更新 function.py

function.py

@@ -121,18 +121,46 @@ def load_data(filepath):
     
     return data, target_variable
 
+def accuracy(X, y, weights):
+    predictions = [predict_logreg(x, weights) for x in X]
+    accuracy = np.mean(predictions == y)
+    return accuracy
+
+
+def grid_search(X_train, y_train, X_test, y_test, param_grid):
+    best_accuracy = 0
+    best_params = None
+
+    for params in product(*param_grid.values()):
+        learning_rate, iterations, batch_size, regularization, lambda_reg = params
+
+        print(f"尝试参数组合: {params}")
+        weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, regularization, lambda_reg)
+        acc = accuracy(X_test, y_test, weights)
+
+        print(f"当前准确率: {acc:.4f}")
+
+        if acc > best_accuracy:
+            best_accuracy = acc
+            best_params = params
+
+    return best_params, best_accuracy
+
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 定义参数网格
+    param_grid = {
+        'learning_rate': [0.01, 0.05],
+        'iterations': [500, 1000],
+        'batch_size': [16, 32],
+        'regularization': [None, 'L1', 'L2'],
+        'lambda_reg': [0.1, 0.5]
+    }
 
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, batch_size=16, regularization='L1',
-                           lambda_reg=0.1)
+    # 进行网格搜索
+    best_params, best_accuracy = grid_search(X_train, y_train, X_test, y_test, param_grid)
 
-    # 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]}")
+    print(f"最佳参数组合: {best_params}")
+    print(f"最佳准确率: {best_accuracy:.4f}")