Dataset summary in CSV and leaderboard links

docs/Makefile

@@ -17,6 +17,7 @@ help:
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
+	@python prepare_summary_tables.py ../moabb/datasets $(BUILDDIR)
 	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
 
 apidoc:

docs/prepare_summary_tables.py

@@ -0,0 +1,34 @@
+import glob
+from argparse import ArgumentParser
+from pathlib import Path
+
+import pandas as pd
+
+
+def prepare_table(df: pd.DataFrame):
+    no_pwc = df["PapersWithCode leaderboard"].isna()
+    df.loc[no_pwc, "PapersWithCode leaderboard"] = "No"
+    df.loc[~no_pwc, "PapersWithCode leaderboard"] = df.loc[
+        ~no_pwc, "PapersWithCode leaderboard"
+    ].apply(lambda x: f"`Yes <{x}>`_")
+    df["Dataset"] = df["Dataset"].apply(lambda x: f":class:`{x}`")
+
+
+def main(source_dir: str, target_dir: str):
+    target_dir = Path(target_dir)
+    target_dir.mkdir(parents=True, exist_ok=True)
+    files = glob.glob(str(Path(source_dir) / "*.csv"))
+    for f in files:
+        target_file = target_dir / Path(f).name
+        print(f"Processing {f} -> {target_file}")
+        df = pd.read_csv(f, index_col=False, header=0, skipinitialspace=True)
+        prepare_table(df)
+        df.to_csv(target_file, index=False)
+
+
+if __name__ == "__main__":
+    parser = ArgumentParser()
+    parser.add_argument("source_dir", type=str)
+    parser.add_argument("target_dir", type=str)
+    args = parser.parse_args()
+    main(args.source_dir, args.target_dir)

docs/source/dataset_summary.rst

@@ -22,66 +22,28 @@ Motor Imagery
 ======================
 
 .. csv-table::
-   :header: Dataset, #Subj, #Chan, #Classes, #Trials, Trial length, Freq, #Session, #Runs, Total_trials
+   :file: ../build/summary_imagery.csv
+   :header-rows: 1
    :class: sortable
 
-        :class:`AlexMI`,8,16,3,20,3s,512Hz,1,1,480
-        :class:`BNCI2014_001`,9,22,4,144,4s,250Hz,2,6,62208
-        :class:`BNCI2014_002`,14,15,2,80,5s,512Hz,1,8,17920
-        :class:`BNCI2014_004`,9,3,2,360,4.5s,250Hz,5,1,32400
-        :class:`BNCI2015_001`,12,13,2,200,5s,512Hz,3,1,14400
-        :class:`BNCI2015_004`,9,30,5,80,7s,256Hz,2,1,7200
-        :class:`Cho2017`,52,64,2,100,3s,512Hz,1,1,9800
-        :class:`Lee2019_MI`,54,62,2,100,4s,1000Hz,2,1,11000
-        :class:`GrosseWentrup2009`,10,128,2,150,7s,500Hz,1,1,3000
-        :class:`Schirrmeister2017`,14,128,4,120,4s,500Hz,1,2,13440
-        :class:`Ofner2017`,15,61,7,60,3s,512Hz,1,10,63000
-        :class:`PhysionetMI`,109,64,4,23,3s,160Hz,1,1,69760
-        :class:`Shin2017A`,29,30,2,30,10s,200Hz,3,1,5220
-        :class:`Shin2017B`,29,30,2,30,10s,200Hz,3,1,5220
-        :class:`Weibo2014`,10,60,7,80,4s,200Hz,1,1,5600
-        :class:`Zhou2016`,4,14,3,160,5s,250Hz,3,2,11496
-        :class:`Stieger2021`,62,64,4,450,3s,1000Hz,7 or 11,1,250000
 
 P300/ERP
 ======================
 
 .. csv-table::
-   :header: Dataset, #Subj, #Chan, #Trials / class, Trials length, Sampling rate, #Sessions
+   :file: ../build/summary_p300.csv
+   :header-rows: 1
    :class: sortable
 
-   :class:`BNCI2014_008`, 8, 8, 3500 NT / 700 T, 1s, 256Hz, 1
-   :class:`BNCI2014_009`, 10, 16, 1440 NT / 288 T, 0.8s, 256Hz, 3
-   :class:`BNCI2015_003`, 10, 8, 1500 NT / 300 T, 0.8s, 256Hz, 1
-   :class:`BI2012`, 25, 16, 640 NT / 128 T, 1s, 128Hz, 2
-   :class:`BI2013a`, 24, 16, 3200 NT / 640 T, 1s, 512Hz, 8 for subjects 1-7 else 1
-   :class:`BI2014a`, 64, 16, 990 NT / 198 T, 1s, 512Hz, up to 3
-   :class:`BI2014b`, 38, 32, 200 NT / 40 T, 1s, 512Hz, 3
-   :class:`BI2015a`, 43, 32, 4131 NT / 825 T, 1s, 512Hz, 3
-   :class:`BI2015b`, 44, 32, 2160 NT / 480 T, 1s, 512Hz, 1
-   :class:`Cattan2019_VR`, 21, 16, 600 NT / 120 T, 1s, 512Hz, 2
-   :class:`Huebner2017`, 13, 31, 364 NT / 112 T, 0.9s, 1000Hz, 3
-   :class:`Huebner2018`, 12, 31, 364 NT / 112 T, 0.9s, 1000Hz, 3
-   :class:`Sosulski2019`, 13, 31, 7500 NT / 1500 T, 1.2s, 1000Hz, 1
-   :class:`EPFLP300`, 8, 32, 2753 NT / 551 T, 1s, 2048Hz, 4
-   :class:`Lee2019_ERP`, 54, 62, 6900 NT / 1380 T, 1s, 1000Hz, 2
-
 
