gum::IMarkovNet< GUM_SCALAR > Class Template Reference

Class representing the minimal interface for Bayesian Network. More...

#include <agrum/BN/IMarkovNet.h>

Inheritance diagram for gum::IMarkovNet< GUM_SCALAR >:

Collaboration diagram for gum::IMarkovNet< GUM_SCALAR >:

Public Member Functions
bool	operator== (const IMarkovNet< GUM_SCALAR > &from) const
	This operator compares 2 BNs ! More...
bool	operator!= (const IMarkovNet< GUM_SCALAR > &from) const
Size	dim () const
	Returns the dimension (the number of free parameters) in this bayes net. More...
Size	maxVarDomainSize () const
GUM_SCALAR	minParam () const
GUM_SCALAR	maxParam () const
GUM_SCALAR	minNonZeroParam () const
GUM_SCALAR	maxNonOneParam () const
virtual std::string	toDot () const
std::string	toString () const
bool	hasSameStructure (const UGmodel &other)
double	log10DomainSize () const
Constructors / Destructors
	IMarkovNet ()
	Default constructor. More...
	IMarkovNet (std::string name)
	Default constructor. More...
virtual	~IMarkovNet ()
	Destructor. More...
	IMarkovNet (const IMarkovNet< GUM_SCALAR > &source)
	Copy constructor. More...
IMarkovNet< GUM_SCALAR > &	operator= (const IMarkovNet< GUM_SCALAR > &source)
	Copy operator. More...
Pure Virtual methods
virtual const Potential< GUM_SCALAR > &	factor (const NodeSet &varIds) const =0
	Returns the factor of a set of variable. More...
virtual const FactorTable< GUM_SCALAR > &	factors () const =0
	Returns the set of factors as a IMarkovNet::FactorTable. More...
virtual const VariableNodeMap &	variableNodeMap () const =0
	Returns a constant reference to the VariableNodeMap of thisBN. More...
virtual const DiscreteVariable &	variable (NodeId id) const =0
	Returns a constant reference over a variable given it's node id. More...
virtual NodeId	nodeId (const DiscreteVariable &var) const =0
	Return id node from discrete var pointer. More...
virtual NodeId	idFromName (const std::string &name) const =0
	Getter by name. More...
virtual const DiscreteVariable &	variableFromName (const std::string &name) const =0
	Getter by name. More...
Variable manipulation methods.
const UndiGraph &	graph () const
	Returns a constant reference to the dag of this Bayes Net. More...
virtual Size	size () const final
	Returns the number of variables in this Directed Graphical Model. More...
Size	sizeEdges () const
	Returns the number of arcs in this Directed Graphical Model. More...
const NodeGraphPart &	nodes () const
	Returns a constant reference to the dag of this Bayes Net. More...
Edge manipulation methods.
const EdgeSet &	edges () const
	returns the neighbours of a node as set of nodes More...
const NodeSet &	neighbours (const NodeId id) const
	returns the neighbours of a node as set of nodes More...
const NodeSet &	neighbours (const std::string &name) const
	returns the neighbours of a node as set of nodes More...
Getter and setters
const std::string &	property (const std::string &name) const
	Return the value of the property name of this GraphicalModel. More...
const std::string &	propertyWithDefault (const std::string &name, const std::string &byDefault) const
	Return the value of the property name of this GraphicalModel. More...
void	setProperty (const std::string &name, const std::string &value)
	Add or change a property of this GraphicalModel. More...
Variable manipulation methods.
virtual bool	empty () const
	Retursn true if this Directed Graphical Model is empty. More...
Instantiation	completeInstantiation () const
	Get an instantiation over all the variables of the model. More...

Protected Attributes
UndiGraph	_graph
	The DAG of this Directed Graphical Model. More...

Detailed Description

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

Class representing the minimal interface for Bayesian Network.

This class is used as a base class for different versions of Bayesian Networks. No data (except the dag herited from DAGmodel are included in this class. Many algorithms (inference for instance) may use this class when a simple BN is needed.

Definition at line 64 of file IMarkovNet.h.

Constructor & Destructor Documentation

IMarkovNet() [1/3]

template<typename GUM_SCALAR >

INLINE gum::IMarkovNet< GUM_SCALAR >::IMarkovNet

(

)

Default constructor.

