更新 function.py

function.py

@@ -1,5 +1,6 @@
-import numpy as np
+	import numpy as np
 import os
+from sklearn.preprocessing import StandardScaler  # 导入标准化库
 
 # 学号和姓名
 id = "202210423130"
@@ -45,7 +46,7 @@ def predict_logreg(inX, weights):
     h = sigmoid(z)
     return 1 if h >= 0.5 else 0
 
-def load_data(filepath, remove_indices=None):
+def load_data(filepath):
     """从文件中加载数据。"""
     if not os.path.exists(filepath):
         raise FileNotFoundError(f"文件 {filepath} 不存在！")
@@ -53,10 +54,8 @@ def load_data(filepath, remove_indices=None):
     data, labels = [], []
     print(f"加载数据中: {filepath}")
     with open(filepath, 'r') as f:
-        for line_idx, line in enumerate(f):
+        for line in f:
             line = line.strip().split()
-            if line_idx == 2:  # 跳过第三行
-                continue
             if len(line) >= 1 and line[-1].isdigit():
                 line_data = [0 if x == '?' else float(x) for x in line[:-1]]
                 data.append(line_data)
@@ -65,20 +64,18 @@ def load_data(filepath, remove_indices=None):
     data = np.array(data)
     labels = np.array(labels)
     
-    if remove_indices is not None:
-        data = np.delete(data, remove_indices, axis=1)
+    num_features = data.shape[1]
+	    indices_to_remove = [2]  # 去掉特征3（索引2）
     
+    if num_features > 23:
+        indices_to_remove.extend(range(23, min(28, num_features)))
+
+    data = np.delete(data, indices_to_remove, axis=1)
     target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
 
     print(f"数据加载成功，数据形状: {data.shape}, 标签形状: {target_variable.shape}")
     return data, target_variable
 
-def normalize_data(X):
-    """归一化数据。"""
-    min_vals = X.min(axis=0)
-    max_vals = X.max(axis=0)
-    return (X - min_vals) / (max_vals - min_vals)
-
 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。"""
     m = X.shape[0]
@@ -104,18 +101,16 @@ def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, ba
     return np.mean(accuracies)
 
 if __name__ == "__main__":
-    # 剔除特征索引
-    indices_to_remove = [2]  # 去掉特征3（索引2）
-    
     # 加载训练集
     try:
-        X_train, y_train = load_data("./data/horse-colic.data", remove_indices=indices_to_remove)
+        X_train, y_train = load_data("./data/horse-colic.data")
     except FileNotFoundError as e:
         print(e)
         exit()
 
-    # 归一化训练集
-    X_train = normalize_data(X_train)
+    # 数据归一化处理
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)  # 使用训练集进行标准化
 
     # k折交叉验证
     avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)
@@ -123,13 +118,13 @@ if __name__ == "__main__":
 
     # 加载测试集
     try:
-        X_test, y_test = load_data("./data/horse-colic.test", remove_indices=indices_to_remove)
+        X_test, y_test = load_data("./data/horse-colic.test")
     except FileNotFoundError as e:
         print(e)
         exit()
 
-    # 归一化测试集
-    X_test = normalize_data(X_test)
+    # 测试集也需要进行相同的归一化
+    X_test = scaler.transform(X_test)  # 使用相同的Scaler进行测试集的标准化
 
     # 训练对率回归模型
     weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)