operators += ugp4.GenOperator(ugp4.create_random_individual, 0)
operators += ugp4.GenOperator(ugp4.macro_pool_uniform_crossover, 2)
# Create the object that will manage the evolution__________________________________________________________________
mu = 10
nu = 20
strength = 0.5
lambda_ = 7
max_age = 10
for _ in range(1):
darwin = ugp4.Darwin(
constraints=library,
operators=operators,
mu=mu,
nu=nu,
lambda_=lambda_,
strength=strength,
max_age=max_age,
)
# Evolve____________________________________________________________________________________________________________
darwin.evolve()
logging.bare("This is the final population:")
for individual in darwin.population:
ugp4.print_individual(individual)
ugp4.logging.bare(individual.fitness)
ugp4.logging.bare("")
# Print best individuals
logging.bare("These are the best ever individuals:")
# Fitness (simple)
library.evaluator = ugp4.fitness.make_evaluator(
evaluator=lambda s: s.count('1'), fitness_type=ugp4.fitness.Simple)
# Create a list of operators with their aritiy
operators = ugp4.Operators()
# Add initialization operators
operators += ugp4.GenOperator(ugp4.create_random_individual, 0)
# Add mutation operators
operators += ugp4.GenOperator(ugp4.hierarchical_mutation, 1)
operators += ugp4.GenOperator(ugp4.flat_mutation, 1)
# Evolution core
darwin = ugp4.Darwin(constraints=library,
operators=operators,
mu=50,
nu=50,
lambda_=10,
strength=.7,
max_age=50,
max_generations=10)
darwin.evolve()
# That's all
ugp4.logging.bare("Final archive:")
for i in darwin.archive.individuals:
ugp4.logging.bare(f"{i.id}: {i} [{i.fitness}]")
ugp4.logging.log_cpu(ugp4.logging.INFO, "Program completed")
sys.exit(0)