Note
Go to the end to download the full example code.
Extracting \(\mu\)-wave from the somato-sensory dataset#
This example illustrates how to learn rank-1 atoms [1] on the multivariate
somato-sensorymotor dataset from mne. The displayed results highlight
the presence of \(\mu\)-waves located in the SI cortex.
# Authors: Thomas Moreau <thomas.moreau@inria.fr>
# Mainak Jas <mainak.jas@telecom-paristech.fr>
# Tom Dupre La Tour <tom.duprelatour@telecom-paristech.fr>
# Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
#
# License: BSD (3-clause)
Let us first define the parameters of our model.
sfreq = 150.
# Define the shape of the dictionary
n_atoms = 25
n_times_atom = int(round(sfreq * 1.0)) # 1000. ms
Next, we define the parameters for multivariate CSC
from alphacsc import BatchCDL
cdl = BatchCDL(
# Shape of the dictionary
n_atoms=n_atoms,
n_times_atom=n_times_atom,
# Request a rank1 dictionary with unit norm temporal and spatial maps
rank1=True, uv_constraint='separate',
# Initialize the dictionary with random chunk from the data
D_init='chunk',
# rescale the regularization parameter to be 20% of lambda_max
lmbd_max="scaled", reg=.2,
# Number of iteration for the alternate minimization and cvg threshold
n_iter=100, eps=1e-4,
# solver for the z-step
solver_z="lgcd", solver_z_kwargs={'tol': 1e-2, 'max_iter': 1000},
# solver for the d-step
solver_d='alternate_adaptive', solver_d_kwargs={'max_iter': 300},
# Technical parameters
verbose=1, random_state=0, n_jobs=6)
Here, we load the data from the somato-sensory dataset and preprocess them in epochs. The epochs are selected around the stim, starting 2 seconds before and finishing 4 seconds after.
Using default location ~/mne_data for somato...
0%| | 0.00/611M [00:00<?, ?B/s]
0%| | 546k/611M [00:00<02:04, 4.89MB/s]
0%| | 1.32M/611M [00:00<01:44, 5.81MB/s]
0%|▏ | 2.22M/611M [00:00<01:25, 7.14MB/s]
1%|▏ | 3.93M/611M [00:00<00:55, 10.9MB/s]
1%|▎ | 6.02M/611M [00:00<00:42, 14.3MB/s]
2%|▌ | 9.34M/611M [00:00<00:29, 20.2MB/s]
2%|▊ | 12.2M/611M [00:00<00:26, 22.8MB/s]
2%|▉ | 15.0M/611M [00:00<00:24, 24.5MB/s]
3%|█ | 17.9M/611M [00:00<00:23, 25.7MB/s]
3%|█▎ | 20.7M/611M [00:01<00:22, 26.5MB/s]
4%|█▍ | 23.5M/611M [00:01<00:21, 27.0MB/s]
4%|█▋ | 26.4M/611M [00:01<00:21, 27.5MB/s]
5%|█▊ | 29.2M/611M [00:01<00:20, 27.7MB/s]
5%|█▉ | 32.1M/611M [00:01<00:20, 27.9MB/s]
6%|██▏ | 34.9M/611M [00:01<00:20, 28.0MB/s]
6%|██▎ | 37.8M/611M [00:01<00:20, 28.1MB/s]
7%|██▌ | 40.6M/611M [00:01<00:20, 28.2MB/s]
7%|██▋ | 43.4M/611M [00:01<00:20, 28.2MB/s]
8%|██▉ | 46.3M/611M [00:01<00:19, 28.2MB/s]
8%|███ | 49.1M/611M [00:02<00:19, 28.3MB/s]
9%|███▏ | 52.0M/611M [00:02<00:19, 28.3MB/s]
9%|███▍ | 54.8M/611M [00:02<00:19, 28.3MB/s]
9%|███▌ | 57.6M/611M [00:02<00:19, 28.3MB/s]
10%|███▊ | 60.5M/611M [00:02<00:19, 28.3MB/s]
10%|███▉ | 63.3M/611M [00:02<00:19, 28.3MB/s]
11%|████ | 66.2M/611M [00:02<00:19, 28.3MB/s]
11%|████▎ | 69.0M/611M [00:02<00:19, 28.3MB/s]
12%|████▍ | 71.9M/611M [00:02<00:18, 28.4MB/s]
12%|████▋ | 74.7M/611M [00:02<00:18, 28.3MB/s]
13%|████▊ | 77.6M/611M [00:03<00:18, 28.4MB/s]
