gemseo / algos / doe

Hide inherited members

lib_scalable module

Build a diagonal DOE for scalable model construction.

class gemseo.algos.doe.lib_scalable.DiagonalDOE

Bases: DOELibrary

Class used to create a diagonal DOE.

class ApproximationMode(value)

Bases: StrEnum

The approximation derivation modes.

CENTERED_DIFFERENCES = 'centered_differences'

The centered differences method used to approximate the Jacobians by perturbing each variable with a small real number.

COMPLEX_STEP = 'complex_step'

The complex step method used to approximate the Jacobians by perturbing each variable with a small complex number.

FINITE_DIFFERENCES = 'finite_differences'

The finite differences method used to approximate the Jacobians by perturbing each variable with a small real number.

class DifferentiationMethod(value)

Bases: StrEnum

The differentiation methods.

CENTERED_DIFFERENCES = 'centered_differences'

COMPLEX_STEP = 'complex_step'

FINITE_DIFFERENCES = 'finite_differences'

USER_GRAD = 'user'

clear_listeners()

Remove the listeners from the database.

Return type:

None

compute_doe(variables_space, size=None, unit_sampling=False, **options)

Compute a design of experiments (DOE) in a variables space.

Parameters:

• variables_space (DesignSpace | int) – Either the variables space to be sampled or its dimension.

• size (int | None) – The size of the DOE. If None, the size is deduced from the options.

• unit_sampling (bool) –

  Whether to sample in the unit hypercube. If the value provided in variables_space is the dimension, the samples will be generated in the unit hypercube whatever the value of unit_sampling.

  By default it is set to False.

• **options (DOELibraryOptionType) – The options of the DOE algorithm.

Returns:

The design of experiments whose rows are the samples and columns the variables.

Return type:

RealArray

deactivate_progress_bar()

Deactivate the progress bar.

Return type:

None

driver_has_option(option_name)

Check the existence of an option.

Parameters:

option_name (str) – The name of the option.

Returns:

Whether the option exists.

Return type:

bool

ensure_bounds(orig_func, normalize=True)

Project the design vector onto the design space before execution.

Parameters:

• orig_func – The original function.

• normalize (bool) –

  Whether to use the normalized design space.

  By default it is set to True.

Returns:

A function calling the original function with the input data projected onto the design space.

evaluate_samples(eval_jac=False, n_processes=1, wait_time_between_samples=0.0, use_database=True, callbacks=())

Evaluate all the functions of the optimization problem at the samples.

Parameters:

• eval_jac (bool) –

  Whether to evaluate the Jacobian function.

  By default it is set to False.

• n_processes (int) –

  The maximum simultaneous number of processes used to parallelize the execution.

  By default it is set to 1.

• wait_time_between_samples (float) –

  The time to wait between each sample evaluation, in seconds.

  By default it is set to 0.0.

• use_database (bool) –

  Whether to store the evaluations in the database.

  By default it is set to True.

• callbacks (Iterable[CallbackType]) –

  The functions to be evaluated after each call to OptimizationProblem.evaluate_functions(); to be called as callback(index, (output, jacobian)).

  By default it is set to ().

Return type:

None

Warning

This class relies on multiprocessing features when n_processes > 1, it is therefore necessary to protect its execution with an if __name__ == '__main__': statement when working on Windows.

execute(problem, algo_name=None, eval_obs_jac=False, skip_int_check=False, **options)

Execute the driver.

Parameters:

• problem (OptimizationProblem) – The problem to be solved.

• algo_name (str | None) – The name of the algorithm. If None, use the algo_name attribute which may have been set by the factory.

• eval_obs_jac (bool) –

  Whether to evaluate the Jacobian of the observables.

  By default it is set to False.

• skip_int_check (bool) –

  Whether to skip the integer variable handling check of the selected algorithm.

  By default it is set to False.

• **options (DriverLibOptionType) – The options for the algorithm.

Returns:

The optimization result.

Raises:

ValueError – If algo_name was not either set by the factory or given as an argument.

Return type:

OptimizationResult

export_samples(doe_output_file)

Export the samples generated by DOE library to a CSV file.

Parameters:

doe_output_file (Path | str) – The path to the output file.

Return type:

None

filter_adapted_algorithms(problem)

Filter the algorithms capable of solving the problem.

Parameters:

problem (Any) – The problem to be solved.

Returns:

The names of the algorithms adapted to this problem.

Return type:

list[str]

finalize_iter_observer()

Finalize the iteration observer.

