flag_unexpected = True
incomplete_processing[base_feature][weight_method][
ds_name].append(sample)
else:
flag_incomplete = True
incomplete_processing[base_feature][weight_method][
ds_name].append(sample)
# print('processing incomplete for {} {} {}'.format(ds_name, weight_method, sample))
if flag_nan_exists or flag_incomplete or flag_unexpected:
pass
# print('{:20} {:25} - processing unusable; totally skipping it.'.format(base_feature, weight_method))
else:
print('{:20} {:5} {:25} - fully usable.'.format(
base_feature, ds_name, weight_method))
dataset.description = '{}_{}'.format(base_feature, weight_method)
out_path = pjoin(
out_dir, '{}_{}.MLDataset.pkl'.format(base_feature,
weight_method))
dataset.save(out_path)
# saving
with open(pjoin(out_dir, 'incomplete_unusable_processing.pkl'),
'wb') as ipf:
pickle.dump([incomplete_processing, comb_nan_values], ipf)
# reading
with open(pjoin(out_dir, 'incomplete_unusable_processing.pkl'), 'rb') as ipf:
incomplete_processing, comb_nan_values = pickle.load(ipf)
# results
incomplete_processing[multi_feature][weight_method][
ds_name].append(sample)
else:
flag_incomplete = True
sys.stdout.write('-')
incomplete_processing[multi_feature][weight_method][
ds_name].append(sample)
# print('processing incomplete for {} {} {}'.format(ds_name, weight_method, sample))
if flag_nan_exists or flag_incomplete or flag_unexpected:
pass
# print('{:20} {:25} - processing unusable; totally skipping it.'.format(base_feature, weight_method))
else:
print('{:20} {:5} {:25} : fully usable.'.format(
multi_feature, ds_name, weight_method))
dataset.description = '{}_{}'.format(summary_stat, weight_method)
out_path = pjoin(
out_dir, '{}_{}.MLDataset.pkl'.format(summary_stat,
weight_method))
dataset.save(out_path)
# saving
with open(pjoin(out_dir, 'incomplete_unusable_processing.pkl'),
'wb') as ipf:
pickle.dump([incomplete_processing, comb_nan_values], ipf)
# reading
with open(pjoin(out_dir, 'incomplete_unusable_processing.pkl'), 'rb') as ipf:
incomplete_processing, comb_nan_values = pickle.load(ipf)
# results
flag_unexpected = True
incomplete_processing[base_feature][stat_method][
ds_name].append(sample)
else:
flag_incomplete = True
incomplete_processing[base_feature][stat_method][
ds_name].append(sample)
# print('processing incomplete for {} {} {}'.format(ds_name, stat_method, sample))
if flag_nan_exists or flag_incomplete or flag_unexpected:
pass
# print('{:20} {:25} - processing unusable; totally skipping it.'.format(base_feature, stat_method))
else:
print('{:20} {} \t- fully usable.'.format(base_feature,
stat_method))
dataset.description = '{}'.format(stat_method)
out_path = pjoin(
out_dir,
'{}_roi_stats_{}.MLDataset.pkl'.format(base_feature,
stat_method))
dataset.save(out_path)
# saving
with open(pjoin(out_dir, 'incomplete_unusable_processing.pkl'),
'wb') as ipf:
pickle.dump([incomplete_processing, comb_nan_values], ipf)
# reading
with open(pjoin(out_dir, 'incomplete_unusable_processing.pkl'), 'rb') as ipf:
incomplete_processing, comb_nan_values = pickle.load(ipf)
class_set = np.array(['C{:05d}'.format(x) for x in range(num_classes)])
feat_names = np.array([str(x) for x in range(num_features)])
test_dataset = MLDataset()
for class_index, class_id in enumerate(class_set):
for sub_ix in range(class_sizes[class_index]):
subj_id = '{}_S{:05d}'.format(class_set[class_index], sub_ix)
feat = np.random.random(num_features)
test_dataset.add_sample(subj_id, feat, class_index, class_id,
feat_names)
out_file = os.path.join(out_dir, 'random_example_dataset.pkl')
test_dataset.save(out_file)
test_dataset.description = 'test dataset'
print(test_dataset)
print('default format:\n {}'.format(test_dataset))
print('full repr :\n {:full}'.format(test_dataset))
print('string/short :\n {:s}'.format(test_dataset))
class_set, label_set, class_sizes = test_dataset.summarize_classes()
reloaded_dataset = MLDataset(filepath=out_file,
description='reloaded test_dataset')
copy_dataset = MLDataset(in_dataset=test_dataset)
rand_index = np.random.randint(0, len(class_set), 1)[0]
random_class_name = class_set[rand_index]
random_class_ds = test_dataset.get_class(random_class_name)
out_file = os.path.join(out_dir,'random_example_dataset.pkl')
test_dataset.save(out_file)
# same IDs, new features
same_ids_new_feat = MLDataset()
for sub_id in test_dataset.keys:
feat = np.random.random(num_features)
same_ids_new_feat.add_sample(sub_id, feat,
test_dataset.labels[sub_id],
test_dataset.classes[sub_id])
same_ids_new_feat.feature_names = np.array([ 'new_f{}'.format(x) for x in range(
num_features) ])
test_dataset.description = 'test dataset'
print(test_dataset)
print('default format:\n {}'.format(test_dataset))
print('full repr :\n {:full}'.format(test_dataset))
print('string/short :\n {:s}'.format(test_dataset))
class_set, label_set, class_sizes = test_dataset.summarize_classes()
reloaded_dataset = MLDataset(filepath=out_file, description='reloaded test_dataset')
copy_dataset = MLDataset(in_dataset=test_dataset)
rand_index = np.random.randint(0,len(class_set),1)[0]
random_class_name = class_set[rand_index]
random_class_ds = test_dataset.get_class(random_class_name)