whats_new.rst

.. currentmodule:: moabb

What's new

Develop branch

Enhancements

• Switch to python-3.8, update dependencies, fix code link in doc, add code coverage (:gh:`315` by Sylvain Chevallier)
• Adding a comprehensive benchmarking function (:gh:`264` by Divyesh Narayanan and Sylvain Chevallier)
• Add meta-information for datasets in documentation (:gh:`317` by Bruno Aristimunha)
• Add GridSearchCV for different evaluation procedure (:gh:`319` by Igor Carrara)
• Adding new tutorial to benchmark with GridSearchCV (:gh:`323` by Igor Carrara)
• Add six deep learning models (Tensorflow), and build a tutorial to show to use the deep learning model (:gh:`326` by Igor Carrara, Bruno Aristimunha and Sylvain Chevallier)
• Add a augmentation model to the pipeline (:gh:`326` by Igor Carrara)
• Add BrainDecode example(:gh:`340` by Igor Carrara and Bruno Aristimunha)
• Add Google Analytics to the documentation (:gh:`335` by Bruno Aristimunha)

Bugs

• Fix bug for MotorImagery when we handle all events (:gh:`327` by Igor Carrara)
• Fixing CI to handle with new deep learning dependencies (:gh:`332` and :gh:`326` by Igor Carrara, Bruno Aristimunha and Sylvain Chevallier)
• Correct CI error due to isort (:gh:`330` by Bruno Aristimunha)
• Restricting Python <= 3.11 version and adding tensorflow, keras, scikeras, braindecode, skorch and torch, as optional dependence (:gh:`329` by Bruno Aristimunha)
• Fix numpy variable to handle with the new version of python (:gh:`324` by Bruno Aristimunha)
• Correct CI error due to black (:gh:`292` by Sylvain Chevallier)
• Preload Schirrmeister2017 raw files (:gh:`290` by Pierre Guetschel)
• Incorrect event assignation for Lee2019 in MNE >= 1.0.0 (:gh:`298` by Sylvain Chevallier)
• Correct usage of name simplification function in analyze (:gh:`306` by Divyesh Narayanan)
• Fix downloading path issue for Weibo2014 and Zhou2016, numy error in DemonsP300 (:gh:`315` by Sylvain Chevallier)
• Fix unzip error for Huebner2017 and Huebner2018 (:gh:`318` by Sylvain Chevallier)
• Fix n_classes when events set to None (:gh:`337` by Igor Carrara and Sylvain Chevallier)
• Change n_jobs=-1 to self.n_jobs in GridSearch (:gh:`344` by Igor Carrara)

API changes

• None

Version - 0.4.6 (Stable - PyPi)

Enhancements

• Add P300 BrainInvaders datasets (:gh:`283` by Sylvain Chevallier)
• Add explicit warning when lambda function are used to parametrize pipelines (:gh:`278` by Jan Sosulski)

Bugs

• Correct default path for ERP visualization (:gh:`279` by Jan Sosulski)
• Correct documentation (:gh:`282` and :gh:`284` by Jan Sosulski)

Version - 0.4.5

Enhancements

• Progress bars, pooch, tqdm (:gh:`258` by Divyesh Narayanan and Sylvain Chevallier)
• Adding test and example for set_download_dir (:gh:`249` by Divyesh Narayanan)
• Update to newer version of Schirrmeister2017 dataset (:gh:`265` by Robin Schirrmeister)
• Adding Huebner2017 and Huebner2018 P300 datasets (:gh:`260` by Jan Sosulski)
• Adding Sosulski2019 auditory P300 datasets (:gh:`266` by Jan Sosulski)
• New script to visualize ERP on all datasets, as a sanity check (:gh:`261` by Jan Sosulski)

Bugs

• Removing dependency on mne method for PhysionetMI data downloading, renaming runs (:gh:`257` by Divyesh Narayanan)
• Correcting events management in Schirrmeister2017, renaming session and run (:gh:`255` by Pierre Guetschel and Sylvain Chevallier)
• Switch session and runs in MAMEM1, 2 and 3 to avoid error in WithinSessionEvaluation (:gh:`256` by Sylvain Chevallier)
• Correct doctstrings for the documentation, incuding Lee2017 (:gh:`256` by Sylvain Chevallier)

