Fitter class, entry point for performing all type of fits.

Fits are performed using the generic ROOT::Fit::Fitter::Fit method. The inputs are the data points and a model function (using a ROOT::Math::IParamFunction) The result of the fit is returned and kept internally in the ROOT::Fit::FitResult class. The configuration of the fit (parameters, options, etc...) are specified in the ROOT::Math::FitConfig class. After fitting the config of the fit will be modified to have the new values the resulting parameter of the fit with step sizes equal to the errors. FitConfig can be preserved with initial parameters by calling FitConfig.SetUpdateAfterFit(false);

Definition at line 77 of file Fitter.h.

Public Types
typedef ROOT::Math::IMultiGenFunction	BaseFunc

typedef ROOT::Math::IMultiGradFunction	BaseGradFunc

typedef ROOT::Math::IParamGradFunction	IGradModel1DFunction

typedef ROOT::Math::IParamMultiGradFunction	IGradModelFunction

typedef ROOT::Math::IParamMultiGradFunction	IGradModelFunction_v

typedef ROOT::Math::IParamFunction	IModel1DFunction

typedef ROOT::Math::IParamMultiFunction	IModelFunction

typedef ROOT::Math::IParamMultiFunction	IModelFunction_v

template<class T >
using	IModelFunctionTempl = ROOT::Math::IParamMultiFunctionTempl< T >

typedef void(*	MinuitFCN_t) (int &npar, double gin, double &f, double u, int flag)
	fit using user provided FCN with Minuit-like interface If npar = 0 it is assumed that the parameters are specified in the parameter settings created before For the options same consideration as in the previous method

Public Member Functions
	Fitter ()
	Default constructor.

	Fitter (const Fitter &)=delete
	Copy constructor (disabled, class is not copyable)

	Fitter (const std::shared_ptr< FitResult > &result)
	Constructor from a result.

virtual	~Fitter ()
	Destructor.

bool	ApplyWeightCorrection (const ROOT::Math::IMultiGenFunction &loglw2, bool minimizeW2L=false)
	apply correction in the error matrix for the weights for likelihood fits This method can be called only after a fit.

bool	CalculateHessErrors ()
	perform an error analysis on the result using the Hessian Errors are obtained from the inverse of the Hessian matrix To be called only after fitting and when a minimizer supporting the Hessian calculations is used otherwise an error (false) is returned.

bool	CalculateMinosErrors ()
	perform an error analysis on the result using MINOS To be called only after fitting and when a minimizer supporting MINOS is used otherwise an error (false) is returned.

FitConfig &	Config ()
	access to the configuration (non const method)

const FitConfig &	Config () const
	access to the fit configuration (const method)

bool	EvalFCN ()
	Perform a simple FCN evaluation.

bool	Fit (const BinData &data, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Fit a binned data set using a least square fit.

template<class Data , class Function , class cond = typename std::enable_if<!(std::is_same<Function, ROOT::EExecutionPolicy>::value \|\| std::is_same<Function, int>::value), Function>::type>
bool	Fit (const Data &data, const Function &func, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	fit a data set using any generic model function If data set is binned a least square fit is performed If data set is unbinned a maximum likelihood fit (not extended) is done Pre-requisite on the function: it must implement the 1D or multidimensional parametric function interface.

bool	Fit (const std::shared_ptr< BinData > &data, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Fit a binned data set using a least square fit.

bool	Fit (const std::shared_ptr< UnBinData > &data, bool extended=false, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Fit an un-binned data set using the negative log-likelihood method.

bool	Fit (const UnBinData &data, bool extended=false, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Fit an un-binned data set using the negative log-likelihood method.

bool	FitFCN ()
	Perform a fit with the previously set FCN function.

bool	FitFCN (const ROOT::Math::FitMethodFunction &fcn, const double *params=nullptr)
	Fit using a FitMethodFunction interface.

bool	FitFCN (const ROOT::Math::FitMethodGradFunction &fcn, const double *params=nullptr)
	Fit using a FitMethodGradFunction interface.

bool	FitFCN (const ROOT::Math::IMultiGenFunction &fcn, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	Fit using the given FCN function represented by a multi-dimensional function interface (ROOT::Math::IMultiGenFunction).

bool	FitFCN (const ROOT::Math::IMultiGradFunction &fcn, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	Fit using the given FCN function representing a multi-dimensional gradient function interface (ROOT::Math::IMultiGradFunction).

bool	FitFCN (MinuitFCN_t fcn, int npar=0, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)

template<class Function >
bool	FitFCN (unsigned int npar, Function &fcn, const double *params=0, unsigned int dataSize=0, bool chi2fit=false)
	Fit using the a generic FCN function as a C++ callable object implementing double () (const double *) Note that the function dimension (i.e.

ROOT::Math::IMultiGenFunction *	GetFCN () const
	return pointer to last used objective function (is NULL in case fit is not yet done) This pointer will be valid as far as the fitter class has not been deleted.

