Release v.1.4.3

Enhancements

• Add “Open in Colab” buttons for gallery examples (:gh:853 by Bruno Aristimunha_)
• Refresh docs homepage design and citation visibility (:gh:853 by Bruno Aristimunha_)
• Add moabb.datasets.preprocessing.FixedPipeline and moabb.datasets.preprocessing.make_fixed_pipeline to avoid scikit-learn unfitted pipeline warnings (:gh:850 by Bruno Aristimunha_)

API changes

• None.

Requirements

• Improve compatibility with Python 3.14 (:gh:848 by Bruno Aristimunha_)

Bugs

• Fixing warnings from the latest scikit-learn version within the Preprocessing logic (:gh:850 by Bruno Aristimunha_)
• Fixing compatibility with Scikit-learn 1.8 (:gh:852 by Bruno Aristimunha_)

Enhancements

• Adding dataset moabb.datasets.RomaniBF2025ERP converted to BIDS (:gh:825 by Romani Michele_)
• Improve compute_pvals_perm function (:gh:818 by Quentin Barthelemy_)

Bugs

• Fixes the management of include/exclude datasets in moabb.benchmark, adds additional verifications (:gh:834 by Anton Andreev_)
• Fixing pagination issue with figshare (:gh:839 by Bruno Aristimunha_)
• Fixes moabb.datasets.preprocessing.SetRawAnnotations in case no STIM channel is present (:gh:838 by Pierre Guetschel_ and Simon Kojima_)

Full Changelog: v1.4.0...v.1.4.3

What's Changed

• Release V1.2.0 by @bruAristimunha in #714
• Skip tests due to network issues with dataverse.harvard.edu by @bruAristimunha in #835
• Improved _inc_exc_datasets() and paradigms handling in benchmark() by @toncho11 in #834
• Dataset class for BrainForm by Romani et al. by @BRomans in #825
• Improve compute_pvals_perm function by @qbarthelemy in #818
• [HOT-FIX] fixing the pagination of figure share and doing mini release by @bruAristimunha in #839
• V1.4.2 by @bruAristimunha in #845
• Fix SetRawAnnotations when no stim channel by @PierreGtch in #838
• Increase compatibility with Python 3.14 by @Copilot in #848
• Fix warnings from scikit-learn 1.8+ and introduce FixedPipeline by @bruAristimunha in #850
• Fix compatibility with scikit-learn 1.8 by @bruAristimunha in #852
• Enhance documentation and update design elements by @bruAristimunha in #853

