def calc_demos(output_dir, info_out_dir, demo_file, pwd, new_id_lut_file=None):
'''
Calcluates demos from acq_time
'''
# get qcq_dates
acq_dates = get_acq_dates(info_out_dir)
assert pwd != "", "password empty"
demo_df = read_protected_file(
demo_file, pwd, "demos.txt").reset_index().rename(
columns={"subject_id": "old_participant_id"})
demo_df["participant_id"] = get_public_sub_id(demo_df.old_participant_id,
new_id_lut_file)
demo_df["participant_id"] = "sub-" + demo_df["participant_id"]
demo_df = demo_df.drop(columns=["old_participant_id"])
df = pd.merge(acq_dates, demo_df, how="left", on="participant_id")
df["dob"] = pd.to_datetime(df.dob)
df["acq_date"] = pd.to_datetime(df.acq_date)
df["age"] = ((df.acq_date - df.dob).dt.days / 365.25).apply(np.round,
decimals=1)
df = df[["participant_id", "session_id", "sex", "age"]]
to_tsv(df, output_dir / "participants.tsv")
subjects = df.participant_id.unique()
print(
f"\n\n\n\nDONE.\nExported demos for {len(subjects)} subjects.\n {subjects}"
)
def update_sub_scans_file(output_dir,
bids_sub,
bids_ses,
bids_modality,
out_filename,
par_file,
public_output=True):
"""
one file per subject with
-ses id
-filename
-if not public: date of acquisition
"""
general_info, image_defs = read_par(par_file)
acq_time = parse_acq_time(general_info)
scans_file = os.path.join(output_dir, bids_sub, bids_sub + "_scans.tsv")
if os.path.exists(scans_file):
scans = read_tsv(scans_file)
else:
scans = pd.DataFrame([])
scans = scans.append(
{
"participant_id": bids_sub,
"session_id": bids_ses,
"filename":
bids_ses + "/" + bids_modality + "/" + out_filename + ".nii.gz",
"acq_time": acq_time
},
ignore_index=True)
if not public_output:
scans = scans[["participant_id", "session_id", "filename", "acq_time"]]
else:
scans = scans[["participant_id", "session_id", "filename"]]
to_tsv(scans, scans_file)
def save_physio(output_filename_base, meta_data, physio_data):
tsv_filename = output_filename_base + ".tsv.gz"
json_filename = output_filename_base + ".json"
header = physio_data.columns.tolist()
json_data = {"Columns": header, "StartTime": 0, "SamplingFrequency": 496}
add_info_to_json(json_filename, json_data, create_new=True)
to_tsv(physio_data, tsv_filename, header=False)
def save_physio(output_filename_base, meta_data, physio_data):
tsv_filename = output_filename_base + ".tsv"
json_filename = output_filename_base + ".json"
header = physio_data.columns.tolist()
json_data = {"header": header, "meta_data": meta_data}
add_info_to_json(json_filename, json_data, create_new=True)
to_tsv(physio_data, tsv_filename, header=False)
def reduce_sub_files(bids_dir, output_file, sub_file):
df = pd.DataFrame([])
layout = BIDSLayout(bids_dir)
files = layout.get(extensions=sub_file)
for file in [f.filename for f in files]:
print(file)
df_ = read_tsv(file)
df = pd.concat((df, df_))
to_tsv(df, os.path.join(bids_dir, output_file))
def get_scan_duration(output_dir, modality="func", task="rest"):
"""
"""
layout = BIDSLayout(output_dir)
subjects_list = layout.get_subjects()
scan_duration = pd.DataFrame([])
#
for sub_id in subjects_list:
sub_dir = os.path.join(output_dir, "sub-" + sub_id)
ses_id_list = layout.get_sessions(subject=sub_id)
for ses_id in ses_id_list:
sub_ses_path = os.path.join(sub_dir, "ses-" + ses_id)
f = layout.get(subject=sub_id,
session=ses_id,
modality=modality,
task=task,
extensions='.nii.gz')
if len(f) > 1:
raise Exception(
"something went wrong, more than one %s %s file detected: %s"
% (modality, task, f))
elif len(f) == 1:
