def __init__(self, subject, experiment, session, outdir, rootdir=None):
self.rootdir = get_root_dir(rootdir)
self.outdir = Path(self.rootdir).joinpath(outdir)
self.reader = CMLReader(subject, experiment, session, rootdir=rootdir)
sources_filename = self.reader.path_finder.find("sources")
with open(sources_filename, "r") as infile:
self.sources = json.load(infile)
self.eeg_files = [
sorted(
Path(sources_filename).parent.joinpath("noreref").glob(
info["name"] + "*")) for info in self.sources.values()
]
def test_get_root_dir(path, with_env_var):
with set_cml_root("/override" if with_env_var else None):
root = get_root_dir(path)
if with_env_var:
if path is None:
assert root == os.environ["CML_ROOT"]
else:
assert root == path
else:
if path is None:
assert root == "/"
else:
assert root == path
def as_timeseries(self, events: pd.DataFrame,
rel_start: Union[float, int],
rel_stop: Union[float, int]) -> EEGContainer:
"""Read the timeseries.
Parameters
----------
events
Events to read EEG data from
rel_start
Relative start times in ms
rel_stop
Relative stop times in ms
Returns
-------
A time series with shape (channels, epochs, time). By default, this
returns data as it was physically recorded (e.g., if recorded with a
common reference, each channel will be a contact's reading referenced
to the common reference, a.k.a. "monopolar channels").
Raises
------
RereferencingNotPossibleError
When rereferencing is not possible.
"""
eegs = []
# sanity check on the offsets
if rel_start != 0 and rel_stop != -1 and rel_start > rel_stop:
raise ValueError('rel_start must precede rel_stop')
for filename in events["eegfile"].unique():
# select subset of events for this basename
ev = events[events["eegfile"] == filename]
# determine experiment, session, dtype, and sample rate
experiment = ev["experiment"].unique()[0]
session = ev["session"].unique()[0]
basename = os.path.basename(filename)
finder = PathFinder(subject=self.subject,
experiment=experiment,
session=session,
eeg_basename=basename,
rootdir=self.rootdir)
sources = EEGMetaReader.fromfile(finder.find("sources"),
subject=self.subject)
sample_rate = sources["sample_rate"]
dtype = sources["data_format"]
is_scalp = dtype in (".bdf", ".raw", ".mff")
# Convert events to epochs (onset & offset times)
if rel_start == 0 and rel_stop == -1 and len(events) == 1:
epochs = [(0, None)]
else:
epochs = convert.events_to_epochs(ev, rel_start, rel_stop,
sample_rate)
# Scalp EEG reader requires onsets, rel_start (in sec), and rel_
# stop (in sec) to cut data into epochs
if is_scalp:
on_off_epochs = epochs # The onset & offset times will still
# be passed to the EEGContainer later
if rel_start == 0 and rel_stop == -1 and len(events) == 1:
epochs = None
else:
epochs = np.zeros((len(ev), 3), dtype=int)
epochs[:, 0] = ev["eegoffset"]
epochs = dict(epochs=epochs, tmin=rel_start / 1000.,
tmax=rel_stop / 1000.)
root = get_root_dir(self.rootdir)
eeg_filename = os.path.join(root, filename.lstrip("/"))
reader_class = self._get_reader_class(filename)
reader = reader_class(filename=eeg_filename,
dtype=dtype,
epochs=epochs,
scheme=self.scheme,
clean=self.clean)
# if scalp EEG, info is an MNE Info object; if iEEG, info is a list
# of contacts
data, info = reader.read()
attrs = {}
if is_scalp:
# Pass MNE info and events as extra attributes, to be able to
# fully reconstruct MNE Raw/Epochs objects
attrs["mne_info"] = info
channels = info["ch_names"]
if epochs is not None:
# Crop out any events/epoch times that ran beyond the
# bounds of the EEG recording
te_pre = info["truncated_events_pre"] \
if info["truncated_events_pre"] > 0 else None
te_post = -info["truncated_events_post"] \
if info["truncated_events_post"] > 0 else None
on_off_epochs = on_off_epochs[te_pre:te_post]
ev = ev[te_pre:te_post]
# Pass the onset & offset time epoch list to EEGContainer, NOT
# the MNE-formatted epoch list
epochs = on_off_epochs
elif self.scheme is not None:
data, channels = reader.rereference(data, info)
else:
channels = ["CH{}".format(n + 1) for n in range(data.shape[1])]
eegs.append(
EEGContainer(
data,
sample_rate,
epochs=epochs,
events=ev,
channels=channels,
tstart=rel_start,
attrs=attrs
)
)
eegs = EEGContainer.concatenate(eegs)
eegs.attrs["rereferencing_possible"] = reader.rereferencing_possible
return eegs
def as_timeseries(self, events: pd.DataFrame, rel_start: Union[float, int],
rel_stop: Union[float, int]) -> EEGContainer:
"""Read the timeseries.
Parameters
----------
events
Events to read EEG data from
rel_start
Relative start times in ms
rel_stop
Relative stop times in ms
Returns
-------
A time series with shape (channels, epochs, time). By default, this
returns data as it was physically recorded (e.g., if recorded with a
common reference, each channel will be a contact's reading referenced to
the common reference, a.k.a. "monopolar channels").
Raises
------
RereferencingNotPossibleError
When rereferencing is not possible.
"""
eegs = []
for filename in events["eegfile"].unique():
# select subset of events for this basename
ev = events[events["eegfile"] == filename]
# determine experiment, session, dtype, and sample rate
experiment = ev["experiment"].unique()[0]
session = ev["session"].unique()[0]
finder = PathFinder(subject=self.subject,
experiment=experiment,
session=session,
rootdir=self.rootdir)
sources = EEGMetaReader.fromfile(finder.find("sources"),
subject=self.subject)
sample_rate = sources["sample_rate"]
dtype = sources["data_format"]
# convert events to epochs
if rel_stop < 0:
# We're trying to load to the end of the session. Only allow
# this in cases where we're trying to load a whole session.
if len(events) > 1:
raise ValueError("rel_stop must not be negative")
epochs = [(0, None)]
else:
epochs = convert.events_to_epochs(ev, rel_start, rel_stop,
sample_rate)
root = get_root_dir(self.rootdir)
eeg_filename = os.path.join(root, filename.lstrip("/"))
reader_class = self._get_reader_class(filename)
reader = reader_class(filename=eeg_filename,
dtype=dtype,
epochs=epochs,
scheme=self.scheme)
data, contacts = reader.read()
if self.scheme is not None:
data, labels = reader.rereference(data, contacts)
channels = labels
else:
channels = ["CH{}".format(n + 1) for n in range(data.shape[1])]
eegs.append(
EEGContainer(
data,
sample_rate,
epochs=epochs,
events=ev,
channels=channels,
tstart=rel_start,
))
eegs = EEGContainer.concatenate(eegs)
eegs.attrs["rereferencing_possible"] = reader.rereferencing_possible
return eegs