return gene_constraints(new_g1), gene_constraints(new_g2)
def crossover(ind1, ind2):
offspring_genes = crossover_blend(ind1.get_gene(), ind2.get_gene())
return [
create_individual(offspring_genes[0]),
create_individual(offspring_genes[1])
]
if __name__ == '__main__':
random.seed(30)
p_1 = create_random_individual()
p_2 = create_random_individual()
offspring = crossover(p_1, p_2)
c_1 = offspring[0]
c_2 = offspring[1]
x = np.linspace(MIN_BORDER, MAX_BORDER)
plt.plot(x, fitness(x), '--', color='blue')
plt.plot([p_1.get_gene(), p_2.get_gene()], [p_1.fitness, p_2.fitness],
'o',
markersize=15,
color='orange')
plt.plot([c_1.get_gene(), c_2.get_gene()], [c_1.fitness, c_2.fitness],
's',
import random
from ch2.individual import create_random_individual
def select_tournament(population, tournament_size):
new_offspring = []
for _ in range(len(population)):
candidates = [random.choice(population) for _ in range(tournament_size)]
new_offspring.append(max(candidates, key = lambda ind: ind.fitness))
return new_offspring
if __name__ == '__main__':
random.seed(29)
POPULATION_SIZE = 5
generation_1 = [create_random_individual() for _ in range(POPULATION_SIZE)]
generation_2 = select_tournament(generation_1, 3)
print("Generation 1")
[print(ind) for ind in generation_1]
print("Generation 2")
[print(ind) for ind in generation_2]
from ch2.crossover import crossover
from ch2.individual import create_random_individual
from ch2.mutate import mutate
from ch2.population import plot_population
from ch2.selection import select_tournament
if __name__ == '__main__':
POPULATION_SIZE = 10
CROSSOVER_PROBABILITY = .8
MUTATION_PROBABILITY = .1
MAX_GENERATIONS = 10
random.seed(29)
population = [create_random_individual() for _ in range(POPULATION_SIZE)]
for generation_number in range(POPULATION_SIZE):
# SELECTION
selected = select_tournament(population, 3)
# CROSSOVER
crossed_offspring = []
for ind1, ind2 in zip(selected[::2], selected[1::2]):
if random.random() < CROSSOVER_PROBABILITY:
children = crossover(ind1, ind2)
crossed_offspring.append(children[0])
crossed_offspring.append(children[1])
else:
crossed_offspring.append(ind1)
crossed_offspring.append(ind2)
# MUTATION
def mutate_gaussian(g, mu, sigma):
mutated_gene = g + random.gauss(mu, sigma)
return gene_constraints(mutated_gene)
def mutate(ind):
return create_individual(mutate_gaussian(ind.get_gene(), 0, 1))
if __name__ == '__main__':
random.seed(37)
individual = create_random_individual()
mutated = mutate(individual)
x = np.linspace(MIN_BORDER, MAX_BORDER)
plt.plot(x, fitness(x), '--', color = 'blue')
plt.plot(
[individual.get_gene()],
[individual.fitness],
'o', markersize = 20, color = 'orange'
)
plt.plot(
[mutated.get_gene()],
[mutated.fitness],
's', markersize = 20, color = 'green'
)
plt.title("Circle : Before Mutation, Square: After Mutation")