gemseo / algos / opt

lib_scipy_linprog module¶

SciPy linear programming library wrapper.

Classes:

ScipyLinprog()

SciPy linear programming library interface.

class gemseo.algos.opt.lib_scipy_linprog.ScipyLinprog[source]¶

Bases: gemseo.algos.opt.opt_lib.OptimizationLibrary

SciPy linear programming library interface.

See OptimizationLibrary.

Constructor.

Generate the library dictionary that contains the list of algorithms with their characteristics.

Attributes:

Methods:

`algorithm_handles_eqcstr`(algo_name)	Returns True if the algorithms handles equality constraints.
`algorithm_handles_ineqcstr`(algo_name)	Returns True if the algorithms handles inequality constraints.
`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.
`execute`(problem[, algo_name])	Executes the driver.
`filter_adapted_algorithms`(problem)	Filters the algorithms capable of solving the problem.
`finalize_iter_observer`()	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_right_sign_constraints`()	Transforms the problem constraints into their opposite sign counterpart if the algorithm requires positive constraints.
`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_algo_requires_positive_cstr`(algo_name)	Returns True if the algorithm requires positive constraints False otherwise.
`is_algorithm_suited`(algo_dict, problem)	Checks if the algorithm is suited to the problem according to its algo dict.
`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.

COMPLEX_STEP_METHOD = 'complex_step'¶

DESCRIPTION = 'description'¶

DIFFERENTIATION_METHODS = ['user', 'complex_step', 'finite_differences']¶

EQ_TOLERANCE = 'eq_tolerance'¶

FINITE_DIFF_METHOD = 'finite_differences'¶

F_TOL_ABS = 'ftol_abs'¶

F_TOL_REL = 'ftol_rel'¶

HANDLE_EQ_CONS = 'handle_equality_constraints'¶

HANDLE_INEQ_CONS = 'handle_inequality_constraints'¶

INEQ_TOLERANCE = 'ineq_tolerance'¶

INTERNAL_NAME = 'internal_algo_name'¶

LIB = 'lib'¶

LIB_COMPUTE_GRAD = True¶

LS_STEP_NB_MAX = 'max_ls_step_nb'¶

LS_STEP_SIZE_MAX = 'max_ls_step_size'¶

MAX_DS_SIZE_PRINT = 40¶

MAX_FUN_EVAL = 'max_fun_eval'¶

MAX_ITER = 'max_iter'¶

MAX_TIME = 'max_time'¶

NORMALIZE_DESIGN_SPACE_OPTION = 'normalize_design_space'¶

OPTIONS_DIR = 'options'¶

OPTIONS_MAP = {'max_iter': 'maxiter', 'redundancy removal': 'rr', 'verbose': 'disp'}¶

PG_TOL = 'pg_tol'¶

POSITIVE_CONSTRAINTS = 'positive_constraints'¶

PROBLEM_TYPE = 'problem_type'¶

REDUNDANCY_REMOVAL = 'redundancy removal'¶

REQUIRE_GRAD = 'require_grad'¶

REVISED_SIMPLEX = 'REVISED_SIMPLEX'¶

ROUND_INTS_OPTION = 'round_ints'¶

STOP_CRIT_NX = 'stop_crit_n_x'¶

USER_DEFINED_GRADIENT = 'user'¶

USE_DATABASE_OPTION = 'use_database'¶

VERBOSE = 'verbose'¶

WEBSITE = 'website'¶

X_TOL_ABS = 'xtol_abs'¶

X_TOL_REL = 'xtol_rel'¶

algorithm_handles_eqcstr(algo_name)¶

Returns True if the algorithms handles equality constraints.

Parameters: algo_name – the name of the algorithm
Returns: True or False

algorithm_handles_ineqcstr(algo_name)¶

Returns True if the algorithms handles inequality constraints.

Parameters: algo_name – the name of the algorithm
Returns: True or False

property algorithms¶: Return the available algorithms.

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

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

filter_adapted_algorithms(problem)¶

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_right_sign_constraints()¶: Transforms the problem constraints into their opposite sign counterpart if the algorithm requires positive constraints.

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

is_algo_requires_grad(algo_name)¶

Returns True if the algorithm requires a gradient evaluation.

Parameters: algo_name – name of the algorithm

is_algo_requires_positive_cstr(algo_name)¶

Returns True if the algorithm requires positive constraints False otherwise.

Parameters: algo_name – the name of the algorithm
Returns: True if constraints must be positive
Return type: logical

static is_algorithm_suited(algo_dict, problem)¶

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

`COMPLEX_STEP_METHOD`
`DESCRIPTION`
`DIFFERENTIATION_METHODS`
`EQ_TOLERANCE`
`FINITE_DIFF_METHOD`
`F_TOL_ABS`
`F_TOL_REL`
`HANDLE_EQ_CONS`
`HANDLE_INEQ_CONS`
`INEQ_TOLERANCE`
`INTERNAL_NAME`
`LIB`
`LIB_COMPUTE_GRAD`
`LS_STEP_NB_MAX`
`LS_STEP_SIZE_MAX`
`MAX_DS_SIZE_PRINT`
`MAX_FUN_EVAL`
`MAX_ITER`
`MAX_TIME`
`NORMALIZE_DESIGN_SPACE_OPTION`
`OPTIONS_DIR`
`OPTIONS_MAP`
`PG_TOL`
`POSITIVE_CONSTRAINTS`
`PROBLEM_TYPE`
`REDUNDANCY_REMOVAL`
`REQUIRE_GRAD`
`REVISED_SIMPLEX`
`ROUND_INTS_OPTION`
`STOP_CRIT_NX`
`USER_DEFINED_GRADIENT`
`USE_DATABASE_OPTION`
`VERBOSE`
`WEBSITE`
`X_TOL_ABS`
`X_TOL_REL`
`algorithms`	Return the available algorithms.