the class for computing G2 independence test scores More...

#include <agrum/BN/learning/scores_and_tests/indepTestG2.h>

Inheritance diagram for gum::learning::IndepTestG2< ALLOC >:

Collaboration diagram for gum::learning::IndepTestG2< ALLOC >:

Public Member Functions
Constructors / Destructors
	IndepTestG2 (const DBRowGeneratorParser< ALLOC > &parser, const Apriori< ALLOC > &external_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...

	IndepTestG2 (const DBRowGeneratorParser< ALLOC > &parser, const Apriori< ALLOC > &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...

	IndepTestG2 (const IndepTestG2< ALLOC > &from)
	copy constructor More...

	IndepTestG2 (const IndepTestG2< ALLOC > &from, const allocator_type &alloc)
	copy constructor with a given allocator More...

	IndepTestG2 (IndepTestG2< ALLOC > &&from)
	move constructor More...

	IndepTestG2 (IndepTestG2< ALLOC > &&from, const allocator_type &alloc)
	move constructor with a given allocator More...

virtual IndepTestG2< ALLOC > *	clone () const
	virtual copy constructor More...

virtual IndepTestG2< ALLOC > *	clone (const allocator_type &alloc) const
	virtual copy constructor with a given allocator More...

virtual	~IndepTestG2 ()
	destructor More...

Operators
IndepTestG2< ALLOC > &	operator= (const IndepTestG2< ALLOC > &from)
	copy operator More...

IndepTestG2< ALLOC > &	operator= (IndepTestG2< ALLOC > &&from)
	move operator More...

std::pair< double, double >	statistics (NodeId var1, NodeId var2, const std::vector< NodeId, ALLOC< NodeId > > &rhs_ids={})
	get the pair <G2statistic,pvalue> for a test var1 indep var2 given rhs_ids More...

Accessors / Modifiers
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 independence test 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...

double	score (const NodeId var1, const NodeId var2)
	returns the score of a pair of nodes More...

double	score (const NodeId var1, const NodeId var2, const std::vector< NodeId, ALLOC< NodeId > > &rhs_ids)
	returns the score of a pair of nodes given some other nodes More...

virtual void	clear ()
	clears all the data structures from memory, including the cache More...

virtual void	clearCache ()
	clears the current cache More...

virtual void	useCache (const bool on_off)
	turn on/off the use of a cache of the previously computed score More...

const Bijection< NodeId, std::size_t, ALLOC< std::size_t > > &	nodeId2Columns () const
	return the mapping between the columns of the database and the node ids More...

const DatabaseTable< ALLOC > &	database () const
	return the database used by the score 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
const double	one_log2_ {M_LOG2E}
	1 / log(2) More...

Apriori< ALLOC > *	apriori_ {nullptr}
	the expert knowledge a priori we add to the contingency tables More...

RecordCounter< ALLOC >	counter_
	the record counter used for the countings over discrete variables More...

ScoringCache< ALLOC >	cache_
	the scoring cache More...

bool	use_cache_ {true}
	a Boolean indicating whether we wish to use the cache More...

const std::vector< NodeId, ALLOC< NodeId > >	empty_ids_
	an empty vector More...

Protected Member Functions
virtual double	score_ (const IdCondSet< ALLOC > &idset) final
	returns the score for a given IdCondSet More...

std::pair< double, double >	statistics_ (const IdCondSet< ALLOC > &idset)
	compute the pair <G2 statistic,pvalue> More...

std::vector< double, ALLOC< double > >	marginalize_ (const std::size_t node_2_marginalize, const std::size_t X_size, const std::size_t Y_size, const std::size_t Z_size, const std::vector< double, ALLOC< double > > &N_xyz) const
	returns a counting vector where variables are marginalized from N_xyz More...

Detailed Description

template<template< typename > class ALLOC = std::allocator>
class gum::learning::IndepTestG2< ALLOC >

the class for computing G2 independence test scores

Definition at line 47 of file indepTestG2.h.

Member Typedef Documentation

◆ allocator_type

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

using gum::learning::IndepTestG2< ALLOC >::allocator_type = ALLOC< NodeId >

type for the allocators passed in arguments of methods

Definition at line 50 of file indepTestG2.h.

Constructor & Destructor Documentation

◆ IndepTestG2() [1/6]

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

gum::learning::IndepTestG2< ALLOC >::IndepTestG2	(	const DBRowGeneratorParser< ALLOC > &	parser,
		const Apriori< ALLOC > &	external_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 (this should come from expert knowledge): this consists in adding numbers to countings in the contingency tables
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.

