更新 function.py

function.py

@@ -141,40 +141,16 @@ def load_data(filepath):
     """
 
 if __name__ == "__main__":
-    # 加载数据并分割为训练集和验证集
+    # 以下代码可用于测试，可自行随意修改
-    X, y = load_data("./data/horse-colic.data")
+    # 加载训练集
-    X_train, X_val, y_train, y_val = split_train_val(X, y)
+    X_train, y_train = load_data("./data/horse-colic.data")
 
-    # 模型调优参数
+    # 加载测试集
-    learning_rates = [0.01, 0.001, 0.0001]
-    iterations = [500, 1000, 2000]
-    batch_sizes = [16, 32, 64]
-    
-    best_accuracy = 0
-    best_params = {}
-
-    # 网格搜索
-    for lr in learning_rates:
-        for it in iterations:
-            for bs in batch_sizes:
-                initial_weights = np.random.randn(X_train.shape[1] + 1)
-                weights = train_logreg(X_train, y_train, lr, it, bs, initial_weights)
-                accuracy = evaluate_model(X_val, y_val, weights)
-                
-                print(f"Learning Rate: {lr}, Iterations: {it}, Batch Size: {bs}, Accuracy: {accuracy}")
-                
-                if accuracy > best_accuracy:
-                    best_accuracy = accuracy
-                    best_params = {'learning_rate': lr, 'iterations': it, 'batch_size': bs}
-
-    # 输出最佳参数
-    print(f"Best Parameters: {best_params}")
-    print(f"Best Validation Accuracy: {best_accuracy}")
-
-    # 使用最佳参数训练最终模型
-    final_weights = train_logreg(X_train, y_train, **best_params)
-    
-    # 在测试集上评估最终模型
     X_test, y_test = load_data("./data/horse-colic.test")
-    test_accuracy = evaluate_model(X_test, y_test, final_weights)
+
-    print(f"Test Set Accuracy: {test_accuracy}")
+    # 训练对率回归模型
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+
+    # 测试单个数据
+    y_pred = predict_logreg(X_test[11], weights)
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")