From a3a1d0d6a7686e2cf4554e1b91a53946a9bd0cb8 Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Thu, 31 Oct 2024 16:54:38 +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 | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/function.py b/function.py
index 68c6c40..ad04fe9 100644
--- a/function.py
+++ b/function.py
@@ -27,7 +27,7 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
-
+from sklearn.model_selection import KFold
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
@@ -92,6 +92,21 @@ def load_data(filepath):
     X = data[:, :-1]
     y = data[:, -1]
     return X, y
+def cross_validate(X, y, k=5, learning_rate=0.01, iterations=1000):
+    kf = KFold(n_splits=k)
+    accuracies = []
+
+    for train_index, test_index in kf.split(X):
+        X_train, X_test = X[train_index], X[test_index]
+        y_train, y_test = y[train_index], y[test_index]
+
+        weights = train_logreg(X_train, y_train, learning_rate, iterations)
+        predictions = [predict_logreg(x, weights) for x in X_test]
+        
+        accuracy = np.mean(predictions == y_test)
+        accuracies.append(accuracy)
+
+    return np.mean(accuracies)
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
@@ -102,8 +117,7 @@ if __name__ == "__main__":
     X_test, y_test = load_data("./data/horse-colic.test")
 
     # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=10000)
+     k = 5  # 设置折数
+    accuracy = cross_validate(X, y, k=k, learning_rate=0.01, iterations=5000)
 
-    # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    print(f"{k}-折交叉验证的平均准确率: {accuracy:.2f}")