svm_modell.py aktualisiert

svm_modell.py

@@ -19,6 +19,7 @@ def load_and_preprocess_data():
     df = activities.copy()
     df.columns = df.columns.str.strip()
 
+# Kategorisieren der Sportklassen
     def classify_activity(x):
         x = str(x).lower()
         if 'cardio' in x or 'gehen' in x or 'multisport' in x:
@@ -33,6 +34,7 @@ def load_and_preprocess_data():
 
     df = df[df['sport_category'] != -1]
 
+# Numerische Daten welche miteinbezogen werden
     numeric_features = ['Distanz', 'Kalorien', 'Ø Herzfrequenz', 'Maximale Herzfrequenz', 'Aerober TE', 'Training Stress Score®']
 
     available_features = [col for col in numeric_features if col in df.columns]
@@ -141,14 +143,12 @@ def evaluate_model(y_test, y_pred, cv_scores, best_params):         # Evaluiert
 def feature_importance_analysis(model, X_test, feature_names):    # Analysiert die Wichtigkeit der Features (für lineare SVM)
     
     if model.kernel == 'linear':
-        # Feature-Wichtigkeit für lineare SVM
-        importance = np.abs(model.coef_[0])
+        importance = np.abs(model.coef_[0])                       # Feature-Wichtigkeit für lineare SVM
         feature_importance = pd.DataFrame({'feature': feature_names, 'importance': importance}).sort_values('importance', ascending=False)
         
         print("\nFeature-Wichtigkeit (lineare SVM):")
         print(feature_importance)
-        
-        # Visualisierung
+      
         plt.figure(figsize=(10, 6))
         sns.barplot(data=feature_importance.head(10), x='importance', y='feature')
         plt.title('Top 10 Feature-Wichtigkeiten')
@@ -159,6 +159,7 @@ def feature_importance_analysis(model, X_test, feature_names):    # Analysiert d
     else:
         print("\nFeature-Wichtigkeit nur für lineare SVM verfügbar")
 
+
 def main():
     
     print("Starte SVM-Modell für Sportarten-Klassifikation...")