 SSVEP
 ======================
 
-
 .. csv-table::
-   :header: Dataset, #Subj, #Chan, #Classes, #Trials / class, Trials length, Sampling rate, #Sessions
+   :file: ../build/summary_ssvep.csv
+   :header-rows: 1
    :class: sortable
 
-   :class:`Lee2019_SSVEP`,54,62,4,50,4s,1000Hz,2
-   :class:`Kalunga2016`,12,8,4,16,2s,256Hz,1
-   :class:`MAMEM1`,10,256,5,12-15,3s,250Hz,1
-   :class:`MAMEM2`,10,256,5,20-30,3s,250Hz,1
-   :class:`MAMEM3`,10,14,4,20-30,3s,128Hz,1
-   :class:`Nakanishi2015`,9,8,12,15,4.15s,256Hz,1
-   :class:`Wang2016`,34,62,40,6,5s,250Hz,1
 
 c-VEP
 ======================
@@ -97,17 +59,10 @@ potentials (c-VEP): A literature review. Journal of Neural Engineering, 18(6), 0
 DOI: https://doi.org/10.1088/1741-2552/ac38cf
 
 .. csv-table::
-   :header: Dataset, #Subj, #Sessions, Sampling rate, #Chan, Trials length, #Trial classes, #Trials / class, #Epochs classes, #Epochs / class, Codes, Presentation rate
+   :file: ../build/summary_cvep.csv
+   :header-rows: 1
    :class: sortable
 
-   :class:`Thielen2015`,12,1,2048Hz,64,4.2s,36,3,2,27216 NT / 27216 T,Gold codes,120Hz
-   :class:`Thielen2021`,30,1,512Hz,8,31.5s,20,5,2,18900 NT / 18900 T,Gold codes,60Hz
-   :class:`CastillosCVEP100`,    12,1,500Hz,32,2.2s,4,15/15/15/15,2,3525 NT / 3495 T,m-sequence,60Hz
-   :class:`CastillosCVEP40`,     12,1,500Hz,32,2.2s,4,15/15/15/15,2,3525 NT / 3495 T,m-sequence,60Hz
-   :class:`CastillosBurstVEP40`, 12,1,500Hz,32,2.2s,4,15/15/15/15,2,5820 NT / 1200 T,Burst-CVEP,60Hz
-   :class:`CastillosBurstVEP100`,12,1,500Hz,32,2.2s,4,15/15/15/15,2,5820 NT / 1200 T,Burst-CVEP,60Hz
-
-
 Resting States
 ======================
 
@@ -116,12 +71,9 @@ For example, recoding the EEG of a subject while s/he is having the eye closed o
 is a resting state experiment.
 
 .. csv-table::
-   :header: Dataset, #Subj, #Chan, #Classes, #Blocks / class, Trials length, Sampling rate, #Sessions
-   :class: sortable
-
-   :class:`Cattan2019_PHMD`,12,16,2,10,60s,512Hz,1
-   :class:`Hinss2021`,15,62,4,1,2s,250Hz,1
-   :class:`Rodrigues2017`,20,16,2,5,10s,512Hz,1
+    :file: ../build/summary_rstate.csv
+    :header-rows: 1
+    :class: sortable
 
 Compound Datasets
 ======================

docs/source/whats_new.rst

@@ -17,7 +17,7 @@ Develop branch
 
 Enhancements
 ~~~~~~~~~~~~
-- None
+- Centralize dataset summary tables in CSV files (:gh:`635` by `Pierre Guetschel`_)
 
 Bugs
 ~~~~

moabb/datasets/Lee2019.py

@@ -220,15 +220,6 @@ def data_path(
 class Lee2019_MI(Lee2019):
     """BMI/OpenBMI dataset for MI.
 
-    .. admonition:: Dataset summary
-
-
-        ==========  =======  =======  ==========  =================  ============  ===============  ===========
-        Name          #Subj    #Chan    #Classes    #Trials / class  Trials len    Sampling rate      #Sessions
-        ==========  =======  =======  ==========  =================  ============  ===============  ===========
-        Lee2019_MI       54       62           2                100  4s            1000Hz                     2
-        ==========  =======  =======  ==========  =================  ============  ===============  ===========
-
     Dataset from Lee et al 2019 [1]_.
 
