一个简单的K-近邻

import numpy
import operator

def createDateSet(): #定义数据集
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group, labels

group, labels = createDateSet()
def classify0(inX, dataSet, labels , k):
    dataSetSize = dataSet.shape[0] # 判断二维数组的行数，也就是标签/样本的个数
    diffMat = numpy.tile(inX, (dataSetSize, 1)) - dataSet #tile（[0,0],(4,1)）创建二维数组，[[0, 0],[0, 0],[0, 0],[0, 0]],减去原数组，获取差值
    print(diffMat)
    sqDiffMat = diffMat**2 #差值为矩阵，矩阵*矩阵,对应元素相乘
    print(sqDiffMat)
    sqDistance = sqDiffMat.sum(axis=1)#将一个矩阵的每一行元素相加
    print(sqDistance)
    distance = sqDistance**0.5 #[ 1.48660687  1.41421356  0.          0.1       ]
    print(distance)
    sortedDistIndicies= sqDistance.argsort()#argsort()返回从小到大的索引值 [2 3 1 0]
    print(sortedDistIndicies)
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 #classCount中如果有voteIlabel就+1，初始值为1（因为后边+1）。
        print(classCount)
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1), reverse = True) #降序排列，key用来提取用于比较的值
    return sortedClassCount[0][0]

classify0([0,0], group, labels, 3)