def test_anonymize(self):
header = highlevel.make_header(technician='tech',
recording_additional='radd',
patientname='name',
patient_additional='padd',
patientcode='42',
equipment='eeg',
admincode='420',
gender='Male',
birthdate='05.09.1980')
annotations = [[0.01, -1, 'begin'], [0.5, -1, 'middle'],
[10, -1, 'end']]
header['annotations'] = annotations
signal_headers = highlevel.make_signal_headers(
['ch' + str(i) for i in range(3)])
signals = np.random.rand(3, 256 * 300) * 200 #5 minutes of eeg
highlevel.write_edf(self.personalized, signals, signal_headers, header)
highlevel.anonymize_edf(self.personalized,
new_file=self.anonymized,
to_remove=[
'patientname', 'birthdate', 'admincode',
'patientcode', 'technician'
],
new_values=['x', '', 'xx', 'xxx', 'xxxx'],
verify=True,
verbose=True)
new_header = highlevel.read_edf_header(self.anonymized)
self.assertEqual(new_header['birthdate'], '')
self.assertEqual(new_header['patientname'], 'x')
self.assertEqual(new_header['admincode'], 'xx')
self.assertEqual(new_header['patientcode'], 'xxx')
self.assertEqual(new_header['technician'], 'xxxx')
highlevel.anonymize_edf(self.personalized,
to_remove=[
'patientname', 'birthdate', 'admincode',
'patientcode', 'technician'
],
new_values=['x', '', 'xx', 'xxx', 'xxxx'],
verify=True)
new_header = highlevel.read_edf_header(self.personalized[:-4] +
'_anonymized.edf')
self.assertEqual(new_header['birthdate'], '')
self.assertEqual(new_header['patientname'], 'x')
self.assertEqual(new_header['admincode'], 'xx')
self.assertEqual(new_header['patientcode'], 'xxx')
self.assertEqual(new_header['technician'], 'xxxx')
with self.assertRaises(AssertionError):
highlevel.anonymize_edf(self.personalized,
new_file=self.anonymized,
to_remove=[
'patientname', 'birthdate',
'admincode', 'patientcode',
'technician'
],
new_values=['x', '', 'xx', 'xxx'],
verify=True)
def extract_ecg(edf_file, copy_folder):
filename = os.path.basename(edf_file)
new_edf_file = os.path.join(copy_folder, filename)
if os.path.exists(new_edf_file): return
try:
header = highlevel.read_edf_header(edf_file)
except:
print(f'error in file {edf_file}')
return
channels = header['channels']
try:
channels.remove('cs_ECG')
except:
print(f'warning, {edf_file} has no cs_ECG')
ch_names = [x for x in channels if 'ECG' in x.upper()]
if len(ch_names) > 1:
print(
f'Warning, these are present: {ch_names}, selecting {ch_names[0]}')
ch_name = ch_names[0]
signals, shead, header = highlevel.read_edf(edf_file,
ch_names=[ch_name],
digital=True,
verbose=False)
shead[0]['label'] = 'ECG'
assert len(signals) > 0, 'signal empty'
try:
highlevel.write_edf(new_edf_file, signals, shead, header, digital=True)
except:
shead[0]['digital_min'] = signals.min()
shead[0]['digital_max'] = signals.max()
highlevel.write_edf(new_edf_file, signals, shead, header, digital=True)
def test_read_header(self):
header = highlevel.read_edf_header(self.test_generator)
self.assertEqual(len(header), 14)
self.assertEqual(len(header['channels']), 11)
self.assertEqual(len(header['SignalHeaders']), 11)
self.assertEqual(header['Duration'], 600)
self.assertEqual(header['admincode'], 'Dr. X')
self.assertEqual(header['birthdate'], '30 jun 1969')
self.assertEqual(header['equipment'], 'test generator')
self.assertEqual(header['gender'], 'Male')
self.assertEqual(header['patient_additional'], 'patient')
self.assertEqual(header['patientcode'], 'abcxyz99')
self.assertEqual(header['patientname'], 'Hans Muller')
self.assertEqual(header['technician'], 'Mr. Spotty')
def convert_hypnograms(datadir):
"""
This function is quite a hack to read the edf hypnogram as a byte array.
I found no working reader for the hypnogram edfs.
"""
print('Converting hypnograms')
files = [x for x in os.listdir(datadir) if x.endswith('Hypnogram.edf')]
for file in tqdm(files):
file = os.path.join(datadir, file)
hypnogram = []
annot = highlevel.read_edf_header(file)['annotations']
for bstart, blength, bstage in annot:
length = int(blength.decode())
stage = bstage.decode()
if 'movement' in stage.lower(): stage = 'M'
stage = [str(stage[-1])] * (length // 30)
hypnogram.extend(stage)
csv_file = file.replace('-Hypnogram', '')[:-5] + '0-PSG.csv'
with open(csv_file, "w") as f:
writer = csv.writer(f, lineterminator='\r')
writer.writerows(hypnogram)
help='Number of columns to display in the viewer')
parser.add_argument(
'-page',
type=int,
default=0,
help='At which page (epoch*gridsize) to start the viewer')
args = parser.parse_args()
edf_file = args.edf_file
nrows = args.nrows
ncols = args.ncols
page = args.page
if edf_file is None:
edf_file = misc.choose_file(exts=['edf', 'npy'],
title='Choose a EDF to display')
print('loading {}'.format(edf_file))
channels = highlevel.read_edf_header(edf_file)['channels']
ch_nr = channels.index([ch for ch in channels if 'ECG' in ch.upper()][0])
data, sheader, header = highlevel.read_edf(edf_file, ch_nrs=ch_nr)
data = data[0]
fs = sheader[0]['sample_rate']
title = os.path.basename(edf_file)
self = ECGPlotter(data=data,
fs=fs,
startpage=page,
nrows=nrows,
ncols=ncols,
title=title)
plt.show(block=True)
return df_ann
# To improve
source_selection = st.sidebar.selectbox('Chose source seleciton',
options=['Physionet', 'La Teppe'],
index=0)
if source_selection == 'La Teppe':
edf_patient_selection = st.sidebar.selectbox('Chose patient',
options=edf_files,
index=0)
edf_file = edf_path + edf_patient_selection
headers = highlevel.read_edf_header(edf_file)
channels = headers['channels']
limited_channels = [
'ECG1+ECG1-', 'EMG1+EMG1-', 'EMG6+EMG6-', 'EMG2G2', 'EMG3G2',
'EMG2G2-EMG3G2'
]
limited_channels = [
limited_channels[i] for i in range(len(limited_channels))
if limited_channels[i] in channels
]
channels_selection = st.sidebar.selectbox('select channel',
options=limited_channels,
index=0)
e.g. another name for ECG that has not been added to the mappings dictionary
that is present in config.py
@author: skjerns
"""
import config as cfg
import os
import sleep_utils
import misc
import ospath
from tqdm import tqdm
from pyedflib.highlevel import read_edf_header
ch_mapping = cfg.mapping_channels
missing = set()
if __name__ == '__main__':
files = []
for dataset in cfg.datasets.values():
files.extend(ospath.list_files(dataset, exts='edf', subfolders=True))
ch_mapping = cfg.mapping_channels
for file in tqdm(files):
channels = read_edf_header(file)['channels']
for ch in channels:
if not ch in ch_mapping and not ch in ch_mapping.values():
missing.add(ch)
print(ch)
