Parent class for surrogate models. More...

Inheritance diagram for Surrogate:

Public Member Functions
	Surrogate ()
	Constructor that uses defaultConfigOptions and does not build.

	Surrogate (const ParameterList &param_list)
	Constructor that sets configOptions but does not build. More...

	Surrogate (const MatrixXd &samples, const MatrixXd &response, const ParameterList &param_list)
	Constructor for the Surrogate that sets configOptions and builds the surrogate (does nothing in the base class). More...

virtual	~Surrogate ()
	Default destructor.

virtual void	build (const MatrixXd &samples, const MatrixXd &response)=0
	Build the Surrogate using specified build data. More...

virtual VectorXd	value (const MatrixXd &eval_points)
	Evaluate the Surrogate at a set of prediction points for a scalar QoI. More...

virtual VectorXd	values (const MatrixXd &eval_points)
	Evaluate the Surrogate at a set of prediction points for field QoIs. More...

virtual MatrixXd	gradient (const MatrixXd &eval_points)
	Evaluate the gradient of the scalar Surrogate at a set of prediction points. More...

MatrixXd	gradients (const MatrixXd &eval_points)
	Evaluate the gradient of the field Surrogate at a set of prediction points. More...

virtual MatrixXd	hessian (const MatrixXd &eval_point)
	Evaluate the Hessian of the scalar Surrogate at a set of prediction points. More...

virtual MatrixXd	hessians (const MatrixXd &eval_point)
	Evaluate the Hessian of the field Surrogate at a set of prediction points. More...

void	variable_labels (const std::vector< std::string > &var_labels)
	Set the variable/feature names. More...

const std::vector< std::string > &	variable_labels () const
	Get the (possibly empty) variable/feature names. More...

void	response_labels (const std::vector< std::string > &resp_labels)
	Set the response/QoI names. More...

const std::vector< std::string > &	response_labels () const
	Get the (possibly empty) response/QoI names. More...

void	set_options (const ParameterList &options)
	Set the Surrogate's configOptions. More...

void	get_options (ParameterList &options)
	Get the Surrogate's configOptions. More...

void	print_options ()
	Print the Surrogate's configOptions.

virtual void	default_options ()=0
	Initialize the Surrogate's defaultConfigOptions.

virtual bool	diagnostics_available ()

VectorXd	evaluate_metrics (const StringArray &mnames, const MatrixXd &points, const MatrixXd &ref_values)
	Evalute metrics at specified points (within surrogates)

VectorXd	cross_validate (const MatrixXd &samples, const MatrixXd &response, const StringArray &mnames, const int num_folds=5, const int seed=20)
	Perform K-folds cross-validation (within surrogates)

template<typename DerivedSurr >
void	save (const DerivedSurr &surr_out, const std::string &outfile, const bool binary)
	Serialize a derived (i.e. non-base) surrogate model. More...

template<typename DerivedSurr >
void	load (const std::string &infile, const bool binary, DerivedSurr &surr_in)
	Load a derived (i.e. non-base) surrogate model. More...

Static Public Member Functions
template<typename SurrHandle >
static void	save (const SurrHandle &surr_out, const std::string &outfile, const bool binary)
	serialize Surrogate to file (typically through shared_ptr<Surrogate>, but Derived& or Derived* okay too)

template<typename SurrHandle >
static void	load (const std::string &infile, const bool binary, SurrHandle &surr_in)
	serialize Surrogate from file (typically through shared_ptr<Surrogate>, but Derived& or Derived* okay too)

static std::shared_ptr< Surrogate >	load (const std::string &infile, const bool binary)
	serialize Surrogate from file through pointer to base class (must have been saved via same data type)

Public Attributes
util::DataScaler	dataScaler
	DataScaler class for a Surrogate's build samples.

double	responseOffset = 0.
	Response offset.

double	responseScaleFactor = 1.
	Response scale factor.