duration = (layout.get_metadata(
f[0].filename)["ScanDurationSec"])
scan_duration_sub = pd.DataFrame(
OrderedDict([("subject_id", sub_id),
("sesssion_id", ses_id),
("scan_duration_s", [duration])]))
scan_duration = scan_duration.append(scan_duration_sub)
out_str = modality
if task:
out_str += "_" + task
output_file = os.path.join(output_dir, "scan_duration_%s.tsv" % out_str)
print("Writing scan duration to %s" % output_file)
to_tsv(scan_duration, output_file)
# get subject list
raw_subjects_list = []
for ses in ses_id_list:
search_dir = os.path.join(raw_dir, ses, in_ses_folder)
os.chdir(search_dir)
raw_subjects_list += sorted(glob.glob("lhab*"))
old_subject_id_list = sorted(list(set([s[:9] for s in raw_subjects_list])))
# export all subjects list
all_sub_file = os.path.join(output_dir, "lhab_all_subjects.tsv")
if os.path.exists(all_sub_file):
raise FileExistsError("\n%s exists. Stopped and did nothing." %
all_sub_file)
all_sub = pd.DataFrame({"sub_id": old_subject_id_list},
index=old_subject_id_list)
to_tsv(all_sub, all_sub_file)
print("All-subject list written to %s" % all_sub_file)
os.chmod(all_sub_file, 0o444)
print("Permission of %s set to read only\n" % all_sub_file)
# create new ids
new_id = []
for i in range(1, 1000):
new_id.append('lhabX{:04d}'.format(i))
# for good measures, shuffle
n_sub = len(old_subject_id_list)
new_id_used = new_id[:n_sub]
random.shuffle(new_id_used)
new_id_spare = new_id[n_sub:]
def calc_demos(
output_dir,
ses_id_list,
raw_dir,
in_ses_folder,
demo_file,
pwd,
use_new_ids=True,
new_id_lut_file=None,
public_output=True,
):
'''
Calcluates demos from acq_time
'''
assert pwd != "", "password empty"
demo_df = read_protected_file(demo_file, pwd, "demos.txt")
out_demo_df = pd.DataFrame([])
out_acq_time_df = pd.DataFrame([])
layout = BIDSLayout(output_dir)
new_sub_id_list = layout.get_subjects()
for new_subject_id in new_sub_id_list:
old_subject_id = get_private_sub_id(new_subject_id, new_id_lut_file)
for old_ses_id in ses_id_list:
subject_ses_folder = os.path.join(raw_dir, old_ses_id,
in_ses_folder)
os.chdir(subject_ses_folder)
subject_folder = sorted(glob(old_subject_id + "*"))
assert len(
subject_folder
) < 2, "more than one subject folder %s" % old_subject_id
if subject_folder:
subject_folder = subject_folder[0]
abs_subject_folder = os.path.abspath(subject_folder)
os.chdir(abs_subject_folder)
if use_new_ids:
bids_sub = new_subject_id
else:
bids_sub = get_clean_subject_id(old_subject_id)
bids_ses = get_clean_ses_id(old_ses_id)
par_file_list = glob(os.path.join(abs_subject_folder, "*.par"))
if par_file_list:
par_file = par_file_list[0]
df_subject, df_acq_time_subject = fetch_demos(
demo_df, old_subject_id, bids_sub, bids_ses, par_file)
out_demo_df = pd.concat((out_demo_df, df_subject))
out_acq_time_df = pd.concat(
(out_acq_time_df, df_acq_time_subject))
to_tsv(out_demo_df, os.path.join(output_dir, "participants.tsv"))
if not public_output:
to_tsv(out_acq_time_df, os.path.join(output_dir, "acq_time.tsv"))
print("\n\n\n\nDONE.\nExported demos for %d subjects." %
len(new_sub_id_list))
print(new_sub_id_list)
def compare_par_nii(output_dir, old_sub_id_list, raw_dir, ses_id_list,
in_ses_folder, info_list, new_id_lut_file):
"""
- Checks that all subjects from subject list are in sourcedata
- Checks that par and nii filecount agrees
- Exports nii filecount to output_dir
"""
# first check that all subjects from id list are in the output_dir
print("\nchecking that all subjects from id list are in the output_dir...")
