linkedin / linkedin/FastTreeSHAP
Update package
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 566
- Forks
- 38
- PR merge metrics
- No merged PRs in 30d
Description
Hi, love your package. Will it receive an update so its in sync with SHAP? Preferably it would be nice if we could distill the computation and perhaps propose a PR for SHAP, since keeping up to date with shap might be infeasible.
For example when running Fasttreeshap I found a bug related to Lightgbm where if the data contained categorical values it wouldn't run: https://github.com/shap/shap/issues/2144
This is fixed in the latest shap but not in FastTreeSHAP.
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 comparing FastTreeSHAP with the latest SHAP behavior for LightGBM data containing categorical values, using SHAP issue #2144 as the reference case. Reproduce the reported failure and determine the scope of keeping FastTreeSHAP in sync; done means the categorical-data case works and the relevant behavior is covered.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100