Nixtla / neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.
https://nixtlaverse.nixtla.io/neuralforecast
Apache License 2.0
2.69k stars 312 forks source link

fix num_tasks in spark integration #1028

Closed jmoralez closed 3 weeks ago

jmoralez commented 3 weeks ago

Moves the logic of the distributed processing to separate methods to make it easier to follow the original methods (fit and predict).

During this refactor I found and fixed the error here: https://github.com/Nixtla/neuralforecast/blob/0e43ae0e7bc42294be95e1f4ebb497d7de1817d7/neuralforecast/common/_base_model.py#L333

After this I reran and updated the sample notebook, which was missing from the sidebar, so this adds it as well.

review-notebook-app[bot] commented 3 weeks ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB