Note
Go to the end to download the full example code.
Tutorial 5: Creating a dataset class#
# Author: Gregoire Cattan
#
# https://github.com/plcrodrigues/Workshop-MOABB-BCI-Graz-2019
from pyriemann.classification import MDM
from pyriemann.estimation import ERPCovariances
from sklearn.pipeline import make_pipeline
from moabb.datasets import Cattan2019_VR
from moabb.datasets.braininvaders import BI2014a
from moabb.datasets.compound_dataset import CompoundDataset
from moabb.datasets.utils import blocks_reps
from moabb.evaluations import WithinSessionEvaluation
from moabb.paradigms.p300 import P300
Initialization#
This tutorial illustrates how to use the CompoundDataset to: 1) Select a few subjects/sessions/runs in an existing dataset 2) Merge two CompoundDataset into a new one 3) … and finally use this new dataset on a pipeline (this steps is not specific to CompoundDataset)
Let’s define a paradigm and a pipeline for evaluation first.
paradigm = P300()
pipelines = {}
pipelines["MDM"] = make_pipeline(ERPCovariances(estimator="lwf"), MDM(metric="riemann"))
Creation a selection of subject#
We are going to great two CompoundDataset, namely CustomDataset1 & 2. A CompoundDataset accepts a subjects_list of subjects. It is a list of tuple. A tuple contains 4 values:
the original dataset
the subject number to select
the sessions. It can be:
a session name (‘0’)
a list of sessions ([‘0’, ‘1’])
None to select all the sessions attributed to a subject
the runs. As for sessions, it can be a single run name, a list or None` (to select all runs).
class CustomDataset1(CompoundDataset):
def __init__(self):
biVR = Cattan2019_VR(virtual_reality=True, screen_display=True)
runs = blocks_reps([0, 2], [0, 1, 2, 3, 4], biVR.n_repetitions)
subjects_list = [
(biVR, 1, "0VR", runs),
(biVR, 2, "0VR", runs),
]
CompoundDataset.__init__(
self,
subjects_list=subjects_list,
code="CustomDataset1",
interval=[0, 1.0],
)
class CustomDataset2(CompoundDataset):
def __init__(self):
bi2014 = BI2014a()
subjects_list = [
(bi2014, 4, None, None),
(bi2014, 7, None, None),
]
CompoundDataset.__init__(
self,
subjects_list=subjects_list,
code="CustomDataset2",
interval=[0, 1.0],
)
Merging the datasets#
We are now going to merge the two CompoundDataset into a single one. The implementation is straight forward. Instead of providing a list of subjects, you should provide a list of CompoundDataset. subjects_list = [CustomDataset1(), CustomDataset2()]
class CustomDataset3(CompoundDataset):
def __init__(self):
subjects_list = [CustomDataset1(), CustomDataset2()]
CompoundDataset.__init__(
self,
subjects_list=subjects_list,
code="CustomDataset3",
interval=[0, 1.0],
)
Evaluate and display#
Let’s use a WithinSessionEvaluation to evaluate our new dataset. If you already new how to do this, nothing changed: The CompoundDataset can be used as a normal dataset.
