def arf2bark(arf_file,
root_path,
timezone,
verbose,
mangle_prefix=ENTRY_PREFIX):
with arf.open_file(arf_file, 'r') as af:
os.mkdir(root_path)
root = bark.Root(root_path)
if verbose:
print('Created Root: ' + root_path)
tle = None
found_trigin = False
for ename, entry in af.items(): # entries and top-level datasets
if isinstance(entry, h5py.Group): # entries
entry_path = os.path.join(root_path, ename)
entry_attrs = copy_attrs(entry.attrs)
for pos_arg in ('name', 'parents'):
# along with 'timestamp' below, these are positional arguments to create_entry
# for now, I prefer hard-coding them over messing with runtime introspection
new_name = pos_arg
while new_name in entry_attrs:
new_name = '{}_{}'.format(mangle_prefix, new_name)
try:
entry_attrs[new_name] = entry_attrs.pop(pos_arg)
except KeyError:
pass
else:
if verbose:
print('Renamed attribute {} of entry {} to {}'.
format(pos_arg, ename, new_name))
timestamp = entry_attrs.pop('timestamp')
if timezone:
timestamp = bark.convert_timestamp(timestamp, timezone)
else:
timestamp = bark.convert_timestamp(timestamp)
bark_entry = bark.create_entry(entry_path,
timestamp,
parents=False,
**entry_attrs)
if verbose:
print('Created Entry: ' + entry_path)
for ds_name, dataset in entry.items(): # entry-level datasets
if ds_name == 'trig_in': # accessing trig_in -> segfault
found_trigin = True # and skip the dataset
else:
transfer_dset(ds_name, dataset, entry_path, verbose)
elif isinstance(entry, h5py.Dataset): # top-level datasets
if arf.is_time_series(entry) or arf.is_marked_pointproc(entry):
if tle is None:
path = os.path.join(root_path, 'top_level')
tle = bark.create_entry(path, 0, parents=False).path
transfer_dset(ename, entry, tle, verbose)
else:
unknown_ds_warning(ename) # and skip, w/o creating TLE
if found_trigin:
print('Warning: found datasets named "trig_in". Jill-created ' +
'"trig_in" datasets segfault when read, so these datasets' +
' were skipped. If you know the datasets are good, rename' +
' them and try again.')
return bark.Root(root_path)
def transfer_dset(ds_name, ds, e_path, verbose=False):
ds_attrs = copy_attrs(ds.attrs)
units = ds_attrs.pop('units', None)
if arf.is_time_series(ds):
ds_name += '.dat'
ds_path = os.path.join(e_path, ds_name)
ds_attrs['columns'] = build_columns(units)
sr = ds_attrs.pop('sampling_rate')
bark_ds = bark.write_sampled(ds_path, ds, sr, **ds_attrs)
if verbose:
print('Created sampled dataset: ' + ds_path)
elif arf.is_marked_pointproc(ds):
ds_name += '.csv'
ds_path = os.path.join(e_path, ds_name)
ds_data = pandas.DataFrame(ds[:])
ds_attrs['columns'] = build_columns(units,
column_names=ds_data.columns)
for ser in ds_data:
if ds_data[ser].dtype == numpy.dtype('O'): # bytes object
ds_data[ser] = ds_data[ser].str.decode('utf-8')
bark_ds = bark.write_events(ds_path, ds_data, **ds_attrs)
if verbose:
print('Created event dataset: ' + ds_path)
else:
unknown_ds_warning(ds_name)
def send(self, chunk):
""" align spikes, compute features """
# pass data we can't use
from arf import is_marked_pointproc
if not is_marked_pointproc(chunk.data) or "spike" not in chunk.data.dtype.names:
Node.send(self, chunk)
else:
# need to read data now because it won't be available in close
self._queue.append(chunk._replace(data=chunk.data[:]))
if chunk.ds != self._queue[0].ds:
self._queue.pop()
raise DataError("%s: sampling rate doesn't match other spikes" % chunk)
def arf2bark(arf_file, root_path, timezone, verbose):
with arf.open_file(arf_file, 'r') as af:
os.mkdir(root_path)
root = bark.Root(root_path)
if verbose:
print('Created Root: ' + root_path)
tle = None
found_trigin = False
for ename, entry in af.items(): # entries and top-level datasets
if isinstance(entry, h5py.Group): # entries
entry_path = os.path.join(root_path, ename)
entry_attrs = copy_attrs(entry.attrs)
timestamp = entry_attrs.pop('timestamp')
# rename 'name' attribute created by openephys arf module
try:
entry_attrs['openephys_name'] = entry_attrs.pop('name')
except KeyError:
pass
if timezone:
timestamp = bark.convert_timestamp(timestamp, timezone)
else:
timestamp = bark.convert_timestamp(timestamp)
bark_entry = bark.create_entry(entry_path,
timestamp,
parents=False,
**entry_attrs)
if verbose:
print('Created Entry: ' + entry_path)
for ds_name, dataset in entry.items(): # entry-level datasets
if ds_name == 'trig_in': # accessing trig_in -> segfault
found_trigin = True # and skip the dataset
else:
transfer_dset(ds_name, dataset, entry_path, verbose)
elif isinstance(entry, h5py.Dataset): # top-level datasets
if arf.is_time_series(entry) or arf.is_marked_pointproc(entry):
if tle is None:
path = os.path.join(root_path, 'top_level')
tle = bark.create_entry(path, 0, parents=False).path
transfer_dset(ename, entry, tle, verbose)
else:
unknown_ds_warning(ename) # and skip, w/o creating TLE
if found_trigin:
print('Warning: found datasets named "trig_in". Jill-created ' +
'"trig_in" datasets segfault when read, so these datasets' +
' were skipped. If you know the datasets are good, rename' +
' them and try again.')
return bark.Root(root_path)