gemseo / algos / doe

# doe_lib module¶

## DOE library base class wrapper¶

Classes:

 Abstract class to use for DOE library link See DriverLib.
class gemseo.algos.doe.doe_lib.DOELibrary[source]

Abstract class to use for DOE library link See DriverLib.

Constructor Abstract class.

Attributes:

Methods:

 compute_phip_criteria(samples) Compute the phi^p criteria (see Morris & Mitchell, Exploratory designs for computational experiments, 1995) driver_has_option(option_key) Checks if the option key exists. ensure_bounds(orig_func[, normalize]) Project the design vector onto the design space before execution. evaluate_samples([eval_jac, n_processes, …]) Evaluates all functions of optimization problem at the samples. execute(problem[, algo_name]) Executes the driver. export_samples(doe_output_file) Export samples generated by DOE library to a csv file. filter_adapted_algorithms(problem) Filters the algorithms capable of solving the problem. Finalize the iteration observer. get_optimum_from_database([message, status]) Retrieves the optimum from the database and builds an optimization result object from it. get_x0_and_bounds_vects(normalize_ds) Gets x0, bounds, normalized or not depending on algo options, all as numpy arrays. init_iter_observer(max_iter, message) Initialize the iteration observer. init_options_grammar(algo_name) Initializes the options grammar. is_algo_requires_grad(algo_name) Returns True if the algorithm requires a gradient evaluation. is_algorithm_suited(algo_dict, problem) Checks if the algorithm is suited to the problem according to its algo dict. Callback called at each new iteration, ie every time a design vector that is not already in the database is proposed by the optimizer.
COMPLEX_STEP_METHOD = 'complex_step'
DESCRIPTION = 'description'
DESIGN_ALGO_NAME = 'Design algorithm'
DIFFERENTIATION_METHODS = ['user', 'complex_step', 'finite_differences']
DIMENSION = 'dimension'
EQ_TOLERANCE = 'eq_tolerance'
EVAL_JAC = 'eval_jac'
FINITE_DIFF_METHOD = 'finite_differences'
HANDLE_EQ_CONS = 'handle_equality_constraints'
HANDLE_INEQ_CONS = 'handle_inequality_constraints'
INEQ_TOLERANCE = 'ineq_tolerance'
INTERNAL_NAME = 'internal_algo_name'
LIB = 'lib'
MAX_DS_SIZE_PRINT = 40
MAX_TIME = 'max_time'
MIN_DIMS = 'min_dims'
NORMALIZE_DESIGN_SPACE_OPTION = 'normalize_design_space'
N_PROCESSES = 'n_processes'
N_SAMPLES = 'n_samples'
OPTIONS_DIR = 'options'
OPTIONS_MAP = {}
PHIP_CRITERIA = 'phi^p'
POSITIVE_CONSTRAINTS = 'positive_constraints'
PROBLEM_TYPE = 'problem_type'
ROUND_INTS_OPTION = 'round_ints'
SAMPLES_TAG = 'samples'
SEED = 'seed'
USE_DATABASE_OPTION = 'use_database'
WAIT_TIME_BETWEEN_SAMPLES = 'wait_time_between_samples'
WEBSITE = 'website'
property algorithms

Return the available algorithms.

static compute_phip_criteria(samples)[source]

Compute the phi^p criteria (see Morris & Mitchell, Exploratory designs for computational experiments, 1995)

Parameters

samples – design variables list

driver_has_option(option_key)

Checks if the option key exists.

Parameters

option_key – the name of the option

Returns

True if the option is in the grammar

ensure_bounds(orig_func, normalize=True)

Project the design vector onto the design space before execution.

Parameters
• orig_func – the original function

• normalize – if True, use the normalized design space

Returns

the wrapped function

evaluate_samples(eval_jac=False, n_processes=1, wait_time_between_samples=0)[source]

Evaluates all functions of optimization problem at the samples.

Parameters

eval_jac – if True, the jacobian is also evaluated (Default value = False)

execute(problem, algo_name=None, **options)

Executes the driver.

Parameters
• problem – the problem to be solved

• algo_name – name of the algorithm if None, use self.algo_name which may have been set by the factory (Default value = None)

• options – the options dict for the algorithm

export_samples(doe_output_file)[source]

Export samples generated by DOE library to a csv file.

Parameters

doe_output_file (string) – export file name

Filters the algorithms capable of solving the problem.

Parameters

problem – the opt_problem to be solved

Returns

the list of adapted algorithms names

finalize_iter_observer()

Finalize the iteration observer.

get_optimum_from_database(message=None, status=None)

Retrieves the optimum from the database and builds an optimization result object from it.

Parameters
• message – Default value = None)

• status – Default value = None)

get_x0_and_bounds_vects(normalize_ds)

Gets x0, bounds, normalized or not depending on algo options, all as numpy arrays.

Parameters

normalize_ds – if True, normalizes all input vars that are not integers, according to design space normalization policy

Returns

x, lower bounds, upper bounds

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 – maximum number of calls

• message – message to display at the beginning

init_options_grammar(algo_name)

Initializes the options grammar.

Parameters

algo_name – name of the algorithm

Returns True if the algorithm requires a gradient evaluation.

Parameters

algo_name – name of the algorithm

static is_algorithm_suited(algo_dict, problem)[source]

Checks if the algorithm is suited to the problem according to its algo dict.

Parameters
• algo_dict – the algorithm characteristics

• problem – the opt_problem to be solved

new_iteration_callback()

Callback called at each new iteration, ie every time a design vector that is not already in the database is proposed by the optimizer.

Iterates the progress bar, implements the stop criteria.