def call_mlrose_curve(algorith_keyword, problem, pop_size=200, mutation_prob=0.1, max_attempts=10, max_iters=np.inf, curve=False\
, random_state=None, schedule=mlrose.GeomDecay(), init_state=None, restarts=0, keep_pct=0.2, fast_mimic=True):
if algorith_keyword == 'RHC':
best_state, best_fitness, curve_output = mlrose.random_hill_climb(problem, max_attempts=max_attempts, max_iters=max_iters\
, restarts=restarts, init_state=init_state, curve=curve, random_state=random_state)
elif algorith_keyword == 'GA':
best_state, best_fitness, curve_output = mlrose.genetic_alg(problem, pop_size=pop_size, mutation_prob=mutation_prob\
, max_attempts=max_attempts, max_iters=max_iters, curve=curve, random_state=random_state)
elif algorith_keyword == 'SA':
best_state, best_fitness, curve_output = mlrose.simulated_annealing(problem, schedule=schedule, max_attempts=max_attempts\
,max_iters=max_iters, init_state=init_state, curve=curve, random_state=random_state)
elif algorith_keyword == 'MIMIC':
print("problem: ", problem, "\npop_size: ", pop_size, "\n",
"keep_pct: ", keep_pct)
print("max_attempts: ", max_attempts, "\nmax_iters: ", max_iters,
"\nrandom_state: ", random_state, "\nfast_mimic: ", fast_mimic)
best_state, best_fitness, curve_output = mlrose.mimic(problem, pop_size=pop_size, keep_pct=keep_pct\
, max_attempts=max_attempts, max_iters=max_iters, curve=curve, random_state=random_state)
print("best_fitness: ", best_fitness)
else:
print(
"\n\nIncorrect 'algorithm_keyword'. Please check the input to the 'call_mlrose' function.\n\n"
)
best_state, best_fitness, curve_output = 'incorrect key word', 'incorrect key word', 'incorrect key word'
return best_state, best_fitness, curve_output
def rank(fnames, ga_max_attempts=25):
"""return fnames ranked"""
dist_mat = np.load(fnames["dmat"])
dist_list = mat2tuples(dist_mat)
# define fitness function object
fitness_dists = mlrose.TravellingSales(distances=dist_list)
# define optimization problem object
n_len = dist_mat.shape[0]
problem_fit = mlrose.TSPOpt(length=n_len, fitness_fn=fitness_dists, maximize=False)
# solve problem using the genetic algorithm
best_state = mlrose.genetic_alg(
problem_fit, mutation_prob=0.2, max_attempts=ga_max_attempts, random_state=2
)[0]
# retrieve ranked list
cand = load(fnames["cand"])
ranked_cand = cand.loc[best_state]
# save the output
fname, ext = os.path.splitext(fnames["cand"])
fname_ranked = fname + "_ranked" + ext
write(fname_ranked, ranked_cand)
_log.info("Ordered candidates saved to %s", fname_ranked)
return fname_ranked
def runComplexityGenetic(pType, problem):
if pType == 'One Max':
neighbor = 50
populationSize = 800
iterations = 1000
mutation = 0.001
elif pType == 'Flip Flop':
neighbor = 36
populationSize = 1000
iterations = 1000
mutation = 0.001
else:
neighbor = 50
populationSize = 250
iterations = 10000
mutation = 0.15
s = time()
# best_state, best_fitness = mlrose.genetic_alg(problem,
# pop_size=populationSize,
# mutation_prob=mutation,
# max_attempts=neighbor,
# max_iters= iterations,
# random_state=1)
best_state, best_fitness, c = hive.genetic_alg(problem,
pop_size=populationSize,
mutation_prob=mutation,
max_attempts=neighbor,
max_iters=iterations,
random_state=1)
timeTaken = time() - s
return best_fitness, timeTaken
def gen_alg(opt):
global count
count = 0
gen_loss_list = []
gen_train_acc_list = []
gen_test_acc_list = []
for population in range(200, 4001, 200):
best_state_spam, best_fitness_spam, _ = mlrose.genetic_alg(
opt, pop_size=population, curve=True)
train_predict_gen = predict(best_state_spam, train_features_spam_norm)
test_predict_gen = predict(best_state_spam, test_features_spam_norm)
train_accuracy_hill = accuracy_score(train_labels_spam,
train_predict_gen)
test_accuracy_hill = accuracy_score(test_labels_spam, test_predict_gen)
gen_loss_list.append(best_fitness_spam)
gen_train_acc_list.append(train_accuracy_hill)
gen_test_acc_list.append(test_accuracy_hill)
plt.figure(figsize=(10, 6))
plt.subplot(121)
plt.plot(np.arange(200, 4001, 200), gen_loss_list, label='-1*loss')
plt.xlabel('population num')
plt.ylabel('minus of loss')
plt.title('loss versus population num')
plt.legend(loc='lower right')
plt.subplot(122)
plt.plot(np.arange(200, 4001, 200), gen_train_acc_list, label='train')
plt.plot(np.arange(200, 4001, 200), gen_test_acc_list, label='test')
plt.xlabel('population num')
plt.ylabel('accuracy')
plt.title('accuracy versus population num')
plt.legend(loc='lower right')
plt.show()
def compare_methods(num_char):
global count
count=0
