Learn a graphical representation of a function as a decision tree. More...

#include <agrum/FMDP/planning/FunctionGraph/iti.h>

Inheritance diagram for gum::ITI< AttributeSelection, isScalar >:

Collaboration diagram for gum::ITI< AttributeSelection, isScalar >:

Public Member Functions
Size	size ()
Constructor & destructor.
	ITI (MultiDimFunctionGraph< double > target, double attributeSelectionThreshold, gum::VariableSet attributeListe, const DiscreteVariable learnedValue)
	ITI constructor for functions describing the behaviour of one variable according to a set of other variable such as conditionnal probabilities.
	ITI (MultiDimFunctionGraph< double > *target, double attributeSelectionThreshold, gum::VariableSet attributeListe)
	ITI constructeur for real functions.
	~ITI ()
	Default destructor.
Visit Methods
NodeId	root () const
bool	isTerminal (NodeId ni) const
const DiscreteVariable *	nodeVar (NodeId ni) const
NodeId	nodeSon (NodeId ni, Idx modality) const
Idx	nodeNbObservation (NodeId ni) const
virtual void	insertSetOfVars (MultiDimFunctionGraph< double > *ret) const

Protected Member Functions
void	insertSetOfVars_ (MultiDimFunctionGraph< double > *ret)
	insertSetOfVars_

Protected Attributes
MultiDimFunctionGraph< double > *	target_
	The final diagram we're building.
gum::VariableSet	setOfVars_
const DiscreteVariable *	value_
Sequence< ValueType >	valueAssumed_
bool	needUpdate_
Model handling datastructures
NodeGraphPart	model_
	The source of nodeId.
NodeId	root_
	The root of the ordered tree.
HashTable< NodeId, const DiscreteVariable * >	nodeVarMap_
	Gives for any node its associated variable.
HashTable< NodeId, NodeId * >	nodeSonsMap_
	A table giving for any node a table mapping to its son idx is the modality of associated variable.
HashTable< const DiscreteVariable , LinkedList< NodeId > >	var2Node_
	Associates to any variable the list of all nodes associated to this variable.
HashTable< NodeId, NodeDatabase< AttributeSelection, isScalar > * >	nodeId2Database_
	This hashtable binds every node to an associated NodeDatabase which handles every observation that concerns that node.
HashTable< NodeId, Set< const Observation * > * >	leafDatabase_
	This hashtable binds to every leaf an associated set of all hte observations compatible with it.

Private Types
using	ValueType

Private Member Functions
Constructor & destructor.
void	_clearValue_ ()
	Template function dispatcher.
New Observation insertion methods
void	_assumeValue_ (const Observation *obs)
	Get value assumed by studied variable for current observation.
Idx	_branchObs_ (const Observation obs, const DiscreteVariable var)
	Seek modality assumed in obs for given var.

Private Attributes
HashTable< NodeId, bool >	_staleTable_
	Hashtable indicating if given node has been modified (upon receiving new exemple or through a transpose) The aim is not if we have revise the installed variable on that node.
Idx	_nbTotalObservation_
	The total number of observation added to this tree.
double	_attributeSelectionThreshold_
	The threshold above which we consider variables to be dependant.

New Observation insertion methods
void	addObservation (const Observation *obs)
	Inserts a new observation.
void	updateNodeWithObservation_ (const Observation *newObs, NodeId currentNodeId)
	Will update internal graph's NodeDatabase of given node with the new observation.

Graph Structure update methods
void	updateGraph ()
	Updates the internal graph after a new observation has been added.
NodeId	insertNode_ (NodeDatabase< AttributeSelection, isScalar > nDB, const DiscreteVariable boundVar)
	inserts a new node in internal graph
void	chgNodeBoundVar_ (NodeId chgedNodeId, const DiscreteVariable *desiredVar)
	Changes the associated variable of a node.
void	removeNode_ (NodeId removedNodeId)
	Removes a node from the internal graph.

Function Graph Updating methods
void	updateFunctionGraph ()
	Updates target to currently learned graph structure.
NodeId	_insertNodeInFunctionGraph_ (NodeId src)
	Inserts an internal node in the target.
NodeId	_insertTerminalNode_ (NodeId src)
	Insert a terminal node in the target.
NodeId	_insertTerminalNode_ (NodeId src, Int2Type< true >)
	Insert a terminal node in the target.
NodeId	_insertTerminalNode_ (NodeId src, Int2Type< false >)
	Insert a terminal node in the target.

Graph Structure update methods
virtual void	updateVar (const DiscreteVariable *)
	If a new modality appears to exists for given variable, call this method to turn every associated node to this variable into leaf. Graph has then indeed to be revised.
void	updateNode_ (NodeId nody, gum::VariableSet &bestVars)
	From the given sets of node, selects randomly one and installs it on given node.
virtual void	convertNode2Leaf_ (NodeId)
	Turns the given node into a leaf if not already so.
virtual void	transpose_ (NodeId, const DiscreteVariable *)
	Installs given variable to the given node, ensuring that the variable is not present in its subtree.
virtual NodeId	insertInternalNode_ (NodeDatabase< AttributeSelection, isScalar > nDB, const DiscreteVariable boundVar, NodeId *sonsMap)
	inserts a new internal node in internal graph
virtual NodeId	insertLeafNode_ (NodeDatabase< AttributeSelection, isScalar > nDB, const DiscreteVariable boundVar, Set< const Observation * > *obsSet)
	inserts a new leaf node in internal graohs

Detailed Description

template<TESTNAME AttributeSelection, bool isScalar = false>
class gum::ITI< AttributeSelection, isScalar >

Learn a graphical representation of a function as a decision tree.

This learning is done incrementaly. Hence first observation are add to the structure and then the structure is updated. Maintains two graph function : one internal for the learning and a target which is updated on demand.

Definition at line 79 of file iti.h.

Member Typedef Documentation

◆ ValueType

using gum::IncrementalGraphLearner< AttributeSelection, isScalar >::ValueType

privateinherited

Definition at line 84 of file incrementalGraphLearner.h.

