Sylvain Chevallier

Integrating BrainDecode in MOABB benchmarking pipelines

20

Using the scikit-learn API, BrainDecode could be used as a regular scikit-learn pipeline and benchmarked against others classical BCI pipelines.

(WIP) MDWM for transfer learning

6

This is a new home for PR #155 to correct my messed up rebase.

In order to comply with BrainDecode standard, data should be available as raw files. This PR implements this first step to be able to plug BrainDecode models into MOABB evaluation...

Implement proper deprecation warning

1

For now, the deprecation is just indicated in the docstring of the functions. It should raise a warning and the docstring should be automatically filled.

Office hours

5

Here is a tentative schedule for the next office hours. I kept the 1 hour slot and weekly basis, as it seems to worked previously. The difference is that I...

Error in evaluation's additional columns when data are not numeric

2

When instancing a new evaluation that make use of additional columns capability, there could be an error if the additional columns are set to record string or non-numeric values. This...

Subject 88 of Physionet is sampled at 128Hz instead of 160Hz for the rest of the datasets. This results in error when loading the dataset with any paradigm. It was...

Error in BIDS conversion example

6

There is an error in the BIDS conversion, using the caching process. ``` /home/runner/work/moabb/moabb/examples/plot_bids_conversion.py failed leaving traceback: Traceback (most recent call last): File "/home/runner/work/moabb/moabb/examples/plot_bids_conversion.py", line 50, in _ = dataset.get_data(cache_config=dict(path=temp_dir,...

There is an issue arising in Cattan2019_VR when reading matlab, but I could not track to what triggered it. I thought it was from h5py new version (above 3.8), but...

We could continue the work of #374 to use the doc building only on PR merging into develop, using `workflow_run`, as documented in this [SO page](https://stackoverflow.com/a/69743847)