A dirichlet priori: computes its N'_ijk from a database. More...

#include <agrum/base/database/DirichletPriorFromBN.h>

Inheritance diagram for gum::learning::DirichletPriorFromBN< GUM_SCALAR >:

Collaboration diagram for gum::learning::DirichletPriorFromBN< GUM_SCALAR >:

Public Member Functions
Constructors / Destructors
	DirichletPriorFromBN (const DatabaseTable &learning_db, const BayesNet< GUM_SCALAR > *priorbn)
	default constructor
	DirichletPriorFromBN (const DirichletPriorFromBN &from)
	copy constructor
	DirichletPriorFromBN (DirichletPriorFromBN &&from) noexcept
	move constructor
DirichletPriorFromBN *	clone () const final
	virtual copy constructor
virtual	~DirichletPriorFromBN ()
	destructor
Operators
DirichletPriorFromBN &	operator= (const DirichletPriorFromBN &from)
	copy operator
DirichletPriorFromBN &	operator= (DirichletPriorFromBN &&from)
	move operator
Accessors / Modifiers
PriorType	getType () const final
	returns the type of the prior
bool	isInformative () const final
	indicates whether the prior is tensorly informative
void	setWeight (double weight) final
	sets the weight of the a prior(kind of virtual sample size)
void	addJointPseudoCount (const IdCondSet &idset, std::vector< double > &counts) final
	adds the prior to a counting vector corresponding to the idset
void	addConditioningPseudoCount (const IdCondSet &idset, std::vector< double > &counts) final
	adds the prior to a counting vector defined over the right hand side of the idset
Accessors / Modifiers
double	weight () const
	returns the weight assigned to the prior

Protected Attributes
double	weight_ {1.0}
	the weight of the prior
const DatabaseTable *	database_
	a reference to the database in order to have access to its variables
Bijection< NodeId, std::size_t >	nodeId2columns_
	a mapping from the NodeIds of the variables to the indices of the columns in the database

Private Member Functions
void	_addCountsForJoint_ (Instantiation &Ijoint, const Set< NodeId > &joint, std::vector< double > &counts)

Private Attributes
const BayesNet< GUM_SCALAR > *	_prior_bn_

Detailed Description

template<typename GUM_SCALAR>
class gum::learning::DirichletPriorFromBN< GUM_SCALAR >

A dirichlet priori: computes its N'_ijk from a database.

Definition at line 66 of file DirichletPriorFromBN.h.

Constructor & Destructor Documentation

◆ DirichletPriorFromBN() [1/3]

template<typename GUM_SCALAR>

gum::learning::DirichletPriorFromBN< GUM_SCALAR >::DirichletPriorFromBN	(	const DatabaseTable &	learning_db,
		const BayesNet< GUM_SCALAR > *	priorbn )

default constructor

Parameters

bn	the prior bayesian network from which computation is performed. This is useful to get access to the random variables
nodeId2priorId	a mapping from the ids of the nodes in the graphical model to the corresponding id in the prior BN. An empty nodeId2Columns bijection means that the mapping is an identity.

Referenced by DirichletPriorFromBN(), DirichletPriorFromBN(), ~DirichletPriorFromBN(), clone(), operator=(), and operator=().

Here is the caller graph for this function:

◆ DirichletPriorFromBN() [2/3]

template<typename GUM_SCALAR>

gum::learning::DirichletPriorFromBN< GUM_SCALAR >::DirichletPriorFromBN ( const DirichletPriorFromBN< GUM_SCALAR > & from )

copy constructor

References DirichletPriorFromBN().

Here is the call graph for this function:

◆ DirichletPriorFromBN() [3/3]

template<typename GUM_SCALAR>

gum::learning::DirichletPriorFromBN< GUM_SCALAR >::DirichletPriorFromBN ( DirichletPriorFromBN< GUM_SCALAR > && from )

noexcept

move constructor

References DirichletPriorFromBN().

Here is the call graph for this function:

◆ ~DirichletPriorFromBN()

template<typename GUM_SCALAR>

virtual gum::learning::DirichletPriorFromBN< GUM_SCALAR >::~DirichletPriorFromBN ( )

virtual

destructor

References DirichletPriorFromBN().

Here is the call graph for this function:

Member Function Documentation

◆ _addCountsForJoint_()

template<typename GUM_SCALAR>

void gum::learning::DirichletPriorFromBN< GUM_SCALAR >::_addCountsForJoint_	(	Instantiation &	Ijoint,
		const Set< NodeId > &	joint,
		std::vector< double > &	counts )

private

References _addCountsForJoint_().

Referenced by _addCountsForJoint_().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ addConditioningPseudoCount()

template<typename GUM_SCALAR>

void gum::learning::DirichletPriorFromBN< GUM_SCALAR >::addConditioningPseudoCount	(	const IdCondSet &	idset,
		std::vector< double > &	counts )

finalvirtual

adds the prior to a counting vector defined over the right hand side of the idset

Warning: the method assumes that the size of the vector is exactly the domain size of the joint RHS variables of the idset.

Implements gum::learning::Prior.