Constructor & Destructor Documentation

◆ ITI() [1/2]

template<TESTNAME AttributeSelection, bool isScalar>

gum::ITI< AttributeSelection, isScalar >::ITI	(	MultiDimFunctionGraph< double > *	target,
		double	attributeSelectionThreshold,
		gum::VariableSet	attributeListe,
		const DiscreteVariable *	learnedValue )

ITI constructor for functions describing the behaviour of one variable according to a set of other variable such as conditionnal probabilities.

Parameters

target	: the MultiDimFunctionGraph in which we load the structure
attributeSelectionThreshold	: threshold under which a node is not installed (pe-pruning)
attributeListe	: Set of vars on which we rely to explain the behaviour of learned variable
learnedValue	: the variable from which we try to learn the behaviour
target	: the MultiDimFunctionGraph in which we load the structure
attributeSelectionThreshold	: threshold under which a node is not installed (pe-pruning)
temporaryAPIfix	: Issue in API in regard to IMDDI
attributeListe	: Set of vars on which we rely to explain the behaviour of learned variable
learnedValue	: the variable from which we try to learn the behaviour

Definition at line 84 of file iti_tpl.h.

                                                                                 :
      IncrementalGraphLearner< AttributeSelection, isScalar >(target, attributeListe, learnedValue),
      _nbTotalObservation_(0), _attributeSelectionThreshold_(attributeSelectionThreshold) {
    GUM_CONSTRUCTOR(ITI);
    _staleTable_.insert(this->root_, false);
  }

References gum::IncrementalGraphLearner< AttributeSelection, false >::IncrementalGraphLearner(), ITI(), _attributeSelectionThreshold_, _nbTotalObservation_, _staleTable_, and gum::IncrementalGraphLearner< AttributeSelection, false >::root_.

Referenced by ITI(), ITI(), and ~ITI().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ ITI() [2/2]

template<TESTNAME AttributeSelection, bool isScalar>

gum::ITI< AttributeSelection, isScalar >::ITI	(	MultiDimFunctionGraph< double > *	target,
		double	attributeSelectionThreshold,
		gum::VariableSet	attributeListe )

ITI constructeur for real functions.

We try to predict the output of a function f given a set of variable

Parameters

target	: the MultiDimFunctionGraph in which we load the structure
attributeSelectionThreshold	: threshold under which a node is not installed (pe-pruning)
attributeListe	: Set of vars on which we rely to explain the behaviour of learned function

We try to predict the output of a function f given a set of variable

Parameters

target	: the MultiDimFunctionGraph in which we load the structure
attributeSelectionThreshold	: threshold under which a node is not installed (pe-pruning)
temporaryAPIfix	: Issue in API in regard to IMDDI
attributeListeSet	of vars on which we rely to explain the behaviour of learned function

Definition at line 107 of file iti_tpl.h.

                                                                          :
      IncrementalGraphLearner< AttributeSelection, isScalar >(
          target,
          attributeListe,
          new LabelizedVariable("Reward", "", 2)),
      _nbTotalObservation_(0), _attributeSelectionThreshold_(attributeSelectionThreshold) {
    GUM_CONSTRUCTOR(ITI);
    _staleTable_.insert(this->root_, false);
  }

References gum::IncrementalGraphLearner< AttributeSelection, false >::IncrementalGraphLearner(), ITI(), _attributeSelectionThreshold_, _nbTotalObservation_, _staleTable_, and gum::IncrementalGraphLearner< AttributeSelection, false >::root_.

Here is the call graph for this function:

◆ ~ITI()

template<TESTNAME AttributeSelection, bool isScalar = false>

gum::ITI< AttributeSelection, isScalar >::~ITI ( )

inline

Default destructor.

Definition at line 122 of file iti.h.

           {
      GUM_DESTRUCTOR(ITI);
      ;
    }

References ITI().

Here is the call graph for this function:

Member Function Documentation

◆ _assumeValue_()

void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::_assumeValue_ ( const Observation * obs )

inlineprivateinherited

Get value assumed by studied variable for current observation.

Definition at line 153 of file incrementalGraphLearner.h.

153{ _assumeValue_(obs, Int2Type< isScalar >()); }

gum::IncrementalGraphLearner

Definition incrementalGraphLearner.h:83

gum::IncrementalGraphLearner< AttributeSelection, false >::_assumeValue_

void _assumeValue_(const Observation *obs)

Definition incrementalGraphLearner.h:153

◆ _branchObs_()

Idx gum::IncrementalGraphLearner< AttributeSelection, isScalar >::_branchObs_	(	const Observation *	obs,
		const DiscreteVariable *	var )

inlineprivateinherited

Seek modality assumed in obs for given var.

Definition at line 168 of file incrementalGraphLearner.h.

                                                                         {
      return _branchObs_(obs, var, Int2Type< isScalar >());
    }

Referenced by addObservation(), and insertLeafNode_().

Here is the caller graph for this function:

◆ _clearValue_()

void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::_clearValue_ ( )

inlineprivateinherited

Template function dispatcher.

Definition at line 117 of file incrementalGraphLearner.h.

117{ _clearValue_(Int2Type< isScalar >()); }

gum::IncrementalGraphLearner< AttributeSelection, false >::_clearValue_

void _clearValue_()

Definition incrementalGraphLearner.h:117

Referenced by ~IncrementalGraphLearner().

Here is the caller graph for this function:

◆ _insertNodeInFunctionGraph_()

template<TESTNAME AttributeSelection, bool isScalar>

NodeId gum::ITI< AttributeSelection, isScalar >::_insertNodeInFunctionGraph_ ( NodeId currentNodeId )

private

Inserts an internal node in the target.

Parameters

src	the source node in internal graph

Returns: the mathcing node id in the target

Parameters

the	source node in internal graph

Returns: the mathcing node id in the target

Definition at line 279 of file iti_tpl.h.

