unconditional-time-series-diffusion
unconditional-time-series-diffusion copied to clipboard
Adding dynamic real features for TSDiffCond
Thanks for sharing the code base!
I have a question regarding the class of TSDiffCond. It takes num_feat_dynamic_real as an input but in the _extract_features no dynamic real features are added to the used features. I am working with energy data (wind and solar) and would like to use additional past and future covariates (weather forecasts) to improve my predictions on the respective energy target time series.
I was wondering: How you would suggest incorporating those into the code?