gum::ShaferShenoyInference< GUM_SCALAR > Class Template Reference

<agrum/BN/inference/ShaferShenoyInference.h> More...

#include <ShaferShenoyInference.h>

Inheritance diagram for gum::ShaferShenoyInference< GUM_SCALAR >:

Collaboration diagram for gum::ShaferShenoyInference< GUM_SCALAR >:

Public Member Functions
Potential< GUM_SCALAR >	evidenceJointImpact (const NodeSet &targets, const NodeSet &evs)
	Create a gum::Potential for P(joint targets|evs) (for all instanciation of targets and evs) More...
Potential< GUM_SCALAR >	evidenceJointImpact (const std::vector< std::string > &targets, const std::vector< std::string > &evs)
	Create a gum::Potential for P(joint targets|evs) (for all instanciation of targets and evs) More...
Potential< GUM_SCALAR >	evidenceImpact (NodeId target, const NodeSet &evs)
	Create a gum::Potential for P(target|evs) (for all instanciation of target and evs) More...
Potential< GUM_SCALAR >	evidenceImpact (const std::string &target, const std::vector< std::string > &evs)
	Create a gum::Potential for P(target|evs) (for all instanciation of target and evs) More...
Constructors / Destructors
	ShaferShenoyInference (const IBayesNet< GUM_SCALAR > *BN, FindBarrenNodesType barren_type=FindBarrenNodesType::FIND_BARREN_NODES, bool use_binary_join_tree=true)
	default constructor More...
	~ShaferShenoyInference () final
	destructor More...
Accessors / Modifiers
void	setTriangulation (const Triangulation &new_triangulation)
	use a new triangulation algorithm More...
void	setFindBarrenNodesType (FindBarrenNodesType type)
	sets how we determine barren nodes More...
const JoinTree *	joinTree ()
	returns the current join tree used More...
const JunctionTree *	junctionTree ()
	returns the current junction tree More...
GUM_SCALAR	evidenceProbability ()
	returns the probability of evidence More...
Probability computations
virtual const Potential< GUM_SCALAR > &	jointPosterior (const NodeSet &nodes) final
	Compute the joint posterior of a set of nodes. More...
virtual const Potential< GUM_SCALAR > &	posterior (NodeId node) final
	Computes and returns the posterior of a node. More...
virtual const Potential< GUM_SCALAR > &	posterior (const std::string &nodeName) final
	Computes and returns the posterior of a node. More...
Targets
virtual void	eraseAllTargets ()
	Clear all previously defined targets (marginal and joint targets) More...
virtual void	eraseAllJointTargets () final
	Clear all previously defined joint targets. More...
virtual void	eraseAllMarginalTargets () final
	Clear all the previously defined marginal targets. More...
virtual void	addJointTarget (const NodeSet &joint_target) final
	Add a set of nodes as a new joint target. As a collateral effect, every node is added as a marginal target. More...
virtual void	eraseJointTarget (const NodeSet &joint_target) final
	removes an existing joint target More...
virtual bool	isJointTarget (const NodeSet &vars) const final
	return true if target is a joint target. More...
virtual const Set< NodeSet > &	jointTargets () const noexcept final
	returns the list of joint targets More...
virtual Size	nbrJointTargets () const noexcept final
	returns the number of joint targets More...
Information Theory related functions
GUM_SCALAR	I (NodeId X, NodeId Y)
	Mutual information between X and Y. More...
GUM_SCALAR	I (const std::string &Xname, const std::string &Yname)
	Mutual information between X and Y. More...
GUM_SCALAR	VI (NodeId X, NodeId Y)
	Variation of information between X and Y. More...
GUM_SCALAR	VI (const std::string &Xname, const std::string &Yname)
	Variation of information between X and Y. More...
GUM_SCALAR	jointMutualInformation (const NodeSet &targets)
	Mutual information between targets. More...
GUM_SCALAR	jointMutualInformation (const std::vector< std::string > &targets)
	Mutual information between targets. More...
Targets
virtual void	addAllTargets () final
	adds all nodes as targets More...
virtual void	addTarget (NodeId target) final
	Add a marginal target to the list of targets. More...
virtual void	addTarget (const std::string &nodeName) final
	Add a marginal target to the list of targets. More...
virtual void	eraseTarget (NodeId target) final
	removes an existing (marginal) target More...
virtual void	eraseTarget (const std::string &nodeName) final
	removes an existing (marginal) target More...
virtual bool	isTarget (NodeId node) const final
	return true if variable is a (marginal) target More...
virtual bool	isTarget (const std::string &nodeName) const final
	return true if variable is a (marginal) target More...
virtual const Size	nbrTargets () const noexcept final
	returns the number of marginal targets More...
virtual const NodeSet &	targets () const noexcept final
	returns the list of marginal targets More...
Information Theory related functions
virtual GUM_SCALAR	H (NodeId X) final
	Entropy Compute Shanon's entropy of a node given the observation. More...
virtual GUM_SCALAR	H (const std::string &nodeName) final
	Entropy Compute Shanon's entropy of a node given the observation. More...
Accessors / Modifiers
virtual void	setBN (const IBayesNet< GUM_SCALAR > *bn)
	assigns a new BN to the inference engine More...
virtual const IBayesNet< GUM_SCALAR > &	BN () const final
	Returns a constant reference over the IBayesNet referenced by this class. More...
Accessors / Modifiers
virtual const GraphicalModel &	model () const final
	Returns a constant reference over the IBayesNet referenced by this class. More...
virtual const NodeProperty< Size > &	domainSizes () const final
	get the domain sizes of the random variables of the model More...
virtual bool	isInferenceReady () const noexcept final
	returns whether the inference object is in a ready state More...
virtual bool	isInferenceOutdatedStructure () const noexcept final
	returns whether the inference object is in a OutdatedStructure state More...
virtual bool	isInferenceOutdatedPotentials () const noexcept final
	returns whether the inference object is in a OutdatedPotential state More...
virtual bool	isInferenceDone () const noexcept final
	returns whether the inference object is in a InferenceDone state More...
virtual void	prepareInference () final
	prepare the internal inference structures for the next inference More...
virtual void	makeInference () final
	perform the heavy computations needed to compute the targets' posteriors More...
virtual void	clear ()
	clears all the data structures allocated for the last inference More...
virtual StateOfInference	state () const noexcept final
	returns the state of the inference engine More...
Evidence
virtual void	addEvidence (NodeId id, const Idx val) final
	adds a new hard evidence on node id More...
virtual void	addEvidence (const std::string &nodeName, const Idx val) final
	adds a new hard evidence on node named nodeName More...
virtual void	addEvidence (NodeId id, const std::string &label) final
	adds a new hard evidence on node id More...
virtual void	addEvidence (const std::string &nodeName, const std::string &label) final
	adds a new hard evidence on node named nodeName More...
virtual void	addEvidence (NodeId id, const std::vector< GUM_SCALAR > &vals) final
	adds a new evidence on node id (might be soft or hard) More...
virtual void	addEvidence (const std::string &nodeName, const std::vector< GUM_SCALAR > &vals) final
	adds a new evidence on node named nodeName (might be soft or hard) More...
virtual void	addEvidence (const Potential< GUM_SCALAR > &pot) final
	adds a new evidence on node id (might be soft or hard) More...
virtual void	addEvidence (Potential< GUM_SCALAR > &&pot) final
	adds a new evidence on node id (might be soft or hard) More...
virtual void	addSetOfEvidence (const Set< const Potential< GUM_SCALAR > * > &potset) final
	adds a new set of evidence More...
virtual void	addListOfEvidence (const List< const Potential< GUM_SCALAR > * > &potlist) final
	adds a new list of evidence More...
virtual void	chgEvidence (NodeId id, const Idx val) final
	change the value of an already existing hard evidence More...
virtual void	chgEvidence (const std::string &nodeName, const Idx val) final
	change the value of an already existing hard evidence More...
virtual void	chgEvidence (NodeId id, const std::string &label) final
	change the value of an already existing hard evidence More...
virtual void	chgEvidence (const std::string &nodeName, const std::string &label) final
	change the value of an already existing hard evidence More...
virtual void	chgEvidence (NodeId id, const std::vector< GUM_SCALAR > &vals) final
	change the value of an already existing evidence (might be soft or hard) More...
virtual void	chgEvidence (const std::string &nodeName, const std::vector< GUM_SCALAR > &vals) final
	change the value of an already existing evidence (might be soft or hard) More...
virtual void	chgEvidence (const Potential< GUM_SCALAR > &pot) final
	change the value of an already existing evidence (might be soft or hard) More...
virtual void	eraseAllEvidence () final
	removes all the evidence entered into the network More...
virtual void	eraseEvidence (NodeId id) final
	removed the evidence, if any, corresponding to node id More...
virtual void	eraseEvidence (const std::string &nodeName) final
	removed the evidence, if any, corresponding to node of name nodeName More...
virtual bool	hasEvidence () const final
	indicates whether some node(s) have received evidence More...
virtual bool	hasEvidence (NodeId id) const final
	indicates whether node id has received an evidence More...
virtual bool	hasEvidence (const std::string &nodeName) const final
	indicates whether node id has received an evidence More...
virtual bool	hasHardEvidence (NodeId id) const final
	indicates whether node id has received a hard evidence More...
virtual bool	hasHardEvidence (const std::string &nodeName) const final
	indicates whether node id has received a hard evidence More...
virtual bool	hasSoftEvidence (NodeId id) const final
	indicates whether node id has received a soft evidence More...
virtual bool	hasSoftEvidence (const std::string &nodeName) const final
	indicates whether node id has received a soft evidence More...
virtual Size	nbrEvidence () const final
	returns the number of evidence entered into the Bayesian network More...
virtual Size	nbrHardEvidence () const final
	returns the number of hard evidence entered into the Bayesian network More...
virtual Size	nbrSoftEvidence () const final
	returns the number of soft evidence entered into the Bayesian network More...
const NodeProperty< const Potential< GUM_SCALAR > *> &	evidence () const
	returns the set of evidence More...
const NodeSet &	softEvidenceNodes () const
	returns the set of nodes with soft evidence More...
const NodeSet &	hardEvidenceNodes () const
	returns the set of nodes with hard evidence More...
const NodeProperty< Idx > &	hardEvidence () const
	indicate for each node with hard evidence which value it took More...

Public Types
enum	StateOfInference { StateOfInference::OutdatedStructure, StateOfInference::OutdatedPotentials, StateOfInference::ReadyForInference, StateOfInference::Done }
	current state of the inference More...

