The diagonal Categorical mixture model Categorical_pjk is the most general diagonal Categorical model and has a probability function of the form. More...

#include <STK_Categorical_pjk.h>

Inheritance diagram for STK::Categorical_pjk< Array >:

Public Types
typedef CategoricalBase< Categorical_pjk< Array > >	Base

Public Types inherited from STK::IMixtureDensity< Derived >
typedef hidden::MixtureTraits< Derived >::Array	Array

typedef hidden::MixtureTraits< Derived >::Parameters	Parameters

typedef hidden::Traits< Array >::Type	Type

Public Member Functions
	Categorical_pjk (int nbCluster)
	default constructor

	Categorical_pjk (Categorical_pjk const &model)
	copy constructor

	~Categorical_pjk ()
	destructor

void	randomInit (CArrayXX const const &p_tik, CPointX const const &p_tk)
	Initialize randomly the parameters of the Categorical mixture.

bool	run (CArrayXX const const &p_tik, CPointX const const &p_tk)
	Compute the weighted probabilities.

int	computeNbFreeParameters () const

Public Member Functions inherited from STK::CategoricalBase< Categorical_pjk< Array > >
PointXi const &	nbModalities () const

Range const &	modalities () const

Real	proba (int k, int j, int l) const

CVectorX	proba (int k, int j) const

void	initializeModelImpl ()
	Initialize the model.

Real	lnComponentProbability (int i, int k) const

int	impute (int i, int j, Weights const &tk) const

int	rand (int i, int j, int k) const

void	getParameters (Array &params) const
	This function is used in order to get the current values of the parameters in an array.

void	writeParameters (CArrayXX const *p_tik, ostream &os) const
	This function can be used to write summary of parameters to the output stream.

Public Member Functions inherited from STK::IMixtureDensity< Derived >
	~IMixtureDensity ()
	destructor

int	nbCluster () const

int	nbSample () const

Real	lnNbSample () const

Array const *const &	p_data () const

Parameters const &	param () const

void	setData (Array const &data)
	Set the data set.

void	setData (Array const &data, int nbRow, int nbCol, bool byRow=true)
	Set the data set and give dimensions.

bool	initializeStep ()
	This function will be called at the beginning of the estimation process once the model is created and data is set.

void	setParametersStep ()
	set the parameters obtained with the intermediate results and release the intermediate results.

void	finalizeStep ()
	This function will be called once the model is estimated.

template<class Weights >
Type	sample (int i, int j, Weights const &tk) const

Public Member Functions inherited from STK::IRecursiveTemplate< Derived >
Derived &	asDerived ()
	static cast : return a reference of this with a cast to the derived class.

Derived const &	asDerived () const
	static cast : return a const reference of this with a cast to the derived class.

Derived *	asPtrDerived ()
	static cast : return a ptr on a `Derived` of this with a cast to the derived class.

Derived const *	asPtrDerived () const
	static cast : return a ptr on a constant `Derived` of this with a cast to the derived class.

Derived *	clone () const
	create a leaf using the copy constructor of the Derived class.

Derived *	clone (bool isRef) const
	create a leaf using the copy constructor of the Derived class and a flag determining if the clone is a reference or not.

Additional Inherited Members
Protected Types inherited from STK::CategoricalBase< Categorical_pjk< Array > >
typedef IMixtureDensity< Categorical_pjk< Array > >	Base

Protected Member Functions inherited from STK::CategoricalBase< Categorical_pjk< Array > >
	CategoricalBase (int nbCluster)
	default constructor

	CategoricalBase (CategoricalBase const &model)
	copy constructor

	~CategoricalBase ()
	destructor

Array const *const &	p_data () const

Protected Member Functions inherited from STK::IMixtureDensity< Derived >
	IMixtureDensity (int nbCluster)
	Default constructor.

	IMixtureDensity (IMixtureDensity const &model)
	copy constructor.

void	initializeModel ()
	Initialize the model before its first use.

bool	initializeStepImpl ()
	default implementation of initializeStepImpl (do nothing and return true)

void	finalizeStepImpl ()
	default implementation of finalizeStepImpl (do nothing)

void	setNbSample (int nbSample)
	Set the number of sample of the model (needed by kernel models)

Protected Member Functions inherited from STK::IRecursiveTemplate< Derived >
	IRecursiveTemplate ()
	constructor.

	~IRecursiveTemplate ()
	destructor.

Protected Attributes inherited from STK::CategoricalBase< Categorical_pjk< Array > >
PointXi	nbModalities_
	Array with the number of modalities of each columns of the data set.

Range	modalities_
	range of the modalities

Parameters	param_
	parameters of the derived mixture model.

Protected Attributes inherited from STK::IMixtureDensity< Derived >
Parameters	param_
	parameters of the derived mixture model.

