def create_dataset(template_specifications, visit_ages=None, dataset_filenames=None, subject_ids=None, dimension=None):
"""
Creates a longitudinal dataset object from xml parameters.
"""
deformable_objects_dataset = []
if dataset_filenames is not None:
for i in range(len(dataset_filenames)):
deformable_objects_subject = []
for j in range(len(dataset_filenames[i])):
object_list = []
reader = DeformableObjectReader()
for object_id in template_specifications.keys():
if object_id not in dataset_filenames[i][j]:
raise RuntimeError('The template object with id ' + object_id + ' is not found for the visit '
+ str(j) + ' of subject ' + str(i) + '. Check the dataset xml.')
else:
object_type = template_specifications[object_id]['deformable_object_type']
object_list.append(reader.create_object(dataset_filenames[i][j][object_id], object_type,
dimension))
deformable_objects_subject.append(DeformableMultiObject(object_list))
deformable_objects_dataset.append(deformable_objects_subject)
longitudinal_dataset = LongitudinalDataset(
subject_ids, times=visit_ages, deformable_objects=deformable_objects_dataset)
return longitudinal_dataset
def create_scalar_dataset(group, observations, timepoints):
"""
Builds a dataset from the given data.
"""
times = []
subject_ids = []
scalars = []
for subject_id in group:
if subject_id not in subject_ids:
subject_ids.append(subject_id)
times_subject = []
scalars_subject = []
for i in range(len(observations)):
if group[i] == subject_id:
times_subject.append(timepoints[i])
scalars_subject.append(observations[i])
assert len(times_subject) > 0, subject_id
assert len(times_subject) == len(scalars_subject)
times.append(np.array(times_subject))
scalars.append(Variable(torch.from_numpy(np.array(scalars_subject)).type(Settings().tensor_scalar_type)))
longitudinal_dataset = LongitudinalDataset()
longitudinal_dataset.times = times
longitudinal_dataset.subject_ids = subject_ids
longitudinal_dataset.deformable_objects = scalars
longitudinal_dataset.number_of_subjects = len(subject_ids)
longitudinal_dataset.total_number_of_observations = len(timepoints)
return longitudinal_dataset
def create_image_dataset(group, observations, timepoints):
times = []
subject_ids = []
images = []
for subject_id in group:
if subject_id not in subject_ids:
subject_ids.append(subject_id)
times_subject = []
images_subject = []
for i in range(len(observations)):
if group[i] == subject_id:
times_subject.append(timepoints[i])
images_subject.append(observations[i])
assert len(times_subject) > 0, subject_id
assert len(times_subject) == len(images_subject)
times.append(np.array(times_subject))
images.append(images_subject)
longitudinal_dataset = LongitudinalDataset()
longitudinal_dataset.times = times
longitudinal_dataset.subject_ids = subject_ids
longitudinal_dataset.deformable_objects = images
longitudinal_dataset.number_of_subjects = len(subject_ids)
longitudinal_dataset.total_number_of_observations = len(timepoints)
longitudinal_dataset.check_image_shapes()
longitudinal_dataset.order_observations()
return longitudinal_dataset
def read_and_create_image_dataset(dataset_filenames, visit_ages, subject_ids, template_specifications):
"""
Builds a longitudinal dataset of images (non deformable images). Loads everything into memory. #TODO assert on the format of the images !
"""
deformable_objects_dataset = []
for i in range(len(dataset_filenames)):
deformable_objects_subject = []
for j in range(len(dataset_filenames[i])):
for object_id in template_specifications.keys():
if object_id not in dataset_filenames[i][j]:
raise RuntimeError('The template object with id ' + object_id + ' is not found for the visit '
+ str(j) + ' of subject ' + str(i) + '. Check the dataset xml.')
else:
objectType = template_specifications[object_id]['deformable_object_type']
reader = DeformableObjectReader()
deformable_object_visit = reader.create_object(dataset_filenames[i][j][object_id], objectType)
deformable_object_visit.update()
deformable_objects_subject.append(deformable_object_visit)
if len(deformable_objects_subject) <= 1:
msg = "I have only one observation for subject {}".format(str(i))
warnings.warn(msg)
deformable_objects_dataset.append(deformable_objects_subject)
longitudinal_dataset = LongitudinalDataset()
longitudinal_dataset.times = [np.array(elt) for elt in visit_ages]
longitudinal_dataset.subject_ids = subject_ids
longitudinal_dataset.deformable_objects = deformable_objects_dataset
longitudinal_dataset.update()
longitudinal_dataset.check_image_shapes()
longitudinal_dataset.order_observations()
return longitudinal_dataset
mean_observation_time_window,
math.sqrt(model.get_time_shift_variance()))
time_between_two_consecutive_visits = observation_time_window / float(
number_of_visits - 1)
age_at_baseline = normal(model.get_reference_time(), math.sqrt(model.get_time_shift_variance())) \
- 0.5 * observation_time_window
ages = [
age_at_baseline + j * time_between_two_consecutive_visits
for j in range(number_of_visits)
]
visit_ages.append(ages)
subject_ids = ['s' + str(i) for i in range(number_of_subjects)]
dataset = LongitudinalDataset(subject_ids, times=visit_ages)
logger.info(
'>> %d subjects will be generated, with %.2f visits on average, covering an average period of %.2f years.'
%
(number_of_subjects, float(dataset.total_number_of_observations) /
float(number_of_subjects),
np.mean(np.array([ages[-1] - ages[0]
for ages in dataset.times]))))
"""
Generate individual RER.
"""
# Complementary xml parameters.
t0 = xml_parameters.t0
tmin = xml_parameters.tmin