search

business-science / modeltime.ensemble

Time Series Ensemble Forecasting
https://business-science.github.io/modeltime.ensemble/
Other
73 stars 16 forks source link

Error in Tuning Ensembles #31

Closed bdav56 closed 3 months ago

bdav56 commented 4 months ago

I am working on the ensembles portion of the Business Science Forecasting Course. Each time I attempt to tune parameters within the ensemble_model_spec(), I receive the error below. It works when I choose parameters like penalty and mixture manually, but not when I use tune(). I am using the development version of the model.ensemble package:

! ... must be empty. :heavy_multiplication_x: Problematic argument: • ..1 = metric :information_source: Did you forget to name an argument?

trentonpulsipher commented 4 months ago

I'm also seeing the same issue. Error in tune::show_best(., metric, n = 1) : ...must be empty. ✖ Problematic argument: • ..1 = metric ℹ Did you forget to name an argument?

mdancho84 commented 4 months ago

I'll do my best to fix this week

trentonpulsipher commented 3 months ago

What's the update or ETA on this issue (and the related issue)?

mdancho84 commented 3 months ago

Should be fixed now.

Arnold-Kakas commented 1 month ago

Hi @mdancho84, I think this is still not working, I get the same error: Error in tune::show_best(): ! ... must be empty. ✖ Problematic argument: • ..1 = metric ℹ Did you forget to name an argument?