New Contributors

• @BRomans made their first contribution in #825

Full Changelog: v1.4.0...v.1.4.3

v1.4.0

This release note was generated automatically

What's Changed

• develop into master v1.1.1 by @bruAristimunha in #645
• Release candidate for v1.2.0 by @bruAristimunha in #710
• MNT Release 1.2.0 by @bruAristimunha in #711
• V1.2.0 by @bruAristimunha in #713
• Correct bug when corrupted cache results by @sylvchev in #715
• [MNT] update the documentation generation by @bruAristimunha in #706
• [EHN] creating the metainformation file to allow lazy loading by default by @bruAristimunha in #688
• [WIP] Adding a A large EEG database with users' profile information for motor imagery Brain-Computer Interface dataset by @Sara04 in #404
• Removing the Keras sub-module from moabb by @bruAristimunha in #692
• Add BEETL data to MOABB for benchmarking by @Samuel-Boehm in #675
• MNT adjusting the docs by @bruAristimunha in #719
• Update tdlda dep by @PierreGtch in #717
• BaseBIDSDataset and LocalBIDSDataset by @PierreGtch in #724
• Pick all data channels in filter preprocessing step by @PierreGtch in #729
• [mnt] fix the n2pc by @bruAristimunha in #730
• [mnt] removing the rest session and unit by @bruAristimunha in #731
• Including cross-session splitter by @bruAristimunha in #720
• Fix analysis test by @gcattan in #735
• Fix seed in permutation test by @PierreGtch in #736
• [MNT] Updating the doc by @bruAristimunha in #738
• Update the range of python versions to allow moabb to work with python 3.13.2 by @papadop in #740
• Updating ci by @bruAristimunha in #742
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in #745
• Mnt fix doc by @bruAristimunha in #746
• Including Cross subject splitter by @bruAristimunha in #722
• Fix linux server download issue (#750) by @zyao197 in #751
• Dataset bubbles plot by @PierreGtch in #753
• Add shape, gap and size_mode parameters to dataset_bubble_plot by @PierreGtch in #755
• Additional fixes for dataset_bubble_plot by @PierreGtch in #756
• Add test for dataset plot by @PierreGtch in #757
• Add plot_all_datasets function by @PierreGtch in #758
• Fix links in paper_results.rst to point to the correct pages by @noostale in #759
• [MNT] dataset_bubble_plot tight_layout by @PierreGtch in #761
• Add plot_all_datasets function to doc by @PierreGtch in #764
• Improve the dataset cards by @PierreGtch in #765
• Add plot_datasets_cluster function by @PierreGtch in #766
• Fix some tests not running in test_datasets by @lucas-heck in #768
• Improve dataset plots by @PierreGtch in #770
• Creating a tutorial showing how to play with pre-processing steps by @bruAristimunha in #771
• Last mini-change to the dataset plot by @PierreGtch in #772
• Add tutorial on using mne-features in pipeline by @alexander-de-ranitz in #762
• remove keras eegnet codecarbon example by @amar-enkhbat in #777
• Added a tutorial for the Within session splitter named tutorial splitter by @jellymace in #776
• Fix regression in process_pipeline flag by @bruAristimunha in #774
• Including the fix_bad_channels for the :class:moabb.datasets.Stieger2021 by @bruAristimunha in #783
• Changed channels CB1 and CB2's type from 'misc' to 'eeg' from Wang2016 dataset by @UlysseDurand in #781
• FIX Reduce warnings when building documentation by @lucas-heck in #784
• DOC Add function to auto-generate the paper results tables by @lucas-heck in #785
• Update README.md by @lionelkusch in #791
• Update CONTRIBUTING.md by @lionelkusch in #792
• Exposing util functions by @bruAristimunha in #788
• Update CODE_OF_CONDUCT.md by @bruAristimunha in #796
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in #798
• Fix: number of trial per class for PHMD_ML dataset by @gcattan in #797
• A tutorial on how to create and use a MOABB dataset from X y (non continuous, epoched) data by @toncho11 in #800
• Filterbank tutorial by @bruAristimunha in #787
• [FIX] Converting the Zhou2016 to allow increase the moabb version by @bruAristimunha in #802
• Update to pyRiemann 0.9 and mne 1.10 by @gcattan in #789
• Increased visibility of LocalBIDSDataset by adding small description to data summary page by @TessvandeVijver in #778
• Pre-release 1.3.0 by @bruAristimunha in #803
• Update evaluation to use new splitters and include updates by @bruAristimunha in #769
• Add BNCI2003_004 dataset (BCI Competition III Dataset IVa) by @griffinkeeler in #811
• Add auditory ERP dataset (Kojima2024A) by @simonkojima in #807
• [BUG] swap the labels of '17' and '21' by @ponpopon in #814
• Add auditory ERP dataset (Kojima2024B) by @simonkojima in #806
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in #819
• Fix issues in Dreyer2023 dataset by @simonkojima in #828
• Document pyRiemann 0.9 and numpy 2.0 compatibility update in changelog by @Copilot in #821
• Easier handling of pipelines for benchmark() by @toncho11 in #826
• Pre-release 1.4.0 by @PierreGtch in #831

New Contributors

• @papadop made their first contribution in #740
• @zyao197 made their first contribution in #751
• @noostale made their first contribution in #759
• @lucas-heck made their first contribution in #768
• @alexander-de-ranitz made their first contribution in #762
• @amar-enkhbat made their first contribution in #777
• @jellymace made their first contribution in #776
• @UlysseDurand made their first contribution in #781
• @lionelkusch made their first contribution in #791
• @TessvandeVijver made their first contribution in #778
• @griffinkeeler made their first contribution in #811
• @simonkojima made their first contribution in #807
• @ponpopon made their first contribution in #814
• @Copilot made their first contribution in #821

Full Changelog: v1.2.0...v1.4.0

v1.2.0

New Contributors

• @martinwimpff made their first contribution in #651
• @Samuel-Boehm made their first contribution in #674
• @allwaysFindFood made their first contribution in #685

Full Changelog: v1.1.1...v1.2.0

v1.1.1

Version - 1.1.1 (Stable - PyPi)

