Ada Puślecka08/24/2023, 7:17 PM
values)? In the documentation it says that I can do this using
and supplying to it "DataFrame with [
]", however whenever I try to predict with
columns it gives all NaNs (and when I add
column it works fine, but obviously at prediction time you don't have the
Cristian (Nixtla)08/24/2023, 7:18 PM
its only for the future exogenous variables. To pass new data, use the
argument of the
method. The forecasts will correspond to the future after the last timestamps of the new data.
should contain historic values of all the variables used during training, including the target variable
and historic exogenous covariates.
, it must be present in the new data. To train a model that only depends on exogenous covariates you need to set
when instantiating the model.
Ada Puślecka08/25/2023, 7:22 AM
Cristian (Nixtla)08/25/2023, 11:57 AM
). Since the
is not used by the model, you can pass any new data you want, including new time series.