From 7c68af79b7e717bb05f6cfd1d805d9a980bbbe4e Mon Sep 17 00:00:00 2001
From: heart20003 <1789588961@qq.com>
Date: Sun, 3 Nov 2024 20:46:15 +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 | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/function.py b/function.py
index 7cf27a9..6973ca5 100644
--- a/function.py
+++ b/function.py
@@ -25,6 +25,8 @@ id = "202210423204"
 name = "陈垣豪"
 
 
+import numpy as np
+from sklearn.preprocessing import StandardScaler
 
 def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     """训练逻辑回归模型，使用随机梯度下降."""
@@ -33,15 +35,11 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     X = np.c_[X, np.ones((n_samples, 1))]  # 增加偏置项
 
     for _ in range(iterations):
-        # 随机选择一个样本
         random_index = np.random.randint(n_samples)
         X_i = X[random_index]
         y_i = y[random_index]
         
-        # 计算线性模型输出
         linear_model = np.dot(X_i, weights)
-        
-        # 更新权重
         dw = (linear_model - y_i) * X_i
         weights -= learning_rate * dw
 
@@ -67,10 +65,16 @@ if __name__ == "__main__":
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
     
+    # 数据标准化
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+
     # 训练逻辑回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000)
 
     # 测试单个数据
     X_test, y_test = load_data("./data/horse-colic.test")
+    X_test = scaler.transform(X_test)  # 同样标准化测试集
     y_pred = predict_logreg(X_test[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+