更新 function.py

function.py

@@ -1,4 +1,5 @@
 import numpy as np
+import os
 
 # 学号和姓名
 id = "202210423130"
@@ -17,20 +18,7 @@ def compute_gradient(X_batch, y_batch, weights, lambda_reg):
     return gradient
 
 def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
-    """
+    """对率回归训练函数。"""
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - learning_rate (float): 学习率。
-    - iterations (int): 迭代次数。
-    - batch_size (int): 批量大小。
-    - lambda_reg (float): L2正则化参数。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
     m, n = X.shape
     weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
     for _ in range(iterations):
@@ -47,31 +35,16 @@ def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lam
     return weights
 
 def predict_logreg(inX, weights):
-    """
+    """对率回归预测函数。"""
-    对率回归预测函数。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
     z = np.dot(inX, weights)
     h = sigmoid(z)
     return 1 if h >= 0.5 else 0
 
 def load_data(filepath):
-    """
+    """从文件中加载数据。"""
-    从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
+    if not os.path.exists(filepath):
-
+        raise FileNotFoundError(f"文件 {filepath} 不存在！")
-    Args:
+    
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
     data, labels = [], []
     with open(filepath, 'r') as f:
         for line in f:
@@ -81,47 +54,27 @@ def load_data(filepath):
                 data.append(line_data)
                 labels.append(int(line[-1]))
 
-    # 将数据转换为numpy数组
     data = np.array(data)
     labels = np.array(labels)
     
-    # 特征选择：去掉特征3（索引2）和特征24~28（索引23到27），检查数据的形状
+    num_features = data.shape[1]
-    num_features = data.shape[1]  # 获取特征的总数
+    indices_to_remove = [2]  # 去掉特征3（索引2）
-    indices_to_remove = [2]  # 特征3的索引是2
     
-    # 仅在数据的特征数量足够时才删除特征24~28
     if num_features > 23:
-        indices_to_remove.extend(range(23, min(28, num_features)))  # 从特征24开始到特征28
+        indices_to_remove.extend(range(23, min(28, num_features)))
 
     data = np.delete(data, indices_to_remove, axis=1)
-    
-    # 将标签二分类化，2（死亡）和3（安乐死）合并为0，其余为1
     target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
 
     return data, target_variable
 
 def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
-    """
+    """K折交叉验证。"""
-    K折交叉验证。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - k (int): 折数。
-    - learning_rate (float): 学习率。
-    - iterations (int): 迭代次数。
-    - batch_size (int): 批量大小。
-    - lambda_reg (float): L2正则化参数。
-
-    Returns:
-    - float: 平均准确率。
-    """
     m = X.shape[0]
     fold_size = m // k
     accuracies = []
 
     for i in range(k):
-        # 创建训练集和验证集
         val_start = i * fold_size
         val_end = (i + 1) * fold_size if i != k - 1 else m
         
@@ -129,26 +82,34 @@ def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, ba
         y_val = y[val_start:val_end]
         X_train = np.concatenate((X[:val_start], X[val_end:]))
         y_train = np.concatenate((y[:val_start], y[val_end:]))
-        
+
-        # 训练模型
         weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg)
         
-        # 验证模型
         val_accuracy = np.mean([predict_logreg(X_val[j], weights) == y_val[j] for j in range(len(y_val))])
         accuracies.append(val_accuracy)
 
+        print(f"Fold {i + 1}/{k} - 验证准确率: {val_accuracy:.4f}")
+
     return np.mean(accuracies)
 
 if __name__ == "__main__":
     # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    try:
+        X_train, y_train = load_data("./data/horse-colic.data")
+    except FileNotFoundError as e:
+        print(e)
+        exit()
 
     # k折交叉验证
     avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)
     print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}")
 
     # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    try:
+        X_test, y_test = load_data("./data/horse-colic.test")
+    except FileNotFoundError as e:
+        print(e)
+        exit()
 
     # 训练对率回归模型
     weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)