def devp_fit_decoding_sensor_space(self, **kwargs):
from mne.decoding import (SlidingEstimator, GeneralizingEstimator,
Scaler, cross_val_multiscore, LinearModel,
get_coef, Vectorizer, CSP)
from devp_basicio import save_pkl, load_pkl
kwargs.update(dict(name=f'model_{kwargs["target_event"]}'))
model_f = self.get_decoding_model_pkl(**kwargs)
kwargs.update(dict(name=f'score_{kwargs["target_event"]}'))
scores_f = self.get_decoding_score_pkl(**kwargs)
if Path(model_f).exists() and Path(scores_f).exists():
time_decod = load_pkl(model_f, logger=self.logger)
scores = load_pkl(scores_f, logger=self.logger)
if kwargs['retrain'] == False:
return scores, None
X, y, epochs = self.devp_get_data_sensor_space(**kwargs)
time_decod = self.devp_estimator(**kwargs)
time_decod.fit(X, y)
save_pkl(time_decod, model_f, logger=self.logger)
scores = cross_val_multiscore(time_decod, X, y, cv=12, n_jobs=6)
scores = np.mean(scores, axis=0)
save_pkl(scores, scores_f, logger=self.logger)
# self.plot_auc(epochs, scores, **kwargs)
# coef = get_coef(time_decod, 'patterns_', inverse_transform=True)
# self.plot_decoding_joint(coef, epochs, **kwargs)
return scores, epochs
def NeuralNet(X_train, y_train, X_test, y_test, scorer, predict_mode, params):
" Neural Network estimator "
# Model
model = MLPClassifier(solver='lbfgs', alpha=1e-5, hidden_layer_sizes=(3,), random_state=1)
# Cross-validation scheme
cv = StratifiedKFold(n_splits=4, random_state=0, shuffle=True)
# Scaler
scaler = StandardScaler()
# Pipeline
clf = make_pipeline(scaler, model)
# Define scorer
if scorer is 'scorer_auc':
scorer = 'roc_auc'
elif scorer is 'accuracy':
scorer = None
else:
print('using accuracy as the scorer')
# Learning and scoring
time_gen = GeneralizingEstimator(clf, n_jobs=2, scoring=scorer)
scores = cross_val_multiscore(time_gen, X_train, y_train, cv=cv, n_jobs=2)
return scores
def logreg_timedecoding(epochs, numcv=4, jobs=1):
"""
Logistic regression over sensors. Returns Evoked array containing coefficients and ROC.
Code snippets stolen from:
https://martinos.org/mne/stable/auto_tutorials/plot_sensors_decoding.html
"""
X = epochs.get_data() # MEG signals: n_epochs, n_channels, n_times
X = X.astype(float)
y = epochs.events[:, 2] # targets
# setup and run the decoder
clf = make_pipeline(StandardScaler(), LinearModel(LogisticRegression()))
time_decod = SlidingEstimator(clf, scoring='roc_auc',
n_jobs=jobs) #scoring='roc_auc',
scores = cross_val_multiscore(time_decod, X, y, cv=numcv, n_jobs=jobs)
# Mean scores across cross-validation splits
scores = np.mean(scores, axis=0)
#
time_decod = SlidingEstimator(clf, scoring='roc_auc', n_jobs=jobs)
time_decod.fit(X, y)
coef = get_coef(time_decod, 'patterns_', inverse_transform=True)
evoked = mne.EvokedArray(coef, epochs.info, tmin=epochs.times[0])
evoked.roc_auc = scores
return evoked
def LogisticRegression(X_train, y_train, X_test, y_test, scorer, predict_mode, params):
" Logistic Regression within or across conditions "
# Model
model = linear_model.LogisticRegression(class_weight='balanced')
# Cross-validation scheme
cv = StratifiedKFold(n_splits=4, random_state=0, shuffle=True)
# Scaler
scaler = StandardScaler()
# Pipeline
clf = make_pipeline(scaler, model)
# Define scorer
if scorer is 'scorer_auc':
scorer = 'roc_auc'
elif scorer is 'accuracy':
scorer = None
else:
print('using accuracy as the scorer')
# Learning and scoring
time_gen = GeneralizingEstimator(clf, n_jobs=2, scoring=scorer)
scores = cross_val_multiscore(time_gen, X_train, y_train, cv=cv, n_jobs=2)
return scores
def run_time_decoding(subject, condition1, condition2, session=None):
print("Processing subject: %s (%s vs %s)"
% (subject, condition1, condition2))
# Construct the search path for the data file. `sub` is mandatory
subject_path = op.join('sub-{}'.format(subject))
# `session` is optional
if session is not None:
subject_path = op.join(subject_path, 'ses-{}'.format(session))
subject_path = op.join(subject_path, config.kind)
bids_basename = make_bids_basename(subject=subject,
session=session,
task=config.task,
acquisition=config.acq,
run=None,
processing=config.proc,
recording=config.rec,
space=config.space
)
fpath_deriv = op.join(config.bids_root, 'derivatives',
config.PIPELINE_NAME, subject_path)
fname_in = \
op.join(fpath_deriv, bids_basename + '-epo.fif')
epochs = mne.read_epochs(fname_in)
# We define the epochs and the labels
epochs = mne.concatenate_epochs([epochs[condition1],
epochs[condition2]])
epochs.apply_baseline()
# Get the data and labels
X = epochs.get_data()
n_cond1 = len(epochs[condition1])
n_cond2 = len(epochs[condition2])
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
# Use AUC because chance level is same regardless of the class balance
se = SlidingEstimator(