Definition at line 40 of file IMarkovNet_tpl.h.

                                              : UGmodel() {
    GUM_CONSTRUCTOR(IMarkovNet);
  }

IMarkovNet() [2/3]

template<typename GUM_SCALAR >

INLINE gum::IMarkovNet< GUM_SCALAR >::IMarkovNet ( std::string  name )

explicit

Default constructor.

Definition at line 45 of file IMarkovNet_tpl.h.

References gum::GraphicalModel::setProperty().

                                                            : UGmodel() {
    GUM_CONSTRUCTOR(IMarkovNet);
    this->setProperty("name", name);
  }

Here is the call graph for this function:

~IMarkovNet()

template<typename GUM_SCALAR >

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

virtual

Destructor.

Definition at line 65 of file IMarkovNet_tpl.h.

                                        {
    GUM_DESTRUCTOR(IMarkovNet);
  }

IMarkovNet() [3/3]

template<typename GUM_SCALAR >

gum::IMarkovNet< GUM_SCALAR >::IMarkovNet

(

const IMarkovNet< GUM_SCALAR > &

source

)

Copy constructor.

Definition at line 51 of file IMarkovNet_tpl.h.

                                                                             :
      UGmodel(source) {
    GUM_CONS_CPY(IMarkovNet);
  }

Member Function Documentation

completeInstantiation()

INLINE Instantiation gum::GraphicalModel::completeInstantiation ( ) const

inherited

Get an instantiation over all the variables of the model.

Definition at line 85 of file graphicalModel_inl.h.

References gum::GraphicalModel::nodes(), and gum::GraphicalModel::variable().

                                                            {
    Instantiation I;

    for (const auto node: nodes())
      I << variable(node);

    return I;
  }

Here is the call graph for this function:

dim()

template<typename GUM_SCALAR >

Size gum::IMarkovNet< GUM_SCALAR >::dim

(

)

const

Returns the dimension (the number of free parameters) in this bayes net.

\( dim(G)=\sum_{i \in nodes} ((r_i-1)\cdot q_i) \) where \( r_i \) is the number of instantiations of node \( i \) and \( q_i \) is the number of instantiations of its parents.

Definition at line 70 of file IMarkovNet_tpl.h.

References gum::IMarkovNet< GUM_SCALAR >::factors().

                                           {
    Size res = 0;
    for (auto f: factors()) {
      res += f.second->domainSize();
    }
    return res;
  }

Here is the call graph for this function:

edges()

INLINE const EdgeSet & gum::UGmodel::edges ( ) const

inherited

returns the neighbours of a node as set of nodes

Note that the set of nodes returned may be empty if no edge within the EdgeGraphPart contains the given node.

Parameters

id	the node toward which the edge returned are pointing

Definition at line 44 of file UGmodel_inl.h.

References gum::UGmodel::_graph, and gum::EdgeGraphPart::edges().

Referenced by gum::UGmodel::hasSameStructure().

{ return _graph.edges(); }

Here is the call graph for this function:

Here is the caller graph for this function:

empty()

INLINE bool gum::GraphicalModel::empty ( ) const

virtualinherited

Retursn true if this Directed Graphical Model is empty.

Definition at line 95 of file graphicalModel_inl.h.

References gum::GraphicalModel::size().

{ return size() == 0; }

Here is the call graph for this function:

factor()

template<typename GUM_SCALAR>

virtual const Potential< GUM_SCALAR >& gum::IMarkovNet< GUM_SCALAR >::factor ( const NodeSet &  varIds ) const

pure virtual

Returns the factor of a set of variable.

Exceptions

NotFound

If no variable's id matches varId.

Referenced by gum::IMarkovNet< GUM_SCALAR >::toString().

Here is the caller graph for this function:

factors()

template<typename GUM_SCALAR>

virtual const FactorTable< GUM_SCALAR >& gum::IMarkovNet< GUM_SCALAR >::factors ( ) const

pure virtual

Returns the set of factors as a IMarkovNet::FactorTable.

Referenced by gum::IMarkovNet< GUM_SCALAR >::dim(), and gum::IMarkovNet< GUM_SCALAR >::toString().

