def test_scaler():
"""Test methods of Scaler."""
raw = io.read_raw_fif(raw_fname)
events = read_events(event_name)
picks = pick_types(raw.info, meg=True, stim=False, ecg=False,
eog=False, exclude='bads')
picks = picks[1:13:3]
epochs = Epochs(raw, events, event_id, tmin, tmax, picks=picks,
baseline=(None, 0), preload=True)
epochs_data = epochs.get_data()
scaler = Scaler(epochs.info)
y = epochs.events[:, -1]
X = scaler.fit_transform(epochs_data, y)
assert_true(X.shape == epochs_data.shape)
X2 = scaler.fit(epochs_data, y).transform(epochs_data)
assert_array_equal(X2, X)
# these should be across time
assert_allclose(X.std(axis=-2), 1.)
assert_allclose(X.mean(axis=-2), 0., atol=1e-12)
# Test inverse_transform
Xi = scaler.inverse_transform(X, y)
assert_array_almost_equal(epochs_data, Xi)
for kwargs in [{'with_mean': False}, {'with_std': False}]:
scaler = Scaler(epochs.info, **kwargs)
scaler.fit(epochs_data, y)
assert_array_almost_equal(
X, scaler.inverse_transform(scaler.transform(X)))
# Test init exception
assert_raises(ValueError, scaler.fit, epochs, y)
assert_raises(ValueError, scaler.transform, epochs, y)
def test_scaler():
"""Test methods of Scaler."""
raw = io.read_raw_fif(raw_fname)
events = read_events(event_name)
picks = pick_types(raw.info, meg=True, stim=False, ecg=False,
eog=False, exclude='bads')
picks = picks[1:13:3]
epochs = Epochs(raw, events, event_id, tmin, tmax, picks=picks,
baseline=(None, 0), preload=True)
epochs_data = epochs.get_data()
scaler = Scaler(epochs.info)
y = epochs.events[:, -1]
# np invalid divide value warnings
with warnings.catch_warnings(record=True):
X = scaler.fit_transform(epochs_data, y)
assert_true(X.shape == epochs_data.shape)
X2 = scaler.fit(epochs_data, y).transform(epochs_data)
assert_array_equal(X2, X)
# Test inverse_transform
with warnings.catch_warnings(record=True): # invalid value in mult
Xi = scaler.inverse_transform(X, y)
assert_array_almost_equal(epochs_data, Xi)
for kwargs in [{'with_mean': False}, {'with_std': False}]:
scaler = Scaler(epochs.info, **kwargs)
scaler.fit(epochs_data, y)
assert_array_almost_equal(
X, scaler.inverse_transform(scaler.transform(X)))
# Test init exception
assert_raises(ValueError, scaler.fit, epochs, y)
assert_raises(ValueError, scaler.transform, epochs, y)
def raw_to_data(raw_edf, training=True, drop_rejects=True, subj=None):
tmin, tmax = 0, 4.
stim_code = dict([(32766,1),(769,2), (770,3), (771,4), (772,5),(783,6),(276,7),(277,8),(768,9),
(1023,10),(1072,11)])
if training:
path = op.join('data_i2r', 'BCI_IV_2a', 'TrainingSet')
if not training:
path = op.join('data_i2r', 'BCI_IV_2a', 'TestingSet')
label_path = op.join('data_i2r', 'BCI_IV_2a', 'true_labels')
label_files_list = glob.glob(label_path + '/*E.mat')
label_subj = [ int(f.split('A0')[1][0]) for f in label_files_list ]
file_list = glob.glob(path + '/*.gdf')
subjects = [ int(f.split('A0')[1][0]) for f in file_list ]
if not training:
label_subj = [ np.argwhere(np.array(label_subj)==subjects[i])[0][0]
for i in range(len(subjects))]
event_id = dict()
events_from_edf = []
sampling_frequency = raw_edf._raw_extras[0]['max_samp']
original_event = raw_edf.find_edf_events()
annot_list = list(zip(original_event[1], original_event[4], original_event[2]))
# Remove rejected trials from events
if drop_rejects:
annot_list = pd.DataFrame(annot_list)
rejected = annot_list[0].isin(annot_list[annot_list[2] == 1023][0])
accepted_trials_index = [True] * 288
ind=-1
for row in annot_list.itertuples():
if row[3] == 1023:
rejected.loc[row[0]+1] = True
accepted_trials_index[ind] = False
if row[3] == 768:
ind = ind + 1
annot_list = annot_list[~rejected]
annot_list = list(zip(annot_list[0], annot_list[1], annot_list[2]))
events_from_edf.extend(annot_list)
events_from_edf = np.array(events_from_edf)
events_arr = np.zeros(events_from_edf.shape, dtype=int)
for (i, i_event) in enumerate(events_from_edf):
index = int((float(i_event[0])) * sampling_frequency)
events_arr[i,:] = index,0,stim_code[int(i_event[2])]
i=i+1
# strip channel names of "." characters
raw_edf.rename_channels(lambda x: x.strip('.'))
