commit 3d2b6f208ed02e029e0c6ecbc19509d2cf6c725f
Author: Adu Alex Göllnitz <adualex.goellnitz@stud.fhgr.ch>
Date:   Wed Nov 19 15:34:13 2025 +0100

    Dateien nach "/" hochladen

diff --git a/Activities_rohdaten.csv b/Activities_rohdaten.csv
new file mode 100644
index 0000000..778d891
--- /dev/null
+++ b/Activities_rohdaten.csv
@@ -0,0 +1,21 @@
+Aktivitätstyp,Datum,Favorit,Titel,Distanz,Kalorien,Zeit,Ø Herzfrequenz,Maximale Herzfrequenz,Aerober TE,Ø Trittfrequenz,Max. Trittfrequenz,Ø Geschwindigkeit,Maximale Geschwindigkeit,Anstieg gesamt,Abstieg gesamt,Ø Schrittlänge,Durchschnittliches vertikales Verhältnis,Ø vertikale Bewegung,Ø Bodenkontaktzeit,Durchschnittliche Balance der Bodenkontaktzeit,Durchschnittliche SAP,Ø Trittfrequenz,Max. Trittfrequenz,Normalized Power® (NP®),Training Stress Score®,Ø Leistung,Max. Leistung,Schläge insgesamt,Ø Swolf,Ø Schlagrate,Schritte,Wiederholungen insgesamt,Sätze insgesamt,Minimale Temperatur,Dekompression,Beste Rundenzeit,Anzahl der Runden,Maximale Temperatur,Ø Atemfrequenz,Minimale Atemfrequenz,Maximale Atemfrequenz,Zeit in Bewegung,Verstrichene Zeit,Minimale Höhe,Maximale Höhe
+Krafttraining,2025-09-23 18:03:52,false,"Krafttrai​ning","0.00","136","00:24:35","102","134","0.5","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","8","4","1","26.0","Nein","00:24:35","1","29.0","--","--","--","00:24:32","00:24:35","--","--"
+Krafttraining,2025-09-22 19:03:03,false,"Krafttrai​ning","0.00","224","00:42:47","103","133","2.0","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","226","113","12","22.0","Nein","00:42:47","1","26.0","--","--","--","00:04:27.2","00:42:47","--","--"
+Rennradfahren,2025-09-21 12:10:15,false,"Walenstadt Rennradfahren","87.59","1,724","02:48:41","158","179","4.5","--","--","31.2","61.2","441","439","--","--","--","--","--","--","86","111","--","0.0","--","--","14247","--","--","--","--","--","25.0","Nein","00:05:29.0","18","35.0","35","22","45","02:48:31","02:57:35","426","596"
+Krafttraining,2025-09-19 19:08:18,false,"Krafttrai​ning","0.00","403","01:12:08","110","155","0.6","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","652","326","26","25.0","Nein","01:12:08","1","28.0","--","--","--","00:13:10","01:12:08","--","--"
+Rennradfahren,2025-09-18 18:30:39,false,"Walenstadt Rennradfahren","30.01","671","00:56:08","152","185","3.2","--","--","32.1","52.2","128","120","--","--","--","--","--","--","86","120","--","0.0","--","--","4790","--","--","--","--","--","17.0","Nein","00:00:01.7","7","24.0","33","23","41","00:56:05","00:56:08","426","497"
+Rennradfahren,2025-09-17 15:30:28,false,"Walenstadt Rennradfahren","62.83","1,379","02:06:52","157","196","4.1","--","--","29.7","79.2","518","514","--","--","--","--","--","--","85","120","--","0.0","--","--","10431","--","--","--","--","--","18.0","Nein","00:05:20.0","13","23.0","34","24","45","02:06:47","02:10:28","426","715"
+Cardio,2025-09-16 13:59:18,false,"Cardio","0.00","471","02:12:50","83","146","1.1","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","1,032","--","--","--","Nein","02:12:50","1","--","--","--","--","00:00:00","02:12:50","--","--"
+Laufen,2025-09-15 18:47:23,false,"Walenstadt Laufen","6.06","508","00:43:15","147","188","2.8","149","186","7:08","3:03","15","12","0.94","10.4","9.8","315","49.5 % Links / 50.5 % Rechts","7:11","--","--","337","0.0","330","695","--","--","--","6,390","--","--","--","Nein","00:00:12.5","7","--","32","23","41","00:42:52","00:43:15","417","426"
+Schwimmbad,2025-09-15 13:33:41,false,"Schwimmbad","2,325","494","00:51:44","135","151","2.4","--","--","2:14","1:46","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","1241","47","24","--","--","--","--","Nein","00:51:44","1","--","--","--","--","00:51:44","00:52:40","--","--"