Here is the caller graph for this function:

graph()

INLINE const UndiGraph & gum::UGmodel::graph ( ) const

inherited

Returns a constant reference to the dag of this Bayes Net.

Definition at line 36 of file UGmodel_inl.h.

References gum::UGmodel::_graph.

Referenced by gum::UGmodel::size(), and gum::IMarkovNet< GUM_SCALAR >::toString().

{ return _graph; }

Here is the caller graph for this function:

hasSameStructure()

bool gum::UGmodel::hasSameStructure ( const UGmodel &  other )

inherited

Returns

true if all the named node are the same and all the named arcs are the same

Definition at line 47 of file UGmodel.cpp.

References gum::UGmodel::edges(), gum::Set< Key, Alloc >::exists(), gum::UGmodel::idFromName(), gum::UGmodel::nodes(), gum::UGmodel::size(), gum::UGmodel::sizeEdges(), and gum::UGmodel::variable().

                                                     {
    if (this == &other) return true;

    if (size() != other.size()) return false;

    if (sizeEdges() != other.sizeEdges()) return false;

    for (const auto& nid: nodes()) {
      try {
        other.idFromName(variable(nid).name());
      } catch (NotFound) { return false; }
    }

    for (const auto& edge: edges()) {
      if (!other.edges().exists(
             Edge(other.idFromName(variable(edge.first()).name()),
                  other.idFromName(variable(edge.second()).name()))))
        return false;
    }

    return true;
  }

Here is the call graph for this function:

idFromName()

template<typename GUM_SCALAR>

virtual NodeId gum::IMarkovNet< GUM_SCALAR >::idFromName ( const std::string &  name ) const

pure virtual

Getter by name.

Exceptions

NotFound

if no such name exists in the graph.

Implements gum::UGmodel.

log10DomainSize()

INLINE double gum::GraphicalModel::log10DomainSize ( ) const

inherited

Definition at line 74 of file graphicalModel_inl.h.

References gum::GraphicalModel::nodes(), and gum::GraphicalModel::variable().

Referenced by gum::InfluenceDiagram< GUM_SCALAR >::toString(), and gum::IMarkovNet< GUM_SCALAR >::toString().

                                               {
    double dSize = 0.0;

    for (const auto node: nodes()) {
      dSize += std::log10(variable(node).domainSize());
    }

    return dSize;
  }

Here is the call graph for this function:

Here is the caller graph for this function:

maxNonOneParam()

template<typename GUM_SCALAR >

GUM_SCALAR gum::IMarkovNet< GUM_SCALAR >::maxNonOneParam

(

)

const

Returns

the biggest value (not equal to 1) in the CPTs of *this

Definition at line 132 of file IMarkovNet_tpl.h.

References GUM_ERROR.

                                                            {
    /*
    GUM_SCALAR res = 0.0;
    for (auto node: nodes()) {
      auto v = factor(node).maxNonOne();
      if (v > res) { res = v; }
    }
    return res;
     */
    GUM_ERROR(FatalError, "Not Implemented Yet")
  }

maxParam()

template<typename GUM_SCALAR >

GUM_SCALAR gum::IMarkovNet< GUM_SCALAR >::maxParam

(

)

const

Returns

the biggest value in the CPTs of *this

Definition at line 105 of file IMarkovNet_tpl.h.

References GUM_ERROR.

                                                      {
    /*
    GUM_SCALAR res = 1.0;
    for (auto node: nodes()) {
      auto v = factor(node).max();
      if (v > res) { res = v; }
    }
    return res;*/

    GUM_ERROR(FatalError, "Not Implemented Yet")
  }

maxVarDomainSize()

template<typename GUM_SCALAR >

Size gum::IMarkovNet< GUM_SCALAR >::maxVarDomainSize

(

)

const

Returns

the biggest domainSize among the variables of *this

Definition at line 79 of file IMarkovNet_tpl.h.

References GUM_ERROR.

                                                        {
    /*
    Size res = 0;
    for (auto node: nodes()) {
      auto v = variable(node).domainSize();
      if (v > res) { res = v; }
    }
    return res;*/

    GUM_ERROR(FatalError, "Not Implemented Yet")
  }

minNonZeroParam()

template<typename GUM_SCALAR >

GUM_SCALAR gum::IMarkovNet< GUM_SCALAR >::minNonZeroParam

(

)

const

Returns

the smallest value (not equal to 0) in the CPTs of *this

Definition at line 118 of file IMarkovNet_tpl.h.

