def test_SSVEP_paradigm(self):
paradigm = SSVEP(n_classes=None)
dataset = FakeDataset(event_list=["13", "15", "17", "19"],
paradigm="ssvep")
X, labels, metadata = paradigm.get_data(dataset, subjects=[1])
# Verify that they have the same length
self.assertEqual(len(X), len(labels), len(metadata))
# X must be a 3D array
self.assertEqual(len(X.shape), 3)
# labels must contain 4 values, defined in the dataset
self.assertEqual(len(np.unique(labels)), 4)
# metadata must have subjets, sessions, runs
self.assertTrue("subject" in metadata.columns)
self.assertTrue("session" in metadata.columns)
self.assertTrue("run" in metadata.columns)
# Only one subject in the metadata
self.assertEqual(np.unique(metadata.subject), 1)
# We should have two sessions in the metadata
self.assertEqual(len(np.unique(metadata.session)), 2)
# should return epochs
epochs, _, _ = paradigm.get_data(dataset,
subjects=[1],
return_epochs=True)
self.assertIsInstance(epochs, BaseEpochs)
def test_SSVEP_singlepass(self):
# Accept only single pass filter
paradigm = SSVEP(fmin=2, fmax=25)
dataset = FakeDataset(paradigm='ssvep')
X, labels, metadata = paradigm.get_data(dataset, subjects=[1])
# Verify that they have the same length
self.assertEqual(len(X), len(labels), len(metadata))
# X must be a 3D array
self.assertEqual(len(X.shape), 3)
# labels must contain 2 values, as n_classes = 2 by default
self.assertEqual(len(np.unique(labels)), 2)
def test_SSVEP_singlepass(self):
# Accept only single pass filter
paradigm = SSVEP(fmin=2, fmax=25)
dataset = FakeDataset(paradigm="ssvep")
X, labels, metadata = paradigm.get_data(dataset, subjects=[1])
# Verify that they have the same length
self.assertEqual(len(X), len(labels), len(metadata))
# X must be a 3D array
self.assertEqual(len(X.shape), 3)
# labels must contain all 3 classes of dataset,
# as n_classes is "None" by default (taking all classes)
self.assertEqual(len(np.unique(labels)), 3)
# should return epochs
epochs, _, _ = paradigm.get_data(dataset, subjects=[1], return_epochs=True)
self.assertIsInstance(epochs, BaseEpochs)
def test_SSVEP_paradigm(self):
paradigm = SSVEP(n_classes=None)
dataset = FakeDataset(event_list=['13', '15', '17', '19'],
paradigm='ssvep')
X, labels, metadata = paradigm.get_data(dataset, subjects=[1])
# Verify that they have the same length
self.assertEqual(len(X), len(labels), len(metadata))
# X must be a 3D array
self.assertEqual(len(X.shape), 3)
# labels must contain 4 values, defined in the dataset
self.assertEqual(len(np.unique(labels)), 4)
# metadata must have subjets, sessions, runs
self.assertTrue('subject' in metadata.columns)
self.assertTrue('session' in metadata.columns)
self.assertTrue('run' in metadata.columns)
# Only one subject in the metadata
self.assertEqual(np.unique(metadata.subject), 1)
# We should have two sessions in the metadata
self.assertEqual(len(np.unique(metadata.session)), 2)
#
# Load 2 subjects of MAMEM3 dataset, with 3 session each
subj = [1, 3]
dataset = MAMEM3()
