The basic class for computing the next graph changes possible in a structure learning algorithm. More...

#include <graphChangesGeneratorOnSubDiGraph.h>

Inheritance diagram for gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >:

Collaboration diagram for gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >:

Public Types
using	iterator = typename Set< GraphChange >::const_iterator
	the iterator for parsing the list of possible graph change operators
using	const_iterator = iterator
	the const iterator for parsing the list of graph change operators

Public Member Functions
Constructors / Destructors
	GraphChangesGeneratorOnSubDiGraph (STRUCT_CONSTRAINT &constraint)
	default constructor
	GraphChangesGeneratorOnSubDiGraph (const GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > &from)
	copy constructor
	GraphChangesGeneratorOnSubDiGraph (GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > &&from)
	move operator
virtual	~GraphChangesGeneratorOnSubDiGraph ()
	destructor
Operators
GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > &	operator= (const GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > &from)
	copy operator
GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > &	operator= (GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > &&from)
	move operator
Iterators
iterator	begin () const
	returns an (unsafe) iterator on the beginning of the list of operators
const iterator &	end () const
	returns an (unsafe) iterator on the end of the list of operators
Accessors / Modifiers
STRUCT_CONSTRAINT &	constraint () const noexcept
	returns the constraint that is used by the generator
void	setGraph (const DiGraph &graph)
	sets a new graph from which the operator will compute possible changes
void	setTargets (const NodeSet &nodes)
	assign a set of target nodes
void	addTarget (NodeId node)
	adds a new target node
void	eraseTarget (NodeId node)
	removes a target
void	setTails (const NodeSet &nodes)
	assign a set of "tail" nodes
void	setTails (Size nb_nodes)
	assign a set of "tail" nodes from 0 to nb_nodes - 1
void	addTail (NodeId node)
	adds a new "tail" node
void	eraseTail (NodeId node)
	removes a tail node
void	modifyGraph (const ArcAddition &change)
	notify the operator set of a change applied to the graph
void	modifyGraph (const ArcDeletion &change)
	notify the operator set of a change applied to the graph
void	modifyGraph (const ArcReversal &change)
	notify the operator set of a change applied to the graph
void	modifyGraph (const GraphChange &change)
	notify the operator set of a change applied to the graph
void	clearChanges () noexcept
	empty the set of possible change operators that can be applied
void	notifyGetCompleted ()
	notifies the generator that we have parsed all its legal changes
void	setMaxNbThreads (Size nb) noexcept
	sets the maximum number of threads used to compute the set of changes

Protected Member Functions
void	createChanges_ ()
	create the set of legal and illegal changes from a given graph

Protected Attributes
STRUCT_CONSTRAINT *	constraint_
	a reference on the structural constraint used to restrict the changes
NodeSet	target_nodes_
	the set of target nodes
NodeSet	tail_nodes_
	the tail nodes (other extremities than the targets)
Set< GraphChange >	legal_changes_
	the current set of operators

Private Attributes
Size	_max_threads_number_ {gum::getNumberOfThreads()}
	the max number of threads authorized

Detailed Description

template<typename STRUCT_CONSTRAINT>
class gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >

The basic class for computing the next graph changes possible in a structure learning algorithm.

Structure learning algorithm try different modifications of the graph. Class GraphChangesGeneratorOnSubDiGraph provides a simple way to compute those that we wish to perform when we wish to limit the set of changes over a subgraph of the graph we learn. For instance, we may wish to relearn an already partially learnt structure just around nodes A,B,C. In this case, we can set the set of target nodes of the GraphChangesGeneratorOnSubDiGraph to {A,B,C} and the set of "tail" nodes as all the nodes of the graph. In this case, only the arcs whose heads are A, B or C will be trnasmitted to the learning algorithm.

Basically, the idea is to use method setGraph at the beginning of the structure learning in order to initialize the possible set of operators. Then, parse this set using a for ( auto iter = operator_set.begin (); iter != operator_set.end (); ++iter ) loop and compute the scores induced by these changes. When this is done, flush the operator set by calling method clearChanges. Then iterate changes and after each new change applied, used again the iterator for loop, and so on. Note that, whenever you execute method modifyGraph, this will automatically flush the current list of changes and put into the list only the changes that are affected by the graph modification.

Definition at line 113 of file graphChangesGeneratorOnSubDiGraph.h.