datasets = [CustomDataset3()]
evaluation = WithinSessionEvaluation(
paradigm=paradigm, datasets=datasets, overwrite=False, suffix="newdataset"
)
scores = evaluation.process(pipelines)
print(scores)
CustomDataset3-WithinSession: 0%| | 0/4 [00:00<?, ?it/s]
CustomDataset3-WithinSession: 25%|██▌ | 1/4 [00:44<02:13, 44.58s/it]
CustomDataset3-WithinSession: 50%|█████ | 2/4 [01:35<01:36, 48.04s/it]
0%| | 0.00/46.4M [00:00<?, ?B/s]
0%| | 12.3k/46.4M [00:00<09:55, 78.0kB/s]
0%| | 41.0k/46.4M [00:00<05:13, 148kB/s]
0%| | 92.2k/46.4M [00:00<03:10, 243kB/s]
0%|▏ | 168k/46.4M [00:00<02:09, 357kB/s]
1%|▏ | 253k/46.4M [00:00<01:44, 444kB/s]
1%|▎ | 315k/46.4M [00:00<01:44, 442kB/s]
1%|▎ | 417k/46.4M [00:01<01:26, 531kB/s]
1%|▍ | 499k/46.4M [00:01<01:24, 545kB/s]
1%|▌ | 630k/46.4M [00:01<01:09, 662kB/s]
2%|▋ | 776k/46.4M [00:01<00:58, 776kB/s]
2%|▋ | 858k/46.4M [00:01<01:03, 715kB/s]
2%|▊ | 1.01M/46.4M [00:01<00:55, 813kB/s]
2%|▉ | 1.09M/46.4M [00:01<01:01, 739kB/s]
3%|▉ | 1.19M/46.4M [00:02<01:02, 725kB/s]
3%|█ | 1.26M/46.4M [00:02<01:08, 661kB/s]
3%|█ | 1.35M/46.4M [00:02<01:09, 652kB/s]
4%|█▎ | 1.68M/46.4M [00:02<00:38, 1.15MB/s]
4%|█▌ | 1.90M/46.4M [00:02<00:34, 1.29MB/s]
6%|██ | 2.64M/46.4M [00:02<00:17, 2.45MB/s]
9%|███▎ | 4.19M/46.4M [00:02<00:08, 4.98MB/s]
11%|███▉ | 4.96M/46.4M [00:03<00:23, 1.74MB/s]
11%|████▎ | 5.33M/46.4M [00:04<00:23, 1.73MB/s]
12%|████▍ | 5.64M/46.4M [00:04<00:22, 1.80MB/s]
14%|█████▏ | 6.50M/46.4M [00:04<00:15, 2.53MB/s]
15%|█████▋ | 7.07M/46.4M [00:04<00:13, 2.83MB/s]
17%|██████▏ | 7.76M/46.4M [00:04<00:11, 3.27MB/s]
18%|██████▌ | 8.30M/46.4M [00:04<00:11, 3.39MB/s]
19%|███████▏ | 8.95M/46.4M [00:04<00:10, 3.70MB/s]
21%|███████▌ | 9.53M/46.4M [00:05<00:09, 3.78MB/s]
22%|████████ | 10.0M/46.4M [00:05<00:09, 3.76MB/s]
23%|████████▌ | 10.8M/46.4M [00:05<00:08, 4.09MB/s]
25%|█████████ | 11.4M/46.4M [00:05<00:08, 4.23MB/s]
26%|█████████▌ | 12.0M/46.4M [00:05<00:07, 4.30MB/s]
27%|██████████ | 12.6M/46.4M [00:05<00:07, 4.23MB/s]
29%|██████████▌ | 13.3M/46.4M [00:05<00:07, 4.35MB/s]
30%|███████████ | 13.8M/46.4M [00:06<00:07, 4.24MB/s]
31%|███████████▍ | 14.3M/46.4M [00:06<00:08, 3.97MB/s]
32%|███████████▊ | 14.8M/46.4M [00:06<00:07, 4.23MB/s]
33%|████████████▎ | 15.4M/46.4M [00:06<00:07, 4.19MB/s]
35%|████████████▊ | 16.1M/46.4M [00:06<00:06, 4.38MB/s]
36%|█████████████▎ | 16.8M/46.4M [00:06<00:06, 4.47MB/s]
38%|█████████████▉ | 17.4M/46.4M [00:06<00:06, 4.48MB/s]
39%|██████████████▍ | 18.1M/46.4M [00:07<00:06, 4.49MB/s]
41%|██████████████▉ | 18.8M/46.4M [00:07<00:05, 4.73MB/s]
42%|███████████████▌ | 19.5M/46.4M [00:07<00:05, 4.73MB/s]