#create Event dictionary based on File
events_in_edf = [event[2] for event in events_arr[:]]
if(events_in_edf.__contains__(2)):
event_id['LEFT_HAND'] = 2
if (events_in_edf.__contains__(3)):
event_id['RIGHT_HAND'] = 3
if (events_in_edf.__contains__(4)):
event_id['FEET'] = 4
if (events_in_edf.__contains__(5)):
event_id['TONGUE'] = 5
if (events_in_edf.__contains__(6)):
event_id['CUE_UNKNOWN'] = 6
# Read epochs (train will be done only between -0.5 and 4s)
# Testing will be done with a running classifier
# raw_edf.filter(0., 40., fir_design='firwin', skip_by_annotation='edge') # 4-40Hz
picks = pick_types(raw_edf.info, meg=False, eeg=True,
stim=False, eog=False, exclude='bads')
epochs = Epochs(raw_edf, events_arr, event_id, tmin, tmax, proj=True, picks=picks,
baseline=None, preload=True)
y = epochs.events[:, 2] - 2
filter_data = []
#filter_bank = [(4.,40.)]
filter_bank = [(4.,8.),(8.,12.),(12.,16.),(16.,20.),(20.,24.),(24.,28.),(28.,32.),(32.,36.),(36.,40)]
for _filter in filter_bank:
#filter_data.append(np.abs(signal.hilbert(epochs.copy().filter(_filter[0], _filter[1], fir_design='firwin').get_data())))
filter_data.append(epochs.copy().filter(_filter[0], _filter[1], fir_design='firwin').get_data())
filter_data = np.array(filter_data)
if training:
oScaler = Scaler(scalings='mean').fit(filter_data.flatten().reshape(-1,1))
#oScaler = MinMaxScaler(copy=True, feature_range=(-1, 1)).fit(filter_data.flatten().reshape(-1,1))
pk.dump(oScaler,open("./fb/subject{}_filter_oscaler.pk".format(subjects[subj]),'wb'))
else:
oScaler = pk.load(open("./fb/subject{}_filter_oscaler.pk".format(subjects[subj]),'rb'))
shape = filter_data.shape
filter_data = oScaler.transform(filter_data.flatten().reshape(-1,1))
filter_data = filter_data.reshape(shape)
filter_data = filter_data.transpose(1,3,2,0) # 273, 1001, 22, 10
# Augment and reshape data into image
filter_data = filter_data.transpose(2,0,1,3) # 22, 273, 1001, 10
filter_data = np.split(filter_data,[1,6,13,18,21])
empty_ch = np.zeros(filter_data[0].shape)
filter_data = np.vstack([empty_ch,empty_ch,empty_ch,filter_data[0],empty_ch,empty_ch,empty_ch,
empty_ch,filter_data[1],empty_ch,
filter_data[2],
empty_ch,filter_data[3],empty_ch,
empty_ch,empty_ch,filter_data[4],empty_ch,empty_ch,
empty_ch,empty_ch,empty_ch,filter_data[5],empty_ch,empty_ch,empty_ch])
filter_data = filter_data.transpose(1,2,0,3) # 273, 1001, 42, 10
filter_data = filter_data.reshape(filter_data.shape[0],filter_data.shape[1],6,7,filter_data.shape[3]) # 273, 1001, 6, 7, 10
if training:
return filter_data, y
else:
y = sio.loadmat(label_files_list[label_subj[subj]])['classlabel'].flatten()
y = np.array([ i - 1 for i in y ])
if drop_rejects:
y_drop = [ i for i in range(288) if not accepted_trials_index[i] ]
y = np.delete(y, y_drop, None)
return filter_data, y
def decoding_withKfold(X, Y_speech, Y_lips, n_fold, train_index, test_index,
examples, feature):
predictions_speech = np.zeros((Y_speech.shape))
speech = np.zeros((Y_speech.shape))
predictions_lips = np.zeros((Y_lips.shape))
lips = np.zeros((Y_lips.shape))
scores_speech = np.zeros((n_fold, ))
for k in range(0, n_fold):
eegScaler = MultiChannelScaler(scalings='mean')
