Is there a function like

predict_insample

that you can pass a df to instead of using the last training df? I'd like to evaluate a test set (completely separate unique_ids) by running sliding window forecasts.

sorry @Dan Howarth I don't think I understand what you want to do. Could you elaborate? In the meantime, maybe the

forward

method can be useful. You train a dataset and then you generate forecasts for a different one. Here's the forward method for the AutoETS, for example.

@Mariana Menchero I want to do exactly what

predict_insample

does, but on an arbitrary df instead of the training df.

ok, then I think the answer to your question is no. As stated in the tutorial that you shared, _`predict_insample` will always take the last dataset used for training in either the

fit

or

cross_validation

methods._