def test_collecting_feature():
"""Test computation of spectral markers"""
epochs = _get_data()[:2]
psds_params = dict(n_fft=4096, n_overlap=100, n_jobs='auto', nperseg=128)
estimator = PowerSpectralDensityEstimator(tmin=None,
tmax=None,
fmin=1.,
fmax=45.,
psd_method='welch',
psd_params=psds_params,
comment='default')
wpli = WeightedPhaseLagIndex()
markers_list = [
PowerSpectralDensity(estimator=estimator, fmin=1, fmax=4),
ContingentNegativeVariation(), wpli
]
markers = Markers(markers_list)
# check states and names
for name, marker in markers.items():
assert_true(not any(k.endswith('_') for k in vars(marker)))
assert_equal(name, marker._get_title())
# check order
assert_equal(list(markers.values()), markers_list)
# check fit
markers.fit(epochs)
for t_marker in markers_list:
assert_true(any(k.endswith('_') for k in vars(t_marker)))
tmp = _TempDir()
tmp_fname = tmp + '/test-smarkers.hdf5'
markers.save(tmp_fname)
markers2 = read_markers(tmp_fname)
for ((k1, v1), (k2, v2)) in zip(markers.items(), markers2.items()):
assert_equal(k1, k2)
assert_equal(
{
k: v
for k, v in vars(v1).items()
if not k.endswith('_') and not k == 'estimator'
}, {
k: v
for k, v in vars(v2).items()
if not k.endswith('_') and not k == 'estimator'
})
pe = PermutationEntropy().fit(epochs)
markers._add_marker(pe)
tmp = _TempDir()
tmp_fname = tmp + '/test-markers.hdf5'
markers.save(tmp_fname)
markers3 = read_markers(tmp_fname)
assert_true(pe._get_title() in markers3)
assert_true(wpli._get_title() in markers3)
sns.set_color_codes()
def trim_mean80(a, axis=0): # noqa
return trim_mean(a, proportiontocut=.1, axis=axis)
def entropy(a, axis=0): # noqa
return -np.nansum(a * np.log(a), axis=axis) / np.log(a.shape[axis])
fname = 'data/JSXXX-markers.hdf5'
if not op.exists(fname):
raise ValueError('Please run compute_doc_forest_markers.py example first')
fc = read_markers(fname)
##############################################################################
# Set regions of interest
#
# For some markers we do not want to use all channels. We therefore supply
# selections of channels for some markers.
scalp_roi = np.arange(224)
non_scalp = np.arange(224, 256)
cnv_roi = np.array([5, 6, 13, 14, 15, 21, 22])
mmn_roi = np.array([5, 6, 8, 13, 14, 15, 21, 22, 44, 80, 131, 185])
p3b_roi = np.array([8, 44, 80, 99, 100, 109, 118, 127, 128, 131, 185])
p3a_roi = np.array([5, 6, 8, 13, 14, 15, 21, 22, 44, 80, 131, 185])
for k, v in attrs.items():
if k.endswith('_'):
setattr(out, k, v)
return out
# Resgister the marker to NICE
register_marker_class(MyCustomMarker)
# Now you can create a collection with nice markers and the custom marker
markers_list = [
PermutationEntropy(),
ContingentNegativeVariation(),
MyCustomMarker()
]
markers = Markers(markers_list)
# Fit on test data
epochs = _get_data()[:2]
markers.fit(epochs)
# Save to a file
tmp = _TempDir()
tmp_fname = tmp + '/test-markers.hdf5'
markers.save(tmp_fname)
# Read from file
markers2 = read_markers(tmp_fname)
df_data['condition'] = []
for k in markers.keys():
df_data[k] = []
o_path = op.join(db_path, 'results', 'sources')
o_path = op.join(o_path, subject)
with open('../data/rois.json', 'r') as f:
rois = json.load(f)
for condition in conditions:
print('Using condition: {}'.format(condition))
t_path = op.join(o_path, condition)
fc = nice.read_markers(op.join(t_path, 'results-markers.hdf5'))
_samp = fc['nice/marker/SymbolicMutualInformation/theta_weighted']
labels = _samp.ch_info_['ch_names']
rois_idx = OrderedDict()
for roi, ch_names in rois.items():
t_elems = np.array([labels.index(x) for x in ch_names])
rois_idx[roi] = t_elems
n_rois = len(rois_idx)
rois_names = list(rois_idx.keys())
for i in range(n_rois):
i_roi = rois_names[i]
i_idx = rois_idx[i_roi]
for j in range(i, n_rois):
j_roi = rois_names[j]
j_idx = rois_idx[j_roi]