Protected Member Functions
void	onStateChanged_ () final
	fired when the stage is changed More...
void	onEvidenceAdded_ (const NodeId id, bool isHardEvidence) final
	fired after a new evidence is inserted More...
void	onEvidenceErased_ (const NodeId id, bool isHardEvidence) final
	fired before an evidence is removed More...
void	onAllEvidenceErased_ (bool contains_hard_evidence) final
	fired before all the evidence are erased More...
void	onEvidenceChanged_ (const NodeId id, bool hasChangedSoftHard) final
	fired after an evidence is changed, in particular when its status (soft/hard) changes More...
void	onMarginalTargetAdded_ (const NodeId id) final
	fired after a new single target is inserted More...
void	onMarginalTargetErased_ (const NodeId id) final
	fired before a single target is removed More...
virtual void	onModelChanged_ (const GraphicalModel *bn) final
	fired after a new Bayes net has been assigned to the engine More...
void	onJointTargetAdded_ (const NodeSet &set) final
	fired after a new joint target is inserted More...
void	onJointTargetErased_ (const NodeSet &set) final
	fired before a joint target is removed More...
void	onAllMarginalTargetsAdded_ () final
	fired after all the nodes of the BN are added as single targets More...
void	onAllMarginalTargetsErased_ () final
	fired before a all the single targets are removed More...
void	onAllJointTargetsErased_ () final
	fired before a all the joint targets are removed More...
void	onAllTargetsErased_ () final
	fired before a all single and joint_targets are removed More...
void	updateOutdatedStructure_ () final
	prepares inference when the latter is in OutdatedStructure state More...
void	updateOutdatedPotentials_ () final
	prepares inference when the latter is in OutdatedPotentials state More...
void	makeInference_ () final
	called when the inference has to be performed effectively More...
const Potential< GUM_SCALAR > &	posterior_ (NodeId id) final
	returns the posterior of a given variable More...
const Potential< GUM_SCALAR > &	jointPosterior_ (const NodeSet &set) final
	returns the posterior of a declared target set More...
const Potential< GUM_SCALAR > &	jointPosterior_ (const NodeSet &wanted_target, const NodeSet &declared_target) final
	asks derived classes for the joint posterior of a set of variables not declared as a joint target More...
Potential< GUM_SCALAR > *	unnormalizedJointPosterior_ (NodeId id) final
	returns a fresh potential equal to P(argument,evidence) More...
Potential< GUM_SCALAR > *	unnormalizedJointPosterior_ (const NodeSet &set) final
	returns a fresh potential equal to P(argument,evidence) More...
void	setTargetedMode_ ()
bool	isTargetedMode_ () const
void	setOutdatedStructureState_ ()
	put the inference into an outdated model structure state More...
void	setOutdatedPotentialsState_ ()
	puts the inference into an OutdatedPotentials state if it is not already in an OutdatedStructure state More...
virtual void	setState_ (const StateOfInference state) final
	set the state of the inference engine and call the notification onStateChanged_ when necessary (i.e. when the state has effectively changed). More...
void	setModel_ (const GraphicalModel *model)
void	setModelDuringConstruction_ (const GraphicalModel *model)
	assigns a model during the inference engine construction More...
bool	hasNoModel_ () const

Detailed Description

template<typename GUM_SCALAR>
class gum::ShaferShenoyInference< GUM_SCALAR >

<agrum/BN/inference/ShaferShenoyInference.h>

Implementation of Shafer-Shenoy's propagation algorithm for inference in Bayesian networks

Definition at line 67 of file ShaferShenoyInference.h.

Member Typedef Documentation

PotentialSet__

template<typename GUM_SCALAR>

typedef Set< const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::PotentialSet__

private

Definition at line 221 of file ShaferShenoyInference.h.

PotentialSetIterator__

template<typename GUM_SCALAR>

typedef SetIteratorSafe< const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::PotentialSetIterator__

private

Definition at line 223 of file ShaferShenoyInference.h.

Member Enumeration Documentation

EvidenceChangeType

template<typename GUM_SCALAR>

enum gum::ShaferShenoyInference::EvidenceChangeType

private

the possible types of evidence changes

Enumerator
EVIDENCE_ADDED
EVIDENCE_ERASED
EVIDENCE_MODIFIED

Definition at line 352 of file ShaferShenoyInference.h.

    {
      EVIDENCE_ADDED,
      EVIDENCE_ERASED,
      EVIDENCE_MODIFIED
    };

StateOfInference

template<typename GUM_SCALAR >

enum gum::GraphicalModelInference::StateOfInference

stronginherited

current state of the inference

graphicalModelInference can be in one of 4 different states:

• OutdatedStructure: in this state, the inference is fully unprepared to be applied because some events changed the "logical" structure of the model: for instance a node received a hard evidence, which implies that its outgoing arcs can be removed from the model, hence involving a structural change in the model.
• OutdatedPotentials: in this state, the structure of the model remains unchanged, only some potentials stored in it have changed. Therefore, the inference probably just needs to invalidate some already computed potentials to be ready. Only a light amount of preparation is needed to be able to perform inference.
• Ready4Inference: in this state, all the data structures are ready for inference. There just remains to perform the inference computations.
• Done: the heavy computations of inference have been done. There might still remain a few light computations to perform to get the posterior potentials we need.

Enumerator
OutdatedStructure
OutdatedPotentials
ReadyForInference
Done

Definition at line 106 of file graphicalModelInference.h.

    {
      OutdatedStructure,
      OutdatedPotentials,
      ReadyForInference,
      Done
    };

Constructor & Destructor Documentation

ShaferShenoyInference() [1/2]

template<typename GUM_SCALAR>

gum::ShaferShenoyInference< GUM_SCALAR >::ShaferShenoyInference ( const IBayesNet< GUM_SCALAR > *  BN, FindBarrenNodesType  barren_type = FindBarrenNodesType::FIND_BARREN_NODES, bool  use_binary_join_tree = true  )

explicit

default constructor

~ShaferShenoyInference()

template<typename GUM_SCALAR>

gum::ShaferShenoyInference< GUM_SCALAR >::~ShaferShenoyInference ( )

final

destructor

ShaferShenoyInference() [2/2]

template<typename GUM_SCALAR>

gum::ShaferShenoyInference< GUM_SCALAR >::ShaferShenoyInference ( const ShaferShenoyInference< GUM_SCALAR > &  )

private

avoid copy constructors

Member Function Documentation

addAllTargets()

template<typename GUM_SCALAR >

void gum::MarginalTargetedInference< GUM_SCALAR >::addAllTargets ( )

finalvirtualinherited

adds all nodes as targets

Definition at line 135 of file marginalTargetedInference_tpl.h.

                                                              {
    // check if the node belongs to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");


    setTargetedMode_();   // does nothing if already in targeted mode
    for (const auto target: this->BN().dag()) {
      if (!targets__.contains(target)) {
        targets__.insert(target);
        onMarginalTargetAdded_(target);
        this->setState_(GraphicalModelInference<
                        GUM_SCALAR >::StateOfInference::OutdatedStructure);
      }
    }
  }

addEvidence() [1/8]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( NodeId  id, const Idx  val  )

finalvirtualinherited

adds a new hard evidence on node id

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if id already has an evidence

Definition at line 243 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                                {
    addEvidence(createHardEvidence__(id, val));
  }

Here is the call graph for this function:

addEvidence() [2/8]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( const std::string &  nodeName, const Idx  val  )

finalvirtualinherited

adds a new hard evidence on node named nodeName

Exceptions

UndefinedElement	if nodeName does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if nodeName already has an evidence

Definition at line 250 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                             {
    addEvidence(this->model().idFromName(nodeName), val);
  }

Here is the call graph for this function:

addEvidence() [3/8]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( NodeId  id, const std::string &  label  )

finalvirtualinherited

adds a new hard evidence on node id

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if id already has an evidence

Definition at line 259 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                                {
    addEvidence(id, this->model().variable(id)[label]);
  }

Here is the call graph for this function:

addEvidence() [4/8]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( const std::string &  nodeName, const std::string &  label  )

finalvirtualinherited

adds a new hard evidence on node named nodeName

Exceptions

UndefinedElement	if nodeName does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if nodeName already has an evidence

Definition at line 266 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                             {
    NodeId id = this->model().idFromName(nodeName);
    addEvidence(id, this->model().variable(id)[label]);
  }

Here is the call graph for this function:

addEvidence() [5/8]

template<typename GUM_SCALAR >

void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( NodeId  id, const std::vector< GUM_SCALAR > &  vals  )

finalvirtualinherited

adds a new evidence on node id (might be soft or hard)

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if id already has an evidence
FatalError	if vals=[0,0,...,0]
InvalidArgument	if the size of vals is different from the domain size of node id

Definition at line 275 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                          {
    // checks that the evidence is meaningful
    if (model__ == nullptr)
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    if (!model__->exists(id)) {
      GUM_ERROR(UndefinedElement, id << " is not a NodeId in the model");
    }

    if (model__->variable(id).domainSize() != vals.size()) {
      GUM_ERROR(InvalidArgument,
                "node " << model__->variable(id)
                        << " and its evidence vector have different sizes.");
    }

    Potential< GUM_SCALAR > pot;
    pot.add(model__->variable(id));
    pot.fillWith(vals);
    addEvidence(std::move(pot));
  }

Here is the call graph for this function:

addEvidence() [6/8]

template<typename GUM_SCALAR >

void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( const std::string &  nodeName, const std::vector< GUM_SCALAR > &  vals  )

finalvirtualinherited

adds a new evidence on node named nodeName (might be soft or hard)

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if nodeName already has an evidence
FatalError	if vals=[0,0,...,0]
InvalidArgument	if the size of vals is different from the domain size of node nodeName

Definition at line 302 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                          {
    addEvidence(this->model().idFromName(nodeName), vals);
  }

Here is the call graph for this function:

addEvidence() [7/8]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( const Potential< GUM_SCALAR > &  pot )

finalvirtualinherited

adds a new evidence on node id (might be soft or hard)

Exceptions

UndefinedElement	if the potential is defined over several nodes
UndefinedElement	if the node on which the potential is defined does not belong to the Bayesian network
InvalidArgument	if the node of the potential already has an evidence
FatalError	if pot=[0,0,...,0]

Definition at line 352 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                         {
    Potential< GUM_SCALAR > new_pot(pot);
    addEvidence(std::move(new_pot));
  }

Here is the call graph for this function:

addEvidence() [8/8]

template<typename GUM_SCALAR >

void gum::GraphicalModelInference< GUM_SCALAR >::addEvidence ( Potential< GUM_SCALAR > &&  pot )

finalvirtualinherited

adds a new evidence on node id (might be soft or hard)

Exceptions

UndefinedElement	if the potential is defined over several nodes
UndefinedElement	if the node on which the potential is defined does not belong to the Bayesian network
InvalidArgument	if the node of the potential already has an evidence
FatalError	if pot=[0,0,...,0]

Definition at line 310 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                    {
    // check if the potential corresponds to an evidence
    if (pot.nbrDim() != 1) {
      GUM_ERROR(InvalidArgument, pot << " is not mono-dimensional.");
    }
    if (model__ == nullptr)
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    NodeId id = model__->nodeId(pot.variable(0));

    if (hasEvidence(id)) {
      GUM_ERROR(InvalidArgument,
                " node " << id
                         << " already has an evidence. Please use chgEvidence().");
    }

    // check whether we have a hard evidence (and also check whether the
    // potential only contains 0 (in this case, this will automatically raise
    // an exception) )
    Idx  val;
    bool is_hard_evidence = isHardEvidence__(pot, val);

    // insert the evidence
    evidence__.insert(
       id,
       new Potential< GUM_SCALAR >(std::forward< Potential< GUM_SCALAR > >(pot)));
    if (is_hard_evidence) {   // pot is deterministic
      hard_evidence__.insert(id, val);
      hard_evidence_nodes__.insert(id);
    } else {
      soft_evidence_nodes__.insert(id);
    }
    setState_(StateOfInference::OutdatedStructure);
    onEvidenceAdded_(id, is_hard_evidence);
  }

Here is the call graph for this function:

addJointTarget()

template<typename GUM_SCALAR >

void gum::JointTargetedInference< GUM_SCALAR >::addJointTarget ( const NodeSet &  joint_target )

finalvirtualinherited

Add a set of nodes as a new joint target. As a collateral effect, every node is added as a marginal target.

