EpistasisLab / EpistasisLab/tpot
Have TPOT explain why it selected a particular pipeline
Open
enhancement
need contributor
- Dominant language
- Jupyter Notebook
- Stars
- 10.1k
- Forks
- 1.6k
- PR merge metrics
- No merged PRs in 30d
Description
Brief description until I get more time: Currently, TPOT recommends pipelines to the user based on the predictive performance of the pipeline. It would be helpful to some users if it could explain *why* that pipeline was selected, e.g., use the information from its evaluated pipelines dictionary to suggest that using a particular preprocessing method/ML algorithm/parameter setting improves performance over others.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.