Version - 0.4.4

Enhancements

• Add TRCA algorithm for SSVEP (:gh:`238` by Ludovic Darmet)

Bugs

• Remove unused argument from dataset_search (:gh:`243` by Divyesh Narayanan)
• Remove MNE call to _fetch_dataset and use MOABB _fetch_file (:gh:`235` by Jan Sosulski)
• Correct doc formatting (:gh:`232` by Sylvain Chevallier)

API changes

• Minimum supported Python version is now 3.7
• MOABB now depends on scikit-learn >= 1.0

Version - 0.4.3

Enhancements

• Rewrite Lee2019 to add P300 and SSVEP datasets (:gh:`217` by Pierre Guetschel)

Bugs

• Avoid information leakage for MNE Epochs pipelines in evaluation (:gh:`222` by Sylvain Chevallier)
• Correct error in set_download_dir (:gh:`225` by Sylvain Chevallier)
• Ensure that channel order is consistent across dataset when channel argument is specified in paradigm (:gh:`229` by Sylvain Chevallier)

API changes

• ch_names argument added to init of moabb.datasets.fake.FakeDataset (:gh:`229` by Sylvain Chevallier)

Version - 0.4.2

Enhancements

• None

Bugs

• Correct error when downloading Weibo dataset (:gh:`212` by Sylvain Chevallier)

API changes

• None

Version - 0.4.1

Enhancements

• None

Bugs

• Correct path error for first time launch (:gh:`204` by Sylvain Chevallier)
• Fix optional dependencies issues for PyPi (:gh:`205` by Sylvain Chevallier)

API changes

• Remove update_path on all datasets, update_path parameter in dataset.data_path() is deprecated (:gh:`207` by Sylvain Chevallier)

Version - 0.4.0

Enhancements

• Implementation for learning curves (:gh:`155` by Jan Sosulski)
• Adding Neiry Demons P300 dataset (:gh:`156` by Vladislav Goncharenko)
• Coloredlogs removal (:gh:`163` by Vladislav Goncharenko)
• Update for README (:gh:`164` by Vladislav Goncharenko and Sylvain Chevallier)
• Test all relevant python versions in Github Actions CI (:gh:`167` by Vladislav Goncharenko)
• Adding motor imagery part of the Lee2019 dataset (:gh:`170` by Ali Abdul Hussain)
• CI: deploy docs from CI pipeline (:gh:`124` by Erik Bjäreholt, Divyesh Narayanan and Sylvain Chevallier)
• Remove dependencies: WFDB and pyunpack (:gh:`180` and :gh:`188` by Sylvain Chevallier)
• Add support for FigShare API (:gh:`188` by Sylvain Chevallier)
• New download backend function relying on Pooch, handling FTP, HTTP and HTTPS (:gh:`188` by Sylvain Chevallier)
• Complete rework of examples and tutorial (:gh:`188` by Sylvain Chevallier)
• Change default storage location for results: instead of moabb source code directory it is now stored in mne_data (:gh:`188` by Sylvain Chevallier)
• Major update of test (:gh:`188` by Sylvain Chevallier)
• Adding troubleshooting and badges in README (:gh:`189` by Jan Sosulski and Sylvain Chevallier)
• Use MNE epoch in evaluation (:gh:`192` by Sylvain Chevallier)
• Allow changing of storage location (:gh:`192` by Divyesh Narayanan and Sylvain Chevallier)
• Deploy docs on moabb.github.io (:gh:`196` by Sylvain Chevallier)
• Broadening subject_list type for :func:`moabb.datasets.BaseDataset` (:gh:`198` by Sylvain Chevallier)
• Adding this what's new (:gh:`200` by Sylvain Chevallier)
• Improving cache usage and save computation time in CI (:gh:`200` by Sylvain Chevallier)
• Rewrite Lee2019 to add P300 and SSVEP datasets (:gh:`217` by Pierre Guetschel)

Bugs

• Restore basic logging (:gh:`177` by Jan Sosulski)
• Correct wrong type of results dataframe columns (:gh:`188` by Sylvain Chevallier)
• Add accept arg to acknowledge licence for :func:`moabb.datasets.Shin2017A` and :func:`moabb.datasets.Shin2017B` (:gh:`201` by Sylvain Chevallier)

