azul

icon indicating an email [email protected]

icon company @Nixtla icon location Mexico icon location CTO & Co-Founder @Nixtla. I’m interested in Machine Learning, and Deep Learning applied to time series forecasting. she/her. 🇲🇽🏳️‍⚧️

Results 63 comments of azul

Multiple seasonal arima

hey @jelc53. In the meantime, you can explore our implementation of the [`MSTL`](https://nixtla.github.io/statsforecast/examples/multipleseasonalities.html) model to handle multiple seasonalities.

[Models] Evaluate `torch.compile` on `nf` models

@quest-bot stash 400

points_to_evaluate parameter

hey @candalfigomoro! Thanks for using neuralforecast. The `Auto` classes receive a parameter called `search_alg` which receives a [ray.tune.search.searcher.Searcher](https://docs.ray.io/en/latest/tune/api/doc/ray.tune.search.Searcher.html#ray.tune.search.Searcher) class. So, you can instantiate the `HyperOptSearch` class with your parameters and...