+Rennradfahren,2025-09-14 12:24:30,false,"Walenstadt Rennradfahren","30.11","877","01:08:03","164","189","4.4","--","--","26.5","76.4","399","400","--","--","--","--","--","--","85","126","--","0.0","--","--","5456","--","--","--","--","--","18.0","Nein","00:00:12.4","7","25.0","35","24","47","01:07:58","01:11:44","426","729"
+Rennradfahren,2025-09-12 17:02:31,false,"Walenstadt Rennradfahren","30.05","781","00:54:38","168","199","4.1","--","--","33.0","50.5","130","127","--","--","--","--","--","--","89","109","--","0.0","--","--","4737","--","--","--","--","--","16.0","Nein","00:00:04.0","7","19.0","37","26","46","00:54:32","00:59:57","427","499"
+Krafttraining,2025-09-11 18:52:04,false,"Krafttrai​ning","0.00","220","00:39:14","105","166","0.8","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","220","110","12","24.0","Nein","00:39:14","1","26.0","--","--","--","00:06:50.4","00:39:14","--","--"
+Rennradfahren,2025-09-10 19:00:07,false,"Walenstadt Rennradfahren","29.85","737","00:55:28","159","192","3.9","--","--","32.3","56.9","128","125","--","--","--","--","--","--","87","115","--","0.0","--","--","4628","--","--","--","--","--","16.0","Nein","00:07:12.5","6","22.0","34","19","43","00:55:25","00:55:28","427","498"
+Radfahren,2025-09-10 17:47:49,false,"Radfahren","0.41","6","00:02:00","--","--","--","--","--","12.4","48.1","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","197","--","--","--","--","--","--","Nein","00:02:00","1","--","--","--","--","00:01:45","00:02:30","--","--"
+Radfahren,2025-09-10 17:12:48,false,"Radfahren","0.21","6","00:02:05","--","--","--","--","--","6.2","41.9","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","102","--","--","--","--","--","--","Nein","00:02:05","1","--","--","--","--","00:00:55","00:09:00","--","--"
+Krafttraining,2025-09-09 19:04:42,false,"Krafttrai​ning","0.00","278","00:53:18","100","139","0.6","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","420","210","17","24.0","Nein","00:53:18","1","27.0","--","--","--","00:07:01.5","00:53:18","--","--"
+Krafttraining,2025-09-07 11:32:58,false,"Krafttrai​ning","0.00","272","00:34:46","119","151","1.3","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","202","101","11","26.0","Nein","00:34:46","1","27.0","--","--","--","00:04:58.5","00:34:46","--","--"
+Radfahren,2025-09-06 11:23:07,false,"Radfahren","4.10","151","00:10:45","--","--","--","--","--","22.9","40.4","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","636","--","--","--","--","--","--","Nein","00:10:45","1","--","--","--","--","00:10:35","00:11:00","--","--"
+Rennradfahren,2025-09-06 10:58:49,false,"Walenstadt Rennradfahren","126.36","2,401","04:28:11","145","175","3.9","--","--","28.3","54.7","597","573","--","--","--","--","--","--","80","163","--","0.0","--","--","19676","--","--","--","--","--","15.0","Nein","00:03:58.3","26","28.0","33","20","47","04:27:27","05:13:45","409","466"
+Krafttraining,2025-09-05 13:32:08,false,"Krafttrai​nin","0.00","203","00:48:40","91","147","0.2","--","--","--","--","--","--","--","--","--","--","--","--","--","--","--","0.0","--","--","--","--","--","880","440","31","26.0","Nein","00:48:40","1","30.0","--","--","--","00:17:29","00:49:11","--","--"
diff --git a/svm_modell.py b/svm_modell.py
new file mode 100644
index 0000000..6815d9d
--- /dev/null
+++ b/svm_modell.py
@@ -0,0 +1,204 @@
+# Machine Learning Modell 1 / Leistungsnachweis II Data Science / 1. Semester
+# Support Vector Machine zu binären Klassifikation
+
