Note
Go to the end to download the full example code.
Examples of analysis of a Dreyer2023 A dataset.#
This example shows how to plot Dreyer2023A Left-Right Imagery ROC AUC scores obtained with CSP+LDA pipeline versus demographic information of the examined subjects (gender and age) and experimenters (gender).
To reduce computational time, the example is provided for four subjects.
# Authors: Sara Sedlar <sara.sedlar@gmail.com>
# Sylvain Chevallier <sylvain.chevallier@universite-paris-saclay.fr>
# License: BSD (3-clause)
import matplotlib.patches as mpatches
import matplotlib.pyplot as plt
import seaborn as sb
from pyriemann.estimation import Covariances
from pyriemann.spatialfilters import CSP
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
from sklearn.pipeline import make_pipeline
from moabb.datasets import Dreyer2023A
from moabb.evaluations import WithinSessionEvaluation
from moabb.paradigms import MotorImagery
Defining dataset, selecting subject for analysis and getting data
dreyer2023 = Dreyer2023A()
dreyer2023.subject_list = [1, 5, 7, 35]
dreyer2023.get_data()
0%| | 0.00/5.84k [00:00<?, ?B/s]
0%| | 0.00/5.84k [00:00<?, ?B/s]
100%|█████████████████████████████████████| 5.84k/5.84k [00:00<00:00, 50.4MB/s]
0it [00:00, ?it/s]
0%| | 0.00/698 [00:00<?, ?B/s]
0%| | 0.00/698 [00:00<?, ?B/s]
100%|█████████████████████████████████████████| 698/698 [00:00<00:00, 6.68MB/s]
1it [00:01, 1.71s/it]
0%| | 0.00/89.0k [00:00<?, ?B/s]
0%| | 0.00/89.0k [00:00<?, ?B/s]
100%|██████████████████████████████████████| 89.0k/89.0k [00:00<00:00, 353MB/s]
2it [00:03, 1.56s/it]
0%| | 0.00/303 [00:00<?, ?B/s]
0%| | 0.00/303 [00:00<?, ?B/s]
100%|█████████████████████████████████████████| 303/303 [00:00<00:00, 2.79MB/s]
3it [00:04, 1.51s/it]
0%| | 0.00/485k [00:00<?, ?B/s]
37%|██████████████▎ | 177k/485k [00:00<00:00, 1.76MB/s]
0%| | 0.00/485k [00:00<?, ?B/s]
100%|███████████████████████████████████████| 485k/485k [00:00<00:00, 1.97GB/s]
4it [00:06, 1.55s/it]
0%| | 0.00/1.92k [00:00<?, ?B/s]
0%| | 0.00/1.92k [00:00<?, ?B/s]
100%|█████████████████████████████████████| 1.92k/1.92k [00:00<00:00, 19.1MB/s]
5it [00:08, 1.77s/it]
0%| | 0.00/788 [00:00<?, ?B/s]
0%| | 0.00/788 [00:00<?, ?B/s]
100%|█████████████████████████████████████████| 788/788 [00:00<00:00, 8.37MB/s]
6it [00:09, 1.60s/it]
0%| | 0.00/2.22k [00:00<?, ?B/s]
0%| | 0.00/2.22k [00:00<?, ?B/s]
100%|█████████████████████████████████████| 2.22k/2.22k [00:00<00:00, 23.0MB/s]
7it [00:11, 1.63s/it]
0%| | 0.00/1.39M [00:00<?, ?B/s]
14%|█████▏ | 189k/1.39M [00:00<00:00, 1.88MB/s]
0%| | 0.00/1.39M [00:00<?, ?B/s]
100%|█████████████████████████████████████| 1.39M/1.39M [00:00<00:00, 5.85GB/s]
8it [00:12, 1.63s/it]
0%| | 0.00/72.6M [00:00<?, ?B/s]
0%| | 179k/72.6M [00:00<00:41, 1.76MB/s]
3%|█ | 2.15M/72.6M [00:00<00:05, 12.2MB/s]
19%|███████ | 13.8M/72.6M [00:00<00:00, 59.4MB/s]