Enhancements

• Add possibility to use OptunaGridSearch (#630 by Igor Carrara)
• Add scripts to upload results on PapersWithCode (#561 by Pierre Guetschel)
• Centralize dataset summary tables in CSV files (#635 by Pierre Guetschel)
• Add new dataset moabb.datasets.Liu2024 (#619 by Taha Habib)

Bugs

• Fix caching in the workflows (#632 by Pierre Guetschel)

API changes

• Include optuna as a soft-dependency in the benchmark function and in the base of evaluation (#630 by Igor Carrara)

MOABB stable version v1.1.0

Enhancements

• Add cache option to the evaluation (#518 by Bruno Aristimunha)
• Option to interpolate channel in paradigms’ match_all method (#480 by Gregoire Cattan)
• Add leave k-Subjects out evaluations (#470 by Bruno Aristimunha)
• Update Braindecode dependency to 0.8 (#542 by Pierre Guetschel)
• Improve transform function of AugmentedDataset (#541 by Quentin Barthelemy)
• Add new paper results website (#556 by Bruno Aristimunha)
• Move cVEP common functions to moabb.datasets.utils (#564 #557 by Pierre Guetschel)
• Normalize c-VEP description tables (#562 #566 by Pierre Guetschel and Bruno Aristimunha)
• Update citation in README (#573 by Igor Carrara)
• Update pyRiemann dependency (#577 by Gregoire Cattan)
• Add resting stage Hinss2021 dataset (#580 by Gregoire Cattan and Yash Chauhan)
• Expose the learning rate parameter in the keras deep learning methods and optimize parameters (#589 and #592 by Bruno Aristimunha)
• Updating the braindecode pipelines for the new braindecode version 0.8.1 (#589 by Bruno Aristimunha)
• Add SSVEP and ERP paradigms to DL pipelines (#590 by Pierre Guetschel)
• Allow to pass a single pipeline file to benchmark (#591 by Pierre Guetschel)
• Add new dataset moabb.datasets.Stieger2021 (#604 by Reinmar Kobler and Bruno Aristimunha)
• Exposing the drop_rate for all the deep learning parameters (#592 by Bruno Aristimunha)
• Add new dataset moabb.datasets.Rodrigues2017 dataset (#602 by Gregoire Cattan and Pedro L. C. Rodrigues)
• Change unittest to pytest (#618 by Bruno Aristimunha)
• Remove tensorflow import warning (#622 by Bruno Aristimunha)

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 (#530 by Pierre Guetschel)
• Fix import of keras BatchNormalization for TF 2.13 and higher (#544 by Brian Irvine)
• Fix the doc summary tables of moabb.datasets.Lee2019_SSVEP (#548 #547 #546 by Pierre Guetschel)
• Fix the doc summary for Castillos2023 dataset (#561 by Bruno Aristimunha)
• Fix format string receiving incorrect number of args in bids interface (#563 by Pierre Guetschel)
• Fix number of sessions in doc of moabb.datasets.Sosulski2019 (#565 by Pierre Guetschel)
• Fix code column of moabb.datasets.CastillosCVEP100 and moabb.datasets.CastillosCVEP100 (#567 by Pierre Guetschel)
• MAINT updating the packages pre-release (#578 by Bruno Aristimunha)
• Fix mne_bids version incompatibility with mne (#586 by Bruna Lopes)
• Updating the parameters of the SSVEP_TRCA method (#589 by Bruno Aristimunha)
• Fix and updating the parameters for the benchmark function (#588 by Bruno Aristimunha)
• Fix moabb.datasets.preprocessing.SetRawAnnotations setting incorrect annotations when the dataset’s interval does not start at 0 (#607 by Pierre Guetschel)
• Fix download link for GigaDB Cho2017 and Lee2019 datasets (#621 by Anton Andreev)

API changes

• None

MOABB stable version

This new stable version of MOABB brings several new features (details below) and this is a new major version as the integration of BIDS compatibility was the opportunity to normalize dataset names, including a more regular naming scheme for sessions and runs. New addition includes support for new datasets, including cVEP ones.

