更新 function.py

function.py

@@ -128,21 +128,45 @@ def accuracy(X, y, weights):
     predictions = [predict_logreg(sample, weights) for sample in X]
     return np.mean(predictions == y)  # 计算准确率
 
-if __name__ == "__main__":
+def grid_search(X_train, y_train, X_test, y_test, param_grid):
-    # 以下代码可用于测试，可自行随意修改
+    best_accuracy = 0
-    # 加载训练集
+    best_params = None
-    X_train, y_train = load_data("./horse-colic.data")
 
-    # 加载测试集
+    for params in product(*param_grid.values()):
+        learning_rate, iterations, batch_size, regularization, lambda_reg = params
+
+        weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, regularization, lambda_reg)
+        acc = accuracy(X_test, y_test, weights)
+
+        if acc > best_accuracy:
+            best_accuracy = acc
+            best_params = params
+
+    return best_params, best_accuracy
+
+if __name__ == "__main__":
+    X_train, y_train = load_data("./horse-colic.data")
     X_test, y_test = load_data("./horse-colic.test")
 
-    # 训练对率回归模型
+    # 定义参数网格
-    weights = train_logreg(X_train, y_train, learning_rate=0.25, iterations=1500, batch_size=16, regularization='L2',
+    param_grid = {
-                           lambda_reg=0.5)
+        'learning_rate': [0.01, 0.05, 0.1, 0.15, 0.2, 0.25],
-    # 计算并输出准确率
+        'iterations': [200, 500, 1000, 1500],
-    acc = accuracy(X_test, y_test, weights)
+        'batch_size': [16, 32, 64, 128],
-    print(f"模型的准确率: {acc:.2f}")
+        'regularization': [None, 'L1', 'L2'],
+        'lambda_reg': [0.1, 0.5, 0.05, 0.15]
+    }
 
-    # 测试单个数据
+    # 进行网格搜索
-    y_pred = predict_logreg(X_test[11], weights)
+    best_params, best_accuracy = grid_search(X_train, y_train, X_test, y_test, param_grid)
-    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}")
+
+    # 使用最佳参数组合进行最终测试
+    best_learning_rate, best_iterations, best_batch_size, best_regularization, best_lambda_reg = best_params
+    final_weights = train_logreg(X_train, y_train, best_learning_rate, best_iterations, best_batch_size, best_regularization, best_lambda_reg)
+
+    # 计算并输出最终测试集的准确率
+    final_accuracy = accuracy(X_test, y_test, final_weights)
+    print(f"最终测试集的准确率: {final_accuracy:.4f}")