Exceptions

UndefinedElement

if some node(s) do not belong to the Bayes net

Definition at line 117 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                  {
    // check if the nodes in the target belong to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    const auto& dag = this->BN().dag();
    for (const auto node: joint_target) {
      if (!dag.exists(node)) {
        GUM_ERROR(UndefinedElement,
                  "at least one one in " << joint_target
                                         << " does not belong to the bn");
      }
    }

    // check that the joint_target set does not contain the new target
    if (joint_targets__.contains(joint_target)) return;

    // check if joint_target is a subset of an already existing target
    for (const auto& target: joint_targets__) {
      if (target.isProperSupersetOf(joint_target)) return;
    }

    // check if joint_target is not a superset of an already existing target
    // in this case, we need to remove old existing target
    for (auto iter = joint_targets__.beginSafe();
         iter != joint_targets__.endSafe();
         ++iter) {
      if (iter->isProperSubsetOf(joint_target)) eraseJointTarget(*iter);
    }

    this->setTargetedMode_();   // does nothing if already in targeted mode
    joint_targets__.insert(joint_target);
    onJointTargetAdded_(joint_target);
    this->setState_(
       GraphicalModelInference< GUM_SCALAR >::StateOfInference::OutdatedStructure);
  }

Here is the call graph for this function:

addListOfEvidence()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addListOfEvidence ( const List< const Potential< GUM_SCALAR > * > &  potlist )

finalvirtualinherited

adds a new list of evidence

Exceptions

UndefinedElement	if some potential is defined over several nodes
UndefinedElement	if the node on which some potential is defined does not belong to the Bayesian network
InvalidArgument	if the node of some potential already has an evidence
FatalError	if pot=[0,0,...,0]

Definition at line 361 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                            {
    for (const auto pot: potlist)
      addEvidence(*pot);
  }

Here is the call graph for this function:

addSetOfEvidence()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::addSetOfEvidence ( const Set< const Potential< GUM_SCALAR > * > &  potset )

finalvirtualinherited

adds a new set of evidence

Exceptions

UndefinedElement	if some potential is defined over several nodes
UndefinedElement	if the node on which some potential is defined does not belong to the Bayesian network
InvalidArgument	if the node of some potential already has an evidence
FatalError	if pot=[0,0,...,0]

Definition at line 370 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                          {
    for (const auto pot: potset)
      addEvidence(*pot);
  }

Here is the call graph for this function:

addTarget() [1/2]

template<typename GUM_SCALAR >

void gum::MarginalTargetedInference< GUM_SCALAR >::addTarget ( NodeId  target )

finalvirtualinherited

Add a marginal target to the list of targets.

Exceptions

UndefinedElement

if target is not a NodeId in the Bayes net

Definition at line 111 of file marginalTargetedInference_tpl.h.

                                                                       {
    // check if the node belongs to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    if (!this->BN().dag().exists(target)) {
      GUM_ERROR(UndefinedElement, target << " is not a NodeId in the bn");
    }

    setTargetedMode_();   // does nothing if already in targeted mode
    // add the new target
    if (!targets__.contains(target)) {
      targets__.insert(target);
      onMarginalTargetAdded_(target);
      this->setState_(GraphicalModelInference<
                      GUM_SCALAR >::StateOfInference::OutdatedStructure);
    }
  }

addTarget() [2/2]

template<typename GUM_SCALAR >

void gum::MarginalTargetedInference< GUM_SCALAR >::addTarget ( const std::string &  nodeName )

finalvirtualinherited

Add a marginal target to the list of targets.

Exceptions

UndefinedElement

if target is not a NodeId in the Bayes net

Definition at line 157 of file marginalTargetedInference_tpl.h.

                                {
    // check if the node belongs to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    addTarget(this->BN().idFromName(nodeName));
  }

BN()

template<typename GUM_SCALAR >

INLINE const IBayesNet< GUM_SCALAR > & gum::BayesNetInference< GUM_SCALAR >::BN ( ) const

finalvirtualinherited

Returns a constant reference over the IBayesNet referenced by this class.

Exceptions

UndefinedElement

is raised if no Bayes net has been assigned to the inference.

Definition at line 59 of file BayesNetInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                         {
    return static_cast< const IBayesNet< GUM_SCALAR >& >(this->model());
  }

Here is the call graph for this function:

chgEvidence() [1/7]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( NodeId  id, const Idx  val  )

finalvirtualinherited

change the value of an already existing hard evidence

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if id does not already have an evidence

Definition at line 432 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                                {
    chgEvidence(createHardEvidence__(id, val));
  }

Here is the call graph for this function:

chgEvidence() [2/7]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( const std::string &  nodeName, const Idx  val  )

finalvirtualinherited

change the value of an already existing hard evidence

Exceptions

UndefinedElement	if nodeName does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if id does not already have an evidence

Definition at line 439 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                             {
    chgEvidence(this->model().idFromName(nodeName), val);
  }

Here is the call graph for this function:

chgEvidence() [3/7]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( NodeId  id, const std::string &  label  )

finalvirtualinherited

change the value of an already existing hard evidence

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if id does not already have an evidence

Definition at line 448 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                                {
    chgEvidence(id, this->model().variable(id)[label]);
  }

Here is the call graph for this function:

chgEvidence() [4/7]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( const std::string &  nodeName, const std::string &  label  )

finalvirtualinherited

change the value of an already existing hard evidence

Exceptions

UndefinedElement	if nodeName does not belong to the Bayesian network
InvalidArgument	if val is not a value for id
InvalidArgument	if id does not already have an evidence

Definition at line 455 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                             {
    NodeId id = this->model().idFromName(nodeName);
    chgEvidence(id, this->model().variable(id)[label]);
  }

Here is the call graph for this function:

chgEvidence() [5/7]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( NodeId  id, const std::vector< GUM_SCALAR > &  vals  )

finalvirtualinherited

change the value of an already existing evidence (might be soft or hard)

Exceptions

UndefinedElement	if id does not belong to the Bayesian network
InvalidArgument	if the node does not already have an evidence
FatalError	if vals=[0,0,...,0]
InvalidArgument	if the size of vals is different from the domain size of node id

Definition at line 464 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                          {
    // check whether this corresponds to an evidence
    if (model__ == nullptr)
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    if (!model__->exists(id)) {
      GUM_ERROR(UndefinedElement, id << " is not a NodeId in the model");
    }

    if (model__->variable(id).domainSize() != vals.size()) {
      GUM_ERROR(InvalidArgument,
                "node " << model__->variable(id)
                        << " and its evidence have different sizes.");
    }

    // create the potential corresponding to vals
    Potential< GUM_SCALAR > pot;
    pot.add(model__->variable(id));
    pot.fillWith(vals);
    chgEvidence(pot);
  }

Here is the call graph for this function:

chgEvidence() [6/7]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( const std::string &  nodeName, const std::vector< GUM_SCALAR > &  vals  )

finalvirtualinherited

change the value of an already existing evidence (might be soft or hard)

Exceptions

UndefinedElement	if nodeName does not belong to the Bayesian network
InvalidArgument	if the node does not already have an evidence
FatalError	if vals=[0,0,...,0]
InvalidArgument	if the size of vals is different from the domain size of node id

Definition at line 492 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                          {
    chgEvidence(this->model().idFromName(nodeName), vals);
  }

Here is the call graph for this function:

chgEvidence() [7/7]

template<typename GUM_SCALAR >

void gum::GraphicalModelInference< GUM_SCALAR >::chgEvidence ( const Potential< GUM_SCALAR > &  pot )

finalvirtualinherited

change the value of an already existing evidence (might be soft or hard)

Exceptions

UndefinedElement	if the potential is defined over several nodes
UndefinedElement	if the node on which the potential is defined does not belong to the Bayesian network
InvalidArgument	if the node of the potential does not already have an evidence
FatalError	if pot=[0,0,...,0]

Definition at line 501 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                         {
    // check if the potential corresponds to an evidence
    if (pot.nbrDim() != 1) {
      GUM_ERROR(InvalidArgument, pot << " is not a mono-dimensional potential.");
    }
    if (model__ == nullptr)
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    NodeId id = model__->nodeId(pot.variable(0));

    if (!hasEvidence(id)) {
      GUM_ERROR(InvalidArgument,
                id << " has no evidence. Please use addEvidence().");
    }

    // check whether we have a hard evidence (and also check whether the
    // potential only contains 0 (in this case, this will automatically raise
    // an exception) )
    Idx  val;
    bool is_hard_evidence = isHardEvidence__(pot, val);

    // modify the evidence already stored
    const Potential< GUM_SCALAR >* localPot = evidence__[id];
    Instantiation                  I(pot);
    for (I.setFirst(); !I.end(); I.inc()) {
      localPot->set(I, pot[I]);
    }

    // the inference state will be different
    // whether evidence change from Hard to Soft or not.
    bool hasChangedSoftHard = false;

    if (is_hard_evidence) {
      if (!hasHardEvidence(id)) {
        hasChangedSoftHard = true;
        hard_evidence__.insert(id, val);
        hard_evidence_nodes__.insert(id);
        soft_evidence_nodes__.erase(id);
      } else {
        hard_evidence__[id] = val;
      }
    } else {
      if (hasHardEvidence(id)) {   // evidence was hard
        hard_evidence__.erase(id);
        hard_evidence_nodes__.erase(id);
        soft_evidence_nodes__.insert(id);
        hasChangedSoftHard = true;
      }
    }

    if (hasChangedSoftHard) {
      setState_(StateOfInference::OutdatedStructure);
    } else {
      if (!isInferenceOutdatedStructure()) {
        setState_(StateOfInference::OutdatedPotentials);
      }
    }

    onEvidenceChanged_(id, hasChangedSoftHard);
  }

Here is the call graph for this function:

clear()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::clear ( )

virtualinherited

clears all the data structures allocated for the last inference

Reimplemented in gum::ShaferShenoyLIMIDInference< GUM_SCALAR >.

