From e3fd53e88535f5da7afe15019d82204859956fa4 Mon Sep 17 00:00:00 2001
From: hao <19382120447@163.com>
Date: Mon, 14 Oct 2024 21:09:00 +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, 20 insertions(+), 8 deletions(-)

diff --git a/function.py b/function.py
index 2393b3b..6f1692f 100644
--- a/function.py
+++ b/function.py
@@ -25,8 +25,8 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
-name = "test_name"
+id = "202210423228"
+name = "黎世浩"
 
 
 """
@@ -41,7 +41,7 @@ name = "test_name"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=0):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -56,6 +56,23 @@ def classify0(inX, dataSet, labels, k=0):
     """
 
 
+# 计算待分类样本与数据集中每个样本的距离
+    distances = np.sqrt(np.sum((dataSet - inX) ** 2, axis=1))
+    
+    # 获取距离最近的k个样本的索引
+    sortedDistIndices = np.argsort(distances)
+    classCount = {}
+    
+    # 遍历距离最近的k个样本
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
+        # 统计每个类别的出现次数
+        classCount[voteIlabel] = classCount.getvoteIlabel, classCount.getvoteIlabel + 1)
+    
+    # 选择出现次数最多的类别作为预测标签
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
+
 def load_data(file_path):
     """
     加载 TSV 格式数据文件。
@@ -65,12 +82,7 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
-
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-
     train_file = "datingTrainSet2.tsv"
-
     train_data, train_labels = load_data(train_file)
-
     print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))