API changes

• Drop update_path from moabb.download.data_path and moabb.download.data_dl

Version 0.3.0

Enhancements

• Expose sklearn error_score parameter (:gh:`70` by Jan Sosulski)
• Adds a unit_factor attribute to base_paradigms (:gh:`72` by Jan Sosulski)
• Allow event lists in P300 paradigm (:gh:`83` by Jan Sosulski)
• Return epochs instead of np.ndarray in process_raw (:gh:`86` by Jan Sosulski)
• Set path for hdf5 files (:gh:`92` by Jan Sosulski)
• Update to MNE 0.21 (:gh:`101` by Ramiro Gatti and Sylvain Chevallier)
• Adding a baseline correction (:gh:`115` by Ramiro Gatti)
• Adding SSVEP datasets: MAMEM1, MAMEM2, MAMEM3, Nakanishi2015, Wang2016, (:gh:`118` by Sylvain Chevallier, Quentin Barthelemy, and Divyesh Narayanan)
• Switch to GitHub Actions (:gh:`124` by Erik Bjäreholt)
• Allow recording of additional scores/parameters/metrics in evaluation (:gh:`127` and :gh:`128` by Jan Sosulski)
• Fix Ofner2017 and PhysionetMI annotations (:gh:`135` by Ali Abdul Hussain)
• Adding Graz workshop tutorials (:gh:`130` and :gh:`137` by Sylvain Chevallier and Lucas Custódio)
• Adding pre-commit configuration using isort, black and flake8 (:gh:`140` by Vladislav Goncharenko)
• style: format Python code with black (:gh:`147` by Erik Bjäreholt)
• Switching to Poetry dependency management (:gh:`150` by Vladislav Goncharenko)
• Using Prettier to format md and yml files (:gh:`151` by Vladislav Goncharenko)

Bugs

• Use stim_channels or check annotation when loading files in Paradigm (:gh:`72` by Jan Sosulski)
• Correct MNE issues (:gh:`76` by Sylvain Chevallier)
• Fix capitalization in channel names of cho dataset (:gh:`90` by Jan Sosulski)
• Correct failling CI tests (:gh:`100` by Sylvain Chevallier)
• Fix EPFL dataset flat signal sections and wrong scaling (:gh:`104` and :gh:`96` by Jan Sosulski)
• Fix schirrmeister dataset for Python3.8 (:gh:`105` by Robin Schirrmeister)
• Correct event detection problem and duplicate event error (:gh:`106` by Sylvain Chevallier)
• Fix channel selection in paradigm (:gh:`108` by Sylvain Chevallier)
• Fix upperlimb Ofner2017 error and gdf import problem (:gh:`111` and :gh:`110` by Sylvain Chevallier)
• Fix event_id in events_from_annotations missed (:gh:`112` by Ramiro Gatti)
• Fix h5py>=3.0 compatibility issue (:gh:`138` by Mohammad Mostafa Farzan)
• Python 2 support removal (:gh:`148` by Vladislav Goncharenko)
• Travis-ci config removal (:gh:`149` by Vladislav Goncharenko)

API changes

• None

Version 0.2.1

Enhancements

• Add Tikhonov regularized CSP in moabb.pipelines.csp from the paper (:gh:`60` by Vinay Jayaram)
• update to MNE version 0.19 (:gh:`73` by Jan Sosulski)
• Improve doc building in CI (:gh:`60` by Sylvain Chevallier)

Bugs

• Update GigaDB Cho2017 URL (Pedro L. C. Rodrigues and Vinay Jayaram)
• Fix braininvaders ERP data (Pedro L. C. Rodrigues)
• Replace MNE read_montage with make_standard_montage (Jan Sosulski)
• Correct Flake and PEP8 error (Sylvain Chevallier)

API changes

• None

Version 0.2.0

Enhancements

• MOABB corresponding to the paper version by Vinay Jayaram and Alexandre Barachant
• Creating P300 paradigm and BNCI datasets (:gh:`53` by Pedro L. C. Rodrigues)
• Adding EPFL P300 dataset (:gh:`56` by Pedro L. C. Rodrigues)
• Adding BrainInvaders P300 dataset (:gh:`57` by Pedro L. C. Rodrigues)
• Creating SSVEP paradigm and SSVEPExo dataset (:gh:`59` by Sylvain Chevallier)

Bugs

• None

API changes

• None