intial commit (forked from private repo)

extracted_cells/cell17.py

@@ -0,0 +1,65 @@
+# Erkläre die Vorhersage mit LIME
+
+def analyze_lime_feature_importance(instance, rf_model, lime_explainer, num_features=5):
+    """
+    Analysiert die Feature-Wichtigkeiten der LIME-Erklärung.
+    """
+    # LIME-Erklärung generieren
+    exp = lime_explainer.explain_instance(
+        instance,
+        rf_model.predict_proba,
+        num_features=num_features
+    )
+    
+    # Random Forest Vorhersage (nur zur Information)
+    feature_names = rf_model.feature_names_in_
+    instance_df = pd.DataFrame([instance], columns=feature_names)
+    rf_prediction = rf_model.predict_proba(instance_df)[0, 1]
+    
+    # Feature-Wichtigkeiten aus LIME extrahieren
+    feature_importance = exp.as_list()
+    
+    # Visualisierung der Feature-Wichtigkeiten
+    plt.figure(figsize=(10, 6))
+    
+    # Features und ihre Wichtigkeiten trennen
+    features, importances = zip(*feature_importance)
+    
+    # Balkendiagramm erstellen
+    colors = ['red' if imp < 0 else 'green' for imp in importances]
+    y_pos = np.arange(len(features))
+    
+    plt.barh(y_pos, importances, color=colors)
+    plt.yticks(y_pos, features)
+    
+    plt.xlabel('Feature-Einfluss')
+    plt.title('LIME Feature-Wichtigkeiten')
+    
+    # Vertikale Linie bei 0 für bessere Lesbarkeit
+    plt.axvline(x=0, color='black', linestyle='-', alpha=0.3)
+    
+    plt.grid(alpha=0.3)
+    plt.tight_layout()
+    plt.savefig('output/lime_feature_importance.png', dpi=300)
+    plt.show()
+    
+    # Ausgabe der Ergebnisse
+    print("\nLIME Feature-Wichtigkeiten Analyse:")
+    print("-" * 50)
+    print(f"Random Forest Vorhersage für diese Instanz: {rf_prediction:.4f}")
+    print("\nFeature-Einflüsse:")
+    for feature, importance in feature_importance:
+        print(f"{feature}: {importance:+.4f}")
+    
+    return {
+        'rf_prediction': rf_prediction,
+        'feature_importance': dict(feature_importance)
+    }
+
+# Analysiere wie gut LIME die RF-Vorhersage erklärt
+importance_analysis = analyze_lime_feature_importance(
+    instance=instance,
+    rf_model=best_rf_model,
+    lime_explainer=lime_explainer,
+    num_features=20
+)