def get_subject_session_list(input_dir,
ss_file=None,
is_bids_dir=True,
use_session_tsv=False,
tsv_dir=None):
"""Parse a BIDS or CAPS directory to get the subjects and sessions.
This function lists all the subjects and sessions based on the content of
the BIDS or CAPS directory or (if specified) on the provided
subject-sessions TSV file.
Args:
input_dir: A BIDS or CAPS directory path.
ss_file: A subjects-sessions file (.tsv format).
is_bids_dir: Indicates if input_dir is a BIDS or CAPS directory
use_session_tsv (boolean): Specify if the list uses the sessions listed in the sessions.tsv files
tsv_dir (str): if TSV file does not exist, it will be created in output_dir. If
not specified, output_dir will be in <tmp> folder
Returns:
subjects: A subjects list.
sessions: A sessions list.
Notes:
This is a generic method based on folder names. If your <BIDS> dataset contains e.g.:
- sub-CLNC01/ses-M00/anat/sub-CLNC01_ses-M00_T1w.nii
- sub-CLNC02/ses-M00/dwi/sub-CLNC02_ses-M00_dwi.{bval|bvec|json|nii}
- sub-CLNC02/ses-M00/anat/sub-CLNC02_ses-M00_T1w.nii
get_subject_session_list(<BIDS>, None, True) will return
['ses-M00', 'ses-M00'], ['sub-CLNC01', 'sub-CLNC02'].
However, if your pipeline needs both T1w and DWI files, you will need to check
with e.g. clinica_file_reader_function.
"""
import os
import tempfile
from time import localtime, strftime, time
import clinica.iotools.utils.data_handling as cdh
if not ss_file:
if tsv_dir:
output_dir = tsv_dir
else:
output_dir = tempfile.mkdtemp()
timestamp = strftime("%Y%m%d_%H%M%S", localtime(time()))
tsv_file = f"subjects_sessions_list_{timestamp}.tsv"
ss_file = os.path.join(output_dir, tsv_file)
cdh.create_subs_sess_list(
input_dir=input_dir,
output_dir=output_dir,
file_name=tsv_file,
is_bids_dir=is_bids_dir,
use_session_tsv=use_session_tsv,
)
participant_ids, session_ids = read_participant_tsv(ss_file)
return session_ids, participant_ids
def run_command(self, args):
import os
import errno
from clinica.iotools.utils import data_handling as dt
output_directory = os.path.dirname(args.out_tsv)
if not os.path.exists(output_directory):
try:
os.makedirs(output_directory)
except OSError as exc: # Guard against race condition
if exc.errno != errno.EEXIST:
raise
dt.create_subs_sess_list(args.bids_directory, output_directory, os.path.basename(args.out_tsv))
def run_command(self, args):
"""
"""
from tempfile import mkdtemp
from clinica.pipelines.dwi_preprocessing_multi_shell.dwi_preprocessing_multi_shell_pipeline import DwiPreprocessingMultiShell
import os
import errno
from clinica.iotools.utils.data_handling import create_subs_sess_list
from nipype import config
cfg = dict(execution={'parameterize_dirs': False})
config.update_config(cfg)
if args.subjects_sessions_tsv is None:
try:
temp_dir = mkdtemp()
except OSError as exception:
if exception.errno != errno.EEXIST:
raise
create_subs_sess_list(args.bids_directory, temp_dir)
args.subjects_sessions_tsv = os.path.join(temp_dir, 'subjects_sessions_list.tsv')
pipeline = DwiPreprocessingNoddi(
bids_directory=self.absolute_path(args.bids_directory),
caps_directory=self.absolute_path(args.caps_directory),
tsv_file=self.absolute_path(args.subjects_sessions_tsv))
pipeline.parameters = {
'epi_param': dict(
[
('echospacing', args.echo_spacing),
('acc_factor', args.acceleration_factor),
('enc_dir', args.phase_encoding_direction),
('epi_factor', args.epi_factor)
]),
'alt_epi_params': dict(
[
('echospacing', args.echo_spacing),
('acc_factor', args.acceleration_factor),
('enc_dir_alt', args.phase_encoding_direction_alternative),
('epi_factor', args.epi_factor)
])
}
if args.working_directory is None:
args.working_directory = mkdtemp()
pipeline.base_dir = self.absolute_path(args.working_directory)
if args.n_procs:
pipeline.run(plugin='MultiProc',
plugin_args={'n_procs': args.n_procs})
else:
pipeline.run()
def run_command(self, args):
import os
from clinica.iotools.utils import data_handling as dt
from clinica.utils.inputs import check_bids_folder
from clinica.utils.stream import cprint
check_bids_folder(args.bids_directory)
output_directory = os.path.dirname(os.path.abspath(args.out_tsv))
os.makedirs(output_directory, exist_ok=True)
dt.create_subs_sess_list(args.bids_directory, output_directory,
os.path.basename(args.out_tsv))
cprint("The TSV file was saved to %s" % os.path.abspath(args.out_tsv))
def run_createsubjectsession(
input_dir: PathLike, output_dir: PathLike, ref_dir: PathLike
) -> None:
from clinica.iotools.utils import data_handling as dt
# Arrage
tsv_name = "subject_session_list.tsv"
# Act - Create subject_session file
dt.create_subs_sess_list(input_dir / "bids", output_dir, tsv_name)
# Assert
out_tsv = fspath(output_dir / tsv_name)
ref_tsv = fspath(ref_dir / tsv_name)
assert identical_subject_list(out_tsv, ref_tsv)
def get_subject_session_list(input_dir,
ss_file=None,
is_bids_dir=True,
use_session_tsv=False):
"""Parses a BIDS or CAPS directory to get the subjects and sessions.
