Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

My initial idea was that adapters perform the bare minimum preprocessing such that the data can be consumed by the respective frameworks, but I agree that we can also incorporate the best practices here.

If we go for target encoding, we should probably enable/disable it via an optional argument to the GluonTSAdapter. Currently these are not supported since fev.convert_input_data does not forward kwargs to the adapters.

How about we

1. Merge this (or some other simple strategy) as a simple default that unbreaks GluonTS models with covaraites
2. Add a better strategy after the Task refactor with an optional argument to the GluonTSAdapter?