speechScaler = MultiChannelScaler(scalings='mean')
lipsScaler = MultiChannelScaler(scalings='mean')
speechModel = LReg()
lipsModel = LReg()
#####COPY X AND Y VARIABLES
X_standard = np.zeros((X.shape))
Y_lips_standard = np.zeros((Y_lips.shape))
Y_speech_standard = np.zeros((Y_speech.shape))
# standardazing data
X_standard[train_index[k], :, :] = eegScaler.fit_transform(
X[train_index[k], :, :])
X_standard[test_index[k], :, :] = eegScaler.transform(
X[test_index[k], :, :])
Y_lips_standard[train_index[k], :] = lipsScaler.fit_transform(
Y_lips[train_index[k], :]).squeeze()
Y_lips_standard[test_index[k], :] = lipsScaler.transform(
Y_lips[test_index[k], :]).squeeze()
Y_speech_standard[train_index[k], :] = speechScaler.fit_transform(
Y_speech[train_index[k], :]).squeeze()
Y_speech_standard[test_index[k], :] = speechScaler.transform(
Y_speech[test_index[k], :]).squeeze()
X_TRAIN = X_standard[train_index[k], :, :]
X_TEST = X_standard[test_index[k], :, :]
Y_envelope_sp_TRAIN = Y_speech_standard[train_index[k], :]
Y_envelope_sp_TEST = Y_speech_standard[test_index[k], :]
Y_lips_ap_TRAIN = Y_lips_standard[train_index[k], :]
Y_lips_ap_TEST = Y_lips_standard[test_index[k], :]
#X_train and test now are (#trials,#channnels,#timepoints)
n_trial = X_TRAIN.shape[0]
n_trial_test = X_TEST.shape[0]
n_ch = X_TRAIN.shape[1]
trial_length = X_TRAIN.shape[2]
if examples == 'are_Trials':
X_TRAIN_tmp = np.zeros((X_TRAIN.shape[0], n_ch * trial_length))
X_TEST_tmp = np.zeros((X_TEST.shape[0], n_ch * trial_length))
for i in range(0, n_ch):
X_TRAIN_tmp[:, i * trial_length:(i + 1) *
trial_length] = X_TRAIN[:, i, :]
X_TEST_tmp[:, i * trial_length:(i + 1) *
trial_length] = X_TEST[:, i, :]
X_TRAIN = X_TRAIN_tmp
X_TEST = X_TEST_tmp
elif examples == 'are_Time':
X_TRAIN_tmp = np.zeros((n_trial * trial_length, n_ch))
X_TEST_tmp = np.zeros((n_trial_test * trial_length, n_ch))
Y_envelope_sp_TRAIN_tmp = np.zeros((n_trial * trial_length, ))
Y_envelope_sp_TEST_tmp = np.zeros((n_trial_test * trial_length, ))
Y_lips_ap_TRAIN_tmp = np.zeros((n_trial * trial_length, ))
Y_lips_ap_TEST_tmp = np.zeros((n_trial_test * trial_length, ))
for i in range(0, n_trial):
X_TRAIN_tmp[i * trial_length:(i + 1) *
trial_length, :] = X_TRAIN[i, :, :].T
Y_envelope_sp_TRAIN_tmp[i * trial_length:(i + 1) *
trial_length] = Y_envelope_sp_TRAIN[
i, :]
Y_lips_ap_TRAIN_tmp[i * trial_length:(i + 1) *
trial_length] = Y_lips_ap_TRAIN[i, :]
if i < X_TEST.shape[0]: #test trials are less than train
X_TEST_tmp[i * trial_length:(i + 1) *
trial_length, :] = X_TEST[i, :, :].T
Y_envelope_sp_TEST_tmp[i * trial_length:(i + 1) *
trial_length] = Y_envelope_sp_TEST[
i, :]
Y_lips_ap_TEST_tmp[i * trial_length:(i + 1) *
trial_length] = Y_lips_ap_TEST[i, :]
X_TRAIN = X_TRAIN_tmp
X_TEST = X_TEST_tmp
Y_envelope_sp_TRAIN = Y_envelope_sp_TRAIN_tmp
Y_envelope_sp_TEST = Y_envelope_sp_TEST_tmp
Y_lips_ap_TRAIN = Y_lips_ap_TRAIN_tmp
Y_lips_ap_TEST = Y_lips_ap_TEST_tmp
if feature == 'pca':
[pca, n_comp] = pca_decomposition(X_TRAIN)
X_TRAIN = pca.transform(X_TRAIN)[:, :n_comp]
X_TEST = pca.transform(X_TEST)[:, :n_comp]
if feature == 'Kpca':
[pca, n_comp] = kernel_pca_decomposition(X_TRAIN)
X_TRAIN = pca.transform(X_TRAIN)[:, :n_comp]