ROOT::Math::Minimizer *	GetMinimizer () const
	return pointer to last used minimizer (is NULL in case fit is not yet done) This pointer is guaranteed to be valid as far as the fitter class is valid and a new fit is not redone.

bool	IsBinFit () const
	query if fit is binned.

bool	LeastSquareFit (const BinData &data, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Fit a binned data set using a least square fit copying the input data.

bool	LeastSquareFit (const std::shared_ptr< BinData > &data, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Fit a binned data set using a least square fit NOT copying the input data.

bool	LikelihoodFit (const BinData &data, bool extended=true, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Binned Likelihood fit copying the input data.

template<class Data , class Function >
bool	LikelihoodFit (const Data &data, const Function &func, bool extended)
	Likelihood fit given a data set (Binned or Un-binned) using any generic model function.

bool	LikelihoodFit (const std::shared_ptr< BinData > &data, bool extended=true, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Binned Likelihood fit using a `shared_ptr` for NOT copying the input data.

bool	LikelihoodFit (const std::shared_ptr< UnBinData > &data, bool extended=false, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Un-binned Likelihood fit using a `shared_ptr` for NOT copying the input data.

bool	LikelihoodFit (const UnBinData &data, bool extended=false, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	Un-binned Likelihood fit copying the input data Default is NOT extended.

bool	LinearFit (const BinData &data)
	Do a linear fit copying the input data.

bool	LinearFit (const std::shared_ptr< BinData > &data)
	Do a linear fit using a `shared_ptr` for NOT copying the input data.

Fitter &	operator= (const Fitter &)=delete
	Assignment operator (disabled, class is not copyable)

const FitResult &	Result () const
	get fit result

bool	SetFCN (const ROOT::Math::FitMethodFunction &fcn, const double *params=nullptr)
	Set the objective function (FCN) using a FitMethodFunction interface.

bool	SetFCN (const ROOT::Math::FitMethodGradFunction &fcn, const double *params=nullptr)
	Set the objective function (FCN) using a FitMethodGradFunction interface.

bool	SetFCN (const ROOT::Math::IMultiGenFunction &fcn, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	Set the FCN function represented by a multi-dimensional function interface (ROOT::Math::IMultiGenFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN.

bool	SetFCN (const ROOT::Math::IMultiGenFunction &fcn, const IModelFunction &func, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	Set the FCN function represented by a multi-dimensional function interface (ROOT::Math::IMultiGenFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN With this interface we pass in addition a ModelFunction that will be attached to the FitResult and used to compute confidence interval of the fit.

bool	SetFCN (const ROOT::Math::IMultiGradFunction &fcn, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	Set the FCN function represented by a multi-dimensional gradient function interface (ROOT::Math::IMultiGradFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN.

bool	SetFCN (const ROOT::Math::IMultiGradFunction &fcn, const IModelFunction &func, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	Set the FCN function represented by a multi-dimensional gradient function interface (ROOT::Math::IMultiGradFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN With this interface we pass in addition a ModelFunction that will be attached to the FitResult and used to compute confidence interval of the fit.

bool	SetFCN (MinuitFCN_t fcn, int npar=0, const double *params=nullptr, unsigned int dataSize=0, bool chi2fit=false)
	set objective function using user provided FCN with Minuit-like interface If npar = 0 it is assumed that the parameters are specified in the parameter settings created before For the options same consideration as in the previous method

template<class Function >
bool	SetFCN (unsigned int npar, Function &fcn, const double *params=0, unsigned int dataSize=0, bool chi2fit=false)
	Set a generic FCN function as a C++ callable object implementing double () (const double *) Note that the function dimension (i.e.

void	SetFunction (const IGradModel1DFunction &func, bool useGradient=true)
	Set the fitted function from 1D gradient parametric function interface.

void	SetFunction (const IGradModelFunction &func, bool useGradient=true)
	Set the fitted function (model function) from a parametric gradient function interface.

void	SetFunction (const IModel1DFunction &func, bool useGradient=false)
	Set the fitted function (model function) from a vectorized parametric function interface.

void	SetFunction (const IModelFunction &func, bool useGradient=false)
	Set the fitted function (model function) from a parametric function interface.

Protected Member Functions
bool	DoBinnedLikelihoodFit (bool extended=true, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	binned likelihood fit

bool	DoInitMinimizer ()

bool	DoLeastSquareFit (const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	least square fit

bool	DoLinearFit ()
	linear least square fit

bool	DoMinimization (const ROOT::Math::IMultiGenFunction *chifunc=nullptr)

template<class ObjFunc_t >
bool	DoMinimization (std::unique_ptr< ObjFunc_t > f, const ROOT::Math::IMultiGenFunction *chifunc=nullptr)
	do minimization

bool	DoSetFCN (bool useExtFCN, const ROOT::Math::IMultiGenFunction &fcn, const double *params, unsigned int dataSize, bool chi2fit)
	Set Objective function.