Definition at line 147 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                           {
    eraseAllEvidence();
    setState_(StateOfInference::OutdatedStructure);
  }

Here is the call graph for this function:

collectMessage__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::collectMessage__ ( NodeId  id, NodeId  from  )

private

actually perform the collect phase

computeJoinTreeRoots__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::computeJoinTreeRoots__ ( )

private

compute a root for each connected component of JT__

createNewJT__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::createNewJT__ ( )

private

create a new junction tree as well as its related data structures

diffuseMessageInvalidations__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::diffuseMessageInvalidations__ ( NodeId  from, NodeId  to, NodeSet &  cliques_invalidated  )

private

invalidate all the messages sent from a given clique

domainSizes()

template<typename GUM_SCALAR >

INLINE const NodeProperty< Size > & gum::GraphicalModelInference< GUM_SCALAR >::domainSizes ( ) const

finalvirtualinherited

get the domain sizes of the random variables of the model

Definition at line 168 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                        {
    return domain_sizes__;
  }

Here is the call graph for this function:

eraseAllEvidence()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::eraseAllEvidence ( )

finalvirtualinherited

removes all the evidence entered into the network

Definition at line 597 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                      {
    bool has_hard_evidence = !hard_evidence__.empty();
    this->onAllEvidenceErased_(has_hard_evidence);

    for (const auto& pair: evidence__) {
      if (pair.second != nullptr) { delete (pair.second); }
    }

    evidence__.clear();
    hard_evidence__.clear();
    hard_evidence_nodes__.clear();
    soft_evidence_nodes__.clear();

    if (has_hard_evidence) {
      setState_(StateOfInference::OutdatedStructure);
    } else {
      if (!isInferenceOutdatedStructure()) {
        setState_(StateOfInference::OutdatedPotentials);
      }
    }
  }

Here is the call graph for this function:

eraseAllJointTargets()

template<typename GUM_SCALAR >

INLINE void gum::JointTargetedInference< GUM_SCALAR >::eraseAllJointTargets ( )

finalvirtualinherited

Clear all previously defined joint targets.

Definition at line 96 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                         {
    if (joint_targets__.size() > 0) {
      // we already are in target mode. So no this->setTargetedMode_();  is needed
      onAllJointTargetsErased_();
      joint_targets__.clear();
      this->setState_(GraphicalModelInference<
                      GUM_SCALAR >::StateOfInference::OutdatedStructure);
    }
  }

Here is the call graph for this function:

eraseAllMarginalTargets()

template<typename GUM_SCALAR >

INLINE void gum::JointTargetedInference< GUM_SCALAR >::eraseAllMarginalTargets ( )

finalvirtualinherited

Clear all the previously defined marginal targets.

Definition at line 89 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                            {
    MarginalTargetedInference< GUM_SCALAR >::eraseAllTargets();
  }

Here is the call graph for this function:

eraseAllTargets()

template<typename GUM_SCALAR >

INLINE void gum::JointTargetedInference< GUM_SCALAR >::eraseAllTargets ( )

virtualinherited

Clear all previously defined targets (marginal and joint targets)

Clear all previously defined targets. As a result, no posterior can be computed (since we can only compute the posteriors of the marginal or joint targets that have been added by the user).

Reimplemented from gum::MarginalTargetedInference< GUM_SCALAR >.

Definition at line 109 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                    {
    eraseAllMarginalTargets();
    eraseAllJointTargets();
  }

Here is the call graph for this function:

eraseEvidence() [1/2]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::eraseEvidence ( NodeId  id )

finalvirtualinherited

removed the evidence, if any, corresponding to node id

Definition at line 568 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                            {
    if (hasEvidence(id)) {
      if (hasHardEvidence(id)) {
        onEvidenceErased_(id, true);
        hard_evidence__.erase(id);
        hard_evidence_nodes__.erase(id);
        setState_(StateOfInference::OutdatedStructure);
      } else {
        onEvidenceErased_(id, false);
        soft_evidence_nodes__.erase(id);
        if (!isInferenceOutdatedStructure()) {
          setState_(StateOfInference::OutdatedPotentials);
        }
      }

      delete (evidence__[id]);
      evidence__.erase(id);
    }
  }

Here is the call graph for this function:

eraseEvidence() [2/2]

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::eraseEvidence ( const std::string &  nodeName )

finalvirtualinherited

removed the evidence, if any, corresponding to node of name nodeName

Definition at line 589 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                {
    eraseEvidence(this->model().idFromName(nodeName));
  }

Here is the call graph for this function:

eraseJointTarget()

template<typename GUM_SCALAR >

void gum::JointTargetedInference< GUM_SCALAR >::eraseJointTarget ( const NodeSet &  joint_target )

finalvirtualinherited

removes an existing joint target

Warning

If the joint target does not already exist, the method does nothing. In particular, it does not raise any exception.

Definition at line 160 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                  {
    // check if the nodes in the target belong to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    const auto& dag = this->BN().dag();
    for (const auto node: joint_target) {
      if (!dag.exists(node)) {
        GUM_ERROR(UndefinedElement,
                  "at least one one in " << joint_target
                                         << " does not belong to the bn");
      }
    }

    // check that the joint_target set does not contain the new target
    if (joint_targets__.contains(joint_target)) {
      // note that we have to be in target mode when we are here
      // so, no this->setTargetedMode_();  is necessary
      onJointTargetErased_(joint_target);
      joint_targets__.erase(joint_target);
      this->setState_(GraphicalModelInference<
                      GUM_SCALAR >::StateOfInference::OutdatedStructure);
    }
  }

Here is the call graph for this function:

eraseTarget() [1/2]

template<typename GUM_SCALAR >

void gum::MarginalTargetedInference< GUM_SCALAR >::eraseTarget ( NodeId  target )

finalvirtualinherited

removes an existing (marginal) target

Warning

If the target does not already exist, the method does nothing. In particular, it does not raise any exception.

Definition at line 171 of file marginalTargetedInference_tpl.h.

                                                                         {
    // check if the node belongs to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    if (!this->BN().dag().exists(target)) {
      GUM_ERROR(UndefinedElement, target << " is not a NodeId in the bn");
    }


    if (targets__.contains(target)) {
      targeted_mode__ = true;   // we do not use setTargetedMode_ because we do not
                                // want to clear the targets
      onMarginalTargetErased_(target);
      targets__.erase(target);
      this->setState_(GraphicalModelInference<
                      GUM_SCALAR >::StateOfInference::OutdatedStructure);
    }
  }

eraseTarget() [2/2]

template<typename GUM_SCALAR >

void gum::MarginalTargetedInference< GUM_SCALAR >::eraseTarget ( const std::string &  nodeName )

finalvirtualinherited

removes an existing (marginal) target

Warning

If the target does not already exist, the method does nothing. In particular, it does not raise any exception.

Definition at line 196 of file marginalTargetedInference_tpl.h.

                                {
    // check if the node belongs to the Bayesian network
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    eraseTarget(this->BN().idFromName(nodeName));
  }

evidence()

template<typename GUM_SCALAR >

INLINE const NodeProperty< const Potential< GUM_SCALAR > *> & gum::GraphicalModelInference< GUM_SCALAR >::evidence ( ) const

inherited

returns the set of evidence

Definition at line 652 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                     {
    return evidence__;
  }

Here is the call graph for this function:

evidenceImpact() [1/2]

template<typename GUM_SCALAR >

Potential< GUM_SCALAR > gum::MarginalTargetedInference< GUM_SCALAR >::evidenceImpact ( NodeId  target, const NodeSet &  evs  )

inherited

Create a gum::Potential for P(target|evs) (for all instanciation of target and evs)

Warning

If some evs are d-separated, they are not included in the Potential

Parameters

bn	the BayesNet
target	the nodeId of the targetted variable
evs	the vector of nodeId of the observed variables

Returns

a Potential

Definition at line 284 of file marginalTargetedInference_tpl.h.

                                                                                 {
    const auto& vtarget = this->BN().variable(target);

    if (evs.contains(target)) {
      GUM_ERROR(InvalidArgument,
                "Target <" << vtarget.name() << "> (" << target
                           << ") can not be in evs (" << evs << ").");
    }
    auto condset = this->BN().minimalCondSet(target, evs);

    Potential< GUM_SCALAR > res;
    this->eraseAllTargets();
    this->eraseAllEvidence();
    res.add(this->BN().variable(target));
    this->addTarget(target);
    for (const auto& n: condset) {
      res.add(this->BN().variable(n));
      this->addEvidence(n, 0);
    }

    Instantiation inst(res);
    for (inst.setFirst(); !inst.end(); inst.incNotVar(vtarget)) {
      // inferring
      for (const auto& n: condset)
        this->chgEvidence(n, inst.val(this->BN().variable(n)));
      this->makeInference();
      // populate res
      for (inst.setFirstVar(vtarget); !inst.end(); inst.incVar(vtarget)) {
        res.set(inst, this->posterior(target)[inst]);
      }
      inst.setFirstVar(vtarget);   // remove inst.end() flag
    }

    return res;
  }

evidenceImpact() [2/2]

template<typename GUM_SCALAR >

Potential< GUM_SCALAR > gum::MarginalTargetedInference< GUM_SCALAR >::evidenceImpact ( const std::string &  target, const std::vector< std::string > &  evs  )

inherited

Create a gum::Potential for P(target|evs) (for all instanciation of target and evs)

Warning

If some evs are d-separated, they are not included in the Potential

Parameters

target	the nodeId of the target variable
evs	the nodeId of the observed variable

Returns

a Potential

Definition at line 323 of file marginalTargetedInference_tpl.h.

                                        {
    const auto& bn = this->BN();
    return evidenceImpact(bn.idFromName(target), bn.nodeset(evs));
  }

evidenceJointImpact() [1/2]

template<typename GUM_SCALAR >

Potential< GUM_SCALAR > gum::JointTargetedInference< GUM_SCALAR >::evidenceJointImpact ( const NodeSet &  targets, const NodeSet &  evs  )

inherited

Create a gum::Potential for P(joint targets|evs) (for all instanciation of targets and evs)

Warning

If some evs are d-separated, they are not included in the Potential

Parameters

targets	the NodeSet of the targeted variables
evs	the NodeSet of observed variables

Returns

a Potential

Definition at line 341 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                            {
    if (!(evs * targets).empty()) {
      GUM_ERROR(InvalidArgument,
                "Targets (" << targets << ") can not intersect evs (" << evs
                            << ").");
    }
    auto condset = this->BN().minimalCondSet(targets, evs);

    this->eraseAllTargets();
    this->eraseAllEvidence();

    Instantiation           iTarget;
    Potential< GUM_SCALAR > res;
    for (const auto& target: targets) {
      res.add(this->BN().variable(target));
      iTarget.add(this->BN().variable(target));
    }
    this->addJointTarget(targets);

    for (const auto& n: condset) {
      res.add(this->BN().variable(n));
      this->addEvidence(n, 0);
    }

    Instantiation inst(res);
    for (inst.setFirstOut(iTarget); !inst.end(); inst.incOut(iTarget)) {
      // inferring
      for (const auto& n: condset)
        this->chgEvidence(n, inst.val(this->BN().variable(n)));
      this->makeInference();
      // populate res
      for (inst.setFirstIn(iTarget); !inst.end(); inst.incIn(iTarget)) {
        res.set(inst, this->jointPosterior(targets)[inst]);
      }
      inst.setFirstIn(iTarget);   // remove inst.end() flag
    }

    return res;
  }

Here is the call graph for this function:

evidenceJointImpact() [2/2]

template<typename GUM_SCALAR >

Potential< GUM_SCALAR > gum::JointTargetedInference< GUM_SCALAR >::evidenceJointImpact ( const std::vector< std::string > &  targets, const std::vector< std::string > &  evs  )

inherited

Create a gum::Potential for P(joint targets|evs) (for all instanciation of targets and evs)

Warning

If some evs are d-separated, they are not included in the Potential

Parameters

targets	the vector of std::string of the targeted variables
evs	the vector of std::string of observed variables

Returns

a Potential

Definition at line 385 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                           {
    const auto& bn = this->BN();
    return evidenceJointImpact(bn.nodeset(targets), bn.nodeset(evs));
  }

Here is the call graph for this function:

evidenceProbability()

template<typename GUM_SCALAR>

GUM_SCALAR gum::ShaferShenoyInference< GUM_SCALAR >::evidenceProbability ( )

virtual

returns the probability of evidence

Implements gum::EvidenceInference< GUM_SCALAR >.

