Explain model predictions by attributing outputs to input features with SHAP values.
npx skills add https://github.com/tomlupo/ai-playground --skill shap-tomlupo
Please help me install this Agent Skill. Skill: shap Source: https://github.com/tomlupo/ai-playground/tree/main/.claude/skills/shap Command: npx skills add https://github.com/tomlupo/ai-playground --skill shap-tomlupo
This Skill enables transparent interpretation of machine learning models by attributing predictions to individual features using SHAP values, helping users understand why a model made a certain decision.
Instantiate an appropriate explainer (TreeExplainer for tree-based models, DeepExplainer for neural networks), compute SHAP values on your data, and visualize results with the built-in plotting functions.
High-intent search queries and answers about installing and using this skill.
SHAP values explain machine learning model predictions by quantifying the contribution of each input feature to the final output. This Skill computes these values to provide global and local explanations for model behavior.
SHAP supports interpreting tree-based, deep learning, and linear models. The Skill utilizes specific explainers including TreeExplainer, DeepExplainer, KernelExplainer, and LinearExplainer for these model architectures.
Generate feature importance visualizations by computing SHAP values and applying built-in plotting functions. The Skill produces waterfall, beeswarm, bar, scatter, force, and heatmap plots for model debugging and fairness analysis.
SHAP values enable bias analysis by attributing model outputs to specific features, revealing potential fairness issues. You can use these insights to build explainable AI dashboards and compare model behavior.
Computing SHAP values requires the SHAP library and compatible model inputs. You instantiate an appropriate explainer based on your model type, then compute the values on your dataset.
AlterLab-IEUExplain model predictions with SHAP values and attributions across model types.
Yezez9Compute SHAP feature attributions and generate explanation plots for machine learning models.
Mekann2904Train classical machine learning models with scikit-learn, SHAP, and UMAP.
tondevrelAnalyze scikit-learn model feature importance with SHAP, LIME, and partial dependence plots.
