Description of the class TKernel. More...

#include <TKernel.h>

Inheritance diagram for URANIE::Modeler::TKernel:

Collaboration diagram for URANIE::Modeler::TKernel:

Public Types
enum	EKernelType { kUnknown, kLinear, kPoly, kSigmoid, kRBF, kLaplace, kSpline1, kBernoulli1 }

Public Member Functions
Constructor and Destructor
	TKernel (URANIE::DataServer::TDataServer tds, TString architecture, Option_t option="")
	constructor with the TDataServer and the architecture More...

	TKernel (URANIE::DataServer::TDataServer tds, const char varexpinput, const char varexpoutput, Option_t option="")
	Default constructor with input and output attributes. More...

virtual	~TKernel ()
	Default destructor. More...

Get and Set methods
void	setKernel (EKernelType nKernel)
	Set the type of kernel without parameter. More...

void	setKernel (EKernelType nKernel, Double_t dparam1)

void	setKernel (EKernelType nKernel, Double_t dparam1, Double_t dparam2)
	Set the type of kernel with two parameters. More...

void	setKernel (EKernelType nKernel, Double_t dparam1, Double_t dparam2, Double_t dparam3)
	Set the type of kernel with three parameters. More...

EKernelType	getKernel ()
	Return the type of Y distribution. More...

Double_t	getParameter1 ()
	Return First Parameter. More...

Double_t	getParameter2 ()
	Return Second Parameter. More...

void	setLambda (Double_t dlambda)
	Set the Lambda parameter. More...

Double_t	getLambda ()
	Get the Lambda. More...

TMatrixDSym	getMatrixK ()
	Get the matrix _matK. More...

Estimate
void	estimate (Option_t *option="")
	estimate More...

void	fillData ()
	Fill the matrix of Inputs attributes and the vector of output attribute (nY=1) More...

void	computeK (Option_t *option="")
	compute the matrix K More...

Export the model in extrenal langage
void	exportModelCplusplus (std::ofstream *sourcefile) const
	Export the model in C++ langage in a file. More...

void	exportModelFortran (std::ofstream *sourcefile) const
	Export the model in Fortran langage in a file. More...

void	exportModelPMML (const char file="", const char name="", Option_t *option="") const
	Export the model in a PMML file (not yet implemented) More...

void	exportModelPython (std::ofstream *sourcefile) const
	Export the model in Python langage in a file (not yet implemented) More...

Printing Log
void	printLog (Option_t *option="")

Public Member Functions inherited from URANIE::Modeler::TModeler
	TModeler (URANIE::DataServer::TDataServer tds, TString architecture, Option_t option="")
	Constructor with a dataserver. More...

	TModeler (URANIE::DataServer::TDataServer tds, const char varexpinput, const char varexpoutput, Option_t option="")
	Default constructor with input and output attributes. More...

virtual	~TModeler ()
	Default destructor. More...

TVectorD	getParameters ()
	Return the parameter vector of the model. More...

Double_t	getR2 () const
	Return the R2 quality. More...

const char *	getInputName (Int_t i) const
	Return the name of input attributes. More...

const char *	getOutputName (Int_t i=0)
	Return the name of output attribute. More...

Int_t	getNInput ()
	Gets the number of input. More...

Bool_t	getIntercept ()
	Gets the boolean attribut _bIntercept. More...

void	setDrawProgressBar (Bool_t bbool=kTRUE)
	Set the "draw progress bar" flag. More...

Bool_t	getDrawProgressBar ()
	Get the "draw progress bar" flag. More...

void	train (Option_t *option="text")

virtual void	exportFunction (const char lang, const char file="", const char name="", Option_t option="")
	Export the model in an external file with a specified langage. More...

void	setLog ()

void	unsetLog ()

void	changeLog ()

Bool_t	getLog ()

Private Attributes
Private and Public attributes
EKernelType	_nKernelType
	The type of Kernel. More...

Double_t	_dParameter1
	The First Parameter (gamma) [1.0]. More...

Double_t	_dParameter2
	The Second Parameter (coeff) [0.0]. More...

Double_t	_dParameter3
	The Third Parameter (degree) [1.0]. More...

Int_t	_nParameter
	The number of parameter. More...

TMatrixD	_matX
	The matrix of inputs attributes. More...

TVectorD	_vecY
	The vector of Y (outputs) More...

TMatrixDSym	_matK
	The matrix of K (inputs) More...

Double_t	_dLambda
	The lambda parameter (default 1.e-6) More...

Additional Inherited Members
Public Attributes inherited from URANIE::Modeler::TModeler
Bool_t	_blog
	Boolean for edit the log. More...

Bool_t	_bdrawProgressBar
	Boolean to know if the progress bar has to be drawn. More...

Bool_t	_bStoreYHat
	Boolean to specify if we add the {} attribute in the TDS [default kTRUE]. More...

