Steady-State (Asynchronous) Algorithm#

class SteadyStateEA(search_space, n_iterations: int, population_size: int, selection_size: int, evaluation, save_dir, models=None, pop_path=None, crossover=<dragon.search_operators.crossover.DAGTwoPoint object>, verbose=False, **args)[source]

Bases: SearchAlgorithm

Search algorithm implementing the steady-state (asynchronous) search algorithm inheriting from the SearchAlgorithm class. It implements a select_next_configuration and a process_evaluated_configuration methods, specific to the evolutionary algorithm.

Parameters:

search_space (Variable) – Variable containing all the design choices from the search space. It should implement a random method and a neighbor one.
n_iterations (int) – Number of iterations.
population_size (int) – Size of the population.
selection_size (int:) – Size of the tournament selection.
crossover (function, default=DAGTwoPoint()) – Crossover function to use.
evaluation (function) – Performance evaluation function. Takes as argument a set of configuration and the unique index of this configuration. Returns the performance and the model built.
save_dir (str) – Path towards saving directory. If not empty, the content will be replaced.
models (list, default=None) – List of configurations that should be included into the initial population.
pop_path (str, default=None) – Path towards a directory containing an former evaluation that we aim to continue.
verbose (bool, default=False) – Verbose boolean.

selection_size

Size of the tournament selection.

Type:: int:

crossover

Crossover function to use.

Type:: function, default=DAGTwoPoint()

sent

Dictionary containing the configurations that are currently evaluated and thus are temporarly removed from the population.

Type:: dict, default={}

search_space

Variable containing all the design choices from the search space. It should implement a random method and a neighbor one if necessary.

Type:: Variable

n_iterations

Number of iterations.

Type:: int

population_size

Size of the randomly initialized population.

Type:: int

evaluation

Performance evaluation function. Takes as argument a set of configuration and the unique index of this configuration. Returns the performance and the model built.

Type:: function

save_dir

Path towards saving directory. If not empty, the content will be replaced.

Type:: str

models

List of configurations that should be included into the initial population.

Type:: list, default=None

pop_path

Path towards a directory containing an former evaluation that we aim to continue.

Type:: str, default=None

verbose

Verbose boolean.

Type:: bool, default=False

run

Run function to use: MPI (run_mpi) or not (run_no_mpi).

Type:: function

set_mpi

Dictionary containing the MPI parameters.

Type:: dict

storage

Dictionary storing the configurations from the population.

Type:: dict, default={}

min_loss

Current minimum loss found.

Type:: float, default=np.min

Example

>>> from dragon.search_space.base_variables import ArrayVar
>>> from dragon.search_operators.base_neighborhoods import ArrayInterval
>>> from dragon.search_algorithm.ssea import SteadyStateEA
>>> search_space = ArrayVar(dag, label="Search Space", neighbor=ArrayInterval())
>>> search_algorithm = SteadyStateEA(search_space, save_dir="save/test_ssea", n_iterations=20, population_size=5, selection_size=3, evaluation=loss_function)
>>> search_algorithm.run()

select_next_configurations()[source]

Defines a selection strategy for SSEA. Uses tournament selection of size self.selection_size to select two parent configurations. Creates two offsprings by mutating (through the neighbor attribute of the configuration) and with the crossover function.

Returns:: [self.K-1, self.K] – List containing the indexes of the two offsprings.
Return type:: list

process_evaluated_configuration(idx, loss)[source]

Determines if the configuration should be added to the population or not by calling self.replace_worst_individual(idx, loss).

Parameters:

idx (int) – Index of the configuration.
loss (float) – Loss of the evaluation.

Returns:

delete (True) – Boolean indicating if the configuration extra-information should be deleted. In SSEA, only extra-information of the best model are kept.
row_pop (dict) – Dictionary containing evaluation information to be saved within a .csv file called computation_file.csv.
loss (float) – Loss of the configuration.

replace_worst_individual(idx, loss)[source]

replace_worst_individualidx, loss) Determines if the configuration is better than the worst one from the population. If this is the case, removes the worst one from the population and returns True. Else, returns False.

Parameters:

idx (int) – Index of the configuration.
loss (float) – Loss of the evaluation.

Returns:

add – Boolean indicating if the configuration should be added to the population.

Return type:

boolean