更新 function.py

function.py

@@ -1,6 +1,5 @@
 import numpy as np
 import os
-from sklearn.preprocessing import StandardScaler
 
 # 学号和姓名
 id = "202210423130"
@@ -68,12 +67,18 @@ def load_data(filepath, remove_indices=None):
     
     if remove_indices is not None:
         data = np.delete(data, remove_indices, 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]
@@ -99,9 +104,9 @@ def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, ba
     return np.mean(accuracies)
 
 if __name__ == "__main__":
-    # 定义要剔除的特征索引
-    indices_to_remove = [2] + list(range(23, 28))  # 去掉特征3和24到28的特征
-
+    # 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)
@@ -109,9 +114,8 @@ if __name__ == "__main__":
         print(e)
         exit()
 
-    # 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
+    # 归一化训练集
+    X_train = normalize_data(X_train)
 
     # k折交叉验证
     avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)
@@ -124,8 +128,8 @@ if __name__ == "__main__":
         print(e)
         exit()
 
-    # 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
+    # 归一化测试集
+    X_test = normalize_data(X_test)
 
     # 训练对率回归模型
     weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)