Compare the different ICA algorithms in MNE

Different ICA algorithms are fit to raw MEG data, and the corresponding maps are displayed.

# Authors: Pierre Ablin <pierreablin@gmail.com>
#
# License: BSD-3-Clause

from time import time

import mne
from mne.preprocessing import ICA
from mne.datasets import sample


print(__doc__)

Read and preprocess the data. Preprocessing consists of:

• MEG channel selection

• 1-30 Hz band-pass filter

data_path = sample.data_path()
meg_path = data_path / "MEG" / "sample"
raw_fname = meg_path / "sample_audvis_filt-0-40_raw.fif"

raw = mne.io.read_raw_fif(raw_fname).crop(0, 60).pick("meg").load_data()

reject = dict(mag=5e-12, grad=4000e-13)
raw.filter(1, 30, fir_design="firwin")

Opening raw data file /home/circleci/mne_data/MNE-sample-data/MEG/sample/sample_audvis_filt-0-40_raw.fif...
    Read a total of 4 projection items:
        PCA-v1 (1 x 102)  idle
        PCA-v2 (1 x 102)  idle
        PCA-v3 (1 x 102)  idle
        Average EEG reference (1 x 60)  idle
    Range : 6450 ... 48149 =     42.956 ...   320.665 secs
Ready.
Removing projector <Projection | Average EEG reference, active : False, n_channels : 60>
Reading 0 ... 9009  =      0.000 ...    59.999 secs...
Filtering raw data in 1 contiguous segment
Setting up band-pass filter from 1 - 30 Hz

FIR filter parameters
---------------------
Designing a one-pass, zero-phase, non-causal bandpass filter:
- Windowed time-domain design (firwin) method
- Hamming window with 0.0194 passband ripple and 53 dB stopband attenuation
- Lower passband edge: 1.00
- Lower transition bandwidth: 1.00 Hz (-6 dB cutoff frequency: 0.50 Hz)
- Upper passband edge: 30.00 Hz
- Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
- Filter length: 497 samples (3.310 s)

[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    0.0s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:    0.0s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed:    0.0s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   4 out of   4 | elapsed:    0.0s remaining:    0.0s
[Parallel(n_jobs=1)]: Done 306 out of 306 | elapsed:    0.2s finished

Measurement date	December 03, 2002 19:01:10 GMT
Experimenter	Unknown
Participant	Unknown
Digitized points	146 points
Good channels	204 Gradiometers, 102 Magnetometers
Bad channels	MEG 2443
EOG channels	Not available
ECG channels	Not available
Sampling frequency	150.15 Hz
Highpass	1.00 Hz
Lowpass	30.00 Hz
Projections	PCA-v1 : off PCA-v2 : off PCA-v3 : off
Filenames	sample_audvis_filt-0-40_raw.fif
Duration	00:00:60 (HH:MM:SS)

Define a function that runs ICA on the raw MEG data and plots the components

def run_ica(method, fit_params=None):
    ica = ICA(
        n_components=20,
        method=method,
        fit_params=fit_params,
        max_iter="auto",
        random_state=0,
    )
    t0 = time()
    ica.fit(raw, reject=reject)
    fit_time = time() - t0
    title = "ICA decomposition using %s (took %.1fs)" % (method, fit_time)
    ica.plot_components(title=title)

FastICA

run_ica("fastica")

Fitting ICA to data using 305 channels (please be patient, this may take a while)
Selecting by number: 20 components
Fitting ICA took 0.7s.

Picard

run_ica("picard")

Fitting ICA to data using 305 channels (please be patient, this may take a while)
Selecting by number: 20 components
Fitting ICA took 2.8s.

Infomax

run_ica("infomax")

Fitting ICA to data using 305 channels (please be patient, this may take a while)
Selecting by number: 20 components

Fitting ICA took 2.9s.

Extended Infomax

run_ica("infomax", fit_params=dict(extended=True))

Fitting ICA to data using 305 channels (please be patient, this may take a while)
Selecting by number: 20 components
Computing Extended Infomax ICA
Fitting ICA took 4.3s.

Estimated memory usage: 10 MB