                                                                                              {
    if (this->nodeVarMap_[currentNodeId] == this->value_) {
      NodeId nody = _insertTerminalNode_(currentNodeId);
      return nody;
    }
 
    if (!this->target_->variablesSequence().exists(this->nodeVarMap_[currentNodeId])) {
      this->target_->add(*(this->nodeVarMap_[currentNodeId]));
    }
 
    NodeId nody = this->target_->manager()->addInternalNode(this->nodeVarMap_[currentNodeId]);
    for (Idx moda = 0; moda < this->nodeVarMap_[currentNodeId]->domainSize(); ++moda) {
      NodeId son = this->_insertNodeInFunctionGraph_(this->nodeSonsMap_[currentNodeId][moda]);
      this->target_->manager()->setSon(nody, moda, son);
    }
 
    return nody;
  }

References _insertNodeInFunctionGraph_(), _insertTerminalNode_(), gum::IncrementalGraphLearner< AttributeSelection, false >::nodeSonsMap_, gum::IncrementalGraphLearner< AttributeSelection, false >::nodeVarMap_, gum::IncrementalGraphLearner< AttributeSelection, false >::target_, and gum::IncrementalGraphLearner< AttributeSelection, false >::value_.

Referenced by _insertNodeInFunctionGraph_(), and updateFunctionGraph().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ _insertTerminalNode_() [1/3]

template<TESTNAME AttributeSelection, bool isScalar = false>

NodeId gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_ ( NodeId src )

inlineprivate

Insert a terminal node in the target.

This function is a dispatcher that will call the right function according to the value of the template isScalar

Parameters

src	the source node in the learned graph

Returns: the matching node in the target

Definition at line 229 of file iti.h.

                                            {
      return _insertTerminalNode_(src, Int2Type< isScalar >());
    }

References _insertTerminalNode_().

Referenced by _insertNodeInFunctionGraph_(), and _insertTerminalNode_().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ _insertTerminalNode_() [2/3]

template<TESTNAME AttributeSelection, bool isScalar>

NodeId gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_	(	NodeId	currentNodeId,
		Int2Type< false >	)

private

Insert a terminal node in the target.

This function is called if we're learning the behaviour of a variable. Inserts then this variable and the relevant value beneath into target.

Parameters

src	the source node in the learned graph

Returns: the matching node in the target

This function is called if we're learning a real value function. Inserts then a single value in target.

Parameters

the	source node in the learned graph

Returns: the matching node in the target

Definition at line 308 of file iti_tpl.h.

                                                                                      {
    if (!this->target_->variablesSequence().exists(this->value_))
      this->target_->add(*(this->value_));
 
    Size tot = this->nodeId2Database_[currentNodeId]->nbObservation();
    if (tot == Size(0)) return this->target_->manager()->addTerminalNode(0.0);
 
    NodeId* sonsMap
        = static_cast< NodeId* >(SOA_ALLOCATE(sizeof(NodeId) * this->value_->domainSize()));
    for (Idx modality = 0; modality < this->value_->domainSize(); ++modality) {
      double newVal = 0.0;
      newVal = (double)this->nodeId2Database_[currentNodeId]->effectif(modality) / (double)tot;
      sonsMap[modality] = this->target_->manager()->addTerminalNode(newVal);
    }
    NodeId nody = this->target_->manager()->addInternalNode(this->value_, sonsMap);
    return nody;
  }

References gum::IncrementalGraphLearner< AttributeSelection, false >::nodeId2Database_, SOA_ALLOCATE, gum::IncrementalGraphLearner< AttributeSelection, false >::target_, and gum::IncrementalGraphLearner< AttributeSelection, false >::value_.

◆ _insertTerminalNode_() [3/3]

template<TESTNAME AttributeSelection, bool isScalar>

NodeId gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_	(	NodeId	currentNodeId,
		Int2Type< true >	)

private

Insert a terminal node in the target.

This function is called if we're learning a real value function. Inserts then a single value in target.

Parameters

src	the source node in the learned graph

Returns: the matching node in the target

This function is called if we're learning the behaviour of a variable. Inserts then this variable and the relevant value beneath into target.

Parameters

the	source node in the learned graph

Returns: the matching node in the target

Definition at line 337 of file iti_tpl.h.

                                                                                     {
    double value = 0.0;
    for (auto valIter = this->nodeId2Database_[currentNodeId]->cbeginValues();
         valIter != this->nodeId2Database_[currentNodeId]->cendValues();
         ++valIter) {
      value += (double)valIter.key() * valIter.val();
    }
    if (this->nodeId2Database_[currentNodeId]->nbObservation())
      value /= (double)this->nodeId2Database_[currentNodeId]->nbObservation();
    NodeId nody = this->target_->manager()->addTerminalNode(value);
    return nody;
  }

References gum::IncrementalGraphLearner< AttributeSelection, false >::nodeId2Database_, and gum::IncrementalGraphLearner< AttributeSelection, false >::target_.

◆ addObservation()

template<TESTNAME AttributeSelection, bool isScalar>

void gum::ITI< AttributeSelection, isScalar >::addObservation ( const Observation * obs )

virtual

Inserts a new observation.

Parameters

obs	the new observation to learn
the	new observation to learn

Reimplemented from gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 130 of file iti_tpl.h.

                                                                                 {
    _nbTotalObservation_++;
    IncrementalGraphLearner< AttributeSelection, isScalar >::addObservation(obs);
  }

References _nbTotalObservation_, and gum::IncrementalGraphLearner< AttributeSelection, isScalar >::addObservation().

Here is the call graph for this function:

◆ chgNodeBoundVar_()

template<TESTNAME AttributeSelection, bool isScalar>

void gum::ITI< AttributeSelection, isScalar >::chgNodeBoundVar_	(	NodeId	currentNodeId,
		const DiscreteVariable *	desiredVar )

protectedvirtual

Changes the associated variable of a node.

Parameters

chgedNodeId	: the node to change
desiredVar	: its new associated variable

Reimplemented from gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 237 of file iti_tpl.h.

                                                                                                 {
    if (this->nodeVarMap_[currentNodeId] != desiredVar) {
      _staleTable_[currentNodeId] = true;
      IncrementalGraphLearner< AttributeSelection, isScalar >::chgNodeBoundVar_(currentNodeId,
                                                                                desiredVar);
    }
  }

References _staleTable_, gum::IncrementalGraphLearner< AttributeSelection, isScalar >::chgNodeBoundVar_(), and gum::IncrementalGraphLearner< AttributeSelection, false >::nodeVarMap_.

