更新 function.py

function.py

@@ -117,20 +117,19 @@ def load_data(filepath):
     data = [line.strip().split() for line in lines]
     data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
     
-    # 处理缺失值，这里简单用平均值填充
-    for i in range(len(data[0])):
-        mean_val = np.nanmean([row[i] for row in data if not np.isnan(row[i])])
-        for row in data:
+    # 使用“0”填充缺失值
+    for row in data:
+        for i in range(len(row)):
             if np.isnan(row[i]):
-                row[i] = mean_val
+                row[i] = 0.0
     
     # 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）
+        if row[22] == 2 or row == 3:  # 假设特征23是第23个元素
             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）
+    # 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
     data = [row[:2] + row[3:23] + row[28:] for row in data]
     
     # 分离特征和标签