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
Add expanding window splitter #627
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.
Thanks @koralturkk - looks all good to me, very clean code!
Could we add a simple unit test to make sure it's behaving as expected?
@mloning Yes, I was thinking of doing that, I still need to check the existing unit tests which are being used on other splitters. I will be updating the PR when the unit tests are also implemented. |
Great - thanks @koralturkk! |
Hi @mloning, I have added a notebook example and unit tests, I would appreciate if you take a look and let me know if you want to add more. |
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.
Thanks @koralturkk - looks all good to me! Very clean code, great work!
I started playing around with the notebook and made some minor changes, mostly formatting and style.
Will leave this PR open a bit longer and merge later today or in the next few days!
Thanks again @koralturkk - now merging! |
* expanding window validation added * credits edited * test_window overlap fixed for training and test window * codeowners edited * Notebook examples added for expanding window * unit tests for expanding window added * Minor changes to notebook Co-authored-by: Martin Walter <mf-walter@web.de> Co-authored-by: mloning <markus.loning.17@ucl.ac.uk>
Reference Issues/PRs
Feature #552
What does this implement/fix? Explain your changes.
It adds a functionality crossvalidate models with an expanding window.
Does your contribution introduce a new dependency? If yes, which one?
No, it does not.
What should a reviewer concentrate their feedback on?
Still in debugging
Any other comments?
PR checklist
For all contributions
For new estimators