     **Dataset Description**
@@ -290,15 +281,6 @@ class Lee2019_MI(Lee2019):
 class Lee2019_ERP(Lee2019):
     """BMI/OpenBMI dataset for P300.
 
-    .. admonition:: Dataset summary
-
-
-        ===========  =======  =======  =================  ===============  ===============  ===========
-        Name           #Subj    #Chan  #Trials / class    Trials length    Sampling rate      #Sessions
-        ===========  =======  =======  =================  ===============  ===============  ===========
-        Lee2019_ERP       54       62  6900 NT / 1380 T   1s               1000Hz                     2
-        ===========  =======  =======  =================  ===============  ===============  ===========
-
     Dataset from Lee et al 2019 [1]_.
 
     **Dataset Description**
@@ -380,15 +362,6 @@ class Lee2019_ERP(Lee2019):
 class Lee2019_SSVEP(Lee2019):
     """BMI/OpenBMI dataset for SSVEP.
 
-    .. admonition:: Dataset summary
-
-
-        =============  =======  =======  ==========  =================  ===============  ===============  ===========
-        Name             #Subj    #Chan    #Classes    #Trials / class  Trials length    Sampling rate      #Sessions
-        =============  =======  =======  ==========  =================  ===============  ===============  ===========
-        Lee2019_SSVEP       54       62           4                 50  4s               1000Hz                     2
-        =============  =======  =======  ==========  =================  ===============  ===============  ===========
-
     Dataset from Lee et al 2019 [1]_.
 
     **Dataset Description**

moabb/datasets/Weibo2014.py

@@ -64,15 +64,6 @@ def get_subjects(sub_inds, sub_names, ind):
 class Weibo2014(BaseDataset):
     """Motor Imagery dataset from Weibo et al 2014.
 
-    .. admonition:: Dataset summary
-
-
-        =========  =======  =======  ==========  =================  ============  ===============  ===========
-        Name         #Subj    #Chan    #Classes    #Trials / class  Trials len    Sampling rate      #Sessions
-        =========  =======  =======  ==========  =================  ============  ===============  ===========
-        Weibo2014       10       60           7                 80  4s            200Hz                      1
-        =========  =======  =======  ==========  =================  ============  ===============  ===========
-
     Dataset from the article *Evaluation of EEG oscillatory patterns and
     cognitive process during simple and compound limb motor imagery* [1]_.
 

moabb/datasets/Zhou2016.py

@@ -50,15 +50,6 @@ def local_data_path(base_path, subject):
 class Zhou2016(BaseDataset):
     """Motor Imagery dataset from Zhou et al 2016.
 
-    .. admonition:: Dataset summary
-
-
-        ========  =======  =======  ==========  =================  ============  ===============  ===========
-        Name        #Subj    #Chan    #Classes    #Trials / class  Trials len    Sampling rate      #Sessions
-        ========  =======  =======  ==========  =================  ============  ===============  ===========
-        Zhou2016        4       14           3                160  5s            250Hz                      3
-        ========  =======  =======  ==========  =================  ============  ===============  ===========
-
     Dataset from the article *A Fully Automated Trial Selection Method for
     Optimization of Motor Imagery Based Brain-Computer Interface* [1]_.
     This dataset contains data recorded on 4 subjects performing 3 type of

moabb/datasets/alex_mi.py

@@ -12,15 +12,6 @@
 class AlexMI(BaseDataset):
     """Alex Motor Imagery dataset.
 
-    .. admonition:: Dataset summary
-
-
-        ======  =======  =======  ==========  =================  ============  ===============  ===========
-        Name      #Subj    #Chan    #Classes    #Trials / class  Trials len    Sampling rate      #Sessions
-        ======  =======  =======  ==========  =================  ============  ===============  ===========
-        AlexMI        8       16           3                 20  3s            512Hz                      1
-        ======  =======  =======  ==========  =================  ============  ===============  ===========
-
     Motor imagery dataset from the PhD dissertation of A. Barachant [1]_.
 
     This Dataset contains EEG recordings from 8 subjects, performing 2 task of

moabb/datasets/alphawaves.py

@@ -17,16 +17,6 @@
 class Rodrigues2017(BaseDataset):
     """Alphawaves dataset
 
-    .. admonition:: Dataset summary
-
-
-        =============== ======= ======= ========== =============== ============ =============== ===========
-        Name            #Subj   #Chan   #Classes   #Blocks/class   Trials len   Sampling rate   #Sessions
-        =============== ======= ======= ========== =============== ============ =============== ===========
-        Rodrigues2017   20      16      2          5               10s          512Hz           1
-        =============== ======= ======= ========== =============== ============ =============== ===========
-
-
     Dataset containing EEG recordings of subjects in a simple
     resting-state eyes open/closed experimental protocol. Data were recorded
     during a pilot experiment taking place in the GIPSA-lab, Grenoble,
@@ -139,7 +129,6 @@ def _get_single_subject_data(self, subject):
     def data_path(
         self, subject, path=None, force_update=False, update_path=None, verbose=None
     ):
-
         if subject not in self.subject_list:
             raise (ValueError("Invalid subject number"))