Mark Aron Szulyovszky03/23/2023, 3:59 PM
when calling predict_rolled to get in_sample predictions?
? it looks like I get widely different return values than the number I pass in. I’d expect insample_size=100 to return 100 in_sample predictions, which looks like is the case, but 110 returns 1100, which seems to be really weird.
Cristian (Nixtla)03/24/2023, 7:19 PM
its a wrapper of the
method, where models are not trained. In principle, the model's parameters should not change after using this function.
function is to forecast multiple windows. You can use this function to forecast any fixed number of
or subset of your dataset
in this case is equivalent to the
method. Anything before the
is discarded (except for the last
window used as inputs for the first forecast).
to 900, you will have all the forecasts starting at the 100th timestamp. Also consider adjusting the
, the default is 1, so it will produce forecasts of size
at every timestamp.
Mark Aron Szulyovszky03/25/2023, 1:32 PM
Cristian (Nixtla)03/27/2023, 3:05 PM