更新 function.py

function.py

@@ -38,28 +38,6 @@ name = "吴俊煯"
 
 
 # 这里写自己的代码实现
-def euclidean_distance(instance1, instance2, length):  
-    """  
-    计算两个实例之间的欧几里得距离  
-    """  
-    distance = 0  
-    for x in range(length):  
-        distance += (instance1[x] - instance2[x]) ** 2  
-    return np.sqrt(distance)
-    
-def get_neighbors(train, test_row, k=4):  
-    """  
-    获取测试实例的 k 个最近邻  
-    """  
-    distances = []  
-    length = len(test_row) - 1  # 假设最后一列是标签  
-    for index in range(len(train)):  
-        dist = euclidean_distance(test_row, train[index], length)  
-        distances.append((train[index], dist))  
-    distances.sort(key=lambda tup: tup[1])  
-    neighbors = distances[:k]  
-    return neighbors
-
 def classify0(inX, dataSet, labels,k=4):
     """
     KNN 分类算法。
@@ -72,15 +50,24 @@ def classify0(inX, dataSet, labels,k=4):
     Returns:
     - int: 预测的分类标签。
     """
-    if dataSet.shape[0] == 0:  
-        raise ValueError("数据集为空")  
-    distances = get_neighbors(dataSet, inX, k)  
-    classVotes = {}  
-    for x in range(len(distances)):  
-        response = labels[distances[x][0][-1]]  # 假设最后一列是标签  
-        classVotes[response] = classVotes.get(response, 0) + 1  
-    sortedVotes = sorted(classVotes.items(), key=lambda x: x[1], reverse=True)  
-    return sortedVotes[0][0]
+    dataSetSize = dataSet.shape[0]  
+    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet  
+    sqDiffMat = diffMat ** 2  
+    sqDistances = sqDiffMat.sum(axis=1)  
+    distances = sqDistances ** 0.5  
+      
+    # 对距离进行排序，并获取索引  
+    sortedDistIndicies = distances.argsort()  
+      
+    # 选择距离最小的k个点  
+    classCount = {}  
+    for i in range(k):  
+        voteIlabel = labels[sortedDistIndicies[i]]  
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  
+      
+    # 多数投票  
+    sortedClassCount = sorted(classCount.items(), key=lambda item: item[1], reverse=True)  
+    return sortedClassCount[0][0]
 
 def load_data(file_path):
     """