From 16b9377f359b60b392a3195e768edb752fbd94f5 Mon Sep 17 00:00:00 2001
From: zhe <2904040094@qq.com>
Date: Wed, 23 Oct 2024 11:40:33 +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 | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/function.py b/function.py
index ddc4b6c..7faac63 100644
--- a/function.py
+++ b/function.py
@@ -1,7 +1,8 @@
 # function.py
 import numpy as np
 import os
-
+from scipy.spatial.distance import mahalanobis  
+from collections import Counter 
 """
 实验说明:
 - 自行编写实现数据加载与 kNN 的手写数字分类算法。
@@ -43,11 +44,15 @@ name = "李劲"
 # 这里写自己的代码实现
 def classify(input_vector, dataSet, labels, k=1):  
     """  
-    KNN 分类算法。  
+    KNN 分类算法，使用马氏距离。  
     """  
-    # 计算欧式距离  
-    distances = np.linalg.norm(dataSet - input_vector, axis=1)  
-      
+    # 计算协方差矩阵及其逆  
+    cov_matrix = np.cov(dataSet.T)  
+    inv_cov_matrix = np.linalg.inv(cov_matrix)  
+    
+    # 计算马氏距离  
+    distances = [mahalanobis(input_vector, point, inv_cov_matrix) for point in dataSet]  
+    
     # 获取距离最近的 k 个样本的索引  
     k_indices = np.argsort(distances)[:k]  
       
@@ -55,9 +60,8 @@ def classify(input_vector, dataSet, labels, k=1):
     k_nearest_labels = [labels[i] for i in k_indices]  
       
     # 找出出现次数最多的标签  
-    from collections import Counter  
     most_common = Counter(k_nearest_labels).most_common(1)[0][0]  
-      
+    
     return most_common  
   
 def load_dataset(directory):