Conversation
Thank you for contributing to
|
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
I would rather sort out the tags and what we want them to be before merging this (or at the very least the release). That is a much bigger pain to change later. |
… in forecast. Update tests for ETS Forecaster. Add script to verify ETS Forecaster against statsforecast module using a large number of random parameter inputs. (#2318) Co-authored-by: Alex Banwell <arb1g19@soton.ac.uk>
# Conflicts: # aeon/testing/testing_data.py # aeon/testing/utils/estimator_checks.py
* Add fully functional ETS Forecaster. Modify base to not set default y in forecast. Update tests for ETS Forecaster. Add script to verify ETS Forecaster against statsforecast module using a large number of random parameter inputs. * Add faster numba version of ETS forecaster * Seperate out predict code, and add test to test without creating a class - significantly faster! * Modify _verify_ets.py to allow easy switching between statsforecast versions. This confirms that my algorithms without class overheads is significantly faster than nixtla statsforecast, and with class overheads, it is faster than their current algorithm * Add basic gradient decent optimization algorithm for smoothing parameters --------- Co-authored-by: Alex Banwell <arb1g19@soton.ac.uk>
Reference Issues/PRs
First draft of the new forecasting module. See aeon-toolkit/aeon-admin#14 for some discussion.
This is very early, still lots to do. This includes
and lots more. Note after discussion, we have adopted @alexbanwell1 proposal to call X exog to remove confusion with collection estimators.