def generate_param_list(Job_Params, params, config, subject):
sp = spearmint_lite.spearmint_lite(Job_Params, [], config, Job_Params.type)
params_dict = sp.generate_params_dict(params, subject)
params_list = []
if "cutoff_frequencies_low_list" in params_dict:
# cutoff_frequencies_low_list = params_dict.pop('cutoff_frequencies_low_list')
# cutoff_frequencies_high_list = params_dict.pop('cutoff_frequencies_high_list')
params_list = [
float(params_dict['discard_mv_begin']),
float(params_dict['discard_mv_end']),
float(params_dict['discard_nc_begin']),
float(params_dict['discard_nc_end']),
float(params_dict['window_size']),
float(params_dict['window_overlap_size']),
params_dict['cutoff_frequencies_low_list'],
params_dict['cutoff_frequencies_high_list'],
params_dict['channel_type']
]
else:
params_list = [
float(params_dict['discard_mv_begin']),
float(params_dict['discard_mv_end']),
float(params_dict['discard_nc_begin']),
float(params_dict['discard_nc_end']),
float(params_dict['window_size']),
float(params_dict['window_overlap_size']),
params_dict['channel_type']
]
return params_list
def generate_param_list(Job_Params, params, config, subject):
sp = spearmint_lite.spearmint_lite(Job_Params, [], config, Job_Params.type)
params_dict = sp.generate_params_dict(params, subject)
params_list = []
if "cutoff_frequencies_low_list" in params_dict:
# cutoff_frequencies_low_list = params_dict.pop('cutoff_frequencies_low_list')
# cutoff_frequencies_high_list = params_dict.pop('cutoff_frequencies_high_list')
params_list = [float(params_dict['discard_mv_begin']), float(params_dict['discard_mv_end']), float(params_dict['discard_nc_begin']),
float(params_dict['discard_nc_end']), float(params_dict['window_size']), float(params_dict['window_overlap_size']),
params_dict['cutoff_frequencies_low_list'], params_dict['cutoff_frequencies_high_list'], params_dict['channel_type']]
else:
params_list = [float(params_dict['discard_mv_begin']), float(params_dict['discard_mv_end']), float(params_dict['discard_nc_begin']),
float(params_dict['discard_nc_end']), float(params_dict['window_size']), float(params_dict['window_overlap_size']), params_dict['channel_type']]
return params_list
def generate_params_dict(self, params):
sp = spearmint_lite.spearmint_lite(None, None, self.config, self.optimization_type)
params_dict = sp.generate_params_dict(map(float, params.split(' ')[2:]), self.subject)
params_list = SJR.Simple_Job_Runner.create_params_list(params_dict)
out_file_name = SJR.Simple_Job_Runner.generate_learner_output_file_name( params_list, self.subject)
results_path = self.config.configuration['results_path_str']
results_opt_path = self.config.configuration['results_opt_path_str']
results_path, results_opt_path = SJR.Simple_Job_Runner.set_results_path( results_path, results_opt_path, self.classifier, self.feature,
optimization_type = self.optimization_type, BO_selection_type = '')
res_file_name = os.path.join(results_path, out_file_name)
my_Learner_Manager = Learner_Manager.Learner_Manager(self.config, self.classifier, self.feature)
current_error, learner_params = my_Learner_Manager.find_cv_error(res_file_name)
# params_dict = sp.generate_params_dict(map(float, params), self.subject)
params_dict = dict(params_dict.items() + learner_params.items())
return float(params.split(' ')[0]), params_dict, params_list, learner_params
'BCI_Framework', dataset)
complete_jobs = np.zeros(
config.configuration['number_of_subjects'])
all_mvs_have_same_lebngth = all(
map(
lambda x: x == config.configuration[
'movement_trial_size_list'][0],
config.configuration['movement_trial_size_list']))
for subj_ind, subj in enumerate(
config.configuration['subject_names_str']):
if all_mvs_have_same_lebngth:
all_subjects_candidates_list = all_subjects_candidates_dict[
(dataset_ind, optimization_type)][0]
else:
all_subjects_candidates_list = all_subjects_candidates_dict[
(dataset_ind, optimization_type)][subj_ind]
sp = spearmint_lite.spearmint_lite(
Job_Params, all_subjects_candidates_list, config,
optimization_type)
finished[(subj + str(dataset_ind),
optimization_type)] = sp.main(
Job_Params, complete_jobs, subj)
sleep(30)
first_iteration = False
os.chdir('../bci_framework')
sys.path.append('./BCI_Framework')
import Main
import Configuration_BCI
import numpy as np
import spearmint_lite
class Job_Params:
job_dir = 'BCI_Framework'
num_all_jobs = 100
dataset = 'BCICIV2b'
seed = 1
classifier_name = 'LogisticRegression'
feature_extraction = 'BP'
n_concurrent_jobs = 3
chooser_module = "GPEIOptChooser"
n_initial_candidates = 12
if __name__ == '__main__':
BO_type = 2
config = Configuration_BCI.Configuration_BCI('BCI_Framework', 'BCICIV2b')
sp = spearmint_lite.spearmint_lite(Job_Params, [], config, BO_type)
params = [687.0, 1.0, 1.5, 3.5]
subj = '100'
sp.run_job(params, subj)
from random import randrange
seed = randrange(50)
classifier_name = classifier
feature_extraction = feature
n_concurrent_jobs = 1
chooser_module = bo_type
Job_Params.n_initial_candidates = 0
config = Configuration_BCI.Configuration_BCI('BCI_Framework', dataset)
complete_jobs = np.zeros(config.configuration['number_of_subjects'])
all_mvs_have_same_lebngth = all(map(lambda x: x == config.configuration['movement_trial_size_list'][0], config.configuration['movement_trial_size_list']))
for subj_ind, subj in enumerate(config.configuration['subject_names_str']):
if all_mvs_have_same_lebngth:
all_subjects_candidates_list = all_subjects_candidates_dict[(dataset_ind, optimization_type)][0]
else:
all_subjects_candidates_list = all_subjects_candidates_dict[(dataset_ind, optimization_type)][subj_ind]
sp = spearmint_lite.spearmint_lite(Job_Params, all_subjects_candidates_list, config, optimization_type)
finished[(subj+str(dataset_ind), optimization_type)] = sp.main(Job_Params, complete_jobs, subj)
# sleep(1)
first_iteration = False
# execution_time = time.time() - start_time
# print execution_time
import sys
os.chdir('../bci_framework')
sys.path.append('./BCI_Framework')
import Main
import Configuration_BCI
import numpy as np
import spearmint_lite
class Job_Params:
job_dir = 'BCI_Framework'
num_all_jobs = 100
dataset = 'BCICIV2b'
seed = 1
classifier_name = 'LogisticRegression'
feature_extraction = 'BP'
n_concurrent_jobs = 3
chooser_module = "GPEIOptChooser"
n_initial_candidates = 12
if __name__ == '__main__':
BO_type = 2
config = Configuration_BCI.Configuration_BCI('BCI_Framework', 'BCICIV2b')
sp = spearmint_lite.spearmint_lite(Job_Params, [], config, BO_type)
params = [687.0, 1.0, 1.5, 3.5]
subj = '100'
sp.run_job(params, subj)