Member Typedef Documentation

◆ const_iterator

template<typename STRUCT_CONSTRAINT>

using gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::const_iterator = iterator

the const iterator for parsing the list of graph change operators

Definition at line 119 of file graphChangesGeneratorOnSubDiGraph.h.

◆ iterator

template<typename STRUCT_CONSTRAINT>

using gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::iterator = typename Set< GraphChange >::const_iterator

the iterator for parsing the list of possible graph change operators

Definition at line 116 of file graphChangesGeneratorOnSubDiGraph.h.

Constructor & Destructor Documentation

◆ GraphChangesGeneratorOnSubDiGraph() [1/3]

template<typename STRUCT_CONSTRAINT>

gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::GraphChangesGeneratorOnSubDiGraph ( STRUCT_CONSTRAINT & constraint )

default constructor

References constraint().

Referenced by GraphChangesGeneratorOnSubDiGraph(), GraphChangesGeneratorOnSubDiGraph(), ~GraphChangesGeneratorOnSubDiGraph(), operator=(), and operator=().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GraphChangesGeneratorOnSubDiGraph() [2/3]

template<typename STRUCT_CONSTRAINT>

gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::GraphChangesGeneratorOnSubDiGraph ( const GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > & from )

copy constructor

References GraphChangesGeneratorOnSubDiGraph().

Here is the call graph for this function:

◆ GraphChangesGeneratorOnSubDiGraph() [3/3]

template<typename STRUCT_CONSTRAINT>

gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::GraphChangesGeneratorOnSubDiGraph ( GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > && from )

move operator

References GraphChangesGeneratorOnSubDiGraph().

Here is the call graph for this function:

◆ ~GraphChangesGeneratorOnSubDiGraph()

template<typename STRUCT_CONSTRAINT>

virtual gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::~GraphChangesGeneratorOnSubDiGraph ( )

virtual

destructor

References GraphChangesGeneratorOnSubDiGraph().

Here is the call graph for this function:

Member Function Documentation

◆ addTail()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::addTail ( NodeId node )

adds a new "tail" node

References addTail().

Referenced by addTail().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ addTarget()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::addTarget ( NodeId node )

adds a new target node

References addTarget().

Referenced by addTarget().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ begin()

template<typename STRUCT_CONSTRAINT>

iterator gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::begin ( ) const

virtual

returns an (unsafe) iterator on the beginning of the list of operators

Implements gum::learning::IGraphChangesGenerator4DiGraph.

◆ clearChanges()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::clearChanges ( )

virtualnoexcept

empty the set of possible change operators that can be applied

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References clearChanges().

Referenced by clearChanges().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ constraint()

template<typename STRUCT_CONSTRAINT>

STRUCT_CONSTRAINT & gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::constraint ( ) const

noexcept

returns the constraint that is used by the generator

Referenced by GraphChangesGeneratorOnSubDiGraph().

Here is the caller graph for this function:

◆ createChanges_()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::createChanges_ ( )

protected

create the set of legal and illegal changes from a given graph

References createChanges_().

Referenced by createChanges_().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ end()

template<typename STRUCT_CONSTRAINT>

const iterator & gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::end ( ) const

virtual

returns an (unsafe) iterator on the end of the list of operators

Implements gum::learning::IGraphChangesGenerator4DiGraph.

◆ eraseTail()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::eraseTail ( NodeId node )

removes a tail node

References eraseTail().

Referenced by eraseTail().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ eraseTarget()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::eraseTarget ( NodeId node )

removes a target

References eraseTarget().

Referenced by eraseTarget().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ modifyGraph() [1/4]

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::modifyGraph ( const ArcAddition & change )

virtual

notify the operator set of a change applied to the graph

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References modifyGraph().

Referenced by modifyGraph(), modifyGraph(), modifyGraph(), and modifyGraph().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ modifyGraph() [2/4]

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::modifyGraph ( const ArcDeletion & change )

virtual

notify the operator set of a change applied to the graph

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References modifyGraph().

Here is the call graph for this function:

◆ modifyGraph() [3/4]

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::modifyGraph ( const ArcReversal & change )

virtual

notify the operator set of a change applied to the graph

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References modifyGraph().

Here is the call graph for this function:

◆ modifyGraph() [4/4]

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::modifyGraph ( const GraphChange & change )

virtual

notify the operator set of a change applied to the graph

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References modifyGraph().

Here is the call graph for this function:

◆ notifyGetCompleted()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::notifyGetCompleted ( )

virtual

notifies the generator that we have parsed all its legal changes

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References notifyGetCompleted().

