search

zalandoresearch / pytorch-ts

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend
MIT License
1.21k stars 190 forks source link

Can I turn off the frequency argument in the DeepAREstimator? #52

Open Kimonili opened 3 years ago

Kimonili commented 3 years ago

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!

kashif commented 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