y_train = y_true[train_index]
# transform
X_test = xdawn.transform(epochs[test_index])
y_test = y_true[test_index]
# All time decoder
# Fit
raw_decoder.fit(X_train, y_train)
# Predict
y_pred[test_index] = raw_decoder.predict(X_test)
# Time decoder
# Fit
time_decoder.fit(X_train, y_train)
# Predict
y_pred_time[test_index] = time_decoder.predict(X_test)
# Time window decoder
for window_length, _info in time_windows.items():
# _info[0], w_start
# _info[1], w_length
# _info[2], w_time
w_length = _info[1]
for j, w_start in enumerate(_info[0]):
w_stop = w_start + w_length
print(w_start)
# Crop X_train and X_test
_X_train = X_train[:, :, w_start:w_start + w_length]
_X_test = X_test[:, :, w_start:w_start + w_length]
# Fit
raw_decoder.fit(_X_train, y_train)
y_all = np.concatenate([y1, y2], axis=0)
X_all.shape, y_all.shape
times = worker.clean_epochs.times
n_splits = int(y1.shape[0] / 64)
y_pred_time = np.zeros((3313, 141))
skf = StratifiedKFold(n_splits=n_splits, shuffle=False)
for train_index, test_index in skf.split(X_all, y_all):
X_train, y_train = X_all[train_index], y_all[train_index]
X_test, y_test = X_all[test_index], y_all[test_index]
estimator.fit(X_train, y_train)
y_pred_time[test_index] = estimator.predict(X_test)
# %%
y_pred_time.shape
# %%
report = metrics.classification_report(y_true=y_all,
y_pred=y_pred_time[:, 60],
output_dict=True)
print(report)
# %%
def fuck_report(report):
# I don't know why report has to be 2-layers dictionary,
# Prepare predicted label matrix
num_samples, num_times = X_all.shape[0], X_all.shape[2]
y_pred_sliding = np.zeros((num_samples, num_times))
# Cross validation
skf = StratifiedKFold(n_splits=n_splits, shuffle=False)
for train_index, test_index in skf.split(X_all, y_all):
# Separate training and testing data
X_train, y_train = X_all[train_index], y_all[train_index]
X_test, y_test = X_all[test_index], y_all[test_index]
# Fit estimator
estimator.fit(X_train, y_train)
# Predict
y_pred_sliding[test_index] = estimator.predict(X_test)
# Summary results
output_dict = dict(
times=times,
y_all=y_all,
y_pred_sliding=y_pred_sliding,
)
# Save results
with open(os.path.join(RESULTS_FOLDER, f'{running_name}_sliding.pkl'),
'wb') as f:
pickle.dump(output_dict, f)
# %%