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.svm import SVC
+from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
+from sklearn.impute import SimpleImputer
+import matplotlib.pyplot as plt
+import seaborn as sns
+from datetime import datetime
+import warnings
+warnings.filterwarnings('ignore')
+
+def load_and_preprocess_data():
+   
+    # Lädt und bereitet die Daten aus verschiedenen CSV-Dateien vor
+   
+    # CSV-Dateien laden
+    activities = pd.read_csv("Activities_rohdaten.csv", sep=None, engine="python")
+    
+    # Daten bereinigen und konsolidieren
+    df = activities.copy()
+    
+    # Spaltennamen bereinigen
+    df.columns = df.columns.str.strip()
+    
+    # Sportarten für binäre Klassifikation definieren
+
+    # Wir klassifizieren zwischen 'Ausdauersport' und 'Kraftsport'
+    endurance_sports = ['Laufen', 'Rennradfahren', 'Schwimmen', 'Radfahren']
+    strength_sports = ['Krafttraining']
+    
+    # Binäre Zielvariable erstellen
+    df['sport_category'] = df['Aktivitätstyp'].apply(lambda x: 1 
+                                                     if x in endurance_sports 
+                                                     else (0 if x in strength_sports else -1))
+    
+    # Nur gültige Kategorien behalten
+    df = df[df['sport_category'] != -1]
+    
+    # Features auswählen, die für die Klassifikation relevant sind
+    numeric_features = ['Distanz', 'Kalorien', 'Ø Herzfrequenz', 'Maximale Herzfrequenz', 'Aerober TE', 'Training Stress Score®']
+    
+    # Nur verfügbare numerische Features auswählen
+    available_features = [col for col in numeric_features if col in df.columns]
+    
+    return df, available_features
+
+def feature_engineering(df, features):  # Führt Feature Engineering durch
+    
+    # Kopie erstellen
+    df_processed = df.copy()
+    
+    # Numerische Features bereinigen
+    for feature in features:
+        if df_processed[feature].dtype == 'object':
+            df_processed[feature] = df_processed[feature].astype(str).str.replace(',', '')
+            
+        # In numerische Werte umwandeln
+        df_processed[feature] = pd.to_numeric(df_processed[feature], errors='coerce')
+    
+    # Zeitbasierte Features aus Datum extrahieren
+    if 'Datum' in df_processed.columns:
+        df_processed['Datum'] = pd.to_datetime(df_processed['Datum'], errors='coerce')
+        df_processed['hour'] = df_processed['Datum'].dt.hour
+        df_processed['day_of_week'] = df_processed['Datum'].dt.dayofweek
+        df_processed['month'] = df_processed['Datum'].dt.month
+        
+        # Zeitbasierte Features hinzufügen
+        time_features = ['hour', 'day_of_week', 'month']
+        features.extend(time_features)
+    
+    # Fehlende Werte behandeln
+    X = df_processed[features]
+    y = df_processed['sport_category']
+    
+    # SimpleImputer für fehlende Werte
+    imputer = SimpleImputer(strategy='median')
+    X_imputed = imputer.fit_transform(X)
+    
+    return X_imputed, y, features, imputer
+
+def train_svm_model(X, y):      # Trainiert das SVM-Modell mit Hyperparameter-Tuning
+   
+    # Daten in Trainings- und Testsets aufteilen
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42, stratify=y)
+    
+    # Features skalieren
+    scaler = StandardScaler()
+    X_train_scaled = scaler.fit_transform(X_train)
+    X_test_scaled = scaler.transform(X_test)
+    
+    # SVM-Modell mit Hyperparameter-Tuning
+    param_grid = {
+        'C': [0.1, 1, 10, 100],
+        'gamma': ['scale', 'auto', 0.001, 0.01, 0.1, 1],
+        'kernel': ['rbf', 'linear']
+    }
+    
+    svm = SVC(random_state=42)
