def load_raw_data(self, subject, series):
"""Load data for a subject / series."""
test = series == TEST_SERIES
if not test:
fnames = [
glob('../data/train/subj%d_series%d_data.csv' % (subject, i))
for i in series
]
else:
fnames = [
glob('../data/test/subj%d_series%d_data.csv' % (subject, i))
for i in series
]
fnames = list(np.concatenate(fnames))
fnames.sort()
raw_train = [
creat_mne_raw_object(fname, read_events=not test)
for fname in fnames
]
raw_train = concatenate_raws(raw_train)
# pick eeg signal
picks = pick_types(raw_train.info, eeg=True)
self.data = raw_train._data[picks].transpose()
self.data = preprocessData(self.data)
if not test:
self.events = raw_train._data[32:].transpose()
def load_raw_data(self, subject, series):
"""Load data for a subject / series."""
# test = series == TEST_SERIES
test = False
if not test:
fnames = [glob(get_horizo_path(subject, i)) for i in series]
else:
fnames = [
glob('../data/test/subj%d_series%d_data.csv' % (subject, i))
for i in series
]
fnames = list(np.concatenate(fnames))
fnames.sort()
self.fnames = fnames
action_1D_type = 'HO'
raw_train = [
creat_mne_raw_object(fnames[i], i, read_events=action_1D_type)
for i in range(len(fnames))
]
raw_train = concatenate_raws(raw_train)
# pick eeg signal
picks = pick_types(raw_train.info, eeg=True)
self.data = raw_train._data[picks].transpose()
self.data = preprocessData(self.data)
if not test:
self.events = raw_train._data[14:].transpose()
def load_raw_data(self, subject, series):
"""
Load data for a subject / series.
n_points: int. The number of timepoints that can be predict/train.
Because the timepoints in the start are not valid for windows or there are no velocity.
"""
# test = series == TEST_SERIES
test = False
if not test:
fnames = [glob(get_horizo_path(subject, i)) for i in series]
else:
fnames = [glob('../data/test/subj%d_series%d_data.csv' %
(subject, i)) for i in series]
fnames = list(np.concatenate(fnames))
fnames.sort()
self.fnames = fnames
action_1D_type = 'HO'
raw_train = [creat_mne_raw_object(fnames[i], i, read_events=action_1D_type)
for i in range(len(fnames))]
raw_train = concatenate_raws(raw_train)
# pick eeg signal
picks = pick_types(raw_train.info, eeg=True)
self.data = raw_train._data[picks].transpose()
self.data = preprocessData(self.data)
self.n_points = self.data.shape[0] - START_TRAIN
if not test:
self.events = raw_train._data[14:].transpose()
def load_raw_data(self, subject, series):
"""Load data for a subject / series."""
test = series == TEST_SERIES
if not test:
fnames = [glob('../data/train/subj%d_series%d_data.csv' %
(subject, i)) for i in series]
else:
fnames = [glob('../data/test/subj%d_series%d_data.csv' %
(subject, i)) for i in series]
fnames = list(np.concatenate(fnames))
fnames.sort()
raw_train = [creat_mne_raw_object(fname, read_events=not test)
for fname in fnames]
raw_train = concatenate_raws(raw_train)
# pick eeg signal
picks = pick_types(raw_train.info, eeg=True)
self.data = raw_train._data[picks].transpose()
self.data = preprocessData(self.data)
if not test:
self.events = raw_train._data[32:].transpose()
series_test_tot = []
# #### generate predictions #####
for subject in subjects:
print 'Loading data for subject %d...' % subject
# ############### READ DATA ###############################################
# fnames = glob('data/train/subj%d_series*_data.csv' % (subject))
fnames = glob(get_all_horizon_path_from_the_subject(subject))
fnames.sort()
fnames_val = fnames[-1:]
# fnames_test = glob('data/test/subj%d_series*_data.csv' % (subject))
# fnames_test.sort()
action_1D_type = 'HO'