fitness_obj=mlrose.CustomFitness(heter_string_fn)
opt=mlrose.DiscreteOpt(num_char,fitness_obj,maximize=True,max_val=num_char)
best_state_climb,best_fitness_climb,fitness_curve_climb=mlrose.random_hill_climb(opt,curve=True)
print('---------------------random hill climb-------------------------')
print('hill climbing best state for heter-string problem:',best_state_climb)
print('hill climbing best fitness for heter-string problem:',best_fitness_climb)
print('hill climbing fitting curve for heter-string problem:',fitness_curve_climb)
print('number of fitness call used:',count)
count=0
print('-------------------simulated annealing-------------------------')
best_state_ann,best_fitness_ann,fitness_curve_ann=mlrose.simulated_annealing(opt,schedule=mlrose.ExpDecay(),curve=True)
print('simulated annealing best state for heter-string problem:',best_state_ann)
print('simulated annealing best fitness for heter-string problem:',best_fitness_ann)
print('simulated annealing fitting curve for heter-string problem:',fitness_curve_ann)
print('number of fitness call used:',count)
count=0
best_state_ga,best_fitness_ga,fitness_curve_ga=mlrose.genetic_alg(opt,pop_size=200, mutation_prob=0.5,curve=True)
print('---------------------genetic alg----------------------------')
print('genetic algorithm best state for heter-string problem:',best_state_ga)
print('genetic algorithm best fitnees for heter-string problem:',best_fitness_ga)
print('genetic algorithm fitness curve for heter-string problem:',fitness_curve_ga)
print('number of fitness call used:',count)
count=0
best_state_mimic,best_fitness_mimic,fitness_curve_mimic=mlrose.mimic(opt,pop_size=200,curve=True)
print('------------------------mimic-------------------------------')
print('mimic best state for heter-string problem:',best_state_mimic)
print('mimic best fitness value for heter-string problem:',best_fitness_mimic)
print('mimic curve for heter-string problem:',fitness_curve_mimic)
print('number of fitness call used:',count)
count=0
plt.figure(figsize=(10,10))
plt.subplot(221)
plt.plot(fitness_curve_climb)
plt.ylabel('fitness')
plt.xlabel('num_iter')
plt.ylim(20,50)
plt.title('random hill climb')
plt.subplot(222)
plt.plot(fitness_curve_ann)
plt.ylabel('fitness')
plt.xlabel('num_iter')
plt.ylim(20,50)
plt.title('simulated annealing')
plt.subplot(223)
plt.plot(fitness_curve_ga)
plt.ylim(20,50)
plt.ylabel('fitness')
plt.xlabel('num_iter')
plt.title('genetic algorithm')
plt.subplot(224)
plt.plot(fitness_curve_mimic)
plt.ylim(20,50)
plt.title('mimic')
plt.ylabel('fitness')
plt.xlabel('num_iter')
plt.show()
def gen(problem, init_state, max_attempts, max_iters):
best_state, best_fitness, fitness_curve = mlrose_hiive.genetic_alg(problem, pop_size=200, mutation_prob=0.1,
max_attempts = max_attempts, max_iters = max_iters, curve=True, random_state = 1)
print('genetic')
print(best_state)
print(best_fitness)
# print(fitness_curve)
return best_state, best_fitness, fitness_curve
def test_genetic_alg_discrete_min():
"""Test genetic_alg function for a discrete minimization problem"""
problem = DiscreteOpt(5, OneMax(), maximize=False)
best_state, best_fitness, _ = genetic_alg(problem, max_attempts=50)
x = np.array([0, 0, 0, 0, 0])
assert (np.array_equal(best_state, x) and best_fitness == 0)
def test_genetic_alg_continuous_min():
"""Test genetic_alg function for a continuous minimization problem"""
problem = ContinuousOpt(5, OneMax(), maximize=False)
best_state, best_fitness, _ = genetic_alg(problem, max_attempts=200)
x = np.array([0, 0, 0, 0, 0])
assert (np.allclose(best_state, x, atol=0.5) and best_fitness < 1)
def tsp(distances=None, num_of_nodes=None):
'''https://mlrose.readthedocs.io/en/stable/source/tutorial2.html'''
fitness_coordinates = TravellingSales(distances=distances)
problem_fit = TSPOpt(length=num_of_nodes,
fitness_fn=fitness_coordinates,
maximize=False)
best_route, _ = genetic_alg(problem_fit, random_state=2)
return best_route
def ga(problem, iterations, random_seed, graph_file, graph_title):
mutation_prob = [0.1, 0.2, 0.3, 0.4, 0.5]
best_score = []
time_taken = []
fn_evals_taken = []
global eval_count
for m in mutation_prob:
fitness = []
fit_time = []
fn_evals = []
for i in iterations:
eval_count = 0
start = datetime.datetime.now()
best_state, best_fitness, _ = mlrose_hiive.genetic_alg(problem, mutation_prob=m,
max_iters=i, random_state=random_seed)
finish = datetime.datetime.now()
fitness.append(best_fitness)
fit_time.append((finish - start).total_seconds())
fn_evals.append(eval_count)
