TGPCostFunction::printLog ( Option_t *  option = "")
virtual

Referenced by ClassImp().

◆ setBuilder()

void URANIE::Modeler::TGPCostFunction::setBuilder ( TGPBuilder gpb)
inline

References gpBuilder.

◆ setLog()

void URANIE::Modeler::TGPCostFunction::setLog ( )
inline

References _blog.

◆ unsetLog()

void URANIE::Modeler::TGPCostFunction::unsetLog ( )
inline

References _blog.

Member Data Documentation

◆ _blog

Bool_t URANIE::Modeler::TGPCostFunction::_blog

Boolean to decide if the log information is shown or not.

Referenced by changeLog(), ClassImp(), ClassImp(), ClassImp(), ClassImp(), getLog(), setLog(), and unsetLog().

◆ _C

Double_t* URANIE::Modeler::TGPCostFunction::_C
protected

pointer to the correlation matrix (size: _n * _n)

Referenced by ClassImp(), and getCorrelationMatrix().

◆ _H

Double_t* URANIE::Modeler::TGPCostFunction::_H
protected

pointer to the deterministic trend matrix (size: _n * _p)

Referenced by ClassImp(), ClassImp(), and ClassImp().

◆ _K

Double_t* URANIE::Modeler::TGPCostFunction::_K
protected

pointer to the covariance matrix (size: _n * _n)

Referenced by ClassImp(), ClassImp(), ClassImp(), ClassImp(), and getCovarianceMatrix().

◆ _n

Int_t URANIE::Modeler::TGPCostFunction::_n
protected

number of observations

Referenced by ClassImp(), ClassImp(), ClassImp(), and getNObs().

◆ _p

Int_t URANIE::Modeler::TGPCostFunction::_p
protected

number of deterministic trend coefficients

Referenced by ClassImp(), ClassImp(), and ClassImp().

◆ _yObs

Double_t* URANIE::Modeler::TGPCostFunction::_yObs
protected

pointer to the vector of observations outputs (size: _n)

Referenced by ClassImp(), ClassImp(), ClassImp(), and getObservationVector().

◆ gpBuilder

TGPBuilder* URANIE::Modeler::TGPCostFunction::gpBuilder

pointer to a gaussian process builder object.

Referenced by ClassImp(), ClassImp(), ClassImp(), ClassImp(), getBuilder(), and setBuilder().