333

function.py

@@ -36,7 +36,9 @@ def load_data(filepath):
     
     # Add bias term (intercept)  
     X = np.insert(X, 0, 1, axis=1)  
-    
+    scaler = StandardScaler()
+    X = scaler.fit_transform(X)
+
     return X, y_train  
 
 def train_logreg(X, y, numIter=1000, learning_rate=0.01, batch_size=128, lambda_reg=0.01):  
@@ -74,60 +76,3 @@ def predict_logreg(inX, weights):
     prob = 1 / (1 + np.exp(-z))  
     return 1 if prob >= 0.5 else 0  
 
-if __name__ == "__main__":  
-    # Data loading  
-    X_train, y_train = load_data("./data/horse-colic.data")  
-    X_test, y_test = load_data("./data/horse-colic.test")  
-
-    # Standardize the features  
-    scaler = StandardScaler()  
-    X_train = scaler.fit_transform(X_train)  
-    X_test = scaler.transform(X_test)  
-
-    # Split training data into training and validation sets  
-    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)  
-
-    # Logistic regression training and evaluation  
-    best_weights = None  
-    best_auc = 0  
-    
-    for iter in range(1, 1001):  
-        weights = train_logreg(X_train, y_train, numIter=iter, learning_rate=0.01, lambda_reg=0.1)  
-        y_pred = [predict_logreg(x, weights) for x in X_val]  
-        
-        # AUC score for validation predictions  
-        auc = roc_auc_score(y_val, y_pred)  
-        
-        if auc > best_auc:  
-            best_auc = auc  
-            best_weights = weights  
-            
-        if iter > 10 and auc == best_auc:  
-            break  
-
-    # Predictions on the test set  
-    y_pred_test = [predict_logreg(x, best_weights) for x in X_test]  
-    accuracy_test = accuracy_score(y_test, y_pred_test)  
-    print(f"Test Accuracy: {accuracy_test}")  
-
-    # Random Forest model example  
-    rf = RandomForestClassifier(n_estimators=100, random_state=42)  
-    rf.fit(X_train, y_train)  
-    rf_accuracy = rf.score(X_test, y_test)  
-    print(f"Random Forest Test Accuracy: {rf_accuracy}")  
-
-    # Gradient Boosting model example  
-    gb_clf = GradientBoostingClassifier()  
-    gb_clf.fit(X_train, y_train)  
-    yf_pred_gb = gb_clf.predict(X_test)  
-    gb_accuracy = accuracy_score(y_test, yf_pred_gb)  
-    print(f"Gradient Boosting Test Accuracy: {gb_accuracy}")  
-
-    # Cross-validation for Gradient Boosting  
-    scores = cross_val_score(gb_clf, X_train, y_train, cv=5, scoring='accuracy')  
-    print("Cross-validation scores:", scores)  
-    print("Average cross-validation score:", np.mean(scores))  
-
-    # F1 score evaluation  
-    f1 = f1_score(y_test, yf_pred_gb)  
-    print("F1 Score:", f1)