更新 function.py

function.py

@@ -65,13 +65,18 @@ def load_data(filepath):
     """
     data = np.genfromtxt(filepath, delimiter=" ", dtype=float, missing_values="?", filling_values=np.nan)
     
-    # 使用列均值填充缺失值
-    col_means = np.nanmean(data, axis=0)
-    indices = np.where(np.isnan(data))
-    data[indices] = np.take(col_means, indices[1])
+    # 对每一列单独填充缺失值
+    for i in range(data.shape[1] - 1):  # 最后一列是标签列
+        if np.isnan(data[:, i]).any():
+            # 使用中位数填充数值型数据
+            median = np.nanmedian(data[:, i])
+            data[np.isnan(data[:, i]), i] = median
+    
+    # 标准化特征数据
+    X = data[:, :-1]
+    y = data[:, -1]
+    X = (X - X.mean(axis=0)) / X.std(axis=0)
     
-    X = data[:, :-1]  # 特征
-    y = data[:, -1]   # 标签
     return X, y
 
 if __name__ == "__main__":