From 6a5fd7b2c4528b57f2e06fc7b5c0b327576906a2 Mon Sep 17 00:00:00 2001
From: 77 <3298722099@qq.com>
Date: Thu, 21 Nov 2024 09:13:05 +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, 18 insertions(+), 5 deletions(-)

diff --git a/function.py b/function.py
index ad3460e..34fdce4 100644
--- a/function.py
+++ b/function.py
@@ -43,7 +43,8 @@ name = "陈瑞琪祥"
 # 这里写自己的代码实现
 
 
-def classify0(inX, dataSet, labels, k=3):
+
+def classify0(inX, dataSet, labels, k=5):
     """
     KNN 分类算法。
 
@@ -51,7 +52,7 @@ def classify0(inX, dataSet, labels, k=3):
     - inX (numpy array): 输入待分类的样本。
     - dataSet (numpy array): 训练数据集。
     - labels (list or numpy array): 训练集对应的标签。
-    - k (int): kNN 算法参数，默认值为 3。
+    - k (int): kNN 算法参数，默认值为 5。
 
     Returns:
     - int: 预测的分类标签。
@@ -77,15 +78,27 @@ def classify0(inX, dataSet, labels, k=3):
 
 def load_data(file_path):
     """
-    加载 TSV 格式数据文件。
+    加载 TSV 格式数据文件，并进行标准化处理。
     """
     data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
+    
+    # 标准化特征
+    features = (features - np.mean(features, axis=0)) / np.std(features, axis=0)
+    
     return features, labels
 
 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)
-    print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))
+    test_file = "datingTestSet2.tsv"
+    test_data, test_labels = load_data(test_file)
+    
+    # 测试 KNN 分类器
+    correct_count = 0
+    for i in range(test_data.shape[0]):
+        if classify0(test_data[i], train_data, train_labels) == test_labels[i]:
+            correct_count += 1
+    
+    print(f"Accuracy: {correct_count / test_data.shape[0] * 100:.2f}%")
\ No newline at end of file