# Find the best score achieved in that mutation prob
best_score.append(max(fitness))
index = fitness.index(max(fitness))
# find the time that was taken to achieve that
time_taken.append(fit_time[index])
fn_evals_taken.append(fn_evals[index])
plt.plot(iterations, fitness, label="Mutation = " + str(m))
plt.legend(loc="best", title='Mutation Probability')
plt.grid()
generate_graph(graph_file + "ga", graph_title + "Genetic Algorithm", "Iterations", "Fitness")
# Decays best_score and time_taken
plt.plot(mutation_prob, best_score)
plt.grid()
generate_graph(graph_file + "ga_mut", graph_title + "Genetic Algorithm",
"Mutation Probability", "Best Score Achieved")
"""
plt.plot(mutation_prob, time_taken)
plt.grid()
generate_graph("cp_sa_decay_time", "Continuous Peaks - Genetic Algorithm", "Mutation Probability",
"Time taken to achieve that")
"""
plt.scatter(time_taken, best_score)
for i, txt in enumerate(mutation_prob):
plt.annotate(s=str(txt), xy=(time_taken[i], best_score[i]))
plt.legend(loc='best', title='Mutation Probability')
plt.grid()
generate_graph(graph_file + "ga_scatter", graph_title + "Genetic Algorithm",
"Time Taken", "Best Score achieved")
print('Mutation prob: ', mutation_prob)
print('Best scores reached: ', best_score)
print('Time taken to do that: ', time_taken)
print('Function evaluations taken: ', fn_evals_taken)
def genetic_algorithm(problem_fit, vectorLength, data_dir, iterlist):
directory = "./" + data_dir + "/curves/"
if not os.path.exists(directory):
os.makedirs(directory)
path1 = './' + data_dir
path2 = "./" + data_dir + "/curves/"
prl = []
beststate = []
bestfit = []
curve = []
time = []
iterlistn = []
for pr in np.linspace(0.1, 1, 5):
for iters in iterlist:
start = clock()
best_state, best_fitness, train_curve = mlrose.genetic_alg(problem_fit, \
mutation_prob = pr,\
max_iters=int(iters),
curve=True, random_state=randomSeed)
end = clock()
iterlistn.append(int(iters))
time.append(end - start)
beststate.append(best_state)
bestfit.append(best_fitness)
prl.append(pr)
curve.append(train_curve)
if (verbose == True):
print(pr)
print(int(iters))
print(best_state)
print(best_fitness)
ffga = pd.DataFrame({
'Mutation Probability': prl,
'Best Fitness': bestfit,
'Iterations': iterlistn,
'Time': time
})
beststatedf = pd.DataFrame(0.0,
index=range(1, vectorLength + 1),
columns=range(len(beststate)))
for i in range(len(curve)):
curvedf = pd.DataFrame(curve[i])
curvedf.to_csv(
os.path.join(path2,
'gacurve{}_{}.csv'.format(prl[i], iterlistn[i])))
for i in range(1, len(beststate) + 1):
beststatedf.loc[:, i] = beststate[i - 1]
ffga.to_csv(os.path.join(path1, 'ga.csv'))
beststatedf.to_csv(os.path.join(path1, 'gastates.csv'))
def compare_multi_round_k_color():
global count
count = 0
fitness_obj = mlrose.CustomFitness(k_color_fit)
opt = mlrose.DiscreteOpt(50, fitness_obj, maximize=True, max_val=8)
fitness_list_rhc = []
fitness_list_ann = []
fitness_list_genetic = []
fitness_list_mimic = []
num_sample_rhc = []
num_sample_ann = []
num_sample_genetic = []
num_sample_mimic = []
for i in range(20):
best_state_climb, best_fitness_climb, fitness_curve_climb = mlrose.random_hill_climb(
opt, curve=True)
fitness_list_rhc.append(best_fitness_climb)
num_sample_rhc.append(count)
count = 0
best_state_ann, best_fitness_ann, fitness_curve_ann = mlrose.simulated_annealing(
opt, schedule=mlrose.ExpDecay(), curve=True)
fitness_list_ann.append(best_fitness_ann)
num_sample_ann.append(count)
count = 0
best_state_ga, best_fitness_ga, fitness_curve_ga = mlrose.genetic_alg(
opt, pop_size=500, mutation_prob=0.5, curve=True)
fitness_list_genetic.append(best_fitness_ga)
num_sample_genetic.append(count)
count = 0
best_state_mimic, best_fitness_mimic, fitness_curve_mimic = mlrose.mimic(
opt, pop_size=500, curve=True)
fitness_list_mimic.append(best_fitness_mimic)
num_sample_mimic.append(count)
count = 0
plt.figure(figsize=(10, 6))
plt.subplot(121)
plt.plot(fitness_list_rhc, label='rhc')
plt.plot(fitness_list_ann, label='ann')
plt.plot(fitness_list_genetic, label='ga')
plt.plot(fitness_list_mimic, label='mimic')
plt.xlabel('rounds')
plt.ylabel('finess value')
plt.title('fitness value comparision')
plt.legend(loc='lower right')
plt.subplot(122)
plt.plot(num_sample_rhc, label='rhc')
plt.plot(num_sample_ann, label='ann')
plt.plot(num_sample_genetic, label='ga')
plt.plot(num_sample_mimic, label='mimic')
plt.xlabel('rounds')
plt.ylabel('fitness calls')
plt.title('fitness call number comparision')
plt.legend(loc='upper right')
plt.show()
def get_genetic(problem, pop_size=300, mutation_prob=0.4):
