A Diagonal Gaussian Mixture Model. More...

Public Member Functions
	DiagonalGMM ()
	Create an empty Diagonal Gaussian Mixture Model, with zero gaussians. More...

	DiagonalGMM (const size_t gaussians, const size_t dimensionality)
	Create a GMM with the given number of Gaussians, each of which have the specified dimensionality. More...

	DiagonalGMM (const std::vector< distribution::DiagonalGaussianDistribution > &dists, const arma::vec &weights)
	Create a DiagonalGMM with the given dists and weights. More...

	DiagonalGMM (const DiagonalGMM &other)
	Copy constructor for DiagonalGMMs. More...

void	Classify (const arma::mat &observations, arma::Row< size_t > &labels) const
	Classify the given observations as being from an individual component in this DiagonalGMM. More...

const distribution::DiagonalGaussianDistribution &	Component (size_t i) const
	Return a const reference to a component distribution. More...

distribution::DiagonalGaussianDistribution &	Component (size_t i)
	Return a reference to a component distribution. More...

size_t	Dimensionality () const
	Return the dimensionality of the model. More...

size_t	Gaussians () const
	Return the number of Gaussians in the model. More...

double	LogProbability (const arma::vec &observation) const
	Return the log probability that the given observation came from this distribution. More...

void	LogProbability (const arma::mat &observation, arma::vec &logProbs) const
	Return the log probability that the given observation matrix. More...

double	LogProbability (const arma::vec &observation, const size_t component) const
	Return the log probability that the given observation came from the given Gaussian component in this distribution. More...

DiagonalGMM &	operator= (const DiagonalGMM &other)
	Copy operator for DiagonalGMMs. More...

double	Probability (const arma::vec &observation) const
	Return the probability that the given observation came from this distribution. More...

void	Probability (const arma::mat &observation, arma::vec &probs) const
	Return the probability that the given observation matrix. More...

double	Probability (const arma::vec &observation, const size_t component) const
	Return the probability that the given observation came from the given Gaussian component in this distribution. More...

arma::vec	Random () const
	Return a randomly generated observation according to the probability distribution defined by this object. More...

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the DiagonalGMM. More...

template<typename FittingType = EMFit<kmeans::KMeans<>, DiagonalConstraint, distribution::DiagonalGaussianDistribution>>
double	Train (const arma::mat &observations, const size_t trials=1, const bool useExistingModel=false, FittingType fitter=FittingType())
	Estimate the probability distribution directly from the given observations, using the given algorithm in the FittingType class to fit the data. More...

template<typename FittingType = EMFit<kmeans::KMeans<>, DiagonalConstraint, distribution::DiagonalGaussianDistribution>>
double	Train (const arma::mat &observations, const arma::vec &probabilities, const size_t trials=1, const bool useExistingModel=false, FittingType fitter=FittingType())
	Estimate the probability distribution directly from the given observations, taking into account the probability of each observation actually being from this distribution, and using the given algorithm in the FittingType class to fit the data. More...

const arma::vec &	Weights () const
	Return a const reference to the a priori weights of each Gaussian. More...

arma::vec &	Weights ()
	Return a reference to the a priori weights of each Gaussian. More...

Detailed Description

A Diagonal Gaussian Mixture Model.

This class uses maximum likelihood loss functions to estimate the parameters of the DiagonalGMM on a given dataset via the given fitting mechanism, defined by the FittingType template parameter. The DiagonalGMM can be trained using normal data, or data with probabilities of being from this GMM (see DiagonalGMM::Train() for more information). The DiagonalGMM is the same as GMM except for wrapping gmm_diag class.

The Train() method uses a template type 'FittingType'. The FittingType template class must provide a way for the DiagonalGMM to train on data. It must provide the following two functions:

void Estimate(
    const arma::mat& observations,
    std::vector<distribution::DiagonalGaussianDistribution>& dists,
    arma::vec& weights);
void Estimate(
    const arma::mat& observations,
    const arma::vec& probabilities,
    std::vector<distribution::DiagonalGaussianDistribution>& dists,
    arma::vec& weights);

Example use:

// Set up a mixture of 5 gaussians in a 4-dimensional space.
DiagonalGMM g(5, 4);
// Train the DiagonalGMM given the data observations, using the default
// EM fitting mechanism.
g.Train(data);
// Get the probability of 'observation' being observed from this
// DiagoanlGMM.
double probability = g.Probability(observation);
// Get a random observation from the DiagonalGMM.
arma::vec observation = g.Random();

Definition at line 74 of file diagonal_gmm.hpp.

