hangout
https://hangouts.google.com/call/_J_VC2HCflr5Lb2I0MkUAEEI?no_rd is link I have in browser
you joining?
have time?
@sliwy
are you here?
can you have a look @robintibor @sliwy
https://gist.github.com/gemeinl/1220413cb4418a94c48b71c5014bb390
https://gist.github.com/gemeinl/1220413cb4418a94c48b71c5014bb390
i wonder if you could reverse the order in that tutorial, like first show the last part saying this is how you get a braindecode-dataset from this mne, and then saying ok now let's look into each step in detail
also, if we already had mne epochs, would there also be a clear way atm? is this not intended atm? how is it?
but ya also @sliwy maybe you can say how you find it in terms of understand dataset structure? it seems quite helpful to me!
I also added my current naming preference here: braindecode/braindecode#59
@gemeinl I really like the dataset tutorial, great thing! I agree with @robintibor to start with the last cell - just quickly show how to read mne data. It looks simple and straightforward, you do not have to spend time to figure out where to start and what you need. It may be the first part - basic and usual application. The second part may describe more advanced usage e.g. with splitting (looks really interesting, I didn't know we have this functionality) and any other cool stuff is inside braindecode.
It really helps a lot in understanding the dataset structures!
also, if we already had mne epochs, would there also be a clear way atm? is this not intended atm? how is it?
I will see to this next. It could become a bit more tricky, though. The WindowsDataset gives x, y, ind, where y and ind are read from the metadata pandas.DataFrame from the mne.Epochs objects. If it is not there, you have to manually add it. I have never tried it, will see how it can be done.
like dataset = create_from_X_y(X,y)
with dataset being windows dataset
such a function does not exsist yet, but i think this would be the way to go: https://gist.github.com/gemeinl/1220413cb4418a94c48b71c5014bb390#file-braindecode_xy_data_example-ipynb
Both examples i now sent would benefit from removing pandas import, i believe. We could do this by changing
description argument of BaseDataset from pandas.Series to dict and cast it internally. What do you think abou this?
x y looks great, would be super to make it into single function
did anyone of you touch something to circleci or github config https://app.circleci.com/pipelines/github/braindecode/braindecode/450/workflows/545362fa-2038-4537-b85b-a1548bbec69a/jobs/535 ? @robintibor ?
deploy of docs failed multiple times with some error about read-only SSH key, so I added a User key under https://app.circleci.com/settings/project/github/braindecode/braindecode/ssh?return-to=https%3A%2F%2Fapp.circleci.com%2Fpipelines%2Fgithub%2Fbraindecode%2Fbraindecode @agramfort
here circleci code is indeed read-only, I don't know if that is a problem: https://github.com/braindecode/braindecode/settings/keys
if you asked about touching something before, them I am not aware of it. the screenshot above shows something visible under https://github.com/braindecode/braindecode/settings/keys , which I do not know why it happened
one needs to have read write keys in sync between circle ci and github
I also reran the one you linked above and it succeeded now https://app.circleci.com/pipelines/github/braindecode/braindecode/450/workflows/24366b0c-fee0-4663-bfc1-90023ee4326c/jobs/544