best_state, best_fitness, fitness_curve = mlrose.genetic_alg(
problem,
pop_size=pop_size,
mutation_prob=mutation_prob,
max_attempts=100,
max_iters=np.inf,
curve=True,
random_state=23)
return best_state, best_fitness, fitness_curve
def plot_optimization_problem_fitness(fitness_function, iterations, random_state, title):
start_rhc = timeit.default_timer()
rhc_best_state, rhc_best_fitness, rch_fitness_curve = mlrose.random_hill_climb(fitness_function, max_iters=iterations, random_state= random_state, restarts=10, curve=True)
rhc_elapsed = timeit.default_timer() - start_rhc
start_sa = timeit.default_timer()
sa_best_state, sa_best_fitness, sa_fitness_curve = mlrose.simulated_annealing(fitness_function, max_iters=iterations, random_state= random_state, curve=True)
sa_elapsed = timeit.default_timer() - start_sa
start_ga = timeit.default_timer()
ga_best_state, ga_best_fitness, ga_fitness_curve = mlrose.genetic_alg(fitness_function, max_iters=iterations, random_state= random_state, curve=True)
ga_elapsed = timeit.default_timer() - start_ga
start_mimic = timeit.default_timer()
mimic_best_state, mimic_best_fitness, mimic_fitness_curve = mlrose.mimic(fitness_function, max_iters=iterations, random_state= random_state, curve=True)
mimic_elapsed = timeit.default_timer() - start_mimic
# Fill in arrays.
rch_fitness_curve_bf = np.full(iterations, rhc_best_fitness)
rch_fitness_curve_bf[:rch_fitness_curve.shape[0]] = rch_fitness_curve
sa_fitness_curve_bf = np.full(iterations, sa_best_fitness)
sa_fitness_curve_bf[:sa_fitness_curve.shape[0]] = sa_fitness_curve
ga_fitness_curve_bf = np.full(iterations, ga_best_fitness)
ga_fitness_curve_bf[:ga_fitness_curve.shape[0]] = ga_fitness_curve
mimic_fitness_curve_bf = np.full(iterations, mimic_best_fitness)
mimic_fitness_curve_bf[:mimic_fitness_curve.shape[0]] = mimic_fitness_curve
# Plot the convergance times.
plot_ro_algo_times(rhc_elapsed, ga_elapsed, sa_elapsed, mimic_elapsed, title)
# Plot the fitness over iterations.
fig = plt.figure(figsize=(8,6))
plt.plot(rch_fitness_curve_bf, label="RHC")
plt.plot(sa_fitness_curve_bf, label="SA")
plt.plot(ga_fitness_curve_bf, label="GA")
plt.plot(mimic_fitness_curve_bf, label="MIMIC")
plt.xlabel("Number of Iterations")
plt.xticks(np.arange(0.0, iterations, step=iterations / 10))
plt.ylabel("Fitness Function")
plt.title(title)
plt.legend(prop={'size':13}, loc='lower right')
plt.savefig('Charts/OptimizationProblems/' + title + '.png')
plt.clf()
def get_order(self, distance_matrix) -> Tuple[np.ndarray, float]:
n_locations = len(distance_matrix)
distance_triples = _create_distance_triples(distance_matrix)
fitness_dists = mlrose.TravellingSales(distances=distance_triples)
problem_fit = mlrose.TSPOpt(length=n_locations,
fitness_fn=fitness_dists,
maximize=False)
best_state, best_fitness, iterations = mlrose.genetic_alg(
problem_fit, mutation_prob=0.2, max_attempts=100, random_state=2)
best_state = super()._close_circle(
super()._roll_state_in_order(best_state))
return best_state, best_fitness
def find_best(self, pois: list, **kwargs):
logging.debug('init bucket')
bucket = Bucket(self.routing)
logging.debug('compute distance matrix')
self.compute_distances(pois, bucket)
logging.debug('define fitness function')
fitness_dists = mlrose.TravellingSales(distances=bucket.distances)
logging.debug('define optimization problem')
problem_fit = mlrose.TSPOpt(
length=len(pois),
fitness_fn=fitness_dists,
maximize=False
)
logging.debug('run randomized optimization algorithm')
best_state, best_fitness, fitness_curve = mlrose.genetic_alg(problem_fit, random_state=2, **kwargs)
segments = bucket.segments(self._generate_keys(best_state))
meters = sum([segment.path.distance for segment in segments])
return Tour(segments, meters)
def plot_GAmutpop(problem, problem_fit, max_attempts, gamut, maxIter, seed, min=False):
Mutatepop = [200, 300, 400, 500, 600, 700, 800, 900, 1000]
plt.figure()
for m in Mutatepop:
best_state, best_fitness, gafitness_curve = mlrose.genetic_alg(problem_fit, pop_size=m, mutation_prob=gamut,
curve=True, max_attempts=max_attempts,
max_iters=maxIter, random_state=seed)
if min:
gafitness_curve = np.array(gafitness_curve) * -1
plt.plot(gafitness_curve, label='mut pop = ' + str(m))
print(m, best_fitness)
plt.title(problem + " - GA - Mutation Populations")
plt.xlabel('Iterations')
plt.ylabel('Fitness')
plt.grid(True)
plt.legend()
plt.savefig("Images\\" + problem + " - GA - Mutation Populations")
plt.show()
def plot_GAmut(problem, problem_fit, max_attempts, gapop, maxIter, seed, min=False):
Mutate = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
plt.figure()
for m in Mutate:
best_state, best_fitness, gafitness_curve = mlrose.genetic_alg(problem_fit, mutation_prob=m, curve=True,
max_iters=maxIter, max_attempts=max_attempts,
pop_size=gapop, random_state=seed)
if min:
gafitness_curve = np.array(gafitness_curve) * -1
plt.plot(gafitness_curve, label='mut prob =' + str(m))
print(m, best_fitness)
plt.title(problem + " - GA - Mutation Probabilities")
plt.xlabel('Iterations')
plt.ylabel('Fitness')
plt.grid(True)
plt.legend()
plt.savefig("Images\\" + problem + " - GA - Mutation Probabilities")
plt.show()
def plot_ga_graph(prob_type):
try:
os.mkdir("./GA")
except FileExistsError:
pass
except OSError as error:
print("Error creating directory results.")
print('\n plot_ga_graph - Progress: ', end="")
fitness, problem = get_fitness_function(prob_type)
process_time = []
fitness_score = []
population = [100, 200, 300, 500, 700, 1000, 1500]
for i in population:
print(".", end="")
start = time.time()
best_state, best_fitness, fitness_curve = mlrose.genetic_alg(
problem,
pop_size=i,
mutation_prob=__MUTATION_PROBABILITY,
max_attempts=__MAX_ATTEMPTS[prob_type],
max_iters=__MAX_ITERS,
random_state=10)
fitness_score.append(best_fitness)
process_time.append(time.time() - start)
plt.figure(300)
plt.plot(fitness_score)
plt.xticks(np.arange(len(population)), [str(p) for p in population])
plt.xlabel("pop_size constant")
plt.ylabel("fitness score")
plt.title('Genetic Algorithm')
plt.savefig("GA/" + "Fitness.png")
plt.figure(301)
plt.plot(process_time)
plt.xticks(np.arange(len(population)), [str(p) for p in population])
plt.xlabel("pop_size constant")
plt.ylabel("time")
plt.title('GA')
plt.savefig("GA/" + "Time.png")
def genetic_algorithm(problem, init_state, max_attempts, max_iters):
start_time = time.time()
# Does the kind of mutation/algo matter?
best_state, best_fitness, fitness_curve = mlr.genetic_alg(
problem,
pop_size=200,
mutation_prob=0.1,
max_attempts=max_attempts,
max_iters=max_iters,
curve=True,
random_state=RANDOM_STATE)
end_time = time.time()
total_time = end_time - start_time
print('Genetic Algorithm')
print("Elapsed Time", total_time)
#print(best_state)
print(best_fitness)
# print(fitness_curve)
return best_state, best_fitness, fitness_curve, total_time
def run_GA_1(problem, init_state, **kwargs):
fit_vals = []
fit_curves = []
times = []
fevals = []
# run multiple times to get average
for random_state in random_states:
start = time.time()
_, best_fit, fit_curve, evals = genetic_alg(problem,
random_state=random_state,
curve=True,
fevals=True,
pop_size=120,
mutation_prob=0.12,
**kwargs)
fit_vals.append(best_fit)
fit_curves.append(fit_curve)
times.append(time.time() - start)
fevals.append(sum(evals.values()))
# plot average fitness value
# now = datetime.now()
# dt_string = now.strftime("%Y-%m-%d-%H-%M-%S")
# hack for ease of naming
problem_name = str(problem.fitness_fn).split('.')[-1].split(' ')[0]
# chart_name = f"charts/ga_{problem_name}_{len(init_state)}_{dt_string}"
# plt.plot(average_curves(fit_curves), label="ga")
# plt.title(f"GA {problem_name} ({len(init_state)})")
# plt.xlabel("step")
# plt.ylabel("fitness")
# plt.savefig(chart_name)
# plt.show()
avg_fit = np.average(fit_vals)
avg_time = round(np.mean(times), 2)
avg_evals = np.mean(fevals)
print(f"GA {problem_name}: {avg_fit}: {avg_time}: {avg_evals}")
return avg_fit, avg_time, avg_evals
def compare_gen_mimic():
fitness_obj = mlrose.CustomFitness(n_peak_fit)
opt = mlrose.DiscreteOpt(1, fitness_obj, maximize=True, max_val=10000)
global count
count = 0
iter_num_counter_ga = []
fitness_list_ga = []
iter_num_counter_mimic = []
fitness_list_mimic = []
for i in range(20):
best_state_ga, best_fitness_ga, fitness_curve_ga = mlrose.genetic_alg(
opt, pop_size=20, mutation_prob=0.5, curve=True)
iter_num_counter_ga.append(count)
fitness_list_ga.append(best_fitness_ga)
count = 0
best_state_mimic, best_fitness_mimic, fitness_curve_mimic = mlrose.mimic(
opt, pop_size=20, curve=True)
iter_num_counter_mimic.append(count)
fitness_list_mimic.append(best_fitness_mimic)
count = 0
plt.figure(figsize=(8, 6))
plt.subplot(121)
plt.plot(fitness_list_ga, label='ga')
plt.plot(fitness_list_mimic, label='mimic')
plt.xlabel('rounds')
plt.ylabel('finess value')
plt.title('fitness value comparision')
plt.legend(loc='lower right')
plt.subplot(122)
plt.plot(iter_num_counter_ga, label='ga')
plt.plot(iter_num_counter_mimic, label='mimic')
plt.xlabel('rounds')
plt.ylabel('fitness call no.')
