From 5f7d2a00804f2d947d618b0c98ee33fde956aaf7 Mon Sep 17 00:00:00 2001
From: Xionghaoran <719929980@qq.com>
Date: Mon, 14 Oct 2024 21:27:12 +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 | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/function.py b/function.py
index 6b2ab1d..a412777 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,7 @@
 # function.py
 import numpy as np
 from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import cross_val_score
 
 """
 挑战说明:
@@ -85,11 +86,29 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
+def find_best_k(dataSet, labels):
+    """
+    使用交叉验证找到最佳 k 值。
+    """
+    best_score = 0
+    best_k = 3
+    for k in range(1, 11):
+        predictions = [classify0(x, dataSet, labels, k) for x in dataSet]
+        score = np.mean(predictions == labels)
+        if score > best_score:
+            best_score = score
+            best_k = k
+    return best_k
+
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
     train_file = "datingTrainSet2.tsv"
     train_data, train_labels = load_data(train_file)
-
+    
+    # 找到最佳 k 值
+    best_k = find_best_k(train_data, train_labels)
+    print(f"Best k: {best_k}")
+    
     # 预测结果
-    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels, k=3))
\ No newline at end of file
+    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels, best_k))
\ No newline at end of file