metaheuristic_designer.parent_selection.parent_selection_functions

Core parent selection functions (tournament, roulette, SUS, best, …) and fitness scaling helpers.

Functions

create_scaling_fn(method[, scaling_factor])	Create a callable that computes normalized selection weights.
exponential_ranking(fitness, scaling_factor)	Exponential ranking: weight decays exponentially with rank.
fitness_proportional(fitness, scaling_factor)	Fitness proportional scaling.
flat_ranking(fitness, scaling_factor)	Flat ranking: every individual receives equal weight.
linear_ranking(fitness, scaling_factor)	Linear ranking: weight proportional to rank.
prob_tournament(fitness, amount[, rng, ...])	Selects the parents for the next generation by tournament.
repeating_selection(fitness, amount[, rng])	Chooses the entire population repeated in order duplicated enough times to reach the specified amount.
roulette(fitness, amount[, rng, method, ...])	Fitness proportionate parent selection.
select_best(fitness, amount[, rng])	Selects the best parent of the population as parents.
shuffle_population(fitness, amount[, rng])	Chooses a number of individuals from the population at random without replacement if amount < population_size.
sigma_scaling(fitness, scaling_factor)	Sigma scaling: weight based on standard deviations above the mean.
sus(fitness, amount[, rng, method, ...])	Stochastic universal sampling parent selection method.
uniform_selection(fitness, amount[, rng])	Chooses a number of individuals from the population at random with replacement.