make_pipeline(StandardScaler(),
LogisticRegression(solver='liblinear',
random_state=config.random_state)),
scoring=config.decoding_metric, n_jobs=config.N_JOBS)
cv = StratifiedKFold(random_state=config.random_state,
n_splits=config.decoding_n_splits)
scores = cross_val_multiscore(se, X=X, y=y, cv=cv)
# let's save the scores now
a_vs_b = '%s_vs_%s' % (condition1, condition2)
a_vs_b = a_vs_b.replace(op.sep, '')
fname_td = op.join(config.bids_root, 'derivatives', config.PIPELINE_NAME,
'%s_%s_%s_%s.mat' %
(subject, config.study_name, a_vs_b,
config.decoding_metric))
savemat(fname_td, {'scores': scores, 'times': epochs.times})
def run_time_decoding(subject_id, condition1, condition2):
print("processing subject: %s (%s vs %s)" %
(subject_id, condition1, condition2))
subject = "S%02d" % subject_id
data_path = os.path.join(ana_path, subject, 'EEG', 'New_Preproc')
epochs = mne.read_epochs(
os.path.join(data_path, '%s-causal-highpass-2Hz-epo.fif' % subject))
# We define the epochs and the labels
epochs = epochs[condition1, condition2]
epochs.apply_baseline()
# Let us restrict ourselves to the MEG channels, and also decimate to
# make it faster (although we might miss some detail / alias)
epochs.pick_types(eeg=True).decimate(2, verbose='error')
mne.epochs.combine_event_ids(epochs, ['stim/face', 'stim/house'],
{'stim': 100},
copy=False)
mne.epochs.combine_event_ids(epochs, ['imag/face', 'imag/house'],
{'imag': 200},
copy=False)
# Get the data and labels
X = epochs.get_data()
# fit and time decoder
le = LabelEncoder()
y = le.fit_transform(epochs.events[:, 2])
# Use AUC because chance level is same regardless of the class balance
se = SlidingEstimator(make_pipeline(StandardScaler(),
LogisticRegression()),
scoring='roc_auc',
n_jobs=1)
#
scores = cross_val_multiscore(se, X=X, y=y, cv=StratifiedKFold())
#cv=StratifiedKFold()
#scores, permutation_scores, pvalue = permutation_test_score(estimator = se, X=X, y=y, groups=None, scoring = None,
# cv=3, n_permutations=100)
#print("********* %s Classification score %s (pvalue : %s) ***********" % (subject, scores, pvalue))
# let's save the scores now
cond1 = condition1.replace('/', '-')
cond2 = condition2.replace('/', '-')
a_vs_b = '%s_vs_%s' % (cond1, cond2)
fname_td = os.path.join(
results_path,
'%s-causal-highpass-2Hz-td-auc-%s.mat' % (subject, a_vs_b))
savemat(fname_td, {
'scores': scores,
'times': epochs.times
}) #, 'perm_scores': permutation_scores, 'pval' : pvalue})
def run_time_decoding(subject, condition1, condition2, session=None):
msg = f'Contrasting conditions: {condition1} – {condition2}'
logger.info(
gen_log_message(message=msg, step=7, subject=subject, session=session))
fname_epochs = BIDSPath(subject=subject,
session=session,
task=config.get_task(),
acquisition=config.acq,
run=None,
recording=config.rec,
space=config.space,
suffix='epo',
extension='.fif',
datatype=config.get_datatype(),
root=config.deriv_root,
check=False)
epochs = mne.read_epochs(fname_epochs)
# We define the epochs and the labels
epochs = mne.concatenate_epochs([epochs[condition1], epochs[condition2]])
X = epochs.get_data()
n_cond1 = len(epochs[condition1])
n_cond2 = len(epochs[condition2])
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
clf = make_pipeline(
StandardScaler(),
LogisticRegression(solver='liblinear',
random_state=config.random_state))
se = SlidingEstimator(clf,
scoring=config.decoding_metric,
n_jobs=config.N_JOBS)
scores = cross_val_multiscore(se, X=X, y=y, cv=config.decoding_n_splits)
# let's save the scores now
a_vs_b = f'{condition1}-{condition2}'.replace(op.sep, '')
processing = f'{a_vs_b}+{config.decoding_metric}'
processing = processing.replace('_', '-').replace('-', '')
fname_mat = fname_epochs.copy().update(suffix='decoding',
processing=processing,
extension='.mat')
savemat(fname_mat, {'scores': scores, 'times': epochs.times})
fname_tsv = fname_mat.copy().update(extension='.tsv')
tabular_data = pd.DataFrame(
dict(cond_1=[condition1] * len(epochs.times),
cond_2=[condition2] * len(epochs.times),
time=epochs.times,
mean_crossval_score=scores.mean(axis=0),
metric=[config.decoding_metric] * len(epochs.times)))
tabular_data.to_csv(fname_tsv, sep='\t', index=False)
def classify(epochs):
Xall = epochs.get_data() # epochs*channels*time
rel = epochs.events[:, 2] != 2 # throw out standard
X = Xall[rel, :, :] # classifying target vs. novelty
y = epochs.events[rel, 2] # target, standard or novelty
clf = make_pipeline(StandardScaler(), LogisticRegression())
clfest = dc.SlidingEstimator(clf, n_jobs=1, scoring='accuracy')
values = dc.cross_val_multiscore(clfest, X, y, cv=5, n_jobs=1)
return np.mean(values, axis=0)
def run_gat(name, decoder="ridge"):
"""
Function to run Generalization Across Time (GAT).
