更新 function.py

function.py

@@ -26,7 +26,43 @@ name = "赵昊龙"
 
 
 # 这里写自己的代码实现
-def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
+def load_data(filepath):
+    """
+    从文件中加载数据。
+
+    Args:
+    - filepath (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    file = open(filepath)
+    fr = file.readlines()
+    data_list = []
+    y = []
+    for data in fr:
+        data = data.strip()
+        data = data.split(' ')
+        data_25 = data[24]
+        y.append(data[22])
+        del data[-1]
+        del data[26]
+        del data[25]
+        del data[24]
+        del data[22]
+        del data[2]
+        for i in data_25:
+            data.append(i)
+        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
+        data_list.append(data)
+    data_number = len(y)
+    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
+    X = np.array(data_list)
+    X_train = np.insert(X, 0, 1, axis=1) 
+    return X_train, y_train
+
+def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
     """
     对率回归训练函数，加入L2正则化。
 
@@ -34,29 +70,33 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
     - X (numpy array): 特征数据。
     - y (numpy array): 标签数据。
     - numIter (int): 迭代次数。默认为1000。
-    - learning_rate (float): 学习率。默认为0.01。
+    - learning_rate (float): 学习率。默认为0.06。
+    - batch_size (int): 批量大小。默认为128。
     - lambda_reg (float): L2正则化参数。默认为0.01。
 
     Returns:
     - numpy array: 训练得到的权重。
     """
-    m, n = X.shape  # m: 样本数, n: 特征数
-    weights = np.zeros(n)  # 参数初始化
+    m, n = X.shape 
+    weights = np.zeros(n)  
 
     for j in range(numIter):
         dataIndex = np.random.permutation(m)
-        for i in range(0, m, 1):  # 使用整个数据集进行梯度下降
-            end = i + 1
+        for i in range(0, m, batch_size):
+            end = min(i + batch_size, m)
+            # 批量梯度上升
             batch_X = X[dataIndex[i:end]]
             batch_y = y[dataIndex[i:end]]
             
+            # 计算梯度
             z = np.dot(batch_X, weights)
             h = 1 / (1 + np.exp(-z))  # 计算h
             error = batch_y - h  # 计算误差
             gradient = np.dot(batch_X.T, error) / len(batch_y)  # 计算梯度
+            # 添加L2正则化
             reg_term = 2 * lambda_reg * weights
-            gradient += reg_term / len(batch_y)
-            weights -= learning_rate * gradient  # 更新权重
+            gradient -= reg_term / len(batch_y)
+            weights += learning_rate * gradient  # 更新权重
 
     return weights
 
@@ -73,58 +113,9 @@ def predict_logreg(inX, weights):
     """
     z = np.dot(inX, weights)  # 线性组合
     prob = 1 / (1 + np.exp(-z))  # 计算概率
-    return 1 if prob >= 0.5 else 0
-
-# 这里也写自己的代码实现
-def load_data(filepath):
-    """
-    从文件中加载数据。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-    with open(filepath, 'r') as file:
-        data_list = []
-        y_list = []
-        for line in file:
-            data = line.strip()
-            data = data.split(' ')
-            if '?' in data:
-                continue  # 跳过包含 '?' 的行
-            
-            # 提取标签并删除不需要的列
-            y_list.append(data[22])
-            del data[-1] 
-            del data[26] 
-            del data[25]  
-            del data[24]  
-            del data[22] 
-            del data[2]   
-            
-            # 将data_25的元素添加回data
-            data_25 = data[24]  # 假设data_25是索引为24的列的数据
-            for i in data_25:
-                data.append(i)
-            
-            # 将字符串转换为浮点数，除了'?'字符，它将被转换为0
-            data = [0.0 if data_elem == '?' else float(data_elem) for data_elem in data]
-            data_list.append(data)
-        
-        # 将标签转换为1如果它们是'2'或'3'，否则为0
-        y_array = np.array([1 if label == '2' or label == '3' else 0 for label in y_list])
-        
-        # 添加偏置项
-        X_array = np.array(data_list)
-        X_array = np.insert(X_array, 0, 1, axis=1)  # 添加偏置项
-        
-        return X_array, y_array
+    return 1 if prob >= 0.5 else 0  # 返回分类标签
 
 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")
 
@@ -132,8 +123,15 @@ if __name__ == "__main__":
     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)
+    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.2)
 
-    # 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]}")
+    # 测试模型
+    error = 0
+    accuracy_list = []
+    for i in range(len(y_test)):
+        y_pred = predict_logreg(X_test[i], weights)
+        if y_pred != y_test[i]:
+            error += 1
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
+    accuracy = (len(y_test) - error) / len(y_test)
+    print(f"Accuracy: {accuracy}")