◆ IndepTestG2() [2/6]

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

gum::learning::IndepTestG2< ALLOC >::IndepTestG2	(	const DBRowGeneratorParser< ALLOC > &	parser,
		const Apriori< ALLOC > &	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
apriori	An apriori that we add to the computation of the score
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.

◆ IndepTestG2() [3/6]

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

gum::learning::IndepTestG2< ALLOC >::IndepTestG2 ( const IndepTestG2< ALLOC > & from )

copy constructor

◆ IndepTestG2() [4/6]

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

gum::learning::IndepTestG2< ALLOC >::IndepTestG2	(	const IndepTestG2< ALLOC > &	from,
		const allocator_type &	alloc
	)

copy constructor with a given allocator

◆ IndepTestG2() [5/6]

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

gum::learning::IndepTestG2< ALLOC >::IndepTestG2 ( IndepTestG2< ALLOC > && from )

move constructor

◆ IndepTestG2() [6/6]

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

gum::learning::IndepTestG2< ALLOC >::IndepTestG2	(	IndepTestG2< ALLOC > &&	from,
		const allocator_type &	alloc
	)

move constructor with a given allocator

◆ ~IndepTestG2()

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

virtual gum::learning::IndepTestG2< ALLOC >::~IndepTestG2 ( )

virtual

destructor

Member Function Documentation

◆ clear()

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

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

virtualinherited

clears all the data structures from memory, including the cache

Reimplemented in gum::learning::KNML< ALLOC >.

◆ clearCache()

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

virtual void gum::learning::IndependenceTest< ALLOC >::clearCache ( )

virtualinherited

clears the current cache

Reimplemented in gum::learning::KNML< ALLOC >.

◆ clearRanges()

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

void gum::learning::IndependenceTest< 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 IndepTestG2< ALLOC >* gum::learning::IndepTestG2< ALLOC >::clone ( ) const

virtual

virtual copy constructor

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

◆ clone() [2/2]

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

virtual IndepTestG2< ALLOC >* gum::learning::IndepTestG2< ALLOC >::clone ( const allocator_type & alloc ) const

virtual

virtual copy constructor with a given allocator

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

◆ database()

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

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

inherited

return the database used by the score

◆ getAllocator()

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

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

inherited

returns the allocator used by the score

◆ marginalize_()

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

std::vector< double, ALLOC< double > > gum::learning::IndependenceTest< ALLOC >::marginalize_	(	const std::size_t	node_2_marginalize,
		const std::size_t	X_size,
		const std::size_t	Y_size,
		const std::size_t	Z_size,
		const std::vector< double, ALLOC< double > > &	N_xyz
	)		const

protectedinherited

returns a counting vector where variables are marginalized from N_xyz

Parameters

node_2_marginalize	indicates which node(s) shall be marginalized: 0 means that X should be marginalized 1 means that Y should be marginalized 2 means that Z should be marginalized
X_size	the domain size of variable X
Y_size	the domain size of variable Y
Z_size	the domain size of the set of conditioning variables Z
N_xyz	a counting vector of dimension X * Y * Z (in this order)

◆ minNbRowsPerThread()

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

virtual std::size_t gum::learning::IndependenceTest< 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::IndependenceTest< 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::IndependenceTest< ALLOC >::nodeId2Columns ( ) const

inherited

return the mapping between the columns of the database and the node ids

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>

IndepTestG2< ALLOC >& gum::learning::IndepTestG2< ALLOC >::operator= ( const IndepTestG2< ALLOC > & from )

copy operator

◆ operator=() [2/2]

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

IndepTestG2< ALLOC >& gum::learning::IndepTestG2< ALLOC >::operator= ( IndepTestG2< ALLOC > && from )

move operator

◆ 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::IndependenceTest< ALLOC >::ranges ( ) const

inherited

returns the current ranges

◆ score() [1/2]

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

double gum::learning::IndependenceTest< ALLOC >::score	(	const NodeId	var1,
		const NodeId	var2
	)

inherited

returns the score of a pair of nodes

◆ score() [2/2]

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

double gum::learning::IndependenceTest< ALLOC >::score	(	const NodeId	var1,
		const NodeId	var2,
		const std::vector< NodeId, ALLOC< NodeId > > &	rhs_ids
	)

inherited

returns the score of a pair of nodes given some other nodes

Parameters

var1	the first variable on the left side of the conditioning bar
var2	the second variable on the left side of the conditioning bar
rhs_ids	the set of variables on the right side of the conditioning bar

◆ score_()

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

virtual double gum::learning::IndepTestG2< ALLOC >::score_ ( const IdCondSet< ALLOC > & idset )

finalprotectedvirtual

returns the score for a given IdCondSet

Exceptions

OperationNotAllowed is raised if the score does not support calling method score such an idset (due to too many/too few variables in the left hand side or the right hand side of the idset).

