python实现：K近邻算法改进约会网站匹配效果

#!/usr/bin/env python27
# -*- coding:utf-8 -*-
#K近邻算法改进约会网站匹配效果
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt
def createDataSet():
    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):
    dataSetSize = dataSet.shape[0]
    diffMat=tile(inX,(dataSetSize,1))-dataSet
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1)
    distances=sqDistances**0.5
    sortedDistIndicies=distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel =labels[sortedDistIndicies[i]]
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
    sortedClassCount = sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]
#group,labels=createDataSet()
#print(classify0([0.3,0.8],group,labels,3))

#将文本数据导出
def file2matrix(filename):
    fr=open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat=zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()#截取掉所有的回车符
        listFromLine=line.split()
        returnMat[index,:]=listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index +=1
    return returnMat,classLabelVector
#归一化特征值
def autoNorm(dataSet):
    minVals=dataSet.min(0)
    maxVals=dataSet.max(0)
    ranges=maxVals-minVals
    normDataSet=zeros(shape(dataSet))
    m=dataSet.shape[0]
    normDataSet = dataSet-tile(minVals,(m,1))
    normDataSet = normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals
def datingClassTest():
    hoRatio=0.10
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    m=normMat.shape[0]
    numTestVecs=int(m*hoRatio)#计算测试向量的数量
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],\
                                     datingLabels[numTestVecs:m],3)
        print "the classifier came back 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))#输出错误率
def classifyPerson():
    resultList=['not at all','in small doses','in large doses']
    percentTats = float(raw_input(\
        "percentage of time spent playing video games?"))
    iceCream=float(raw_input("liters of ice cream consumed per year?"))
    ffMiles=float(raw_input("frequent flier miles earned per year?"))
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    inArr=array([ffMiles,percentTats,iceCream])
    classifierResult=classify0((inArr-\
                                minVals)/ranges,normMat,datingLabels,3)
    print "You will probably like this person:  ",\
          resultList[classifierResult-1]
classifyPerson()
#datingClassTest()
#datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
#fig=plt.figure()
#ax=fig.add_subplot(111)
#ax.scatter(datingDataMat[:,1],datingDataMat[:,2],s=15.0*array(datingLabels),c=15.0*array(datingLabels))
#plt.show()
#print(datingDataMat)
#print(datingLabels)
#normMat,ranges,minVals=autoNorm(datingDataMat)
#print(normMat)
#print(ranges)
#print(minVals)