This function lists all the subjects and sessions based on the content of
the BIDS or CAPS directory or (if specified) on the provided
subject-sessions TSV file.
Args:
input_dir: A BIDS or CAPS directory path.
ss_file: A subjects-sessions file (.tsv format).
is_bids_dir: Indicates if input_dir is a BIDS or CAPS directory
use_session_tsv (boolean): Specify if the list uses the sessions listed in the sessions.tsv files
Returns:
subjects: A subjects list.
sessions: A sessions list.
"""
import clinica.iotools.utils.data_handling as cdh
import pandas as pd
import tempfile
from time import time, strftime, localtime
import os
if not ss_file:
output_dir = tempfile.mkdtemp()
timestamp = strftime('%Y%m%d_%H%M%S', localtime(time()))
tsv_file = '%s_subjects_sessions_list.tsv' % timestamp
ss_file = os.path.join(output_dir, tsv_file)
cdh.create_subs_sess_list(input_dir=input_dir,
output_dir=output_dir,
file_name=tsv_file,
is_bids_dir=is_bids_dir,
use_session_tsv=use_session_tsv)
ss_df = pd.io.parsers.read_csv(ss_file, sep='\t')
if 'participant_id' not in list(ss_df.columns.values):
raise Exception('No participant_id column in TSV file.')
if 'session_id' not in list(ss_df.columns.values):
raise Exception('No session_id column in TSV file.')
subjects = list(ss_df.participant_id)
sessions = list(ss_df.session_id)
# Remove potential whitespace in participant_id or session_id
return [ses.strip(' ')
for ses in sessions], [sub.strip(' ') for sub in subjects]
def create_subjects_visits(bids_directory: str, output_tsv: str) -> None:
"""Export participants with their sessions."""
from os import makedirs
from os.path import basename, dirname
from clinica.iotools.utils.data_handling import create_subs_sess_list
from clinica.utils.inputs import check_bids_folder
from clinica.utils.stream import cprint
check_bids_folder(bids_directory)
output_directory = dirname(output_tsv)
makedirs(output_directory, exist_ok=True)
create_subs_sess_list(bids_directory, output_directory,
basename(output_tsv))
cprint(f"The TSV file was saved to {output_tsv}.")
def load_and_check_tsv(tsv_path, caps_dir, output_path):
import pandas as pd
from os.path import join
from clinica.iotools.utils.data_handling import create_subs_sess_list
if tsv_path is not None:
df = pd.read_csv(tsv_path, sep='\t')
if ('session_id' not in list(df.columns.values)) or (
'participant_id' not in list(df.columns.values)):
raise Exception("the data file is not in the correct format."
"Columns should include ['participant_id', 'session_id']")
else:
create_subs_sess_list(caps_dir, output_path, is_bids_dir=False, use_session_tsv=False)
df = pd.read_csv(join(output_path, 'subjects_sessions_list.tsv'), sep="\t")
return df
def run_command(self, args):
import os
import errno
from clinica.iotools.utils import data_handling as dt
from clinica.utils.stream import cprint
from clinica.utils.inputs import check_bids_folder
check_bids_folder(args.bids_directory)
output_directory = os.path.dirname(os.path.abspath(args.out_tsv))
if not os.path.exists(output_directory):
try:
os.makedirs(output_directory)
except OSError as exc: # Guard against race condition
if exc.errno != errno.EEXIST:
raise
dt.create_subs_sess_list(args.bids_directory, output_directory,
os.path.basename(args.out_tsv))
cprint("The TSV file was saved to %s" % os.path.abspath(args.out_tsv))
def test_run_CreateSubjectSessionList(cmdopt):
from os.path import join, dirname, abspath
from os import remove
from clinica.iotools.utils import data_handling as dt
root = join(dirname(abspath(__file__)), pardir, 'data', 'CreateSubjectSessionList')
# Set variables
bids_directory = join(root, 'in', 'bids')
output_directory = join(root, 'out')
tsv_name = 'subject_session_list.tsv'
# Create subject_session file
dt.create_subs_sess_list(bids_directory, output_directory, tsv_name)
# Comparison bitwise
out_tsv = join(output_directory, tsv_name)
ref_tsv = join(root, 'ref', tsv_name)
assert identical_subject_list(out_tsv, ref_tsv)
remove(out_tsv)
def load_and_check_tsv(tsv_path, caps_dict, output_path):
from os.path import join
import pandas as pd
from clinica.iotools.utils.data_handling import create_subs_sess_list
from clinicadl.utils.caps_dataset.data import check_multi_cohort_tsv
if tsv_path is not None:
if len(caps_dict) == 1:
df = pd.read_csv(tsv_path, sep="\t")
if ("session_id" not in list(
df.columns.values)) or ("participant_id" not in list(
df.columns.values)):
raise Exception(
"the data file is not in the correct format."