URANIE::DataServer::TDataServer *	_tds

Int_t	_nS
	Pointer to a TDS. More...

TString	_sInputAttributes
	The string of input attributes (separated by the character ":". More...

TString	_sOutputAttributes
	The string of output attributes (separated by the character ":". More...

TString	_sIntermediateArchitecture
	The intermediate (between the first and last character ",") information. More...

TList *	_listOfInputAttributes
	The list of input Leaf. More...

TList *	_listOfOutputAttributes
	The list of output Leaf. More...

Int_t	_nX
	The number of input attributes. More...

Int_t	_nY
	The number of output attributes. More...

TString	_sFileName
	The name of the file when export the model without extension. More...

TString	_sFunctionName
	The name of the function when export the model. More...

TVectorD	_parameterValues
	The list of parameters. More...

Double_t	_dr2
	The R2 quality. More...

Bool_t	_bIntercept
	For certain models, add the intercept (Default is TRUE) More...

Detailed Description

Description of the class TKernel.

Member Enumeration Documentation

◆ EKernelType

enum URANIE::Modeler::TKernel::EKernelType

Enumerator
kUnknown
kLinear
kPoly
kSigmoid
kRBF
kLaplace
kSpline1
kBernoulli1

Constructor & Destructor Documentation

◆ TKernel() [1/2]

URANIE::Modeler::TKernel::TKernel	(	URANIE::DataServer::TDataServer *	tds,
		TString	architecture,
		Option_t *	option = `""`
	)

constructor with the TDataServer and the architecture

Parameters

tds	(URANIE::DataServer::TDataServer *) the dataserver
architecture	(TString) The architecture (input and output attributes) of the model separated by the caracter ":"
option	(Option_t *)[""] The option to pass

Referenced by ClassImp().

◆ TKernel() [2/2]

URANIE::Modeler::TKernel::TKernel	(	URANIE::DataServer::TDataServer *	tds,
		const char *	varexpinput,
		const char *	varexpoutput,
		Option_t *	option = `""`
	)

Default constructor with input and output attributes.

Parameters

tds	(URANIE::DataServer::TDataServer *) the dataserver
varexpinput(const	char*)[""] The list of input attributes to pass to the function separated by the caracter ":"
varexpoutput	(const char *)[""] The list of output attributes separated by the caracter ":"
option	(Option_t *)[""] The option to pass

◆ ~TKernel()

virtual URANIE::Modeler::TKernel::~TKernel ( )

virtual

Default destructor.

Referenced by ClassImp().

Member Function Documentation

◆ computeK()

void URANIE::Modeler::TKernel::computeK ( Option_t * option = "" )

compute the matrix K

Parameters

option

Referenced by ClassImp().

◆ estimate()

void URANIE::Modeler::TKernel::estimate ( Option_t * option = "" )

estimate

Parameters

option

Referenced by ClassImp().

◆ exportModelCplusplus()

void URANIE::Modeler::TKernel::exportModelCplusplus ( std::ofstream * sourcefile ) const

virtual

Export the model in C++ langage in a file.

Warning: Don't use this method. Use the main method TModeler::exportFunction.

Parameters

sourcefile (std::ofstream *) the pointer to the file to export the modeler.

Implements URANIE::Modeler::TModeler.

Referenced by ClassImp().

◆ exportModelFortran()

void URANIE::Modeler::TKernel::exportModelFortran ( std::ofstream * sourcefile ) const

virtual

Export the model in Fortran langage in a file.

Warning: Don't use this method. Use the main method TModeler::exportFunction.

Parameters

sourcefile (std::ofstream *) the pointer to the file to export the modeler.

Implements URANIE::Modeler::TModeler.

Referenced by ClassImp().

◆ exportModelPMML()

void URANIE::Modeler::TKernel::exportModelPMML	(	const char *	file = `""`,
		const char *	name = `""`,
		Option_t *	option = `""`
	)		const

inlinevirtual

Export the model in a PMML file (not yet implemented)

Parameters

sourcefile (std::ofstream *) the pointer to the file to export the modeler.

Warning: Don't use this method. Use the main method TModeler::exportFunction.

Implements URANIE::Modeler::TModeler.

◆ exportModelPython()

void URANIE::Modeler::TKernel::exportModelPython ( std::ofstream * sourcefile ) const

inlinevirtual

Export the model in Python langage in a file (not yet implemented)

Warning: Don't use this method. Use the main method TModeler::exportFunction.

Parameters

sourcefile (std::ofstream *) the pointer to the file to export the modeler.

Implements URANIE::Modeler::TModeler.

◆ fillData()

void URANIE::Modeler::TKernel::fillData ( )

Fill the matrix of Inputs attributes and the vector of output attribute (nY=1)

Todo:: To deplace in the TModeler Class because it is the same for TLinearRegression.

Referenced by ClassImp().