13%|█████ | 80.4M/611M [00:03<00:18, 28.3MB/s]
14%|█████▏ | 83.2M/611M [00:03<00:18, 28.3MB/s]
14%|█████▎ | 86.1M/611M [00:03<00:18, 28.3MB/s]
15%|█████▌ | 88.9M/611M [00:03<00:18, 28.3MB/s]
15%|█████▋ | 91.8M/611M [00:03<00:18, 28.3MB/s]
15%|█████▉ | 94.6M/611M [00:03<00:18, 28.3MB/s]
16%|██████ | 97.4M/611M [00:03<00:18, 28.3MB/s]
16%|██████▍ | 100M/611M [00:03<00:18, 28.3MB/s]
17%|██████▌ | 103M/611M [00:03<00:17, 28.3MB/s]
17%|██████▊ | 106M/611M [00:04<00:17, 28.3MB/s]
18%|██████▉ | 109M/611M [00:04<00:17, 28.3MB/s]
18%|███████▏ | 112M/611M [00:04<00:17, 28.3MB/s]
19%|███████▎ | 114M/611M [00:04<00:17, 28.3MB/s]
19%|███████▍ | 117M/611M [00:04<00:17, 28.3MB/s]
20%|███████▋ | 120M/611M [00:04<00:17, 28.3MB/s]
20%|███████▊ | 123M/611M [00:04<00:17, 28.3MB/s]
21%|████████ | 126M/611M [00:04<00:17, 28.3MB/s]
21%|████████▏ | 129M/611M [00:04<00:17, 28.3MB/s]
22%|████████▍ | 132M/611M [00:04<00:16, 28.3MB/s]
22%|████████▌ | 134M/611M [00:05<00:16, 28.3MB/s]
22%|████████▊ | 137M/611M [00:05<00:16, 28.3MB/s]
23%|████████▉ | 140M/611M [00:05<00:16, 28.3MB/s]
23%|█████████▏ | 143M/611M [00:05<00:16, 28.3MB/s]
24%|█████████▎ | 146M/611M [00:05<00:16, 28.3MB/s]
24%|█████████▍ | 149M/611M [00:05<00:16, 28.3MB/s]
25%|█████████▋ | 151M/611M [00:05<00:16, 28.4MB/s]
25%|█████████▊ | 154M/611M [00:05<00:16, 28.3MB/s]
26%|██████████ | 157M/611M [00:05<00:15, 28.4MB/s]
26%|██████████▏ | 160M/611M [00:05<00:15, 28.3MB/s]
27%|██████████▍ | 163M/611M [00:06<00:15, 28.3MB/s]
27%|██████████▌ | 166M/611M [00:06<00:15, 28.3MB/s]
28%|██████████▊ | 169M/611M [00:06<00:15, 28.4MB/s]
28%|██████████▉ | 171M/611M [00:06<00:15, 28.3MB/s]
29%|███████████▏ | 174M/611M [00:06<00:15, 28.4MB/s]
29%|███████████▎ | 177M/611M [00:06<00:15, 28.4MB/s]
29%|███████████▍ | 180M/611M [00:06<00:15, 28.4MB/s]
30%|███████████▋ | 183M/611M [00:06<00:15, 28.3MB/s]
30%|███████████▊ | 186M/611M [00:06<00:15, 28.3MB/s]
31%|████████████ | 188M/611M [00:06<00:14, 28.3MB/s]
31%|████████████▏ | 191M/611M [00:07<00:14, 28.3MB/s]
32%|████████████▍ | 194M/611M [00:07<00:14, 28.3MB/s]
32%|████████████▌ | 197M/611M [00:07<00:14, 28.3MB/s]
33%|████████████▊ | 200M/611M [00:07<00:14, 28.3MB/s]
33%|████████████▉ | 203M/611M [00:07<00:14, 28.3MB/s]
34%|█████████████▏ | 205M/611M [00:07<00:14, 28.3MB/s]
34%|█████████████▎ | 208M/611M [00:07<00:14, 28.3MB/s]
35%|█████████████▍ | 211M/611M [00:07<00:14, 28.3MB/s]
35%|█████████████▋ | 214M/611M [00:07<00:14, 28.3MB/s]
36%|█████████████▊ | 217M/611M [00:07<00:13, 28.4MB/s]
36%|██████████████ | 220M/611M [00:08<00:13, 28.3MB/s]
36%|██████████████▏ | 223M/611M [00:08<00:13, 28.4MB/s]
37%|██████████████▍ | 225M/611M [00:08<00:13, 28.3MB/s]
37%|██████████████▌ | 228M/611M [00:08<00:13, 28.4MB/s]
38%|██████████████▊ | 231M/611M [00:08<00:13, 28.3MB/s]
38%|██████████████▉ | 234M/611M [00:08<00:13, 28.3MB/s]
39%|███████████████ | 237M/611M [00:08<00:13, 28.3MB/s]
39%|███████████████▎ | 240M/611M [00:08<00:13, 28.3MB/s]
40%|███████████████▍ | 242M/611M [00:08<00:12, 28.4MB/s]
40%|███████████████▋ | 245M/611M [00:08<00:12, 28.3MB/s]
