The class for estimating parameters of CPTs using Maximum Likelihood. More...

#include <agrum/BN/learning/paramUtils/paramEstimatorML.h>

Inheritance diagram for gum::learning::ParamEstimatorML< ALLOC >:

Collaboration diagram for gum::learning::ParamEstimatorML< ALLOC >:

Public Member Functions
Constructors / Destructors
	ParamEstimatorML (const DBRowGeneratorParser< ALLOC > &parser, const Apriori< ALLOC > &external_apriori, const Apriori< ALLOC > &_score_internal_apriori, const std::vector< std::pair< std::size_t, std::size_t >, ALLOC< std::pair< std::size_t, std::size_t > > > &ranges, const Bijection< NodeId, std::size_t, ALLOC< std::size_t > > &nodeId2columns=Bijection< NodeId, std::size_t, ALLOC< std::size_t > >(), const allocator_type &alloc=allocator_type())
	default constructor More...

	ParamEstimatorML (const DBRowGeneratorParser< ALLOC > &parser, const Apriori< ALLOC > &external_apriori, const Apriori< ALLOC > &_score_internal_apriori, const Bijection< NodeId, std::size_t, ALLOC< std::size_t > > &nodeId2columns=Bijection< NodeId, std::size_t, ALLOC< std::size_t > >(), const allocator_type &alloc=allocator_type())
	default constructor More...

	ParamEstimatorML (const ParamEstimatorML< ALLOC > &from)
	copy constructor More...

	ParamEstimatorML (const ParamEstimatorML< ALLOC > &from, const allocator_type &alloc)
	copy constructor with a given allocator More...

	ParamEstimatorML (ParamEstimatorML< ALLOC > &&from)
	move constructor More...

	ParamEstimatorML (ParamEstimatorML< ALLOC > &&from, const allocator_type &alloc)
	move constructor with a given allocator More...

virtual ParamEstimatorML< ALLOC > *	clone () const
	virtual copy constructor More...

virtual ParamEstimatorML< ALLOC > *	clone (const allocator_type &alloc) const
	virtual copy constructor with a given allocator More...

virtual	~ParamEstimatorML ()
	destructor More...

Operators
ParamEstimatorML< ALLOC > &	operator= (const ParamEstimatorML< ALLOC > &from)
	copy operator More...

ParamEstimatorML< ALLOC > &	operator= (ParamEstimatorML< ALLOC > &&from)
	move operator More...

Accessors / Modifiers
virtual std::vector< double, ALLOC< double > >	parameters (const NodeId target_node, const std::vector< NodeId, ALLOC< NodeId > > &conditioning_nodes)
	returns the CPT's parameters corresponding to a given nodeset More...

Accessors / Modifiers
virtual void	clear ()
	clears all the data structures from memory More...

virtual void	setMaxNbThreads (std::size_t nb) const
	changes the max number of threads used to parse the database More...

virtual std::size_t	nbThreads () const
	returns the number of threads used to parse the database More...

virtual void	setMinNbRowsPerThread (const std::size_t nb) const
	changes the number min of rows a thread should process in a multithreading context More...

virtual std::size_t	minNbRowsPerThread () const
	returns the minimum of rows that each thread should process More...

template<template< typename > class XALLOC>
void	setRanges (const std::vector< std::pair< std::size_t, std::size_t >, XALLOC< std::pair< std::size_t, std::size_t > > > &new_ranges)
	sets new ranges to perform the countings used by the parameter estimator More...

void	clearRanges ()
	reset the ranges to the one range corresponding to the whole database More...

const std::vector< std::pair< std::size_t, std::size_t >, ALLOC< std::pair< std::size_t, std::size_t > > > &	ranges () const
	returns the current ranges More...

std::vector< double, ALLOC< double > >	parameters (const NodeId target_node)
	returns the CPT's parameters corresponding to a given target node More...

template<typename GUM_SCALAR >
void	setParameters (const NodeId target_node, const std::vector< NodeId, ALLOC< NodeId > > &conditioning_nodes, Potential< GUM_SCALAR > &pot)
	sets the CPT's parameters corresponding to a given Potential More...

