更新 function.py

function.py

@@ -51,17 +51,21 @@ def classify0(inX, dataSet, labels,k=4):
     Returns:
     - int: 预测的分类标签。
     """
-    k=min(k,dataSet.shape[0])
+    # 计算每个训练样本与待分类样本之间的欧氏距离  
-    diffMat =np.tile(inX,(dataSet.shape[0],1))- dataSet
+    distances = [np.sqrt(np.sum((x_train - inX) ** 2)) for x_train in dataSet]  
-    sqDiffMat =diffMat **2
+      
-    distances =np.sqrt(sqDiffMat.sum(axis=1))
+    # 按距离排序，并获取最近的 k 个邻居的索引  
-    sortedDistIndicies=distances.argsort()
+    k_indices = np.argsort(distances)[:k]  
-    classCount={}
+      
-    for i in range(k):
+    # 获取这 k 个邻居的标签  
-        voteIlabel=labels[sortedDistIndicies[i]]
+    k_nearest_labels = [labels[i] for i in k_indices]  
-        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
+      
-    sortedClassCount = sorted(classCount.items(), key=lambda item: item[1], reverse=True)
+    # 统计每个标签出现的次数，并找出出现次数最多的标签  
-    return sortedclassCount[0][0]
+    from collections import Counter  
+    most_common = Counter(k_nearest_labels).most_common(1)  
+      
+    # 返回出现次数最多的标签  
+    return most_common[0][0]
 
 
 def load_data(file_path):