41%|███████████████▊ | 248M/611M [00:09<00:12, 28.3MB/s]
41%|████████████████ | 251M/611M [00:09<00:12, 28.3MB/s]
42%|████████████████▏ | 254M/611M [00:09<00:12, 28.3MB/s]
42%|████████████████▍ | 257M/611M [00:09<00:12, 28.3MB/s]
43%|████████████████▌ | 259M/611M [00:09<00:12, 28.0MB/s]
43%|████████████████▊ | 262M/611M [00:09<00:12, 27.1MB/s]
43%|████████████████▉ | 265M/611M [00:09<00:13, 26.4MB/s]
44%|█████████████████ | 268M/611M [00:09<00:12, 27.0MB/s]
44%|█████████████████▎ | 271M/611M [00:09<00:12, 27.2MB/s]
45%|█████████████████▍ | 273M/611M [00:09<00:12, 27.6MB/s]
45%|█████████████████▋ | 276M/611M [00:10<00:12, 27.7MB/s]
46%|█████████████████▊ | 279M/611M [00:10<00:11, 27.9MB/s]
46%|██████████████████ | 282M/611M [00:10<00:11, 28.1MB/s]
47%|██████████████████▏ | 285M/611M [00:10<00:11, 28.1MB/s]
47%|██████████████████▎ | 288M/611M [00:10<00:11, 28.1MB/s]
48%|██████████████████▌ | 290M/611M [00:10<00:11, 28.1MB/s]
48%|██████████████████▋ | 293M/611M [00:10<00:11, 28.1MB/s]
48%|██████████████████▉ | 296M/611M [00:10<00:11, 28.1MB/s]
49%|███████████████████ | 299M/611M [00:10<00:10, 28.4MB/s]
49%|███████████████████▎ | 302M/611M [00:10<00:10, 28.3MB/s]
50%|███████████████████▍ | 305M/611M [00:11<00:10, 28.3MB/s]
50%|███████████████████▋ | 307M/611M [00:11<00:10, 28.3MB/s]
51%|███████████████████▊ | 310M/611M [00:11<00:10, 28.2MB/s]
51%|████████████████████ | 313M/611M [00:11<00:10, 28.2MB/s]
52%|████████████████████▏ | 316M/611M [00:11<00:10, 28.2MB/s]
52%|████████████████████▎ | 319M/611M [00:11<00:10, 28.2MB/s]
53%|████████████████████▌ | 322M/611M [00:11<00:10, 28.3MB/s]
53%|████████████████████▋ | 324M/611M [00:11<00:10, 28.3MB/s]
54%|████████████████████▉ | 327M/611M [00:11<00:10, 28.2MB/s]
54%|█████████████████████ | 330M/611M [00:12<00:09, 28.4MB/s]
55%|█████████████████████▎ | 333M/611M [00:12<00:09, 28.4MB/s]
55%|█████████████████████▍ | 336M/611M [00:12<00:09, 28.3MB/s]
55%|█████████████████████▋ | 339M/611M [00:12<00:09, 28.4MB/s]
56%|█████████████████████▊ | 342M/611M [00:12<00:09, 28.3MB/s]
56%|█████████████████████▉ | 344M/611M [00:12<00:09, 28.3MB/s]
57%|██████████████████████▏ | 347M/611M [00:12<00:09, 28.3MB/s]
57%|██████████████████████▎ | 350M/611M [00:12<00:09, 28.3MB/s]
58%|██████████████████████▌ | 353M/611M [00:12<00:09, 28.3MB/s]
58%|██████████████████████▋ | 356M/611M [00:12<00:09, 28.3MB/s]
59%|██████████████████████▉ | 359M/611M [00:13<00:08, 28.4MB/s]
59%|███████████████████████ | 361M/611M [00:13<00:08, 28.3MB/s]
60%|███████████████████████▎ | 364M/611M [00:13<00:08, 28.2MB/s]
60%|███████████████████████▍ | 367M/611M [00:13<00:08, 28.6MB/s]
61%|███████████████████████▋ | 370M/611M [00:13<00:08, 28.4MB/s]
61%|███████████████████████▊ | 373M/611M [00:13<00:08, 28.0MB/s]
62%|████████████████████████ | 376M/611M [00:13<00:07, 29.3MB/s]
62%|████████████████████████▏ | 379M/611M [00:13<00:08, 26.6MB/s]
63%|████████████████████████▍ | 382M/611M [00:13<00:08, 27.1MB/s]
63%|████████████████████████▌ | 385M/611M [00:13<00:08, 27.4MB/s]
