goellnaduale/Leistungsnachweis-2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

svm_modell.py aktualisiert

Browse Source
This commit is contained in:
Adu Alex Göllnitz 2025-11-24 07:10:59 +01:00
parent d94ee5ea70
commit e850fc3ba6
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
svm_modell.py
View File

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