const Bijection< NodeId, std::size_t, ALLOC< std::size_t > > &	nodeId2Columns () const
	returns the mapping from ids to column positions in the database More...

const DatabaseTable< ALLOC > &	database () const
	returns the database on which we perform the counts More...

template<typename GUM_SCALAR >
void	setBayesNet (const BayesNet< GUM_SCALAR > &new_bn)
	assign a new Bayes net to all the counter's generators depending on a BN More...

allocator_type	getAllocator () const
	returns the allocator used by the score More...

Public Types
using	allocator_type = ALLOC< NodeId >
	type for the allocators passed in arguments of methods More...

Protected Attributes
Apriori< ALLOC > *	external_apriori_ {nullptr}
	an external a priori More...

Apriori< ALLOC > *	score_internal_apriori_ {nullptr}
	if a score was used for learning the structure of the PGM, this is the a priori internal to the score More...

RecordCounter< ALLOC >	counter_
	the record counter used to parse the database More...

const std::vector< NodeId, ALLOC< NodeId > >	empty_nodevect_
	an empty vector of nodes, used for empty conditioning More...

Detailed Description

template<template< typename > class ALLOC = std::allocator>
class gum::learning::ParamEstimatorML< ALLOC >

The class for estimating parameters of CPTs using Maximum Likelihood.

Definition at line 45 of file paramEstimatorML.h.

Member Typedef Documentation

◆ allocator_type

template<template< typename > class ALLOC = std::allocator>

using gum::learning::ParamEstimatorML< ALLOC >::allocator_type = ALLOC< NodeId >

type for the allocators passed in arguments of methods

Definition at line 48 of file paramEstimatorML.h.

Constructor & Destructor Documentation

◆ ParamEstimatorML() [1/6]

template<template< typename > class ALLOC = std::allocator>

gum::learning::ParamEstimatorML< ALLOC >::ParamEstimatorML	(	const DBRowGeneratorParser< ALLOC > &	parser,
		const Apriori< ALLOC > &	external_apriori,
		const Apriori< ALLOC > &	_score_internal_apriori,
		const std::vector< std::pair< std::size_t, std::size_t >, ALLOC< std::pair< std::size_t, std::size_t > > > &	ranges,
		const Bijection< NodeId, std::size_t, ALLOC< std::size_t > > &	nodeId2columns = `Bijection< NodeId, std::size_t, ALLOC< std::size_t > >()`,
		const allocator_type &	alloc = `allocator_type()`
	)

default constructor

Parameters

parser	the parser used to parse the database
external_apriori	An apriori that we add to the computation of the score
score_internal_apriori	The apriori within the score used to learn the data structure (might be a NoApriori)
ranges	a set of pairs {(X1,Y1),...,(Xn,Yn)} of database's rows indices. The countings are then performed only on the union of the rows [Xi,Yi), i in {1,...,n}. This is useful, e.g, when performing cross validation tasks, in which part of the database should be ignored. An empty set of ranges is equivalent to an interval [X,Y) ranging over the whole database.
nodeId2Columns	a mapping from the ids of the nodes in the graphical model to the corresponding column in the DatabaseTable parsed by the parser. This enables estimating from a database in which variable A corresponds to the 2nd column the parameters of a BN in which variable A has a NodeId of 5. An empty nodeId2Columns bijection means that the mapping is an identity, i.e., the value of a NodeId is equal to the index of the column in the DatabaseTable.
alloc	the allocator used to allocate the structures within the Score.

Warning: If nodeId2columns is not empty, then only the scores over the ids belonging to this bijection can be computed: applying method score() over other ids will raise exception NotFound.

