def test_dataset_search_fun(self):
print([
type(i).__name__
for i in utils.dataset_search('imagery', multi_session=True)
])
print([
type(i).__name__
for i in utils.dataset_search('imagery', multi_session=False)
])
l = utils.dataset_search(
'imagery',
events=['right_hand', 'left_hand', 'feet', 'tongue', 'rest'])
for out in l:
print('multiclass: {}'.format(out.selected_events))
l = utils.dataset_search('imagery',
events=['right_hand', 'feet'],
has_all_events=True)
for out in l:
print('rh/f: {}, {}'.format(
type(out).__name__, out.selected_events))
l = utils.dataset_search(
'imagery',
events=['right_hand', 'left_hand', 'feet', 'tongue', 'rest'],
total_classes=2)
for out in l:
print('two class: {}'.format(out.selected_events))
def test_dataset_channel_search(self):
chans = ['C3', 'Cz']
All = utils.dataset_search('imagery', events=[
'right_hand', 'left_hand', 'feet', 'tongue', 'rest'])
has_chans = utils.dataset_search('imagery', events=[
'right_hand', 'left_hand', 'feet', 'tongue', 'rest'],
channels=chans)
has_types = set([type(x) for x in has_chans])
for d in has_chans:
s1 = d.get_data([1], False)[0][0][0]
self.assertTrue(set(chans) <= set(s1.info['ch_names']))
for d in All:
if type(d) not in has_types:
s1 = d.get_data([1], False)[0][0][0]
self.assertFalse(set(chans) <= set(s1.info['ch_names']))
def test_dataset_search_fun(self):
found = utils.dataset_search("imagery", multi_session=True)
print([type(dataset).__name__ for dataset in found])
found = utils.dataset_search("imagery", multi_session=False)
print([type(dataset).__name__ for dataset in found])
res = utils.dataset_search(
"imagery", events=["right_hand", "left_hand", "feet", "tongue", "rest"]
)
for out in res:
print("multiclass: {}".format(out.event_id.keys()))
res = utils.dataset_search(
"imagery", events=["right_hand", "feet"], has_all_events=True
)
for out in res:
self.assertTrue(set(["right_hand", "feet"]) <= set(out.event_id.keys()))
def datasets(self):
if self.tmax is None:
interval = None
else:
interval = self.tmax - self.tmin
return utils.dataset_search(
paradigm="p300", events=self.events, interval=interval, has_all_events=True
)
def datasets(self):
if self.tmax is None:
interval = None
else:
interval = self.tmax - self.tmin
return utils.dataset_search(paradigm='imagery',
events=self.events,
interval=interval,
has_all_events=False)
def datasets(self):
if self.tmax is None:
interval = None
else:
interval = self.tmax - self.tmin
return utils.dataset_search(paradigm='ssvep',
events=self.events,
total_classes=self.n_classes,
interval=interval,
has_all_events=False)
def test_dataset_search_fun(self):
print([
type(i).__name__
for i in utils.dataset_search('imagery', multi_session=True)
])
print([
type(i).__name__
for i in utils.dataset_search('imagery', multi_session=False)
])
res = utils.dataset_search(
'imagery',
events=['right_hand', 'left_hand', 'feet', 'tongue', 'rest'])
for out in res:
print('multiclass: {}'.format(out.event_id.keys()))
res = utils.dataset_search('imagery',
events=['right_hand', 'feet'],
has_all_events=True)
for out in res:
self.assertTrue(
set(['right_hand', 'feet']) <= set(out.event_id.keys()))
def test_dataset_channel_search(self):
chans = ["C3", "Cz"]
All = utils.dataset_search(
"imagery", events=["right_hand", "left_hand", "feet", "tongue", "rest"]
)
has_chans = utils.dataset_search(
"imagery",
events=["right_hand", "left_hand", "feet", "tongue", "rest"],
channels=chans,
)
has_types = set([type(x) for x in has_chans])
for d in has_chans:
s1 = d.get_data([1])[1]
sess1 = s1[list(s1.keys())[0]]
raw = sess1[list(sess1.keys())[0]]
self.assertTrue(set(chans) <= set(raw.info["ch_names"]))
for d in All:
if type(d) not in has_types:
s1 = d.get_data([1])[1]
sess1 = s1[list(s1.keys())[0]]
raw = sess1[list(sess1.keys())[0]]
self.assertFalse(set(chans) <= set(raw.info["ch_names"]))
pipe = make_pipeline(LogVariance(), clf) pipelines["AM+SVM"] = pipe ############################################################################## # Datasets # ----------------- # # Datasets can be specified in many ways: Each paradigm has a property # 'datasets' which returns the datasets that are appropriate for that paradigm print(LeftRightImagery().datasets) ########################################################################## # Or you can run a search through the available datasets: print(utils.dataset_search(paradigm="imagery", min_subjects=6)) ########################################################################## # Or you can simply make your own list (which we do here due to computational # constraints) dataset = BNCI2014001() dataset.subject_list = dataset.subject_list[:2] datasets = [dataset] ########################################################################## # Paradigm # -------------------- # # Paradigms define the events, epoch time, bandpass, and other preprocessing # parameters. They have defaults that you can read in the documentation, or you
pipelines['AM + SVM'] = pipe ############################################################################## # Datasets # ----------------- # # Datasets can be specified in many ways: Each paradigm has a property # 'datasets' which returns the datasets that are appropriate for that paradigm print(LeftRightImagery().datasets) ########################################################################## # Or you can run a search through the available datasets: print(utils.dataset_search(paradigm='imagery', total_classes=2)) ########################################################################## # Or you can simply make your own list (which we do here due to computational # constraints) datasets = [BNCI2014001()] ########################################################################## # Paradigm # -------------------- # # Paradigms define the events, epoch time, bandpass, and other preprocessing # parameters. They have defaults that you can read in the documentation, or you # can simply set them as we do here. A single paradigm defines a method for # going from continuous data to trial data of a fixed size. To learn more look
def datasets(self):
return utils.dataset_search(paradigm='imagery',
events=self.events,
has_all_events=True)
def datasets(self):
return utils.dataset_search(paradigm='imagery',
events=['right_hand', 'left_hand'],
has_all_events=True)
def datasets(self):
return utils.dataset_search(paradigm='imagery',
total_classes=self.n_classes,
has_all_events=True)
def datasets(self):
return utils.dataset_search(paradigm='imagery')
from collections import OrderedDict
from moabb.datasets import utils
from moabb.analysis import analyze
import mne
mne.set_log_level(False)
import logging
import coloredlogs
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger()
coloredlogs.install(level=logging.DEBUG)
datasets = utils.dataset_search('imagery',
events=['supination', 'hand_close'],
has_all_events=False,
min_subjects=2,
multi_session=False)
for d in datasets:
d.subject_list = d.subject_list[:10]
paradigm = ImageryNClass(2)
context = WithinSessionEvaluation(paradigm=paradigm,
datasets=datasets,
random_state=42)
pipelines = OrderedDict()
pipelines['av+TS'] = make_pipeline(Covariances(estimator='oas'),
TSclassifier())
pipelines['av+CSP+LDA'] = make_pipeline(Covariances(estimator='oas'), CSP(8),