43%|████████████████ | 20.1M/46.4M [00:07<00:05, 4.69MB/s]
45%|████████████████▌ | 20.7M/46.4M [00:07<00:05, 4.52MB/s]
46%|█████████████████ | 21.4M/46.4M [00:07<00:05, 4.61MB/s]
48%|█████████████████▋ | 22.1M/46.4M [00:07<00:05, 4.28MB/s]
49%|██████████████████▏ | 22.8M/46.4M [00:08<00:05, 4.40MB/s]
51%|██████████████████▋ | 23.5M/46.4M [00:08<00:05, 4.49MB/s]
52%|███████████████████▎ | 24.2M/46.4M [00:08<00:04, 4.64MB/s]
53%|███████████████████▊ | 24.8M/46.4M [00:08<00:04, 4.56MB/s]
55%|████████████████████▎ | 25.5M/46.4M [00:08<00:04, 4.57MB/s]
56%|████████████████████▊ | 26.2M/46.4M [00:08<00:04, 4.68MB/s]
58%|█████████████████████▎ | 26.8M/46.4M [00:08<00:04, 4.59MB/s]
59%|█████████████████████▉ | 27.4M/46.4M [00:09<00:04, 4.62MB/s]
61%|██████████████████████▍ | 28.1M/46.4M [00:09<00:03, 4.65MB/s]
62%|██████████████████████▉ | 28.7M/46.4M [00:09<00:03, 4.57MB/s]
63%|███████████████████████▎ | 29.2M/46.4M [00:09<00:04, 4.17MB/s]
64%|███████████████████████▌ | 29.6M/46.4M [00:09<00:04, 3.36MB/s]
65%|████████████████████████ | 30.2M/46.4M [00:09<00:04, 3.52MB/s]
66%|████████████████████████▌ | 30.7M/46.4M [00:10<00:04, 3.56MB/s]
67%|████████████████████████▊ | 31.2M/46.4M [00:10<00:04, 3.47MB/s]
69%|█████████████████████████▍ | 31.9M/46.4M [00:10<00:03, 3.85MB/s]
70%|█████████████████████████▉ | 32.5M/46.4M [00:10<00:03, 3.94MB/s]
72%|██████████████████████████▌ | 33.3M/46.4M [00:10<00:02, 4.39MB/s]
73%|███████████████████████████ | 33.9M/46.4M [00:10<00:02, 4.51MB/s]
75%|███████████████████████████▌ | 34.6M/46.4M [00:10<00:02, 4.54MB/s]
76%|████████████████████████████ | 35.2M/46.4M [00:11<00:02, 4.34MB/s]
77%|████████████████████████████▌ | 35.8M/46.4M [00:11<00:02, 4.48MB/s]
79%|█████████████████████████████ | 36.5M/46.4M [00:11<00:02, 4.48MB/s]
80%|█████████████████████████████▌ | 37.1M/46.4M [00:11<00:02, 4.48MB/s]
82%|██████████████████████████████▏ | 37.9M/46.4M [00:11<00:01, 4.75MB/s]
83%|██████████████████████████████▋ | 38.4M/46.4M [00:11<00:01, 4.43MB/s]
84%|███████████████████████████████ | 38.9M/46.4M [00:11<00:01, 4.17MB/s]
85%|███████████████████████████████▌ | 39.6M/46.4M [00:12<00:01, 4.36MB/s]
87%|████████████████████████████████ | 40.3M/46.4M [00:12<00:01, 4.40MB/s]
88%|████████████████████████████████▌ | 40.8M/46.4M [00:12<00:01, 4.29MB/s]
89%|████████████████████████████████▉ | 41.3M/46.4M [00:13<00:03, 1.69MB/s]
90%|█████████████████████████████████▎ | 41.7M/46.4M [00:13<00:02, 1.93MB/s]
91%|█████████████████████████████████▋ | 42.3M/46.4M [00:13<00:01, 2.27MB/s]