X_TEST = pca.transform(X_TEST)[:, :n_comp]
if feature == 'ica':
ICA_decomposition
[ica, selected_comps] = ICA_decomposition(X_TRAIN)
X_TRAIN = ica.transform(X_TRAIN)[:,
selected_comps.astype('int')]
X_TEST = ica.transform(X_TEST)[:, selected_comps.astype('int')]
if feature == 'derivative1':
de1 = np.diff(X_TRAIN, axis=0) / 0.01
de1 = np.concatenate((np.zeros((1, de1.shape[1])), de1),
axis=0)
for i in range(0, de1.shape[0], trial_length):
de1[i, :] = np.zeros((1, de1.shape[1]))
X_TRAIN = np.concatenate((X_TRAIN, de1), 1)
de1 = np.diff(X_TEST, axis=0) / 0.01
de1 = np.concatenate((np.zeros((1, de1.shape[1])), de1),
axis=0)
for i in range(0, de1.shape[0], trial_length):
de1[i, :] = np.zeros((1, de1.shape[1]))
X_TEST = np.concatenate((X_TEST, de1), 1)
if feature == 'derivative2':
de1 = np.diff(X_TRAIN, axis=0) / 0.01
de1 = np.concatenate((np.zeros((1, de1.shape[1])), de1),
axis=0)
for i in range(0, de1.shape[0], trial_length):
de1[i, :] = np.zeros((1, de1.shape[1]))
de2 = np.diff(de1, axis=0)
de2 = np.concatenate((np.zeros((1, de2.shape[1])), de2),
axis=0)
for i in range(0, de2.shape[0], trial_length):
de2[i, :] = np.zeros((1, de2.shape[1]))
de2[i + 1, :] = np.zeros((1, de2.shape[1]))
X_TRAIN = np.concatenate((np.concatenate(
(X_TRAIN, de1), 1), de2), 1)
de1 = np.diff(X_TEST, axis=0) / 0.01
de1 = np.concatenate((np.zeros((1, de1.shape[1])), de1),
axis=0)
for i in range(0, de1.shape[0], trial_length):
de1[i, :] = np.zeros((1, de1.shape[1]))
de2 = np.diff(de1, axis=0)
de2 = np.concatenate((np.zeros((1, de2.shape[1])), de2),
axis=0)
for i in range(0, de2.shape[0], trial_length):
de2[i, :] = np.zeros((1, de2.shape[1]))
de2[i + 1, :] = np.zeros((1, de2.shape[1]))
X_TEST = np.concatenate((np.concatenate(
(X_TEST, de1), 1), de2), 1)
if feature == 'polynomial':
X_TRAIN = np.concatenate((X_TRAIN, np.power(X_TRAIN, 2)), 1)
X_TEST = np.concatenate((X_TEST, np.power(X_TEST, 2)), 1)
# training models and predict
speechModel.fit(X_TRAIN, Y_envelope_sp_TRAIN)
lipsModel.fit(X_TRAIN, Y_lips_ap_TRAIN)
reconstructed_speech = speechModel.predict(X_TEST)
reconstructed_lips = lipsModel.predict(X_TEST)
if examples == 'are_Time':
reconstructed_speech_tmp = np.zeros((n_trial_test, trial_length))
reconstructed_lips_tmp = np.zeros((n_trial_test, trial_length))
Y_envelope_sp_TEST_tmp = np.zeros((n_trial_test, trial_length))
Y_lips_ap_TEST_tmp = np.zeros((n_trial_test, trial_length))
t = 0
for i in range(0, len(reconstructed_speech), trial_length):
reconstructed_speech_tmp[
t, :] = reconstructed_speech[i:i + trial_length]
reconstructed_lips_tmp[t, :] = reconstructed_lips[i:i +
trial_length]
Y_envelope_sp_TEST_tmp[t, :] = Y_envelope_sp_TEST[i:i +
trial_length]
Y_lips_ap_TEST_tmp[t, :] = Y_lips_ap_TEST[i:i + trial_length]
t += 1
reconstructed_speech = reconstructed_speech_tmp
reconstructed_lips = reconstructed_lips_tmp
Y_envelope_sp_TEST = Y_envelope_sp_TEST_tmp
Y_lips_ap_TEST = Y_lips_ap_TEST_tmp
predictions_speech[test_index[k], :] = reconstructed_speech
speech[test_index[k], :] = Y_envelope_sp_TEST
predictions_lips[test_index[k], :] = reconstructed_lips
lips[test_index[k], :] = Y_lips_ap_TEST
# computing scores
speech_score = evaluate(speech.T, predictions_speech.T, 'corrcoeff')