References GUM_ERROR.

                                                             {
    /*
    GUM_SCALAR res = 1.0;
    for (auto node: nodes()) {
      auto v = factor(node).minNonZero();
      if (v < res) { res = v; }
    }
    return res;
     */

    GUM_ERROR(FatalError, "Not Implemented Yet")
  }

minParam()

template<typename GUM_SCALAR >

GUM_SCALAR gum::IMarkovNet< GUM_SCALAR >::minParam

(

)

const

Returns

the smallest value in the CPTs of *this

Definition at line 92 of file IMarkovNet_tpl.h.

References GUM_ERROR.

                                                      {
    /*
    GUM_SCALAR res = 1.0;
    for (auto node: nodes()) {
      auto v = factor(node).min();
      if (v < res) { res = v; }
    }
    return res;*/

    GUM_ERROR(FatalError, "Not Implemented Yet")
  }

neighbours() [1/2]

INLINE const NodeSet & gum::UGmodel::neighbours ( const NodeId  id ) const

inherited

returns the neighbours of a node as set of nodes

Note that the set of nodes returned may be empty if no edge within the EdgeGraphPart contains the given node.

Parameters

id	the node toward which the edge returned are pointing

Definition at line 46 of file UGmodel_inl.h.

References gum::UGmodel::_graph, and gum::EdgeGraphPart::neighbours().

Referenced by gum::UGmodel::neighbours().

                                                                 {
    return _graph.neighbours(id);
  }

Here is the call graph for this function:

Here is the caller graph for this function:

neighbours() [2/2]

INLINE const NodeSet & gum::UGmodel::neighbours ( const std::string &  name ) const

inherited

returns the neighbours of a node as set of nodes

Note that the set of nodes returned may be empty if no edge within the EdgeGraphPart contains the given node.

Parameters

id	the node toward which the edge returned are pointing

Definition at line 49 of file UGmodel_inl.h.

References gum::UGmodel::idFromName(), and gum::UGmodel::neighbours().

                                                                       {
    return neighbours(idFromName(name));
  }

Here is the call graph for this function:

nodeId()

template<typename GUM_SCALAR>

virtual NodeId gum::IMarkovNet< GUM_SCALAR >::nodeId ( const DiscreteVariable &  var ) const

pure virtual

Return id node from discrete var pointer.

Exceptions

NotFound

If no variable matches var.

Implements gum::UGmodel.

nodes()

INLINE const NodeGraphPart & gum::UGmodel::nodes ( ) const

virtualinherited

Returns a constant reference to the dag of this Bayes Net.

Implements gum::GraphicalModel.

Definition at line 53 of file UGmodel_inl.h.

References gum::UGmodel::_graph.

Referenced by gum::UGmodel::hasSameStructure().

                                                   {
    return (NodeGraphPart&)_graph;
  }

Here is the caller graph for this function:

operator!=()

template<typename GUM_SCALAR >

bool gum::IMarkovNet< GUM_SCALAR >::operator!=

(

const IMarkovNet< GUM_SCALAR > &

from

)

const

Returns

Returns false if the src and this are equal.

Definition at line 254 of file IMarkovNet_tpl.h.

References gum::IMarkovNet< GUM_SCALAR >::operator==().

                                                                        {
    return !this->operator==(from);
  }

Here is the call graph for this function:

operator=()

template<typename GUM_SCALAR >

IMarkovNet< GUM_SCALAR > & gum::IMarkovNet< GUM_SCALAR >::operator=

(

const IMarkovNet< GUM_SCALAR > &

source

)

Copy operator.

Definition at line 58 of file IMarkovNet_tpl.h.

References gum::UGmodel::operator=().

Referenced by gum::build_node().

                                                                               {
    if (this != &source) { UGmodel::operator=(source); }

    return *this;
  }

Here is the call graph for this function:

Here is the caller graph for this function:

operator==()

template<typename GUM_SCALAR >

bool gum::IMarkovNet< GUM_SCALAR >::operator==

(

const IMarkovNet< GUM_SCALAR > &

from

)

const

This operator compares 2 BNs !

