更新 function.py

function.py

@@ -1,6 +1,6 @@
 import numpy as np
 import os
-from sklearn.preprocessing import StandardScaler  # 导入标准化库
+from sklearn.preprocessing import StandardScaler
 
 # 学号和姓名
 id = "202210423130"
@@ -46,7 +46,7 @@ def predict_logreg(inX, weights):
     h = sigmoid(z)
     return 1 if h >= 0.5 else 0
 
-def load_data(filepath):
+def load_data(filepath, remove_indices=None):
     """从文件中加载数据。"""
     if not os.path.exists(filepath):
         raise FileNotFoundError(f"文件 {filepath} 不存在！")
@@ -66,14 +66,9 @@ def load_data(filepath):
     data = np.array(data)
     labels = np.array(labels)
     
-    num_features = data.shape[1]
-    indices_to_remove = [2]  # 去掉特征3（索引2）
+    if remove_indices is not None:
+        data = np.delete(data, remove_indices, axis=1)
     
-    # 剔除特征 24-28（索引 23-27）
-    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}")
@@ -104,9 +99,12 @@ 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
+
     # 加载训练集
     try:
-        X_train, y_train = load_data("./data/horse-colic.data")
+        X_train, y_train = load_data("./data/horse-colic.data", remove_indices=indices_to_remove)
     except FileNotFoundError as e:
         print(e)
         exit()
@@ -121,7 +119,7 @@ if __name__ == "__main__":
 
     # 加载测试集
     try:
-        X_test, y_test = load_data("./data/horse-colic.test")
+        X_test, y_test = load_data("./data/horse-colic.test", remove_indices=indices_to_remove)
     except FileNotFoundError as e:
         print(e)
         exit()