bool	DoUnbinnedLikelihoodFit (bool extended=false, const ROOT::EExecutionPolicy &executionPolicy=ROOT::EExecutionPolicy::kSequential)
	un-binned likelihood fit

void	DoUpdateFitConfig ()

bool	DoUpdateMinimizerOptions (bool canDifferentMinim=true)

template<class ObjFunc_t >
bool	DoWeightMinimization (std::unique_ptr< ObjFunc_t > f, const ROOT::Math::IMultiGenFunction *chifunc=nullptr)

void	ExamineFCN ()
	look at the user provided FCN and get data and model function is they derive from ROOT::Fit FCN classes

template<class ObjFuncType >
bool	GetDataFromFCN ()
	internal functions to get data set and model function from FCN useful for fits done with customized FCN classes

int	GetNCallsFromFCN ()

const ROOT::Math::IBaseFunctionMultiDimTempl< double > *	ObjFunction () const
	Return pointer to the used objective function for fitting.

template<class Data >
void	SetData (const Data &data)
	Set the input data for the fit (Copying the given data object)

template<class Data >
void	SetData (const std::shared_ptr< Data > &data)
	Set the input data for the fit using a shared ptr (No Copying)

Private Attributes
bool	fBinFit = false
	flag to indicate if fit is binned in case of false the fit is unbinned or undefined) flag it is used to compute chi2 for binned likelihood fit

FitConfig	fConfig
	fitter configuration (options and parameter settings)

std::shared_ptr< ROOT::Fit::FitData >	fData
	! pointer to the fit data (binned or unbinned data)

int	fDataSize = 0
	size of data sets (need for Fumili or LM fitters)

const ROOT::Math::IMultiGenFunction *	fExtObjFunction = nullptr
	! pointer to an external FCN

int	fFitType = 0
	type of fit (0 undefined, 1 least square, 2 likelihood)

std::shared_ptr< IModelFunction >	fFunc
	! copy of the fitted function containing on output the fit result

std::shared_ptr< IModelFunction_v >	fFunc_v
	! copy of the fitted function containing on output the fit result

std::shared_ptr< ROOT::Math::Minimizer >	fMinimizer
	! pointer to used minimizer

std::shared_ptr< ROOT::Math::IMultiGenFunction >	fObjFunction
	! pointer to used objective function

std::shared_ptr< ROOT::Fit::FitResult >	fResult
	! pointer to the object containing the result of the fit

bool	fUseGradient = false
	flag to indicate if using gradient or not

#include <Fit/Fitter.h>

Member Typedef Documentation

◆ BaseFunc

typedef ROOT::Math::IMultiGenFunction ROOT::Fit::Fitter::BaseFunc

Definition at line 95 of file Fitter.h.

◆ BaseGradFunc

typedef ROOT::Math::IMultiGradFunction ROOT::Fit::Fitter::BaseGradFunc

Definition at line 96 of file Fitter.h.

◆ IGradModel1DFunction

typedef ROOT::Math::IParamGradFunction ROOT::Fit::Fitter::IGradModel1DFunction

Definition at line 93 of file Fitter.h.

◆ IGradModelFunction

typedef ROOT::Math::IParamMultiGradFunction ROOT::Fit::Fitter::IGradModelFunction

Definition at line 91 of file Fitter.h.

◆ IGradModelFunction_v

typedef ROOT::Math::IParamMultiGradFunction ROOT::Fit::Fitter::IGradModelFunction_v

Definition at line 89 of file Fitter.h.

◆ IModel1DFunction

typedef ROOT::Math::IParamFunction ROOT::Fit::Fitter::IModel1DFunction

Definition at line 92 of file Fitter.h.

◆ IModelFunction

typedef ROOT::Math::IParamMultiFunction ROOT::Fit::Fitter::IModelFunction

Definition at line 81 of file Fitter.h.

◆ IModelFunction_v

typedef ROOT::Math::IParamMultiFunction ROOT::Fit::Fitter::IModelFunction_v

Definition at line 88 of file Fitter.h.

◆ IModelFunctionTempl

template<class T >

using ROOT::Fit::Fitter::IModelFunctionTempl = ROOT::Math::IParamMultiFunctionTempl<T>

Definition at line 83 of file Fitter.h.

◆ MinuitFCN_t

typedef void(* ROOT::Fit::Fitter::MinuitFCN_t) (int &npar, double *gin, double &f, double *u, int flag)

fit using user provided FCN with Minuit-like interface If npar = 0 it is assumed that the parameters are specified in the parameter settings created before For the options same consideration as in the previous method

Definition at line 363 of file Fitter.h.

Constructor & Destructor Documentation

◆ Fitter() [1/3]

ROOT::Fit::Fitter::Fitter ( )

inline

Default constructor.

Definition at line 102 of file Fitter.h.

◆ Fitter() [2/3]

ROOT::Fit::Fitter::Fitter ( const std::shared_ptr< FitResult > & result )

Constructor from a result.

Definition at line 51 of file Fitter.cxx.

◆ ~Fitter()

virtual ROOT::Fit::Fitter::~Fitter ( )

inlinevirtual

Destructor.

Make it virtual in case users derive from Fitter class to extend it by adding new methods. This is needed to avoid a warning seen when doing from Python (see ROOT issue #12391 ). Note that the Fitter class does not provide virtual functions to be re-implemented by derived classes.

