From f2b293e4ad216ab6d1af7bacff349c7ffe9d33e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=88=98=E7=87=9A=E7=87=8A?= <maylin2233@outlook.com>
Date: Sun, 3 Nov 2024 17:12:57 +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 | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/function.py b/function.py
index 85939e5..83481da 100644
--- a/function.py
+++ b/function.py
@@ -6,8 +6,10 @@ from sklearn.impute import SimpleImputer
 id = "202210423107"
 name = "刘燚燊"
 
+import pandas as pd
+
 def load_data(filepath):
-    """ 
+    """
     从文件中加载数据，处理缺失值和标签。
     
     Args:
@@ -17,20 +19,15 @@ def load_data(filepath):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    with open(filepath, 'r') as f:
-        data = [line.strip().split() for line in f.readlines()]
+    # 使用pandas读取数据
+    data = pd.read_csv(filepath, header=None, na_values='?')
 
-    # 将数据中缺失值用0填充
-    data = [[0 if value == '?' else float(value) for value in line] for line in data]
-    data = np.array(data)
+    # 填充缺失值
+    data.fillna(data.mean(), inplace=True)
 
     # 分离特征和标签
-    X = data[:, :-1]
-    y = data[:, -1]
-
-    # 使用均值填充缺失值
-    imputer = SimpleImputer(strategy='mean')
-    X = imputer.fit_transform(X)
+    X = data.iloc[:, :-1].values
+    y = data.iloc[:, -1].values
 
     # 过滤掉没有类别标签的数据
     valid_indices = np.isfinite(y)
@@ -40,6 +37,7 @@ def load_data(filepath):
     return X, y
 
 
+
 def train_logreg(X, y, learning_rate=0.01, iterations=1000, reg_param=0.01):
     # 初始化权重
     weights = np.zeros(X.shape[1])