-
Notifications
You must be signed in to change notification settings - Fork 7
Add sktime adapter for OnlineLinearModel estimator #152
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.
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
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Copilot wasn't able to review any files in this pull request.
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Co-authored-by: simon-hirsch <64348015+simon-hirsch@users.noreply.github.com>
Co-authored-by: simon-hirsch <64348015+simon-hirsch@users.noreply.github.com>
|
@copilot tests are not passing. I see: Please fix. |
Co-authored-by: BerriJ <37799358+BerriJ@users.noreply.github.com>
... Fixed the import error by making the sktime adapter import conditional in |
|
@copilot please instead install sktime in the CICD pipeline. |
Co-authored-by: simon-hirsch <64348015+simon-hirsch@users.noreply.github.com>
This PR implements a comprehensive sktime adapter for the
OnlineLinearModelestimator, enabling its use within the sktime time series analysis ecosystem while preserving its online learning capabilities.Overview
The
OnlineLinearModelSktimeadapter wraps the existing sklearn-compliantOnlineLinearModelto provide full compatibility with sktime's regression interface. This allows users to leverage ondil's online linear regression capabilities in sktime workflows.Key Features
BaseRegressorand implements all required methods (_fit,_predict)update()method for incremental learningUsage Example
Implementation Details
(n_instances, n_timepoints, n_features)to(n_instances, n_timepoints * n_features)Files Added/Modified
src/ondil/estimators/sktime_adapter.py- Main adapter implementationsrc/ondil/estimators/__init__.py- Export the new adaptersrc/ondil/__init__.py- Conditional import when sktime is availabletests/test_sktime_adapter.py- Comprehensive test suiteSKTIME_ADAPTER.md- Complete documentation and usage guideexample_sktime_adapter.py- Practical usage examplesTesting
All tests pass validation for:
The adapter is designed to work seamlessly with existing OnlineLinearModel functionality while providing a clean interface for sktime users.
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.