raw_val = concatenate_raws([creat_mne_raw_object(fnames[i], i, read_events=action_1D_type) for i in range(len(fnames_val))])
# raw_test = concatenate_raws([creat_mne_raw_object(fname, read_events=False) for fname in fnames_test])
# extract labels for series 7&8
labels = raw_val._data[len(CH_NAMES):]
lbls_tot.append(labels.transpose())
# aggregate infos for validation (series 7&8)
raw_series5 = creat_mne_raw_object(fnames_val[0], 4, action_1D_type)
series = np.array([5] * raw_series5.n_times)
series_val_tot.append(series)
subjs = np.array([subject]*labels.shape[1])
subjects_val_tot.append(subjs)
# aggregate infos for test (series 9&10)
ids_tot = []
subjects_test_tot = []
series_test_tot = []
# #### generate predictions #####
for subject in subjects:
print 'Loading data for subject %d...' % subject
# ############### READ DATA ###############################################
fnames = glob('data/train/subj%d_series*_data.csv' % (subject))
fnames.sort()
fnames_val = fnames[-2:]
fnames_test = glob('data/test/subj%d_series*_data.csv' % (subject))
fnames_test.sort()
raw_val = concatenate_raws([creat_mne_raw_object(fname, read_events=True)
for fname in fnames_val])
raw_test = concatenate_raws([creat_mne_raw_object(fname, read_events=False)
for fname in fnames_test])
# extract labels for series 7&8
labels = raw_val._data[32:]
lbls_tot.append(labels.transpose())
# aggregate infos for validation (series 7&8)
raw_series7 = creat_mne_raw_object(fnames_val[0])
raw_series8 = creat_mne_raw_object(fnames_val[1])
series = np.array([7] * raw_series7.n_times +
[8] * raw_series8.n_times)
series_val_tot.append(series)
subjects_test_tot = []
series_test_tot = []
# #### generate predictions #####
for subject in subjects:
print('Loading data for subject %d...' % subject)
# ############### READ DATA ###############################################
fnames = glob('data/train/subj%d_series*_data.csv' % (subject))
fnames.sort()
fnames_val = fnames[-2:]
fnames_test = glob('data/test/subj%d_series*_data.csv' % (subject))
fnames_test.sort()
raw_val = concatenate_raws([
creat_mne_raw_object(fname, read_events=True) for fname in fnames_val
])
raw_test = concatenate_raws([
creat_mne_raw_object(fname, read_events=False) for fname in fnames_test
])
# extract labels for series 7&8
labels = raw_val._data[32:]
lbls_tot.append(labels.transpose())
# aggregate infos for validation (series 7&8)
raw_series7 = creat_mne_raw_object(fnames_val[0])
raw_series8 = creat_mne_raw_object(fnames_val[1])
series = np.array([7] * raw_series7.n_times + [8] * raw_series8.n_times)
series_val_tot.append(series)
ids_tot = []
subjects_test_tot = []
series_test_tot = []
# #### generate predictions #####
for subject in subjects:
print "Loading data for subject %d..." % subject
# ############### READ DATA ###############################################
fnames = glob("data/train/subj%d_series*_data.csv" % (subject))
fnames.sort()
fnames_val = fnames[-2:]
fnames_test = glob("data/test/subj%d_series*_data.csv" % (subject))
fnames_test.sort()
raw_val = concatenate_raws([creat_mne_raw_object(fname, read_events=True) for fname in fnames_val])
raw_test = concatenate_raws([creat_mne_raw_object(fname, read_events=False) for fname in fnames_test])
# extract labels for series 7&8
labels = raw_val._data[32:]
lbls_tot.append(labels.transpose())
# aggregate infos for validation (series 7&8)
raw_series7 = creat_mne_raw_object(fnames_val[0])
raw_series8 = creat_mne_raw_object(fnames_val[1])
series = np.array([7] * raw_series7.n_times + [8] * raw_series8.n_times)
series_val_tot.append(series)
subjs = np.array([subject] * labels.shape[1])
subjects_val_tot.append(subjs)
