From 2d89a0a7e3d40f7c5d4fe24b01b0711ea9754a07 Mon Sep 17 00:00:00 2001
From: 77 <3298722099@qq.com>
Date: Thu, 21 Nov 2024 09:00:12 +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 | 33 ++++++++++++++++++++++++---------
 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/function.py b/function.py
index 2393b3b..ad3460e 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 = "202210423201"
+name = "陈瑞琪祥"
 
 
 """
@@ -41,7 +41,9 @@ 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。
 
@@ -49,12 +51,29 @@ def classify0(inX, dataSet, labels, k=0):
     - inX (numpy array): 输入待分类的样本。
     - dataSet (numpy array): 训练数据集。
     - labels (list or numpy array): 训练集对应的标签。
-    - k (int): kNN 算法参数，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
+    - k (int): kNN 算法参数，默认值为 3。
 
     Returns:
     - int: 预测的分类标签。
     """
-
+    # 计算待分类样本与训练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 = sqDistances**0.5
+    
+    # 对距离进行排序，获取距离最近的 k 个样本的索引
+    sortedDistIndices = distances.argsort()
+    
+    # 提取距离最近的 k 个样本的标签
+    classCount = {}
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
+    
+    # 根据出现次数最多的标签来预测待分类样本的标签
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
 def load_data(file_path):
     """
@@ -65,12 +84,8 @@ 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))