Silas Klug10/17/2023, 11:00 AM
However, I cannot predict without feeding y:
models = [NBEATS(h=h,input_size=7, loss=DistributionLoss(distribution='Poisson', level=), max_steps=100, scaler_type='standard', hist_exog_list=['x1','x2'], exclude_insample_y = True)]
Also, when I set y to zero, it gives a different result to when I don't. It seems like y is still used for prediction, although it should be excluded.
p = model.predict(train[['ds','unique_id','x1','x2']])
Cristian (Nixtla)10/17/2023, 3:36 PM
because this is the target variable you are training to predict. Can you give us more information of your use case?
Silas Klug10/17/2023, 3:56 PM
Cristian (Nixtla)10/17/2023, 4:42 PM
should not affect the outcome
Silas Klug11/02/2023, 9:33 AM
Cristian (Nixtla)11/04/2023, 7:40 PM
José Morales11/06/2023, 4:11 PM