the list of models names passed to ts_fit_forecast() is very strict when it comes to the named elements passed to the "models" argument. it is case sensitive (if you pass in a list with an element named "ARIMA" instead of "arima" it will assume ARIMA is NULL) and doesnt allow you to pass in different "flavors" of models (e.g., a list with "arima_unrestricted" and "arima_restricted" side-by-side).
is there a way we can make the handling of model names more flexible?
the list of models names passed to
ts_fit_forecast()
is very strict when it comes to the named elements passed to the "models" argument. it is case sensitive (if you pass in a list with an element named "ARIMA" instead of "arima" it will assume ARIMA isNULL
) and doesnt allow you to pass in different "flavors" of models (e.g., a list with "arima_unrestricted" and "arima_restricted" side-by-side).is there a way we can make the handling of model names more flexible?