References addConditioningPseudoCount().

Referenced by addConditioningPseudoCount().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ addJointPseudoCount()

template<typename GUM_SCALAR>

void gum::learning::DirichletPriorFromBN< GUM_SCALAR >::addJointPseudoCount	(	const IdCondSet &	idset,
		std::vector< double > &	counts )

finalvirtual

adds the prior to a counting vector corresponding to the idset

adds the prior to an already created counting vector defined over the union of the variables on both the left and right hand side of the conditioning bar of the idset.

Warning: the method assumes that the size of the vector is exactly the domain size of the joint variables set.

Implements gum::learning::Prior.

References addJointPseudoCount().

Referenced by addJointPseudoCount().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ clone()

template<typename GUM_SCALAR>

DirichletPriorFromBN * gum::learning::DirichletPriorFromBN< GUM_SCALAR >::clone ( ) const

finalvirtual

virtual copy constructor

Implements gum::learning::Prior.

References DirichletPriorFromBN().

Here is the call graph for this function:

◆ getType()

template<typename GUM_SCALAR>

PriorType gum::learning::DirichletPriorFromBN< GUM_SCALAR >::getType ( ) const

finalvirtual

returns the type of the prior

Implements gum::learning::Prior.

References getType().

Referenced by getType().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ isInformative()

template<typename GUM_SCALAR>

bool gum::learning::DirichletPriorFromBN< GUM_SCALAR >::isInformative ( ) const

finalvirtual

indicates whether the prior is tensorly informative

Basically, only the NoPrior is uninformative. However, it may happen that, under some circumstances, a prior, which is usually not equal to the NoPrior, becomes equal to it (e.g., when the weight is equal to zero). In this case, if the prior can detect this case, it shall inform the classes that use it that it is temporarily uninformative. These classes will then be able to speed-up their code by avoiding to take into account the prior in their computations.

Implements gum::learning::Prior.

References isInformative().

Referenced by isInformative().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ operator=() [1/2]

template<typename GUM_SCALAR>

DirichletPriorFromBN & gum::learning::DirichletPriorFromBN< GUM_SCALAR >::operator= ( const DirichletPriorFromBN< GUM_SCALAR > & from )

copy operator

References DirichletPriorFromBN().

Here is the call graph for this function:

◆ operator=() [2/2]

template<typename GUM_SCALAR>

DirichletPriorFromBN & gum::learning::DirichletPriorFromBN< GUM_SCALAR >::operator= ( DirichletPriorFromBN< GUM_SCALAR > && from )

move operator

References DirichletPriorFromBN().

Here is the call graph for this function:

◆ setWeight()

template<typename GUM_SCALAR>

void gum::learning::DirichletPriorFromBN< GUM_SCALAR >::setWeight ( double weight )

finalvirtual

sets the weight of the a prior(kind of virtual sample size)

Reimplemented from gum::learning::Prior.

References setWeight(), and gum::learning::Prior::weight().

Referenced by setWeight().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ weight()

double gum::learning::Prior::weight ( ) const

inherited

returns the weight assigned to the prior

Referenced by gum::learning::BDeuPrior::setEffectiveSampleSize(), gum::learning::BDeuPrior::setWeight(), gum::learning::DirichletPriorFromBN< GUM_SCALAR >::setWeight(), gum::learning::DirichletPriorFromDatabase::setWeight(), gum::learning::K2Prior::setWeight(), gum::learning::NoPrior::setWeight(), and setWeight().

Here is the caller graph for this function:

Member Data Documentation

◆ _prior_bn_

template<typename GUM_SCALAR>

const BayesNet< GUM_SCALAR >* gum::learning::DirichletPriorFromBN< GUM_SCALAR >::_prior_bn_

private

Definition at line 150 of file DirichletPriorFromBN.h.

◆ database_

const DatabaseTable* gum::learning::Prior::database_

protectedinherited

a reference to the database in order to have access to its variables

Definition at line 161 of file prior.h.

◆ nodeId2columns_

Bijection< NodeId, std::size_t > gum::learning::Prior::nodeId2columns_

protectedinherited

a mapping from the NodeIds of the variables to the indices of the columns in the database

Definition at line 165 of file prior.h.

◆ weight_

double gum::learning::Prior::weight_ {1.0}

protectedinherited

the weight of the prior

Definition at line 158 of file prior.h.

158{1.0};

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

agrum/BN/learning/priors/DirichletPriorFromBN.h

Public Member Functions

Protected Attributes

Private Member Functions

Private Attributes

Detailed Description

Constructor & Destructor Documentation

◆ DirichletPriorFromBN() [1/3]

◆ DirichletPriorFromBN() [2/3]

◆ DirichletPriorFromBN() [3/3]

◆ ~DirichletPriorFromBN()

Member Function Documentation

◆ _addCountsForJoint_()

◆ addConditioningPseudoCount()

◆ addJointPseudoCount()

◆ clone()

◆ getType()

◆ isInformative()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ setWeight()

◆ weight()

Member Data Documentation

◆ _prior_bn_

◆ database_

◆ nodeId2columns_

◆ weight_