31%|███████████▋ | 22.8M/72.6M [00:00<00:00, 71.6MB/s]
46%|████████████████▉ | 33.1M/72.6M [00:00<00:00, 82.9MB/s]
57%|█████████████████████▏ | 41.4M/72.6M [00:00<00:00, 80.3MB/s]
69%|█████████████████████████▌ | 50.1M/72.6M [00:00<00:00, 82.3MB/s]
84%|███████████████████████████████ | 60.8M/72.6M [00:00<00:00, 66.8MB/s]
100%|████████████████████████████████████▊| 72.3M/72.6M [00:01<00:00, 78.7MB/s]
0%| | 0.00/72.6M [00:00<?, ?B/s]
100%|██████████████████████████████████████| 72.6M/72.6M [00:00<00:00, 523GB/s]
9it [00:16, 2.07s/it]
9it [00:16, 1.78s/it]
0it [00:00, ?it/s]
0%| | 0.00/65.0M [00:00<?, ?B/s]
0%| | 122k/65.0M [00:00<00:53, 1.21MB/s]
1%|▍ | 654k/65.0M [00:00<00:17, 3.61MB/s]
5%|█▉ | 3.44M/65.0M [00:00<00:04, 14.6MB/s]
18%|██████▌ | 11.6M/65.0M [00:00<00:01, 40.8MB/s]
30%|███████████▏ | 19.7M/65.0M [00:00<00:00, 55.6MB/s]
40%|██████████████▋ | 25.8M/65.0M [00:00<00:00, 57.3MB/s]
52%|███████████████████ | 33.6M/65.0M [00:00<00:00, 60.9MB/s]
64%|███████████████████████▋ | 41.7M/65.0M [00:00<00:00, 64.0MB/s]
76%|████████████████████████████ | 49.2M/65.0M [00:00<00:00, 67.5MB/s]
92%|██████████████████████████████████▏ | 60.1M/65.0M [00:01<00:00, 76.7MB/s]
0%| | 0.00/65.0M [00:00<?, ?B/s]
100%|██████████████████████████████████████| 65.0M/65.0M [00:00<00:00, 326GB/s]
9it [00:02, 3.19it/s]
9it [00:02, 3.19it/s]
0it [00:00, ?it/s]
0%| | 0.00/64.3M [00:00<?, ?B/s]
0%| | 166k/64.3M [00:00<00:38, 1.65MB/s]
2%|▋ | 1.13M/64.3M [00:00<00:09, 6.34MB/s]
13%|████▋ | 8.21M/64.3M [00:00<00:01, 35.8MB/s]
26%|█████████▌ | 16.7M/64.3M [00:00<00:00, 54.8MB/s]
37%|█████████████▋ | 23.8M/64.3M [00:00<00:00, 60.8MB/s]
54%|███████████████████▊ | 34.4M/64.3M [00:00<00:00, 76.1MB/s]
65%|████████████████████████▏ | 42.0M/64.3M [00:00<00:00, 74.8MB/s]
81%|██████████████████████████████ | 52.3M/64.3M [00:00<00:00, 81.5MB/s]
99%|████████████████████████████████████▊| 64.0M/64.3M [00:00<00:00, 92.3MB/s]
0%| | 0.00/64.3M [00:00<?, ?B/s]
100%|██████████████████████████████████████| 64.3M/64.3M [00:00<00:00, 384GB/s]
9it [00:02, 3.36it/s]
9it [00:02, 3.36it/s]
0it [00:00, ?it/s]
0%| | 0.00/67.2M [00:00<?, ?B/s]
0%| | 166k/67.2M [00:00<00:40, 1.66MB/s]
2%|▊ | 1.46M/67.2M [00:00<00:07, 8.30MB/s]
16%|█████▉ | 10.8M/67.2M [00:00<00:01, 47.3MB/s]
24%|████████▊ | 16.1M/67.2M [00:00<00:01, 49.3MB/s]
31%|███████████▌ | 21.0M/67.2M [00:00<00:00, 47.5MB/s]
44%|████████████████▏ | 29.3M/67.2M [00:00<00:00, 59.3MB/s]
54%|███████████████████▉ | 36.2M/67.2M [00:00<00:00, 62.3MB/s]
64%|███████████████████████▊ | 43.3M/67.2M [00:00<00:00, 65.1MB/s]
81%|██████████████████████████████ | 54.5M/67.2M [00:00<00:00, 63.6MB/s]
0%| | 0.00/67.2M [00:00<?, ?B/s]
100%|██████████████████████████████████████| 67.2M/67.2M [00:00<00:00, 242GB/s]
9it [00:02, 3.44it/s]
9it [00:02, 3.44it/s]