92%|██████████████████████████████████▏ | 42.9M/46.4M [00:13<00:01, 2.74MB/s]
94%|██████████████████████████████████▋ | 43.5M/46.4M [00:13<00:00, 2.97MB/s]
95%|███████████████████████████████████ | 44.0M/46.4M [00:13<00:00, 3.09MB/s]
96%|███████████████████████████████████▌ | 44.6M/46.4M [00:13<00:00, 3.53MB/s]
98%|████████████████████████████████████ | 45.3M/46.4M [00:14<00:00, 3.83MB/s]
99%|████████████████████████████████████▌| 45.9M/46.4M [00:14<00:00, 3.87MB/s]
0%| | 0.00/46.4M [00:00<?, ?B/s]
100%|██████████████████████████████████████| 46.4M/46.4M [00:00<00:00, 171GB/s]
CustomDataset3-WithinSession: 75%|███████▌ | 3/4 [02:02<00:38, 38.60s/it]
0%| | 0.00/74.3M [00:00<?, ?B/s]
0%| | 11.3k/74.3M [00:00<20:31, 60.3kB/s]
0%| | 34.8k/74.3M [00:00<10:52, 114kB/s]
0%| | 84.0k/74.3M [00:00<05:53, 210kB/s]
0%| | 148k/74.3M [00:00<04:08, 298kB/s]
0%| | 230k/74.3M [00:00<03:09, 391kB/s]
0%|▏ | 345k/74.3M [00:00<02:21, 522kB/s]
1%|▏ | 427k/74.3M [00:01<02:17, 535kB/s]
1%|▎ | 525k/74.3M [00:01<02:07, 579kB/s]
1%|▎ | 672k/74.3M [00:01<01:43, 710kB/s]
1%|▍ | 754k/74.3M [00:01<01:50, 664kB/s]
1%|▍ | 901k/74.3M [00:01<01:35, 769kB/s]
1%|▌ | 999k/74.3M [00:01<01:39, 739kB/s]
1%|▌ | 1.08M/74.3M [00:01<01:46, 685kB/s]
2%|▋ | 1.23M/74.3M [00:02<01:34, 773kB/s]
2%|▋ | 1.33M/74.3M [00:02<01:38, 744kB/s]
2%|▋ | 1.44M/74.3M [00:02<01:36, 753kB/s]
2%|▊ | 1.52M/74.3M [00:02<01:47, 677kB/s]
2%|▊ | 1.62M/74.3M [00:02<01:45, 688kB/s]
2%|▊ | 1.70M/74.3M [00:02<01:51, 651kB/s]
2%|▉ | 1.77M/74.3M [00:02<02:02, 591kB/s]
3%|▉ | 1.88M/74.3M [00:03<01:51, 646kB/s]
3%|█ | 2.03M/74.3M [00:03<01:35, 754kB/s]
3%|█ | 2.14M/74.3M [00:03<01:34, 763kB/s]
3%|█▏ | 2.26M/74.3M [00:03<01:33, 767kB/s]
3%|█▏ | 2.36M/74.3M [00:03<01:37, 738kB/s]
3%|█▏ | 2.44M/74.3M [00:03<01:44, 686kB/s]
3%|█▎ | 2.54M/74.3M [00:03<01:45, 681kB/s]
4%|█▎ | 2.63M/74.3M [00:04<01:45, 678kB/s]
4%|█▍ | 2.78M/74.3M [00:04<01:32, 769kB/s]
4%|█▍ | 2.88M/74.3M [00:04<01:39, 717kB/s]
4%|█▌ | 3.01M/74.3M [00:04<01:32, 768kB/s]
4%|█▌ | 3.13M/74.3M [00:04<01:32, 772kB/s]
4%|█▋ | 3.27M/74.3M [00:04<01:24, 840kB/s]
5%|█▋ | 3.39M/74.3M [00:05<01:26, 821kB/s]
5%|█▊ | 3.47M/74.3M [00:05<01:35, 740kB/s]
5%|█▊ | 3.57M/74.3M [00:05<01:38, 719kB/s]
5%|█▉ | 3.66M/74.3M [00:05<01:40, 705kB/s]
5%|█▉ | 3.76M/74.3M [00:05<01:41, 694kB/s]
5%|█▉ | 3.84M/74.3M [00:05<01:48, 652kB/s]
5%|██ | 3.93M/74.3M [00:05<01:52, 624kB/s]
5%|██ | 4.01M/74.3M [00:06<01:56, 604kB/s]
6%|██▏ | 4.16M/74.3M [00:06<01:36, 724kB/s]
6%|██▏ | 4.24M/74.3M [00:06<01:43, 675kB/s]
6%|██▏ | 4.33M/74.3M [00:06<01:44, 672kB/s]
6%|██▎ | 4.45M/74.3M [00:06<01:38, 705kB/s]
6%|██▎ | 4.55M/74.3M [00:06<01:40, 692kB/s]
