A class that represents a univariate conditionally Gaussian distribution. More...

Public Member Functions
	RegressionDistribution ()
	Default constructor, which creates a Gaussian with zero dimension. More...

	RegressionDistribution (const arma::mat &predictors, const arma::vec &responses)
	Create a Conditional Gaussian distribution with conditional mean function obtained by running RegressionFunction on predictors, responses. More...

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

const GaussianDistribution &	Err () const
	Return error distribution. More...

GaussianDistribution &	Err ()
	Modify error distribution. More...

double	LogProbability (const arma::vec &observation) const
	Evaluate log probability density function of given observation. More...

const arma::vec &	Parameters () const
	Return the parameters (the b vector). More...

void	Predict (const arma::mat &points, arma::vec &predictions) const
	Calculate y_i for each data point in points. More...

double	Probability (const arma::vec &observation) const
	Evaluate probability density function of given observation. More...

const regression::LinearRegression &	Rf () const
	Return regression function. More...

regression::LinearRegression &	Rf ()
	Modify regression function. More...

template<typename Archive >
void	Serialize (Archive &ar, const unsigned int)
	Serialize the distribution. More...

void	Train (const arma::mat &observations)
	Estimate the Gaussian distribution directly from the given observations. More...

void	Train (const arma::mat &observations, const arma::vec &weights)
	Estimate parameters using provided observation weights. More...

Private Attributes
GaussianDistribution	err
	Error distribution. More...

regression::LinearRegression	rf
	Regression function for representing conditional mean. More...

Detailed Description

A class that represents a univariate conditionally Gaussian distribution.

Can be used as an emission distribution with the hmm class to implement HMM regression (HMMR) as described in https://www.ima.umn.edu/preprints/January1994/1195.pdf The hmm observations should have the dependent variable in the first row, with the independent variables in the other rows.

Definition at line 30 of file regression_distribution.hpp.

Constructor & Destructor Documentation

mlpack::distribution::RegressionDistribution::RegressionDistribution ( )

inline

Default constructor, which creates a Gaussian with zero dimension.

Definition at line 42 of file regression_distribution.hpp.

mlpack::distribution::RegressionDistribution::RegressionDistribution	(	const arma::mat &	predictors,
		const arma::vec &	responses
	)

inline

Create a Conditional Gaussian distribution with conditional mean function obtained by running RegressionFunction on predictors, responses.

Parameters

predictors	Matrix of predictors (X).
responses	Vector of responses (y).

Definition at line 51 of file regression_distribution.hpp.

References mlpack::regression::LinearRegression::ComputeError(), and mlpack::distribution::GaussianDistribution::Covariance().

Member Function Documentation

size_t mlpack::distribution::RegressionDistribution::Dimensionality ( ) const

inline

Return the dimensionality.

Definition at line 123 of file regression_distribution.hpp.

References mlpack::regression::LinearRegression::Parameters().

const GaussianDistribution& mlpack::distribution::RegressionDistribution::Err ( ) const

inline

Return error distribution.

Definition at line 77 of file regression_distribution.hpp.

References err.

GaussianDistribution& mlpack::distribution::RegressionDistribution::Err ( )

inline

Modify error distribution.

Definition at line 79 of file regression_distribution.hpp.

References err, Probability(), and Train().

double mlpack::distribution::RegressionDistribution::LogProbability ( const arma::vec & observation ) const

inline

Evaluate log probability density function of given observation.

Parameters

observation point to evaluate log probability at

Definition at line 107 of file regression_distribution.hpp.

References Predict(), and Probability().

const arma::vec& mlpack::distribution::RegressionDistribution::Parameters ( ) const

inline

Return the parameters (the b vector).

Definition at line 120 of file regression_distribution.hpp.

References mlpack::regression::LinearRegression::Parameters().

void mlpack::distribution::RegressionDistribution::Predict	(	const arma::mat &	points,
		arma::vec &	predictions
	)		const

Calculate y_i for each data point in points.

Parameters

points	the data points to calculate with.
predictions	y, will contain calculated values on completion.

Referenced by LogProbability().

double mlpack::distribution::RegressionDistribution::Probability ( const arma::vec & observation ) const

Evaluate probability density function of given observation.

Parameters

observation point to evaluate probability at

Referenced by Err(), and LogProbability().

const regression::LinearRegression& mlpack::distribution::RegressionDistribution::Rf ( ) const

inline

Return regression function.

Definition at line 72 of file regression_distribution.hpp.

References rf.

regression::LinearRegression& mlpack::distribution::RegressionDistribution::Rf ( )

inline

Modify regression function.

Definition at line 74 of file regression_distribution.hpp.

References rf.

template<typename Archive >

void mlpack::distribution::RegressionDistribution::Serialize	(	Archive &	ar,
		const unsigned	int
	)

inline

Serialize the distribution.

Definition at line 65 of file regression_distribution.hpp.

References mlpack::data::CreateNVP().

void mlpack::distribution::RegressionDistribution::Train ( const arma::mat & observations )

Estimate the Gaussian distribution directly from the given observations.

Parameters

observations List of observations.

Referenced by Err().

void mlpack::distribution::RegressionDistribution::Train	(	const arma::mat &	observations,
		const arma::vec &	weights
	)

Estimate parameters using provided observation weights.

Parameters

weights probability that given observation is from distribution

Member Data Documentation

GaussianDistribution mlpack::distribution::RegressionDistribution::err

private

Error distribution.

Definition at line 36 of file regression_distribution.hpp.

Referenced by Err().

regression::LinearRegression mlpack::distribution::RegressionDistribution::rf

private

Regression function for representing conditional mean.

Definition at line 34 of file regression_distribution.hpp.

Referenced by Rf().

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

src/mlpack/core/dists/regression_distribution.hpp

Public Member Functions

Private Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation