def test_get_coef_multiclass_full(n_classes, n_channels, n_times):
"""Test a full example with pattern extraction."""
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import StratifiedKFold
data = np.zeros((10 * n_classes, n_channels, n_times))
# Make only the first channel informative
for ii in range(n_classes):
data[ii * 10:(ii + 1) * 10, 0] = ii
events = np.zeros((len(data), 3), int)
events[:, 0] = np.arange(len(events))
events[:, 2] = data[:, 0, 0]
info = create_info(n_channels, 1000., 'eeg')
epochs = EpochsArray(data, info, events, tmin=0)
clf = make_pipeline(
Scaler(epochs.info),
Vectorizer(),
LinearModel(LogisticRegression(random_state=0, multi_class='ovr')),
)
scorer = 'roc_auc_ovr_weighted'
time_gen = GeneralizingEstimator(clf, scorer, verbose=True)
X = epochs.get_data()
y = epochs.events[:, 2]
n_splits = 3
cv = StratifiedKFold(n_splits=n_splits)
scores = cross_val_multiscore(time_gen, X, y, cv=cv, verbose=True)
want = (n_splits, )
if n_times > 1:
want += (n_times, n_times)
assert scores.shape == want
assert_array_less(0.8, scores)
clf.fit(X, y)
patterns = get_coef(clf, 'patterns_', inverse_transform=True)
assert patterns.shape == (n_classes, n_channels, n_times)
assert_allclose(patterns[:, 1:], 0., atol=1e-7) # no other channels useful
def test_decim():
"""Test evoked decimation."""
rng = np.random.RandomState(0)
n_epochs, n_channels, n_times = 5, 10, 20
dec_1, dec_2 = 2, 3
decim = dec_1 * dec_2
sfreq = 1000.
sfreq_new = sfreq / decim
data = rng.randn(n_epochs, n_channels, n_times)
events = np.array([np.arange(n_epochs), [0] * n_epochs, [1] * n_epochs]).T
info = create_info(n_channels, sfreq, 'eeg')
info['lowpass'] = sfreq_new / float(decim)
epochs = EpochsArray(data, info, events)
data_epochs = epochs.copy().decimate(decim).get_data()
data_epochs_2 = epochs.copy().decimate(decim, offset=1).get_data()
data_epochs_3 = epochs.decimate(dec_1).decimate(dec_2).get_data()
assert_array_equal(data_epochs, data[:, :, ::decim])
assert_array_equal(data_epochs_2, data[:, :, 1::decim])
assert_array_equal(data_epochs, data_epochs_3)
# Now let's do it with some real data
raw = read_raw_fif(raw_fname, add_eeg_ref=False)
events = read_events(event_name)
sfreq_new = raw.info['sfreq'] / decim
raw.info['lowpass'] = sfreq_new / 4. # suppress aliasing warnings
picks = pick_types(raw.info, meg=True, eeg=True, exclude=())
epochs = Epochs(raw, events, 1, -0.2, 0.5, picks=picks, preload=True,
add_eeg_ref=False)
for offset in (0, 1):
ev_ep_decim = epochs.copy().decimate(decim, offset).average()
ev_decim = epochs.average().decimate(decim, offset)
expected_times = epochs.times[offset::decim]
assert_allclose(ev_decim.times, expected_times)
assert_allclose(ev_ep_decim.times, expected_times)
expected_data = epochs.get_data()[:, :, offset::decim].mean(axis=0)
assert_allclose(ev_decim.data, expected_data)
assert_allclose(ev_ep_decim.data, expected_data)
assert_equal(ev_decim.info['sfreq'], sfreq_new)
assert_array_equal(ev_decim.times, expected_times)
mode='mean',
vmin=vmin,
vmax=vmax,
title='Using Morlet wavelets and EpochsTFR',
show=False)
###############################################################################
# Operating on arrays
# -------------------
#
# MNE also has versions of the functions above which operate on numpy arrays
# instead of MNE objects. They expect inputs of the shape
# ``(n_epochs, n_channels, n_times)``. They will also return a numpy array
# of shape ``(n_epochs, n_channels, n_freqs, n_times)``.
power = tfr_array_morlet(epochs.get_data(),
sfreq=epochs.info['sfreq'],
freqs=freqs,
n_cycles=n_cycles,
output='avg_power')
# Baseline the output
rescale(power, epochs.times, (0., 0.1), mode='mean', copy=False)
fig, ax = plt.subplots()
mesh = ax.pcolormesh(epochs.times * 1000,
freqs,
power[0],
cmap='RdBu_r',
vmin=vmin,
vmax=vmax)
ax.set_title('TFR calculated on a numpy array')
ax.set(ylim=freqs[[0, -1]], xlabel='Time (ms)')
power = tfr_morlet(epochs, freqs=freqs,
n_cycles=n_cycles, return_itc=False, average=False)
print(type(power))
avgpower = power.average()
avgpower.plot([0], baseline=(0., 0.1), mode='mean', vmin=vmin, vmax=vmax,
title='Using Morlet wavelets and EpochsTFR', show=False)
###############################################################################
# Operating on arrays
# -------------------
#
# MNE also has versions of the functions above which operate on numpy arrays
# instead of MNE objects. They expect inputs of the shape
# ``(n_epochs, n_channels, n_times)``. They will also return a numpy array
# of shape ``(n_epochs, n_channels, n_frequencies, n_times)``.
power = tfr_array_morlet(epochs.get_data(), sfreq=epochs.info['sfreq'],
frequencies=freqs, n_cycles=n_cycles,
output='avg_power')
# Baseline the output
rescale(power, epochs.times, (0., 0.1), mode='mean', copy=False)
fig, ax = plt.subplots()
mesh = ax.pcolormesh(epochs.times * 1000, freqs, power[0],
cmap='RdBu_r', vmin=vmin, vmax=vmax)
ax.set_title('TFR calculated on a numpy array')
ax.set(ylim=freqs[[0, -1]], xlabel='Time (ms)')
fig.colorbar(mesh)
plt.tight_layout()
plt.show()
power = tfr_morlet(epochs, freqs=freqs,
n_cycles=n_cycles, return_itc=False, average=False)
print(type(power))
avgpower = power.average()
avgpower.plot([0], baseline=(0., 0.1), mode='mean', vmin=vmin, vmax=vmax,
title='Using Morlet wavelets and EpochsTFR', show=False)
###############################################################################
# Operating on arrays
# -------------------
#
# MNE also has versions of the functions above which operate on numpy arrays
# instead of MNE objects. They expect inputs of the shape
# ``(n_epochs, n_channels, n_times)``. They will also return a numpy array
# of shape ``(n_epochs, n_channels, n_freqs, n_times)``.
power = tfr_array_morlet(epochs.get_data(), sfreq=epochs.info['sfreq'],
freqs=freqs, n_cycles=n_cycles,
output='avg_power')
# Baseline the output
rescale(power, epochs.times, (0., 0.1), mode='mean', copy=False)
fig, ax = plt.subplots()
mesh = ax.pcolormesh(epochs.times * 1000, freqs, power[0],
cmap='RdBu_r', vmin=vmin, vmax=vmax)
ax.set_title('TFR calculated on a numpy array')
ax.set(ylim=freqs[[0, -1]], xlabel='Time (ms)')
fig.colorbar(mesh)
plt.tight_layout()
plt.show()
raw = mne.io.read_raw_fif(raw_fname, preload=True)
raw.pick_types(meg='grad', eog=True) # we just look at gradiometers
# bandpass filter and compute Hilbert
raw.filter(fmin, fmax, n_jobs=1, # use more jobs to speed up.
l_trans_bandwidth=1, # make sure filter params are the same
h_trans_bandwidth=1, # in each band and skip "auto" option.
fir_design='firwin')
raw.apply_hilbert(n_jobs=1, envelope=False)
epochs = mne.Epochs(raw, events, event_id, tmin, tmax, baseline=baseline,
reject=dict(grad=4000e-13, eog=350e-6), preload=True)
# remove evoked response and get analytic signal (envelope)
epochs.subtract_evoked() # for this we need to construct new epochs.
epochs = mne.EpochsArray(
data=np.abs(epochs.get_data()), info=epochs.info, tmin=epochs.tmin)
# now average and move on
frequency_map.append(((band, fmin, fmax), epochs))
beta_data = frequency_map[2][1]
beta_sim = sd.make_sim_data(beta_data, order=17)
alpha_data = frequency_map[1][1]
alpha_sim = sd.make_sim_data(alpha_data, order=17)
theta_data = frequency_map[0][1]
theta_sim = sd.make_sim_data(theta_data, order=17)
gamma_data = frequency_map[3][1]
gamma_sim = sd.make_sim_data(theta_data, order=17)
beta_sim.average().plot_joint()
beta_data.average().plot_joint()
beta_diff = mne.combine_evoked([beta_data.average(), -beta_sim.average()],