Return type:

None

get_optimum_from_database(message=None, status=None)

Return the optimization result from the database.

Return type:

OptimizationResult

get_x0_and_bounds_vects(normalize_ds, as_dict=False)

Return the initial design variable values and their lower and upper bounds.

Parameters:

• normalize_ds (bool) – Whether to normalize the design variables.

• as_dict (bool) –

  Whether to return dictionaries instead of NumPy arrays.

  By default it is set to False.

Returns:

The initial values of the design variables, their lower bounds, and their upper bounds.

Return type:

tuple[ndarray, ndarray, ndarray] | tuple[dict[str, ndarray], dict[str, ndarray], dict[str, ndarray]]

init_iter_observer(max_iter, message='')

Initialize the iteration observer.

It will handle the stopping criterion and the logging of the progress bar.

Parameters:

• max_iter (int) – The maximum number of iterations.

• message (str) –

  The message to display at the beginning of the progress bar status.

  By default it is set to “”.

Raises:

ValueError – If max_iter is lower than one.

Return type:

None

init_options_grammar(algo_name)

Initialize the options’ grammar.

Parameters:

algo_name (str) – The name of the algorithm.

Return type:

JSONGrammar

classmethod is_algorithm_suited(algorithm_description, problem)

Check if an algorithm is suited to a problem according to its description.

Parameters:

• algorithm_description (AlgorithmDescription) – The description of the algorithm.

• problem (Any) – The problem to be solved.

Returns:

Whether the algorithm is suited to the problem.

Return type:

bool

new_iteration_callback(x_vect)

Iterate the progress bar, implement the stop criteria.

Parameters:

x_vect (ndarray) – The design variables values.

Raises:

MaxTimeReached – If the elapsed time is greater than the maximum execution time.

Return type:

None

requires_gradient(driver_name)

Check if a driver requires the gradient.

Parameters:

driver_name (str) – The name of the driver.

Returns:

Whether the driver requires the gradient.

Return type:

bool

DESIGN_ALGO_NAME = 'Design algorithm'

DIMENSION = 'dimension'

EQ_TOLERANCE = 'eq_tolerance'

EVAL_JAC = 'eval_jac'

EVAL_OBS_JAC_OPTION = 'eval_obs_jac'

INEQ_TOLERANCE = 'ineq_tolerance'

LEVEL_KEYWORD = 'levels'

LIBRARY_NAME: ClassVar[str | None] = 'GEMSEO'

The name of the interfaced library.

MAX_DS_SIZE_PRINT = 40

MAX_TIME = 'max_time'

NORMALIZE_DESIGN_SPACE_OPTION = 'normalize_design_space'

N_PROCESSES = 'n_processes'

N_SAMPLES = 'n_samples'

OPTIONS_DIR: ClassVar[str | Path] = 'options'

The name of the directory containing the files of the grammars of the options.

OPTIONS_MAP: ClassVar[dict[str, str]] = {}

The names of the options in GEMSEO mapping to those in the wrapped library.

PHIP_CRITERIA = 'phi^p'

ROUND_INTS_OPTION = 'round_ints'

SAMPLES_TAG = 'samples'

SEED = 'seed'

USE_DATABASE_OPTION = 'use_database'

USE_ONE_LINE_PROGRESS_BAR: ClassVar[bool] = False

Whether to use a one line progress bar.

WAIT_TIME_BETWEEN_SAMPLES = 'wait_time_between_samples'

activate_progress_bar: ClassVar[bool] = True

Whether to activate the progress bar in the optimization log.

algo_name: str | None

The name of the algorithm used currently.

property algorithms: list[str]

The available algorithms.

descriptions: dict[str, AlgorithmDescription]

The description of the algorithms contained in the library.

eval_jac: bool

Whether to evaluate the Jacobian.

internal_algo_name: str | None

The internal name of the algorithm used currently.

It typically corresponds to the name of the algorithm in the wrapped library if any.

opt_grammar: JSONGrammar | None

The grammar defining the options of the current algorithm.

problem: OptimizationProblem

The optimization problem the driver library is bonded to.

samples: RealArray

The design vector samples in the design space.

The design space variable types stored as dtype metadata.

To access those in the unit hypercube, use unit_samples.

property seed: int

The default seed used for reproducibility reasons.

unit_samples: RealArray

The design vector samples projected in the unit hypercube.

In the case of a design space of dimension \(d\), the unit hypercube is \([0,1]^d\).

To access those in the design space, use samples.