From 08e453bb46914da063bd90a25488cf3a6b768a5d Mon Sep 17 00:00:00 2001
From: heart20003 <1789588961@qq.com>
Date: Thu, 17 Oct 2024 00:15:30 +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 | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/function.py b/function.py
index 6489d55..797de6a 100644
--- a/function.py
+++ b/function.py
@@ -42,6 +42,7 @@ 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。
 
@@ -54,21 +55,28 @@ def classify0(inX, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
-    print
-
-
-def load_data(file_path):
-    """
-    加载 TSV 格式数据文件。
-    """
-    data = np.loadtxt(file_path, delimiter="\t")
-    features = data[:, :-1]
-    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
+    
+    # 计算输入样本与训练集中每个样本的欧氏距离
+    distances = np.sqrt(np.sum((dataSet - inX) ** 2, axis=1))
+    
+    # 获取距离最小的 k 个样本的索引
+    sorted_indices = np.argsort(distances)[:k]
+    
+    # 获取 k 个最近邻的标签
+    nearest_labels = [labels[i] for i in sorted_indices]
+    
+    # 统计 k 个最近邻中每个类别的出现次数
+    label_count = {}
+    for label in nearest_labels:
+        if label in label_count:
+            label_count[label] += 1
+        else:
+            label_count[label] = 1
+    
+    # 找到出现次数最多的标签
+    predicted_label = max(label_count, key=label_count.get)
+    
+    return predicted_label
 
     train_file = "datingTrainSet2.tsv"