H() [1/2]

template<typename GUM_SCALAR >

INLINE GUM_SCALAR gum::MarginalTargetedInference< GUM_SCALAR >::H ( NodeId  X )

finalvirtualinherited

Entropy Compute Shanon's entropy of a node given the observation.

See also

http://en.wikipedia.org/wiki/Information_entropy

Definition at line 268 of file marginalTargetedInference_tpl.h.

                                                                       {
    return posterior(X).entropy();
  }

H() [2/2]

template<typename GUM_SCALAR >

INLINE GUM_SCALAR gum::MarginalTargetedInference< GUM_SCALAR >::H ( const std::string &  nodeName )

finalvirtualinherited

Entropy Compute Shanon's entropy of a node given the observation.

See also

http://en.wikipedia.org/wiki/Information_entropy

Definition at line 277 of file marginalTargetedInference_tpl.h.

                                                                         {
    return H(this->BN().idFromName(nodeName));
  }

hardEvidence()

template<typename GUM_SCALAR >

INLINE const NodeProperty< Idx > & gum::GraphicalModelInference< GUM_SCALAR >::hardEvidence ( ) const

inherited

indicate for each node with hard evidence which value it took

Definition at line 644 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                         {
    return hard_evidence__;
  }

Here is the call graph for this function:

hardEvidenceNodes()

template<typename GUM_SCALAR >

INLINE const NodeSet & gum::GraphicalModelInference< GUM_SCALAR >::hardEvidenceNodes ( ) const

inherited

returns the set of nodes with hard evidence

the set of nodes that received hard evidence

Definition at line 668 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                              {
    return hard_evidence_nodes__;
  }

Here is the call graph for this function:

hasEvidence() [1/3]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasEvidence ( ) const

finalvirtualinherited

indicates whether some node(s) have received evidence

Definition at line 379 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                       {
    return !evidence__.empty();
  }

Here is the call graph for this function:

hasEvidence() [2/3]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasEvidence ( NodeId  id ) const

finalvirtualinherited

indicates whether node id has received an evidence

Definition at line 386 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                                {
    return evidence__.exists(id);
  }

Here is the call graph for this function:

hasEvidence() [3/3]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasEvidence ( const std::string &  nodeName ) const

finalvirtualinherited

indicates whether node id has received an evidence

Definition at line 409 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                      {
    return hasEvidence(this->model().idFromName(nodeName));
  }

Here is the call graph for this function:

hasHardEvidence() [1/2]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasHardEvidence ( NodeId  id ) const

finalvirtualinherited

indicates whether node id has received a hard evidence

Definition at line 394 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                           {
    return hard_evidence_nodes__.exists(id);
  }

Here is the call graph for this function:

hasHardEvidence() [2/2]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasHardEvidence ( const std::string &  nodeName ) const

finalvirtualinherited

indicates whether node id has received a hard evidence

Definition at line 417 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                      {
    return hasHardEvidence(this->model().idFromName(nodeName));
  }

Here is the call graph for this function:

hasNoModel_()

template<typename GUM_SCALAR >

bool gum::GraphicalModelInference< GUM_SCALAR >::hasNoModel_ ( ) const

inlineprotectedinherited

Definition at line 533 of file graphicalModelInference.h.

{ return model__ == nullptr; };

hasSoftEvidence() [1/2]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasSoftEvidence ( NodeId  id ) const

finalvirtualinherited

indicates whether node id has received a soft evidence

Definition at line 402 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                           {
    return soft_evidence_nodes__.exists(id);
  }

Here is the call graph for this function:

hasSoftEvidence() [2/2]

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::hasSoftEvidence ( const std::string &  nodeName ) const

finalvirtualinherited

indicates whether node id has received a soft evidence

Definition at line 425 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                      {
    return hasSoftEvidence(this->model().idFromName(nodeName));
  }

Here is the call graph for this function:

I() [1/2]

template<typename GUM_SCALAR >

GUM_SCALAR gum::JointTargetedInference< GUM_SCALAR >::I ( NodeId  X, NodeId  Y  )

inherited

Mutual information between X and Y.

See also

http://en.wikipedia.org/wiki/Mutual_information

Warning

Due to limitation of joint, may not be able to compute this value

Exceptions

OperationNotAllowed

in these cases

Definition at line 283 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                       {
    Potential< GUM_SCALAR > pX, pY, *pXY = nullptr;
    if (X == Y) {
      GUM_ERROR(OperationNotAllowed, "Mutual Information I(X,Y) with X==Y");
    }

    try {
      // here use unnormalized joint posterior rather than just posterior
      // to avoid saving the posterior in the cache of the inference engines
      // like LazyPropagation or SahferShenoy.
      pXY = this->unnormalizedJointPosterior_({X, Y});
      pXY->normalize();
      pX = pXY->margSumOut({&(this->BN().variable(Y))});
      pY = pXY->margSumOut({&(this->BN().variable(X))});
    } catch (...) {
      if (pXY != nullptr) { delete pXY; }
      throw;
    }

    Instantiation i(*pXY);
    auto          res = (GUM_SCALAR)0;

    for (i.setFirst(); !i.end(); ++i) {
      GUM_SCALAR vXY = (*pXY)[i];
      GUM_SCALAR vX  = pX[i];
      GUM_SCALAR vY  = pY[i];

      if (vXY > (GUM_SCALAR)0) {
        if (vX == (GUM_SCALAR)0 || vY == (GUM_SCALAR)0) {
          GUM_ERROR(OperationNotAllowed,
                    "Mutual Information (X,Y) with P(X)=0 or P(Y)=0 "
                    "and P(X,Y)>0");
        }

        res += vXY * (std::log2(vXY) - std::log2(vX) - std::log2(vY));
      }
    }

    delete pXY;

    return res;
  }

Here is the call graph for this function:

I() [2/2]

template<typename GUM_SCALAR >

GUM_SCALAR gum::JointTargetedInference< GUM_SCALAR >::I ( const std::string &  Xname, const std::string &  Yname  )

inherited

Mutual information between X and Y.

See also

http://en.wikipedia.org/wiki/Mutual_information

Warning

Due to limitation of joint, may not be able to compute this value

Exceptions

OperationNotAllowed

in these cases

Definition at line 264 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                             {
    return I(this->BN().idFromName(Xname), this->BN().idFromName(Yname));
  }

Here is the call graph for this function:

invalidateAllMessages__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::invalidateAllMessages__ ( )

private

invalidate all messages, posteriors and created potentials

isInferenceDone()

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::isInferenceDone ( ) const

finalvirtualnoexceptinherited

returns whether the inference object is in a InferenceDone state

The inference object is in a done state when the posteriors can be retrieved without performing a new inference, i.e., all the heavy computations have already been performed. Typically, in a junction tree algorithm, this corresponds to a situation in which all the messages needed in the JT have been computed and sent.

Definition at line 89 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                           {
    return (state__ == StateOfInference::Done);
  }

Here is the call graph for this function:

isInferenceOutdatedPotentials()

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::isInferenceOutdatedPotentials ( ) const

finalvirtualnoexceptinherited

returns whether the inference object is in a OutdatedPotential state

Definition at line 82 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                       {
    return (state__ == StateOfInference::OutdatedPotentials);
  }

Here is the call graph for this function:

isInferenceOutdatedStructure()

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::isInferenceOutdatedStructure ( ) const

finalvirtualnoexceptinherited

returns whether the inference object is in a OutdatedStructure state

Definition at line 75 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                    {
    return (state__ == StateOfInference::OutdatedStructure);
  }

Here is the call graph for this function:

isInferenceReady()

template<typename GUM_SCALAR >

INLINE bool gum::GraphicalModelInference< GUM_SCALAR >::isInferenceReady ( ) const

finalvirtualnoexceptinherited

returns whether the inference object is in a ready state

Definition at line 70 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                            {
    return (state__ == StateOfInference::ReadyForInference);
  }

Here is the call graph for this function:

isJointTarget()

template<typename GUM_SCALAR >

INLINE bool gum::JointTargetedInference< GUM_SCALAR >::isJointTarget ( const NodeSet &  vars ) const

finalvirtualinherited

return true if target is a joint target.

Definition at line 69 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                {
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");

    const auto& dag = this->BN().dag();
    for (const auto var: vars) {
      if (!dag.exists(var)) {
        GUM_ERROR(UndefinedElement, var << " is not a NodeId in the bn");
      }
    }

    return joint_targets__.contains(vars);
  }

Here is the call graph for this function:

isNewJTNeeded__()

template<typename GUM_SCALAR>

bool gum::ShaferShenoyInference< GUM_SCALAR >::isNewJTNeeded__ ( ) const

private

check whether a new join tree is really needed for the next inference

isTarget() [1/2]

template<typename GUM_SCALAR >

INLINE bool gum::MarginalTargetedInference< GUM_SCALAR >::isTarget ( NodeId  node ) const

finalvirtualinherited

return true if variable is a (marginal) target

Definition at line 75 of file marginalTargetedInference_tpl.h.

                                                                        {
    // check that the variable belongs to the bn
    if (this->hasNoModel_())
      GUM_ERROR(NullElement,
                "No Bayes net has been assigned to the "
                "inference algorithm");
    if (!this->BN().dag().exists(node)) {
      GUM_ERROR(UndefinedElement, node << " is not a NodeId in the bn");
    }

    return targets__.contains(node);
  }

isTarget() [2/2]

template<typename GUM_SCALAR >

INLINE bool gum::MarginalTargetedInference< GUM_SCALAR >::isTarget ( const std::string &  nodeName ) const

finalvirtualinherited

return true if variable is a (marginal) target

Definition at line 90 of file marginalTargetedInference_tpl.h.

                                      {
    return isTarget(this->BN().idFromName(nodeName));
  }

isTargetedMode_()

template<typename GUM_SCALAR >

INLINE bool gum::MarginalTargetedInference< GUM_SCALAR >::isTargetedMode_ ( ) const

protectedinherited

Definition at line 332 of file marginalTargetedInference_tpl.h.

                                                                             {
    return targeted_mode__;
  }

jointMutualInformation() [1/2]

template<typename GUM_SCALAR >

GUM_SCALAR gum::JointTargetedInference< GUM_SCALAR >::jointMutualInformation ( const NodeSet &  targets )

inherited

Mutual information between targets.