◆ ParamEstimatorML() [2/6]

template<template< typename > class ALLOC = std::allocator>

gum::learning::ParamEstimatorML< ALLOC >::ParamEstimatorML	(	const DBRowGeneratorParser< ALLOC > &	parser,
		const Apriori< ALLOC > &	external_apriori,
		const Apriori< ALLOC > &	_score_internal_apriori,
		const Bijection< NodeId, std::size_t, ALLOC< std::size_t > > &	nodeId2columns = `Bijection< NodeId, std::size_t, ALLOC< std::size_t > >()`,
		const allocator_type &	alloc = `allocator_type()`
	)

default constructor

Parameters

parser	the parser used to parse the database
external_apriori	An apriori that we add to the computation of the score
score_internal_apriori	The apriori within the score used to learn the data structure (might be a NoApriori)
nodeId2Columns	a mapping from the ids of the nodes in the graphical model to the corresponding column in the DatabaseTable parsed by the parser. This enables estimating from a database in which variable A corresponds to the 2nd column the parameters of a BN in which variable A has a NodeId of 5. An empty nodeId2Columns bijection means that the mapping is an identity, i.e., the value of a NodeId is equal to the index of the column in the DatabaseTable.
alloc	the allocator used to allocate the structures within the Score.

Warning: If nodeId2columns is not empty, then only the scores over the ids belonging to this bijection can be computed: applying method score() over other ids will raise exception NotFound.

◆ ParamEstimatorML() [3/6]

template<template< typename > class ALLOC = std::allocator>

gum::learning::ParamEstimatorML< ALLOC >::ParamEstimatorML ( const ParamEstimatorML< ALLOC > & from )

copy constructor

◆ ParamEstimatorML() [4/6]

template<template< typename > class ALLOC = std::allocator>

gum::learning::ParamEstimatorML< ALLOC >::ParamEstimatorML	(	const ParamEstimatorML< ALLOC > &	from,
		const allocator_type &	alloc
	)

copy constructor with a given allocator

◆ ParamEstimatorML() [5/6]

template<template< typename > class ALLOC = std::allocator>

gum::learning::ParamEstimatorML< ALLOC >::ParamEstimatorML ( ParamEstimatorML< ALLOC > && from )

move constructor

◆ ParamEstimatorML() [6/6]

template<template< typename > class ALLOC = std::allocator>

gum::learning::ParamEstimatorML< ALLOC >::ParamEstimatorML	(	ParamEstimatorML< ALLOC > &&	from,
		const allocator_type &	alloc
	)

move constructor with a given allocator

◆ ~ParamEstimatorML()

template<template< typename > class ALLOC = std::allocator>

virtual gum::learning::ParamEstimatorML< ALLOC >::~ParamEstimatorML ( )

virtual

destructor

Member Function Documentation

◆ clear()

template<template< typename > class ALLOC = std::allocator>

virtual void gum::learning::ParamEstimator< ALLOC >::clear ( )

virtualinherited

clears all the data structures from memory

◆ clearRanges()

template<template< typename > class ALLOC = std::allocator>

void gum::learning::ParamEstimator< ALLOC >::clearRanges ( )

inherited

reset the ranges to the one range corresponding to the whole database

◆ clone() [1/2]

template<template< typename > class ALLOC = std::allocator>

virtual ParamEstimatorML< ALLOC >* gum::learning::ParamEstimatorML< ALLOC >::clone ( ) const

virtual

virtual copy constructor

Implements gum::learning::ParamEstimator< ALLOC >.

◆ clone() [2/2]

template<template< typename > class ALLOC = std::allocator>

virtual ParamEstimatorML< ALLOC >* gum::learning::ParamEstimatorML< ALLOC >::clone ( const allocator_type & alloc ) const

virtual

virtual copy constructor with a given allocator

Implements gum::learning::ParamEstimator< ALLOC >.