63%|████████████████████████▊ | 388M/611M [00:14<00:08, 27.7MB/s]
64%|████████████████████████▉ | 390M/611M [00:14<00:07, 27.9MB/s]
64%|█████████████████████████ | 393M/611M [00:14<00:07, 28.0MB/s]
65%|█████████████████████████▎ | 396M/611M [00:14<00:07, 28.1MB/s]
65%|█████████████████████████▍ | 399M/611M [00:14<00:07, 28.2MB/s]
66%|█████████████████████████▋ | 402M/611M [00:14<00:07, 28.2MB/s]
66%|█████████████████████████▊ | 405M/611M [00:14<00:07, 28.3MB/s]
67%|██████████████████████████ | 407M/611M [00:14<00:07, 28.2MB/s]
67%|██████████████████████████▏ | 410M/611M [00:14<00:07, 28.3MB/s]
68%|██████████████████████████▍ | 413M/611M [00:14<00:06, 28.3MB/s]
68%|██████████████████████████▌ | 416M/611M [00:15<00:06, 28.3MB/s]
69%|██████████████████████████▊ | 419M/611M [00:15<00:06, 28.3MB/s]
69%|██████████████████████████▉ | 422M/611M [00:15<00:06, 28.3MB/s]
70%|███████████████████████████ | 425M/611M [00:15<00:06, 28.3MB/s]
70%|███████████████████████████▎ | 427M/611M [00:15<00:06, 28.3MB/s]
70%|███████████████████████████▍ | 430M/611M [00:15<00:06, 28.3MB/s]
71%|███████████████████████████▋ | 433M/611M [00:15<00:06, 28.3MB/s]
71%|███████████████████████████▊ | 436M/611M [00:15<00:06, 28.3MB/s]
72%|████████████████████████████ | 439M/611M [00:15<00:06, 28.3MB/s]
72%|████████████████████████████▏ | 442M/611M [00:15<00:05, 28.3MB/s]
73%|████████████████████████████▍ | 444M/611M [00:16<00:05, 28.3MB/s]
73%|████████████████████████████▌ | 447M/611M [00:16<00:05, 28.3MB/s]
74%|████████████████████████████▊ | 450M/611M [00:16<00:05, 28.3MB/s]
74%|████████████████████████████▉ | 453M/611M [00:16<00:05, 28.3MB/s]
75%|█████████████████████████████ | 456M/611M [00:16<00:05, 28.3MB/s]
75%|█████████████████████████████▎ | 459M/611M [00:16<00:05, 28.3MB/s]
76%|█████████████████████████████▍ | 461M/611M [00:16<00:05, 28.3MB/s]
76%|█████████████████████████████▋ | 464M/611M [00:16<00:05, 28.3MB/s]
77%|█████████████████████████████▊ | 467M/611M [00:16<00:05, 28.3MB/s]
77%|██████████████████████████████ | 470M/611M [00:16<00:04, 28.3MB/s]
77%|██████████████████████████████▏ | 473M/611M [00:17<00:04, 28.3MB/s]
78%|██████████████████████████████▍ | 476M/611M [00:17<00:04, 28.3MB/s]
78%|██████████████████████████████▌ | 478M/611M [00:17<00:04, 28.3MB/s]
79%|██████████████████████████████▋ | 481M/611M [00:17<00:04, 28.3MB/s]
79%|██████████████████████████████▉ | 484M/611M [00:17<00:04, 28.3MB/s]
80%|███████████████████████████████ | 487M/611M [00:17<00:04, 28.3MB/s]
80%|███████████████████████████████▎ | 490M/611M [00:17<00:04, 28.3MB/s]
81%|███████████████████████████████▍ | 493M/611M [00:17<00:04, 28.3MB/s]
81%|███████████████████████████████▋ | 495M/611M [00:17<00:04, 28.3MB/s]
82%|███████████████████████████████▊ | 498M/611M [00:17<00:03, 28.3MB/s]
82%|████████████████████████████████ | 501M/611M [00:18<00:03, 28.3MB/s]
83%|████████████████████████████████▏ | 504M/611M [00:18<00:03, 28.3MB/s]
83%|████████████████████████████████▍ | 507M/611M [00:18<00:03, 28.3MB/s]
83%|████████████████████████████████▌ | 510M/611M [00:18<00:03, 28.3MB/s]
