更新 function.py

function.py

@@ -87,18 +87,17 @@ def accuracy(X, y, weights):
 
 if __name__ == "__main__":
     X_train, y_train = load_data("./data/horse-colic.data")
-    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
+    X_test, y_test = load_data("./data/horse-colic.test")
 
     kf = KFold(n_splits=5, shuffle=True, random_state=42)
-    accuracies = [accuracy(X_val_kf, y_val_kf, train_logreg(X_train_kf, y_train_kf, batch_size=32))
+    accuracies = [accuracy(X_test_kf, y_test_kf, train_logreg(X_train_kf, y_train_kf, batch_size=32))
                   for train_index, val_index in kf.split(X_train)
-                  for X_train_kf, X_val_kf in [(X_train[train_index], X_train[val_index])]
-                  for y_train_kf, y_val_kf in [(y_train[train_index], y_train[val_index])]]
+                  for X_train_kf, X_test_kf in [(X_train[train_index], X_train[test_index])]
+                  for y_train_kf, y_test_kf in [(y_train[train_index], y_train[test_index])]]
 
     print(f"K折交叉验证得分: {accuracies}")
     print(f"平均准确率: {np.mean(accuracies):.4f}")
 
-    X_test, y_test = load_data("./data/horse-colic.test")
     final_weights = train_logreg(X_train, y_train, batch_size=32)
     test_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"测试集的准确率: {test_accuracy:.4f}")