gsamaras

By using `requests` and `hits` as future covariates (as explained in the [Quickstart guide](https://unit8co.github.io/darts/quickstart/00-quickstart.html#Covariates:-using-external-data)), I was able to reduce MAPE to 1.78! Unless you guys have something else to propose,...

@AzulGarza it seems that I cannot get the token myself too. I was hoping to use TimeGPT for a paper and cite, but when I go to [Get Token](https://dashboard.nixtla.io/), either...

As a TimeGPT user, I found this helpful: https://docs.nixtla.io/docs/timegpt_quickstart

TBH I don't see how to move forward with that guide. In the Keras guide I'd load my already trained model and prune it. With the Pytorch Lightning model I...

Hi @AlexandroLuis, as you can see in the SO question, I am using Python and a typical dataframe for Prophet (with columns `ds` and `y`). Not sure how to apply...