See also

https://en.wikipedia.org/wiki/Interaction_information

Parameters

targets

the NodeSet of the targeted variables

Definition at line 394 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                             {
    const auto& bn  = this->BN();
    const Size  siz = targets.size();
    if (siz <= 1) {
      GUM_ERROR(InvalidArgument,
                "jointMutualInformation needs at least 2 variables (targets="
                   << targets << ")");
    }

    this->eraseAllTargets();
    this->eraseAllEvidence();
    this->addJointTarget(targets);
    this->makeInference();
    const auto po = this->jointPosterior(targets);

    gum::Instantiation caracteristic;
    gum::Instantiation variables;
    for (const auto nod: targets) {
      const auto& var = bn.variable(nod);
      auto        pv  = new gum::RangeVariable(var.name(), "", 0, 1);
      caracteristic.add(*pv);
      variables.add(var);
    }

    Set< const DiscreteVariable* > sov;

    const GUM_SCALAR start = (siz % 2 == 0) ? GUM_SCALAR(-1.0) : GUM_SCALAR(1.0);
    GUM_SCALAR       sign;
    GUM_SCALAR       res = GUM_SCALAR(0.0);

    caracteristic.setFirst();
    for (caracteristic.inc(); !caracteristic.end(); caracteristic.inc()) {
      sov.clear();
      sign = start;
      for (Idx i = 0; i < caracteristic.nbrDim(); i++) {
        if (caracteristic.val(i) == 1) {
          sign = -sign;
          sov.insert(&variables.variable(i));
        }
      }
      res += sign * po.margSumIn(sov).entropy();
    }

    for (Idx i = 0; i < caracteristic.nbrDim(); i++) {
      delete &caracteristic.variable(i);
    }

    return res;
  }

Here is the call graph for this function:

jointMutualInformation() [2/2]

template<typename GUM_SCALAR >

GUM_SCALAR gum::JointTargetedInference< GUM_SCALAR >::jointMutualInformation ( const std::vector< std::string > &  targets )

inherited

Mutual information between targets.

See also

https://en.wikipedia.org/wiki/Interaction_information

Parameters

targets

the vector of std::string of the targeted variables

Definition at line 446 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                            {
    return jointMutualInformation(this->BN().ids(targets));
  }

Here is the call graph for this function:

jointPosterior()

template<typename GUM_SCALAR >

const Potential< GUM_SCALAR > & gum::JointTargetedInference< GUM_SCALAR >::jointPosterior ( const NodeSet &  nodes )

finalvirtualinherited

Compute the joint posterior of a set of nodes.

Returns

a const ref to the posterior joint probability of the set of nodes.

Parameters

nodes

the set of nodes whose posterior joint probability is wanted

Warning

for efficiency reasons, the potential is stored into the inference engine and is returned by reference. In order to ensure that the potential may still exist even if the Inference object is destroyed, the user has to copy it explicitly.

prepareInference and makeInference may be applied if needed.

Exceptions

UndefinedElement

if nodes is not in the targets

Definition at line 211 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                              {
    // try to get the smallest set of targets that contains "nodes"
    NodeSet set;
    bool    found_exact_target = false;

    if (joint_targets__.contains(nodes)) {
      set                = nodes;
      found_exact_target = true;
    } else {
      for (const auto& target: joint_targets__) {
        if (nodes.isProperSubsetOf(target)) {
          set = target;
          break;
        }
      }
    }

    if (set.empty()) {
      GUM_ERROR(UndefinedElement,
                " no joint target containing " << nodes << " could be found among "
                                               << joint_targets__);
    }

    if (!this->isInferenceDone()) { this->makeInference(); }

    if (found_exact_target)
      return jointPosterior_(nodes);
    else
      return jointPosterior_(nodes, set);
  }

Here is the call graph for this function:

jointPosterior_() [1/2]

template<typename GUM_SCALAR>

const Potential< GUM_SCALAR >& gum::ShaferShenoyInference< GUM_SCALAR >::jointPosterior_ ( const NodeSet &  set )

finalprotectedvirtual

returns the posterior of a declared target set

Parameters

set	The set of ids of the variables whose joint posterior is looked for.

Implements gum::JointTargetedInference< GUM_SCALAR >.

jointPosterior_() [2/2]

template<typename GUM_SCALAR>

const Potential< GUM_SCALAR >& gum::ShaferShenoyInference< GUM_SCALAR >::jointPosterior_ ( const NodeSet &  wanted_target, const NodeSet &  declared_target  )

finalprotectedvirtual

asks derived classes for the joint posterior of a set of variables not declared as a joint target

Parameters

wanted_target	The set of ids of the variables whose joint posterior is looked for.
declared_target	the joint target declared by the user that contains set

Implements gum::JointTargetedInference< GUM_SCALAR >.

joinTree()

template<typename GUM_SCALAR>

const JoinTree* gum::ShaferShenoyInference< GUM_SCALAR >::joinTree

(

)

returns the current join tree used

Lazy Propagation does not use a junction tree but a binary join tree because this may enable faster inferences. So do not be surprised to see that somes cliques are contained into others in this tree.

jointTargets()

template<typename GUM_SCALAR >

INLINE const Set< NodeSet > & gum::JointTargetedInference< GUM_SCALAR >::jointTargets ( ) const

finalvirtualnoexceptinherited

returns the list of joint targets

returns the list of target sets

Definition at line 192 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                       {
    return joint_targets__;
  }

Here is the call graph for this function:

junctionTree()

template<typename GUM_SCALAR>

const JunctionTree* gum::ShaferShenoyInference< GUM_SCALAR >::junctionTree

(

)

returns the current junction tree

Lazy Propagation does not use a junction tree but a binary join tree because this may enable faster inferences. This method return the junction tree, before optimizations

makeInference()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::makeInference ( )

finalvirtualinherited

perform the heavy computations needed to compute the targets' posteriors

In a Junction tree propagation scheme, for instance, the heavy computations are those of the messages sent in the JT. This is precisely what makeInference should compute. Later, the computations of the posteriors can be done "lightly" by multiplying and projecting those messages.

Definition at line 714 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                   {
    if (isInferenceDone()) { return; }

    if (!isInferenceReady()) { prepareInference(); }

    makeInference_();

    setState_(StateOfInference::Done);
  }

Here is the call graph for this function:

makeInference_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::makeInference_ ( )

finalprotectedvirtual

called when the inference has to be performed effectively

Once the inference is done, fillPosterior_ can be called.

Implements gum::GraphicalModelInference< GUM_SCALAR >.

marginalizeOut__()

template<typename GUM_SCALAR>

PotentialSet__ gum::ShaferShenoyInference< GUM_SCALAR >::marginalizeOut__ ( PotentialSet__  pot_list, Set< const DiscreteVariable * > &  del_vars, Set< const DiscreteVariable * > &  kept_vars  )

private

removes variables del_vars from a list of potentials and returns the resulting list

model()

template<typename GUM_SCALAR >

INLINE const GraphicalModel & gum::GraphicalModelInference< GUM_SCALAR >::model ( ) const

finalvirtualinherited

Returns a constant reference over the IBayesNet referenced by this class.

Exceptions

UndefinedElement

is raised if no Bayes net has been assigned to the inference.

Definition at line 114 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                  {
    if (model__ == nullptr)
      GUM_ERROR(UndefinedElement,
                "No Bayes net has been assigned to "
                "the inference algorithm.");
    return *model__;
  }

Here is the call graph for this function:

nbrEvidence()

template<typename GUM_SCALAR >

INLINE Size gum::GraphicalModelInference< GUM_SCALAR >::nbrEvidence ( ) const

finalvirtualinherited

returns the number of evidence entered into the Bayesian network

Definition at line 622 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                       {
    return evidence__.size();
  }

Here is the call graph for this function:

nbrHardEvidence()

template<typename GUM_SCALAR >

INLINE Size gum::GraphicalModelInference< GUM_SCALAR >::nbrHardEvidence ( ) const

finalvirtualinherited

returns the number of hard evidence entered into the Bayesian network

Definition at line 629 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                           {
    return hard_evidence_nodes__.size();
  }

Here is the call graph for this function:

nbrJointTargets()

template<typename GUM_SCALAR >

INLINE Size gum::JointTargetedInference< GUM_SCALAR >::nbrJointTargets ( ) const

finalvirtualnoexceptinherited

returns the number of joint targets

returns the number of target sets

Definition at line 199 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                          {
    return joint_targets__.size();
  }

Here is the call graph for this function:

nbrSoftEvidence()

template<typename GUM_SCALAR >

INLINE Size gum::GraphicalModelInference< GUM_SCALAR >::nbrSoftEvidence ( ) const

finalvirtualinherited

returns the number of soft evidence entered into the Bayesian network

Definition at line 636 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                           {
    return soft_evidence_nodes__.size();
  }

Here is the call graph for this function:

nbrTargets()

template<typename GUM_SCALAR >

INLINE const Size gum::MarginalTargetedInference< GUM_SCALAR >::nbrTargets ( ) const

finalvirtualnoexceptinherited

returns the number of marginal targets

Definition at line 218 of file marginalTargetedInference_tpl.h.

                                                                        {
    return targets__.size();
  }

onAllEvidenceErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onAllEvidenceErased_ ( bool  contains_hard_evidence )

finalprotectedvirtual

fired before all the evidence are erased

Implements gum::GraphicalModelInference< GUM_SCALAR >.

onAllJointTargetsErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onAllJointTargetsErased_ ( )

finalprotectedvirtual

fired before a all the joint targets are removed

Implements gum::JointTargetedInference< GUM_SCALAR >.

onAllMarginalTargetsAdded_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onAllMarginalTargetsAdded_ ( )

finalprotectedvirtual

fired after all the nodes of the BN are added as single targets

Implements gum::MarginalTargetedInference< GUM_SCALAR >.

onAllMarginalTargetsErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onAllMarginalTargetsErased_ ( )

finalprotectedvirtual

fired before a all the single targets are removed

Implements gum::MarginalTargetedInference< GUM_SCALAR >.

onAllTargetsErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onAllTargetsErased_ ( )

finalprotectedvirtual

fired before a all single and joint_targets are removed

Implements gum::JointTargetedInference< GUM_SCALAR >.

onEvidenceAdded_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onEvidenceAdded_ ( const NodeId  id, bool  isHardEvidence  )

finalprotectedvirtual

fired after a new evidence is inserted

Implements gum::GraphicalModelInference< GUM_SCALAR >.

onEvidenceChanged_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onEvidenceChanged_ ( const NodeId  id, bool  hasChangedSoftHard  )

finalprotectedvirtual

fired after an evidence is changed, in particular when its status (soft/hard) changes

Parameters

nodeId	the node of the changed evidence
hasChangedSoftHard	true if the evidence has changed from Soft to Hard or from Hard to Soft

Implements gum::GraphicalModelInference< GUM_SCALAR >.

onEvidenceErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onEvidenceErased_ ( const NodeId  id, bool  isHardEvidence  )

finalprotectedvirtual

fired before an evidence is removed

Implements gum::GraphicalModelInference< GUM_SCALAR >.

onJointTargetAdded_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onJointTargetAdded_ ( const NodeSet &  set )

finalprotectedvirtual

fired after a new joint target is inserted

Parameters

set	The set of target variable's ids.

Implements gum::JointTargetedInference< GUM_SCALAR >.

onJointTargetErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onJointTargetErased_ ( const NodeSet &  set )

finalprotectedvirtual

fired before a joint target is removed

Parameters

set	The set of target variable's ids.

Implements gum::JointTargetedInference< GUM_SCALAR >.

onMarginalTargetAdded_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onMarginalTargetAdded_ ( const NodeId  id )

finalprotectedvirtual

fired after a new single target is inserted

Parameters

id	The target variable's id.

Implements gum::MarginalTargetedInference< GUM_SCALAR >.

onMarginalTargetErased_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onMarginalTargetErased_ ( const NodeId  id )

finalprotectedvirtual

fired before a single target is removed

Parameters

id	The target variable's id.

