更新 function.py

2024-10-31 15:59:02 +08:00
parent e609a58412
commit 982b068ffe
1 changed files with 5 additions and 4 deletions
@@ -54,15 +54,16 @@ def load_data(filepath):
    - np.array: 特征数据。
    - np.array: 标签数据。
    """
-    data = np.loadtxt(filepath, delimiter=",", dtype=float)
+
+    data = np.genfromtxt(filepath, delimiter=" ", dtype=float, missing_values="?", filling_values=np.nan)
    
-    # 检查缺失值并使用列均值进行填充
+    # 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])
    
-    X = data[:, :-1]
-    y = data[:, -1]
+    X = data[:, :-1]  # 特征
+    y = data[:, -1]   # 标签
    return X, y

 if __name__ == "__main__":