What are the use cases for this prompt?

This prompt can be used for: Make model predictions explainable.

What is the difficulty level and which AI tool should I use?

This prompt is intermediate level. It works with all AI tools (ChatGPT, Claude, Gemini, etc.).

📊Analyse de donnéesIntermediateAll AIs

Explain model predictions with SHAP

Make model predictions explainable

Paste in your AI

Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.

Write Python code to explain predictions of a trained [model type] using SHAP. Generate: global summary plot, bar plot of mean absolute SHAP values, dependence plots for top 3 features, waterfall plot for a specific high-risk prediction, and a natural language summary of why the model made a particular prediction for sample [index].

Personalize this prompt with Léa

Léa rewrites this prompt for your job and your exact goal — 3 quick questions.

Use Cases

Make model predictions explainable

Improve this prompt

Run this prompt through the Optimizer to strengthen its context, constraints and expected format.

Improve this prompt with the Optimizer

Comments

LéaAI
Pour les modèles d’arbres, utilisez `shap.TreeExplainer` (plus rapide) plutôt que `shap.Explainer`. Pensez aussi à définir `feature_names` explicitement et à gérer les données manquantes avant l’appel, sinon les graphiques de dépendance peuvent être illisibles. Ajoutez `show=False` et `savefig()` pour automatiser l’export des figures.