API changes

• Renaming datasets, sessions and runs, see #455 and #471

Enhancements

• Adding extra thank you section in the documentation (#390 by Bruno Aristimunha)

• Adding new script to get the meta information of the datasets (#389 by Bruno Aristimunha)

• Fixing the dataset description based on the meta information (#389 and 398 by Bruno Aristimunha and Sara Sedlar)

• Adding second deployment of the documentation (#374 by Bruno Aristimunha)

• Adding Parallel evaluation for moabb.evaluations.WithinSessionEvaluation() , moabb.evaluations.CrossSessionEvaluation() (#364 by Bruno Aristimunha)

• Add example with VirtualReality BrainInvaders dataset (#393 by Gregoire Cattan and Pedro L. C. Rodrigues)

• Adding saving option for the models (#401 by Bruno Aristimunha and Igor Carrara)

• Adding example to load different type of models (#401 by Bruno Aristimunha and Igor Carrara)

• Add resting state paradigm with dataset and example (#400 by Gregoire Cattan and Pedro L. C. Rodrigues)

• Speeding the augmentation method by 400% with NumPy vectorization (#419 by Bruno Aristimunha)

• Add possibility to convert datasets to BIDS, plus example (PR #408, PR #391 by Pierre Guetschel and Bruno Aristimunha)

• Allow caching intermediate processing steps on disk, plus example (PR #408, issue #385 by Pierre Guetschel)

• Restructure the paradigms and datasets to move all preprocessing steps to moabb.datasets.preprocessing and as sklearn pipelines (PR #408 by Pierre Guetschel)

• Add moabb.paradigms.FixedIntervalWindowsProcessing() and moabb.paradigms.FilterBankFixedIntervalWindowsProcessing(), plus example (PR #408, issue #424 by Pierre Guetschel)

• Define moabb.paradigms.base.BaseProcessing(), common parent to moabb.paradigms.base.BaseParadigm() and moabb.paradigms.BaseFixedIntervalWindowsProcessing() (PR #408 by Pierre Guetschel)

• Allow passing a fixed processing pipeline to moabb.paradigms.base.BaseProcessing.get_data() and cache its result on disk (PR #408, issue #367 by Pierre Guetschel)

• Update moabb.datasets.fake.FakeDataset()’s code to be unique for each parameter combination (PR #408 by Pierre Guetschel)

• Systematically set the annotations when loading data, eventually using the stim channel (PR #408 by Pierre Guetschel)

• Allow moabb.datasets.utils.dataset_search() to search across paradigms paradigm=None (PR #408 by Pierre Guetschel)

• Improving the review processing with more pre-commit bots (#435 by Bruno Aristimunha)

• Add methods make_processing_pipelines and make_labels_pipeline to moabb.paradigms.base.BaseProcessing (#447 by Pierre Guetschel)

• Pipelines’ digests are now computed from the whole processing+classification pipeline (#447 by Pierre Guetschel)

• Update all dataset codes to remove white spaces and underscores (#448 by Pierre Guetschel)

• Add moabb.utils.depreciated_alias() decorator (#455 by Pierre Guetschel)

• Rename many dataset class names to standardize and deprecate old names (#455 by Pierre Guetschel)

• Change many dataset codes to match the class names (#455 by Pierre Guetschel)

• Add moabb.datasets.compound_dataset.utils.compound_dataset_list (#455 by Pierre Guetschel)

• Add c-VEP paradigm and Thielen2021 c-VEP dataset (#463 by Jordy Thielen)

• Add option to plot scores vertically. (#417 by Sara Sedlar)

• Change naming scheme for runs and sessions to align to BIDS standard (#471 by Pierre Guetschel)

• Increase the python version to 3.11 (#470 by Bruno Aristimunha)

• Add match_all method in paradigm to support CompoundDataset evaluation with MNE epochs (#473 by Gregoire Cattan)

• Automate setting of event_id in compound dataset and add data_origin information to the data (#475 by Gregoire Cattan)

• Add possibility of not saving the model (#489 by Igor Carrara)

Bugs

• Restore 3 subject from Cho2017 (#392 by Igor Carrara and Sylvain Chevallier)

• Correct downloading with VirtualReality BrainInvaders dataset (#393 by Gregoire Cattan)

• Rename event subtraction in moabb.datasets.Shin2017B() (#397 by [Pierre Guetschel](https://github.com/Pie...

MOABB v0.5 (stable)

This is the latest stable version of MOABB, 0.4.6, that is available on PyPi. See What's new section of the documentation for more information.

