Class representing a PDF on a discrete variable. More...

#include <discretepdf.h>

Inheritance diagram for BFL::DiscretePdf:

Public Member Functions
virtual DiscretePdf *	Clone () const
	Clone function.
	DiscretePdf (unsigned int num_states=0)
	Constructor (dimension = number of classes) An equal probability is set for all classes.
	DiscretePdf (const DiscretePdf &)
	Copy Constructor.
int	MostProbableStateGet ()
	Get the index of the most probable state.
unsigned int	NumStatesGet () const
	Get the number of discrete States.
vector< Probability >	ProbabilitiesGet () const
	Get all probabilities.
bool	ProbabilitiesSet (vector< Probability > &values)
	Set all probabilities.
Probability	ProbabilityGet (const int &state) const
	Implementation of virtual base class method.
bool	ProbabilitySet (int state, Probability a)
	Function to change/set the probability of a single state.
bool	SampleFrom (vector< Sample< int > > &list_samples, const unsigned int num_samples, int method=DEFAULT, void *args=NULL) const
bool	SampleFrom (Sample< int > &one_sample, int method=DEFAULT, void *args=NULL) const
	Draw 1 sample from the Pdf:
virtual	~DiscretePdf ()
	Destructor.
Protected Member Functions
bool	CumPDFUpdate ()
	Updates the cumPDF.
bool	NormalizeProbs ()
	Normalize all the probabilities (eg. after setting a probability)
Protected Attributes
vector< double >	_CumPDF
	STL-vector containing the Cumulative PDF (for efficient sampling)
unsigned int	_num_states
	The number of discrete state.
vector< Probability > *	_Values_p
	Pointer to the discrete PDF-values, the sum of the elements = 1.

Detailed Description

Class representing a PDF on a discrete variable.

This class is an instantation from the template class Pdf, with added methods to get a set the probability of a certain discrete value (methods only relevant for discrete pdfs)

Definition at line 34 of file discretepdf.h.

Constructor & Destructor Documentation

BFL::DiscretePdf::DiscretePdf ( unsigned int num_states = 0 )

Constructor (dimension = number of classes) An equal probability is set for all classes.

Parameters:

num_states number of different classes or states

BFL::DiscretePdf::DiscretePdf ( const DiscretePdf & )

Copy Constructor.

virtual BFL::DiscretePdf::~DiscretePdf ( ) [virtual]

Destructor.

Member Function Documentation

virtual DiscretePdf* BFL::DiscretePdf::Clone ( ) const [virtual]

Clone function.

Implements BFL::BFL::Pdf< int >.

bool BFL::DiscretePdf::CumPDFUpdate ( ) [protected]

Updates the cumPDF.

int BFL::DiscretePdf::MostProbableStateGet ( )

Get the index of the most probable state.

bool BFL::DiscretePdf::NormalizeProbs ( ) [protected]

Normalize all the probabilities (eg. after setting a probability)

unsigned int BFL::DiscretePdf::NumStatesGet ( ) const

Get the number of discrete States.

vector<Probability> BFL::DiscretePdf::ProbabilitiesGet ( ) const

Get all probabilities.

bool BFL::DiscretePdf::ProbabilitiesSet ( vector< Probability > & values )

Set all probabilities.

Parameters:

values vector<Probability> containing the new probability values. The sum of the probabilities of this list is not required to be one since the normalization is automatically carried out.

Probability BFL::DiscretePdf::ProbabilityGet ( const int & state ) const [virtual]

Implementation of virtual base class method.

Reimplemented from BFL::BFL::Pdf< int >.

bool BFL::DiscretePdf::ProbabilitySet	(	int	state,
		Probability	a
	)

Function to change/set the probability of a single state.

Changes the probabilities such that AFTER normalization the probability of the state "state" is equal to the probability a

Parameters:

state	number of state of which the probability will be set
a	probability value to which the probability of state "state" will be set (must be <= 1)

bool BFL::DiscretePdf::SampleFrom	(	vector< Sample< int > > &	list_samples,
		const unsigned int	num_samples,
		int	method = `DEFAULT`,
		void *	args = `NULL`
	)		const

bool BFL::DiscretePdf::SampleFrom	(	Sample< int > &	one_sample,
		int	method = `DEFAULT`,
		void *	args = `NULL`
	)		const `[virtual]`

Draw 1 sample from the Pdf:

There's no need to create a list for only 1 sample!

Parameters:

one_sample	sample that will contain result of sampling
method	Sampling method to be used. Each sampling method is currently represented by a #define statement, eg. #define BOXMULLER 1
args	Pointer to a struct representing extra sample arguments