Open arberqoku opened 1 year ago
As discussed, we could also drag it upstream e.g. to mudata
, in future or straightaway.
Another point of discussion can be enabling different strategies when MuData is not a Tensor (e.g. union with missing data or imputation, intersection).
Convert the preprocessed and clean
MuData
into apytorch.Dataset
wrapped into apytorch.DataLoader
to facilitate training during inference, e.g. when introducing mini-batching for SVI. Keep in mind sample-/feature-wise metadata stored in.obs
and.var
fields.