Interface of model function for fitting (for advanced users). More...

#include <IModelFunction.h>

Inheritance diagram for AIDA::IModelFunction:

Public Member Functions
virtual	~IModelFunction ()
	Destructor.

virtual bool	providesNormalization () const =0
	Return false if function does not provide the normalization capability.

virtual void	normalize (bool on)=0
	Normalize by internally adjusting some of the parameters. More...

virtual bool	isNormalized () const =0
	Return true if normalization is currently switched on.

virtual const std::vector < double > &	parameterGradient (const std::vector< double > &x) const =0
	Compute gradient with respect to parameters.

virtual bool	providesParameterGradient () const =0
	Return true if provides parameter gradient.

virtual IRangeSet &	normalizationRange (int iAxis)=0
	Set the normalization range from -inf to +inf in the i-th axis (dimension). More...

virtual void	includeNormalizationAll ()=0
	Set full range in all axes.

virtual void	excludeNormalizationAll ()=0
	Set empty range in all axes.

Public Member Functions inherited from AIDA::IFunction
virtual	~IFunction ()
	Destructor.

virtual std::string	title () const =0
	Get the Function's title. More...

virtual bool	setTitle (const std::string &title)=0
	Set the histogram title. More...

virtual double	value (const std::vector< double > &x) const =0
	Scalar value of the function.

virtual int	dimension () const =0
	Dimensionality of the domain space.

virtual bool	isEqual (const IFunction &f) const =0
	Compare if functions are the same. More...

virtual const std::vector < double > &	gradient (const std::vector< double > &x) const =0
	Gradient of the function. More...

virtual bool	providesGradient () const =0
	Determine whether function is able to compute gradient.

virtual std::string	variableName (int i) const =0
	Get the symbolic name of i-th variable.

virtual std::vector< std::string >	variableNames () const =0
	Get all the names in a vector.

virtual bool	setParameters (const std::vector< double > &params)=0
	Set new vector of parameters.

virtual const std::vector < double > &	parameters () const =0
	Retrieve current vector of parameters.

virtual int	numberOfParameters () const =0
	Number of parameters.

virtual std::vector< std::string >	parameterNames () const =0
	Names of paramaters. More...

virtual bool	setParameter (const std::string &name, double x)=0
	Set parameter's value by name. More...

virtual double	parameter (const std::string &name) const =0

virtual int	indexOfParameter (const std::string &name) const =0
	Return -1 if parameter not found (name undefined). More...

virtual IAnnotation &	annotation ()=0

virtual const IAnnotation &	annotation () const =0

virtual std::string	codeletString () const =0
	String describing the metatype and implementation of the function. More...

virtual void *	cast (const std::string &className) const =0
	See IManagedObject for a description. More...

Detailed Description

Interface of model function for fitting (for advanced users).

OPEN QUESTIONS:

How to treat normalization at user level? Two possibilities:

we have "Gauss" and "NormalizedGauss", the first one user cannot use for ML fit
we have only one "Gauss" function, but it's smart and when normalized, gets rid of one of its parameters

Normalization range might be set directly on the function by the user? Now we set it in the data pipe, Victor thinks that it is not very clear and should be on the function ;)

Author: The AIDA team (http://aida.freehep.org/)

OPEN QUESTIONS:

How to treat normalization at user level? Two possibilities:

we have "Gauss" and "NormalizedGauss", the first one user cannot use for ML fit
we have only one "Gauss" function, but it's smart and when normalized, gets rid of one of its parameters

Normalization range might be set directly on the function by the user? Now we set it in the data pipe, Victor thinks that it is not very clear and should be on the function ;)