madtoinou

Hi @sebros-sandvik, After inspecting the implementation of Croston, it seems like the covariates (`X` in their API) is only used when using conformal prediction (not yet supported by Darts). We...

To centralize conversation in a single issue, closing this one, duplicate of #2359. As mentioned by Dennis, we would prefer to focus our capacity on other features but PRs from...

After answering to a comment on gitter, noticed that some features implemented recently could be reused for this feature: - workaround to add the missing attribute for the NHITS model...

`TFTModel` uses the `MixedCovariatesSequentialDataset` by default, you can look at the `PLMixedCovariatesModule._get_batch_prediction()` method to see how the covariates are handled before passing them to the model (there is an example...

Hi @JoonasHL, Made a bit of progress but other features got priority over this one. Still on the roadmap, I need to find some time for it (or happy to...

Thanks @esnvidia for sharing your experience. It seems like a lot of the error come from sklearn itself, but it's great to see that many models from cuML could be...

Hi @BrainCai, Maintaining the documentation in several languages sadly represent too much work for us. Moreover, since we don't speak Chinese, it will make it very difficult for us to...

I agree that not changing the global config would be better, especially if users use Darts in the context of large projects in combination with other plotting libraries.

Hi @Laenita, Would you mind sharing the value of the parameters? So that we can have an idea of the number of parameters/size of the model. Is the GPU acceleration...

Hi @igorrivin & @Laenita, As mentioned in another tread, the PR ##2295 is adding support for those arguments. Maybe try installing this branch/copy the changes and see if it solves...