From c02a62fa2266a06e9a0d5009aea99b0e46667751 Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Sun, 20 Oct 2024 13:44:26 +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 aeea5fa..01d1c65 100644
--- a/function.py
+++ b/function.py
@@ -55,15 +55,19 @@ def classify(input_vector, dataSet, labels, k=2):
 	    - input_vector (numpy array): 输入待分类的样本（1xN）。  
 	    - dataSet (numpy array): 训练数据集（MxN）。  
     - 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 2。  
   
     返回:  
     - int: 预测的分类标签。  
     """  
-    # 计算输入向量与训练集之间的欧氏距离
-    distances = np.sum((input_vector - dataSet) ** 2, axis=1)
-    sorted_indices = distances.argsort()
-    k_nearest_distances = distances[sorted_indices[:k]]
+     # 将欧氏距离改为马氏距离
+    mean_vector = np.mean(dataSet, axis=0)
+    cov_matrix = np.cov(dataSet.T)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
+    diff_vector = input_vector - dataSet
+    mahalanobis_distances = np.sqrt(np.einsum('ij,jk,ik->i', diff_vector, inv_cov_matrix, diff_vector.T))
+    sorted_indices = mahalanobis_distances.argsort()
+    k_nearest_distances = mahalanobis_distances[sorted_indices[:k]]
     k_nearest_labels = labels[sorted_indices[:k]]
 
     # 计算权重（距离的倒数）