#!/usr/bin/python

# -*- coding: utf-8 -*-

from numpy import *

import operator

def createDataSet():

    '创建数据集'

    group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,1.1]])

    labels=["A","A","B","B"]

    return group,labels

def classify(inX,dataSet,labels,k):

    # 获取维度

    dataSetSize=dataSet.shape[0]   # 训练数据集数量

    print dataSetSize

    print tile(inX,(dataSetSize,1))

    diffMat=tile(inX,(dataSetSize,1))-dataSet  # 测试样本的各维度的差值

    print diffMat

    sqDiffMat=diffMat**2  # 平方计算

    print sqDiffMat

    sqDistance=sqDiffMat.sum(axis=1)  # 输出每行的值

    print sqDistance

    distances=sqDistance**0.5   # 开方计算

    print distances

    sortedDistances=distances.argsort()   # 排序 按距离从小到大 输出索引

    print sortedDistances

    classCount={}

    for i in range(k):

        voteIlabel=labels[sortedDistances[i]]

        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1.0

    sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)

    return sortedClassCount[0][0]

group,labels=createDataSet()

res=classify([1,1],group,labels,3)

print res