Here is the call graph for this function:

◆ convertNode2Leaf_()

void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::convertNode2Leaf_ ( NodeId currentNodeId )

protectedvirtualinherited

Turns the given node into a leaf if not already so.

Definition at line 230 of file incrementalGraphLearner_tpl.h.

                            {
    if (nodeVarMap_[currentNodeId] != value_) {
      leafDatabase_.insert(currentNodeId, new Set< const Observation* >());
 
      // Resolving tensor sons issue
      for (Idx modality = 0; modality < nodeVarMap_[currentNodeId]->domainSize(); ++modality) {
        NodeId sonId = nodeSonsMap_[currentNodeId][modality];
        convertNode2Leaf_(sonId);
        (*leafDatabase_[currentNodeId]) = (*leafDatabase_[currentNodeId]) + *(leafDatabase_[sonId]);
        removeNode_(sonId);
      }
 
      SOA_DEALLOCATE(nodeSonsMap_[currentNodeId],
                     sizeof(NodeId) * nodeVarMap_[currentNodeId]->domainSize());
      nodeSonsMap_.erase(currentNodeId);
 
      chgNodeBoundVar_(currentNodeId, value_);
    }
  }

References chgNodeBoundVar_(), nodeSonsMap_, nodeVarMap_, and value_.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::updateGraph(), and updateNode_().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ insertInternalNode_()

NodeId gum::IncrementalGraphLearner< AttributeSelection, isScalar >::insertInternalNode_	(	NodeDatabase< AttributeSelection, isScalar > *	nDB,
		const DiscreteVariable *	boundVar,
		NodeId *	sonsMap )

protectedvirtualinherited

inserts a new internal node in internal graph

Parameters

nDB	: the associated database
boundVar	: the associated variable
sonsMap	: a table giving node's sons node

Returns: the newly created node's id

Definition at line 258 of file incrementalGraphLearner_tpl.h.

                                                             {
    NodeId newNodeId = this->insertNode_(nDB, boundVar);
    nodeSonsMap_.insert(newNodeId, sonsMap);
    return newNodeId;
  }

References setOfVars_, and value_.

◆ insertLeafNode_()

NodeId gum::IncrementalGraphLearner< AttributeSelection, isScalar >::insertLeafNode_	(	NodeDatabase< AttributeSelection, isScalar > *	nDB,
		const DiscreteVariable *	boundVar,
		Set< const Observation * > *	obsSet )

protectedvirtualinherited

inserts a new leaf node in internal graohs

Parameters

nDB	: the associated database
boundVar	: the associated variable
obsSet	: the set of observation this leaf retains

Returns: the newly created node's id

Reimplemented in gum::IMDDI< AttributeSelection, isScalar >.

Definition at line 271 of file incrementalGraphLearner_tpl.h.

                                                            {
    NodeId newNodeId = this->insertNode_(nDB, boundVar);
    leafDatabase_.insert(newNodeId, obsSet);
    return newNodeId;
  }

References _branchObs_(), gum::NodeDatabase< AttributeSelection, isScalar >::addObservation(), and leafDatabase_.

Referenced by chgNodeBoundVar_().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ insertNode_()

template<TESTNAME AttributeSelection, bool isScalar>

NodeId gum::ITI< AttributeSelection, isScalar >::insertNode_	(	NodeDatabase< AttributeSelection, isScalar > *	nDB,
		const DiscreteVariable *	boundVar )

protectedvirtual

inserts a new node in internal graph

inserts a new node in internal graohs

Parameters

nDB	: the associated database
boundVar	: the associated variable

Returns: the newly created node's id

Reimplemented from gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 221 of file iti_tpl.h.

                                                              {
    NodeId n = IncrementalGraphLearner< AttributeSelection, isScalar >::insertNode_(nDB, boundVar);
    _staleTable_.insert(n, true);
    return n;
  }

References _staleTable_, and gum::IncrementalGraphLearner< AttributeSelection, isScalar >::insertNode_().

Here is the call graph for this function:

◆ insertSetOfVars()

virtual void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::insertSetOfVars ( MultiDimFunctionGraph< double > * ret ) const

inlinevirtualinherited

Implements gum::IVisitableGraphLearner.

Reimplemented in gum::IMDDI< AttributeSelection, isScalar >.

Definition at line 349 of file incrementalGraphLearner.h.

                                                                             {
      for (SetIteratorSafe< const DiscreteVariable* > varIter = setOfVars_.beginSafe();
           varIter != setOfVars_.endSafe();
           ++varIter)
        ret->add(**varIter);
    }

◆ insertSetOfVars_()

template<TESTNAME AttributeSelection, bool isScalar = false>

void gum::ITI< AttributeSelection, isScalar >::insertSetOfVars_ ( MultiDimFunctionGraph< double > * ret )

inlineprotected

insertSetOfVars_

Parameters

ret

Definition at line 265 of file iti.h.

                                                                {
      for (SetIteratorSafe< const DiscreteVariable* > varIter = this->setOfVars_.beginSafe();
           varIter != this->setOfVars_.endSafe();
           ++varIter)
        ret->add(**varIter);
    }

References gum::MultiDimFunctionGraph< GUM_SCALAR, TerminalNodePolicy >::add(), and gum::IncrementalGraphLearner< AttributeSelection, false >::setOfVars_.

Here is the call graph for this function:

◆ isTerminal()

bool gum::IncrementalGraphLearner< AttributeSelection, isScalar >::isTerminal ( NodeId ni ) const

inlinevirtualinherited

Implements gum::IVisitableGraphLearner.

Definition at line 329 of file incrementalGraphLearner.h.

329{ return !this->nodeSonsMap_.exists(ni); }

◆ nodeNbObservation()

Idx gum::IncrementalGraphLearner< AttributeSelection, isScalar >::nodeNbObservation ( NodeId ni ) const

inlinevirtualinherited

Implements gum::IVisitableGraphLearner.