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

◆ setMaxNbThreads()

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

virtual void gum::learning::IndependenceTest< 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::IndependenceTest< 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.

◆ setRanges()

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

template<template< typename > class XALLOC>

void gum::learning::IndependenceTest< 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 independence test

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.

◆ statistics()

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

std::pair< double, double > gum::learning::IndepTestG2< ALLOC >::statistics	(	NodeId	var1,
		NodeId	var2,
		const std::vector< NodeId, ALLOC< NodeId > > &	rhs_ids = `{}`
	)

get the pair <G2statistic,pvalue> for a test var1 indep var2 given rhs_ids

◆ statistics_()

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

std::pair< double, double > gum::learning::IndepTestG2< ALLOC >::statistics_ ( const IdCondSet< ALLOC > & idset )

protected

compute the pair <G2 statistic,pvalue>

◆ useCache()

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

virtual void gum::learning::IndependenceTest< ALLOC >::useCache ( const bool on_off )

virtualinherited

turn on/off the use of a cache of the previously computed score

Reimplemented in gum::learning::KNML< ALLOC >.

Member Data Documentation

◆ apriori_

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

Apriori< ALLOC >* gum::learning::IndependenceTest< ALLOC >::apriori_ {nullptr}

protectedinherited

the expert knowledge a priori we add to the contingency tables

Definition at line 215 of file independenceTest.h.

◆ cache_

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

ScoringCache< ALLOC > gum::learning::IndependenceTest< ALLOC >::cache_

protectedinherited

the scoring cache

Definition at line 221 of file independenceTest.h.

◆ counter_

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

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

protectedinherited

the record counter used for the countings over discrete variables

Definition at line 218 of file independenceTest.h.

◆ empty_ids_

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

const std::vector< NodeId, ALLOC< NodeId > > gum::learning::IndependenceTest< ALLOC >::empty_ids_

protectedinherited

an empty vector

Definition at line 227 of file independenceTest.h.

◆ one_log2_

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

const double gum::learning::IndependenceTest< ALLOC >::one_log2_ {M_LOG2E}

protectedinherited

1 / log(2)

Definition at line 212 of file independenceTest.h.

◆ use_cache_

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

bool gum::learning::IndependenceTest< ALLOC >::use_cache_ {true}

protectedinherited

a Boolean indicating whether we wish to use the cache

Definition at line 224 of file independenceTest.h.

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

agrum/tools/stattests/indepTestG2.h

Public Member Functions

Public Types

Protected Attributes

Protected Member Functions

Detailed Description

template<template< typename > class ALLOC = std::allocator> class gum::learning::IndepTestG2< ALLOC >

Member Typedef Documentation

◆ allocator_type

Constructor & Destructor Documentation

◆ IndepTestG2() [1/6]

◆ IndepTestG2() [2/6]

◆ IndepTestG2() [3/6]

◆ IndepTestG2() [4/6]

◆ IndepTestG2() [5/6]

◆ IndepTestG2() [6/6]

◆ ~IndepTestG2()

Member Function Documentation

◆ clear()

◆ clearCache()

◆ clearRanges()

◆ clone() [1/2]

◆ clone() [2/2]

◆ database()

◆ getAllocator()

◆ marginalize_()

◆ minNbRowsPerThread()

◆ nbThreads()

◆ nodeId2Columns()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ ranges()

◆ score() [1/2]

◆ score() [2/2]

◆ score_()

◆ setMaxNbThreads()

◆ setMinNbRowsPerThread()

◆ setRanges()

◆ statistics()

◆ statistics_()

◆ useCache()

Member Data Documentation

◆ apriori_

◆ cache_

◆ counter_

◆ empty_ids_

◆ one_log2_

◆ use_cache_

template<template< typename > class ALLOC = std::allocator>
class gum::learning::IndepTestG2< ALLOC >