Implements gum::MarginalTargetedInference< GUM_SCALAR >.

onModelChanged_()

template<typename GUM_SCALAR>

virtual void gum::ShaferShenoyInference< GUM_SCALAR >::onModelChanged_ ( const GraphicalModel *  bn )

finalprotectedvirtual

fired after a new Bayes net has been assigned to the engine

Reimplemented from gum::JointTargetedInference< GUM_SCALAR >.

onStateChanged_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::onStateChanged_ ( )

inlinefinalprotectedvirtual

fired when the stage is changed

Implements gum::GraphicalModelInference< GUM_SCALAR >.

Definition at line 125 of file ShaferShenoyInference.h.

{};

operator=()

template<typename GUM_SCALAR>

ShaferShenoyInference< GUM_SCALAR >& gum::ShaferShenoyInference< GUM_SCALAR >::operator= ( const ShaferShenoyInference< GUM_SCALAR > &  )

private

avoid copy operators

posterior() [1/2]

template<typename GUM_SCALAR >

const Potential< GUM_SCALAR > & gum::JointTargetedInference< GUM_SCALAR >::posterior ( NodeId  node )

finalvirtualinherited

Computes and returns the posterior of a node.

Returns

a const ref to the posterior probability of the node.

Parameters

node	the node for which we need a posterior probability

Warning

for efficiency reasons, the potential is stored into the inference engine and is returned by reference. In order to ensure that the potential may still exist even if the Inference object is destroyed, the user has to copy it explicitly.

prepareInference and makeInference may be applied if needed by the posterior method.

Exceptions

UndefinedElement

if node is not in the set of targets

Reimplemented from gum::MarginalTargetedInference< GUM_SCALAR >.

Definition at line 246 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                {
    if (this->isTarget(node))
      return MarginalTargetedInference< GUM_SCALAR >::posterior(node);
    else
      return jointPosterior(NodeSet{node});
  }

Here is the call graph for this function:

posterior() [2/2]

template<typename GUM_SCALAR >

const Potential< GUM_SCALAR > & gum::JointTargetedInference< GUM_SCALAR >::posterior ( const std::string &  nodeName )

finalvirtualinherited

Computes and returns the posterior of a node.

Returns

a const ref to the posterior probability of the node.

Parameters

node	the node for which we need a posterior probability

Warning

for efficiency reasons, the potential is stored into the inference engine and is returned by reference. In order to ensure that the potential may still exist even if the Inference object is destroyed, the user has to copy it explicitly.

prepareInference and makeInference may be applied if needed by the posterior method.

Exceptions

UndefinedElement

if node is not in the set of targets

Reimplemented from gum::MarginalTargetedInference< GUM_SCALAR >.

Definition at line 256 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                              {
    return posterior(this->BN().idFromName(nodeName));
  }

Here is the call graph for this function:

posterior_()

template<typename GUM_SCALAR>

const Potential< GUM_SCALAR >& gum::ShaferShenoyInference< GUM_SCALAR >::posterior_ ( NodeId  id )

finalprotectedvirtual

returns the posterior of a given variable

Parameters

id	The variable's id.

Implements gum::MarginalTargetedInference< GUM_SCALAR >.

prepareInference()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::prepareInference ( )

finalvirtualinherited

prepare the internal inference structures for the next inference

Definition at line 695 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                      {
    if (isInferenceReady() || isInferenceDone()) { return; }

    if (model__ == nullptr)
      GUM_ERROR(NullElement,
                "No model been assigned to the "
                "inference algorithm");

    if (state__ == StateOfInference::OutdatedStructure)
      updateOutdatedStructure_();
    else
      updateOutdatedPotentials_();

    setState_(StateOfInference::ReadyForInference);
  }

Here is the call graph for this function:

produceMessage__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::produceMessage__ ( NodeId  from_id, NodeId  to_id  )

private

creates the message sent by clique from_id to clique to_id

removeBarrenVariables__()

template<typename GUM_SCALAR>

PotentialSet__ gum::ShaferShenoyInference< GUM_SCALAR >::removeBarrenVariables__ ( PotentialSet__ &  pot_list, Set< const DiscreteVariable * > &  del_vars  )

private

setBN()

template<typename GUM_SCALAR >

void gum::BayesNetInference< GUM_SCALAR >::setBN ( const IBayesNet< GUM_SCALAR > *  bn )

virtualinherited

assigns a new BN to the inference engine

Assigns a new BN to the BayesNetInference engine and sends messages to the descendants of BayesNetInference to inform them that the BN has changed.

Warning

By default, all the nodes of the Bayes net are targets.

note that, by aGrUM's rule, the bn is not copied into the inference engine but only referenced.

Definition at line 66 of file BayesNetInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                               {
    this->setModel_(bn);
  }

Here is the call graph for this function:

setCombinationFunction__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::setCombinationFunction__ ( Potential< GUM_SCALAR > *(*)(const Potential< GUM_SCALAR > &, const Potential< GUM_SCALAR > &)  comb )

private

sets the operator for performing the combinations

setFindBarrenNodesType()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::setFindBarrenNodesType

(

FindBarrenNodesType

type

)

sets how we determine barren nodes

Barren nodes are unnecessary for probability inference, so they can be safely discarded in this case (type = FIND_BARREN_NODES). This speeds-up inference. However, there are some cases in which we do not want to remove barren nodes, typically when we want to answer queries such as Most Probable Explanations (MPE).

setModel_()

template<typename GUM_SCALAR >

void gum::GraphicalModelInference< GUM_SCALAR >::setModel_ ( const GraphicalModel *  model )

protectedinherited

Definition at line 125 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                  {
    clear();
    model__ = model;
    computeDomainSizes__();
    onModelChanged_(model);
    setState_(StateOfInference::OutdatedStructure);
  }

Here is the call graph for this function:

setModelDuringConstruction_()

template<typename GUM_SCALAR >

void gum::GraphicalModelInference< GUM_SCALAR >::setModelDuringConstruction_ ( const GraphicalModel *  model )

protectedinherited

assigns a model during the inference engine construction

Definition at line 137 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                  {
    model__ = model;
    computeDomainSizes__();
    setState_(StateOfInference::OutdatedStructure);
  }

Here is the call graph for this function:

setOutdatedPotentialsState_()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::setOutdatedPotentialsState_ ( )

protectedinherited

puts the inference into an OutdatedPotentials state if it is not already in an OutdatedStructure state

OutdatedPotentials: in this state, the structure of the model remains unchanged, only some potentials stored in it have changed. Therefore, the inference probably just needs to invalidate some already computed potentials to be ready. Only a light amount of preparation is needed to be able to perform inference.

Definition at line 688 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                        {
    setState_(StateOfInference::OutdatedPotentials);
  }

Here is the call graph for this function:

setOutdatedStructureState_()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::setOutdatedStructureState_ ( )

protectedinherited

put the inference into an outdated model structure state

OutdatedStructure: in this state, the inference is fully unprepared to be applied because some events changed the "logical" structure of the model: for instance a node received a hard evidence, which implies that its outgoing arcs can be removed from the model, hence involving a structural change in the model. As a consequence, the (incremental) inference (probably) needs a significant amount of preparation to be ready for the next inference. In a Lazy propagation, for instance, this step amounts to compute a new join tree, hence a new structure in which inference will be applied. Note that classes that inherit from graphicalModelInference may be smarter than graphicalModelInference and may, in some situations, find out that their data structures are still ok for inference and, therefore, only resort to perform the actions related to the OutdatedPotentials state. As an example, consider a LazyPropagation inference in Bayes Net A->B->C->D->E in which C has received hard evidence e_C and E is the only target. In this case, A and B are not needed for inference, the only potentials that matter are P(D|e_C) and P(E|D). So the smallest join tree needed for inference contains only one clique DE. Now, adding new evidence e_A on A has no impact on E given hard evidence e_C. In this case, LazyPropagation can be smart and not update its join tree.

Definition at line 679 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                                {
    setState_(StateOfInference::OutdatedStructure);
  }

Here is the call graph for this function:

setProjectionFunction__()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::setProjectionFunction__ ( Potential< GUM_SCALAR > *(*)(const Potential< GUM_SCALAR > &, const Set< const DiscreteVariable * > &)  proj )

private

sets the operator for performing the projections

setState_()

template<typename GUM_SCALAR >

INLINE void gum::GraphicalModelInference< GUM_SCALAR >::setState_ ( const StateOfInference  state )

finalprotectedvirtualinherited

set the state of the inference engine and call the notification onStateChanged_ when necessary (i.e. when the state has effectively changed).

Definition at line 103 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                   {
    if (state__ != state) {
      state__ = state;
      onStateChanged_();
    }
  }

Here is the call graph for this function:

setTargetedMode_()

template<typename GUM_SCALAR >

INLINE void gum::MarginalTargetedInference< GUM_SCALAR >::setTargetedMode_ ( )

protectedinherited

Definition at line 336 of file marginalTargetedInference_tpl.h.

                                                                        {
    if (!targeted_mode__) {
      targets__.clear();
      targeted_mode__ = true;
    }
  }

setTriangulation()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::setTriangulation

(

const Triangulation &

new_triangulation

)

use a new triangulation algorithm

softEvidenceNodes()

template<typename GUM_SCALAR >

INLINE const NodeSet & gum::GraphicalModelInference< GUM_SCALAR >::softEvidenceNodes ( ) const

inherited

returns the set of nodes with soft evidence

the set of nodes that received soft evidence

Definition at line 660 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                              {
    return soft_evidence_nodes__;
  }

Here is the call graph for this function:

state()

template<typename GUM_SCALAR >

INLINE GraphicalModelInference< GUM_SCALAR >::StateOfInference gum::GraphicalModelInference< GUM_SCALAR >::state ( ) const

finalvirtualnoexceptinherited

returns the state of the inference engine

Definition at line 97 of file graphicalModelInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                 {
    return state__;
  }

Here is the call graph for this function:

targets()

template<typename GUM_SCALAR >

INLINE const NodeSet & gum::MarginalTargetedInference< GUM_SCALAR >::targets ( ) const

finalvirtualnoexceptinherited

returns the list of marginal targets

Definition at line 211 of file marginalTargetedInference_tpl.h.

                                                                               {
    return targets__;
  }

unnormalizedJointPosterior_() [1/2]

template<typename GUM_SCALAR>

Potential< GUM_SCALAR >* gum::ShaferShenoyInference< GUM_SCALAR >::unnormalizedJointPosterior_ ( NodeId  id )

finalprotectedvirtual

returns a fresh potential equal to P(argument,evidence)

Implements gum::JointTargetedInference< GUM_SCALAR >.

unnormalizedJointPosterior_() [2/2]

template<typename GUM_SCALAR>

Potential< GUM_SCALAR >* gum::ShaferShenoyInference< GUM_SCALAR >::unnormalizedJointPosterior_ ( const NodeSet &  set )

finalprotectedvirtual

returns a fresh potential equal to P(argument,evidence)

Implements gum::JointTargetedInference< GUM_SCALAR >.

updateOutdatedPotentials_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::updateOutdatedPotentials_ ( )

finalprotectedvirtual

prepares inference when the latter is in OutdatedPotentials state

Note that the values of evidence are not necessarily known and can be changed between updateOutdatedStructure_ and makeInference_.

