diff --git a/function.py b/function.py
index 0577f2b..4d38168 100644
--- a/function.py
+++ b/function.py
@@ -124,8 +124,17 @@ def load_data(filepath):
             if np.isnan(row[i]):
                 row[i] = mean_val
     
+    # 合并特征23的值2和3为0
+    for row in data:
+        if row[22] == 2 or row == 3:  # 假设特征23是第23个元素（索引为22）
+            row[22] = 0
+    
+    # 移除不需要的特征
+    # 假设特征从0开始编号，那么我们需要移除特征3（索引为2）和特征24~28（索引为23~27）
+    data = [row[:2] + row[3:23] + row[28:] for row in data]
+    
     # 分离特征和标签
-    X = [row[:-1] for row in data]
+    X = [row[:-1] for row in data]  # 特征现在是从0到21，然后是23到27
     y = [row[-1] for row in data]
     
     return np.array(X), np.array(y)