lips_score = evaluate(lips.T, predictions_lips.T, 'corrcoeff')
return speech_score, lips_score, predictions_speech, predictions_lips, speech, lips
def decoding(band,regularization,tmin,tmax,n_fold,subject_name, savepath):
data_path = "./ProcessedData/Final_"
eeg="_processed-epo.fif"
features="_Features-epo.fif"
sfreq=100
n_delays = int((tmax - tmin) * sfreq) + 1
T= [51, 61, 71, 81, 91, 101, 111, 121, 131, 141, 151]
results_speech= np.zeros((len(regularization),len(T)))# each raw is the results' vector for one regularization parameter
results_lips= np.zeros((len(regularization),len(T)))# each raw is the results' vector for one regularization parameter
results_speech_all_sub={}
results_lips_all_sub={}
predictions_lips_all_sub={}
predictions_speech_all_sub={}
for s in subject_name:
print('subject '+str(s))
X_orig = use_FreqBand(mne.read_epochs(data_path+s+eeg),band)
Features_orig = use_FreqBand(mne.read_epochs(data_path + s + features),band)
if band=='original':
X_orig=X_orig.get_data() # 3d array (N_trial, N_channel, N_time)
Y_envelope_sp_orig=Features_orig.get_data()[:,0,:] # 2d array (N_trial, N_time)
Y_lips_ap_orig=Features_orig.get_data()[:,2,:] # 2d array (N_trial, N_time)
else:
X_orig= np.mean(X_orig.data,2) # 3d array (N_trial, N_channel, N_time) #averaging power across frequencies
Y_envelope_sp_orig=np.mean(Features_orig.data[:,0,:,:],1)
Y_lips_ap_orig=np.mean(Features_orig.data[:,2,:,:],1)
time = mne.read_epochs(data_path + s + features).times # 1d array (N_time)
channels = mne.read_epochs(data_path + s + eeg).ch_names
predictions_speech = np.zeros((Y_envelope_sp_orig.shape[0], 200, len(T),len(regularization)))
predictions_lips = np.zeros((Y_lips_ap_orig.shape[0],200,len(T),len(regularization)))
train_index, test_index = k_fold(Y_envelope_sp_orig,n_fold) # define index for train and test for each of the k folds
#data standardizers
eegScaler= Scaler(scalings='mean')
speechScaler= Scaler(scalings='mean')
lipsScaler = Scaler(scalings='mean')
scores_speech = np.zeros((n_fold,))
scores_lips = np.zeros((n_fold,))
coefs_speech = np.zeros((n_fold, X_orig.shape[1], n_delays))
patterns_speech = coefs_speech.copy()
coefs_lips = np.zeros((n_fold, X_orig.shape[1], n_delays))
patterns_lips = coefs_lips.copy()
for i, r in enumerate(regularization):
rf_speech = RField(tmin, tmax, sfreq, feature_names=channels, scoring='r2', patterns=True, estimator=r)
rf_lips = RField(tmin, tmax, sfreq, feature_names=channels, scoring='r2', patterns=True, estimator=r)
print('reg parameter #'+str(i))
for j, t_start in enumerate(T): ##estracting the temporal interval of interest
t_end= t_start+200
X = X_orig[:,:,t_start:t_end] #only the eeg window is shifting
Y_envelope_sp = Y_envelope_sp_orig[:,101:301]
Y_lips_ap = Y_lips_ap_orig[:,101:301]
for k in range(0,n_fold):
#####COPY X AND Y VARIABLES
X_standard=np.zeros((X.shape))
Y_lips_ap_standard=np.zeros((Y_lips_ap.shape))
Y_envelope_sp_standard = np.zeros((Y_envelope_sp.shape))
#standardazing data
X_standard[train_index[k], :, :] = eegScaler.fit_transform(X[train_index[k], :, :])
X_standard[test_index[k], :, :] = eegScaler.transform(X[test_index[k], :, :])
