更新 function.py

function.py

@@ -1,6 +1,6 @@
 # function.py  
 import numpy as np  
-from collections import Counter
+
 """  
 挑战说明:  
 - 自行编写实现 KNN 分类算法。  
@@ -54,19 +54,28 @@ def classify0(inX, dataSet, labels, k=3):
     Returns:  
     - int: 预测的分类标签。  
     """  
-    # 计算输入向量与训练集中每一个样本的欧式距离
-    distances = np.sqrt(np.sum((dataSet - inX) ** 2, axis=1))
+    # 计算欧式距离  
+    dataSetSize = dataSet.shape[0]  
+    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet  
+    sqDiffMat = diffMat**2  
+    sqDistances = sqDiffMat.sum(axis=1)  
+    distances = np.sqrt(sqDistances)  
     
-    # 通过对距离进行升序排序并选择前k个最近距离的索引
-    nearest_neighbors_indices = distances.argsort()[:k]
+    # 按距离从小到大排序  
+    sortedDistIndices = distances.argsort()  
     
-    # 收集k个最近距离的样本的标签
-    nearest_labels = [labels[i] for i in nearest_neighbors_indices]
+    # 选择距离最小的k个点  
+    classCount = {}  
+    for i in range(k):  
+        voteIlabel = labels[sortedDistIndices[i]]  
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  
     
-    # 使用计数器查找出现频率最高的标签
-    most_common_label = Counter(nearest_labels).most_common(1)[C_0]()[C_0]()
+    # 按类别票数从大到小排序  
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)  
+    
+    # 返回出现频率最高的类别  
+    return sortedClassCount[0][0]  
 
-    return most_common_label
 
 def load_data(file_path):  
     """