From 4c7715a4b193cd253bc4fe18b90995253421a944 Mon Sep 17 00:00:00 2001
From: llll <2992513220@qq.com>
Date: Thu, 21 Nov 2024 09:17:12 +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 | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/function.py b/function.py
index d628e93..2cdfd8e 100644
--- a/function.py
+++ b/function.py
@@ -41,13 +41,15 @@ name = "李燕如"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=5):
+import numpy as np
+
+def classify0(inX, dataSet, labels, k=3):
     # 数据标准化
     dataSet = (dataSet - np.mean(dataSet, axis=0)) / np.std(dataSet, axis=0)
     inX = (inX - np.mean(dataSet, axis=0)) / np.std(dataSet, axis=0)
     
     # 计算距离
-    distances = np.sqrt(np.sum((dataSet - inX) ** 2, axis=1))
+    distances = [distance.euclidean(inX, x) for x in dataSet]
     
     # 获取k个最近邻的索引
     k_indices = np.argsort(distances)[:k]
@@ -55,14 +57,16 @@ def classify0(inX, dataSet, labels, k=5):
     # 获取这些样本对应的标签
     k_nearest_labels = labels[k_indices]
     
-    # 权重分配（距离的倒数）
-    weights = 1 / distances[k_indices]
-    weights /= np.sum(weights)  # 归一化权重
+    # 投票决定分类
+    result = {}
+    for label in k_nearest_labels:
+        if label in result:
+            result[label] += 1
+        else:
+            result[label] = 1
     
-    # 加权投票
-    prediction = np.argmax(np.bincount(k_nearest_labels, weights=weights))
-    
-    return prediction
+    # 返回出现次数最多的类别
+    return max(result, key=result.get)
 
 def load_data(file_path):
     data = np.loadtxt(file_path, delimiter="\t")