Definition at line 344 of file incrementalGraphLearner.h.

344{ return this->nodeId2Database_[ni]->nbObservation(); }

◆ nodeSon()

NodeId gum::IncrementalGraphLearner< AttributeSelection, isScalar >::nodeSon	(	NodeId	ni,
		Idx	modality ) const

inlinevirtualinherited

Implements gum::IVisitableGraphLearner.

Definition at line 339 of file incrementalGraphLearner.h.

339{ return this->nodeSonsMap_[ni][modality]; }

◆ nodeVar()

const DiscreteVariable * gum::IncrementalGraphLearner< AttributeSelection, isScalar >::nodeVar ( NodeId ni ) const

inlinevirtualinherited

Implements gum::IVisitableGraphLearner.

Definition at line 334 of file incrementalGraphLearner.h.

334{ return this->nodeVarMap_[ni]; }

◆ removeNode_()

template<TESTNAME AttributeSelection, bool isScalar>

void gum::ITI< AttributeSelection, isScalar >::removeNode_ ( NodeId currentNodeId )

protectedvirtual

Removes a node from the internal graph.

Parameters

removedNodeId : the node to remove

Reimplemented from gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 253 of file iti_tpl.h.

                                                                            {
    IncrementalGraphLearner< AttributeSelection, isScalar >::removeNode_(currentNodeId);
    _staleTable_.erase(currentNodeId);
  }

References _staleTable_, and gum::IncrementalGraphLearner< AttributeSelection, isScalar >::removeNode_().

Here is the call graph for this function:

◆ root()

NodeId gum::IncrementalGraphLearner< AttributeSelection, isScalar >::root ( ) const

inlinevirtualinherited

Implements gum::IVisitableGraphLearner.

Definition at line 324 of file incrementalGraphLearner.h.

324{ return this->root_; }

◆ size()

Size gum::IncrementalGraphLearner< AttributeSelection, isScalar >::size ( )

inlineinherited

Definition at line 313 of file incrementalGraphLearner.h.

313{ return nodeVarMap_.size(); }

gum::IncrementalGraphLearner::size

Size size()

Definition incrementalGraphLearner.h:313

◆ transpose_()

void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::transpose_	(	NodeId	currentNodeId,
		const DiscreteVariable *	desiredVar )

protectedvirtualinherited

Installs given variable to the given node, ensuring that the variable is not present in its subtree.

Definition at line 236 of file incrementalGraphLearner_tpl.h.

                                          {
    // **************************************************************************************
    // Si le noeud courant contient déjà la variable qu'on souhaite lui amener
    // Il n'y a rien à faire
    if (nodeVarMap_[currentNodeId] == desiredVar) { return; }
 
    // **************************************************************************************
    // Si le noeud courant est terminal,
    // Il faut artificiellement insérer un noeud liant à la variable
    if (nodeVarMap_[currentNodeId] == value_) {
      // We turned this leaf into an internal node.
      // This mean that we'll need to install children leaves for each value of
      // desiredVar
 
      // First We must prepare these new leaves NodeDatabases and Sets<const
      // Observation*>
      NodeDatabase< AttributeSelection, isScalar >** dbMap
          = static_cast< NodeDatabase< AttributeSelection, isScalar >** >(SOA_ALLOCATE(
              sizeof(NodeDatabase< AttributeSelection, isScalar >*) * desiredVar->domainSize()));
      Set< const Observation* >** obsetMap = static_cast< Set< const Observation* >** >(
          SOA_ALLOCATE(sizeof(Set< const Observation* >*) * desiredVar->domainSize()));
      for (Idx modality = 0; modality < desiredVar->domainSize(); ++modality) {
        dbMap[modality]    = new NodeDatabase< AttributeSelection, isScalar >(&setOfVars_, value_);
        obsetMap[modality] = new Set< const Observation* >();
      }
      for (SetIteratorSafe< const Observation* > obsIter
           = leafDatabase_[currentNodeId]->beginSafe();
           leafDatabase_[currentNodeId]->endSafe() != obsIter;
           ++obsIter) {
        dbMap[_branchObs_(*obsIter, desiredVar)]->addObservation(*obsIter);
        obsetMap[_branchObs_(*obsIter, desiredVar)]->insert(*obsIter);
      }
 
      // Then we can install each new leaves (and put in place the sonsMap)
      NodeId* sonsMap
          = static_cast< NodeId* >(SOA_ALLOCATE(sizeof(NodeId) * desiredVar->domainSize()));
      for (Idx modality = 0; modality < desiredVar->domainSize(); ++modality)
        sonsMap[modality] = insertLeafNode_(dbMap[modality], value_, obsetMap[modality]);
 
      // Some necessary clean up
      SOA_DEALLOCATE(dbMap,
                     sizeof(NodeDatabase< AttributeSelection, isScalar >*)
                         * desiredVar->domainSize());
      SOA_DEALLOCATE(obsetMap, sizeof(Set< const Observation* >*) * desiredVar->domainSize());
 
      // And finally we can turn the node into an internal node associated to
      // desiredVar
      chgNodeBoundVar_(currentNodeId, desiredVar);
      nodeSonsMap_.insert(currentNodeId, sonsMap);
 
      return;
    }
 
    // *************************************************************************************
    // Remains the general case where currentNodeId is an internal node.
 