Parameters
----------
name: str
Name (pseudonym) of individual subject.
decoder: str
Specify type of classifier -'ridge' for Ridge Regression (default),'lin-svm' for linear SVM
'svm' for nonlinear (RBF) SVM and 'log_reg' for Logistic Regression
"""
# load high cloze epochs
epochs = get_epochs(name)['song', 'voice']
# specify whether to use a linear or nonlinear SVM if SVM is used
lin = '' # if not svm it doesn't matter, both log_reg and ridge are linear
if "svm" in decoder:
decoder, lin = decoder.split("-")
# build classifier pipeline #
# pick a machine learning algorithm to use (ridge/SVM/logistic regression)
decoder_dict = {
"ridge":
RidgeClassifier(class_weight='balanced', random_state=42,
solver="sag"),
"svm":
SVC(class_weight='balanced',
kernel=("rbf" if "non" in lin else "linear"),
random_state=42),
"log_reg":
LogisticRegression(class_weight='balanced', random_state=42)
}
clf = make_pipeline(StandardScaler(), decoder_dict[decoder])
gen_clf = GeneralizingEstimator(clf, scoring="roc_auc", n_jobs=4)
scores = cross_val_multiscore(gen_clf,
epochs.get_data(),
epochs.events[:, -1],
cv=5,
n_jobs=4).mean(0)
data = epochs.get_data()
labels = epochs.events[:, -1]
cv = StratifiedKFold(n_splits=5, random_state=42)
# calculate prediction confidence scores
preds = np.empty((len(labels), 225, 225))
for train, test in cv.split(data, labels):
gen_clf.fit(data[train], labels[train])
d = gen_clf.decision_function(data[test])
preds[test] = d
return scores, preds # return subject scores and prediction confidence
def run_time_decoding(subject, condition1, condition2, session=None):
msg = f'Contrasting conditions: {condition1} – {condition2}'
logger.info(
gen_log_message(message=msg, step=8, subject=subject, session=session))
deriv_path = config.get_subject_deriv_path(subject=subject,
session=session,
kind=config.get_kind())
fname_in = BIDSPath(subject=subject,
session=session,
task=config.get_task(),
acquisition=config.acq,
run=None,
recording=config.rec,
space=config.space,
prefix=deriv_path,
kind='epo',
extension='.fif',
check=False)
epochs = mne.read_epochs(fname_in)
# We define the epochs and the labels
epochs = mne.concatenate_epochs([epochs[condition1], epochs[condition2]])
epochs.apply_baseline()
# Get the data and labels
X = epochs.get_data()
n_cond1 = len(epochs[condition1])
n_cond2 = len(epochs[condition2])
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
se = SlidingEstimator(make_pipeline(
StandardScaler(),
LogisticRegression(solver='liblinear',
random_state=config.random_state)),
scoring=config.decoding_metric,
n_jobs=config.N_JOBS)
scores = cross_val_multiscore(se, X=X, y=y, cv=config.decoding_n_splits)
# let's save the scores now
a_vs_b = f'{condition1}-{condition2}'.replace(op.sep, '')
processing = f'{a_vs_b}+{config.decoding_metric}'
processing = processing.replace('_', '-').replace('-', '')
fname_td = fname_in.copy().update(kind='decoding',
processing=processing,
extension='.mat')
savemat(fname_td, {'scores': scores, 'times': epochs.times})
def run_time_decoding(subject, condition1, condition2, session=None):
msg = f'Contrasting conditions: {condition1} – {condition2}'
logger.info(
gen_log_message(message=msg, step=8, subject=subject, session=session))
deriv_path = config.get_subject_deriv_path(subject=subject,
session=session,
kind=config.get_kind())
bids_basename = make_bids_basename(subject=subject,
session=session,
task=config.get_task(),
acquisition=config.acq,
run=None,
processing=config.proc,
recording=config.rec,
space=config.space)
fname_in = op.join(deriv_path, bids_basename + '-epo.fif')
epochs = mne.read_epochs(fname_in)
# We define the epochs and the labels
epochs = mne.concatenate_epochs([epochs[condition1], epochs[condition2]])
epochs.apply_baseline()
# Get the data and labels
X = epochs.get_data()
n_cond1 = len(epochs[condition1])
n_cond2 = len(epochs[condition2])
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
# Use AUC because chance level is same regardless of the class balance
se = SlidingEstimator(make_pipeline(
StandardScaler(),
LogisticRegression(solver='liblinear',
random_state=config.random_state)),
scoring=config.decoding_metric,
n_jobs=config.N_JOBS)
scores = cross_val_multiscore(se, X=X, y=y, cv=config.decoding_n_splits)
# let's save the scores now
a_vs_b = '%s_vs_%s' % (condition1, condition2)
a_vs_b = a_vs_b.replace(op.sep, '')
fname_td = op.join(
config.bids_root, 'derivatives', config.PIPELINE_NAME,
'%s_%s_%s_%s.mat' %
(subject, config.study_name, a_vs_b, config.decoding_metric))
savemat(fname_td, {'scores': scores, 'times': epochs.times})
def mneClassify(self, sj, to_decode, conditions, time=[-0.3, 0.8]):
'''
'''
clf = make_pipeline(StandardScaler(), LogisticRegression())
time_decod = SlidingEstimator(clf, n_jobs=1)
# get eeg data
eeg = []
for session in range(2):
eeg.append(
mne.read_epochs(
'/Users/dirk/Desktop/suppression/processed/subject-{}_ses-{}-epo.fif'
.format(sj, session + 1)))
times = eeg[0].times
# select time window and electrodes
s_idx, e_idx = eeg[0].time_as_index(time)
picks = mne.pick_types(eeg[0].info, eeg=True, exclude='bads')
eeg = np.vstack((eeg[0]._data, eeg[1]._data))[:, picks, :][:, :,
s_idx:e_idx]
# get behavior data
with open(
'/Users/dirk/Desktop/suppression/beh/processed/subject-{}_all.pickle'
.format(sj), 'rb') as handle:
beh = pickle.load(handle)
plt.figure(figsize=(20, 20))
for i, cnd in enumerate(conditions):
X = eeg[beh['condition'] == cnd]
y = beh[to_decode][beh['condition'] == cnd]
scores = cross_val_multiscore(time_decod, X, y, cv=5, n_jobs=1)
plt.plot(times[s_idx:e_idx],
scores.mean(axis=0),
color=['r', 'g', 'b', 'y'][i],
label=cnd)
plt.legend(loc='best')
plt.savefig(
'/Users/dirk/Desktop/suppression/bdm/figs/{}_{}_bdm.pdf'.format(
to_decode, sj))
plt.close()
def run_time_decoding(subject, condition1, condition2):
print("processing subject: %s (%s vs %s)" %
(subject, condition1, condition2))
print("Processing subject: %s" % subject)
meg_subject_dir = op.join(config.meg_dir, subject)
extension = '-epo'
fname_in = op.join(meg_subject_dir, config.base_fname.format(**locals()))
print("Input: ", fname_in)
epochs = mne.read_epochs(fname_in)
# We define the epochs and the labels
epochs = mne.concatenate_epochs([epochs[condition1], epochs[condition2]])
epochs.apply_baseline()
# Get the data and labels
X = epochs.get_data()
n_cond1 = len(epochs[condition1])
n_cond2 = len(epochs[condition2])
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
# Use AUC because chance level is same regardless of the class balance
se = SlidingEstimator(make_pipeline(
StandardScaler(),
LogisticRegression(solver='liblinear',
random_state=config.random_state)),
scoring=config.decoding_metric,
n_jobs=config.N_JOBS)
cv = StratifiedKFold(random_state=config.random_state,
n_splits=config.decoding_n_splits)
scores = cross_val_multiscore(se, X=X, y=y, cv=cv)
# let's save the scores now
a_vs_b = '%s_vs_%s' % (condition1, condition2)
a_vs_b = a_vs_b.replace(op.sep, '')
fname_td = op.join(
meg_subject_dir, '%s_%s_%s_%s.mat' %
(subject, config.study_name, a_vs_b, config.decoding_metric))
savemat(fname_td, {'scores': scores, 'times': epochs.times})
def sliding_logreg_source(X, y, cross_val, return_clf=False):
"""Run a sliding estimator with Logistic Regression on source data.
Parameters:
-----------
X : np.array
features.
y : vector
response vector.
cross_val : cross validation object
cross validation to adopt.
return_clf : bool
whether the clf object should be returned as well.
Returns
-------
score : float
cross-validated AUC score
clf : classifier object
If return_clf == True, the classifier object will be returned, too.
"""
startt = time.time()
# Model
clf = make_pipeline(StandardScaler(), LinearModel(LogisticRegression()))
sliding = SlidingEstimator(clf, scoring='roc_auc', n_jobs=1)
print('Computing Logistic Regression.')
score = cross_val_multiscore(sliding, X, y, cv=cross_val)
endt = time.time()
print('Done. Time elapsed for sliding estimator: %i seconds.' %
(endt - startt))
if return_clf is True:
return score, clf
else:
return score
def run_time_decoding(subject_id, condition1, condition2):
print("processing subject: %s (%s vs %s)" %
(subject_id, condition1, condition2))
subject = "sub%03d" % subject_id
data_path = os.path.join(meg_dir, subject)
epochs = mne.read_epochs(
os.path.join(data_path,
'%s_highpass-%sHz-epo.fif' % (subject, l_freq)))
# We define the epochs and the labels
epochs = mne.concatenate_epochs([epochs[condition1], epochs[condition2]])
epochs.apply_baseline()
# Let us restrict ourselves to the MEG channels, and also decimate to
# make it faster (although we might miss some detail / alias)
epochs.pick_types(meg=True).decimate(4, verbose='error')
# Get the data and labels
X = epochs.get_data()
n_cond1 = len(epochs[condition1])
n_cond2 = len(epochs[condition2])
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
# Use AUC because chance level is same regardless of the class balance
se = SlidingEstimator(make_pipeline(StandardScaler(),
LogisticRegression()),
scoring='roc_auc',
n_jobs=N_JOBS)
scores = cross_val_multiscore(se, X=X, y=y, cv=StratifiedKFold())
# let's save the scores now
a_vs_b = '%s_vs_%s' % (os.path.basename(condition1),
os.path.basename(condition2))
fname_td = os.path.join(
data_path,
'%s_highpass-%sHz-td-auc-%s.mat' % (subject, l_freq, a_vs_b))
savemat(fname_td, {'scores': scores, 'times': epochs.times})
# by using :class:`sklearn.pipeline.Pipeline`. We can construct decoding
# pipelines and perform cross-validation and grid-search. However scikit-learn
# transformers and estimators generally expect 2D data
# (n_samples * n_features), whereas MNE transformers typically output data
# with a higher dimensionality
# (e.g. n_samples * n_channels * n_frequencies * n_times). A Vectorizer
# therefore needs to be applied between the MNE and the scikit-learn steps
# like:
# Uses all MEG sensors and time points as separate classification
# features, so the resulting filters used are spatio-temporal
clf = make_pipeline(Scaler(epochs.info),
Vectorizer(),
LogisticRegression(solver='lbfgs'))
scores = cross_val_multiscore(clf, X, y, cv=5, n_jobs=1)
# Mean scores across cross-validation splits
score = np.mean(scores, axis=0)
print('Spatio-temporal: %0.1f%%' % (100 * score,))
###############################################################################
# PSDEstimator
# ^^^^^^^^^^^^
# The :class:`mne.decoding.PSDEstimator`
# computes the power spectral density (PSD) using the multitaper
# method. It takes a 3D array as input, converts it into 2D and computes the
# PSD.
#
# FilterEstimator
# ^^^^^^^^^^^^^^^
labels_shuffled = np.random.permutation(labels)
# generate iterator for cross validation
kf = StratifiedKFold(n_splits=2, shuffle=True)
cv_iter = kf.split(np.zeros(X.shape), labels_shuffled)
# pipeline for classification
cl = make_pipeline(RobustScaler(), PCA(n_components=var_exp),
LinearSVC(max_iter=10000, dual=False, penalty="l1"))
# temporal generalisation
temp_genr = SlidingEstimator(cl, n_jobs=1, scoring="roc_auc")
# cross validation
scores = cross_val_multiscore(temp_genr,
X,
labels_shuffled,
cv=cv_iter,
n_jobs=-1)
scores_all.append(scores)
scores_all = np.vstack(scores_all)
scores_path = op.join(output_dir,
"reg_vs_odd_chance_level-{}.npy".format(subject))
np.save(scores_path, scores_all)
print("saved")
scores_all = scores_all[::2, :]
# Extract half of the epochs for similar SNR in all conditions
epochs_nr = len(epochs['left/grating'])
epochs_range = np.random.permutation(np.arange(0, epochs_nr, 1))
np.save('%s_epochs_range.npy' % subject, epochs_range)
X = np.concatenate(
(epochs["face"][epochs_range[:int(epochs_nr / 2)]].get_data(),
epochs["grating"][epochs_range[:int(epochs_nr / 2)]].get_data()))
y = np.concatenate(
(np.zeros(int(epochs_nr / 2)), np.ones(int(epochs_nr / 2))))
cv = StratifiedKFold(n_splits=10, shuffle=True)
clf = make_pipeline(StandardScaler(), LogisticRegression())
time_gen = GeneralizingEstimator(clf, scoring='roc_auc', n_jobs=n_jobs)
time_gen.fit(X, y)
scores = cross_val_multiscore(time_gen, X, y, cv=cv)
# Save results
joblib.dump(time_gen, "%s_time_gen_svm.jbl" % subject)
np.save("%s_time_gen_score_svm.npy" % subject, scores)
X_left = np.concatenate(
(epochs["left/face"].get_data(), epochs["left/grating"].get_data()))
y_left = np.concatenate((np.zeros(len(epochs["left/face"].get_data())),
np.ones(len(epochs["left/grating"].get_data()))))
clf = make_pipeline(StandardScaler(), LogisticRegression())
time_gen_left = GeneralizingEstimator(clf,
scoring='roc_auc',
n_jobs=n_jobs)
time_gen_left.fit(X_left, y_left)
scores_left = cross_val_multiscore(time_gen, X_left, y_left, cv=cv)
cv = KFold(5)
if regressor == 'condition':
y = binary_scaler(y) # set values to 0.0 and 1.0
clf = make_pipeline(StandardScaler(), LogisticRegression(solver='liblinear'))
scorer = 'roc_auc'
score = 'AUC'
cv = StratifiedKFold(5)
n_jobs = -1
# set up estimator, get scores
if decode_using == 'spatial':
gen = SlidingEstimator(n_jobs=n_jobs,
scoring=scorer,
base_estimator=clf)
scores = cross_val_multiscore(gen, X, y,
cv=cv)
elif decode_using == 'temporal':
gen = SlidingEstimator(n_jobs=n_jobs,
scoring=scorer,
base_estimator=clf)
scores = cross_val_multiscore(gen, X, y,
cv=cv)
else:
# scoring defaults to neg mean squared so set to scorer
# shuffle must be true when binary values, otherwise fold will only have one value
scores = cross_val_score(clf, X, y,
scoring=scorer, #defaults to neg mean squared
cv=KFold(5, shuffle=True))
# mean scores across cross-validation splits
scores = np.mean(scores, axis=0)
def main():
model_type = "lda"
exp_name = "freq_gen_matrix/"
for i, sample in enumerate(range(1, 22)):
print("sample {}".format(sample))
if not os.path.isdir("Results/{}/{}/sample_{}".format(
model_type, exp_name, sample)):
os.mkdir("Results/{}/{}/sample_{}".format(model_type, exp_name,
sample))
epochs = get_epochs(sample, scale=False)
y_train = epochs.events[:, 2]
freqs = np.logspace(*np.log10([2, 25]), num=15)
n_cycles = freqs / 4.
string_freqs = [round(x, 2) for x in freqs]
print("applying morlet wavelet")
wavelet_output = tfr_array_morlet(epochs.get_data(),
sfreq=epochs.info['sfreq'],
freqs=freqs,
n_cycles=n_cycles,
output='complex')
time_results = np.zeros(
(wavelet_output.shape[3], len(freqs), len(freqs)))
for time in range(wavelet_output.shape[3]):
print("time: {}".format(time))
wavelet_epochs = wavelet_output[:, :, :, time]
wavelet_epochs = np.append(wavelet_epochs.real,
wavelet_epochs.imag,
axis=1)
wavelet_info = mne.create_info(ch_names=wavelet_epochs.shape[1],
sfreq=epochs.info['sfreq'],
ch_types='mag')
wavelet_epochs = mne.EpochsArray(wavelet_epochs,
info=wavelet_info,
events=epochs.events)
x_train = pca(80, wavelet_epochs, plot=False)
model = LinearModel(
LinearDiscriminantAnalysis(solver='lsqr', shrinkage='auto'))
freq_gen = GeneralizingEstimator(model,
n_jobs=1,
scoring='accuracy',
verbose=True)
scores = cross_val_multiscore(freq_gen,
x_train,
y_train,
cv=5,
n_jobs=1)
scores = np.mean(scores, axis=0)
time_results[time] = scores
sns.set()
ax = sns.barplot(
np.sort(string_freqs),
np.diag(scores),
)
ax.set(ylim=(0, 0.8),
xlabel='Frequencies',
ylabel='Accuracy',
title='Cross Val Accuracy {} for Subject {} for Time {}'.