plt.title('fitness call number comparision')
plt.legend(loc='upper right')
plt.show()
schedule=schedule,
max_attempts=attempts,
random_state=seed,
curve=True,
init_state=init)
print(f" best SA State: {best_sa_state}")
sub_end = time.time()
sa_fitnesses.append(best_sa_fitness)
sa_times.append(sub_end - sub_start)
## Genetic Algorithm
sub_start = time.time()
best_ga_state, best_ga_fitness, ga_curve = mlr.genetic_alg(
problem,
pop_size=200,
max_attempts=attempts,
random_state=seed,
curve=True,
elite_dreg_ratio=0.5,
mutation_prob=0.4)
print(f" best GA State: {best_ga_state}")
sub_end = time.time()
ga_fitnesses.append(best_ga_fitness)
ga_times.append(sub_end - sub_start)
## MIMIC
sub_start = time.time()
best_m_state, best_m_fitness, m_curve = mlr.mimic(problem,
pop_size=200,
max_attempts=attempts,
random_state=seed,
curve=True)
# generate N random 3d vectors whose values lie in the range [1, 10)
coords = np.random.randint(1, 10, size=(N, 3))
print(coords)
if k == 2:
coords[:, 0] *= -1
elif k == 3:
coords[:, 0] *= -1
coords[:, 1] *= -1
elif k == 4:
coords[:, 1] *= -1
# compute the distance between each and every point
dist_list = [(i, j, round(np.linalg.norm(coords[i] - coords[j]), 3))
for i in range(N) for j in range(i + 1, N)]
# define the fitness object and run the solver
fitness_coords = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(length=len(coords),
fitness_fn=fitness_coords,
maximize=False)
best_state, _, _ = mlrose.genetic_alg(problem_fit, random_state=2)
with open('drone' + str(k) + '_points.txt', 'w') as out:
# jugaad to avoid regex in parsing coords within controller script
sys.stdout = out
for i in coords:
print(*i, sep=' ', end=';')
print(*best_state, sep=' ', end='')
sys.stdout = oldout
plt.ylabel("Fitness")
plt.title("TSP: Fitness curve vs decay rate in SA")
plt.savefig("output/tsp_sa_decay.png")
plt.close()
print(df.max())
#%% tuning for GA
curve_list = []
pop_sizes = [100, 200, 300]
for p in pop_sizes:
_, _, curve = mlrose.genetic_alg(
problem,
max_attempts=MAX_ATTEMPTS,
max_iters=3000,
pop_size=p,
elite_dreg_ratio=1,
curve=True,
random_state=RANDOM_SEED,
)
curve_list.append(curve)
df = 1 / pd.DataFrame(curve_list).transpose()
df.columns = pop_sizes
df.plot()
plt.xlabel("Iteration")
plt.ylabel("Fitness")
plt.title("TSP: Fitness curve vs population size in GA")
plt.savefig("output/tsp_ga_pop.png")
plt.close()
columns = ['Time', 'Fitness', 'Population Size', 'Mutation Rate']
df=pd.read_csv("./queen/queen_prob/ga__queen_prob__run_stats_df.csv")
print(df[columns].sort_values(by=['Fitness'], ascending=False))
max_attempts = 20
max_iters = 25
mutation_prob=0.5
pop_size = 10
eval_count = 0
best_state, best_fitness, gen_curve = mlrh.genetic_alg(prob,
max_attempts=max_attempts,
max_iters=max_iters,
random_state=random_state,
pop_size=pop_size,
mutation_prob=mutation_prob,
curve=True)
print("Genetic Alg - Total Function Evaluations:", eval_count)
plot_fitness_iteration('fitness_iteration_ga_queens.png',gen_curve,
"Queens - Genetic Alg: mutation_prob: {}, pop_size: {}".format(mutation_prob, pop_size))
# MIMIC
mim = mlrh.MIMICRunner(problem=prob,
experiment_name=experiment_name,
output_directory=output_directory,
seed=random_state,
population_sizes=[50, 100, 200],
keep_percent_list=[0.1, 0.25, 0.5, 0.75],
'onemax': mlrose.OneMax(),
# 'path': mlrose.CustomFitness(path, problem_type='discrete'),
'flipflop': mlrose.FlipFlop(),
# 'cliffs': mlrose.CustomFitness(cf1, problem_type='discrete'),
# 'cliffs': mlrose.CustomFitness(is_larger, problem_type='discrete'),
# 'max2color': mlrose.MaxKColorGenerator.generate(seed=42, number_of_nodes=PROBLEM_LENGTH, max_colors=2),
# 'mod': mlrose.CustomFitness(cf2, problem_type='discrete')
}
RANDOM_STATE = 42
DEFAULTS = {'random_state': RANDOM_STATE, 'curve': True, 'max_attempts': 10}