    // First we ensure that children node use desiredVar as variable
    for (Idx modality = 0; modality < nodeVarMap_[currentNodeId]->domainSize(); ++modality)
      transpose_(nodeSonsMap_[currentNodeId][modality], desiredVar);
 
    //        Sequence<NodeDatabase<AttributeSelection, isScalar>*>
    //        sonsNodeDatabase =
    //        nodeId2Database_[currentNodeId]->splitOnVar(desiredVar);
    NodeId* sonsMap
        = static_cast< NodeId* >(SOA_ALLOCATE(sizeof(NodeId) * desiredVar->domainSize()));
 
    // Then we create the new mapping
    for (Idx desiredVarModality = 0; desiredVarModality < desiredVar->domainSize();
         ++desiredVarModality) {
      NodeId* grandSonsMap = static_cast< NodeId* >(
          SOA_ALLOCATE(sizeof(NodeId) * nodeVarMap_[currentNodeId]->domainSize()));
      NodeDatabase< AttributeSelection, isScalar >* sonDB
          = new NodeDatabase< AttributeSelection, isScalar >(&setOfVars_, value_);
      for (Idx currentVarModality = 0;
           currentVarModality < nodeVarMap_[currentNodeId]->domainSize();
           ++currentVarModality) {
        grandSonsMap[currentVarModality]
            = nodeSonsMap_[nodeSonsMap_[currentNodeId][currentVarModality]][desiredVarModality];
        sonDB->operator+=((*nodeId2Database_[grandSonsMap[currentVarModality]]));
      }
 
      sonsMap[desiredVarModality]
          = insertInternalNode_(sonDB, nodeVarMap_[currentNodeId], grandSonsMap);
    }
 
    // Finally we clean the old remaining nodes
    for (Idx currentVarModality = 0; currentVarModality < nodeVarMap_[currentNodeId]->domainSize();
         ++currentVarModality) {
      removeNode_(nodeSonsMap_[currentNodeId][currentVarModality]);
    }
 
    // We suppress the old sons map and remap to the new one
    SOA_DEALLOCATE(nodeSonsMap_[currentNodeId],
                   sizeof(NodeId) * nodeVarMap_[currentNodeId]->domainSize());
    nodeSonsMap_[currentNodeId] = sonsMap;
 
    chgNodeBoundVar_(currentNodeId, desiredVar);
  }

Referenced by gum::IMDDI< AttributeSelection, isScalar >::_updateNodeSet_(), and updateVar().

Here is the caller graph for this function:

◆ updateFunctionGraph()

template<TESTNAME AttributeSelection, bool isScalar>

void gum::ITI< AttributeSelection, isScalar >::updateFunctionGraph ( )

virtual

Updates target to currently learned graph structure.

Implements gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 266 of file iti_tpl.h.

                                                                {
    this->target_->clear();
    this->target_->manager()->setRootNode(this->_insertNodeInFunctionGraph_(this->root_));
  }

References _insertNodeInFunctionGraph_(), gum::IncrementalGraphLearner< AttributeSelection, false >::root_, and gum::IncrementalGraphLearner< AttributeSelection, false >::target_.

Here is the call graph for this function:

◆ updateGraph()

template<TESTNAME AttributeSelection, bool isScalar>

void gum::ITI< AttributeSelection, isScalar >::updateGraph ( )

virtual

Updates the internal graph after a new observation has been added.

Implements gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 160 of file iti_tpl.h.

                                                        {
    std::vector< NodeId > filo;
    filo.push_back(this->root_);
    HashTable< NodeId, gum::VariableSet* > tensorVars;
    tensorVars.insert(this->root_, new gum::VariableSet(this->setOfVars_));
 
 
    while (!filo.empty()) {
      NodeId currentNodeId = filo.back();
      filo.pop_back();
 
      // First we look for the best var to install on the node
      double           bestValue = _attributeSelectionThreshold_;
      gum::VariableSet bestVars;
 
      for (auto varIter = tensorVars[currentNodeId]->cbeginSafe();
           varIter != tensorVars[currentNodeId]->cendSafe();
           ++varIter)
        if (this->nodeId2Database_[currentNodeId]->isTestRelevant(*varIter)) {
          double varValue = this->nodeId2Database_[currentNodeId]->testValue(*varIter);
          if (varValue >= bestValue) {
            if (varValue > bestValue) {
              bestValue = varValue;
              bestVars.clear();
            }
            bestVars.insert(*varIter);
          }
        }
 
      // Then We installed Variable a test on that node
      this->updateNode_(currentNodeId, bestVars);
 
      // The we move on the children if needed
      if (this->nodeVarMap_[currentNodeId] != this->value_) {
        for (Idx moda = 0; moda < this->nodeVarMap_[currentNodeId]->domainSize(); moda++) {
          gum::VariableSet* itsTensorVars = new gum::VariableSet(*tensorVars[currentNodeId]);
          itsTensorVars->erase(this->nodeVarMap_[currentNodeId]);
          NodeId sonId = this->nodeSonsMap_[currentNodeId][moda];
          if (_staleTable_[sonId]) {
            filo.push_back(sonId);
            tensorVars.insert(sonId, itsTensorVars);
          }
        }
      }
    }
 
    for (HashTableIteratorSafe< NodeId, gum::VariableSet* > nodeIter = tensorVars.beginSafe();
         nodeIter != tensorVars.endSafe();
         ++nodeIter)
      delete nodeIter.val();
  }

References _attributeSelectionThreshold_, _staleTable_, gum::HashTable< Key, Val >::beginSafe(), gum::HashTable< Key, Val >::cendSafe(), gum::Set< Key >::clear(), gum::HashTable< Key, Val >::endSafe(), gum::Set< Key >::erase(), gum::HashTable< Key, Val >::insert(), gum::Set< Key >::insert(), gum::IncrementalGraphLearner< AttributeSelection, false >::nodeId2Database_, gum::IncrementalGraphLearner< AttributeSelection, false >::nodeSonsMap_, gum::IncrementalGraphLearner< AttributeSelection, false >::nodeVarMap_, gum::IncrementalGraphLearner< AttributeSelection, false >::root_, gum::IncrementalGraphLearner< AttributeSelection, false >::setOfVars_, gum::IncrementalGraphLearner< AttributeSelection, false >::updateNode_(), and gum::IncrementalGraphLearner< AttributeSelection, false >::value_.

Here is the call graph for this function:

◆ updateNode_()

void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::updateNode_	(	NodeId	updatedNode,
		gum::VariableSet &	varsOfInterest )

protectedinherited

From the given sets of node, selects randomly one and installs it on given node.

Chechks of course if node's current variable is not in that set first.

Parameters

nody	: the node we update
bestVars	: the set of interessting vars to be installed here

Chechks of course if node's current variable is not in that set first.

Parameters

nody	: the node we update
bestVar	: the set of interessting vars to be installed here

Definition at line 225 of file incrementalGraphLearner_tpl.h.

