From efdd3712a905775cba5315698d86fd09210b0285 Mon Sep 17 00:00:00 2001
From: luderby <2339127037@qq.com>
Date: Tue, 5 Nov 2024 19:14:23 +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 | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/function.py b/function.py
index 9861331..3d96b27 100644
--- a/function.py
+++ b/function.py
@@ -55,19 +55,19 @@ def predict_logreg(inX, weights):
 # 从文件中加载数据  
 def load_data(filepath):
     data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)
-    for col in data.columns:
-        if pd.api.types.is_numeric_dtype(data[col]):
-            data[col].fillna(data[col].median(), inplace=True)
-        else:  # 处理非数值列，例如用众数填充或其他策略
-            data[col].fillna(data[col].mode()[0], inplace=True)
 
-    X = data.iloc[:, :-1].to_numpy()
-    y = data.iloc[:, -1].to_numpy()
+    # 使用SimpleImputer进行中位数填充
+    imputer = SimpleImputer(strategy='median')
+    data_imputed = imputer.fit_transform(data)
+    data = pd.DataFrame(data_imputed)
 
+    X = data.iloc[:, :-1].to_numpy()  # 特征
+    y = data.iloc[:, -1].to_numpy()    # 标签
+    # 使用MinMaxScaler进行特征缩放
     scaler = MinMaxScaler()
-    X = scaler.fit_transform(X)  # 缩放特征
-
-    return X, y 
+    X = scaler.fit_transform(X)
+    return X, y
+    
 # 准确率计算函数
 def calculate_accuracy(X, y, weights):
     predictions = np.array([predict_logreg(x, weights) for x in X])