Definition at line 117 of file Fitter.h.

◆ Fitter() [3/3]

ROOT::Fit::Fitter::Fitter ( const Fitter & )

delete

Copy constructor (disabled, class is not copyable)

Member Function Documentation

◆ ApplyWeightCorrection()

bool ROOT::Fit::Fitter::ApplyWeightCorrection	(	const ROOT::Math::IMultiGenFunction &	loglw2,
		bool	minimizeW2L = `false`
	)

apply correction in the error matrix for the weights for likelihood fits This method can be called only after a fit.

The passed function (loglw2) is a log-likelihood function implemented using the sum of weight squared When using FitConfig.SetWeightCorrection() this correction is applied automatically when doing a likelihood fit (binned or unbinned)

Definition at line 912 of file Fitter.cxx.

◆ CalculateHessErrors()

bool ROOT::Fit::Fitter::CalculateHessErrors ( )

perform an error analysis on the result using the Hessian Errors are obtained from the inverse of the Hessian matrix To be called only after fitting and when a minimizer supporting the Hessian calculations is used otherwise an error (false) is returned.

A new FitResult with the Hessian result will be produced

Definition at line 556 of file Fitter.cxx.

◆ CalculateMinosErrors()

bool ROOT::Fit::Fitter::CalculateMinosErrors ( )

perform an error analysis on the result using MINOS To be called only after fitting and when a minimizer supporting MINOS is used otherwise an error (false) is returned.

The result will be appended in the fit result class Optionally a vector of parameter indices can be passed for selecting the parameters to analyse using FitConfig::SetMinosErrors

Definition at line 619 of file Fitter.cxx.

◆ Config() [1/2]

FitConfig & ROOT::Fit::Fitter::Config ( )

inline

access to the configuration (non const method)

Definition at line 451 of file Fitter.h.

◆ Config() [2/2]

const FitConfig & ROOT::Fit::Fitter::Config ( ) const

inline

access to the fit configuration (const method)

Definition at line 446 of file Fitter.h.

◆ DoBinnedLikelihoodFit()

bool ROOT::Fit::Fitter::DoBinnedLikelihoodFit	(	bool	extended = `true`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

protected

binned likelihood fit

Definition at line 386 of file Fitter.cxx.

◆ DoInitMinimizer()

bool ROOT::Fit::Fitter::DoInitMinimizer ( )

protected

Definition at line 718 of file Fitter.cxx.

◆ DoLeastSquareFit()

bool ROOT::Fit::Fitter::DoLeastSquareFit ( const ROOT::EExecutionPolicy & executionPolicy = ROOT::EExecutionPolicy::kSequential )

protected

least square fit

Definition at line 335 of file Fitter.cxx.

◆ DoLinearFit()

bool ROOT::Fit::Fitter::DoLinearFit ( )

protected

linear least square fit

Definition at line 539 of file Fitter.cxx.

◆ DoMinimization() [1/2]

bool ROOT::Fit::Fitter::DoMinimization ( const ROOT::Math::IMultiGenFunction * chifunc = nullptr )

protected

Definition at line 821 of file Fitter.cxx.

◆ DoMinimization() [2/2]

template<class ObjFunc_t >

bool ROOT::Fit::Fitter::DoMinimization	(	std::unique_ptr< ObjFunc_t >	f,
		const ROOT::Math::IMultiGenFunction *	chifunc = `nullptr`
	)

protected

do minimization

Definition at line 862 of file Fitter.cxx.

◆ DoSetFCN()

bool ROOT::Fit::Fitter::DoSetFCN	(	bool	useExtFCN,
		const ROOT::Math::IMultiGenFunction &	fcn,
		const double *	params,
		unsigned int	dataSize,
		bool	chi2fit
	)

protected

Set Objective function.

Definition at line 137 of file Fitter.cxx.

◆ DoUnbinnedLikelihoodFit()

bool ROOT::Fit::Fitter::DoUnbinnedLikelihoodFit	(	bool	extended = `false`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

protected

un-binned likelihood fit

Definition at line 466 of file Fitter.cxx.

◆ DoUpdateFitConfig()

void ROOT::Fit::Fitter::DoUpdateFitConfig ( )

protected

Definition at line 886 of file Fitter.cxx.

◆ DoUpdateMinimizerOptions()

bool ROOT::Fit::Fitter::DoUpdateMinimizerOptions ( bool canDifferentMinim = true )

protected

Definition at line 789 of file Fitter.cxx.

◆ DoWeightMinimization()

template<class ObjFunc_t >

bool ROOT::Fit::Fitter::DoWeightMinimization	(	std::unique_ptr< ObjFunc_t >	f,
		const ROOT::Math::IMultiGenFunction *	chifunc = `nullptr`
	)

protected

Definition at line 871 of file Fitter.cxx.

◆ EvalFCN()

bool ROOT::Fit::Fitter::EvalFCN ( )

Perform a simple FCN evaluation.

FitResult will be modified and contain the value of the FCN

Definition at line 314 of file Fitter.cxx.