format(model_type, sample, time))
ax.axhline(0.12, color='k', linestyle='--')
ax.figure.set_size_inches(8, 6)
ax.figure.savefig(
"Results/{}/{}/sample_{}/time_{}_accuracy.png".format(
model_type, exp_name, sample, time),
dpi=300)
plt.close('all')
# plt.show()
fig, ax = plt.subplots(1, 1)
im = ax.imshow(scores,
interpolation='lanczos',
origin='lower',
cmap='RdBu_r',
extent=[2, 25, 2, 25],
vmin=0.,
vmax=0.8)
ax.set_xlabel('Testing Frequency (hz)')
ax.set_ylabel('Training Frequency (hz)')
ax.set_title(
'Frequency generalization for Subject {} at Time {}'.format(
sample, time))
plt.colorbar(im, ax=ax)
ax.grid(False)
ax.figure.savefig(
"Results/{}/{}/sample_{}/time_{}_matrix.png".format(
model_type, exp_name, sample, time),
dpi=300)
plt.close('all')
# plt.show()
time_results = time_results.reshape(time_results.shape[0], -1)
all_results_df = pd.DataFrame(time_results)
all_results_df.to_csv(
"Results/{}/{}/sample_{}/all_time_matrix_results.csv".format(
model_type, exp_name, sample))
def run_time_decoding(subject_id, cond1, cond2, event_id):
subject = "S%02d" % subject_id
print subject, cond1, cond2
data_path = os.path.join('/home/claire/DATA/Data_Face_House/' + subject +
'/EEG/')
raw_fname = data_path + subject + '-raw.fif'
event_fname = data_path + subject + '-eve.fif'
tmin, tmax = -0.5, 1.5
raw = mne.io.read_raw_fif(raw_fname, preload=True)
events = mne.read_events(event_fname)
picks = mne.pick_types(raw.info,
meg=False,
eeg=True,
stim=True,
eog=True,
exclude='bads')
# Read epochs
epochs = mne.Epochs(raw,
events,
event_id,
tmin,
tmax,
proj=True,
picks=picks,
baseline=(None, 0.),
preload=True,
decim=4)
epochs.pick_types(eeg=True, exclude='bads')
#only look at occipital channels
# select_chans = [u'Iz', u'Oz', u'O1', u'O2', u'O3', u'PO7', u'PO8', u'POz', u'PO1', u'PO3', u'PO2', u'PO4']
select_chans = [u'PO7', u'PO8']
#select_chans = [ u'Cz', u'FPz']
ch_names = [ch_name.replace('', '') for ch_name in select_chans]
epochs.pick_types(eeg=True).pick_channels(ch_names)
# average group of 4 trials
data_cond1 = epochs['imag/face'].get_data()
data_cond2 = epochs['imag/house'].get_data()
mean_cond1 = []
ind_trial = 0
while ind_trial <= len(data_cond1) - 5:
mean_cond1.append(mean(data_cond1[ind_trial:(ind_trial + 4)], 0))
print ind_trial
ind_trial += 5
mean_cond2 = []
ind_trial = 0
while ind_trial <= len(data_cond2) - 5:
mean_cond2.append(mean(data_cond2[ind_trial:(ind_trial + 4)], 0))
print ind_trial
ind_trial += 5
X = []
# create variable for decoding
X = mean_cond1 + mean_cond2
X = np.array(X)
y = np.array([0] * len(mean_cond1) + [1] * len(mean_cond2))
# fit and time decoder
#X = epochs.get_data() # MEG signals: n_epochs, n_channels, n_times
#y = epochs.events[:, 2] # target: Audio left or right
cv = StratifiedKFold(n_splits=3, shuffle=False)
cv.get_n_splits(X, y)
clf = make_pipeline(StandardScaler(), LogisticRegression())
time_decod = SlidingEstimator(clf, n_jobs=1, scoring='roc_auc')
#scores = cross_val_multiscore(time_decod, X, y, cv=5, n_jobs=1)
scores = cross_val_multiscore(time_decod, X, y, cv=cv, n_jobs=1)
# Mean scores across cross-validation splits
scores = np.mean(scores, axis=0)
# save scores
a_vs_b = '%s_vs_%s' % (cond1, cond2)
print 'a_vs_b = %s' % a_vs_b
fname_td = os.path.join(
data_path, '%s-td-auc-%s_ave_4_trials_po7_po8.mat' % (subject, a_vs_b))
print 'Saving %s' % fname_td
from scipy.io import savemat
savemat(fname_td, {'scores': scores, 'times': epochs.times})
def run_time_decoding(subject, condition1, condition2, session=None):
msg = f'Contrasting conditions: {condition1} – {condition2}'
logger.info(gen_log_message(message=msg, step=7, subject=subject,
session=session))
fname_epochs = BIDSPath(subject=subject,
session=session,
task=config.get_task(),
acquisition=config.acq,
run=None,
recording=config.rec,
space=config.space,
suffix='epo',
extension='.fif',
datatype=config.get_datatype(),
root=config.deriv_root,
check=False)
epochs = mne.read_epochs(fname_epochs)
if config.analyze_channels:
# We special-case the average reference here to work around a situation
# where e.g. `analyze_channels` might contain only a single channel:
# `concatenate_epochs` below will then fail when trying to create /
# apply the projection. We can avoid this by removing an existing
# average reference projection here, and applying the average reference
# directly – without going through a projector.
if 'eeg' in config.ch_types and config.eeg_reference == 'average':
epochs.set_eeg_reference('average')
else:
epochs.apply_proj()
epochs.pick(config.analyze_channels)
# We define the epochs and the labels
if isinstance(config.conditions, dict):
epochs_conds = [config.conditions[condition1],
config.conditions[condition2]]
cond_names = [condition1, condition2]
else:
epochs_conds = cond_names = [condition1, condition2]
epochs_conds = [condition1, condition2]
epochs = mne.concatenate_epochs([epochs[epochs_conds[0]],
epochs[epochs_conds[1]]])
n_cond1 = len(epochs[epochs_conds[0]])
n_cond2 = len(epochs[epochs_conds[1]])
X = epochs.get_data()
y = np.r_[np.ones(n_cond1), np.zeros(n_cond2)]
clf = make_pipeline(
StandardScaler(),
LogisticRegression(solver='liblinear',
random_state=config.random_state))
se = SlidingEstimator(clf,
scoring=config.decoding_metric,
n_jobs=config.N_JOBS)
scores = cross_val_multiscore(se, X=X, y=y, cv=config.decoding_n_splits)
# let's save the scores now
a_vs_b = f'{cond_names[0]}+{cond_names[1]}'.replace(op.sep, '')
processing = f'{a_vs_b}+{config.decoding_metric}'
processing = processing.replace('_', '-').replace('-', '')
fname_mat = fname_epochs.copy().update(suffix='decoding',
processing=processing,
extension='.mat')
savemat(fname_mat, {'scores': scores, 'times': epochs.times})
fname_tsv = fname_mat.copy().update(extension='.tsv')
tabular_data = pd.DataFrame(
dict(cond_1=[cond_names[0]] * len(epochs.times),
cond_2=[cond_names[1]] * len(epochs.times),
time=epochs.times,
mean_crossval_score=scores.mean(axis=0),
metric=[config.decoding_metric] * len(epochs.times))
)
tabular_data.to_csv(fname_tsv, sep='\t', index=False)
# The `inverse_transform` parameter will call this method on any estimator
# contained in the pipeline, in reverse order.
coef = get_coef(clf, name, inverse_transform=True)
evoked = EvokedArray(coef, epochs.info, tmin=epochs.tmin)
evoked.plot_topomap(title='EEG %s' % name[:-1], time_unit='s')
#------------------------------------------------------------------------------
#------------------------------------------------------------------------------
#------------------------------------------------------------------------------
#Applying StandardScaler, LogisticRegression
clf = make_pipeline(StandardScaler(), LogisticRegression(solver='lbfgs'))
time_decod = SlidingEstimator(clf, n_jobs=1, scoring='roc_auc')
scores = cross_val_multiscore(time_decod, ica_data, labels, cv=5, n_jobs=1)
# Mean scores across cross-validation splits
scores = np.mean(scores, axis=0)
# Plot
fig, ax = plt.subplots()
ax.plot(epochs.times, scores, label='score')
ax.axhline(.5, color='k', linestyle='--', label='chance')
ax.set_xlabel('Times')
ax.set_ylabel('AUC') # Area Under the Curve
ax.legend()
ax.axvline(.0, color='k', linestyle='-')
ax.set_title('Sensor space decoding')
#------------------------------------------------------------------------------
if subject[4:] in ("101", "124a", "213",
"301a") and interval != "All":
use_splits = 3
else:
use_splits = n_splits
cv = StratifiedKFold(n_splits=use_splits,
shuffle=True,
random_state=seed)
# Get the data and label
X = eps.get_data()
y = eps.events[:, -1]
# AUC b/c chance level same regardless of the class balance
score = np.mean(
cross_val_multiscore(time_decode,
X=X,
y=y,
cv=cv,
n_jobs=n_jobs),
axis=0,
)
aucs[si, ci, ii] = score[s_ix].mean()
print(" %s vs. %s mean AUC: %.3f on %d epochs" %
(c1, c2, score.mean(), len(eps)))
mne.externals.h5io.write_hdf5(
fname, dict(auc=aucs[si], events=events, intervals=intervals))
ages = np.array(features["age"])
age_bounds = [[40, 80], [105, 150], [175, 210], [40, 210]]
fig, axes = plt.subplots(
len(events),
len(age_bounds),
###############################################################################
# Temporal decoding
# -----------------
#
# We'll use a Logistic Regression for a binary classification as machine
# learning model.
# We will train the classifier on all left visual vs auditory trials on MEG
X = epochs.get_data() # MEG signals: n_epochs, n_channels, n_times
y = epochs.events[:, 2] # target: Audio left or right
clf = make_pipeline(StandardScaler(), LogisticRegression())
time_decod = SlidingEstimator(clf, n_jobs=1, scoring='roc_auc', verbose=True)
scores = cross_val_multiscore(time_decod, X, y, cv=5, n_jobs=1)
# Mean scores across cross-validation splits
scores = np.mean(scores, axis=0)
# Plot
fig, ax = plt.subplots()
ax.plot(epochs.times, scores, label='score')
ax.axhline(.5, color='k', linestyle='--', label='chance')
ax.set_xlabel('Times')
ax.set_ylabel('AUC') # Area Under the Curve
ax.legend()
ax.axvline(.0, color='k', linestyle='-')
ax.set_title('Sensor space decoding')
plt.show()
rangeD = ['Resp_Screen_Object', 'Resp_Screen_Side']
else:
y1 = whattodecod(cow_codes, y) # cow vs. bicycle
y2 = whattodecod(round_codes, y) # round vs. square
y3 = whattodecod(left_codes, y) # left vs. right
y4 = whattodecod(text_codes, y) # text vs. image