Implements gum::GraphicalModelInference< GUM_SCALAR >.

updateOutdatedStructure_()

template<typename GUM_SCALAR>

void gum::ShaferShenoyInference< GUM_SCALAR >::updateOutdatedStructure_ ( )

finalprotectedvirtual

prepares inference when the latter is in OutdatedStructure state

Note that the values of evidence are not necessarily known and can be changed between updateOutdatedStructure_ and makeInference_.

Implements gum::GraphicalModelInference< GUM_SCALAR >.

VI() [1/2]

template<typename GUM_SCALAR >

INLINE GUM_SCALAR gum::JointTargetedInference< GUM_SCALAR >::VI ( NodeId  X, NodeId  Y  )

inherited

Variation of information between X and Y.

See also

http://en.wikipedia.org/wiki/Variation_of_information

Warning

Due to limitation of joint, may not be able to compute this value

Exceptions

OperationNotAllowed

in these cases

See also

http://en.wikipedia.org/wiki/Variation_of_information

Warning

Due to limitation of , may not be able to compute this value

Exceptions

OperationNotAllowed

in these cases

Definition at line 334 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                               {
    return this->H(X) + this->H(Y) - 2 * I(X, Y);
  }

Here is the call graph for this function:

VI() [2/2]

template<typename GUM_SCALAR >

GUM_SCALAR gum::JointTargetedInference< GUM_SCALAR >::VI ( const std::string &  Xname, const std::string &  Yname  )

inherited

Variation of information between X and Y.

See also

http://en.wikipedia.org/wiki/Variation_of_information

Warning

Due to limitation of joint, may not be able to compute this value

Exceptions

OperationNotAllowed

in these cases

Definition at line 270 of file jointTargetedInference_tpl.h.

References gum::Set< Key, Alloc >::emplace().

                                                                              {
    return VI(this->BN().idFromName(Xname), this->BN().idFromName(Yname));
  }

Here is the call graph for this function:

Member Data Documentation

barren_nodes_type__

template<typename GUM_SCALAR>

FindBarrenNodesType gum::ShaferShenoyInference< GUM_SCALAR >::barren_nodes_type__

private

the type of barren nodes computation we wish

Definition at line 227 of file ShaferShenoyInference.h.

clique_potentials__

template<typename GUM_SCALAR>

NodeProperty< PotentialSet__ > gum::ShaferShenoyInference< GUM_SCALAR >::clique_potentials__

private

the list of all potentials stored in the cliques

This structure contains a list for each clique in the join tree. If a clique did not received any potential, then its list is empty but the entry for the clique does exist. Note that clique potentials contain also soft evidence and the CPTs that were projected to remove their variables that received hard evidence. The product of all these potentials is precisely the potential stored into clique_ss_potential__

Definition at line 289 of file ShaferShenoyInference.h.

clique_ss_potential__

template<typename GUM_SCALAR>

NodeProperty< const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::clique_ss_potential__

private

the potentials stored into the cliques by Shafer-Shenoy

For a given clique, there is an entry in clique_ss_potential__ if and only if the clique received some potential(s). In this case, the potential stored is the combination of all the corresponding list of potentials in clique_potentials__.

Definition at line 296 of file ShaferShenoyInference.h.

combination_op__

template<typename GUM_SCALAR>

Potential< GUM_SCALAR >*(* gum::ShaferShenoyInference< GUM_SCALAR >::combination_op__) (const Potential< GUM_SCALAR > &, const Potential< GUM_SCALAR > &)

inlineprivate

the operator for performing the combinations

Definition at line 235 of file ShaferShenoyInference.h.

                                                                                {
       SSNewmultiPotential};

constants__

template<typename GUM_SCALAR>

NodeProperty< GUM_SCALAR > gum::ShaferShenoyInference< GUM_SCALAR >::constants__

private

the constants resulting from the projections of CPTs defined over only hard evidence nodes remove this constant and insert the notion of a constant into potentials/multidim arrays

Definition at line 323 of file ShaferShenoyInference.h.

created_potentials__

template<typename GUM_SCALAR>

ArcProperty< PotentialSet__ > gum::ShaferShenoyInference< GUM_SCALAR >::created_potentials__

private

the set of potentials created for the last inference messages

This structure contains only the arcs on which potentials have been created.

Warning

Note that the CPTs that were projected due to hard evidence do not belong to this structure, they are kept in hard_ev_projected_CPTs__.

Definition at line 309 of file ShaferShenoyInference.h.

evidence_changes__

template<typename GUM_SCALAR>

NodeProperty< EvidenceChangeType > gum::ShaferShenoyInference< GUM_SCALAR >::evidence_changes__

private

indicates which nodes of the BN have evidence that changed since the last inference

Definition at line 361 of file ShaferShenoyInference.h.

graph__

template<typename GUM_SCALAR>

UndiGraph gum::ShaferShenoyInference< GUM_SCALAR >::graph__

private

the undigraph extracted from the BN and used to construct the join tree

If all nodes are targets, this graph corresponds to the moral graph of the BN. Otherwise, it may be a subgraph of this moral graph. For instance if the BN is A->B->C and only B is a target, graph__ will be equal to A-B if we exploit barren nodes (C is a barren node and, therefore, can be removed for inference).

Definition at line 252 of file ShaferShenoyInference.h.

hard_ev_nodes__

template<typename GUM_SCALAR>

NodeSet gum::ShaferShenoyInference< GUM_SCALAR >::hard_ev_nodes__

private

the hard evidence nodes which were projected in CPTs

Definition at line 349 of file ShaferShenoyInference.h.

hard_ev_projected_CPTs__

template<typename GUM_SCALAR>

NodeProperty< const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::hard_ev_projected_CPTs__

private

the CPTs that were projected due to hard evidence nodes

For each node whose CPT is defined over some nodes that contain some hard evidence, assigns a new projected CPT that does not contain these nodes anymore.

Warning

These potentials are owned by LayPropagation.

Definition at line 346 of file ShaferShenoyInference.h.

is_new_jt_needed__

template<typename GUM_SCALAR>

bool gum::ShaferShenoyInference< GUM_SCALAR >::is_new_jt_needed__ {true}

private

indicates whether a new join tree is needed for the next inference

when modifying the set of hard evidence, we can determine that the current JT is no more appropriate for inference. This variable enables us to keep track of this.

Definition at line 264 of file ShaferShenoyInference.h.

joint_target_posteriors__

template<typename GUM_SCALAR>

HashTable< NodeSet, const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::joint_target_posteriors__

private

the set of set target posteriors computed during the last inference

the posteriors are owned by ShaferShenoyInference.

Definition at line 317 of file ShaferShenoyInference.h.

joint_target_to_clique__

template<typename GUM_SCALAR>

HashTable< NodeSet, NodeId > gum::ShaferShenoyInference< GUM_SCALAR >::joint_target_to_clique__

private

for each set target, assign a clique in the JT that contains it

Definition at line 279 of file ShaferShenoyInference.h.

JT__

template<typename GUM_SCALAR>

JoinTree* gum::ShaferShenoyInference< GUM_SCALAR >::JT__ {nullptr}

private

the join (or junction) tree used to answer the last inference query

Definition at line 255 of file ShaferShenoyInference.h.

junctionTree__

template<typename GUM_SCALAR>

JunctionTree* gum::ShaferShenoyInference< GUM_SCALAR >::junctionTree__ {nullptr}

private

the junction tree to answer the last inference query

Definition at line 258 of file ShaferShenoyInference.h.

messages_computed__

template<typename GUM_SCALAR>

ArcProperty< bool > gum::ShaferShenoyInference< GUM_SCALAR >::messages_computed__

private

indicates whether a message (from one clique to another) has been computed

Here, all the messages, computed or not, are put into the property, only the Boolean makes the difference between messages computed and those that were not computed

Definition at line 330 of file ShaferShenoyInference.h.

node_to_clique__

template<typename GUM_SCALAR>

HashTable< NodeId, NodeId > gum::ShaferShenoyInference< GUM_SCALAR >::node_to_clique__

private

for each node of graph__ (~ in the Bayes net), associate an ID in the JT

Definition at line 276 of file ShaferShenoyInference.h.

node_to_soft_evidence__

template<typename GUM_SCALAR>

NodeProperty< const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::node_to_soft_evidence__

private

the soft evidence stored in the cliques per their assigned node in the BN

This variable is useful for method updateOutdatedPotentials_: it enables to know which soft evidence should be removed/added into the cliques of the join tree.

Warning

These potentials are not owned by ShaferShenoyInference, they are only referenced by it. Only the cliques that contain evidence are filled in this structure.

Definition at line 339 of file ShaferShenoyInference.h.

one_minus_epsilon__

template<typename GUM_SCALAR>

const GUM_SCALAR gum::ShaferShenoyInference< GUM_SCALAR >::one_minus_epsilon__ {GUM_SCALAR(1.0 - 1e-6)}

private

for comparisons with 1 - epsilon

Definition at line 364 of file ShaferShenoyInference.h.

projection_op__

template<typename GUM_SCALAR>

Potential< GUM_SCALAR >*(* gum::ShaferShenoyInference< GUM_SCALAR >::projection_op__) (const Potential< GUM_SCALAR > &, const Set< const DiscreteVariable *> &)

inlineprivate

the operator for performing the projections

Definition at line 230 of file ShaferShenoyInference.h.

                                             {SSNewprojPotential};

roots__

template<typename GUM_SCALAR>

NodeSet gum::ShaferShenoyInference< GUM_SCALAR >::roots__

private

a clique node used as a root in each connected component of JT__

For usual probabilistic inference, roots is useless. This is useful when computing the probability of evidence. In this case, we need to compute this probability in every connected component and multiply them to get the overall probability of evidence.

Warning

roots__ should be computed only when evidenceProbability is called.

Definition at line 273 of file ShaferShenoyInference.h.

separator_potentials__

template<typename GUM_SCALAR>

ArcProperty< PotentialSet__ > gum::ShaferShenoyInference< GUM_SCALAR >::separator_potentials__

private

the list of all potentials stored in the separators after inferences

This structure contains all the arcs of the join tree (edges in both directions) whether the arc received any potential or not.

Definition at line 301 of file ShaferShenoyInference.h.

target_posteriors__

template<typename GUM_SCALAR>

NodeProperty< const Potential< GUM_SCALAR >* > gum::ShaferShenoyInference< GUM_SCALAR >::target_posteriors__

private

the set of single posteriors computed during the last inference

the posteriors are owned by ShaferShenoyInference.

Definition at line 313 of file ShaferShenoyInference.h.

triangulation__

template<typename GUM_SCALAR>

Triangulation* gum::ShaferShenoyInference< GUM_SCALAR >::triangulation__

private

the triangulation class creating the junction tree used for inference

Definition at line 237 of file ShaferShenoyInference.h.

use_binary_join_tree__

template<typename GUM_SCALAR>

bool gum::ShaferShenoyInference< GUM_SCALAR >::use_binary_join_tree__ {true}

private

indicates whether we should transform junction trees into binary join trees

Definition at line 244 of file ShaferShenoyInference.h.

---

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

• agrum/BN/inference/ShaferShenoyInference.h