Y_lips_ap_standard[train_index[k], :] = lipsScaler.fit_transform(Y_lips_ap[train_index[k], :])[:,:,0]
Y_lips_ap_standard[test_index[k], :] = lipsScaler.transform(Y_lips_ap[test_index[k], :])[:,:,0]
Y_envelope_sp_standard[train_index[k], :] = speechScaler.fit_transform(Y_envelope_sp[train_index[k], :])[:,:,0]
Y_envelope_sp_standard[test_index[k], :] = speechScaler.transform(Y_envelope_sp[test_index[k], :])[:,:,0]
#shaping data as desired by the decoding model (receptive field function)
X_standard = np.rollaxis(X_standard, 2, 0)
Y_envelope_sp_standard = np.rollaxis(Y_envelope_sp_standard, 1, 0)
Y_lips_ap_standard = np.rollaxis(Y_lips_ap_standard, 1, 0)
X_TRAIN= X_standard[:,train_index[k],:]
X_TEST= X_standard[:,test_index[k],:]
Y_envelope_sp_TRAIN = Y_envelope_sp_standard[:,train_index[k]]
Y_envelope_sp_TEST = Y_envelope_sp_standard[:,test_index[k]]
Y_lips_ap_TRAIN = Y_lips_ap_standard[:,train_index[k]]
Y_lips_ap_TEST = Y_lips_ap_standard[:,test_index[k]]
#training models and predict
rf_speech.fit(X_TRAIN,Y_envelope_sp_TRAIN)
rf_lips.fit(X_TRAIN,Y_lips_ap_TRAIN)
reconstructed_speech = rf_speech.predict(X_TEST)
reconstructed_lips = rf_lips.predict(X_TEST)
predictions_speech[test_index[k],:,j,i]=reconstructed_speech.T
predictions_lips[test_index[k],:,j,i]=reconstructed_lips.T
#computing scores
tmp_score_speech=0
tmp_score_lips = 0
for n, rec in enumerate(reconstructed_speech[:,:,0].T):
tmp_score_speech = tmp_score_speech + mean_squared_error(Y_envelope_sp_TEST[:,n]/max(abs(Y_envelope_sp_TEST[:,n])), rec/max(abs(rec)))
scores_speech[k]= tmp_score_speech/(n+1)
for n, rec in enumerate(reconstructed_lips[:,:,0].T):
tmp_score_lips = tmp_score_lips + mean_squared_error(Y_lips_ap_TEST[:, n]/max(abs(Y_lips_ap_TEST[:, n])), rec/max(abs(rec)))
scores_lips[k] = tmp_score_lips / (n+1)
# scores_speech[k] = rf_speech.score(X_TEST,Y_envelope_sp_TEST)[0]
# scores_lips[k] = rf_speech.score(X_TEST,Y_lips_ap_TEST)[0]
##coef_ is shape (n_outputs, n_features, n_delays).
# coefs_speech[k] = rf_speech.coef_[0, :, :]
# patterns_speech[k] = rf_speech.patterns_[0, :, :]
# coefs_lips[k] = rf_lips.coef_[0, :, :]
# patterns_lips[k] = rf_lips.patterns_[0, :, :]
# mean_coefs_lips = coefs_lips.mean(axis=0)
# mean_patterns_lips = patterns_lips.mean(axis=0)
mean_scores_lips = scores_lips.mean(axis=0)
# mean_coefs_speech = coefs_speech.mean(axis=0)
# mean_patterns_speech = patterns_speech.mean(axis=0)
mean_scores_speech = scores_speech.mean(axis=0)
#saving results for the i-th reg parameter and j-th time lag
results_speech[i, j] = mean_scores_speech
results_lips[i, j] = mean_scores_lips
results_speech_all_sub[s]=results_speech.copy()
results_lips_all_sub[s]=results_lips.copy()
predictions_speech_all_sub[s]=predictions_speech.copy()
predictions_lips_all_sub[s]=predictions_lips.copy()
np.save(savepath+'/results_speech_all_sub',results_speech_all_sub)
np.save(savepath+'/results_lips_all_sub',results_lips_all_sub)
np.save(savepath+'/predictions_speech_all_sub',predictions_speech_all_sub)
np.save(savepath+'/predictions_lips_all_sub',predictions_lips_all_sub)
tmp_results_speech = []
tmp_results_lips = []
for N, s in enumerate(subject_name):
if N ==0:
tmp_results_speech= np.asarray(results_speech_all_sub[s])
