From 8793a9b39cd0f83901f64bb1bb5da0790e8d950e Mon Sep 17 00:00:00 2001
From: yuhaopan <1159526601@qq.com>
Date: Thu, 26 Sep 2024 16:55:19 +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 | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/function.py b/function.py
index 33111b7..25f0261 100644
--- a/function.py
+++ b/function.py
@@ -38,7 +38,7 @@ name = "潘宇豪"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=5):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -51,24 +51,26 @@ def classify0(inX, dataSet, labels, k=5):
     返回值:
     - int: 预测的分类标签。
     """
-    # 计算输入样本与训练数据集中每个样本的欧氏距离
-    diffMat = np.tile(inX, (dataSet.shape[0], 1)) - dataSet
-    sqDiffMat = diffMat**2
-    sqDistances = sqDiffMat.sum(axis=1)
-    distances = np.sqrt(sqDistances)
+ # 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()
+    sortedDistIndices = distances.argsort()[:k]
+    
+    # 进行简单投票
     classCount = {}
-
-    for i in range(k):
-        voteIlabel = labels[sortedDistIndices[i]]
+    for i in sortedDistIndices:
+        voteIlabel = labels[i]
         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
-
+    
     # 返回出现次数最多的类别
     sortedClassCount = sorted(classCount.items(), key=lambda item: item[1], reverse=True)
     return sortedClassCount[0][0]
-
+    
 def load_data(file_path):
     """
     加载TSV格式的数据文件。