From 3677b2ab8666b402cd105bf5b21d166c09524599 Mon Sep 17 00:00:00 2001
From: DREMN2112 <z2117004628@gmail.com>
Date: Thu, 7 Nov 2024 16:52:41 +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 | 33 +++++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/function.py b/function.py
index d0c9b22..7aa8180 100644
--- a/function.py
+++ b/function.py
@@ -56,9 +56,11 @@ def predict_logreg(inX, weights):
     # 将概率转为标签
     return 1 if prob >= 0.5 else 0
 
+import numpy as np
+
 def load_data(filepath):
     """
-    从文件中加载数据。
+    从文件中加载数据，处理缺失数据，并将 '?' 替换为列的均值。
 
     Args:
     - filepath (str): 数据文件路径。
@@ -69,19 +71,38 @@ def load_data(filepath):
     """
     data = []
     labels = []
-    
+
+    # 读取数据
     with open(filepath, 'r') as file:
         for line in file:
             line = line.strip().split()
             if not line:
                 continue
-            # 将特征转换为浮点型
-            features = list(map(float, line[:-1]))
+
+            # 将标签提取出来
             label = int(line[-1])
+
+            # 将特征转换为浮动数组
+            features = line[:-1]  # 去除标签部分
+            # 用特征中的均值替换 '?'，并转换为 float
+            features = [float(f) if f != '?' else None for f in features]
+            
+            # 将数据和标签分别加入到列表
             data.append(features)
             labels.append(label)
-    
-    return np.array(data), np.array(labels)
+
+    # 将列表转换为numpy数组
+    data = np.array(data)
+    labels = np.array(labels)
+
+    # 计算每列的均值，并用均值替换 None
+    col_means = np.nanmean(data, axis=0)  # 计算每列的均值，忽略 NaN
+    # 将 None 替换为对应的列均值
+    for i in range(data.shape[1]):
+        data[:, i] = np.where(np.isnan(data[:, i]), col_means[i], data[:, i])
+
+    return data, labels
+
 
 if __name__ == "__main__":
     # 加载训练集