Skip to content

[ENH] Refactor and improve NaiveForecaster #2823

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
1 of 7 tasks
MatthewMiddlehurst opened this issue May 19, 2025 · 2 comments
Open
1 of 7 tasks

[ENH] Refactor and improve NaiveForecaster #2823

MatthewMiddlehurst opened this issue May 19, 2025 · 2 comments
Assignees
@TonyBagnall @TinaJin0228
Labels
enhancement New feature, improvement request or other non-bug code enhancement forecasting Forecasting package

Comments

@MatthewMiddlehurst
Copy link
Member

MatthewMiddlehurst commented May 19, 2025 •
edited
Loading

Describe the feature or idea you want to propose

We should refactor the DummyForecaster into NaiveForecaster and improve its features. The variants listed in https://otexts.com/fpp2/simple-methods.html would be a good start.

Describe your proposed solution

  • Refactor to NaiveForecaster
  • Add mean
  • Add seasonality
  • Add drift
  • Add testing to tests/test_naive.py
  • Update documentation
  • Add to API page and ensure tidiness

Describe alternatives you've considered, if relevant

No response

Additional context

No response
@MatthewMiddlehurst MatthewMiddlehurst added enhancement New feature, improvement request or other non-bug code enhancement forecasting Forecasting package labels May 19, 2025
@TinaJin0228
Copy link
Contributor

@aeon-actions-bot assign @TinaJin0228

@aeon-toolkit aeon-toolkit deleted a comment from aeon-actions-bot bot May 22, 2025
@TonyBagnall
Copy link
Contributor

TonyBagnall commented May 23, 2025 •
edited
Loading

I dont think we need all these variants, its just for basic benchmarking

  • refactor dummy to naive, default to predict last seen value
  • add option to predict the series mean
  • add option for seasonal naive: predict the last season value

Makradakis finds seasonality in fit, but for now just pass as a parameter. We can add others later

@TonyBagnall TonyBagnall self-assigned this May 23, 2025
@TonyBagnall TonyBagnall mentioned this issue May 23, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@TonyBagnall TonyBagnall

@TinaJin0228 TinaJin0228

Labels
enhancement New feature, improvement request or other non-bug code enhancement forecasting Forecasting package
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@TonyBagnall @MatthewMiddlehurst @TinaJin0228