def run_exp_racos_for_synthetic_problem_analysis():
# parameters
sample_size = 10 # the instance number of sampling in an iteration
budget = 500 # budget in online style
positive_num = 2 # the set size of PosPop
rand_probability = 0.99 # the probability of sample in model
uncertain_bit = 1 # the dimension size that is sampled randomly
adv_threshold = 10 # advance sample size
opt_repeat = 10
dimension_size = 10
problem_name = 'sphere'
problem_num = 200
start_index = 0
bias_region = 0.2
dimension = Dimension()
dimension.set_dimension_size(dimension_size)
dimension.set_regions([[-1.0, 1.0] for _ in range(dimension_size)],
[0 for _ in range(dimension_size)])
log_buffer = []
# logging
learner_path = './ExpLearner/SyntheticProbsLearner/' + problem_name + '/dimension' + str(dimension_size)\
+ '/DirectionalModel/' + 'learner-' + problem_name + '-' + 'dim' + str(dimension_size) + '-'\
+ 'bias' + str(bias_region) + '-'
problem_path = './ExpLog/SyntheticProbsLog/' + problem_name + '/dimension' + str(dimension_size)\
+ '/DirectionalModel/' + 'bias-' + problem_name + '-' + 'dim' + str(dimension_size) + '-'\
+ 'bias' + str(bias_region) + '-'
func = DistributedFunction(dimension, bias_region=[-0.5, 0.5])
target_bias = [0.1 for _ in range(dimension_size)]
func.setBias(target_bias)
if problem_name == 'ackley':
prob_fct = func.DisAckley
else:
prob_fct = func.DisSphere
relate_error_list = []
for prob_i in range(problem_num):
print(
start_index + prob_i,
'++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++')
log_buffer.append(
str(start_index + prob_i) +
'++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++')
log_buffer.append('+++++++++++++++++++++++++++++++')
log_buffer.append('optimization parameters')
log_buffer.append('sample size: ' + str(sample_size))
log_buffer.append('budget: ' + str(budget))
log_buffer.append('positive num: ' + str(positive_num))
log_buffer.append('random probability: ' + str(rand_probability))
log_buffer.append('uncertain bits: ' + str(uncertain_bit))
log_buffer.append('advance num: ' + str(adv_threshold))
log_buffer.append('+++++++++++++++++++++++++++++++')
log_buffer.append('problem parameters')
log_buffer.append('dimension size: ' + str(dimension_size))
log_buffer.append('problem name: ' + problem_name)
log_buffer.append('bias_region: ' + str(bias_region))
log_buffer.append('+++++++++++++++++++++++++++++++')
problem_file = problem_path + str(start_index + prob_i) + '.txt'
problem_str = fo.FileReader(problem_file)[0].split(',')
problem_index = int(problem_str[0])
problem_bias = string2list(problem_str[1])
if problem_index != (start_index + prob_i):
print('problem error!')
exit(0)
print('source bias: ', problem_bias)
log_buffer.append('source bias: ' + list2string(problem_bias))
reduisal = np.array(target_bias) - np.array(problem_bias)
this_distance = reduisal * reduisal.T
learner_file = learner_path + str(start_index + prob_i) + '.pkl'
log_buffer.append('learner file: ' + learner_file)
print('learner file: ', learner_file)
net = torch.load(learner_file)
net_list = [net]
opt_error_list = []
for i in range(opt_repeat):
print('optimize ', i,
'===================================================')
log_buffer.append(
'optimize ' + str(i) +
'===================================================')
exp_racos = ExpRacosOptimization(dimension, net_list)
start_t = time.time()
exp_racos.exp_mix_opt(obj_fct=prob_fct,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold)
end_t = time.time()
print('total budget is ', budget)
log_buffer.append('total budget is ' + str(budget))
hour, minute, second = time_formulate(start_t, end_t)
print('spending time: ', hour, ':', minute, ':', second)
log_buffer.append('spending time: ' + str(hour) + '+' +
str(minute) + '+' + str(second))
optimal = exp_racos.get_optimal()
opt_error = optimal.get_fitness()
optimal_x = optimal.get_features()
opt_error_list.append(opt_error)
print('validation optimal value: ', opt_error)
log_buffer.append('validation optimal value: ' + str(opt_error))
print('optimal x: ', optimal_x)
log_buffer.append('optimal nn structure: ' +
list2string(optimal_x))
opt_mean = np.mean(np.array(opt_error_list))
relate_error_list.append([this_distance, opt_mean])
opt_std = np.std(np.array(opt_error_list))
print('--------------------------------------------------')
print('optimization result: ', opt_mean, '#', opt_std)
log_buffer.append('--------------------------------------------------')
log_buffer.append('optimization result: ' + str(opt_mean) + '#' +
str(opt_std))
result_path = './Results/SyntheticProbs/' + problem_name + '/dimension' + str(
dimension_size) + '/'