◆ database()

template<template< typename > class ALLOC = std::allocator>

const DatabaseTable< ALLOC >& gum::learning::ParamEstimator< ALLOC >::database ( ) const

inherited

returns the database on which we perform the counts

◆ getAllocator()

template<template< typename > class ALLOC = std::allocator>

allocator_type gum::learning::ParamEstimator< ALLOC >::getAllocator ( ) const

inherited

returns the allocator used by the score

◆ minNbRowsPerThread()

template<template< typename > class ALLOC = std::allocator>

virtual std::size_t gum::learning::ParamEstimator< ALLOC >::minNbRowsPerThread ( ) const

virtualinherited

returns the minimum of rows that each thread should process

◆ nbThreads()

template<template< typename > class ALLOC = std::allocator>

virtual std::size_t gum::learning::ParamEstimator< ALLOC >::nbThreads ( ) const

virtualinherited

returns the number of threads used to parse the database

◆ nodeId2Columns()

template<template< typename > class ALLOC = std::allocator>

const Bijection< NodeId, std::size_t, ALLOC< std::size_t > >& gum::learning::ParamEstimator< ALLOC >::nodeId2Columns ( ) const

inherited

returns the mapping from ids to column positions in the database

Warning: An empty nodeId2Columns bijection means that the mapping is an identity, i.e., the value of a NodeId is equal to the index of the column in the DatabaseTable.

◆ operator=() [1/2]

template<template< typename > class ALLOC = std::allocator>

ParamEstimatorML< ALLOC >& gum::learning::ParamEstimatorML< ALLOC >::operator= ( const ParamEstimatorML< ALLOC > & from )

copy operator

◆ operator=() [2/2]

template<template< typename > class ALLOC = std::allocator>

ParamEstimatorML< ALLOC >& gum::learning::ParamEstimatorML< ALLOC >::operator= ( ParamEstimatorML< ALLOC > && from )

move operator

◆ parameters() [1/2]

template<template< typename > class ALLOC = std::allocator>

virtual std::vector< double, ALLOC< double > > gum::learning::ParamEstimatorML< ALLOC >::parameters	(	const NodeId	target_node,
		const std::vector< NodeId, ALLOC< NodeId > > &	conditioning_nodes
	)

virtual

returns the CPT's parameters corresponding to a given nodeset

The vector contains the parameters of an n-dimensional CPT. The distribution of the dimensions of the CPT within the vector is as follows: first, there is the target node, then the conditioning nodes (in the order in which they were specified).

Exceptions

DatabaseError is raised if some values of the conditioning sets were not observed in the database.

Implements gum::learning::ParamEstimator< ALLOC >.

◆ parameters() [2/2]

template<template< typename > class ALLOC = std::allocator>

std::vector< double, ALLOC< double > > gum::learning::ParamEstimator< ALLOC >::parameters ( const NodeId target_node )

inherited

returns the CPT's parameters corresponding to a given target node

◆ ranges()

template<template< typename > class ALLOC = std::allocator>

const std::vector< std::pair< std::size_t, std::size_t >, ALLOC< std::pair< std::size_t, std::size_t > > >& gum::learning::ParamEstimator< ALLOC >::ranges ( ) const

inherited

returns the current ranges

◆ setBayesNet()

template<template< typename > class ALLOC = std::allocator>

template<typename GUM_SCALAR >

void gum::learning::ParamEstimator< ALLOC >::setBayesNet ( const BayesNet< GUM_SCALAR > & new_bn )

inherited

assign a new Bayes net to all the counter's generators depending on a BN

Typically, generators based on EM or K-means depend on a model to compute correctly their outputs. Method setBayesNet enables to update their BN model.

◆ setMaxNbThreads()

template<template< typename > class ALLOC = std::allocator>

virtual void gum::learning::ParamEstimator< ALLOC >::setMaxNbThreads ( std::size_t nb ) const

virtualinherited

changes the max number of threads used to parse the database

◆ setMinNbRowsPerThread()

template<template< typename > class ALLOC = std::allocator>

virtual void gum::learning::ParamEstimator< ALLOC >::setMinNbRowsPerThread ( const std::size_t nb ) const

virtualinherited

changes the number min of rows a thread should process in a multithreading context

When computing score, several threads are used by record counters to perform countings on the rows of the database, the MinNbRowsPerThread method indicates how many rows each thread should at least process. This is used to compute the number of threads actually run. This number is equal to the min between the max number of threads allowed and the number of records in the database divided by nb.