◆ ExamineFCN()

void ROOT::Fit::Fitter::ExamineFCN ( )

protected

look at the user provided FCN and get data and model function is they derive from ROOT::Fit FCN classes

Definition at line 1005 of file Fitter.cxx.

◆ Fit() [1/5]

bool ROOT::Fit::Fitter::Fit	(	const BinData &	data,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Fit a binned data set using a least square fit.

Note that the provided input data are copied in the Fitter class. Use the next function (passing a shared_ptr to the BinData class if you want to avoid copying.

Definition at line 157 of file Fitter.h.

◆ Fit() [2/5]

template<class Data , class Function , class cond = typename std::enable_if<!(std::is_same<Function, ROOT::EExecutionPolicy>::value || std::is_same<Function, int>::value), Function>::type>

bool ROOT::Fit::Fitter::Fit	(	const Data &	data,
		const Function &	func,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

fit a data set using any generic model function If data set is binned a least square fit is performed If data set is unbinned a maximum likelihood fit (not extended) is done Pre-requisite on the function: it must implement the 1D or multidimensional parametric function interface.

Note that both the input data and the function object are copied by the Fitter.

Definition at line 144 of file Fitter.h.

◆ Fit() [3/5]

bool ROOT::Fit::Fitter::Fit	(	const std::shared_ptr< BinData > &	data,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Fit a binned data set using a least square fit.

Pass the input data using a shared_ptr for NOT copying the input data.

Definition at line 165 of file Fitter.h.

◆ Fit() [4/5]

bool ROOT::Fit::Fitter::Fit	(	const std::shared_ptr< UnBinData > &	data,
		bool	extended = `false`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Fit an un-binned data set using the negative log-likelihood method.

This function uses a shared_ptr to avoid copying the input data.

Definition at line 195 of file Fitter.h.

◆ Fit() [5/5]

bool ROOT::Fit::Fitter::Fit	(	const UnBinData &	data,
		bool	extended = `false`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Fit an un-binned data set using the negative log-likelihood method.

This function copies the input data.

Definition at line 188 of file Fitter.h.

◆ FitFCN() [1/7]

bool ROOT::Fit::Fitter::FitFCN ( )

Perform a fit with the previously set FCN function.

Require SetFCN before

Definition at line 295 of file Fitter.cxx.

◆ FitFCN() [2/7]

bool ROOT::Fit::Fitter::FitFCN	(	const ROOT::Math::FitMethodFunction &	fcn,
		const double *	params = `nullptr`
	)

Fit using a FitMethodFunction interface.

Same as method above, but now extra information can be taken from the function class

Definition at line 252 of file Fitter.cxx.

◆ FitFCN() [3/7]

bool ROOT::Fit::Fitter::FitFCN	(	const ROOT::Math::FitMethodGradFunction &	fcn,
		const double *	params = `nullptr`
	)

Fit using a FitMethodGradFunction interface.

Same as method above, but now extra information can be taken from the function class

◆ FitFCN() [4/7]

bool ROOT::Fit::Fitter::FitFCN	(	const ROOT::Math::IMultiGenFunction &	fcn,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Fit using the given FCN function represented by a multi-dimensional function interface (ROOT::Math::IMultiGenFunction).

Give optionally the initial parameter values, data size to have the fit Ndf correctly set in the FitResult and flag specifying if it is a chi2 fit. Note that if the parameters values are not given (params=0) the current parameter settings are used. The parameter settings can be created before by using the FitConfig::SetParamsSetting. If they have not been created they are created automatically when the params pointer is not zero. Note that passing a params != 0 will set the parameter settings to the new value AND also the step sizes to some pre-defined value (stepsize = 0.3 * abs(parameter_value) )

Definition at line 234 of file Fitter.cxx.

◆ FitFCN() [5/7]

bool ROOT::Fit::Fitter::FitFCN	(	const ROOT::Math::IMultiGradFunction &	fcn,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Fit using the given FCN function representing a multi-dimensional gradient function interface (ROOT::Math::IMultiGradFunction).

In this case the minimizer will use the gradient information provided by the function. For the options same consideration as in the previous method

Definition at line 243 of file Fitter.cxx.

◆ FitFCN() [6/7]

bool ROOT::Fit::Fitter::FitFCN	(	MinuitFCN_t	fcn,
		int	npar = `0`,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Definition at line 285 of file Fitter.cxx.

◆ FitFCN() [7/7]

template<class Function >

bool ROOT::Fit::Fitter::FitFCN	(	unsigned int	npar,
		Function &	fcn,
		const double *	params = `0`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Fit using the a generic FCN function as a C++ callable object implementing double () (const double *) Note that the function dimension (i.e.

the number of parameter) is needed in this case For the options see documentation for following methods FitFCN(IMultiGenFunction & fcn,..)

Definition at line 659 of file Fitter.h.

◆ GetDataFromFCN()

template<class ObjFuncType >

bool ROOT::Fit::Fitter::GetDataFromFCN

protected

internal functions to get data set and model function from FCN useful for fits done with customized FCN classes

Definition at line 593 of file Fitter.h.

