[WIP] Adding a A large EEG database with users' profile information for motor imagery Brain-Computer Interface dataset

.pre-commit-config.yaml

@@ -79,7 +79,7 @@ repos:
     hooks:
       - id: codespell
         args:
-          - --ignore-words-list=additionals,alle,alot,bund,currenty,datas,farenheit,falsy,fo,haa,hass,iif,incomfort,ines,ist,nam,nd,pres,pullrequests,resset,rime,ser,serie,te,technik,ue,unsecure,withing,zar
+          - --ignore-words-list=additionals,alle,aline,alot,bund,currenty,datas,farenheit,falsy,fo,haa,hass,iif,incomfort,ines,ist,nam,nd,perfomances,pres,pullrequests,resset,rime,ser,serie,te,technik,ue,unsecure,withing,zar
           - --skip="./.*,*.csv,*.json,*.ambr"
           - --quiet-level=2
         exclude_types: [ csv, json, svg ]

docs/source/datasets.rst

@@ -21,6 +21,9 @@ Motor Imagery Datasets
     BNCI2015_001
     BNCI2015_004
     Cho2017
+    Dreyer2023A
+    Dreyer2023B
+    Dreyer2023C
     Lee2019_MI
     GrosseWentrup2009
     Ofner2017

docs/source/whats_new.rst

@@ -20,6 +20,7 @@ Enhancements
 
 - Adding cache option to the evaluation (:gh:`517` by `Bruno Aristimunha`_)
 - Option to interpolate channel in paradigms' `match_all` method (:gh:`480` by `Gregoire Cattan`_)
+- Adding new motor imagery dataset, Dreyer2023 (PR :gh: `404` by `Sara Sedlar`_ and `Sylvain Chevallier`_)
 - Adding leave k-Subjects out evaluations (:gh:`470` by `Bruno Aristimunha`_)
 - Update Braindecode dependency to 0.8 (:gh:`542` by `Pierre Guetschel`_)
 - Improve transform function of AugmentedDataset (:gh:`541` by `Quentin Barthelemy`_)
@@ -31,6 +32,7 @@ Bugs
 
 - Fix TRCA implementation for different stimulation freqs and for signal filtering (:gh:522 by `Sylvain Chevallier`_)
 - Fix saving to BIDS runs with a description string in their name (:gh:`530` by `Pierre Guetschel`_)
+- Fix issue with WithinSessionEvaluation with multiple datasets (PR :gh: `521`, issue :gh: `514` by `Sara Sedlar`_)
 - Fix import of keras BatchNormalization for TF 2.13 and higher (:gh:`544` by `Brian Irvine`_)
 - Fix the doc summary tables of :class:`moabb.datasets.Lee2019_SSVEP` (:gh:`548` :gh:`547` :gh:`546` by `Pierre Guetschel`_)
 - Fix the doc summary for Castillos2023 dataset (:gh:`561` by `Bruno Aristimunha`_)

examples/Dreyer_clf_scores_vs_subj_info.py

@@ -0,0 +1,159 @@
+"""
+===============================================
+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 pandas as pd
+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
+
+
+# 1. Defining dataset, selecting subject for analysis and getting data
+########################################################################################
+dreyer2023 = Dreyer2023A()
+dreyer2023.subject_list = [1, 5, 7, 35]
+dreyer2023.get_data()
+########################################################################################
+# 2. 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")
+)
+########################################################################################
+# 3. Within session evaluation of the pipeline
+evaluation = WithinSessionEvaluation(
+    paradigm=paradigm, datasets=[dreyer2023], suffix="examples", overwrite=True
+)
+results = evaluation.process(pipelines)
+results = results.loc[results["subject"].isin([str(s) for s in dreyer2023.subject_list])]
+########################################################################################
+# 4. Loading dataset info and concatenation with the obtained results
+info = dreyer2023.get_subject_info().rename(columns={"score": "score_MR"})
+results_info = pd.concat([info, results], axis=1)
+results_info["Age"] = 2019 - results_info["Birth_year"]
+########################################################################################
+# 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)
+########################################################################################
+# 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"),
+    ]
+)
+########################################################################################
+# 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)
+########################################################################################
+# 5.4 Plotting subject AUC ROC scores vs subject's age
+sb.regplot(
+    data=results_info[["score", "Age"]].astype("float32"),
+    y="score",
+    x="Age",
+    ax=ax[1, 1],
+    scatter_kws={"color": "black", "alpha": 0.5},
+    line_kws={"color": "black"},
+)
+ax[1, 1].set_title("AUC ROC scores vs. subject age")
+ax[1, 1].set_ylabel(None)
+plt.show()
+########################################################################################
+# 5.5 Obtained results for four selected subjects correspond to the following figure.
+#
+# .. image:: images/Dreyer_clf_scores_vs_subj_info/4_selected_subjects.png
+#    :align: center
+#    :alt: 4_selected_subjects
+#
+# Obtained results for all subjects correspond to the following figure.
+#
+# .. image:: images/Dreyer_clf_scores_vs_subj_info/all_subjects.png
+#    :align: center
+#    :alt: all_subjects
+#
+########################################################################################