◆ setParameters()

template<template< typename > class ALLOC = std::allocator>

template<typename GUM_SCALAR >

void gum::learning::ParamEstimator< ALLOC >::setParameters	(	const NodeId	target_node,
		const std::vector< NodeId, ALLOC< NodeId > > &	conditioning_nodes,
		Potential< GUM_SCALAR > &	pot
	)

inherited

sets the CPT's parameters corresponding to a given Potential

The potential is assumed to be a conditional probability, the first variable of its variablesSequence() being the target variable, the other ones being on the right side of the conditioning bar.

◆ setRanges()

template<template< typename > class ALLOC = std::allocator>

template<template< typename > class XALLOC>

void gum::learning::ParamEstimator< ALLOC >::setRanges ( const std::vector< std::pair< std::size_t, std::size_t >, XALLOC< std::pair< std::size_t, std::size_t > > > & new_ranges )

inherited

sets new ranges to perform the countings used by the parameter estimator

Parameters

ranges a set of pairs {(X1,Y1),...,(Xn,Yn)} of database's rows indices. The countings are then performed only on the union of the rows [Xi,Yi), i in {1,...,n}. This is useful, e.g, when performing cross validation tasks, in which part of the database should be ignored. An empty set of ranges is equivalent to an interval [X,Y) ranging over the whole database.

Member Data Documentation

◆ counter_

template<template< typename > class ALLOC = std::allocator>

RecordCounter< ALLOC > gum::learning::ParamEstimator< ALLOC >::counter_

protectedinherited

the record counter used to parse the database

Definition at line 242 of file paramEstimator.h.

◆ empty_nodevect_

template<template< typename > class ALLOC = std::allocator>

const std::vector< NodeId, ALLOC< NodeId > > gum::learning::ParamEstimator< ALLOC >::empty_nodevect_

protectedinherited

an empty vector of nodes, used for empty conditioning

Definition at line 245 of file paramEstimator.h.

◆ external_apriori_

template<template< typename > class ALLOC = std::allocator>

Apriori< ALLOC >* gum::learning::ParamEstimator< ALLOC >::external_apriori_ {nullptr}

protectedinherited

an external a priori

Definition at line 235 of file paramEstimator.h.

◆ score_internal_apriori_

template<template< typename > class ALLOC = std::allocator>

Apriori< ALLOC >* gum::learning::ParamEstimator< ALLOC >::score_internal_apriori_ {nullptr}

protectedinherited

if a score was used for learning the structure of the PGM, this is the a priori internal to the score

Definition at line 239 of file paramEstimator.h.

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

agrum/BN/learning/paramUtils/paramEstimatorML.h

Public Member Functions

Public Types

Protected Attributes

Detailed Description

template<template< typename > class ALLOC = std::allocator> class gum::learning::ParamEstimatorML< ALLOC >

Member Typedef Documentation

◆ allocator_type

Constructor & Destructor Documentation

◆ ParamEstimatorML() [1/6]

◆ ParamEstimatorML() [2/6]

◆ ParamEstimatorML() [3/6]

◆ ParamEstimatorML() [4/6]

◆ ParamEstimatorML() [5/6]

◆ ParamEstimatorML() [6/6]

◆ ~ParamEstimatorML()

Member Function Documentation

◆ clear()

◆ clearRanges()

◆ clone() [1/2]

◆ clone() [2/2]

◆ database()

◆ getAllocator()

◆ minNbRowsPerThread()

◆ nbThreads()

◆ nodeId2Columns()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ parameters() [1/2]

◆ parameters() [2/2]

◆ ranges()

◆ setBayesNet()

◆ setMaxNbThreads()

◆ setMinNbRowsPerThread()

◆ setParameters()

◆ setRanges()

Member Data Documentation

◆ counter_

◆ empty_nodevect_

◆ external_apriori_

◆ score_internal_apriori_

template<template< typename > class ALLOC = std::allocator>
class gum::learning::ParamEstimatorML< ALLOC >