def test_contains_row_different_types():
"""Test that _contains_row() can handle different dtypes without warning.
This is to check if we're successfully avoiding a FutureWarning emitted by
NumPy, see https://github.com/mne-tools/mne-bids/pull/372
(pytest must be configured to fail on warnings for this to work!)
"""
data = odict(age=[20, 30, 40, 'n/a']) # string
row = dict(age=60) # int
_contains_row(data, row)
def test_tsv_handler(tmp_path):
"""Test the TSV handling."""
# create some dummy data
d = odict(a=[1, 2, 3, 4], b=['five', 'six', 'seven', 'eight'])
assert _contains_row(d, {'a': 1, 'b': 'five'})
d2 = odict(a=[5], b=['nine'])
d = _combine_rows(d, d2)
assert 5 in d['a']
d2 = odict(a=[5])
d = _combine_rows(d, d2)
assert 'n/a' in d['b']
d2 = odict(a=[5], b=['ten'])
d = _combine_rows(d, d2, drop_column='a')
# make sure that the repeated data was dropped
assert 'nine' not in d['b']
print(_tsv_to_str(d))
d_path = tmp_path / 'output.tsv'
# write the data to an output tsv file
_to_tsv(d, d_path)
# now read it back
d = _from_tsv(d_path)
# test reading the file in with the incorrect number of datatypes raises
# an Error
with pytest.raises(ValueError):
d = _from_tsv(d_path, dtypes=[str])
# we can also pass just a single data type and it will be applied to all
# columns
d = _from_tsv(d_path, str)
# remove any rows with 2 or 5 in them
d = _drop(d, [2, 5], 'a')
assert 2 not in d['a']
# test combining data with differing numbers of columns
d = odict(a=[1, 2], b=['three', 'four'])
d2 = odict(a=[4], b=['five'], c=[3.1415])
# raise error if a new column is tried to be added
with pytest.raises(KeyError):
d = _combine_rows(d, d2)
d2 = odict(a=[5])
d = _combine_rows(d, d2)
assert d['b'] == ['three', 'four', 'n/a']
assert _contains_row(d, {'a': 5})
# test reading a single column
_to_tsv(odict(a=[1, 2, 3, 4]), d_path)
d = _from_tsv(d_path)
assert d['a'] == ['1', '2', '3', '4']
def _participants_tsv(raw, subject_id, fname, overwrite=False,
verbose=True):
"""Create a participants.tsv file and save it.
This will append any new participant data to the current list if it
exists. Otherwise a new file will be created with the provided information.
Parameters
----------
raw : instance of Raw
The data as MNE-Python Raw object.
subject_id : str
The subject name in BIDS compatible format ('01', '02', etc.)
fname : str
Filename to save the participants.tsv to.
overwrite : bool
Whether to overwrite the existing file.
Defaults to False.
If there is already data for the given `subject_id` and overwrite is
False, an error will be raised.
verbose : bool
Set verbose output to true or false.
"""
subject_id = 'sub-' + subject_id
data = OrderedDict(participant_id=[subject_id])
subject_age = "n/a"
sex = "n/a"
subject_info = raw.info['subject_info']
if subject_info is not None:
sexes = {0: 'n/a', 1: 'M', 2: 'F'}
sex = sexes[subject_info.get('sex', 0)]
# determine the age of the participant
age = subject_info.get('birthday', None)
meas_date = raw.info.get('meas_date', None)
if isinstance(meas_date, (tuple, list, np.ndarray)):
meas_date = meas_date[0]
if meas_date is not None and age is not None:
bday = datetime(age[0], age[1], age[2])
meas_datetime = datetime.fromtimestamp(meas_date)
subject_age = _age_on_date(bday, meas_datetime)
else:
subject_age = "n/a"
data.update({'age': [subject_age], 'sex': [sex]})
if os.path.exists(fname):
orig_data = _from_tsv(fname)
# whether the new data exists identically in the previous data
exact_included = _contains_row(orig_data,
{'participant_id': subject_id,
'age': subject_age,
'sex': sex})
# whether the subject id is in the previous data
sid_included = subject_id in orig_data['participant_id']
# if the subject data provided is different to the currently existing
# data and overwrite is not True raise an error
if (sid_included and not exact_included) and not overwrite:
raise FileExistsError('"%s" already exists in the participant ' # noqa: E501 F821
'list. Please set overwrite to '
'True.' % subject_id)
# otherwise add the new data
data = _combine(orig_data, data, 'participant_id')
# overwrite is forced to True as all issues with overwrite == False have
# been handled by this point
_write_tsv(fname, data, True, verbose)
return fname