relate_error_file = result_path + 'relate-error-' + problem_name + '-dim' + str(dimension_size) + '-bias'\
+ str(bias_region) + '.txt'
temp_buffer = []
for i in range(len(relate_error_list)):
relate, error = relate_error_list[i]
temp_buffer.append(str(relate) + ',' + str(error))
print('relate error logging: ', relate_error_file)
log_buffer.append('relate error logging: ' + relate_error_file)
fo.FileWriter(relate_error_file, temp_buffer, style='w')
optimization_log_file = result_path + 'opt-log-' + problem_name + '-dim' + str(dimension_size) + '-bias'\
+ str(bias_region) + '.txt'
print('optimization logging: ', optimization_log_file)
fo.FileWriter(optimization_log_file, log_buffer, style='w')
def run(type):
dimension = Dimension()
dimension.set_dimension_size(dimension_size)
dimension.set_regions([[-1.0, 1.0] for _ in range(dimension_size)],
[0 for _ in range(dimension_size)])
# problem define
func = DistributedFunction(dimension,
bias_region=[-bias_region, bias_region])
target_bias = [0.1 for _ in range(dimension_size)]
func.setBias(target_bias)
if problem_name == 'ackley':
prob_fct = func.DisAckley
elif problem_name == 'sphere':
prob_fct = func.DisSphere
elif problem_name == 'rosenbrock':
prob_fct = func.DisRosenbrock
else:
print('Wrong function!')
exit()
opt_error_list = []
log_buffer.append('+++++++++++++++++++++++++++++++')
log_buffer.append('Running: ' + type)
log_buffer.append('+++++++++++++++++++++++++++++++')
print('+++++++++++++++++++++++++++++++')
print('Running: ' + type)
print('+++++++++++++++++++++++++++++++')
if type == 'ada':
# pre=sorted(predictors,key=lambda a:a.dist)
expert = Experts(predictors=predictors, eta=eta, bg=budget)
for i in range(opt_repeat):
print('optimize ', i,
'===================================================')
log_buffer.append(
'optimize ' + str(i) +
'===================================================')
start_t = time.time()
if type == 'exp':
exp_racos = ExpRacosOptimization(dimension, nets)
opt_error = exp_racos.exp_mix_opt(obj_fct=prob_fct,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold)
elif type == 'ada':
exp_racos = ExpAdaRacosOptimization(dimension, expert)
opt_error = exp_racos.exp_ada_mix_opt(obj_fct=prob_fct,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold)
else:
print('Wrong type!')
return
end_t = time.time()
hour, minute, second = time_formulate(start_t, end_t)
print('spending time: ', hour, ':', minute, ':', second)
log_buffer.append('spending time: ' + str(hour) + '+' + str(minute) +
'+' + str(second))
opt_error_list.append(opt_error)
print('validation optimal value: ', opt_error)
log_buffer.append('validation optimal value: ' + str(opt_error))
opt_mean = np.mean(np.array(opt_error_list), axis=0)
opt_std = np.std(np.array(opt_error_list), axis=0)
print('--------------------------------------------------')
print('optimization result for ' + str(opt_repeat) + ' times average: ',
opt_mean, ', standard variance is: ', opt_std)
log_buffer.append('--------------------------------------------------')
log_buffer.append('optimization result for ' + str(opt_repeat) +
' times average: ' + str(opt_mean) +
', standard variance is: ' + str(opt_std))
return opt_mean
def run_for_real_problem(problem_name, type):
dtrain, dtest, dvalid = mlbp.get_train_test_data(problem_name)
opt_error_list = []
gen_error_list = []
print(type, ' optimize ', problem_name,
'===================================================')
log_buffer.append(type + ' optimize ' + problem_name +
'===================================================')
for j in range(opt_repeat):
print(j)
log_buffer.append(str(j))
model = lgb.LGBMClassifier()
start_t = time.time()
def score_fun(x):
## here is the score function
hyper_param = (sample_codec.sample_decode(x))
model.set_params(**hyper_param)
bst = model.fit(dtrain[:, :-1], dtrain[:, -1])
pred = bst.predict(dvalid[:, :-1])
fitness = -f1_score(dvalid[:, -1], pred, average='macro')
return fitness
if type == 'racos':
optimizer = RacosOptimization(dimension)
optimizer.clear()
optimizer.mix_opt(obj_fct=score_fun,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit)
elif type == 'ave':
optimizer = ExpRacosOptimization(dimension, nets)
log = optimizer.exp_mix_opt(obj_fct=score_fun,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold)
for line in log:
log_buffer.append(line)
elif type == 'ada':
optimizer = ExpAdaRacosOptimization(dimension, expert)
optimizer.clear()
log = optimizer.exp_ada_mix_opt(obj_fct=score_fun,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold,
step=step)
for line in log:
log_buffer.append(line)
else:
print('Wrong type!')