"Columns should include ['participant_id', 'session_id']")
else:
tsv_df = pd.read_csv(tsv_path, sep="\t")
check_multi_cohort_tsv(tsv_df, "labels")
df = pd.DataFrame()
for idx in range(len(tsv_df)):
cohort_name = tsv_df.loc[idx, "cohort"]
cohort_path = tsv_df.loc[idx, "path"]
cohort_df = pd.read_csv(cohort_path, sep="\t")
cohort_df["cohort"] = cohort_name
df = pd.concat([df, cohort_df])
else:
df = pd.DataFrame()
for cohort, caps_path in caps_dict.items():
create_subs_sess_list(caps_path,
output_path,
is_bids_dir=False,
use_session_tsv=False)
cohort_df = pd.read_csv(join(output_path,
"subjects_sessions_list.tsv"),
sep="\t")
cohort_df["cohort"] = cohort
df = pd.concat([df, cohort_df])
return df
def test_run_CreateSubjectSessionList(cmdopt):
from os import remove
from os.path import abspath, dirname, join
from clinica.iotools.utils import data_handling as dt
root = join(dirname(abspath(__file__)), pardir, pardir, "data",
"CreateSubjectSessionList")
# Set variables
bids_directory = join(root, "in", "bids")
output_directory = join(root, "out")
tsv_name = "subject_session_list.tsv"
# Create subject_session file
dt.create_subs_sess_list(bids_directory, output_directory, tsv_name)
# Comparison bitwise
out_tsv = join(output_directory, tsv_name)
ref_tsv = join(root, "ref", tsv_name)
assert identical_subject_list(out_tsv, ref_tsv)
remove(out_tsv)
def grab_noddi_preprocessed_files(caps_directory, tsv):
"""
This is a function to grab the files from the preprocessed data
Args:
caps_directory:
tsv:
Returns:
"""
import os
import csv
import tempfile
from time import time, strftime, localtime
import clinica.iotools.utils.data_handling as cdh
if tsv is None:
output_dir = tempfile.mkdtemp()
timestamp = strftime('%Y%m%d_%H%M%S', localtime(time()))
tsv_file = '%s_subjects_sessions_list.tsv' % timestamp
tsv = os.path.join(output_dir, tsv_file)
cdh.create_subs_sess_list(input_dir=caps_directory,
output_dir=output_dir,
file_name=tsv_file,
is_bids_dir=False)
subject_list = []
session_list = []
subject_id_list = []
with open(tsv, 'rb') as tsvin:
tsv_reader = csv.reader(tsvin, delimiter='\t')
for row in tsv_reader:
if row[0] == 'participant_id':
continue
else:
subject_list.append(row[0])
session_list.append(row[1])
subject_id_list.append((row[0] + '_' + row[1]))
caps_directory = os.path.expanduser(caps_directory)
noddi_preprocessed_dwi = []
noddi_preprocessed_bvec = []
noddi_preprocessed_bval = []
noddi_preprocessed_mask = []
# the number of subject_list and session_list should be the same
try:
len(subject_list) == len(session_list)
except RuntimeError:
print "It seems that the nuber of session_list and subject_list are not in the same length, please check"
raise
num_subject = len(subject_list)
for i in xrange(num_subject):
# AP
subject_nii = os.path.join(
caps_directory, 'subjects', subject_list[i], session_list[i],
'dwi', 'preprocessing',
subject_id_list[i] + '_dwi_space-b0_preproc.nii.gz')
noddi_preprocessed_dwi += [subject_nii]
subject_bvec = os.path.join(
caps_directory, 'subjects', subject_list[i], session_list[i],
'dwi', 'preprocessing',
subject_id_list[i] + '_dwi_space-b0_preproc.bvec')
noddi_preprocessed_bvec += [subject_bvec]
subject_bval = os.path.join(
caps_directory, 'subjects', subject_list[i], session_list[i],
'dwi', 'preprocessing',
subject_id_list[i] + '_dwi_space-b0_preproc.bval')
noddi_preprocessed_bval += [subject_bval]
subject_mask = os.path.join(
caps_directory, 'subjects', subject_list[i], session_list[i],
'dwi', 'preprocessing',
subject_id_list[i] + '_dwi_space-b0_brainmask.nii.gz')
noddi_preprocessed_mask += [subject_mask]
return subject_id_list, noddi_preprocessed_dwi, noddi_preprocessed_bvec, noddi_preprocessed_bval, noddi_preprocessed_mask