Protected Member Functions
virtual std::shared_ptr< Surrogate >	clone () const =0
	clone derived Surrogate class for use in cross-validation

Protected Attributes
int	numSamples
	Number of samples in the Surrogate's build samples.

int	numVariables
	Number of features/variables in the Surrogate's build samples.

std::vector< std::string >	variableLabels
	Names of the variables/features; need not be populated.

int	numQOI
	Number of quantities of interest predicted by the surrogate. For scalar-valued surrogates numQOI = 1.

std::vector< std::string >	responseLabels
	Names of the responses/QoIs; need not be populated.

ParameterList	defaultConfigOptions
	Default Key/value options to configure the surrogate.

ParameterList	configOptions
	Key/value options to configure the surrogate - will override defaultConfigOptions.

Private Member Functions
template<class Archive >
void	serialize (Archive &archive, const unsigned int version)
	Serializer for base class data (call from dervied with base_object)

Friends
class	boost::serialization::access
	Allow serializers access to private class data.

Detailed Description

Parent class for surrogate models.

The Surrogate class defines the API for surrogate models contained in the Dakota surrogates module.

Pure virtual functions include build, value, and default_options. Gradient and Hessian methods are optional.

Configuration options for a surrogate are set through the use of a Teuchos ParameterList named configOptions.

Constructor & Destructor Documentation

◆ Surrogate() [1/2]

Surrogate ( const ParameterList & param_list )

Constructor that sets configOptions but does not build.

Parameters

[in] param_list List that overrides entries in defaultConfigOptions.

References Surrogate::numQOI, and dakota::silence_unused_args().

◆ Surrogate() [2/2]

Surrogate	(	const MatrixXd &	samples,
		const MatrixXd &	response,
		const ParameterList &	param_list
	)

Constructor for the Surrogate that sets configOptions and builds the surrogate (does nothing in the base class).

Parameters

[in]	samples	Matrix of data for surrogate construction - (num_samples by num_features).
[in]	response	Vector of targets for surrogate construction - (num_samples by num_qoi = 1; only 1 response is supported currently).
[in]	param_list	List that overrides entries in defaultConfigOptions.

References Surrogate::numQOI, and dakota::silence_unused_args().

Member Function Documentation

◆ build()

virtual void build	(	const MatrixXd &	samples,
		const MatrixXd &	response
	)

pure virtual

Build the Surrogate using specified build data.

Parameters

[in]	samples	Matrix of data for surrogate construction - (num_samples by num_features).
[in]	response	Vector of responses/targets for surrogate construction - (num_samples by num_qoi = 1).

Implemented in Python, PolynomialRegression, and GaussianProcess.

◆ value()

VectorXd value ( const MatrixXd & eval_points )

virtual

Evaluate the Surrogate at a set of prediction points for a scalar QoI.

Parameters

[in] eval_points Matrix of prediction points - (num_pts by num_features).

Returns: Values of the Surrogate at the prediction points - (num_pts).

Reimplemented in Python, PolynomialRegression, GaussianProcess, and PyPolyReg.

References dakota::silence_unused_args().

Referenced by Surrogate::evaluate_metrics(), dakota::surrogates::fd_check_gradient(), dakota::surrogates::fd_check_hessian(), PYBIND11_MODULE(), and PyPolyReg::value().

◆ values()

VectorXd values ( const MatrixXd & eval_points )

virtual

Evaluate the Surrogate at a set of prediction points for field QoIs.

Parameters

[in] eval_points Vector of prediction points - (num_features).

Returns: Values of the Surrogate at the prediction points - (num_pts).

Reimplemented in Python.

References dakota::silence_unused_args().

Referenced by PYBIND11_MODULE().

◆ gradient()

MatrixXd gradient ( const MatrixXd & eval_points )

virtual

Evaluate the gradient of the scalar Surrogate at a set of prediction points.

Parameters

[in] eval_points Matrix of prediction points - (num_pts by num_features).

Returns: Matrix of gradient vectors at the prediction points - (num_pts by num_features).

Reimplemented in Python, PolynomialRegression, and GaussianProcess.

References dakota::silence_unused_args().

Referenced by dakota::surrogates::fd_check_gradient(), and PYBIND11_MODULE().