◆ getKernel()

EKernelType URANIE::Modeler::TKernel::getKernel ( )

inline

Return the type of Y distribution.

References _nKernelType.

◆ getLambda()

Double_t URANIE::Modeler::TKernel::getLambda ( )

inline

Get the Lambda.

References _dLambda.

◆ getMatrixK()

TMatrixDSym URANIE::Modeler::TKernel::getMatrixK ( )

inline

Get the matrix _matK.

References _matK.

Referenced by ClassImp().

◆ getParameter1()

Double_t URANIE::Modeler::TKernel::getParameter1 ( )

inline

Return First Parameter.

References _dParameter1.

◆ getParameter2()

Double_t URANIE::Modeler::TKernel::getParameter2 ( )

inline

Return Second Parameter.

References _dParameter2.

◆ printLog()

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

virtual

Reimplemented from URANIE::Modeler::TModeler.

Referenced by ClassImp().

◆ setKernel() [1/4]

void URANIE::Modeler::TKernel::setKernel ( EKernelType nKernel )

Set the type of kernel without parameter.

Parameters

nKernel (EKernelType) The type of kernel

Referenced by ClassImp(), and URANIE::Modeler::TkPCA::setKernel().

◆ setKernel() [2/4]

void URANIE::Modeler::TKernel::setKernel	(	EKernelType	nKernel,
		Double_t	dparam1
	)

Parameters

nKernel	(EKernelType) The type of kernel
dparam	(Double_t) the First and only one parameter

◆ setKernel() [3/4]

void URANIE::Modeler::TKernel::setKernel	(	EKernelType	nKernel,
		Double_t	dparam1,
		Double_t	dparam2
	)

Set the type of kernel with two parameters.

Parameters

nKernel	(EKernelType) The type of kernel
dparam1	(Double_t) First parameter
dparam2	(Double_t) Second parameter

◆ setKernel() [4/4]

void URANIE::Modeler::TKernel::setKernel	(	EKernelType	nKernel,
		Double_t	dparam1,
		Double_t	dparam2,
		Double_t	dparam3
	)

Set the type of kernel with three parameters.

Parameters

nKernel	(EKernelType) The type of kernel
dparam1	(Double_t) First parameter
dparam2	(Double_t) Second parameter
dparam3	(Double_t) Third parameter

◆ setLambda()

void URANIE::Modeler::TKernel::setLambda ( Double_t dlambda )

inline

Set the Lambda parameter.

References _dLambda.

Member Data Documentation

◆ _dLambda

Double_t URANIE::Modeler::TKernel::_dLambda

private

The lambda parameter (default 1.e-6)

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

◆ _dParameter1

Double_t URANIE::Modeler::TKernel::_dParameter1

private

The First Parameter (gamma) [1.0].

Referenced by ClassImp(), and getParameter1().

◆ _dParameter2

Double_t URANIE::Modeler::TKernel::_dParameter2

private

The Second Parameter (coeff) [0.0].

Referenced by ClassImp(), and getParameter2().

◆ _dParameter3

Double_t URANIE::Modeler::TKernel::_dParameter3

private

The Third Parameter (degree) [1.0].

Referenced by ClassImp().

◆ _matK

TMatrixDSym URANIE::Modeler::TKernel::_matK

private

The matrix of K (inputs)

Referenced by ClassImp(), and getMatrixK().

◆ _matX

TMatrixD URANIE::Modeler::TKernel::_matX

private

The matrix of inputs attributes.

Referenced by ClassImp().

◆ _nKernelType

EKernelType URANIE::Modeler::TKernel::_nKernelType

private

The type of Kernel.

Referenced by ClassImp(), and getKernel().

◆ _nParameter

Int_t URANIE::Modeler::TKernel::_nParameter

private

The number of parameter.

Referenced by ClassImp().

◆ _vecY

TVectorD URANIE::Modeler::TKernel::_vecY

private

The vector of Y (outputs)

Referenced by ClassImp().

Documentation / Manuel développeur

Modules disponibles

Public Types

Public Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Member Enumeration Documentation

◆ EKernelType

Constructor & Destructor Documentation

◆ TKernel() [1/2]

◆ TKernel() [2/2]

◆ ~TKernel()

Member Function Documentation

◆ computeK()

◆ estimate()

◆ exportModelCplusplus()

◆ exportModelFortran()

◆ exportModelPMML()

◆ exportModelPython()

◆ fillData()

◆ getKernel()

◆ getLambda()

◆ getMatrixK()

◆ getParameter1()

◆ getParameter2()

◆ printLog()

◆ setKernel() [1/4]

◆ setKernel() [2/4]

◆ setKernel() [3/4]

◆ setKernel() [4/4]

◆ setLambda()

Member Data Documentation

◆ _dLambda

◆ _dParameter1

◆ _dParameter2

◆ _dParameter3

◆ _matK

◆ _matX

◆ _nKernelType

◆ _nParameter

◆ _vecY