                                      {
    // If this node has no interesting variable, we turn it into a leaf
    if (varsOfInterest.empty()) {
      convertNode2Leaf_(updatedNode);
      return;
    }
 
    // If this node has already one of the best variable intalled as test, we
    // move on
    if (nodeVarMap_.exists(updatedNode) && varsOfInterest.exists(nodeVarMap_[updatedNode])) {
      return;
    }
 
    // In any other case we have to install variable as best test
    Idx randy = randomValue(varsOfInterest.size()), basc = 0;
    SetConstIteratorSafe< const DiscreteVariable* > varIter;
    for (varIter = varsOfInterest.cbeginSafe(), basc = 0;
         varIter != varsOfInterest.cendSafe() && basc < randy;
         ++varIter, basc++)
      ;
 
    transpose_(updatedNode, *varIter);
  }

References convertNode2Leaf_(), leafDatabase_, and removeNode_().

Referenced by gum::ITI< AttributeSelection, isScalar >::updateGraph().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ updateNodeWithObservation_()

template<TESTNAME AttributeSelection, bool isScalar>

void gum::ITI< AttributeSelection, isScalar >::updateNodeWithObservation_	(	const Observation *	newObs,
		NodeId	currentNodeId )

protectedvirtual

Will update internal graph's NodeDatabase of given node with the new observation.

Parameters

newObs
currentNodeId

Reimplemented from gum::IncrementalGraphLearner< AttributeSelection, false >.

Definition at line 144 of file iti_tpl.h.

                                                                                             {
    IncrementalGraphLearner< AttributeSelection, isScalar >::updateNodeWithObservation_(
        newObs,
        currentNodeId);
    _staleTable_[currentNodeId] = true;
  }

References _staleTable_, and gum::IncrementalGraphLearner< AttributeSelection, isScalar >::updateNodeWithObservation_().

Here is the call graph for this function:

◆ updateVar()

void gum::IncrementalGraphLearner< AttributeSelection, isScalar >::updateVar ( const DiscreteVariable * var )

virtualinherited

If a new modality appears to exists for given variable, call this method to turn every associated node to this variable into leaf. Graph has then indeed to be revised.

Definition at line 207 of file incrementalGraphLearner_tpl.h.

                                   {
    Link< NodeId >* nodIter = var2Node_[var]->list();
    Link< NodeId >* nni     = nullptr;
    while (nodIter) {
      nni = nodIter->nextLink();
      convertNode2Leaf_(nodIter->element());
      nodIter = nni;
    }
  }

References transpose_().

Here is the call graph for this function:

Member Data Documentation

◆ _attributeSelectionThreshold_

template<TESTNAME AttributeSelection, bool isScalar = false>

double gum::ITI< AttributeSelection, isScalar >::_attributeSelectionThreshold_

private

The threshold above which we consider variables to be dependant.

Definition at line 282 of file iti.h.

Referenced by ITI(), ITI(), and updateGraph().

◆ _nbTotalObservation_

template<TESTNAME AttributeSelection, bool isScalar = false>

Idx gum::ITI< AttributeSelection, isScalar >::_nbTotalObservation_

private

The total number of observation added to this tree.

Definition at line 279 of file iti.h.

Referenced by ITI(), ITI(), and addObservation().

◆ _staleTable_

template<TESTNAME AttributeSelection, bool isScalar = false>

HashTable< NodeId, bool > gum::ITI< AttributeSelection, isScalar >::_staleTable_

private

Hashtable indicating if given node has been modified (upon receiving new exemple or through a transpose) The aim is not if we have revise the installed variable on that node.

Definition at line 276 of file iti.h.

Referenced by ITI(), ITI(), chgNodeBoundVar_(), insertNode_(), removeNode_(), updateGraph(), and updateNodeWithObservation_().

◆ leafDatabase_

HashTable< NodeId, Set< const Observation* >* > gum::IncrementalGraphLearner< AttributeSelection, isScalar >::leafDatabase_

protectedinherited

This hashtable binds to every leaf an associated set of all hte observations compatible with it.

Definition at line 403 of file incrementalGraphLearner.h.

Referenced by ~IncrementalGraphLearner(), insertLeafNode_(), and updateNode_().

◆ model_

NodeGraphPart gum::IncrementalGraphLearner< AttributeSelection, isScalar >::model_

protectedinherited

The source of nodeId.

Definition at line 369 of file incrementalGraphLearner.h.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::IMDDI(), and gum::IMDDI< AttributeSelection, isScalar >::IMDDI().

◆ needUpdate_

bool gum::IncrementalGraphLearner< AttributeSelection, isScalar >::needUpdate_

protectedinherited

Definition at line 416 of file incrementalGraphLearner.h.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::updateFunctionGraph().

◆ nodeId2Database_

HashTable< NodeId, NodeDatabase< AttributeSelection, isScalar >* > gum::IncrementalGraphLearner< AttributeSelection, isScalar >::nodeId2Database_

protectedinherited

This hashtable binds every node to an associated NodeDatabase which handles every observation that concerns that node.

Definition at line 397 of file incrementalGraphLearner.h.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::_addLeaf_(), gum::IMDDI< AttributeSelection, isScalar >::_downdateScore_(), gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_(), gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_(), gum::IMDDI< AttributeSelection, isScalar >::_updateNodeSet_(), gum::IMDDI< AttributeSelection, isScalar >::_updateScore_(), and gum::ITI< AttributeSelection, isScalar >::updateGraph().

◆ nodeSonsMap_

HashTable< NodeId, NodeId* > gum::IncrementalGraphLearner< AttributeSelection, isScalar >::nodeSonsMap_

protectedinherited

A table giving for any node a table mapping to its son idx is the modality of associated variable.

Definition at line 385 of file incrementalGraphLearner.h.

Referenced by ~IncrementalGraphLearner(), gum::ITI< AttributeSelection, isScalar >::_insertNodeInFunctionGraph_(), gum::IMDDI< AttributeSelection, isScalar >::_rebuildFunctionGraph_(), gum::IMDDI< AttributeSelection, isScalar >::_updateNodeSet_(), addObservation(), convertNode2Leaf_(), removeNode_(), and gum::ITI< AttributeSelection, isScalar >::updateGraph().

