Aaron Spring

Thanks for your reply @phausamann > if I understand correctly you want to train an independent classifier for each (X, Y) coordinate? That is, each grid cell is trained on...

I also googled sklearn examples at lot but didn’t find anything like what I am looking for. Probably this is not what people do. The workflow of sklearn on a...

I now do a loop over stacked lon and lat: https://gist.github.com/aaronspring/e9f4edba833664ef179113ed25ccea51

I posted this issue and the larger question in the pangeo discourse: https://discourse.pangeo.io/t/vectorized-sklearn/1444

during the https://s2s-ai-challenge.github.io/ a solution appeared using xr.apply_ufunc: https://gist.github.com/aaronspring/36e112e992e36fba935f73404dbbd3cd

I, Aaron Spring, further consent for you, Julius Busecke, to change the xMIP license to Apache-2.0. 👩‍💻🧐👍

In the meantime xarray introduced convert_calendar which might help

I think this is still relevant. Currently we just have my Do it all bootstrap function. Before breaking it down in smaller units I think we need to cover my...

I think we first need to have a plan here how the API should finally look like. My proposal: goal is to get `skill` from `hindcast.verify(...)` as now but also...

all this resampling works nice for `resample_dim='member'` but not for `resample_dim='init'` which is more important