From 8b9ff6e020c36f5868cea11b55d7e9ee51d4e74b Mon Sep 17 00:00:00 2001
From: DREMN2112 <z2117004628@gmail.com>
Date: Thu, 7 Nov 2024 16:48:50 +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 | 28 ++++++----------------------
 1 file changed, 6 insertions(+), 22 deletions(-)

diff --git a/function.py b/function.py
index 9720f59..d0c9b22 100644
--- a/function.py
+++ b/function.py
@@ -58,7 +58,7 @@ def predict_logreg(inX, weights):
 
 def load_data(filepath):
     """
-    从文件中加载数据，处理缺失数据和确保样本数匹配。
+    从文件中加载数据。
 
     Args:
     - filepath (str): 数据文件路径。
@@ -69,36 +69,20 @@ def load_data(filepath):
     """
     data = []
     labels = []
-
+    
     with open(filepath, 'r') as file:
         for line in file:
             line = line.strip().split()
             if not line:
                 continue
-
-            # 过滤掉包含 '?' 的行
-            if '?' in line:
-                continue
-
-            # 确保每行都有正确数量的特征和标签
-            if len(line) != 9:  # 假设每行有8个特征和1个标签
-                continue
-
-            # 将特征转换为浮点数
-            try:
-                features = list(map(float, line[:-1]))  # 所有特征转换为浮点数
-                label = int(line[-1])  # 标签为整数
-            except ValueError:
-                # 如果遇到无法转换的值，则跳过这一行
-                continue
-
-            # 添加到数据集
+            # 将特征转换为浮点型
+            features = list(map(float, line[:-1]))
+            label = int(line[-1])
             data.append(features)
             labels.append(label)
-
+    
     return np.array(data), np.array(labels)
 
-
 if __name__ == "__main__":
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")