RMinimizer class.

Minimizer class that uses the ROOT/R interface to pass functions and minimize them in R.

The class implements the ROOT::Math::Minimizer interface and can be instantiated using the ROOT plugin manager (plugin name is "RMinimizer"). The various minimization algorithms (BFGS, Nelder-Mead, SANN, etc..) can be passed as an option. The default algorithm is BFGS.

The library for this and future R/ROOT classes is currently libRtools.so

Definition at line 33 of file RMinimizer.h.

Public Member Functions
	RMinimizer (Option_t *method)
	Default constructor.

virtual	~RMinimizer ()
	Destructor.

virtual double	CovMatrix (unsigned int ivar, unsigned int jvar) const
	return covariance matrices element for variables ivar,jvar if the variable is fixed the return value is zero The ordering of the variables is the same as in the parameter and errors vectors

virtual const double *	Errors () const
	return errors at the minimum

virtual bool	GetCovMatrix (double *covMat) const
	Fill the passed array with the covariance matrix elements if the variable is fixed or const the value is zero.

double	HessMatrix (unsigned int i, unsigned int j) const
	Returns the ith jth component of the Hessian matrix.

virtual bool	Minimize ()
	Function to find the minimum.

virtual unsigned int	NCalls () const
	Returns the number of function calls.

virtual bool	ProvidesError () const
	minimizer provides error and error matrix

Public Member Functions inherited from ROOT::Math::BasicMinimizer
	BasicMinimizer ()
	Default constructor.

virtual	~BasicMinimizer ()
	Destructor.

virtual bool	FixVariable (unsigned int ivar)
	fix an existing variable

virtual bool	GetVariableSettings (unsigned int ivar, ROOT::Fit::ParameterSettings &varObj) const
	get variable settings in a variable object (like ROOT::Fit::ParamsSettings)

const ROOT::Math::IMultiGradFunction *	GradObjFunction () const
	return pointer to used gradient object function (NULL if gradient is not supported)

virtual bool	IsFixedVariable (unsigned int ivar) const
	query if an existing variable is fixed (i.e.

virtual double	MinValue () const
	return minimum function value

virtual unsigned int	NDim () const
	number of dimensions

virtual unsigned int	NFree () const
	number of free variables (real dimension of the problem)

virtual unsigned int	NPar () const
	total number of parameter defined

const ROOT::Math::IMultiGenFunction *	ObjFunction () const
	return pointer to used objective function

void	PrintResult () const
	print result of minimization

virtual bool	ReleaseVariable (unsigned int ivar)
	release an existing variable

virtual bool	SetFixedVariable (unsigned int, const std::string &, double)
	set fixed variable (override if minimizer supports them )

virtual void	SetFunction (const ROOT::Math::IMultiGenFunction &func)
	set the function to minimize

virtual void	SetFunction (const ROOT::Math::IMultiGradFunction &func)
	set gradient the function to minimize

virtual bool	SetLimitedVariable (unsigned int ivar, const std::string &name, double val, double step, double, double)
	set upper/lower limited variable (override if minimizer supports them )

virtual bool	SetLowerLimitedVariable (unsigned int ivar, const std::string &name, double val, double step, double lower)
	set lower limit variable (override if minimizer supports them )

virtual bool	SetUpperLimitedVariable (unsigned int ivar, const std::string &name, double val, double step, double upper)
	set upper limit variable (override if minimizer supports them )

virtual bool	SetVariable (unsigned int ivar, const std::string &name, double val, double step)
	set free variable

virtual bool	SetVariableLimits (unsigned int ivar, double lower, double upper)
	set the limits of an already existing variable

virtual bool	SetVariableLowerLimit (unsigned int ivar, double lower)
	set the lower-limit of an already existing variable

virtual bool	SetVariableStepSize (unsigned int ivar, double step)
	set the step size of an already existing variable

virtual bool	SetVariableUpperLimit (unsigned int ivar, double upper)
	set the upper-limit of an already existing variable

virtual bool	SetVariableValue (unsigned int ivar, double val)
	set the value of an existing variable

virtual bool	SetVariableValues (const double *x)
	set the values of all existing variables (array must be dimensioned to the size of existing parameters)

virtual const double *	StepSizes () const
	accessor methods

const ROOT::Math::MinimTransformFunction *	TransformFunction () const
	return transformation function (NULL if not having a transformation)

virtual int	VariableIndex (const std::string &name) const
	get index of variable given a variable given a name return -1 if variable is not found

virtual std::string	VariableName (unsigned int ivar) const
	get name of variables (override if minimizer support storing of variable names)

virtual const double *	X () const
	return pointer to X values at the minimum

Public Member Functions inherited from ROOT::Math::Minimizer
	Minimizer ()
	Default constructor.