tmp_results_lips= np.asarray(results_lips_all_sub[s])
tmp_results_speech=np.dstack((tmp_results_speech, np.asarray(results_speech_all_sub[s])))
tmp_results_lips=np.dstack((tmp_results_lips,np.asarray(results_lips_all_sub[s])))
# computing grand average and standard deviation for each time lag
GAVG_sp = np.reshape(np.mean(tmp_results_speech,2),(len(regularization),11))
GAVG_lip = np.reshape(np.mean(tmp_results_lips,2),(len(regularization),11))
GAVG_sp_std = np.reshape(np.std(tmp_results_speech,2),(len(regularization),11))
GAVG_lip_std = np.reshape(np.std(tmp_results_lips,2),(len(regularization),11))
np.save(savepath+'/GAVG_sp',GAVG_sp)
np.save(savepath+'/GAVG_lip',GAVG_lip)
np.save(savepath+'/GAVG_sp_std',GAVG_sp_std)
np.save(savepath+'/GAVG_lip_std',GAVG_lip_std)
####PLOTTING RESULTS#####
T = np.reshape(T, (1, len(T)))
pp.figure(0)
for n, r in enumerate(regularization):
pp.errorbar((T[0,:] - 100) * 10, GAVG_sp[n,:], yerr=GAVG_sp_std[n,:])
pp.legend(regularization)
pp.title('speech MSE')
sfig=savepath+'/GAVG_specch.png'
pp.savefig(fname=sfig)
pp.figure(1)
for n, r in enumerate(regularization):
pp.errorbar((T[0, :] - 100) * 10, GAVG_lip[n, :], yerr=GAVG_lip_std[n, :])
pp.legend(regularization)
pp.title('lips MSE')
sfig = savepath +'/GAVG_lips.png'
pp.savefig(fname=sfig)
#pp.show()
print('bla')
def raw_to_data(raw_edf, training=False, drop_rejects=True, subj=None):
tmin, tmax = -0.5, 4.
X, y = [], []
stim_code = dict([(32766, 1), (769, 2), (770, 3), (771, 4), (772, 5),
(783, 6), (276, 7), (277, 8), (768, 9), (1023, 10),
(1072, 11)])
if training:
path = op.join('data_i2r', 'BCI_IV_2a', 'TrainingSet')
if not training:
path = op.join('data_i2r', 'BCI_IV_2a', 'TestingSet')
label_path = op.join('data_i2r', 'BCI_IV_2a', 'true_labels')
label_files_list = glob.glob(label_path + '/*E.mat')
label_subj = [int(f.split('A0')[1][0]) for f in label_files_list]
file_list = glob.glob(path + '/*.gdf')
subjects = [int(f.split('A0')[1][0]) for f in file_list]
if not training:
label_subj = [
np.argwhere(np.array(label_subj) == subjects[i])[0][0]
for i in range(len(subjects))
]
event_id = dict()
events_from_edf = []
sampling_frequency = raw_edf._raw_extras[0]['max_samp']
original_event = raw_edf.find_edf_events()
annot_list = list(
zip(original_event[1], original_event[4], original_event[2]))
# Remove rejected trials from events
if drop_rejects:
annot_list = pd.DataFrame(annot_list)
rejected = annot_list[0].isin(annot_list[annot_list[2] == 1023][0])
accepted_trials_index = [True] * 288
ind = -1
for row in annot_list.itertuples():
if row[3] == 1023:
rejected.loc[row[0] + 1] = True
accepted_trials_index[ind] = False
if row[3] == 768:
ind = ind + 1
annot_list = annot_list[~rejected]
annot_list = list(zip(annot_list[0], annot_list[1], annot_list[2]))
events_from_edf.extend(annot_list)
events_from_edf = np.array(events_from_edf)
events_arr = np.zeros(events_from_edf.shape, dtype=int)
for (i, i_event) in enumerate(events_from_edf):
index = int((float(i_event[0])) * sampling_frequency)
events_arr[i, :] = index, 0, stim_code[int(i_event[2])]
i = i + 1
# strip channel names of "." characters
raw_edf.rename_channels(lambda x: x.strip('.'))
