From 17d85e7a9d371022dc2d4f3df7553806841b6684 Mon Sep 17 00:00:00 2001
From: dong <2938690875@qq.com>
Date: Thu, 31 Oct 2024 16:58:10 +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 | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/function.py b/function.py
index 19caac4..0bfeecc 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,8 @@
 # function.py
 import numpy as np
-
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
 
 
 """
@@ -88,6 +90,11 @@ def load_data(filepath):
 
     return np.array(data), np.array(labels)
 
+def preprocess_data(X):
+    # 特征标准化
+    scaler = StandardScaler()
+    return scaler.fit_transform(X)
+
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
@@ -99,6 +106,7 @@ if __name__ == "__main__":
 
     # 训练对率回归模型
     weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000,lambda_reg=0.01)
+    X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)