Konstantin Ramthun

[Feature Request] Domain Randomization

2

### 🚀 Feature Literature suggests different techniques for domain randomization. This includes: - Uniform Domain Randomization - [Automatic Domain Randomization](https://arxiv.org/pdf/1910.07113.pdf) - [Active Domain Randomization](https://arxiv.org/pdf/1904.04762.pdf) - [Self-Paced Domain Randomization](https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Carrasco_Damken--SelfPacedDomainRandomization.pdf) These are...

feat: Added frequency aware one-hot and relative cyclic encoding.

3

Checklist before merging this PR: - [x] Mentioned all issues that this PR fixes or addresses. - [x] Summarized the updates of this PR under **Summary**. - [ ] Added...

Add One-Hot Encoder to Time Axis Encoders

6

**Is your feature request related to a current problem?** Some models may perform better with some datetime attributes being one hot encoded. Currently, we have to use the [datetime_attribute_timeseries()](https://unit8co.github.io/darts/generated_api/darts.utils.timeseries_generation.html#darts.utils.timeseries_generation.datetime_attribute_timeseries) function...

[BUG] IndexError when transforming static covariates with OneHotEncoder and parameter drop set

1

**Describe the bug** When using the `StaticCovariatesTransformer` with sklearn's [ `OneHotEncoder`](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.OneHotEncoder.html) as the `transformer_cat` and having the drop parameter specified as `"if_binary"` or `"first"`, the `StaticCovariatesTransformer` is not aware of...