◆ GetFCN()

ROOT::Math::IMultiGenFunction * ROOT::Fit::Fitter::GetFCN ( ) const

inline

return pointer to last used objective function (is NULL in case fit is not yet done) This pointer will be valid as far as the fitter class has not been deleted.

To be used after the fitting. The pointer should not be stored and will be invalided after performing a new fitting. In this case a new instance of the function pointer will be re-created and can be obtained calling again GetFCN()

Definition at line 479 of file Fitter.h.

◆ GetMinimizer()

ROOT::Math::Minimizer * ROOT::Fit::Fitter::GetMinimizer ( ) const

inline

return pointer to last used minimizer (is NULL in case fit is not yet done) This pointer is guaranteed to be valid as far as the fitter class is valid and a new fit is not redone.

To be used only after fitting. The pointer should not be stored and will be invalided after performing a new fitting. In this case a new instance of ROOT::Math::Minimizer will be re-created and can be obtained calling again GetMinimizer()

Definition at line 468 of file Fitter.h.

◆ GetNCallsFromFCN()

int ROOT::Fit::Fitter::GetNCallsFromFCN ( )

protected

Definition at line 896 of file Fitter.cxx.

◆ IsBinFit()

bool ROOT::Fit::Fitter::IsBinFit ( ) const

inline

query if fit is binned.

In cse of false the fit can be unbinned or is not defined (like in case of fitting through a ROOT::Fit::Fitter::FitFCN)

Definition at line 457 of file Fitter.h.

◆ LeastSquareFit() [1/2]

bool ROOT::Fit::Fitter::LeastSquareFit	(	const BinData &	data,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Fit a binned data set using a least square fit copying the input data.

Definition at line 172 of file Fitter.h.

◆ LeastSquareFit() [2/2]

bool ROOT::Fit::Fitter::LeastSquareFit	(	const std::shared_ptr< BinData > &	data,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Fit a binned data set using a least square fit NOT copying the input data.

Definition at line 179 of file Fitter.h.

◆ LikelihoodFit() [1/5]

bool ROOT::Fit::Fitter::LikelihoodFit	(	const BinData &	data,
		bool	extended = `true`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Binned Likelihood fit copying the input data.

Default is extended.

Definition at line 203 of file Fitter.h.

◆ LikelihoodFit() [2/5]

template<class Data , class Function >

bool ROOT::Fit::Fitter::LikelihoodFit	(	const Data &	data,
		const Function &	func,
		bool	extended
	)

inline

Likelihood fit given a data set (Binned or Un-binned) using any generic model function.

This interface copies the input data and the model function object

Definition at line 239 of file Fitter.h.

◆ LikelihoodFit() [3/5]

bool ROOT::Fit::Fitter::LikelihoodFit	(	const std::shared_ptr< BinData > &	data,
		bool	extended = `true`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Binned Likelihood fit using a shared_ptr for NOT copying the input data.

Default is extended.

Definition at line 212 of file Fitter.h.

◆ LikelihoodFit() [4/5]

bool ROOT::Fit::Fitter::LikelihoodFit	(	const std::shared_ptr< UnBinData > &	data,
		bool	extended = `false`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Un-binned Likelihood fit using a shared_ptr for NOT copying the input data.

Default is NOT extended

Definition at line 229 of file Fitter.h.

◆ LikelihoodFit() [5/5]

bool ROOT::Fit::Fitter::LikelihoodFit	(	const UnBinData &	data,
		bool	extended = `false`,
		const ROOT::EExecutionPolicy &	executionPolicy = `ROOT::EExecutionPolicy::kSequential`
	)

inline

Un-binned Likelihood fit copying the input data Default is NOT extended.

Definition at line 221 of file Fitter.h.

◆ LinearFit() [1/2]

bool ROOT::Fit::Fitter::LinearFit ( const BinData & data )

inline

Do a linear fit copying the input data.

Definition at line 247 of file Fitter.h.

◆ LinearFit() [2/2]

bool ROOT::Fit::Fitter::LinearFit ( const std::shared_ptr< BinData > & data )

inline

Do a linear fit using a shared_ptr for NOT copying the input data.

Definition at line 254 of file Fitter.h.

◆ ObjFunction()

const ROOT::Math::IBaseFunctionMultiDimTempl< double > * ROOT::Fit::Fitter::ObjFunction ( ) const

inlineprotected

Return pointer to the used objective function for fitting.

If using an external function (e.g. given in SetFCN), return the cached pointer, otherwise use the one stored as shared ptr and managed by the Fitter class

Definition at line 553 of file Fitter.h.

◆ operator=()

Fitter & ROOT::Fit::Fitter::operator= ( const Fitter & )

delete

Assignment operator (disabled, class is not copyable)

◆ Result()

const FitResult & ROOT::Fit::Fitter::Result ( ) const

inline

get fit result

Definition at line 418 of file Fitter.h.

◆ SetData() [1/2]

template<class Data >

void ROOT::Fit::Fitter::SetData ( const Data & data )

inlineprotected

Set the input data for the fit (Copying the given data object)

Definition at line 535 of file Fitter.h.