ALGORITHMS = {
'rhc': lambda p: mlrose.random_hill_climb(p, **DEFAULTS),
'sa': lambda p: mlrose.simulated_annealing(p, **DEFAULTS),
'ga': lambda p: mlrose.genetic_alg(p, **DEFAULTS),
'mimic': lambda p: mlrose.mimic(p, **DEFAULTS)
}
results = []
PART_1 = True
PART_2 = True
if PART_1:
for f_name, fitness in FITNESS_FUNCS.items():
evaluate_fitness(f_name, fitness, f_name == 'max2color')
alg2curve = {}
overall_best_fitness = -1
for alg_name, alg in ALGORITHMS.items():
if f_name == 'max2color':
def method_compare(opt, train_features_spam_norm, train_labels_spam,
test_features_spam_norm, test_labels_spam):
#best_state_spam,best_fitness_spam,fitness_curve=mlrose.simulated_annealing(opt,schedule=mlrose.ExpDecay(),curve=True)
#best_state_spam,best_fitness_spam,fitness_curve=mlrose.genetic_alg(opt,pop_size=2000,curve=True)
global count
count = 0
loss_list_rhc = []
loss_list_ann = []
loss_list_ga = []
train_acc_list_rhc = []
train_acc_list_ann = []
train_acc_list_ga = []
test_acc_list_rhc = []
test_acc_list_ann = []
test_acc_list_ga = []
fitness_call_list_rhc = []
fitness_call_list_ann = []
fitness_call_list_ga = []
# ten rounds of rhc
for i in range(10):
count = 0
best_state_spam, best_fitness_spam, fitness_curve = mlrose.random_hill_climb(
opt, restarts=70, curve=True)
loss_list_rhc.append(best_fitness_spam)
train_predict_rhc = predict(best_state_spam, train_features_spam_norm)
test_predict_rhc = predict(best_state_spam, test_features_spam_norm)
train_acc_list_rhc.append(
accuracy_score(train_labels_spam, train_predict_rhc))
test_acc_list_rhc.append(
accuracy_score(test_labels_spam, test_predict_rhc))
fitness_call_list_rhc.append(count)
#ten rounds of simulated annealing
for i in range(10):
count = 0
best_state_spam, best_fitness_spam, _ = mlrose.simulated_annealing(
opt, schedule=mlrose.ExpDecay(exp_const=0.003), curve=True)
loss_list_ann.append(best_fitness_spam)
train_predict_ann = predict(best_state_spam, train_features_spam_norm)
test_predict_ann = predict(best_state_spam, test_features_spam_norm)
train_acc_list_ann.append(
accuracy_score(train_labels_spam, train_predict_ann))
test_acc_list_ann.append(
accuracy_score(test_labels_spam, test_predict_ann))
fitness_call_list_ann.append(count)
#ten rounds of genetic algorithm
for i in range(10):
count = 0
best_state_spam, best_fitness_spam, _ = mlrose.genetic_alg(
opt, pop_size=1000, curve=True)
loss_list_ga.append(best_fitness_spam)
train_predict_ga = predict(best_state_spam, train_features_spam_norm)
test_predict_ga = predict(best_state_spam, test_features_spam_norm)
train_acc_list_ga.append(
accuracy_score(train_labels_spam, train_predict_ga))
test_acc_list_ga.append(
accuracy_score(test_labels_spam, test_predict_ga))
fitness_call_list_ga.append(count)
#plot loss curve
plt.figure(figsize=(6, 6))
plt.plot(np.arange(1, 11), loss_list_rhc, label='rhc')
plt.plot(np.arange(1, 11), loss_list_ann, label='s_ann')
plt.plot(np.arange(1, 11), loss_list_ga, label='ga')
plt.xlabel('rounds')
plt.ylabel('-1*losss')
plt.title('loss versus different algorithm')
plt.legend()
plt.show()
#plot acc curve
plt.figure(figsize=(15, 6))
plt.subplot(131)
plt.plot(np.arange(1, 11), train_acc_list_rhc, label='train')
plt.plot(np.arange(1, 11), test_acc_list_rhc, label='test')
plt.xlabel('rounds')
plt.ylabel('accuracy')
plt.title('rhc')
plt.legend()
plt.subplot(132)
plt.plot(np.arange(1, 11), train_acc_list_ann, label='train')
plt.plot(np.arange(1, 11), test_acc_list_ann, label='test')
plt.xlabel('rounds')
plt.ylabel('accuracy')
plt.title('simulated annealing')
plt.legend()
plt.subplot(133)
plt.plot(np.arange(1, 11), train_acc_list_ga, label='train')
plt.plot(np.arange(1, 11), test_acc_list_ga, label='test')
plt.xlabel('rounds')
plt.ylabel('accuracy')
plt.title('genetic algorithm')
plt.legend()
#plot fitness call