dataset.subject_list = subj
###############################################################################
# Choose paradigm
# ---------------
#
# We select the paradigm SSVEP, applying a bandpass filter (3-15 Hz) on
# the data and we keep only the first 3 classes, that is stimulation
# frequency of 6.66, 7.50 and 8.57 Hz.
paradigm = SSVEP(fmin=3, fmax=15, n_classes=3)
##############################################################################
# Create pipelines
# ----------------
#
# Use a Canonical Correlation Analysis classifier
interval = dataset.interval
freqs = paradigm.used_events(dataset)
pipeline = {}
pipeline["CCA"] = make_pipeline(SSVEP_CCA(interval=interval, freqs=freqs, n_harmonics=3))
##############################################################################
# Get data (optional)
interval = dataset.interval ############################################################################### # Choose Paradigm # --------------- # # We define the paradigms (SSVEP, SSSVEP_TRCA and FilterBankSSVEP) and use the dataset # SSVEPExo. The SSVEP paradigm applied a bandpass filter (10-25 Hz) on # the data, SSVEP_TRCA applied a bandpass filter (1-110 Hz) which correspond to almost # no filtering, while the FilterBankSSVEP paradigm uses as many bandpass filters as # there are stimulation frequencies (here 2). For each stimulation frequency # the EEG is filtered with a 1 Hz-wide bandpass filter centered on the # frequency. This results in ``n_classes`` copies of the signal, filtered for each # class, as used in the filterbank motor imagery paradigms. paradigm = SSVEP(fmin=10, fmax=25, n_classes=3) paradigm_TRCA = SSVEP(fmin=1, fmax=110, n_classes=3) paradigm_fb = FilterBankSSVEP(filters=None, n_classes=3) ############################################################################### # Classes are defined by the frequency of the stimulation, here we use # the first two frequencies of the dataset, 13 and 17 Hz. # The evaluation function uses a LabelEncoder, transforming them # to 0 and 1 freqs = paradigm.used_events(dataset) ############################################################################## # Create Pipelines # ---------------- #
for s in subj:
for d in [MAMEM1(), MAMEM2(), MAMEM3()]:
d._get_single_subject_data(s)
datasets = [MAMEM1(), MAMEM2(), MAMEM3()]
for d in datasets:
d.subject_list = subj
###############################################################################
# Choose paradigm
# ---------------
#
# We select the paradigm SSVEP, applying a bandpass filter (3-15 Hz) on
# the data and we keep all the 5 classes, that is stimulation
# frequency of 6.66, 7.50 and 8.57, 10 and 12 Hz.
paradigm = SSVEP(fmin=3, fmax=15, n_classes=None)
##############################################################################
# Create pipelines
# ----------------
#
# Use a Canonical Correlation Analysis classifier
interval = datasets[0].interval
freqs = paradigm.used_events(datasets[0])
pipeline = {}
pipeline["CCA"] = make_pipeline(
SSVEP_CCA(interval=interval, freqs=freqs, n_harmonics=3))
##############################################################################
def test_SSVEP_noevent(self):
# Assert error if events from paradigm and dataset dont overlap
paradigm = SSVEP(events=["11", "12"], n_classes=2)
dataset = FakeDataset(event_list=["13", "14"], paradigm="ssvep")
self.assertRaises(AssertionError, paradigm.get_data, dataset)
def test_SSVEP_noevent(self):
# Assert error if events from paradigm and dataset dont overlap
paradigm = SSVEP(events=['11', '12'], n_classes=2)
dataset = FakeDataset(event_list=['13', '14'], paradigm='ssvep')
self.assertRaises(AssertionError, paradigm.get_data, dataset)
subj = [1, 3]
for s in subj:
MAMEM1()._get_single_subject_data(s)
dataset = MAMEM1()
dataset.subject_list = subj
###############################################################################
# Choose paradigm
# ---------------
#
# We select the paradigm SSVEP, applying a bandpass filter (3-15 Hz) on
# the data and we keep only the first 3 classes, that is stimulation
# frequency of 6.66, 7.50 and 8.57 Hz.
paradigm = SSVEP(fmin=3, fmax=15, n_classes=3)
##############################################################################
# Create pipelines
# ----------------
#
# Use a Canonical Correlation Analysis classifier
interval = dataset.interval
freqs = paradigm.used_events(dataset)
pipeline = {}
pipeline["CCA"] = make_pipeline(
SSVEP_CCA(interval=interval, freqs=freqs, n_harmonics=3))
##############################################################################