◆ SetData() [2/2]

template<class Data >

void ROOT::Fit::Fitter::SetData ( const std::shared_ptr< Data > & data )

inlineprotected

Set the input data for the fit using a shared ptr (No Copying)

Definition at line 529 of file Fitter.h.

◆ SetFCN() [1/8]

bool ROOT::Fit::Fitter::SetFCN	(	const ROOT::Math::FitMethodFunction &	fcn,
		const double *	params = `nullptr`
	)

Set the objective function (FCN) using a FitMethodFunction interface.

Same as method above, but now extra information can be taken from the function class

Definition at line 210 of file Fitter.cxx.

◆ SetFCN() [2/8]

bool ROOT::Fit::Fitter::SetFCN	(	const ROOT::Math::FitMethodGradFunction &	fcn,
		const double *	params = `nullptr`
	)

Set the objective function (FCN) using a FitMethodGradFunction interface.

Same as method above, but now extra information can be taken from the function class

◆ SetFCN() [3/8]

bool ROOT::Fit::Fitter::SetFCN	(	const ROOT::Math::IMultiGenFunction &	fcn,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Set the FCN function represented by a multi-dimensional function interface (ROOT::Math::IMultiGenFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN.

Definition at line 178 of file Fitter.cxx.

◆ SetFCN() [4/8]

bool ROOT::Fit::Fitter::SetFCN	(	const ROOT::Math::IMultiGenFunction &	fcn,
		const IModelFunction &	func,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Set the FCN function represented by a multi-dimensional function interface (ROOT::Math::IMultiGenFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN With this interface we pass in addition a ModelFunction that will be attached to the FitResult and used to compute confidence interval of the fit.

Definition at line 182 of file Fitter.cxx.

◆ SetFCN() [5/8]

bool ROOT::Fit::Fitter::SetFCN	(	const ROOT::Math::IMultiGradFunction &	fcn,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Set the FCN function represented by a multi-dimensional gradient function interface (ROOT::Math::IMultiGradFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN.

Definition at line 190 of file Fitter.cxx.

◆ SetFCN() [6/8]

bool ROOT::Fit::Fitter::SetFCN	(	const ROOT::Math::IMultiGradFunction &	fcn,
		const IModelFunction &	func,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Set the FCN function represented by a multi-dimensional gradient function interface (ROOT::Math::IMultiGradFunction) and optionally the initial parameters See also note above for the initial parameters for FitFCN With this interface we pass in addition a ModelFunction that will be attached to the FitResult and used to compute confidence interval of the fit.

Definition at line 201 of file Fitter.cxx.

◆ SetFCN() [7/8]

bool ROOT::Fit::Fitter::SetFCN	(	MinuitFCN_t	fcn,
		int	npar = `0`,
		const double *	params = `nullptr`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

set objective function using user provided FCN with Minuit-like interface If npar = 0 it is assumed that the parameters are specified in the parameter settings created before For the options same consideration as in the previous method

Definition at line 268 of file Fitter.cxx.

◆ SetFCN() [8/8]

template<class Function >

bool ROOT::Fit::Fitter::SetFCN	(	unsigned int	npar,
		Function &	fcn,
		const double *	params = `0`,
		unsigned int	dataSize = `0`,
		bool	chi2fit = `false`
	)

Set a generic FCN function as a C++ callable object implementing double () (const double *) Note that the function dimension (i.e.

the number of parameter) is needed in this case For the options see documentation for following methods FitFCN(IMultiGenFunction & fcn,..)

Definition at line 666 of file Fitter.h.

◆ SetFunction() [1/4]

void ROOT::Fit::Fitter::SetFunction	(	const IGradModel1DFunction &	func,
		bool	useGradient = `true`
	)

Set the fitted function from 1D gradient parametric function interface.

Definition at line 124 of file Fitter.cxx.

◆ SetFunction() [2/4]

void ROOT::Fit::Fitter::SetFunction	(	const IGradModelFunction &	func,
		bool	useGradient = `true`
	)

Set the fitted function (model function) from a parametric gradient function interface.

Definition at line 110 of file Fitter.cxx.

◆ SetFunction() [3/4]

void ROOT::Fit::Fitter::SetFunction	(	const IModel1DFunction &	func,
		bool	useGradient = `false`
	)

Set the fitted function (model function) from a vectorized parametric function interface.

Set the fitted function from a parametric 1D function interface

Definition at line 86 of file Fitter.cxx.

◆ SetFunction() [4/4]

void ROOT::Fit::Fitter::SetFunction	(	const IModelFunction &	func,
		bool	useGradient = `false`
	)

Set the fitted function (model function) from a parametric function interface.

Definition at line 59 of file Fitter.cxx.

Member Data Documentation

◆ fBinFit

bool ROOT::Fit::Fitter::fBinFit = false

private

flag to indicate if fit is binned in case of false the fit is unbinned or undefined) flag it is used to compute chi2 for binned likelihood fit

Definition at line 563 of file Fitter.h.