◆ nodeVarMap_

HashTable< NodeId, const DiscreteVariable* > gum::IncrementalGraphLearner< AttributeSelection, isScalar >::nodeVarMap_

protectedinherited

Gives for any node its associated variable.

Definition at line 379 of file incrementalGraphLearner.h.

Referenced by ~IncrementalGraphLearner(), gum::ITI< AttributeSelection, isScalar >::_insertNodeInFunctionGraph_(), gum::IMDDI< AttributeSelection, isScalar >::_updateNodeSet_(), addObservation(), gum::IMDDI< AttributeSelection, isScalar >::chgNodeBoundVar_(), gum::ITI< AttributeSelection, isScalar >::chgNodeBoundVar_(), convertNode2Leaf_(), insertNode_(), gum::IMDDI< AttributeSelection, isScalar >::removeNode_(), gum::ITI< AttributeSelection, isScalar >::updateGraph(), and gum::IMDDI< AttributeSelection, isScalar >::updateNodeWithObservation_().

◆ root_

NodeId gum::IncrementalGraphLearner< AttributeSelection, isScalar >::root_

protectedinherited

The root of the ordered tree.

Definition at line 374 of file incrementalGraphLearner.h.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::IMDDI(), gum::IMDDI< AttributeSelection, isScalar >::IMDDI(), gum::ITI< AttributeSelection, isScalar >::ITI(), gum::ITI< AttributeSelection, isScalar >::ITI(), gum::IMDDI< AttributeSelection, isScalar >::_rebuildFunctionGraph_(), gum::ITI< AttributeSelection, isScalar >::updateFunctionGraph(), gum::IMDDI< AttributeSelection, isScalar >::updateGraph(), and gum::ITI< AttributeSelection, isScalar >::updateGraph().

◆ setOfVars_

gum::VariableSet gum::IncrementalGraphLearner< AttributeSelection, isScalar >::setOfVars_

protectedinherited

Definition at line 411 of file incrementalGraphLearner.h.

Referenced by insertInternalNode_(), gum::ITI< AttributeSelection, isScalar >::insertSetOfVars_(), gum::IMDDI< AttributeSelection, isScalar >::updateGraph(), and gum::ITI< AttributeSelection, isScalar >::updateGraph().

◆ target_

MultiDimFunctionGraph< double >* gum::IncrementalGraphLearner< AttributeSelection, isScalar >::target_

protectedinherited

The final diagram we're building.

Definition at line 409 of file incrementalGraphLearner.h.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::_insertLeafInFunctionGraph_(), gum::IMDDI< AttributeSelection, isScalar >::_insertLeafInFunctionGraph_(), gum::ITI< AttributeSelection, isScalar >::_insertNodeInFunctionGraph_(), gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_(), gum::ITI< AttributeSelection, isScalar >::_insertTerminalNode_(), gum::IMDDI< AttributeSelection, isScalar >::_rebuildFunctionGraph_(), and gum::ITI< AttributeSelection, isScalar >::updateFunctionGraph().

◆ value_

const DiscreteVariable* gum::IncrementalGraphLearner< AttributeSelection, isScalar >::value_

protectedinherited

Definition at line 413 of file incrementalGraphLearner.h.

◆ valueAssumed_

Sequence< ValueType > gum::IncrementalGraphLearner< AttributeSelection, isScalar >::valueAssumed_

protectedinherited

Definition at line 414 of file incrementalGraphLearner.h.

Referenced by gum::IMDDI< AttributeSelection, isScalar >::_addLeaf_(), and gum::IMDDI< AttributeSelection, isScalar >::_insertLeafInFunctionGraph_().

◆ var2Node_

HashTable< const DiscreteVariable*, LinkedList< NodeId >* > gum::IncrementalGraphLearner< AttributeSelection, isScalar >::var2Node_

protectedinherited

Associates to any variable the list of all nodes associated to this variable.

Definition at line 391 of file incrementalGraphLearner.h.

Referenced by ~IncrementalGraphLearner(), and gum::IMDDI< AttributeSelection, isScalar >::_rebuildFunctionGraph_().

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

agrum/FMDP/learning/datastructure/iti.h
agrum/FMDP/learning/datastructure/iti_tpl.h

Public Member Functions

Protected Member Functions

Protected Attributes

Private Types

Private Member Functions

Private Attributes

New Observation insertion methods

Graph Structure update methods

Function Graph Updating methods

Graph Structure update methods

Detailed Description

Member Typedef Documentation

◆ ValueType

Constructor & Destructor Documentation

◆ ITI() [1/2]

◆ ITI() [2/2]

◆ ~ITI()

Member Function Documentation

◆ _assumeValue_()

◆ _branchObs_()

◆ _clearValue_()

◆ _insertNodeInFunctionGraph_()

◆ _insertTerminalNode_() [1/3]

◆ _insertTerminalNode_() [2/3]

◆ _insertTerminalNode_() [3/3]

◆ addObservation()

◆ chgNodeBoundVar_()

◆ convertNode2Leaf_()

◆ insertInternalNode_()

◆ insertLeafNode_()

◆ insertNode_()

◆ insertSetOfVars()

◆ insertSetOfVars_()

◆ isTerminal()

◆ nodeNbObservation()

◆ nodeSon()

◆ nodeVar()

◆ removeNode_()

◆ root()

◆ size()

◆ transpose_()

◆ updateFunctionGraph()

◆ updateGraph()

◆ updateNode_()

◆ updateNodeWithObservation_()

◆ updateVar()

Member Data Documentation

◆ _attributeSelectionThreshold_

◆ _nbTotalObservation_

◆ _staleTable_

◆ leafDatabase_

◆ model_

◆ needUpdate_

◆ nodeId2Database_

◆ nodeSonsMap_

◆ nodeVarMap_

◆ root_

◆ setOfVars_

◆ target_

◆ value_

◆ valueAssumed_

◆ var2Node_