6%|██▎ | 4.63M/74.3M [00:06<01:46, 652kB/s]
6%|██▍ | 4.71M/74.3M [00:07<01:52, 621kB/s]
6%|██▍ | 4.81M/74.3M [00:07<01:49, 637kB/s]
7%|██▌ | 4.94M/74.3M [00:07<01:37, 712kB/s]
7%|██▌ | 5.04M/74.3M [00:07<01:38, 701kB/s]
7%|██▌ | 5.12M/74.3M [00:07<01:44, 659kB/s]
7%|██▋ | 5.20M/74.3M [00:07<01:49, 629kB/s]
7%|██▋ | 5.30M/74.3M [00:07<01:47, 642kB/s]
7%|██▊ | 5.38M/74.3M [00:08<01:51, 618kB/s]
7%|██▊ | 5.46M/74.3M [00:08<01:54, 599kB/s]
8%|██▊ | 5.59M/74.3M [00:08<01:39, 687kB/s]
8%|██▉ | 5.74M/74.3M [00:08<01:27, 782kB/s]
8%|███ | 6.10M/74.3M [00:08<00:52, 1.29MB/s]
9%|███▏ | 6.48M/74.3M [00:08<00:40, 1.67MB/s]
10%|███▊ | 7.54M/74.3M [00:09<00:19, 3.36MB/s]
12%|████▌ | 9.09M/74.3M [00:09<00:11, 5.55MB/s]
13%|████▉ | 9.93M/74.3M [00:09<00:11, 5.58MB/s]
14%|█████▏ | 10.5M/74.3M [00:09<00:12, 5.04MB/s]
15%|█████▍ | 11.0M/74.3M [00:09<00:13, 4.57MB/s]
16%|█████▊ | 11.5M/74.3M [00:09<00:14, 4.35MB/s]
17%|██████▏ | 12.3M/74.3M [00:09<00:13, 4.61MB/s]
17%|██████▍ | 13.0M/74.3M [00:10<00:13, 4.60MB/s]
18%|██████▊ | 13.7M/74.3M [00:10<00:13, 4.58MB/s]
19%|███████▏ | 14.3M/74.3M [00:10<00:13, 4.59MB/s]
20%|███████▎ | 14.8M/74.3M [00:10<00:15, 3.74MB/s]
20%|███████▌ | 15.2M/74.3M [00:10<00:17, 3.46MB/s]
21%|███████▉ | 15.8M/74.3M [00:10<00:15, 3.72MB/s]
22%|████████▏ | 16.5M/74.3M [00:10<00:14, 3.91MB/s]
23%|████████▍ | 17.0M/74.3M [00:11<00:14, 3.87MB/s]
24%|████████▊ | 17.7M/74.3M [00:11<00:13, 4.14MB/s]
25%|█████████▎ | 18.6M/74.3M [00:11<00:11, 4.71MB/s]
26%|█████████▌ | 19.1M/74.3M [00:11<00:12, 4.26MB/s]
26%|█████████▋ | 19.5M/74.3M [00:11<00:14, 3.86MB/s]
27%|█████████▉ | 19.9M/74.3M [00:11<00:15, 3.50MB/s]
27%|██████████ | 20.3M/74.3M [00:11<00:16, 3.24MB/s]
28%|██████████▎ | 20.7M/74.3M [00:12<00:17, 3.13MB/s]
28%|██████████▌ | 21.1M/74.3M [00:12<00:18, 2.90MB/s]
29%|██████████▋ | 21.5M/74.3M [00:12<00:17, 2.94MB/s]
30%|██████████▉ | 21.9M/74.3M [00:12<00:17, 2.91MB/s]
30%|███████████▏ | 22.4M/74.3M [00:12<00:17, 2.90MB/s]
31%|███████████▍ | 22.9M/74.3M [00:12<00:16, 3.14MB/s]
32%|███████████▋ | 23.4M/74.3M [00:13<00:16, 3.14MB/s]
32%|███████████▉ | 23.8M/74.3M [00:13<00:16, 3.10MB/s]
33%|████████████ | 24.3M/74.3M [00:13<00:16, 3.08MB/s]
33%|████████████▎ | 24.8M/74.3M [00:13<00:15, 3.12MB/s]
34%|████████████▌ | 25.2M/74.3M [00:13<00:16, 3.06MB/s]
35%|████████████▊ | 25.6M/74.3M [00:13<00:15, 3.07MB/s]
35%|████████████▉ | 26.0M/74.3M [00:13<00:17, 2.78MB/s]
35%|█████████████▏ | 26.4M/74.3M [00:14<00:17, 2.80MB/s]
36%|█████████████▍ | 26.9M/74.3M [00:14<00:15, 3.10MB/s]
38%|██████████████▏ | 28.4M/74.3M [00:14<00:16, 2.84MB/s]
