def get_good_solution(task,
crossover_rate=CROSSOVER_RATE,
mutation_rate=MUTATION_RATE,
tournament_size=TOURNAMENT_SIZE,
population_size=POPULATION_SIZE):
best_individuals_values = np.empty(MAX_ITERATIONS)
population = init_population(task, population_size)
outer_iterator = 0
best_individual = 0
best_individual_value = 0
global_best_individual = 0
global_best_individual_value = 0
print('Initial value of the knapsack =',
population.individuals[0].evaluate())
while outer_iterator < MAX_ITERATIONS:
inner_iterator = 0
new_population = Population()
while inner_iterator < population_size:
parent1 = tournament(population, tournament_size)
parent2 = tournament(population, tournament_size)
child = crossover(parent1, parent2, crossover_rate)
mutate(child, mutation_rate)
new_population.add_individual(child)
inner_iterator += 1
best_individual = population.best_individual()
best_individual_value = best_individual.evaluate()
if best_individual_value >= global_best_individual_value:
global_best_individual = best_individual
global_best_individual_value = best_individual_value
new_population.set_first_individual(global_best_individual)
population = new_population
best_individuals_values[outer_iterator] = global_best_individual_value
outer_iterator += 1
return global_best_individual, best_individuals_values
def genetic():
ITERATIONS = 30
POP_SIZE = 40
CROSSOVER_RATE = 0.5
MUTATION_RATE = 0.01
TOURNAMENT_SIZE = 6
task = read('generatedTaskFile.csv')
print("Here it goes...")
population = init_population(task.numberOfObjects, POP_SIZE, task)
i = 0
while i < ITERATIONS:
print("New iteration")
j = 0
new_population = Population(task)
new_population.listOfIndividuals = []
while j < POP_SIZE:
parent1 = tournament(population, TOURNAMENT_SIZE, task)
parent2 = tournament(population, TOURNAMENT_SIZE, task)
child = Individual()
child.itemsTaken = crossover(parent1, parent2, CROSSOVER_RATE)
mutate(child, MUTATION_RATE)
new_population.addIndividualToPopulation(child)
j += 1
population = new_population
i += 1
return population.best()
def run_task(task):
print('Population size: ' + str(POPULATION_SIZE))
print('Number of generations: ' + str(ITERATIONS))
start = timer()
population = init_population(task, POPULATION_SIZE)
best = get_best_from_population(population)
end = timer()
print('Execution time: ' + str(end - start))
plt.plot(best)
plt.xlabel('GENERATION')
plt.ylabel('BEST INDIVIDUAL')
plt.show()
def genetic_algorithm(task,
crossover_rate=CROSSOVER_RATE,
mutation_rate=MUTATION_RATE,
tournament_size=TOURNAMENT_SIZE,
population_size=POPULATION_SIZE):
best_individuals_values = np.empty(MAX_ITERATIONS)
start_time = time.time()
population = init_population(task, population_size)
outer_iterator = 0
best_individual = 0
best_individual_value = 0
global_best_individual = 0
global_best_individual_value = 0
while outer_iterator < MAX_ITERATIONS:
inner_iterator = 0
new_population = Population()
while inner_iterator < population_size:
parent1 = tournament(population, tournament_size)
parent2 = tournament(population, tournament_size)
child = crossover(parent1, parent2, crossover_rate)
mutate(child, mutation_rate)
new_population.add_individual(child)
inner_iterator += 1
best_individual = population.best_individual()
best_individual_value = best_individual.evaluate()
if best_individual_value >= global_best_individual_value:
global_best_individual = best_individual
global_best_individual_value = best_individual_value
new_population.set_first_individual(global_best_individual)
population = new_population
best_individuals_values[outer_iterator] = global_best_individual_value
outer_iterator += 1
print("--- Genetic algorithm\'s execution time = %s seconds ---" %
(time.time() - start_time))
print('Genetic algorithm\'s final result =', global_best_individual_value)
sys.stderr.write('Usage: run_it [expriment_name (dir)] [generation] [population size]\n')
sys.exit(1)
scriptname = sys.argv[0]
exp_name = sys.argv[1]
generation = int( sys.argv[2] )
population = int( sys.argv[3] )
if generation == 0:
# init dirctory structure for this generation
init_generation(exp_name, generation, population)
# init directory structure for next generation
init_generation(exp_name, generation+1, population)
# initialize the bottom drag values for each member of the population
init_population(exp_name, generation, population)
else:
# init directory structure for next generation
init_generation(exp_name, generation+1, population)
# run models
submit_it(exp_name, generation, population)
# evaluate cost function and run genetic algorithm
# calc_vrms for current generation
# rank current generation
rank_population(exp_name, generation, population)
# cross over and mutate to create next generation
evolve(exp_name, generation, populatoin)