From c44940de9dac12a9f08e34997bdcd7a50a761c10 Mon Sep 17 00:00:00 2001
From: wujunjie <297081150@qq.com>
Date: Thu, 26 Sep 2024 11:01:36 +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 | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/function.py b/function.py
index 86aba4b..9c2a024 100644
--- a/function.py
+++ b/function.py
@@ -38,7 +38,7 @@ name = "吴俊煯"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels,k=4):
+def classify0(inX, dataSet, labels,k=3):
     """
     KNN 分类算法。
 
@@ -50,27 +50,23 @@ def classify0(inX, dataSet, labels,k=4):
     Returns:
     - int: 预测的分类标签。
     """
-    if dataSet.shape[0] == 0:  
-        raise ValueError("数据集为空")  
+    # 特征缩放  
+    scaler = StandardScaler()  
+    dataSet_scaled = scaler.fit_transform(dataSet)  
+    inX_scaled = scaler.transform(inX.reshape(1, -1))  
       
-    # 确保 k 不大于数据集的大小  
-    k = min(k, dataSet.shape[0])  
-      
-    # 计算测试样本与每个训练样本之间的距离  
-    diffMat = np.tile(inX, (dataSet.shape[0], 1)) - dataSet  
+    # KNN 分类  
+    dataSetSize = dataSet_scaled.shape[0]  
+    diffMat = np.tile(inX_scaled, (dataSetSize, 1)) - dataSet_scaled  
     sqDiffMat = diffMat ** 2  
     distances = np.sqrt(sqDiffMat.sum(axis=1))  
-      
-    # 对距离进行排序，并获取索引  
     sortedDistIndicies = distances.argsort()  
       
-    # 选择距离最小的k个点  
     classCount = {}  
     for i in range(k):  
         voteIlabel = labels[sortedDistIndicies[i]]  
         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  
       
-    # 多数投票  
     sortedClassCount = sorted(classCount.items(), key=lambda item: item[1], reverse=True)  
     return sortedClassCount[0][0]