◆ gradients()

MatrixXd gradients ( const MatrixXd & eval_points )

Evaluate the gradient of the field Surrogate at a set of prediction points.

Parameters

[in]

eval_points

Matrix of prediction points

(num_pts by num_features).

Returns: Matrix of gradient vectors at the prediction points - (num_pts by num_features).

References dakota::silence_unused_args().

Referenced by PYBIND11_MODULE().

◆ hessian()

MatrixXd hessian ( const MatrixXd & eval_point )

virtual

Evaluate the Hessian of the scalar Surrogate at a set of prediction points.

Parameters

[in] eval_point Coordinates of the prediction point - (1 by num_features).

Returns: Hessian matrix at the prediction point - (num_features by num_features).

Reimplemented in Python, PolynomialRegression, and GaussianProcess.

References dakota::silence_unused_args().

Referenced by dakota::surrogates::fd_check_hessian(), and PYBIND11_MODULE().

◆ hessians()

MatrixXd hessians ( const MatrixXd & eval_point )

virtual

Evaluate the Hessian of the field Surrogate at a set of prediction points.

Parameters

[in] eval_point Coordinates of the prediction point - (1 by num_features).

Returns: Hessian matrix at the prediction point - (num_features by num_features).

References dakota::silence_unused_args().

Referenced by PYBIND11_MODULE().

◆ variable_labels() [1/2]

void variable_labels ( const std::vector< std::string > & var_labels )

Set the variable/feature names.

Parameters

[in] var_labels Vector of strings, one per input variable

References Surrogate::variableLabels.

◆ variable_labels() [2/2]

const std::vector< std::string > & variable_labels ( ) const

Get the (possibly empty) variable/feature names.

Returns: Vector of strings, one per input variable; empty if not set

References Surrogate::variableLabels.

Referenced by PYBIND11_MODULE().

◆ response_labels() [1/2]

void response_labels ( const std::vector< std::string > & resp_labels )

Set the response/QoI names.

Parameters

[in] resp_labels Vector of strings, one per surrogate response

References Surrogate::responseLabels.

◆ response_labels() [2/2]

const std::vector< std::string > & response_labels ( ) const

Get the (possibly empty) response/QoI names.

Returns: Vector of strings, one per surrogate response; empty if not set

References Surrogate::responseLabels.

Referenced by PYBIND11_MODULE().

◆ set_options()

void set_options ( const ParameterList & options )

Set the Surrogate's configOptions.

Parameters

[in] options ParameterList of configuration options.

References Surrogate::configOptions.

◆ get_options()

void get_options ( ParameterList & options )

Get the Surrogate's configOptions.

Parameters

[out] options ParameterList of configuration options.

References Surrogate::configOptions.

◆ save()

void save	(	const DerivedSurr &	surr_out,
		const std::string &	outfile,
		const bool	binary
	)

Serialize a derived (i.e. non-base) surrogate model.

Parameters

[in]	surr_out	Surrogate to seralize.
[in]	outfile	Name of the output text or binary file.
[in]	binary	Flag for binary or text format.

◆ load()

void load	(	const std::string &	infile,
		const bool	binary,
		DerivedSurr &	surr_in
	)

Load a derived (i.e. non-base) surrogate model.

Parameters

[in]	infile	Filename for serialized surrogate.
[in]	binary	Flag for binary or text format.
[in]	surr_in	Derived surrogate class to be populated with serialized data.

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

SurrogatesBase.hpp
SurrogatesBase.cpp

Public Member Functions

Static Public Member Functions

Public Attributes

Protected Member Functions

Protected Attributes

Private Member Functions

Friends

Detailed Description

Constructor & Destructor Documentation

◆ Surrogate() [1/2]

◆ Surrogate() [2/2]

Member Function Documentation

◆ build()

◆ value()

◆ values()

◆ gradient()

◆ gradients()

◆ hessian()

◆ hessians()

◆ variable_labels() [1/2]

◆ variable_labels() [2/2]

◆ response_labels() [1/2]

◆ response_labels() [2/2]

◆ set_options()

◆ get_options()

◆ save()

◆ load()