return
end_t = time.time()
print('total budget is ', budget)
log_buffer.append('total budget is ' + str(budget))
hour, minute, second = time_formulate(start_t, end_t)
print('spending time: ', hour, ':', minute, ':', second)
log_buffer.append('spending time: ' + str(hour) + '+' + str(minute) +
'+' + str(second))
optimal = optimizer.get_optimal()
opt_error = optimal.get_fitness()
optimal_x = optimal.get_features()
hyper_param = (sample_codec.sample_decode(optimal_x))
model = lgb.LGBMClassifier()
model.set_params(**hyper_param)
train = np.concatenate((dtrain, dvalid), axis=0)
bst = model.fit(train[:, :-1], train[:, -1])
pred = bst.predict(dtest[:, :-1])
gen_error = -f1_score(dtest[:, -1], pred, average='macro')
gen_error_list.append(gen_error)
opt_error_list.append(opt_error)
print('***********validation optimal value: ', opt_error)
log_buffer.append('***********validation optimal value: ' +
str(opt_error))
print('***********generalize optimal value: ', gen_error)
log_buffer.append('***********generalize optimal value: ' +
str(gen_error))
print('optimal x: ', optimal_x)
# log_buffer.append('optimal nn structure: ' + list2string(optimal_x))
opt_mean = np.mean(np.array(opt_error_list))
opt_std = np.std(np.array(opt_error_list))
gen_mean = np.mean(np.array(gen_error_list))
gen_std = np.std(np.array(gen_error_list))
return -opt_mean, opt_std, -gen_mean, gen_std
def run(type):
opt_error_list = []
log_buffer.append('+++++++++++++++++++++++++++++++')
log_buffer.append('Running: ' + type)
log_buffer.append('+++++++++++++++++++++++++++++++')
print('+++++++++++++++++++++++++++++++')
print('Running: ' + type)
print('+++++++++++++++++++++++++++++++')
if type == 'ada':
# pre=sorted(predictors,key=lambda a:a.dist)
expert = Experts(predictors=predictors, eta=eta, bg=budget)
for i in range(opt_repeat):
print('optimize ', i,
'===================================================')
log_buffer.append(
'optimize ' + str(i) +
'===================================================')
start_t = time.time()
if type == 'ave':
exp_racos = ExpRacosOptimization(dimension, nets)
opt_error = exp_racos.exp_mix_opt(obj_fct=prob_fct,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold)
elif type == 'ada':
exp_racos = ExpAdaRacosOptimization(dimension, expert)
opt_error = exp_racos.exp_ada_mix_opt(obj_fct=prob_fct,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold,
step=step)
elif type == 'ground truth':
exp_racos = ExpRacosOptimization(dimension, nets[:step])
exp_racos.exp_mix_opt(obj_fct=prob_fct,
ss=sample_size,
bud=budget,
pn=positive_num,
rp=rand_probability,
ub=uncertain_bit,
at=adv_threshold)
else:
print('Wrong type!')
return
end_t = time.time()
hour, minute, second = time_formulate(start_t, end_t)
print('spending time: ', hour, ':', minute, ':', second)
log_buffer.append('spending time: ' + str(hour) + '+' + str(minute) +
'+' + str(second))
optimal = exp_racos.get_optimal()
opt_error = optimal.get_fitness()
optimal_x = optimal.get_features()
opt_error_list.append(opt_error)
print('validation optimal value: ', opt_error)
log_buffer.append('validation optimal value: ' + str(opt_error))
print('optimal x: ', optimal_x)
log_buffer.append('optimal nn structure: ' + list2string(optimal_x))
opt_mean = np.mean(np.array(opt_error_list), axis=0)
opt_std = np.std(np.array(opt_error_list), axis=0)
print('--------------------------------------------------')
print('optimization result for ' + str(opt_repeat) + ' times average: ',
opt_mean, ', standard variance is: ', opt_std)
log_buffer.append('--------------------------------------------------')
log_buffer.append('optimization result for ' + str(opt_repeat) +
' times average: ' + str(opt_mean) +
', standard variance is: ' + str(opt_std))
return opt_mean, opt_std