{1: {'0': {'0R1acquisition': <RawEDF | sub-01_task-R1acquisition_eeg.edf, 32 x 230400 (450.0 s), ~56.3 MiB, data loaded>, '1R2acquisition': <RawEDF | sub-01_task-R2acquisition_eeg.edf, 32 x 230400 (450.0 s), ~56.3 MiB, data loaded>, '2R3online': <RawEDF | sub-01_task-R3online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '3R4online': <RawEDF | sub-01_task-R4online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '4R5online': <RawEDF | sub-01_task-R5online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '5R6online': <RawEDF | sub-01_task-R6online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>}}, 5: {'0': {'0R1acquisition': <RawEDF | sub-05_task-R1acquisition_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '1R2acquisition': <RawEDF | sub-05_task-R2acquisition_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '2R3online': <RawEDF | sub-05_task-R3online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '3R4online': <RawEDF | sub-05_task-R4online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '4R5online': <RawEDF | sub-05_task-R5online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '5R6online': <RawEDF | sub-05_task-R6online_eeg.edf, 32 x 234496 (458.0 s), ~57.3 MiB, data loaded>}}, 7: {'0': {'0R1acquisition': <RawEDF | sub-07_task-R1acquisition_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '1R2acquisition': <RawEDF | sub-07_task-R2acquisition_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '2R3online': <RawEDF | sub-07_task-R3online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '3R4online': <RawEDF | sub-07_task-R4online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '4R5online': <RawEDF | sub-07_task-R5online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '5R6online': <RawEDF | sub-07_task-R6online_eeg.edf, 32 x 230400 (450.0 s), ~56.3 MiB, data loaded>}}, 35: {'0': {'0R1acquisition': <RawEDF | sub-35_task-R1acquisition_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '1R2acquisition': <RawEDF | sub-35_task-R2acquisition_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '2R3online': <RawEDF | sub-35_task-R3online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '3R4online': <RawEDF | sub-35_task-R4online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '4R5online': <RawEDF | sub-35_task-R5online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>, '5R6online': <RawEDF | sub-35_task-R6online_eeg.edf, 32 x 230912 (451.0 s), ~56.4 MiB, data loaded>}}}
Defining MotorImagery paradigm and CSP+LDA pipeline
paradigm = MotorImagery()
pipelines = {}
pipelines["CSP+LDA"] = make_pipeline(
Covariances(estimator="oas"), CSP(nfilter=6), LDA(solver="lsqr", shrinkage="auto")
)
Within session evaluation of the pipeline
evaluation = WithinSessionEvaluation(
paradigm=paradigm, datasets=[dreyer2023], suffix="examples", overwrite=False
)
results = evaluation.process(pipelines)
0it [00:00, ?it/s]
9it [00:00, 11015.10it/s]
0it [00:00, ?it/s]
9it [00:00, 15860.81it/s]
0it [00:00, ?it/s]