#create Event dictionary based on File
events_in_edf = [event[2] for event in events_arr[:]]
if (events_in_edf.__contains__(2)):
event_id['LEFT_HAND'] = 2
if (events_in_edf.__contains__(3)):
event_id['RIGHT_HAND'] = 3
if (events_in_edf.__contains__(4)):
event_id['FEET'] = 4
if (events_in_edf.__contains__(5)):
event_id['TONGUE'] = 5
if (events_in_edf.__contains__(6)):
event_id['CUE_UNKNOWN'] = 6
# Apply band-pass filter
raw_edf.filter(0., 38., fir_design='firwin',
skip_by_annotation='edge') # 4-40Hz
picks = pick_types(raw_edf.info,
meg=False,
eeg=True,
stim=False,
eog=False,
exclude='bads')
# Read epochs (train will be done only between -0.5 and 4s)
# Testing will be done with a running classifier
epochs = Epochs(raw_edf,
events_arr,
event_id,
tmin,
tmax,
proj=True,
picks=picks,
baseline=None,
preload=True)
X = epochs.get_data().transpose(0, 2, 1)
X_shape = X.shape
if training:
scaler = Scaler(scalings='median').fit(X.flatten().reshape(-1, 1))
#scaler = MinMaxScaler(copy=True, feature_range=(-1, 1)).fit(X.flatten().reshape(-1,1))
pk.dump(
scaler,
open(
"./shallow_convnet/subject{}_oscaler.pk".format(
subjects[subj]), 'wb'))
else:
scaler = pk.load(
open(
"./shallow_convnet/subject{}_oscaler.pk".format(
subjects[subj]), 'rb'))
y = epochs.events[:, 2] - 2
X = scaler.transform(X.flatten().reshape(-1, 1))
X = X.reshape(X_shape)
if training:
return X, y, scaler
else:
y = sio.loadmat(
label_files_list[label_subj[subj]])['classlabel'].flatten()
y = np.array([i - 1 for i in y])
if drop_rejects:
y_drop = [i for i in range(288) if not accepted_trials_index[i]]
y = np.delete(y, y_drop, None)
return X, y
def decoding_withKfold(X,Y_speech,Y_lips,n_fold,train_index,test_index,polynomialReg):
predictions_speech= np.zeros((Y_speech.shape))
speech = np.zeros((Y_speech.shape))
predictions_lips= np.zeros((Y_lips.shape))
lips = np.zeros((Y_lips.shape))
scores_speech=np.zeros((n_fold,))
for k in range(0, n_fold):
eegScaler = Scaler()
speechScaler = Scaler()
lipsScaler = Scaler()
speechModel = LReg()
lipsModel = LReg()
#####COPY X AND Y VARIABLES
X_standard = np.zeros((X.shape))
Y_lips_standard = np.zeros((Y_lips.shape))
Y_speech_standard = np.zeros((Y_speech.shape))
# standardazing data
X_standard[train_index[k], :] = eegScaler.fit_transform(X[train_index[k], :])
X_standard[test_index[k], :] = eegScaler.transform(X[test_index[k], :])
Y_lips_standard[train_index[k], :] = lipsScaler.fit_transform(Y_lips[train_index[k], :])
Y_lips_standard[test_index[k], :] = lipsScaler.transform(Y_lips[test_index[k], :])
Y_speech_standard[train_index[k], :] = speechScaler.fit_transform(Y_speech[train_index[k], :])
Y_speech_standard[test_index[k], :] = speechScaler.transform(Y_speech[test_index[k], :])
X_TRAIN = X_standard[ train_index[k], :]
X_TEST = X_standard[ test_index[k], :]
Y_envelope_sp_TRAIN = Y_speech_standard[train_index[k], :]
Y_envelope_sp_TEST = Y_speech_standard[test_index[k], :]
Y_lips_ap_TRAIN = Y_lips_standard[train_index[k], :]
Y_lips_ap_TEST = Y_lips_standard[test_index[k], :]
if polynomialReg == True:
X_TRAIN= np.concatenate((X_TRAIN,np.power(X_TRAIN,2)),1)
X_TEST = np.concatenate((X_TEST, np.power(X_TEST, 2)), 1)
# training models and predict
speechModel.fit(X_TRAIN, Y_envelope_sp_TRAIN)
lipsModel.fit(X_TRAIN, Y_lips_ap_TRAIN)
reconstructed_speech = speechModel.predict(X_TEST)
reconstructed_lips = lipsModel.predict(X_TEST)
predictions_speech[test_index[k], :] = reconstructed_speech
speech[test_index[k], :] = Y_envelope_sp_TEST
predictions_lips[test_index[k], :] = reconstructed_lips
lips[test_index[k], :] = Y_lips_ap_TEST
# computing scores
speech_score = evaluate(speech.T, predictions_speech.T, 'corrcoeff')
lips_score = evaluate(lips.T, predictions_lips.T, 'corrcoeff')
return speech_score, lips_score, predictions_speech, predictions_lips, speech, lips
