From 485951645e2c81d00c1d5d3c0be6a5c24a936df2 Mon Sep 17 00:00:00 2001
From: yuhaopan <1159526601@qq.com>
Date: Thu, 26 Sep 2024 16:59:52 +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 | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/function.py b/function.py
index 25f0261..587fc93 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,6 @@
 # function.py
 import numpy as np
-
+from numpy.linalg import inv, det
 """
 挑战说明:
 - 自行编写实现 KNN 分类算法。
@@ -51,20 +51,22 @@ def classify0(inX, dataSet, labels, k=3):
     返回值:
     - int: 预测的分类标签。
     """
- # 计算协方差矩阵及其逆
-    covariance_matrix = np.cov(dataSet, rowvar=False)
-    inv_covmat = inv(covariance_matrix)
-
-    # 计算马氏距离
-    distances = np.array([mahalanobis(inX, dataSet[i], inv_covmat) for i in range(dataSet.shape[0])])
-
-    # 对距离进行排序并找到最近的k个邻居
-    sortedDistIndices = distances.argsort()[:k]
+    mean = np.mean(dataSet, axis=0) 
+    cov_inv = inv(np.cov(dataSet, rowvar=False))
     
-    # 进行简单投票
+    # 计算输入样本与每个训练样本之间的马氏距离
+    distances = []
+    for data in dataSet:
+        diff = inX - data
+        distance = np.sqrt(np.dot(np.dot(diff, cov_inv), diff.T))
+        distances.append(distance)
+    
+    # 对距离进行排序并找到最近的k个邻居
+    distances = np.array(distances)
+    sortedDistIndices = distances.argsort()
     classCount = {}
-    for i in sortedDistIndices:
-        voteIlabel = labels[i]
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
     
     # 返回出现次数最多的类别