9it [00:00, 15702.47it/s]
0it [00:00, ?it/s]
9it [00:00, 17142.93it/s]
Loading dataset info and concatenation with the obtained results
info = dreyer2023.get_subject_info().rename(columns={"score": "score_MR"})
# Creating a new column with subject's age
info["Age"] = 2019 - info["Birth_year"]
# Casting to int for merging
info["subject"] = info["SUJ_ID"].astype(int)
results["subject"] = results["subject"].astype(int)
results_info = results.merge(info, on="subject", how="left")
0%| | 0.00/19.8k [00:00<?, ?B/s]
0%| | 0.00/19.8k [00:00<?, ?B/s]
100%|██████████████████████████████████████| 19.8k/19.8k [00:00<00:00, 110MB/s]
5.1 Plotting subject AUC ROC scores vs subject’s gender
fig, ax = plt.subplots(nrows=2, ncols=2, facecolor="white", figsize=[16, 8], sharey=True)
fig.subplots_adjust(wspace=0.0, hspace=0.5)
sb.boxplot(
data=results_info, y="score", x="SUJ_gender", ax=ax[0, 0], palette="Set1", width=0.3
)
sb.stripplot(
data=results_info,
y="score",
x="SUJ_gender",
ax=ax[0, 0],
palette="Set1",
linewidth=1,
edgecolor="k",
size=3,
alpha=0.3,
zorder=1,
)
ax[0, 0].set_title("AUC ROC scores vs. subject gender")
ax[0, 0].set_xticklabels(["Man", "Woman"])
ax[0, 0].set_ylabel("ROC AUC")
ax[0, 0].set_xlabel(None)
ax[0, 0].set_ylim(0.3, 1)
(0.3, 1.0)
5.2 Plotting subject AUC ROC scores vs subjects’s age per gender
sb.regplot(
data=results_info[results_info["SUJ_gender"] == 1][["score", "Age"]].astype(
"float32"
),
y="score",
x="Age",
ax=ax[0, 1],
scatter_kws={"color": "#e41a1c", "alpha": 0.5},
line_kws={"color": "#e41a1c"},
)
sb.regplot(
data=results_info[results_info["SUJ_gender"] == 2][["score", "Age"]].astype(
"float32"
),
y="score",
x="Age",
ax=ax[0, 1],
scatter_kws={"color": "#377eb8", "alpha": 0.5},
line_kws={"color": "#377eb8"},
)
ax[0, 1].set_title("AUC ROC scores vs. subject age per gender")
ax[0, 1].set_ylabel(None)
ax[0, 1].set_xlabel(None)
ax[0, 1].legend(
handles=[
mpatches.Patch(color="#e41a1c", label="Man"),
mpatches.Patch(color="#377eb8", label="Woman"),
]
)
<matplotlib.legend.Legend object at 0x7f4516a61350>
5.3 Plotting subject AUC ROC scores vs experimenter’s gender
sb.boxplot(
data=results_info, y="score", x="EXP_gender", ax=ax[1, 0], palette="Set1", width=0.3
)
sb.stripplot(
data=results_info,
y="score",
x="EXP_gender",
ax=ax[1, 0],
palette="Set1",
linewidth=1,
edgecolor="k",
size=3,
alpha=0.3,
zorder=1,
)
ax[1, 0].set_title("AUC ROC scores vs. experimenter gender")
ax[1, 0].set_xticklabels(["Man", "Woman"])
ax[1, 0].set_ylabel("ROC AUC")
ax[1, 0].set_xlabel(None)
ax[1, 0].set_ylim(0.3, 1)
(0.3, 1.0)
5.4 Plotting subject AUC ROC scores vs subject’s age
5.5 Obtained results for four selected subjects correspond to the following figure.#
Obtained results for all subjects correspond to the following figure.
Total running time of the script: (0 minutes 42.265 seconds)
Estimated memory usage: 3147 MB
Run this example