Warning

To identify nodes between BNs, it is assumed that they share the same name.

Returns

true if the src and this are equal.

Definition at line 208 of file IMarkovNet_tpl.h.

Referenced by gum::IMarkovNet< GUM_SCALAR >::operator!=().

                                                                        {
    return "Not Implemented Yet";
    /*
    if (size() != from.size()) { return false; }

    if (sizeEdges() != from.sizeEdges()) { return false; }

    // alignment of variables between the 2 BNs
    Bijection< const DiscreteVariable*, const DiscreteVariable* > alignment;

    for (auto node: nodes()) {
      try {
        alignment.insert(&variable(node),
                         &from.variableFromName(variable(node).name()));
      } catch (NotFound&) {
        // a name is not found in from
        return false;
      }
    }

    for (auto node: nodes()) {
      NodeId fromnode = from.idFromName(variable(node).name());

      if (factor(node).nbrDim() != from.factor(fromnode).nbrDim()) { return
    false; }

      Instantiation i(factor(node));
      Instantiation j(from.factor(fromnode));

      for (i.setFirst(); !i.end(); i.inc()) {
        for (Idx indice = 0; indice < factor(node).nbrDim(); ++indice) {
          const DiscreteVariable* p = &(i.variable(indice));
          j.chgVal(*(alignment.second(p)), i.val(*p));
        }

        if (std::pow(factor(node).get(i) - from.factor(fromnode).get(j),
    (GUM_SCALAR)2) > (GUM_SCALAR)1e-6) { return false;
        }
      }
    }

    return true;
     */
  }

Here is the caller graph for this function:

property()

INLINE const std::string & gum::GraphicalModel::property ( const std::string &  name ) const

inherited

Return the value of the property name of this GraphicalModel.

Exceptions

NotFound

Raised if no name property is found.

Definition at line 37 of file graphicalModel_inl.h.

References gum::GraphicalModel::__properties(), and GUM_ERROR.

Referenced by gum::InfluenceDiagram< GUM_SCALAR >::toDot().

                                                                       {
    try {
      return __properties()[name];
    } catch (NotFound&) {
      std::string msg = "The following property does not exists: ";
      GUM_ERROR(NotFound, msg + name);
    }
  }

Here is the call graph for this function:

Here is the caller graph for this function:

propertyWithDefault()

INLINE const std::string & gum::GraphicalModel::propertyWithDefault ( const std::string &  name, const std::string &  byDefault  ) const

inherited

Return the value of the property name of this GraphicalModel.

return byDefault if the property name is not found

Definition at line 57 of file graphicalModel_inl.h.

References gum::GraphicalModel::__properties().

                                                                           {
    try {
      return __properties()[name];
    } catch (NotFound&) { return byDefault; }
  }

Here is the call graph for this function:

setProperty()

INLINE void gum::GraphicalModel::setProperty ( const std::string &  name, const std::string &  value  )

inherited

Add or change a property of this GraphicalModel.

Definition at line 65 of file graphicalModel_inl.h.

References gum::GraphicalModel::__properties(), and gum::HashTable< Key, Val, Alloc >::insert().

Referenced by gum::BayesNet< double >::fastPrototype(), and gum::IMarkovNet< GUM_SCALAR >::IMarkovNet().

                                                           {
    try {
      __properties()[name] = value;
    } catch (NotFound&) { __properties().insert(name, value); }
  }

Here is the call graph for this function:

Here is the caller graph for this function:

size()

INLINE Size gum::UGmodel::size ( ) const

finalvirtualinherited

Returns the number of variables in this Directed Graphical Model.

Implements gum::GraphicalModel.

Definition at line 39 of file UGmodel_inl.h.

References gum::UGmodel::graph(), and gum::NodeGraphPart::size().

Referenced by gum::UGmodel::hasSameStructure(), and gum::IMarkovNet< GUM_SCALAR >::toString().

{ return graph().size(); }

Here is the call graph for this function:

Here is the caller graph for this function:

sizeEdges()

INLINE Size gum::UGmodel::sizeEdges ( ) const

inherited

Returns the number of arcs in this Directed Graphical Model.

Definition at line 42 of file UGmodel_inl.h.

References gum::UGmodel::_graph, and gum::EdgeGraphPart::sizeEdges().