plt.figure(figsize=(6, 6))
plt.plot(np.arange(1, 11), fitness_call_list_rhc, label='rhc')
plt.plot(np.arange(1, 11), fitness_call_list_ann, label='s_ann')
plt.plot(np.arange(1, 11), fitness_call_list_ga, label='ga')
plt.xlabel('rounds')
plt.ylabel('fitness call number')
plt.title('fitness call num versus different algorithm')
plt.legend()
plt.show()
def n_queens_ga(nq_problem, max_iters=np.inf, num_runs=20, verbose=False):
# HP to vary
hp_name = 'pop_mate_pct'
hp_values = [0.25, 0.50, 0.75]
# other hyperparameters for genetic algorithm
population_size = 200
elite_dreg_ratio = 0.95
mutation_prob = 0.1
# run for each hp value and append results to list
fitness_dfs = []
runs = np.arange(num_runs)
for hp_value in hp_values:
pop_mate_pct = hp_value # set varied HP at beginning of loop
run_times = np.zeros(num_runs)
fitness_data = pd.DataFrame()
for run in runs:
run_t0 = time()
best_state, best_fitness, fitness_curve = mlrose.genetic_alg(
problem=nq_problem,
pop_size=population_size,
pop_breed_percent=pop_mate_pct,
elite_dreg_ratio=elite_dreg_ratio,
mutation_prob=mutation_prob,
max_attempts=10,
max_iters=max_iters,
curve=True,
)
run_time = time() - run_t0
run_times[run] = run_time
fitness_data = pd.concat(
[fitness_data, pd.DataFrame(fitness_curve)],
axis=1,
sort=False)
fitness_data.columns = runs
fitness_data = fitness_data.fillna(method='ffill')
fitness_dfs.append(fitness_data)
# calculate and print avg time per run
avg_run_time = np.average(run_times)
print("N-Queens - GA avg run time,", hp_value, hp_name, ":",
avg_run_time)
# generate plots
plot_title = "N-Queens GA - " \
+ str(population_size) + " pop, " \
+ str(mutation_prob) + " mut prob, " \
+ ": fit vs iter"
plotting.plot_fitness_curves(
fitness_dfs=fitness_dfs,
hp_values=hp_values,
hp_name=hp_name,
title=plot_title,
)
plt.savefig('graphs/n_queens_ga_fitness.png')
plt.clf()
return fitness_dfs
def ga_optimization(size):
algo = 'ga'
problem = get_problem(size)
# Gridsearch params
max_iters = 500
max_attempts_values = [10, 50, 100, 200]
pop_size_values = [50, 100, 150, 200]
pop_breed_percent_values = [0.5, 0.75]
mutation_prob_values = [0.1, 0.3]
n_runs = len(max_attempts_values) * len(pop_size_values) * len(pop_breed_percent_values) * len(mutation_prob_values)
# Best vals
pop_size, pop_breed_percent, mutation_prob, max_attempts = None, None, None, None
fitness, curves, n_invocations, time = float('-inf'), [], 0, 0
# Gridsearch
global eval_count
run_counter = 0
for run_pop_size in pop_size_values:
for run_pop_breed_percent in pop_breed_percent_values:
for run_mutation_prob in mutation_prob_values:
for run_max_attempts in max_attempts_values:
# Print status
run_counter += 1
print(f'RUN {run_counter} of {n_runs} [pop_size: {run_pop_size}] [pop_breed_percent: {run_pop_breed_percent}] [mutation_prob: {run_mutation_prob}] [max_attempts: {run_max_attempts}]')
# Run problem
eval_count = 0
start = timer()
run_state, run_fitness, run_curves = mlrose_hiive.genetic_alg(problem,
pop_size=run_pop_size,
pop_breed_percent=run_pop_breed_percent,
mutation_prob=run_mutation_prob,
max_attempts=run_max_attempts,
max_iters=max_iters,
random_state=42,
curve=True)
end = timer()
# Save curves and params
if run_fitness > fitness:
pop_size = run_pop_size
pop_breed_percent = run_pop_breed_percent
mutation_prob = run_mutation_prob
max_attempts = run_max_attempts
fitness = run_fitness
curves = run_curves
n_invocations = eval_count
time = end - start
df = pandas.DataFrame(curves, columns=['fitness'])
df['pop_size'] = pop_size
df['pop_breed_percent'] = pop_breed_percent
df['mutation_prob'] = mutation_prob
df['max_attempts'] = max_attempts
df['max_iters'] = max_iters
df['n_invocations'] = n_invocations
df['time'] = time
df.to_csv(f'{STATS_FOLDER}/{algo}_{size}_stats.csv', index=False)
print(f'{algo}_{size} run.')