Referenced by notifyGetCompleted().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ operator=() [1/2]

template<typename STRUCT_CONSTRAINT>

GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > & gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::operator= ( const GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > & from )

copy operator

References GraphChangesGeneratorOnSubDiGraph().

Here is the call graph for this function:

◆ operator=() [2/2]

template<typename STRUCT_CONSTRAINT>

GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > & gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::operator= ( GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT > && from )

move operator

References GraphChangesGeneratorOnSubDiGraph().

Here is the call graph for this function:

◆ setGraph()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::setGraph ( const DiGraph & graph )

virtual

sets a new graph from which the operator will compute possible changes

Implements gum::learning::IGraphChangesGenerator4DiGraph.

References setGraph().

Referenced by setGraph().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ setMaxNbThreads()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::setMaxNbThreads ( Size nb )

noexcept

sets the maximum number of threads used to compute the set of changes

References setMaxNbThreads().

Referenced by setMaxNbThreads().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ setTails() [1/2]

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::setTails ( const NodeSet & nodes )

assign a set of "tail" nodes

References setTails().

Referenced by setTails(), and setTails().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ setTails() [2/2]

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::setTails ( Size nb_nodes )

assign a set of "tail" nodes from 0 to nb_nodes - 1

References setTails().

Here is the call graph for this function:

◆ setTargets()

template<typename STRUCT_CONSTRAINT>

void gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::setTargets ( const NodeSet & nodes )

assign a set of target nodes

References setTargets().

Referenced by setTargets().

Here is the call graph for this function:

Here is the caller graph for this function:

Member Data Documentation

◆ _max_threads_number_

template<typename STRUCT_CONSTRAINT>

Size gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::_max_threads_number_ {gum::getNumberOfThreads()}

private

the max number of threads authorized

Definition at line 243 of file graphChangesGeneratorOnSubDiGraph.h.

243{gum::getNumberOfThreads()};

gum::getNumberOfThreads

unsigned int getNumberOfThreads()

returns the max number of threads used by default when entering the next parallel region

Definition threadsSTL.cpp:68

◆ constraint_

template<typename STRUCT_CONSTRAINT>

STRUCT_CONSTRAINT* gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::constraint_

protected

a reference on the structural constraint used to restrict the changes

Definition at line 227 of file graphChangesGeneratorOnSubDiGraph.h.

◆ legal_changes_

template<typename STRUCT_CONSTRAINT>

Set< GraphChange > gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::legal_changes_

protected

the current set of operators

Definition at line 236 of file graphChangesGeneratorOnSubDiGraph.h.

◆ tail_nodes_

template<typename STRUCT_CONSTRAINT>

NodeSet gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::tail_nodes_

protected

the tail nodes (other extremities than the targets)

Definition at line 233 of file graphChangesGeneratorOnSubDiGraph.h.

◆ target_nodes_

template<typename STRUCT_CONSTRAINT>

NodeSet gum::learning::GraphChangesGeneratorOnSubDiGraph< STRUCT_CONSTRAINT >::target_nodes_

protected

the set of target nodes

Definition at line 230 of file graphChangesGeneratorOnSubDiGraph.h.

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

agrum/BN/learning/structureUtils/graphChangesGeneratorOnSubDiGraph.h

Public Types

Public Member Functions

Protected Member Functions

Protected Attributes

Private Attributes

Detailed Description

Member Typedef Documentation

◆ const_iterator

◆ iterator

Constructor & Destructor Documentation

◆ GraphChangesGeneratorOnSubDiGraph() [1/3]

◆ GraphChangesGeneratorOnSubDiGraph() [2/3]

◆ GraphChangesGeneratorOnSubDiGraph() [3/3]

◆ ~GraphChangesGeneratorOnSubDiGraph()

Member Function Documentation

◆ addTail()

◆ addTarget()

◆ begin()

◆ clearChanges()

◆ constraint()

◆ createChanges_()

◆ end()

◆ eraseTail()

◆ eraseTarget()

◆ modifyGraph() [1/4]

◆ modifyGraph() [2/4]

◆ modifyGraph() [3/4]

◆ modifyGraph() [4/4]

◆ notifyGetCompleted()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ setGraph()

◆ setMaxNbThreads()

◆ setTails() [1/2]

◆ setTails() [2/2]

◆ setTargets()

Member Data Documentation

◆ _max_threads_number_

◆ constraint_

◆ legal_changes_

◆ tail_nodes_

◆ target_nodes_