+    grid_search = GridSearchCV(svm, param_grid, cv=5, scoring='accuracy', n_jobs=-1)
+    grid_search.fit(X_train_scaled, y_train)
+    
+    # Bestes Modell
+    best_svm = grid_search.best_estimator_
+    
+    # Vorhersagen
+    y_pred = best_svm.predict(X_test_scaled)
+    
+    # Kreuzvalidierung
+    cv_scores = cross_val_score(best_svm, X_train_scaled, y_train, cv=5)
+    
+    return best_svm, X_test_scaled, y_test, y_pred, grid_search.best_params_, cv_scores, scaler
+
+def evaluate_model(y_test, y_pred, cv_scores, best_params):         # Evaluiert das Modell und gibt Ergebnisse aus
+    
+    print("=== SVM-Modell für Sportarten-Klassifikation ===")
+    print(f"Anzahl der Datensätze: {len(y_test) + len(y_pred)}")
+    print(f"\nBeste Hyperparameter: {best_params}")
+    
+    print(f"\nKreuzvalidierung (CV-Scores): {cv_scores}")
+    print(f"Mittlere CV-Genauigkeit: {cv_scores.mean():.4f} (+/- {cv_scores.std() * 2:.4f})")
+    
+    print(f"\nTest-Genauigkeit: {accuracy_score(y_test, y_pred):.4f}")
+    
+    print("\nKlassifikationsbericht:")
+    print(classification_report(y_test, y_pred, target_names=['Kraftsport', 'Ausdauersport']))
+    
+    print("\nKonfusionsmatrix:")
+    cm = confusion_matrix(y_test, y_pred)
+    print(cm)
+    
+    # Visualisierung der Konfusionsmatrix
+    plt.figure(figsize=(8, 6))
+    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', 
+                xticklabels=['Kraftsport', 'Ausdauersport'],
+                yticklabels=['Kraftsport', 'Ausdauersport'])
+    plt.title('Konfusionsmatrix - SVM Sportarten-Klassifikation')
+    plt.ylabel('Wahre Klasse')
+    plt.xlabel('Vorhergesagte Klasse')
+    plt.tight_layout()
+    plt.savefig('confusion_matrix.png', dpi=300, bbox_inches='tight')
+    plt.show()
+    
+    return accuracy_score(y_test, y_pred)
+
+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])
+        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')
+        plt.xlabel('Wichtigkeit')
+        plt.tight_layout()
+        plt.savefig('feature_importance.png', dpi=300, bbox_inches='tight')
+        plt.show()
+    else:
+        print("\nFeature-Wichtigkeit nur für lineare SVM verfügbar")
+
+def main():
+    
+    print("Starte SVM-Modell für Sportarten-Klassifikation...")
+    
+    try:
+        # 1. Daten laden und vorverarbeiten
+        df, features = load_and_preprocess_data()
+        print(f"Daten geladen: {df.shape[0]} Datensätze, {len(features)} Features")
+        print(f"Verteilung der Sportarten: {df['sport_category'].value_counts().to_dict()}")
+        
+        # 2. Feature Engineering
+        X, y, feature_names, imputer = feature_engineering(df, features)
+        print(f"Feature Engineering abgeschlossen: {X.shape[1]} Features")
+        
+        # 3. SVM-Modell trainieren
+        model, X_test, y_test, y_pred, best_params, cv_scores, scaler = train_svm_model(X, y)
+        
+        # 4. Modell evaluieren
+        accuracy = evaluate_model(y_test, y_pred, cv_scores, best_params)
+        
+        # 5. Feature-Analyse
+        feature_importance_analysis(model, X_test, feature_names)
+        
+        print(f"\nModell erfolgreich trainiert mit Genauigkeit: {accuracy:.4f}")
+        print("\nGespicherte Dateien: confusion_matrix.png, feature_importance.png")
+        
+        return model, scaler, imputer, feature_names
+        
+    except Exception as e:
+        print(f"Fehler bei der Ausführung: {str(e)}")
+        return None, None, None, None
+
+if __name__ == "__main__":
+    model, scaler, imputer, feature_names = main()
\ No newline at end of file