84%|████████████████████████████████▋ | 513M/611M [00:18<00:03, 28.3MB/s]
84%|████████████████████████████████▉ | 515M/611M [00:18<00:03, 28.3MB/s]
85%|█████████████████████████████████ | 518M/611M [00:18<00:03, 28.3MB/s]
85%|█████████████████████████████████▎ | 521M/611M [00:18<00:03, 28.3MB/s]
86%|█████████████████████████████████▍ | 524M/611M [00:18<00:03, 28.3MB/s]
86%|█████████████████████████████████▋ | 527M/611M [00:18<00:02, 28.3MB/s]
87%|█████████████████████████████████▊ | 530M/611M [00:19<00:02, 28.3MB/s]
87%|██████████████████████████████████ | 532M/611M [00:19<00:02, 28.3MB/s]
88%|██████████████████████████████████▏ | 535M/611M [00:19<00:02, 28.3MB/s]
88%|██████████████████████████████████▍ | 538M/611M [00:19<00:02, 28.3MB/s]
89%|██████████████████████████████████▌ | 541M/611M [00:19<00:02, 28.3MB/s]
89%|██████████████████████████████████▋ | 544M/611M [00:19<00:02, 28.3MB/s]
90%|██████████████████████████████████▉ | 547M/611M [00:19<00:02, 28.3MB/s]
90%|███████████████████████████████████ | 549M/611M [00:19<00:02, 28.3MB/s]
90%|███████████████████████████████████▎ | 552M/611M [00:19<00:02, 28.3MB/s]
91%|███████████████████████████████████▍ | 555M/611M [00:19<00:02, 27.4MB/s]
91%|███████████████████████████████████▋ | 558M/611M [00:20<00:02, 24.1MB/s]
92%|███████████████████████████████████▊ | 561M/611M [00:20<00:01, 25.8MB/s]
92%|████████████████████████████████████ | 564M/611M [00:20<00:01, 26.6MB/s]
93%|████████████████████████████████████▏ | 567M/611M [00:20<00:01, 27.0MB/s]
93%|████████████████████████████████████▍ | 569M/611M [00:20<00:01, 27.4MB/s]
94%|████████████████████████████████████▌ | 572M/611M [00:20<00:01, 27.7MB/s]
94%|████████████████████████████████████▋ | 575M/611M [00:20<00:01, 27.9MB/s]
95%|████████████████████████████████████▉ | 578M/611M [00:20<00:01, 28.0MB/s]
95%|█████████████████████████████████████ | 581M/611M [00:20<00:01, 28.2MB/s]
96%|█████████████████████████████████████▎ | 584M/611M [00:21<00:00, 28.2MB/s]
96%|█████████████████████████████████████▍ | 587M/611M [00:21<00:00, 28.2MB/s]
97%|█████████████████████████████████████▋ | 589M/611M [00:21<00:00, 28.3MB/s]
97%|█████████████████████████████████████▊ | 592M/611M [00:21<00:00, 28.3MB/s]
97%|██████████████████████████████████████ | 595M/611M [00:21<00:00, 28.3MB/s]
98%|██████████████████████████████████████▏| 598M/611M [00:21<00:00, 28.3MB/s]
98%|██████████████████████████████████████▍| 601M/611M [00:21<00:00, 28.3MB/s]
99%|██████████████████████████████████████▌| 604M/611M [00:21<00:00, 28.3MB/s]
99%|██████████████████████████████████████▋| 606M/611M [00:21<00:00, 28.3MB/s]
100%|██████████████████████████████████████▉| 609M/611M [00:21<00:00, 28.3MB/s]
0%| | 0.00/611M [00:00<?, ?B/s]
100%|███████████████████████████████████████| 611M/611M [00:00<00:00, 2.72TB/s]
Attempting to create new mne-python configuration file:
/github/home/.mne/mne-python.json
Download complete in 35s (582.2 MB)
Opening raw data file /github/home/mne_data/MNE-somato-data/sub-01/meg/sub-01_task-somato_meg.fif...