Detailed Description

template<class Array>
class STK::Categorical_pjk< Array >

The diagonal Categorical mixture model Categorical_pjk is the most general diagonal Categorical model and has a probability function of the form.

$P(\mathbf{x}=(l_1,\ldots,l_d)|\theta) = \sum_{k=1}^K p_k \prod_{j=1}^d p_{kl_j}^j.$

Definition at line 69 of file STK_Categorical_pjk.h.

Member Typedef Documentation

◆ Base

template<class Array >

typedef CategoricalBase<Categorical_pjk<Array> > STK::Categorical_pjk< Array >::Base

Definition at line 72 of file STK_Categorical_pjk.h.

Constructor & Destructor Documentation

◆ Categorical_pjk() [1/2]

template<class Array >

STK::Categorical_pjk< Array >::Categorical_pjk ( int nbCluster )

inline

default constructor

Parameters

nbCluster number of cluster of the model

Definition at line 80 of file STK_Categorical_pjk.h.

80: Base(nbCluster) {}

STK::Categorical_pjk::Base

CategoricalBase< Categorical_pjk< Array > > Base

Definition STK_Categorical_pjk.h:72

STK::IMixtureDensity::nbCluster

int nbCluster() const

Definition STK_IMixtureDensity.h:124

◆ Categorical_pjk() [2/2]

template<class Array >

STK::Categorical_pjk< Array >::Categorical_pjk ( Categorical_pjk< Array > const & model )

inline

copy constructor

Parameters

model model to copy

Definition at line 84 of file STK_Categorical_pjk.h.

84: Base(model) {}

◆ ~Categorical_pjk()

template<class Array >

STK::Categorical_pjk< Array >::~Categorical_pjk ( )

inline

destructor

Definition at line 86 of file STK_Categorical_pjk.h.

86{}

Member Function Documentation

◆ computeNbFreeParameters()

template<class Array >

int STK::Categorical_pjk< Array >::computeNbFreeParameters ( ) const

inline

Returns: the number of free parameters of the model

Definition at line 93 of file STK_Categorical_pjk.h.

94 { return this->nbCluster()*((this->nbModalities_-1).sum());}

STK::CategoricalBase< Categorical_pjk< Array > >::nbModalities_

PointXi nbModalities_

Array with the number of modalities of each columns of the data set.

Definition STK_CategoricalBase.h:131

STK::sum

Arrays::SumOp< Lhs, Rhs >::result_type sum(Lhs const &lhs, Rhs const &rhs)

convenience function for summing two arrays

Definition STK_Array2D_Functors.h:554

References STK::IMixtureDensity< Derived >::nbCluster(), STK::CategoricalBase< Categorical_pjk< Array > >::nbModalities_, and STK::sum().

◆ randomInit()

template<class Array >

void STK::Categorical_pjk< Array >::randomInit	(	CArrayXX const *const &	p_tik,
		CPointX const *const &	p_tk
	)

Initialize randomly the parameters of the Categorical mixture.

Definition at line 99 of file STK_Categorical_pjk.h.

{
  for (int k = p_tik->beginCols(); k < p_tik->endCols(); ++k)
  {
    param_.proba_[k].randUnif();
    for (int j=param_.proba_[k].beginCols(); j< param_.proba_[k].endCols(); ++j)
    { param_.proba_[k].col(j) /= param_.proba_[k].col(j).sum();}
  }
}

◆ run()

template<class Array >

bool STK::Categorical_pjk< Array >::run	(	CArrayXX const *const &	p_tik,
		CPointX const *const &	p_tk
	)

Compute the weighted probabilities.

Definition at line 112 of file STK_Categorical_pjk.h.

{
  for (int k = p_tik->beginCols(); k < p_tik->endCols(); ++k)
  {
    param_.proba_[k] = 0.;
    for (int j = p_data()->beginCols(); j < p_data()->endCols(); ++j)
    {
      // count the number of modalities weighted by the tik
      for (int i = p_data()->beginRows(); i < p_data()->endRows(); ++i)
      { param_.proba_[k](p_data()->elt(i, j), j) += p_tik->elt(i, k);}
      // normalize the probabilities
      Real sum = param_.proba_[k].col(j).sum();
      if (sum) { param_.proba_[k].col(j) /= sum;}
    }
  }
  return true;
}

References STK::ICArray< Derived >::col(), and STK::sum().

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

STK_Categorical_pjk.h

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ Base

Constructor & Destructor Documentation

◆ Categorical_pjk() [1/2]

◆ Categorical_pjk() [2/2]

◆ ~Categorical_pjk()

Member Function Documentation

◆ computeNbFreeParameters()

◆ randomInit()

◆ run()