Referenced by gum::UGmodel::hasSameStructure().

{ return _graph.sizeEdges(); }

Here is the call graph for this function:

Here is the caller graph for this function:

toDot()

template<typename GUM_SCALAR >

std::string gum::IMarkovNet< GUM_SCALAR >::toDot ( ) const

virtual

Returns

Returns a dot representation of this IMarkovNet.

Definition at line 166 of file IMarkovNet_tpl.h.

                                                  {
    return "Not Implemented Yet"; /*
     std::stringstream output;
     output << "digraph \"";

     std::string bn_name;

     try {
       bn_name = this->property("name");
     } catch (NotFound&) { bn_name = "no_name"; }

     output << bn_name << "\" {" << std::endl;
     output << "  graph [bgcolor=transparent,label=\"" << bn_name << "\"];"
            << std::endl;
     output << "  node [style=filled fillcolor=\"#ffffaa\"];" << std::endl
            << std::endl;

     for (auto node: nodes())
       output << "\"" << variable(node).name() << "\" [comment=\"" << node << ":"
              << variable(node).toStringWithDescription() << "\"];" << std::endl;

     output << std::endl;

     std::string tab = "  ";

     for (auto node: nodes()) {
       if (children(node).size() > 0) {
         for (auto child: children(node)) {
           output << tab << "\"" << variable(node).name() << "\" -> "
                  << "\"" << variable(child).name() << "\";" << std::endl;
         }
       } else if (parents(node).size() == 0) {
         output << tab << "\"" << variable(node).name() << "\";" << std::endl;
       }
     }

     output << "}" << std::endl;

     return output.str();*/
  }

toString()

template<typename GUM_SCALAR >

INLINE std::string gum::IMarkovNet< GUM_SCALAR >::toString

(

)

const

Returns

Returns a string representation of this IMarkovNet.

Definition at line 145 of file IMarkovNet_tpl.h.

References gum::IMarkovNet< GUM_SCALAR >::factor(), gum::IMarkovNet< GUM_SCALAR >::factors(), gum::UGmodel::graph(), gum::GraphicalModel::log10DomainSize(), gum::UGmodel::size(), and gum::EdgeGraphPart::sizeEdges().

Referenced by gum::operator<<().

                                                            {
    Size   param = 0;
    double dSize = log10DomainSize();

    for (auto factor: factors())
      param += factor.second->content()->realSize();

    std::stringstream s;
    s << "MN{nodes: " << size() << ", edges: " << graph().sizeEdges() << ", ";

    if (dSize > 6)
      s << "domainSize: 10^" << dSize;
    else
      s << "domainSize: " << std::round(std::pow(10.0, dSize));

    s << ", dim: " << param << "}";

    return s.str();
  }

Here is the call graph for this function:

Here is the caller graph for this function:

variable()

template<typename GUM_SCALAR>

virtual const DiscreteVariable& gum::IMarkovNet< GUM_SCALAR >::variable ( NodeId  id ) const

pure virtual

Returns a constant reference over a variable given it's node id.

Exceptions

NotFound

If no variable's id matches varId.

Implements gum::UGmodel.

variableFromName()

template<typename GUM_SCALAR>

virtual const DiscreteVariable& gum::IMarkovNet< GUM_SCALAR >::variableFromName ( const std::string &  name ) const

pure virtual

Getter by name.

Exceptions

NotFound

if no such name exists in the graph.

Implements gum::UGmodel.

variableNodeMap()

template<typename GUM_SCALAR>

virtual const VariableNodeMap& gum::IMarkovNet< GUM_SCALAR >::variableNodeMap ( ) const

pure virtual

Returns a constant reference to the VariableNodeMap of thisBN.

Implements gum::GraphicalModel.

Member Data Documentation

_graph

UndiGraph gum::UGmodel::_graph

protectedinherited

The DAG of this Directed Graphical Model.

Definition at line 137 of file UGmodel.h.

Referenced by gum::UGmodel::edges(), gum::UGmodel::graph(), gum::UGmodel::neighbours(), gum::UGmodel::nodes(), gum::UGmodel::operator=(), and gum::UGmodel::sizeEdges().

---

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

• agrum/MN/IMarkovNet.h
• agrum/MN/IMarkovNet_tpl.h