virtual	~Minimizer ()
	Destructor (no operations)

virtual void	Clear ()
	reset for consecutive minimizations - implement if needed

virtual bool	Contour (unsigned int ivar, unsigned int jvar, unsigned int &npoints, double xi, double xj)
	find the contour points (xi, xj) of the function for parameter ivar and jvar around the minimum The contour will be find for value of the function = Min + ErrorUp();

virtual double	Correlation (unsigned int i, unsigned int j) const
	return correlation coefficient between variable i and j.

virtual int	CovMatrixStatus () const
	return status of covariance matrix using Minuit convention {0 not calculated 1 approximated 2 made pos def , 3 accurate} Minimizer who implements covariance matrix calculation will re-implement the method

virtual double	Edm () const
	return expected distance reached from the minimum (re-implement if minimizer provides it

double	ErrorDef () const
	return the statistical scale used for calculate the error is typically 1 for Chi2 and 0.5 for likelihood minimization

virtual bool	GetHessianMatrix (double *hMat) const
	Fill the passed array with the Hessian matrix elements The Hessian matrix is the matrix of the second derivatives and is the inverse of the covariance matrix If the variable is fixed or const the values for that variables are zero.

virtual bool	GetMinosError (unsigned int ivar, double &errLow, double &errUp, int option=0)
	minos error for variable i, return false if Minos failed or not supported and the lower and upper errors are returned in errLow and errUp An extra flag specifies if only the lower (option=-1) or the upper (option=+1) error calculation is run

virtual double	GlobalCC (unsigned int ivar) const
	return global correlation coefficient for variable i This is a number between zero and one which gives the correlation between the i-th parameter and that linear combination of all other parameters which is most strongly correlated with i.

virtual bool	Hesse ()
	perform a full calculation of the Hessian matrix for error calculation

bool	IsValidError () const
	return true if Minimizer has performed a detailed error validation (e.g. run Hesse for Minuit)

unsigned int	MaxFunctionCalls () const
	max number of function calls

unsigned int	MaxIterations () const
	max iterations

virtual const double *	MinGradient () const
	return pointer to gradient values at the minimum

virtual int	MinosStatus () const
	status code of Minos (to be re-implemented by the minimizers supporting Minos)

virtual unsigned int	NIterations () const
	number of iterations to reach the minimum

virtual MinimizerOptions	Options () const
	retrieve the minimizer options (implement derived class if needed)

double	Precision () const
	precision of minimizer in the evaluation of the objective function ( a value <=0 corresponds to the let the minimizer choose its default one)

int	PrintLevel () const
	minimizer configuration parameters

virtual void	PrintResults ()
	return reference to the objective function virtual const ROOT::Math::IGenFunction & Function() const = 0;

virtual bool	Scan (unsigned int ivar, unsigned int &nstep, double x, double y, double xmin=0, double xmax=0)
	scan function minimum for variable i.

void	SetDefaultOptions ()
	reset the defaut options (defined in MinimizerOptions)

void	SetErrorDef (double up)
	set scale for calculating the errors

void	SetMaxFunctionCalls (unsigned int maxfcn)
	set maximum of function calls

void	SetMaxIterations (unsigned int maxiter)
	set maximum iterations (one iteration can have many function calls)

void	SetOptions (const MinimizerOptions &opt)
	set all options in one go

void	SetPrecision (double prec)
	set in the minimizer the objective function evaluation precision ( a value <=0 means the minimizer will choose its optimal value automatically, i.e.

void	SetPrintLevel (int level)
	set print level

void	SetStrategy (int strategyLevel)
	set the strategy

void	SetTolerance (double tol)
	set the tolerance

void	SetValidError (bool on)
	flag to check if minimizer needs to perform accurate error analysis (e.g. run Hesse for Minuit)

virtual bool	SetVariableInitialRange (unsigned int, double, double)
	set the initial range of an existing variable

template<class VariableIterator >
int	SetVariables (const VariableIterator &begin, const VariableIterator &end)
	add variables . Return number of variables successfully added

int	Status () const
	status code of minimizer

int	Strategy () const
	strategy

double	Tolerance () const
	absolute tolerance

Protected Attributes
std::string	fMethod
	minimizer method to be used, must be of a type listed in R optim or optimx descriptions

Protected Attributes inherited from ROOT::Math::Minimizer
MinimizerOptions	fOptions

int	fStatus

bool	fValidError

Private Attributes
TMatrixD	fCovMatrix
	covariant matrix

std::vector< double >	fErrors
	vector of parameter errors

TMatrixD	fHessMatrix
	Hessian matrix.

