#-*- coding :utf-8-*-
from sklearn.neighbors import KNeighborsClassifier
from numpy import *

def createDataSet():
    group = array([[1.0,0.9],[1.0,1.0],[0.1,0.2],[0.0,0.1]])
    labels = [‘A‘,‘A‘,‘B‘,‘B‘]
    return group,labels
#用欧氏距离算的距离的大小
def kNNClassify(newInput,dataset,labels,K):
    numSample = dataset.shape[0] #dataset的行数
    diff = tile(newInput,(numSample,1)) - dataset  
    ‘‘‘
    格式：tile（A,reps） 
    * A：array_like 
    * 输入的array 
    * reps：array_like 
    * A沿各个维度重复的次数
    ‘‘‘
    squarediff = diff ** 2
    squaredis = sum(squarediff,axis = 1) #行之和
    distance = squaredis ** 0.5
    sortdistance = argsort(distance)
    classcount = {}
    for i in xrange(K):
        voteLable = labels[sortdistance[i]]
        classcount[voteLable] = classcount.get(voteLable,0) + 1

    maxCount = 0
    for key,values in classcount.items():
        if values > maxCount:
            maxCount = values
            index = key
    return index
#取前k个出现频率最高的作为预测结果返回

1 newInput表示的是输入的分类向量(1xN)  
2 dataset表示输入的训练样本集(NxM) 
3 labels表示标签向量
4 k表示选择最近邻居的数目