Compute SHAP values and generate global and local model explanations.
npx skills add https://github.com/schneidermu/agent-dotfiles --skill shap-schneidermu
Please help me install this Agent Skill. Skill: shap Source: https://github.com/schneidermu/agent-dotfiles/tree/main/codex-skills/shap Command: npx skills add https://github.com/schneidermu/agent-dotfiles --skill shap-schneidermu
SHAP-based explanations help you understand and trust machine learning model predictions by attributing outputs to individual features using Shapley values.
Provide SHAP explanations for a trained model on your dataset and visualize insights.
High-intent search queries and answers about installing and using this skill.
Explain machine learning model predictions by computing SHAP values to attribute outputs to individual features. This generates global and local explanations to help you understand and trust model behavior.
Yes, you can generate SHAP explanations for deep learning and linear models. The approach supports multiple explainer classes including TreeExplainer, DeepExplainer, KernelExplainer, and LinearExplainer.
Visualize feature attributions to diagnose model behavior and detect bias using waterfall, beeswarm, bar, scatter, and force plots. These visualizations help compare models and assess fairness across datasets.
Compute SHAP values by applying the appropriate explainer class to your trained model. You must provide input data formatted as arrays or dataframes within a Python environment that has the SHAP library installed.
Use model interpretability techniques during debugging, fairness analysis, feature engineering, and model comparison workflows. SHAP explanations provide end-to-end guidance to diagnose model behavior and assess fairness across datasets.
ManfronEnricoCompute SHAP values and visualizations for tree, deep, and linear models.
dralkhCompute SHAP values and generate feature attribution plots for machine learning models.
robotlearning123Compute SHAP values and generate SHAP plots for model predictions.
tondevrelAnalyze scikit-learn model feature importance with SHAP, LIME, and partial dependence plots.
