Cutoff times are unique per row.
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 123
- Forks
- 22
- PR merge metrics
- No merged PRs in 30d
Description
Currently, problem definition returns a cutoff time for each record in the dataset based on what problem it is. Those times can be improved using 2 methods:
- account only for unique cutoff times.
- group records that can share a cutoff time together.
This improvement will transcend to the calculation of the feature matrix.
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 tracing the problem definition entry point where cutoff times are assigned to dataset records, then follow how those values flow into feature matrix calculation. Determine how unique cutoff times and groups of records that can share a cutoff are represented. Done means the problem definition no longer creates unnecessary per-record cutoff times and the feature matrix calculation uses the improved values.
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
- 25/100