40%|██████████████▉ | 29.9M/74.3M [00:14<00:10, 4.24MB/s]
44%|████████████████▍ | 32.9M/74.3M [00:15<00:05, 7.74MB/s]
46%|████████████████▉ | 34.0M/74.3M [00:15<00:05, 7.61MB/s]
47%|█████████████████▍ | 34.9M/74.3M [00:15<00:06, 5.78MB/s]
48%|█████████████████▊ | 35.6M/74.3M [00:15<00:06, 5.57MB/s]
49%|██████████████████ | 36.3M/74.3M [00:15<00:08, 4.24MB/s]
50%|██████████████████▎ | 36.8M/74.3M [00:16<00:09, 4.09MB/s]
50%|██████████████████▌ | 37.3M/74.3M [00:16<00:09, 3.89MB/s]
51%|██████████████████▊ | 37.7M/74.3M [00:16<00:10, 3.64MB/s]
51%|██████████████████▉ | 38.1M/74.3M [00:16<00:10, 3.34MB/s]
52%|███████████████████▏ | 38.4M/74.3M [00:16<00:11, 3.12MB/s]
52%|███████████████████▎ | 38.8M/74.3M [00:16<00:12, 2.83MB/s]
53%|███████████████████▍ | 39.1M/74.3M [00:16<00:13, 2.63MB/s]
53%|███████████████████▋ | 39.5M/74.3M [00:17<00:13, 2.67MB/s]
54%|███████████████████▊ | 39.8M/74.3M [00:17<00:13, 2.48MB/s]
54%|████████████████████ | 40.2M/74.3M [00:17<00:13, 2.61MB/s]
55%|████████████████████▏ | 40.6M/74.3M [00:17<00:12, 2.69MB/s]
55%|████████████████████▍ | 41.1M/74.3M [00:17<00:11, 2.79MB/s]
56%|████████████████████▋ | 41.5M/74.3M [00:17<00:11, 2.85MB/s]
56%|████████████████████▊ | 41.9M/74.3M [00:18<00:11, 2.71MB/s]
57%|█████████████████████ | 42.2M/74.3M [00:18<00:13, 2.41MB/s]
57%|█████████████████████ | 42.4M/74.3M [00:18<00:14, 2.20MB/s]
58%|█████████████████████▎ | 42.8M/74.3M [00:18<00:13, 2.41MB/s]
58%|█████████████████████▌ | 43.3M/74.3M [00:18<00:12, 2.53MB/s]
59%|█████████████████████▊ | 43.7M/74.3M [00:18<00:11, 2.67MB/s]
59%|█████████████████████▉ | 44.1M/74.3M [00:18<00:11, 2.71MB/s]
60%|██████████████████████▏ | 44.6M/74.3M [00:19<00:10, 2.74MB/s]
61%|██████████████████████▍ | 44.9M/74.3M [00:19<00:10, 2.70MB/s]
61%|██████████████████████▌ | 45.4M/74.3M [00:19<00:10, 2.80MB/s]
62%|██████████████████████▊ | 45.7M/74.3M [00:19<00:10, 2.66MB/s]
62%|██████████████████████▉ | 46.2M/74.3M [00:19<00:10, 2.73MB/s]
63%|███████████████████████▏ | 46.6M/74.3M [00:19<00:09, 2.85MB/s]
63%|███████████████████████▍ | 47.0M/74.3M [00:19<00:09, 2.73MB/s]
64%|███████████████████████▌ | 47.4M/74.3M [00:20<00:09, 2.75MB/s]
64%|███████████████████████▊ | 47.7M/74.3M [00:20<00:10, 2.59MB/s]
65%|███████████████████████▉ | 48.1M/74.3M [00:20<00:09, 2.65MB/s]
65%|████████████████████████▏ | 48.5M/74.3M [00:20<00:09, 2.68MB/s]
66%|████████████████████████▍ | 49.0M/74.3M [00:20<00:09, 2.73MB/s]
67%|████████████████████████▌ | 49.4M/74.3M [00:20<00:08, 2.77MB/s]
67%|████████████████████████▊ | 49.8M/74.3M [00:21<00:09, 2.70MB/s]
