Piotr Pomorski03/05/2023, 6:32 PM
Where it just transforms the price series via
mlf = MLForecast(models=models, differences=, date_features=['month'], lags=None, num_threads=mp.cpu_count()-1, lag_transforms=None, freq='W-FRI')
, I always end up with
Well, I guess it's obvious that the moment you apply first-difference there will be nans, why MLForecast does not delete the first row? And to precede your question, no, my original dataset has no nans.
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').
Max (Nixtla)03/05/2023, 7:39 PM
Piotr Pomorski03/05/2023, 7:55 PM