Range : 237600 ... 506999 = 791.189 ... 1688.266 secs
Ready.
Reading 0 ... 269399 = 0.000 ... 897.077 secs...
Filtering raw data in 1 contiguous segment
Setting up band-stop filter
FIR filter parameters
---------------------
Designing a one-pass, zero-phase, non-causal bandstop filter:
- Windowed time-domain design (firwin) method
- Hamming window with 0.0194 passband ripple and 53 dB stopband attenuation
- Lower transition bandwidth: 0.50 Hz
- Upper transition bandwidth: 0.50 Hz
- Filter length: 1983 samples (6.603 s)
Filtering raw data in 1 contiguous segment
Setting up high-pass filter at 2 Hz
FIR filter parameters
---------------------
Designing a one-pass, zero-phase, non-causal highpass filter:
- Windowed time-domain design (firwin) method
- Hamming window with 0.0194 passband ripple and 53 dB stopband attenuation
- Lower passband edge: 2.00
- Lower transition bandwidth: 2.00 Hz (-6 dB cutoff frequency: 1.00 Hz)
- Filter length: 497 samples (1.655 s)
111 events found on stim channel STI 014
Event IDs: [1]
Not setting metadata
111 matching events found
Setting baseline interval to [-3.9992341833870637, 0.0] s
Applying baseline correction (mode: mean)
0 projection items activated
Using data from preloaded Raw for 111 events and 1202 original time points ...
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
5 bad epochs dropped
NOTE: pick_types() is a legacy function. New code should use inst.pick(...).
/github/workspace/alphacsc/datasets/mne_data.py:98: RuntimeWarning: Something went wrong in the data-driven estimation of the data rank as it exceeds the theoretical rank from the info (204 > 64). Consider setting rank to "auto" or setting it explicitly as an integer.
cov = mne.compute_covariance(epochs_cov)
Reducing data rank from 204 -> 204
Estimating covariance using EMPIRICAL
Done.
Number of samples used : 127412
[done]
Not setting metadata
111 matching events found
Setting baseline interval to [-2.001282051803185, 0.0] s
Applying baseline correction (mode: mean)
0 projection items activated
Using data from preloaded Raw for 111 events and 1803 original time points ...
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
Rejecting epoch based on EOG : ['EOG 061']
8 bad epochs dropped
NOTE: pick_types() is a legacy function. New code should use inst.pick(...).
Fit the model and learn rank1 atoms
..............
[BatchCDL] Converged after 14 iteration, (dz, du) = 8.765e-05, 8.726e-05
[BatchCDL] Fit in 270.8s
<alphacsc.convolutional_dictionary_learning.BatchCDL object at 0x7f05b1f4d730>
Display the 4-th atom, which displays a \(\mu\)-waveform in its temporal pattern.
import mne
import numpy as np
import matplotlib.pyplot as plt
i_atom = 4
n_plots = 3
figsize = (n_plots * 5, 5.5)
fig, axes = plt.subplots(1, n_plots, figsize=figsize, squeeze=False)
# Plot the spatial map of the learn atom using mne topomap
ax = axes[0, 0]
u_hat = cdl.u_hat_[i_atom]
mne.viz.plot_topomap(u_hat, info, axes=ax, show=False)
ax.set(title='Learned spatial pattern')
# Plot the temporal pattern of the learn atom
ax = axes[0, 1]
v_hat = cdl.v_hat_[i_atom]
t = np.arange(v_hat.size) / sfreq
ax.plot(t, v_hat)
ax.set(xlabel='Time (sec)', title='Learned temporal waveform')
ax.grid(True)
# Plot the psd of the time atom
ax = axes[0, 2]
psd = np.abs(np.fft.rfft(v_hat)) ** 2
frequencies = np.linspace(0, sfreq / 2.0, len(psd))
ax.semilogy(frequencies, psd)
ax.set(xlabel='Frequencies (Hz)', title='Power Spectral Density')
ax.grid(True)
ax.set_xlim(0, 30)
plt.tight_layout()
plt.show()
Total running time of the script: (5 minutes 15.516 seconds)