Additional Inherited Members
Protected Member Functions inherited from ROOT::Math::BasicMinimizer
bool	CheckDimension () const

bool	CheckObjFunction () const

MinimTransformFunction *	CreateTransformation (std::vector< double > &startValues, const ROOT::Math::IMultiGradFunction *func=0)

void	SetFinalValues (const double *x)

void	SetMinValue (double val)

#include <Math/RMinimizer.h>

Inheritance diagram for ROOT::Math::RMinimizer:

[legend]

Constructor & Destructor Documentation

◆ RMinimizer()

ROOT::Math::RMinimizer::RMinimizer ( Option_t * method )

Default constructor.

Default constructor with option for the method of minimization, can be any of the following: "Nelder-Mead", "BFGS", "CG", "L-BFGS-B", "SANN", "Brent" (Brent only for 1D minimization)

See R optim or optimx descriptions for more details and options.

Definition at line 38 of file RMinimizer.cxx.

◆ ~RMinimizer()

virtual ROOT::Math::RMinimizer::~RMinimizer ( )

inlinevirtual

Destructor.

Definition at line 53 of file RMinimizer.h.

Member Function Documentation

◆ CovMatrix()

virtual double ROOT::Math::RMinimizer::CovMatrix	(	unsigned int	ivar,
		unsigned int	jvar
	)		const

inlinevirtual

return covariance matrices element for variables ivar,jvar if the variable is fixed the return value is zero The ordering of the variables is the same as in the parameter and errors vectors

Reimplemented from ROOT::Math::Minimizer.

Definition at line 68 of file RMinimizer.h.

◆ Errors()

virtual const double * ROOT::Math::RMinimizer::Errors ( ) const

inlinevirtual

return errors at the minimum

Reimplemented from ROOT::Math::Minimizer.

Definition at line 63 of file RMinimizer.h.

◆ GetCovMatrix()

virtual bool ROOT::Math::RMinimizer::GetCovMatrix ( double * covMat ) const

inlinevirtual

Fill the passed array with the covariance matrix elements if the variable is fixed or const the value is zero.

The array will be filled as cov[i *ndim + j] The ordering of the variables is the same as in errors and parameter value. This is different from the direct interface of Minuit2 or TMinuit where the values were obtained only to variable parameters

Reimplemented from ROOT::Math::Minimizer.

Definition at line 79 of file RMinimizer.h.

◆ HessMatrix()

double ROOT::Math::RMinimizer::HessMatrix	(	unsigned int	i,
		unsigned int	j
	)		const

Returns the ith jth component of the Hessian matrix.

◆ Minimize()

bool ROOT::Math::RMinimizer::Minimize ( )

virtual

Function to find the minimum.

function for finding the minimum

Reimplemented from ROOT::Math::BasicMinimizer.

Definition at line 47 of file RMinimizer.cxx.

◆ NCalls()

unsigned int ROOT::Math::RMinimizer::NCalls ( ) const

virtual

Returns the number of function calls.

returns number of function calls

Reimplemented from ROOT::Math::Minimizer.

Definition at line 44 of file RMinimizer.cxx.

◆ ProvidesError()

virtual bool ROOT::Math::RMinimizer::ProvidesError ( ) const

inlinevirtual

minimizer provides error and error matrix

Reimplemented from ROOT::Math::Minimizer.

Definition at line 61 of file RMinimizer.h.

Member Data Documentation

◆ fCovMatrix

TMatrixD ROOT::Math::RMinimizer::fCovMatrix

private

covariant matrix

Definition at line 39 of file RMinimizer.h.

◆ fErrors

std::vector<double> ROOT::Math::RMinimizer::fErrors

private

vector of parameter errors

Definition at line 38 of file RMinimizer.h.

◆ fHessMatrix

TMatrixD ROOT::Math::RMinimizer::fHessMatrix

private

Hessian matrix.

Definition at line 40 of file RMinimizer.h.

◆ fMethod

std::string ROOT::Math::RMinimizer::fMethod

protected

minimizer method to be used, must be of a type listed in R optim or optimx descriptions

Definition at line 35 of file RMinimizer.h.

Libraries for ROOT::Math::RMinimizer:

[legend]

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

math/rtools/inc/Math/RMinimizer.h
math/rtools/src/RMinimizer.cxx

Public Member Functions

Protected Attributes

Private Attributes

Additional Inherited Members

Constructor & Destructor Documentation

◆ RMinimizer()

◆ ~RMinimizer()

Member Function Documentation

◆ CovMatrix()

◆ Errors()

◆ GetCovMatrix()

◆ HessMatrix()

◆ Minimize()

◆ NCalls()

◆ ProvidesError()

Member Data Documentation

◆ fCovMatrix

◆ fErrors

◆ fHessMatrix

◆ fMethod