CADETProcess.optimization.OptimizationProblem

class CADETProcess.optimization.OptimizationProblem(name)

Class for configuring optimization problems.

Stores information about - optimization variables - objectives - linear and nonlinear constraints - callbacks - meta scores - multi-criteria-decision functions

Attributes:

namestr

Name of the optimization problem

evaluation_objectslist

list: Objects to be evaluated during optimization.

evaluatorsobj

list: Evaluators in OptimizationProblem.

cacheResultsCache

Cache to store (intermediate) results.

variableslist

list: List of all optimization variables.

objectives: list

Objective functions.

nonlinear_constraints: list of callables

Nonlinear constraint functions.

linear_constraintslist

list: Linear inequality constraints of OptimizationProblem.

linear_equality_constraintslist

list: Linear equality constraints of OptimizationProblem.

callbackslist

list: Callback functions for recording progress.

meta_scores: list

Meta score functions.

multi_criteria_decision_functionslist

list: Multi criteria decision functions.

Methods

add_callback(callback[, name, ...])	Add callback function for processing (intermediate) results.
add_evaluation_object(evaluation_object[, name])	Add evaluation object to the optimization problem.
add_evaluator(evaluator[, name, args, kwargs])	Add Evaluator to OptimizationProblem.
add_linear_constraint(opt_vars[, lhs, b])	Add linear inequality constraints.
add_linear_equality_constraint(opt_vars[, ...])	Add linear equality constraints.
add_meta_score(meta_score[, name, ...])	Add Meta score to the OptimizationProblem.
add_multi_criteria_decision_function(...[, name])	Add multi criteria decision function to OptimizationProblem.
add_nonlinear_constraint(nonlincon[, name, ...])	Add nonliner constraint function to optimization problem.
add_objective(objective[, name, ...])	Add objective function to optimization problem.
add_variable(name[, evaluation_objects, ...])	Add optimization variable to the OptimizationProblem.
add_variable_dependency(dependent_variable, ...)	Add dependency between two optimization variables.
check_bounds(x[, cv_bounds_tol])	Check if all bound constraints are kept.
check_config([ignore_linear_constraints])	Check if the OptimizationProblem is configured correctly.
check_duplicate_variables()	Raise warning if duplicate variables exist.
check_individual(x[, cv_bounds_tol, ...])	Check if individual is valid.
check_linear_constraints(x[, cv_lincon_tol])	Check if linear inequality constraints are met at point x.
check_linear_constraints_dependency()	Check that variables used in linear constraints are independent.
check_linear_constraints_transforms()	Check that variables used in linear constraints only use linear transforms.
check_linear_equality_constraints(x[, ...])	Check if linear equality constraints are met at point x.
check_nonlinear_constraints(x[, ...])	Check if all nonlinear constraints are met.
check_required_parameters()	Verify if all required parameters are set.
create_hopsy_problem([...])	Create a hopsy problem from the optimization problem.
create_individual(x[, f, f_minimized, g, ...])	Create new individual from data.
create_initial_values([n_samples, seed, ...])	Create initial value within parameter space.
create_population(X[, F, F_minimized, G, ...])	Create new population from data.
delete_cache([reinit])	Delete cache with (intermediate) results.
ensures2d()	Ensure X array is an ndarray with ndmin=2.
ensures_minimization()	Convert maximization problems to minimization problems.
evaluate_bounds(x)	Calculate bound violation.
evaluate_callbacks(population[, ...])	Evaluate callback functions for each individual x in population X.
evaluate_callbacks_population(*args, **kwargs)	Evaluate callbacks functions for each individual in a population.
evaluate_linear_constraints(x)	Calculate value of linear inequality constraints at point x.
evaluate_linear_equality_constraints(x)	Calculate value of linear equality constraints at point x.
evaluate_meta_scores(X[, ...])	Evaluate meta scores for each individual x in population X.
evaluate_meta_scores_population(*args, **kwargs)	Evaluate meta scores for each individual in a population.
evaluate_multi_criteria_decision_functions(...)	Evaluate evaluate multi criteria decision functions.
evaluate_nonlinear_constraints(X[, ...])	Evaluate nonlinear constraint functions for each individual x in population X.
evaluate_nonlinear_constraints_population(...)	Evaluate nonlinear constraint functions for each individual in a population.
evaluate_nonlinear_constraints_violation(X)	Evaluate nonlinear constraint function violation for each x in population X.
evaluate_nonlinear_constraints_violation_population(...)	Evaluate nonlinear constraint violation for each individual in a population.
evaluate_objectives(X[, ...])	Evaluate objective functions for each individual x in population X.
evaluate_objectives_population(*args, **kwargs)	Evaluate objective functions for each individual in a population.
get_chebyshev_center([...])	Compute chebychev center.
get_dependent_values(X_independent)	Determine values of dependent optimization variables.
get_independent_values(X)	Remove dependent values from x.
gets_dependent_values()	Get dependent values of individual before calling function.
nonlinear_constraint_jacobian(x[, dx])	Compute jacobian of the nonlinear constraints at point x.
objective_jacobian(x[, ensure_minimization, dx])	Compute jacobian of objective functions using finite differences.
prune_cache([tag, close])	Prune cache with (intermediate) results.
remove_linear_constraint(index)	Remove linear inequality constraint.
remove_linear_equality_constraint(index)	Remove linear equality constraint.
remove_variable(var_name)	Remove optimization variable from the OptimizationProblem.
set_variables(x)	Set the values from the x-vector to the EvaluationObjects.
setup_cache([n_shards])	Set up cache to store (intermediate) results.
transform(X_independent)	Transform independent optimization variables from untransformed parameter space.
transform_maximization(s, scores)	Transform maximization problems to minimization problems.
untransform(X_transformed)	Untransform the optimization variables from transformed parameter space.
untransforms()	Untransform population or individual before calling function.