From d0fe2856a8a3f979f953b4bb4285772e1a8e34ef Mon Sep 17 00:00:00 2001
From: wujunjie <297081150@qq.com>
Date: Sun, 6 Oct 2024 18:22:49 +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 | 31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/function.py b/function.py
index 1908924..696ba1d 100644
--- a/function.py
+++ b/function.py
@@ -39,7 +39,7 @@ name = "吴俊煯"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels):
+def classify0(inX, dataSet, labels,k=4):
     """
     KNN 分类算法。
 
@@ -51,25 +51,16 @@ def classify0(inX, dataSet, labels):
     Returns:
     - int: 预测的分类标签。
     """
-# 获取数据集的大小
-    dataSetSize =dataSet.shape[0]
-# 计算数据集的协方差矩阵的逆
-    VI = np.linalg.inv(np.cov(dataSet.T))
-# 计算 Mahalanobis 距离
-    distances =np.zeros(dataSetSize)
-    for i in range(dataSetSize):
-        distances[i]=mahalanobis(inX,dataSet[i],VI)
-# 对距离排序，获取前 k 个最近的样本索引
-    sortedDistIndices=distances.argsort()
-# 统计前 k 个样本的标签
-    classCount ={}
-    for i in range(9):
-        voteLabel=labels[sortedDistIndices[i]]
-        classCount[voteLabel]=classCount.get(voteLabel,0)+1
-# 返回出现次数最多的标签
-    sortedClasscount=sorted(
-        classCount.items(), key=operator.itemgetter(1), reverse = True
-    )
+    k=min(k,dataSet.shape[0])
+    diffMat =np.tile(inX,(dataSet.shape[0],1))- dataSet
+    sqDiffMat =diffMat **2
+    distances =np.sqrt(sqDiffMat.sum(axis=1))
+    sortedDistIndicies=distances.argsort()
+    classCount={}
+    for i in range(k):
+        voteIlabel=labelssortedDistIndiciesi]]
+        classCount[voteIlabel]=classCount.get(voteIlabel，0)+1
+    sortedClassCount = sorted(classCount,items(), key=lambda item: item[1l. reverse=True)
     return sortedclassCount[0][0]