Open Kimonili opened 3 years ago
@Kimonili so if you have a column for the time then I would make time features out of those dates and use them as dynamic features. finally, I would sub-class a model, e.g. DeepAR and remove the time feature transformations from it and see how that works... you can perhaps also use the Fourier time features instead... let me know if that works
Hi,
I am working on some time series data that do not have a stable frequency. I have a datetime column of when X occurs, and this X can occur at any time after the time of the previous occurrence i.e Xt can be 1 minute after Xt-1 but even months after Xt-1.
Is there a way to adapt the frequency argument to be suitable for my case?
Thanks in advance!