更新 function.py

function.py

@@ -1,4 +1,3 @@
-# function.py
 import numpy as np
 
 """
@@ -8,44 +7,55 @@ import numpy as np
 - 在 function.py 中实现对率回归算法。
 - 可以自行导入其他库，需要在 requirements.txt 添加依赖。
 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
-测评环境:
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
-- OS: Ubuntu 22.04.4 LTS
-- Python: 3.10.12
-- numpy: 2.1.1
 """
 
-id = "202210423xxx"
-name = "test_name"
+id = "202210423213"
+name = "熊浩燃"
 
-# 对率回归训练函数
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
+# 对率回归训练函数，包含调参和优化
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01, early_stopping_rounds=100):
     """
-    对率回归训练函数。
+    对率回归训练函数，带有学习率调度和正则化。
     Args:
     - X (numpy array): 特征数据。
     - y (numpy array): 标签数据。
-    - learning_rate (float): 学习率，默认为0.01。
-    - iterations (int): 迭代次数，默认为1000。
+    - learning_rate (float): 初始学习率。
+    - iterations (int): 最大迭代次数。
+    - regularization (float): 正则化参数。
+    - early_stopping_rounds (int): 提前停止轮数。
     Returns:
     - numpy array: 训练得到的权重。
     """
-    # 初始化权重
     weights = np.zeros(X.shape[1])
+    min_loss = float('inf')
+    stopping_step = 0
 
     for i in range(iterations):
         # 预测值：通过对率回归模型得到
         z = np.dot(X, weights)
         predictions = 1 / (1 + np.exp(-z))
         
-        # 计算梯度并更新权重
-        gradient = np.dot(X.T, (predictions - y)) / y.size
-        weights -= learning_rate * gradient
+        # 计算损失（含正则化项）
+        loss = -np.mean(y * np.log(predictions) + (1 - y) * np.log(1 - predictions)) + regularization * np.sum(weights**2)
         
-        # 可选：输出损失，帮助调试
-        if i % 100 == 0:
-            loss = -np.mean(y * np.log(predictions) + (1 - y) * np.log(1 - predictions))
-            print(f"迭代 {i}，损失: {loss}")
+        # 提前停止判断
+        if loss < min_loss:
+            min_loss = loss
+            stopping_step = 0
+        else:
+            stopping_step += 1
+        if stopping_step >= early_stopping_rounds:
+            print("提前停止于迭代:", i)
+            break
+
+        # 计算梯度并更新权重（含正则化项）
+        gradient = (np.dot(X.T, (predictions - y)) + regularization * weights) / y.size
+        weights -= learning_rate * gradient
+
+        # 学习率调整策略
+        if i % 100 == 0 and i != 0:
+            learning_rate *= 0.9  # 每100轮衰减学习率
+            print(f"迭代 {i}，损失: {loss}，学习率: {learning_rate}")
 
     return weights
 
@@ -96,17 +106,56 @@ def load_data(filepath):
 
     return data, labels
 
+# 网格搜索函数
+def grid_search(X, y, learning_rates, iterations_list, regularizations):
+    """
+    网格搜索来优化对率回归模型。
+    Args:
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - learning_rates (list of float): 学习率列表。
+    - iterations_list (list of int): 迭代次数列表。
+    - regularizations (list of float): 正则化参数列表。
+    Returns:
+    - dict: 包含最佳超参数及其对应的权重。
+    """
+    best_params = {}
+    best_weights = None
+    best_loss = float('inf')
+
+    for lr in learning_rates:
+        for iters in iterations_list:
+            for reg in regularizations:
+                print(f"尝试参数: 学习率={lr}, 迭代次数={iters}, 正则化={reg}")
+                weights = train_logreg(X, y, learning_rate=lr, iterations=iters, regularization=reg)
+                z = np.dot(X, weights)
+                predictions = 1 / (1 + np.exp(-z))
+                loss = -np.mean(y * np.log(predictions) + (1 - y) * np.log(1 - predictions))
+                print(f"损失: {loss}")
+
+                if loss < best_loss:
+                    best_loss = loss
+                    best_weights = weights
+                    best_params = {'learning_rate': lr, 'iterations': iters, 'regularization': reg}
+
+    print("最佳参数:", best_params)
+    return best_weights, best_params
 
 if __name__ == "__main__":
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
 
-    # 加载测试集
+    # 超参数列表
+    learning_rates = [0.001, 0.01, 0.1]
+    iterations_list = [1000, 2000, 3000]
+    regularizations = [0.01, 0.1, 1.0]
+
+    # 进行网格搜索以找到最佳超参数组合
+    best_weights, best_params = grid_search(X_train, y_train, learning_rates, iterations_list, regularizations)
+    print("最佳权重:", best_weights)
+
+    # 使用最佳权重进行预测
     X_test, y_test = load_data("./data/horse-colic.test")
-
-    # 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]}")
+    y_pred = [predict_logreg(x, best_weights) for x in X_test]
+    accuracy = np.mean(y_pred == y_test)
+    print(f"测试集准确率: {accuracy}")