[ENH] `sample_weight` for metrics
Open
Nobody has claimed this yet.
feature request
module:metrics&benchmarking
- Dominant language
- Python
- Stars
- 335
- Forks
- 207
- Avg merge
- 1d 20h
- Merged PRs (30d)
- 16
Description
A sample_weight parameters should be added to metrics.
Where it is not clear what to do, the following default can be used:
- compute jackknife pseudo-samples
- weight the pseudo-samples
- average the weighted pseudo-samples
For consideration, a tag is perhaps needed here.
Related discussion: https://github.com/sktime/sktime/issues/6412
FYI @eenticott-shell, due to authorship of some of the metrics.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the metrics implementation and the related discussion in sktime issue #6412, since no files or tests are identified here. Determine the affected metrics and how sample weights should be represented; done means supported metrics accept sample_weight and follow the stated pseudo-sample weighting behavior, with any needed tagging addressed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100