Constructor & Destructor Documentation

◆ DiagonalGMM() [1/4]

DiagonalGMM ( )

inline

Create an empty Diagonal Gaussian Mixture Model, with zero gaussians.

Definition at line 92 of file diagonal_gmm.hpp.

References Log::Debug.

Referenced by DiagonalGMM::DiagonalGMM().

◆ DiagonalGMM() [2/4]

DiagonalGMM	(	const size_t	gaussians,
		const size_t	dimensionality
	)

Create a GMM with the given number of Gaussians, each of which have the specified dimensionality.

The means and covariances will be set to 0.

Parameters

gaussians	Number of Gaussians in this DiagonalGMM.
dimensionality	Dimensionality of each Gaussian.

◆ DiagonalGMM() [3/4]

DiagonalGMM	(	const std::vector< distribution::DiagonalGaussianDistribution > &	dists,
		const arma::vec &	weights
	)

inline

Create a DiagonalGMM with the given dists and weights.

Parameters

dists	Distributions of the model.
weights	Weights of the model.

Definition at line 118 of file diagonal_gmm.hpp.

References DiagonalGMM::DiagonalGMM(), and DiagonalGMM::operator=().

◆ DiagonalGMM() [4/4]

DiagonalGMM ( const DiagonalGMM & other )

Copy constructor for DiagonalGMMs.

Member Function Documentation

◆ Classify()

void Classify	(	const arma::mat &	observations,
		arma::Row< size_t > &	labels
	)		const

Classify the given observations as being from an individual component in this DiagonalGMM.

The resultant classifications are stored in the 'labels' object, and each label will be between 0 and (Gaussians() - 1). Supposing that a point was classified with label 2, and that our DiagonalGMM object was called 'dgmm', one could access the relevant Gaussian distribution as follows:

arma::vec mean = dgmm.Means()[2];
arma::mat covariance = dgmm.Covariances()[2];
double priorWeight = dgmm.Weights()[2];

Parameters

observations	Matrix of observations to classify.
labels	Object which will be filled with labels.

Referenced by DiagonalGMM::Weights().

◆ Component() [1/2]

const distribution::DiagonalGaussianDistribution& Component ( size_t i ) const

inline

Return a const reference to a component distribution.

Parameters

i	Index of component.

Definition at line 141 of file diagonal_gmm.hpp.

◆ Component() [2/2]

distribution::DiagonalGaussianDistribution& Component ( size_t i )

inline

Return a reference to a component distribution.

Parameters

i	Index of component.

Definition at line 151 of file diagonal_gmm.hpp.

◆ Dimensionality()

size_t Dimensionality ( ) const

inline

Return the dimensionality of the model.

Definition at line 134 of file diagonal_gmm.hpp.

◆ Gaussians()

size_t Gaussians ( ) const

inline

Return the number of Gaussians in the model.

Definition at line 132 of file diagonal_gmm.hpp.

◆ LogProbability() [1/3]

double LogProbability ( const arma::vec & observation ) const

Return the log probability that the given observation came from this distribution.

Parameters

observation Observation to evaluate the log-probability of.

Referenced by DiagonalGMM::Weights().

◆ LogProbability() [2/3]

void LogProbability	(	const arma::mat &	observation,
		arma::vec &	logProbs
	)		const

Return the log probability that the given observation matrix.

Parameters

observation	Observation to evaluate the log-probability of.
logProbs	Stores the value of log-probability for observation.

◆ LogProbability() [3/3]

double LogProbability	(	const arma::vec &	observation,
		const size_t	component
	)		const

Return the log probability that the given observation came from the given Gaussian component in this distribution.

Parameters

observation	Observation to evaluate the probability of.
component	Index of the component of the DiagonalGMM.

◆ operator=()

DiagonalGMM& operator= ( const DiagonalGMM & other )

Copy operator for DiagonalGMMs.

Referenced by DiagonalGMM::DiagonalGMM().

◆ Probability() [1/3]

double Probability ( const arma::vec & observation ) const

Return the probability that the given observation came from this distribution.

Parameters

observation Observation to evaluate the probability of.

Referenced by DiagonalGMM::Weights().

◆ Probability() [2/3]

void Probability	(	const arma::mat &	observation,
		arma::vec &	probs
	)		const

Return the probability that the given observation matrix.

Parameters

observation	Observation to evaluate the probability of.
probs	Stores the value of probability for observation.

◆ Probability() [3/3]

double Probability	(	const arma::vec &	observation,
		const size_t	component
	)		const

Return the probability that the given observation came from the given Gaussian component in this distribution.

Parameters

observation	Observation to evaluate the probability of.
component	Index of the component of the DiagonalGMM.

◆ Random()

arma::vec Random ( ) const

Return a randomly generated observation according to the probability distribution defined by this object.

Returns: Random observation from this DiagonalGMM.

Referenced by DiagonalGMM::Weights().

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the DiagonalGMM.

Referenced by DiagonalGMM::Weights().

◆ Train() [1/2]

double Train	(	const arma::mat &	observations,
		const size_t	trials = `1`,
		const bool	useExistingModel = `false`,
		FittingType	fitter = `FittingType()`
	)

Estimate the probability distribution directly from the given observations, using the given algorithm in the FittingType class to fit the data.

The fitting will be performed 'trials' times; from these trials, the model with the greatest log-likelihood will be selected. By default, only one trial is performed. The log-likelihood of the best fitting is returned.

Optionally, the existing model can be used as an initial model for the estimation by setting 'useExistingModel' to true. If the fitting procedure is deterministic after the initial position is given, then 'trials' should be set to 1.

Parameters

observations	Observations of the model.
trials	Number of trials to perform; the model in these trials with the greatest log-likelihood will be selected.
useExistingModel	If true, the existing model is used as an initial model for the estimation.
fitter	Fitting type that estimates observations.

Returns: The log-likelihood of the best fit.

Referenced by DiagonalGMM::Weights().

◆ Train() [2/2]

double Train	(	const arma::mat &	observations,
		const arma::vec &	probabilities,
		const size_t	trials = `1`,
		const bool	useExistingModel = `false`,
		FittingType	fitter = `FittingType()`
	)

Estimate the probability distribution directly from the given observations, taking into account the probability of each observation actually being from this distribution, and using the given algorithm in the FittingType class to fit the data.

The fitting will be performed 'trials' times; from these trials, the model with the greatest log-likelihood will be selected. By default, only one trial is performed. The log-likelihood of the best fitting is returned.

Optionally, the existing model can be used as an initial model for the estimation by setting 'useExistingModel' to true. If the fitting procedure is deterministic after the initial position is given, then 'trials' should be set to 1.

Parameters

observations	Observations of the model.
probabilities	Probability of each observation being from this distribution.
trials	Number of trials to perform; the model in these trials with the greatest log-likelihood will be selected.
useExistingModel	If true, the existing model is used as an initial model for the estimation.
fitter	Fitting type that estimates observations.

Returns: The log-likelihood of the best fit.

◆ Weights() [1/2]

const arma::vec& Weights ( ) const

inline

Return a const reference to the a priori weights of each Gaussian.

Definition at line 157 of file diagonal_gmm.hpp.

◆ Weights() [2/2]

arma::vec& Weights ( )

inline

Return a reference to the a priori weights of each Gaussian.

Definition at line 159 of file diagonal_gmm.hpp.

References DiagonalGMM::Classify(), DiagonalGMM::LogProbability(), DiagonalGMM::Probability(), DiagonalGMM::Random(), DiagonalGMM::serialize(), and DiagonalGMM::Train().

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

/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/gmm/diagonal_gmm.hpp

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ DiagonalGMM() [1/4]

◆ DiagonalGMM() [2/4]

◆ DiagonalGMM() [3/4]

◆ DiagonalGMM() [4/4]

Member Function Documentation

◆ Classify()

◆ Component() [1/2]

◆ Component() [2/2]

◆ Dimensionality()

◆ Gaussians()

◆ LogProbability() [1/3]

◆ LogProbability() [2/3]

◆ LogProbability() [3/3]

◆ operator=()

◆ Probability() [1/3]

◆ Probability() [2/3]

◆ Probability() [3/3]

◆ Random()

◆ serialize()

◆ Train() [1/2]

◆ Train() [2/2]

◆ Weights() [1/2]

◆ Weights() [2/2]