KNN近邻分类

from numpy import *
import operator
def createDataSet():#创建训练集
    group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels=['A','A','B','B']
    return group,labels
def classify0(inX,dataSet,labels,k):
    #index为输入 如[2,3],dataset为训练样本集,k为选择最近邻居的数目
    dataSetSize=dataSet.shape[0]  #行数
    diffMat=tile(inX,(dataSetSize,1))-dataSet
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1)#行向量相加
    distances=sqDistances**0.5  #计算欧氏距离
    sortedDisIndicies=distances.argsort() #距离由小到大的数组索引值,
    classCount={}
    for i in range(k):
        voteIlabel=labels[sortedDisIndicies[i]] #统计前k个点所在类别出现的频率
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
        sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)#按类别的频率书降序排列
        return sortedClassCount[0][0]#排第一的类别
group,labels=createDataSet()
myclass=classify0([0,0],group,labels,3)
print myclass

结果: B

# -*- coding:utf-8 -*-  
from numpy import *
import operator

def classify0(inX,dataSet,labels,k):
    #index为输入 如[2,3],dataset为训练样本集,k为选择最近邻居的数目
    dataSetSize=dataSet.shape[0]  #行数
    diffMat=tile(inX,(dataSetSize,1))-dataSet
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1)#行向量相加
    distances=sqDistances**0.5  #计算欧氏距离
    sortedDisIndicies=distances.argsort() #距离由小到大的数组索引值,
    classCount={}
    for i in range(k):
        voteIlabel=labels[sortedDisIndicies[i]] #统计前k个点所在类别出现的频率
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
        sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)#按类别的频率书降序排列
        return sortedClassCount[0][0]#排第一的类别

def file2matrix(filename):#数据处理
    fr=open(filename)
    arrayOfLines=fr.readlines()
    numberOfLines=len(arrayOfLines)
    returnMat=zeros((numberOfLines,3))
    classLabelVector=[]
    i=0
    for line in arrayOfLines:
        line=line.strip()
        listFromLine=line.split('\t')
        returnMat[i,:]=listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        i=i+1
    return returnMat,classLabelVector

def autoNorm(dataSet):#归一化特征值
    minValues=dataSet.min(0)
    maxValues=dataSet.max(0)
    DValues=maxValues-minValues
    normDataSet=zeros(shape(dataSet))
    m=dataSet.shape[0]
    normDataSet=dataSet-tile(minValues,(m,1))
    normDataSet=normDataSet/tile (DValues,(m,1))
    return normDataSet,DValues,minValues

def datingClassTest():#划分训练集和测试集
    hoRatio=0.1#10%用于test
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,Dvalues,minValues=autoNorm(datingDataMat)
    m=normMat.shape[0]
    numTestVecs=int(m*hoRatio)
    errorCount=0.0
    for i in range(numTestVecs):
        classifierResult=classify0(normMat[i,:],normMat[numTestVecs:,:],datingLabels[numTestVecs:],3)
        print "the classifier comeback with:%d,the real answer is:%d"%(classifierResult,datingLabels[i])
        if(classifierResult!=datingLabels[i]):
            errorCount+=1.0
    print "the total error rate is:%f"%(errorCount/float(numTestVecs))