# Update the mutation variance so that it varies linearly from g_max_mutation_sigma to
# g_min_mutation_sigma
g_current_sigma -= (g_max_mutation_sigma -
g_min_mutation_sigma) / (g_iterations - 1)
# Make sure the mutation variance is up-to-date
gaussian_mutation.setMutationVariance(g_current_sigma)
# Optimisation and visualisation
optimiser = EvolutionaryAlgorithm(test_problem, g_number_of_individuals)
# Set the selection operator
#optimiser.setSelectionOperator(TournamentSelection(2));
#optimiser.setSelectionOperator(RouletteWheel());
optimiser.setSelectionOperator(RankSelection())
# Create the genetic operators
elitism = ElitismOperator(0.1)
new_blood = NewBloodOperator(0.1)
gaussian_mutation = GaussianMutationOperator(0.1, 0.2)
blend_cross_over = BlendCrossoverOperator(0.6, gaussian_mutation)
# Add the genetic operators to the EA
optimiser.addGeneticOperator(new_blood)
optimiser.addGeneticOperator(gaussian_mutation)
optimiser.addGeneticOperator(blend_cross_over)
optimiser.addGeneticOperator(elitism)
test_problem.number_of_evaluation = 0
optimiser.plotAnimation(g_iterations, visualisationCallback)
# Default tournament size
tournament_size = 2
# The tournament size is always two for dual
if args.selection[0] == "dual":
tournament_size = 2
# Update the tournament size if needed
elif not isinstance(args.tournament_size, NoneType):
if isinstance(args.tournament_size, int):
tournament_size = args.tournament_size
else:
tournament_size = args.tournament_size[0]
# Set the selection operator
if args.selection[0] == "dual" or args.selection[0] == "tournament":
optimiser.setSelectionOperator(TournamentSelection(tournament_size))
elif args.selection[0] == "ranking":
optimiser.setSelectionOperator(RankSelection())
elif args.selection[0] == "roulette":
optimiser.setSelectionOperator(RouletteWheelSelection())
else:
raise ValueError(
'Invalid selection operator "%s". Choose "threshold", "tournament" or "dual".'
% (args.selection[0]))
# Create the genetic operators
gaussian_mutation = GaussianMutationOperator(
0.3, args.initial_mutation_variance[0])
blend_cross_over = BlendCrossoverOperator(0.6, gaussian_mutation)
# Add the genetic operators to the EA
#optimiser.setSelectionOperator(RouletteWheelSelection());
#optimiser.setSelectionOperator(RankSelection());
# Set the selection operator
selection_operator = None
if args.selection[0] == "dual" or args.selection[0] == "tournament":
selection_operator = tournament_selection
elif args.selection[0] == "threshold":
selection_operator = ThresholdSelection(0, tournament_selection, 10)
else:
raise ValueError(
'Invalid selection operator "%s". Choose "threshold", "tournament" or "dual".'
% (args.selection[0]))
optimiser.setSelectionOperator(selection_operator)
# Create the genetic operators
new_blood = NewBloodOperator(args.initial_new_blood_probability[0])
gaussian_mutation = GaussianMutationOperator(
1.0 - args.initial_new_blood_probability[0],
args.initial_mutation_variance[0])
# Add the genetic operators to the EA
optimiser.addGeneticOperator(new_blood)
optimiser.addGeneticOperator(gaussian_mutation)
# Show the visualisation
if args.visualisation:
fig, ax = plt.subplots(7, 2)
global_fitness_function.plot(fig, ax, 0, number_of_generation)
optimiser = EvolutionaryAlgorithm(local_fitness, g_number_of_individuals,
global_fitness)
optimiser.full_name = "Fly algorithm"
optimiser.short_name = "FA"
g_max_mutation_sigma = 0.1
g_min_mutation_sigma = 0.01
g_current_sigma = g_max_mutation_sigma
# Set the selection operator
tournament_selection = TournamentSelection(2)
threshold_selection = ThresholdSelection(0.0, tournament_selection,
round(0.25 * g_number_of_individuals))
optimiser.setSelectionOperator(threshold_selection)
#optimiser.setSelectionOperator(tournament_selection);
#optimiser.setSelectionOperator(RouletteWheel());
#optimiser.setSelectionOperator(RankSelection());
# Create the genetic operators
new_blood = NewBloodOperator(0.5)
gaussian_mutation = GaussianMutationOperator(0.5, 0.2)
# Add the genetic operators to the EA
optimiser.addGeneticOperator(new_blood)
optimiser.addGeneticOperator(gaussian_mutation)
g_iterations = round(max_iterations / g_number_of_individuals)
for i in range(g_iterations):