shap
k-dense-ai1.8k installs
Understand which features drive your model's predictions.
What it does
Explain a fitted model's predictions with validated feature attributions and local or global visualizations.
When to use it
Use when selecting explainers or maskers, validating feature attributions, handling multiple outputs, or creating SHAP visualizations.
How to use it
Give it a model-analysis task in the project; it computes validated explanations, produces visualizations, and reports their limitations.
What you provide
- An existing project
Uses
Good to know
- advertises something the task does not need
Latest review
What you need · 3
Requires Python 3.12 or newer for the documented SHAP 0.52.0 workflow.
Requires uv to create the isolated environment and install the pinned SHAP release.
Access · 2
This skill
arXiv
Read
Fetches the current paper citation
shap[plots]
Execute
Installs SHAP with plotting dependencies