layout = BIDSLayout(output_dir)
subjects_list = layout.get_subjects()
for old_sub_id in old_sub_id_list:
new_sub_id = get_public_sub_id(old_sub_id, new_id_lut_file)
sub_dir = os.path.join(output_dir, "sub-" + new_sub_id)
f = glob(sub_dir)
if not f:
raise Exception("No folder not found: %s" % sub_dir)
print("%d subjects from list found in folder %s. Seems OK...\n" %
(len(old_sub_id_list), output_dir))
# compare filecount of par and nii files and export
filecount = pd.DataFrame([])
for new_sub_id in subjects_list:
old_sub_id = get_private_sub_id(new_sub_id, new_id_lut_file)
for old_ses_id in ses_id_list:
new_ses_id = "tp" + old_ses_id[-1]
sub_ses_par_dir = os.path.join(
raw_dir, old_ses_id, in_ses_folder,
old_sub_id + "_t%s_raw" % new_ses_id[-1])
sub_ses_nii_dir = os.path.join(output_dir, "sub-" + new_sub_id,
"ses-" + new_ses_id)
n_files = OrderedDict([("subject_id", new_sub_id),
("session_id", new_ses_id)])
for info in info_list:
par_search_str = os.path.join(
sub_ses_par_dir, "*" + info["search_str"] + "*.par")
par_f = glob(par_search_str)
n_files_par = len(par_f)
if "acq" in info.keys():
acq_str = "_acq-" + info["acq"]
else:
acq_str = ""
if "direction" in info.keys():
dir_str = "_dir-" + info["direction"]
else:
dir_str = ""
nii_search_str = os.path.join(
sub_ses_nii_dir, info["bids_modality"], "*" + acq_str +
"*" + dir_str + "*" + info["bids_name"] + "*.nii.gz")
nii_f = glob(nii_search_str)
n_files_nifti = len(nii_f)
c = info["bids_modality"] + "_" + info["bids_name"] + \
acq_str.replace("-", "") + dir_str.replace("-", "")
n_files[c] = [n_files_nifti]
if not n_files_par == n_files_nifti:
raise Exception(
"missmatch between par and nii file count %s %s %s %s"
% (new_sub_id, new_ses_id, par_search_str,
nii_search_str))
# TODO check physio
if "physio" in info.keys() and info["physio"]:
phys_par_search_str = os.path.join(
sub_ses_par_dir,
"*" + info["search_str"] + "*_physio.log")
phys_par_f = glob(phys_par_search_str)
phys_n_files_par = len(phys_par_f)
phys_nii_search_str = os.path.join(
sub_ses_nii_dir, info["bids_modality"],
"*" + acq_str + "*" + dir_str + "*" +
info["bids_name"] + "*_physio.tsv")
phys_nii_f = glob(phys_nii_search_str)
phys_n_files_nifti = len(phys_nii_f)
c = info["bids_modality"] + "_" + info["bids_name"] + \
acq_str.replace("-", "") + dir_str.replace("-", "") + "_physio"
n_files[c] = [phys_n_files_nifti]
if not phys_n_files_par == phys_n_files_nifti:
raise Exception(
"missmatch between par and nii file count %s %s %s %s"
% (new_sub_id, new_ses_id, phys_par_search_str,
phys_nii_search_str))
filecount = filecount.append(pd.DataFrame(n_files))
output_file = os.path.join(output_dir, "n_files.tsv")
to_tsv(filecount, output_file)
print("Compared filecount from par and nifti files. Seems OK...")
print("Filecount written to %s" % output_file)
