更新 function.py

function.py

@@ -20,7 +20,22 @@ import numpy as np
 - Python: 3.10.12
 - numpy: 2.1.1
 """
-
+# 计算待分类样本与训练集中所有样本的欧氏距离  
+    distances = [np.sqrt(np.sum((x - inX) ** 2)) for x in dataSet]  
+      
+    # 根据距离排序，并获取前k个索引  
+    k_indices = np.argsort(distances)[:k]  
+      
+    # 获取前k个邻居的标签  
+    k_nearest_labels = [labels[i] for i in k_indices]  
+      
+    # 对标签进行投票，选择出现次数最多的标签  
+    from collections import Counter  
+    most_common = Counter(k_nearest_labels).most_common(1)  
+      
+    # 返回投票最多的标签  
+    return most_common[0][0]  
+  
 
 """
 请在这里填写学号和姓名，不填写即成绩无效。
@@ -41,7 +56,7 @@ name = "邓杰元"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=0):
+def classify0(inX, dataSet, labels, k=10):
     """
     KNN 分类算法。
 
@@ -69,8 +84,12 @@ def load_data(file_path):
 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))
+    train_file = "datingTrainSet2.tsv"  
+    test_file = "datingTestSet2.tsv"  
+  
+    train_data, train_labels = load_data(train_file)  
+    test_data, test_labels = load_data(test_file)  
+  
+    # 测试 classify0 函数  
+    # 注意：这里只是演示，实际评测会使用独立的测试集  
+    print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))