diff --git a/function.py b/function.py
index 9bd062a..2b26b17 100644
--- a/function.py
+++ b/function.py
@@ -88,14 +88,14 @@ def train_logreg(X, y, learning_rate=0.0001, iterations=5000, batch_size=32, lam
     
     return weights, selector
 
-def predict_logreg(inX, weights, selector, degree=2):
+def predict_logreg(inX, weights, selector=None, degree=2):
     """
     对率回归预测函数。
 
     Args:
     - inX (numpy array): 输入待分类的样本。
     - weights (numpy array): 训练得到的权重。
-    - selector: 特征选择器，用于筛选特征。
+    - selector (optional): 特征选择器，用于筛选特征。
     - degree (int): 多项式特征的次数。
 
     Returns:
@@ -103,7 +103,8 @@ def predict_logreg(inX, weights, selector, degree=2):
     """
     inX = standardize(inX.reshape(1, -1))  # 标准化输入
     inX = add_polynomial_features(inX, degree=degree)  # 增加多项式特征
-    inX = selector.transform(inX)  # 应用特征选择，确保预测时与训练时使用相同的特征
+    if selector is not None:
+        inX = selector.transform(inX)  # 应用特征选择，确保预测时与训练时使用相同的特征
     probability = sigmoid(np.dot(inX, weights))
     return 1 if probability >= 0.5 else 0
 
@@ -148,5 +149,4 @@ if __name__ == "__main__":
     weights, selector = train_logreg(X_train, y_train, learning_rate=0.0001, iterations=5000, batch_size=32, lambda_=0.1, degree=2)
 
     # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights, selector, degree=2)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    y_pred = predict_logreg(X_test[11], weights