rangeY = [y1, y2, y3, y4]
rangeD = ['Object', 'Cue', 'Button', 'Modality']
# ******** decoding and saving *********
for nb_yy, (yy,
which_decod) in enumerate(zip(rangeY, rangeD)):
scores = cross_val_multiscore(clf,
data_to_dec,
yy,
cv=5,
n_jobs=-1)
scores = scores.mean(0)
fname = op.join(
directorydecod, '%s_%s_%s_%s_%s.npy' %
(subject, file_to_ana, which_decod, type_epo,
which_channels))
np.save(fname, scores)
del epochs
if file_to_ana is 'JustCue':
for subj_nb, (subject,
sessions) in enumerate(zip(subjects_id,
times[525:], (1.5, 1.6),
mode="mean")
labels = np.array(beh.movement_dir_sign)
# data + labels
# parameters for the classification
k_folds = 10 # cv folds
var_exp = 0.99 # percentage of variance
# generate iterator for cross validation
kf = StratifiedKFold(n_splits=k_folds, shuffle=True)
cv_iter = kf.split(np.zeros(data.shape), labels)
# pipeline for classification
cl = make_pipeline(RobustScaler(), PCA(n_components=var_exp),
LinearSVC(max_iter=10000, dual=False, penalty="l1"))
# temporal generalisation
temp_genr = GeneralizingEstimator(cl, n_jobs=1, scoring="roc_auc")
# cross validation
scores = cross_val_multiscore(temp_genr, data, labels, cv=cv_iter, n_jobs=-1)
scores_path = op.join(output_dir,
"clk_vs_anti_new_baseline-{}.npy".format(subject))
np.save(scores_path, scores)
print("saved", scores_path)
st_scores = []
for sub in subjects:
bids_path = dataset.update(subject=sub)
raw_haemo, epochs = epoch_preprocessing(bids_path)
epochs.pick(chroma)
X = epochs.get_data()
y = epochs.events[:, 2]
clf = make_pipeline(Scaler(epochs.info), Vectorizer(),
LogisticRegression(solver='liblinear'))
scores = 100 * cross_val_multiscore(
clf, X, y, cv=5, n_jobs=1, scoring='roc_auc')
st_scores.append(np.mean(scores, axis=0))
print(f"Average spatio-temporal ROC-AUC performance ({chroma}) = "
f"{np.round(np.mean(st_scores))} % ({np.round(np.std(st_scores))})")
# %%
# Conclusion
# ----------
#
# Data were epoched then decoding was performed on the hbo signal and the hbr
# signal. The HbO signal decodes the conditions with 6% greater accuracy
# than the HbR signal. For further discussion about the efficacy of fNIRS
# signals in decoding experimental condition see Luke et. al. (2021)
# :footcite:`Luke2021.11.19.469225`.
def run_time_decoding(subject_id, cond1, cond2, event_id):
print cond1, cond2
subject = "S%02d" % subject_id
data_path = os.path.join('/home/claire/DATA/Data_Face_House/' + subject +
'/EEG/')
raw_fname = data_path + subject + '-raw.fif'
event_fname = data_path + subject + '-eve.fif'
tmin, tmax = -0.2, 1
raw = mne.io.read_raw_fif(raw_fname, preload=True)
events = mne.read_events(event_fname)
picks = mne.pick_types(raw.info,
meg=False,
eeg=True,
stim=True,
eog=True,
exclude='bads')
# Read epochs
epochs = mne.Epochs(raw,
events,
event_id,
tmin,
tmax,
proj=True,
picks=picks,
baseline=(None, 0.),
preload=True,
decim=4)
epochs.pick_types(eeg=True, exclude='bads')
# only look at occipital channels
# select_chans = [u'Iz', u'Oz', u'O1', u'O2', u'O3', u'PO7', u'PO8', u'POz', u'PO1', u'PO3', u'PO2', u'PO4']
#select_chans = [ u'PO7', u'PO8']
#select_chans = [ u'Cz', u'FPz']
#ch_names=[ch_name.replace('', '') for ch_name in select_chans]
#epochs.pick_types(eeg=True).pick_channels(ch_names)
# fit and time decoder
X = epochs.get_data() # MEG signals: n_epochs, n_channels, n_times
y = epochs.events[:, 2] # target: Audio left or right
clf = make_pipeline(StandardScaler(), LogisticRegression())
time_decod = SlidingEstimator(clf, n_jobs=1, scoring='roc_auc')
scores = cross_val_multiscore(time_decod, X, y, cv=5, n_jobs=1)
# Mean scores across cross-validation splits
scores = np.mean(scores, axis=0)
# save scores
a_vs_b = '%s_vs_%s' % (cond1, cond2)
print 'a_vs_b = %s' % a_vs_b
fname_td = os.path.join(data_path, '%s-td-auc-%s.mat' % (subject, a_vs_b))
print 'Saving %s' % fname_td
from scipy.io import savemat
savemat(fname_td, {'scores': scores, 'times': epochs.times})
sfreq=epochs.info['sfreq'],
freqs=freqs,
output='power',
n_cycles=n_cycles)
n_epochs, n_channels, n_freqs, n_times = X.shape
X = X.reshape(n_epochs, n_channels, -1) # collapse freqs and time
# Run decoding on TFR output
for analysis in analyses:
fname = results_folder +\
'%s_tf_scores_%s_%s.npy' % (subject, 'Cue', analysis)
y = np.array(events_behavior[analysis])
clf = make_pipeline(
StandardScaler(),
force_predict(LogisticRegression(), 'predict_proba', axis=1))
scorer = scorer_auc
kwargs = dict()
le = preprocessing.LabelEncoder()
le.fit(y)
y = le.transform(y)
sel = np.where(y != 0)[0]
td = SlidingEstimator(clf,
scoring=make_scorer(scorer),
n_jobs=24,
**kwargs)
td.fit(X[sel], y[sel])
scores = cross_val_multiscore(td, X[sel], y[sel], cv=StratifiedKFold(12))
scores = scores.mean(axis=0)
scores = np.reshape(scores, (n_freqs, n_times))
# Save cross validated scores
np.save(fname, np.array(scores))
LinearModel(LogisticRegression(solver='liblinear')),
)
time_decoder = SlidingEstimator(
clf,
scoring='roc_auc',
n_jobs=n_jobs,
)
y = epochs_df['label'].values.copy()
y[y == 2] = 0
scores = cross_val_multiscore(
time_decoder,
X=label_ts,
y=y,
groups=epochs_df['session'],
cv=len(epochs_df['session'].unique()),
n_jobs=n_jobs,
)
time_decoder.fit(label_ts, y)
coef = get_coef(time_decoder, 'patterns_', inverse_transform=True)
# %%
# Plot
def fig_save(fig, path):
html = fig.to_html()
with open(path, 'w') as f:
f.write(html)