68%|████████████████████████▉ | 50.1M/74.3M [00:21<00:08, 2.82MB/s]
68%|█████████████████████████ | 50.4M/74.3M [00:21<00:09, 2.56MB/s]
68%|█████████████████████████▎ | 50.7M/74.3M [00:21<00:10, 2.32MB/s]
69%|█████████████████████████▍ | 51.0M/74.3M [00:21<00:10, 2.23MB/s]
69%|█████████████████████████▌ | 51.4M/74.3M [00:21<00:09, 2.43MB/s]
70%|█████████████████████████▊ | 51.9M/74.3M [00:21<00:08, 2.64MB/s]
70%|██████████████████████████ | 52.3M/74.3M [00:21<00:08, 2.72MB/s]
71%|██████████████████████████▏ | 52.7M/74.3M [00:22<00:08, 2.70MB/s]
72%|██████████████████████████▍ | 53.1M/74.3M [00:22<00:07, 2.77MB/s]
72%|██████████████████████████▋ | 53.6M/74.3M [00:22<00:07, 2.82MB/s]
73%|██████████████████████████▉ | 54.0M/74.3M [00:22<00:07, 2.84MB/s]
73%|███████████████████████████ | 54.4M/74.3M [00:22<00:06, 2.92MB/s]
74%|███████████████████████████▎ | 54.9M/74.3M [00:22<00:07, 2.53MB/s]
74%|███████████████████████████▌ | 55.3M/74.3M [00:23<00:07, 2.57MB/s]
75%|███████████████████████████▋ | 55.7M/74.3M [00:23<00:06, 2.66MB/s]
76%|███████████████████████████▉ | 56.2M/74.3M [00:23<00:06, 2.79MB/s]
76%|████████████████████████████▏ | 56.6M/74.3M [00:23<00:06, 2.79MB/s]
77%|████████████████████████████▎ | 56.9M/74.3M [00:23<00:06, 2.60MB/s]
77%|████████████████████████████▌ | 57.3M/74.3M [00:23<00:06, 2.69MB/s]
78%|████████████████████████████▊ | 57.7M/74.3M [00:23<00:05, 2.78MB/s]
78%|████████████████████████████▉ | 58.2M/74.3M [00:24<00:05, 2.82MB/s]
79%|█████████████████████████████▏ | 58.5M/74.3M [00:24<00:05, 2.74MB/s]
79%|█████████████████████████████▍ | 59.0M/74.3M [00:24<00:05, 2.79MB/s]
80%|█████████████████████████████▌ | 59.3M/74.3M [00:24<00:05, 2.62MB/s]
80%|█████████████████████████████▊ | 59.7M/74.3M [00:24<00:05, 2.71MB/s]
81%|█████████████████████████████▉ | 60.1M/74.3M [00:24<00:05, 2.76MB/s]
82%|██████████████████████████████▏ | 60.6M/74.3M [00:25<00:04, 2.77MB/s]
82%|██████████████████████████████▎ | 61.0M/74.3M [00:25<00:04, 2.78MB/s]
83%|██████████████████████████████▌ | 61.4M/74.3M [00:25<00:04, 2.77MB/s]
83%|██████████████████████████████▊ | 61.8M/74.3M [00:25<00:04, 2.77MB/s]
84%|██████████████████████████████▉ | 62.2M/74.3M [00:25<00:04, 2.81MB/s]
84%|███████████████████████████████▏ | 62.6M/74.3M [00:25<00:04, 2.70MB/s]
85%|███████████████████████████████▍ | 63.0M/74.3M [00:25<00:04, 2.76MB/s]
85%|███████████████████████████████▌ | 63.4M/74.3M [00:26<00:03, 2.84MB/s]
86%|███████████████████████████████▊ | 63.8M/74.3M [00:26<00:03, 2.82MB/s]
87%|████████████████████████████████ | 64.3M/74.3M [00:26<00:03, 2.85MB/s]
87%|████████████████████████████████▏ | 64.6M/74.3M [00:26<00:03, 2.60MB/s]
88%|████████████████████████████████▍ | 65.0M/74.3M [00:26<00:03, 2.69MB/s]
88%|████████████████████████████████▌ | 65.4M/74.3M [00:26<00:03, 2.75MB/s]
89%|████████████████████████████████▊ | 65.8M/74.3M [00:26<00:03, 2.80MB/s]
89%|█████████████████████████████████ | 66.3M/74.3M [00:27<00:02, 2.83MB/s]
90%|█████████████████████████████████▏ | 66.7M/74.3M [00:27<00:02, 2.81MB/s]
90%|█████████████████████████████████▍ | 67.1M/74.3M [00:27<00:02, 2.83MB/s]
91%|█████████████████████████████████▋ | 67.5M/74.3M [00:27<00:02, 2.85MB/s]
91%|█████████████████████████████████▊ | 67.9M/74.3M [00:27<00:02, 2.83MB/s]
92%|██████████████████████████████████ | 68.4M/74.3M [00:27<00:02, 2.85MB/s]
93%|██████████████████████████████████▎ | 68.8M/74.3M [00:27<00:01, 2.94MB/s]
93%|██████████████████████████████████▍ | 69.2M/74.3M [00:28<00:01, 2.93MB/s]
94%|██████████████████████████████████▋ | 69.7M/74.3M [00:28<00:01, 2.95MB/s]
94%|██████████████████████████████████▉ | 70.1M/74.3M [00:28<00:01, 2.93MB/s]
95%|███████████████████████████████████▏ | 70.5M/74.3M [00:28<00:01, 2.89MB/s]
96%|███████████████████████████████████▎ | 70.9M/74.3M [00:28<00:01, 2.90MB/s]
96%|███████████████████████████████████▌ | 71.4M/74.3M [00:28<00:00, 2.96MB/s]
97%|███████████████████████████████████▋ | 71.7M/74.3M [00:29<00:01, 1.89MB/s]
97%|███████████████████████████████████▊ | 71.9M/74.3M [00:29<00:01, 1.64MB/s]
97%|███████████████████████████████████▉ | 72.1M/74.3M [00:29<00:01, 1.60MB/s]
98%|████████████████████████████████████▏| 72.5M/74.3M [00:29<00:00, 1.92MB/s]
98%|████████████████████████████████████▎| 72.9M/74.3M [00:29<00:00, 2.09MB/s]
99%|████████████████████████████████████▌| 73.3M/74.3M [00:29<00:00, 2.28MB/s]
99%|████████████████████████████████████▋| 73.8M/74.3M [00:30<00:00, 2.46MB/s]
100%|████████████████████████████████████▉| 74.2M/74.3M [00:30<00:00, 2.58MB/s]
0%| | 0.00/74.3M [00:00<?, ?B/s]
100%|██████████████████████████████████████| 74.3M/74.3M [00:00<00:00, 363GB/s]
CustomDataset3-WithinSession: 100%|██████████| 4/4 [02:57<00:00, 45.23s/it]
CustomDataset3-WithinSession: 100%|██████████| 4/4 [02:57<00:00, 44.45s/it]
score time samples ... n_sessions dataset pipeline
0 0.667500 0.362611 120.0 ... 1 CustomDataset3 MDM
1 0.547500 0.354974 120.0 ... 1 CustomDataset3 MDM
2 0.614435 2.157532 768.0 ... 1 CustomDataset3 MDM
3 0.559516 4.388021 1356.0 ... 1 CustomDataset3 MDM
[4 rows x 9 columns]
Total running time of the script: (2 minutes 58.897 seconds)
Estimated memory usage: 610 MB