What's Changed

• Set download dir test and example by @Div12345 in #249
• Fix Schirrmeister2017 error by @sylvchev in #255
• Removing dependency of Physionet MI download on mne method by @Div12345 in #257
• Correct MAMEM issues by @sylvchev in #256
• Progress bars by @Div12345 in #258
• fix doc url in readme by @sylvchev in #262
• Schirrmeister2017 High-Gamma Dataset from EDF by @robintibor in #265
• added 13 + 12 subjects speller datasets by huebner by @jsosulski in #260
• added Spot Auditory oddball dataset by @jsosulski in #266
• Visualize all ERP datasets by @jsosulski in #261
• update to v0.4.5 by @sylvchev in #269
• correct pre-commit error and add code coverage by @sylvchev in #271
• add new erp datasets to docs by @jsosulski in #282
• Add Brain Invaders datasets by @sylvchev in #283
• Fix README.md documentation link in ToC by @jsosulski in #284
• Generalize default path for erp visualization by @jsosulski in #279
• Elicit warning if lambda functions are used by @jsosulski in #278
• update to 0.4.6 by @sylvchev in #286
• fix plot instantly close by @danidask in #288
• correct lint test failing due to black version by @sylvchev in #292
• preload Schirrmsister2017 - Fixes #289 by @PierreGtch in #290
• Fix typo by @yosider in #293
• remove unnecessary indents by @yosider in #297
• Correct Lee dataset loading by @sylvchev in #298
• Bump mistune from 0.8.4 to 2.0.3 by @dependabot in #303
• Hotfix _simplify_names by @Div12345 in #306
• Update deps and doc cleaning by @sylvchev in #315
• Benchmark function by @Div12345 in #264
• Adding Wiki Meta Information to the documentation by @bruAristimunha in #317
• Fix dataset downloading errors by @sylvchev in #318
• Return raw with get_data by @sylvchev in #302
• replacing the np.int to native type int. by @bruAristimunha in #321
• Grid Search on Evaluation by @carraraig in #319
• Beanchmark grid search by @carraraig in #323
• Deprecated numpy by @bruAristimunha in #324
• Updating the .pre-commit-yaml to fix CI. by @bruAristimunha in #330
• Restricting Python < 3.11 version and adding tensorflow, keras, scikeras, braindecode, skorch and torch [optional] by @bruAristimunha in #329
• Updating CI by @bruAristimunha in #332
• Update pipelines by @sylvchev in #326
• Adding Google analytics by @bruAristimunha in #335
• Fix bug for MotorImagery All events by @carraraig in #337
• Adding a convenient Docker by @bruAristimunha in #322
• Fixing whats new and one missed import by @bruAristimunha in #341
• Updating Gitter link by @bruAristimunha in #342
• Change n_jobs=-1 to self.n_jobs by @carraraig in #344
• Plot brain decode by @carraraig in #345
• Disable coverage patch by @bruAristimunha in #346
• Cleaning Pipeline by @carraraig in #349
• CodeCarbon by @carraraig in #350
• Fixing doc generation by @sylvchev in #351
• Circleci project setup by @bruAristimunha in #354
• Removing the CI by @bruAristimunha in #357
• Example CodeCarbon by @carraraig in #356
• Adding Braindecode pipeline by @bruAristimunha in #328
• New theme, PyData by @bruAristimunha in #353
• [Dataset] Brain Invaders dataset with VR/PC display by @gcattan in #358
• Fixing circular import by @bruAristimunha in #363
• Adding Data Description to Huebner2017, Huebner2018, Sosulski2019 by @bruAristimunha in #362
• Speeding the AUG Method by @bruAristimunha in #365
• MsetCCA SSVEP classification + example by @emmanuelkalunga in #359
• Fix dropped epochs by @PierreGtch in #371
• Adding redundancy deployment on web page by @bruAristimunha in #373
• Pipelines for MsetCCA SSVEP, TRCA SSVEP, and others by @emmanuelkalunga in #368

New Contributors

• @danidask made their first contribution in #288
• @yosider made their first contribution in #293
• @bruAristimunha made their first contribution in #317
• @carraraig made their first contribution in #319
• @gcattan made their first contribution in #358
• @emmanuelkalunga made their first contribution in #359

Full Changelog: v0.4.5...v0.5

MOABB v0.4.6 (stable)

This is the latest stable version of MOABB, 0.4.6, that is available on PyPi. See What's new section of the documentation for more information.

MOABB v0.4.5 (stable)

This is the new stable version of MOABB, 0.4.5, that is available on PyPi. See What's new section of the documentation for more information.

First PyPI version

We've added poetry based dependency management, added style checks via pre-commit also tested against all versions of Python starting from 3.6.

Now moabb could be installed like any other package via pip install moabb

Checkout https://pypi.org/project/moabb/