From 03c98cf1b4a64f0745fa4b4dcf7c62a9e90c8d7f Mon Sep 17 00:00:00 2001
From: mogu-king <1547976000@qq.com>
Date: Sun, 3 Nov 2024 04:10:05 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/function.py b/function.py
index 6b87d42..7dc9248 100644
--- a/function.py
+++ b/function.py
@@ -29,12 +29,25 @@ def load_data(filepath):
     - X (numpy array): 特征数据
     - y (numpy array): 标签数据
     """
-    data = np.loadtxt(filepath, delimiter=",")
+    # 读取数据，指定缺失值符号为 '?'
+    data = np.genfromtxt(filepath, delimiter=",", dtype=str)
+    
+    # 将 '?' 替换为 np.nan 并转换为浮点数
+    data[data == '?'] = np.nan
+    data = data.astype(float)
+    
+    # 对每一列的缺失值使用列的均值填充
+    col_means = np.nanmean(data, axis=0)
+    inds = np.where(np.isnan(data))
+    data[inds] = np.take(col_means, inds[1])
+    
+    # 分离特征和标签
     X = data[:, :-1]
     y = data[:, -1]
     return X, y
 
 
+
 # 这里实现对率回归训练函数
 def train_logreg(X, y, learning_rate=0.01, num_iterations=1000, regularization_strength=0.01):
     """