◆ fConfig

FitConfig ROOT::Fit::Fitter::fConfig

private

fitter configuration (options and parameter settings)

Definition at line 571 of file Fitter.h.

◆ fData

std::shared_ptr<ROOT::Fit::FitData> ROOT::Fit::Fitter::fData

private

! pointer to the fit data (binned or unbinned data)

Definition at line 581 of file Fitter.h.

◆ fDataSize

int ROOT::Fit::Fitter::fDataSize = 0

private

size of data sets (need for Fumili or LM fitters)

Definition at line 569 of file Fitter.h.

◆ fExtObjFunction

const ROOT::Math::IMultiGenFunction* ROOT::Fit::Fitter::fExtObjFunction = nullptr

private

! pointer to an external FCN

Definition at line 585 of file Fitter.h.

◆ fFitType

int ROOT::Fit::Fitter::fFitType = 0

private

type of fit (0 undefined, 1 least square, 2 likelihood)

Definition at line 567 of file Fitter.h.

◆ fFunc

std::shared_ptr<IModelFunction> ROOT::Fit::Fitter::fFunc

private

! copy of the fitted function containing on output the fit result

Definition at line 575 of file Fitter.h.

◆ fFunc_v

std::shared_ptr<IModelFunction_v> ROOT::Fit::Fitter::fFunc_v

private

! copy of the fitted function containing on output the fit result

Definition at line 573 of file Fitter.h.

◆ fMinimizer

std::shared_ptr<ROOT::Math::Minimizer> ROOT::Fit::Fitter::fMinimizer

private

! pointer to used minimizer

Definition at line 579 of file Fitter.h.

◆ fObjFunction

std::shared_ptr<ROOT::Math::IMultiGenFunction> ROOT::Fit::Fitter::fObjFunction

private

! pointer to used objective function

Definition at line 583 of file Fitter.h.

◆ fResult

std::shared_ptr<ROOT::Fit::FitResult> ROOT::Fit::Fitter::fResult

private

! pointer to the object containing the result of the fit

Definition at line 577 of file Fitter.h.

◆ fUseGradient

bool ROOT::Fit::Fitter::fUseGradient = false

private

flag to indicate if using gradient or not

Definition at line 561 of file Fitter.h.

Libraries for ROOT::Fit::Fitter:

[legend]

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

math/mathcore/inc/Fit/Fitter.h
math/mathcore/src/Fitter.cxx

Public Types

Public Member Functions

Protected Member Functions

Private Attributes

Member Typedef Documentation

◆ BaseFunc

◆ BaseGradFunc

◆ IGradModel1DFunction

◆ IGradModelFunction

◆ IGradModelFunction_v

◆ IModel1DFunction

◆ IModelFunction

◆ IModelFunction_v

◆ IModelFunctionTempl

◆ MinuitFCN_t

Constructor & Destructor Documentation

◆ Fitter() [1/3]

◆ Fitter() [2/3]

◆ ~Fitter()

◆ Fitter() [3/3]

Member Function Documentation

◆ ApplyWeightCorrection()

◆ CalculateHessErrors()

◆ CalculateMinosErrors()

◆ Config() [1/2]

◆ Config() [2/2]

◆ DoBinnedLikelihoodFit()

◆ DoInitMinimizer()

◆ DoLeastSquareFit()

◆ DoLinearFit()

◆ DoMinimization() [1/2]

◆ DoMinimization() [2/2]

◆ DoSetFCN()

◆ DoUnbinnedLikelihoodFit()

◆ DoUpdateFitConfig()

◆ DoUpdateMinimizerOptions()

◆ DoWeightMinimization()

◆ EvalFCN()

◆ ExamineFCN()

◆ Fit() [1/5]

◆ Fit() [2/5]

◆ Fit() [3/5]

◆ Fit() [4/5]

◆ Fit() [5/5]

◆ FitFCN() [1/7]

◆ FitFCN() [2/7]

◆ FitFCN() [3/7]

◆ FitFCN() [4/7]

◆ FitFCN() [5/7]

◆ FitFCN() [6/7]

◆ FitFCN() [7/7]

◆ GetDataFromFCN()

◆ GetFCN()

◆ GetMinimizer()

◆ GetNCallsFromFCN()

◆ IsBinFit()

◆ LeastSquareFit() [1/2]

◆ LeastSquareFit() [2/2]

◆ LikelihoodFit() [1/5]

◆ LikelihoodFit() [2/5]

◆ LikelihoodFit() [3/5]

◆ LikelihoodFit() [4/5]

◆ LikelihoodFit() [5/5]

◆ LinearFit() [1/2]

◆ LinearFit() [2/2]

◆ ObjFunction()

◆ operator=()

◆ Result()

◆ SetData() [1/2]

◆ SetData() [2/2]

◆ SetFCN() [1/8]

◆ SetFCN() [2/8]

◆ SetFCN() [3/8]

◆ SetFCN() [4/8]

◆ SetFCN() [5/8]

◆ SetFCN() [6/8]

◆ SetFCN() [7/8]

◆ SetFCN() [8/8]

◆ SetFunction() [1/4]

◆ SetFunction() [2/4]