def execute(toolbox: base.Toolbox, cases: int = 100) -> List[str]:
population = toolbox.population(n=POPULATION_SIZE)
hall_of_fame = tools.ParetoFront()
stats = tools.Statistics(lambda i: i.fitness.values)
stats.register("avg", numpy.mean, axis=0)
stats.register("std", numpy.std, axis=0)
stats.register("min", numpy.min, axis=0)
stats.register("max", numpy.max, axis=0)
logbook = tools.Logbook()
logbook.header = "gen", "evals", "std", "min", "avg", "max", "best"
# Evaluate every individuals
for individual in population:
individual.fitness.values = toolbox.evaluate(individual)
hall_of_fame.update(population)
record = stats.compile(population)
logbook.record(gen=0, evals=len(population), **record)
print(logbook.stream)
generated_cases = list
last_fitness = float('inf')
current_fitness = None
generation_count = 1
while generation_count <= MAX_GENERATIONS and (
last_fitness != current_fitness
or current_fitness == float('inf')):
last_fitness = current_fitness
# Select the next generation individuals
offspring = toolbox.select(population, floor(POPULATION_SIZE * 0.9))
# Clone the selected individuals
offspring = list(toolbox.map(toolbox.clone, offspring))
# Add new individuals from the population
offspring += toolbox.population(n=POPULATION_SIZE - len(offspring))
# Apply crossover and mutation on the offspring
for child1, child2 in zip(offspring[::2], offspring[1::2]):
if not random() < MATE_RATIO:
continue
toolbox.mate(child1, child2)
del child1.fitness.values
del child2.fitness.values
for mutant in offspring:
if not random() < MUTATION_RATIO:
continue
toolbox.mutate(mutant)
del mutant.fitness.values
# Evaluate the individuals with an invalid fitness
invalid_ind = [
individual for individual in offspring
if not individual.fitness.valid
]
for individual in offspring:
individual.fitness.values = toolbox.evaluate(individual)
generated_cases = tools.selBest(population, k=cases)
current_fitness = sum(
toolbox.map(op.itemgetter(0),
toolbox.map(toolbox.evaluate, generated_cases)))
best = choice(generated_cases)
word = "".join(best)
# Select the next generation population
population = toolbox.select(population + offspring, POPULATION_SIZE)
record = stats.compile(population)
logbook.record(gen=generation_count,
evals=len(invalid_ind),
best=word,
**record)
print(logbook.stream)
generation_count += 1
return [''.join(case) for case in generated_cases]
def run_opd_ga(toolbox: base.Toolbox,
popsize: int,
gens: int,
cxpb: float,
mutpb: float,
elitism_k: int,
new_inds_per_gen: int,
target_lambda: int,
verbose: bool = False):
if verbose:
print('Starting GA...')
fitness_history = []
pop = toolbox.generate_population(n=popsize)
fitnesses = toolbox.parallel_map(toolbox.evaluate, pop)
for ind, fit in zip(pop, fitnesses):
ind.fitness.values = fit
if verbose:
print('Initial evaluation done.')
fits = [ind.fitness.values[0] for ind in pop]
fitness_history += [fits.copy()]
g = 0
min_fits, max_fits, avg_fits, var_fits = [], [], [], []
while min(fits) > target_lambda and g < gens:
g = g + 1
elite = tools.selBest(pop, elitism_k)
offspring = toolbox.select(
pop,
len(pop) - elitism_k - new_inds_per_gen) + elite
offspring = list(
map(toolbox.clone,
offspring)) + toolbox.generate_population(n=new_inds_per_gen)
for child1, child2 in zip(offspring[::2], offspring[1::2]):
if random.random() < cxpb:
toolbox.mate(child1, child2)
del child1.fitness.values
del child2.fitness.values
for mutant in offspring:
if random.random() < mutpb:
toolbox.mutate(mutant)
del mutant.fitness.values
invalid_ind = [ind for ind in offspring if not ind.fitness.valid]
fitnesses = toolbox.parallel_map(toolbox.evaluate, invalid_ind)
for ind, fit in zip(invalid_ind, fitnesses):
ind.fitness.values = fit
pop[:] = offspring
fits = [ind.fitness.values[0] for ind in pop]
fitness_history += [fits.copy()]
if verbose == 2:
min_fits += [min(fits)]
max_fits += [max(fits)]
avg_fits += [statistics.mean(fits)]
var_fits += [statistics.variance(fits)]
if verbose and (g % (gens // 10) == 0 or g == 1):
print(f'Generation {g}')
if verbose == 2:
print(' Min %s' % min_fits[-1])
print(' Max %s' % max_fits[-1])
print(' Avg %s' % avg_fits[-1])
print(' Var %s' % var_fits[-1])
timeout = min(fits) == target_lambda
return {'fitness_history': fitness_history, 'timeout': timeout}
def learn_causal_structure(
toolbox: base.Toolbox,
pop_size: int = 10,
crossover_pr: float = 1,
mutation_pr: float = 0.2,
num_elites: int = 1,
max_gens: int = 50,
):
"""
Perform the structur learning task using a genetic algorithm
:param toolbox: registry of tools provided by DEAP
:param pop_size: the number of individuals per generation
:param crossover_pr: the crossover rate for every (monogamous) couple
:param mutation_pr: the mutation rate for every individual
:param num_elites:
:param max_gens: the maximum number of generations
:return:
"""
# initialize a collection of instrumentation utilities to facilitate later analysis
instrumentation = initialize_instrumentation()
# ====== 0️⃣ initialize population ======
population = toolbox.population(n=pop_size)
# ====== 1️⃣ Evaluate the entire population ======
n_evals = evaluate_population(population, toolbox)
# Log initial stats for later analysis
log_generation_stats(0, population, n_evals, **instrumentation)
# ====== 2️⃣ the loop is the only termination criterion ======
for gen in range(max_gens):
elites = get_fittest_individuals(population, num_elites)
# ====== 3️⃣ Parent selection ======
# Select the next generation individuals
offspring = toolbox.select(population, len(population))
# Clone the selected individuals
offspring = list(map(toolbox.clone, offspring))
# ====== 4️⃣ Apply crossover and mutation on the offspring ======
for child1, child2 in zip(offspring[::2], offspring[1::2]):
# crossover probability applies to every couple
if random.random() < crossover_pr:
toolbox.mate(child1, child2)
child1.fitness = np.nan
child2.fitness = np.nan
# mutation probability applies to every individual
for mutant in offspring:
if random.random() < mutation_pr:
toolbox.mutate(mutant)
mutant.fitness = np.nan
# ====== 5️⃣ Evaluate the individuals with an invalid fitness ======
n_evals = evaluate_population(offspring, toolbox)
# Log intermediary stats for later analysis
log_generation_stats(gen + 1, population, n_evals, **instrumentation)
# ====== 6️⃣ Replacement ======
# The population is entirely replaced by the offspring, except for the top elites
fittest_offsprings = get_fittest_individuals(offspring,
pop_size - num_elites)
population[:] = elites + fittest_offsprings
# ====== 7️⃣ Return final population ======
return population, instrumentation