guassian_process Module Reference

Defines the base class of the type guassian_process_class. The guassian_process contains code to compuet guassian process profiles. More...

Data Types
type	gaussp_class
	Base class representing a gaussian process. More...
type	gaussp_class_pointer
	Pointer to a gaussian process object. Used for creating arrays of gaussian process pointers. This is needed because fortran does not allow arrays of pointers directly. More...

Functions/Subroutines
type(gaussp_class) function, pointer	gaussp_construct (a_model, n_signals, gaussp_type, profile_index, vrnc, tolerance, cholesky_fac)
	Construct a gaussp_class. More...
subroutine	gaussp_destruct (this)
	Deconstruct a gaussp_class object. More...
subroutine	gaussp_set_signal (this, signal, index)
	Set the object and coefficient for an index. More...
subroutine	gaussp_set_profile (this, a_model)
	Set the object and coefficient for an index. More...
real(rprec) function	gaussp_get_evidence (this, a_model)
	Calculates the evidence. More...

Detailed Description

Defines the base class of the type guassian_process_class. The guassian_process contains code to compuet guassian process profiles.

Function/Subroutine Documentation

gaussp_construct()

type (gaussp_class) function, pointer guassian_process::gaussp_construct	(	type (model_class), intent(in)	a_model,
		integer, intent(in)	n_signals,
		character(len=*), intent(in)	gaussp_type,
		integer, intent(in)	profile_index,
		real (rprec), dimension(:)	vrnc,
		real (rprec)	tolerance,
		real (rprec)	cholesky_fac
	)

Construct a gaussp_class.

Allocates memory and initializes a gaussp_class object. This just allocates the gaussp_class::signals, gaussp_class::a array, and matrixices for the GP computataion. The indices of these arrays are set by gaussp_set_signal, and the matrices are calculated in gaussp_get_modeled_signal

Parameters

[in]	a_model	A model::model_class instance.
[in]	n_signals	Number of signals in this gaussian process.
[in]	gaussp_type	The type of profile modeled by the gaussian process.
[in]	profile_index	Index of the profile of the sxrem profile.
[in]	vrnc	Variance values for the hyper parameters.
[in]	tolerance	Convergence value to maximize the log evidence.
[in]	choleskey_fac	Value added to diagnoal element to ensure K is PSD.

Returns

A pointer to a constructed gaussp_class object.

Todo:

FIXME: The guassian process kernels should know the correct ranges. Query those instead. For now set all to infinity.

Definition at line 103 of file guassian_process.f.

gaussp_destruct()

subroutine guassian_process::gaussp_destruct

(

type (gaussp_class), pointer

this

)

Deconstruct a gaussp_class object.

Deallocates memory and uninitializes a gaussp_class object.

Parameters

[in,out]

this

A gaussp_class instance.

Note

The destructors of the signals in the signal array are not called her because the gaussian process signals do not own the memory for those signals.

Definition at line 251 of file guassian_process.f.

gaussp_get_evidence()

real (rprec) function guassian_process::gaussp_get_evidence	(	type (gaussp_class), intent(inout)	this,
		type (model_class), pointer	a_model
	)

Calculates the evidence.

This method finds a gaussian process evidence. The matrices computed can be later used to set the profile.

Parameters

[in]	this	A gaussp_class instance.
[in,out]	a_model	A model instance.

Returns

The log evidence for the current hyper parameters.

Definition at line 494 of file guassian_process.f.

gaussp_set_profile()

subroutine guassian_process::gaussp_set_profile	(	type (gaussp_class), intent(inout)	this,
		type (model_class), pointer	a_model
	)

Set the object and coefficient for an index.

This method uses a gaussian process to set a model using the signals pointed in the gaussp_class::signals array. Hyper parameters are determined by maximizing the evidence.

Parameters

[in]	this	A gaussp_class instance.
[in,out]	a_model	A model instance.

Definition at line 354 of file guassian_process.f.

gaussp_set_signal()

subroutine guassian_process::gaussp_set_signal	(	type (gaussp_class), intent(inout)	this,
		class (signal_class), pointer	signal,
		integer, intent(in)	index
	)

Set the object and coefficient for an index.

Parameters

[in,out]	this	A gaussp_class instance.
[in]	signal	A signal_class instance.
[in]	a	A weight for the signal
[in]	index	The index to place the gaussp signal.

Note

Only signals that were created before this gaussian process can be added. Otherwise it will creat an infinitely recursive loop in gaussp_get_modeled_signal

Definition at line 323 of file guassian_process.f.