lti::multivariateGaussian Class Reference

this class generates either one point from a given covarianceMatrix and centre or it generates a given number of points according to these parameters. More...

#include <ltiMultivariateGaussian.h>

Inheritance diagram for lti::multivariateGaussian:

[legend]

Collaboration diagram for lti::multivariateGaussian:

[legend]

List of all members.

Classes
class	parameters
	the parameters for the class multivariateGaussian More...
Public Member Functions
	multivariateGaussian ()
	multivariateGaussian (const multivariateGaussian &other)
virtual	~multivariateGaussian ()
virtual const char *	getTypeName () const
bool	apply (const dvector &mean, const dmatrix &covarianceMatrix, dvector &dest) const
bool	apply (const dvector &mean, const dmatrix &covarianceMatrix, const int &number, dmatrix &dest) const
bool	apply (std::list< dvector > &mean, std::list< dmatrix > &covarianceMatrix, std::list< int > &numbers, std::list< dmatrix > &dest) const
bool	apply (std::list< dvector > &mean, std::list< dmatrix > &covarianceMatrix, std::list< int > &numbers, dmatrix &dest) const
double	draw () const
dmatrix	draw (const int &number) const
multivariateGaussian &	copy (const multivariateGaussian &other)
multivariateGaussian &	operator= (const multivariateGaussian &other)
virtual functor *	clone () const
const parameters &	getParameters () const
Protected Attributes
gaussianDistribution *	gaussFunc
jacobi< double > *	eigenFunc
luDecomposition< double > *	detFunc

Detailed Description

this class generates either one point from a given covarianceMatrix and centre or it generates a given number of points according to these parameters.

The points are drawn from a gaussian distribution

The apply methods expect the parameters directly, the parameters for the draw method must be set in the parameter class

Only draw(const int& number) is implemented. draw() is only reimplemented to make sure that the function of the parent class isn't used. This function return always 0. To draw only one point use draw(const int& number) with number=1

Constructor & Destructor Documentation

lti::multivariateGaussian::multivariateGaussian ( )

default constructor

lti::multivariateGaussian::multivariateGaussian ( const multivariateGaussian & other )

copy constructor

Parameters:

other

the object to be copied

virtual lti::multivariateGaussian::~multivariateGaussian ( ) [virtual]

destructor

Member Function Documentation

bool lti::multivariateGaussian::apply	(	std::list< dvector > &	mean,
		std::list< dmatrix > &	covarianceMatrix,
		std::list< int > &	numbers,
		dmatrix &	dest
	)			const

Apply.

Parameters:

	mean	list of dvector with the centres.
	covarianceMatrix	list of dmatrix with the covariances
	numbers	list of int with the number of points to create in each cluster
	dest	dmatrix with the resulting points in its rows

bool lti::multivariateGaussian::apply	(	std::list< dvector > &	mean,
		std::list< dmatrix > &	covarianceMatrix,
		std::list< int > &	numbers,
		std::list< dmatrix > &	dest
	)			const

Apply.

Parameters:

	mean	list of dvectors with the centres.
	covarianceMatrix	list of dmatrix with the covariances
	numbers	list of int with the number of points to create in each cluster
	dest	list of dmatrix with the resulting points in its rows a one dmatrix for each cluster

bool lti::multivariateGaussian::apply	(	const dvector &	mean,
		const dmatrix &	covarianceMatrix,
		const int &	number,
		dmatrix &	dest
	)			const

creates either one cluster of a set of clusters with the given number of points the covarianceMatrix .

Parameters:

	mean	dvector with the centre.
	covarianceMatrix	dmatrix with the covariances
	number	int with the number of points to create
	dest	dmatrix with the resulting points in its rows

Returns:: true if apply successful or false otherwise.

bool lti::multivariateGaussian::apply	(	const dvector &	mean,
		const dmatrix &	covarianceMatrix,
		dvector &	dest
	)			const

computes one point from a gaussian distribution with the given parameters.

The resulting point is left in dest operates on the given parameter.

Parameters:

	mean	dvector with the centre.
	covarianceMatrix	dmatrix with the covariances
	dest	dvector with the resulting point

Returns:: true if apply successful or false otherwise.

virtual functor* lti::multivariateGaussian::clone ( ) const [virtual]

returns a pointer to a clone of this functor.

Reimplemented from lti::continuousRandomDistribution.

multivariateGaussian& lti::multivariateGaussian::copy ( const multivariateGaussian & other )

copy data of "other" functor.

Parameters:

other

the functor to be copied

Returns:: a reference to this functor object

Reimplemented from lti::continuousRandomDistribution.

dmatrix lti::multivariateGaussian::draw ( const int & number ) const

computes a number of points with the parameters set in the parameters object

Parameters:

number

int with the number of points to create

Returns:: return a dmatrix with the points in its rows.

double lti::multivariateGaussian::draw ( ) const [virtual]

In this context this method doesn't make any sense, so it returns 0.Don't use.

Use draw(const int& number) instead and set number equal to one; this returns also only one point in a Matrix with only one row This function was reimplented, because the function is implemented in the parent class, and this function can't be used at this place.

Reimplemented from lti::continuousRandomDistribution.

const parameters& lti::multivariateGaussian::getParameters ( ) const

returns used parameters

Reimplemented from lti::functor.

virtual const char* lti::multivariateGaussian::getTypeName ( ) const [virtual]

returns the name of this type ("multivariateGaussian")

Reimplemented from lti::continuousRandomDistribution.

multivariateGaussian& lti::multivariateGaussian::operator= ( const multivariateGaussian & other )

alias for copy member

Parameters:

other

the functor to be copied