k近邻算法的大概思路:
(1)求出需要预测类别的数据与每一个样本数据的距离,得出一个距离向量
(2)对距离向量中的元素从小到大排序,选出前k个元素
(3)找出前k个元素对应的标签,出现次数最多的标签即为它所属的类别。
用k近邻算法改进约会网站的配对效果
思路:
(1)从文本文件datingTestSet2.txt 中解析数据
(2)如果特征量的范围之间差的很多,则要对特征量进行归一化处理(减去最小值,再除以(最大值 - 最小值))
(3)用k近邻算法进行分类的预测
(4)测试代码,计算错误率
(5)输入数据,进行预测
代码如下:
from numpy import *
import operator
def file2matrix(filename):
fr=open(filename)
arrayOLines=fr.readlines()
m=len(arrayOLines)
returnMat=zeros((m,3))
labelVec=[]
index=0
for line in arrayOLines:
line=line.strip()
line=line.split('\t')
returnMat[index,:]=line[0:3]
labelVec.append(int(line[-1]))
index+=1
return returnMat, labelVec
def autoNorm(dataSet):
minVals=dataSet.min(0)
maxVals=dataSet.max(0)
ranges=maxVals-minVals
m=dataSet.shape[0]
normDataSet=(dataSet-tile(minVals, (m,1)))/tile(ranges, (m,1))
return normDataSet, minVals, ranges
def classify0(inX, dataSet, labelVec, k):
m=len(labelVec)
diffDis=(tile(inX, (m,1))-dataSet)**2
distances=diffDis.sum(axis=1)
sortedDistances=distances.argsort()
classCount={}
for i in range(k):
labels=labelVec[sortedDistances[i]]
classCount[labels]=classCount.get(labels,0)+1
sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
def datingClassTest():
hoRatio=0.10
returnMat, labelVec=file2matrix('datingTestSet2.txt')
normDataSet, minVals, ranges=autoNorm(returnMat)
m=len(labelVec)
numTestVecs=int(m*hoRatio)
errorCount=0.0
for i in range(numTestVecs):
classifierResult=classify0(returnMat[i,:],returnMat[numTestVecs:m,:],labelVec[numTestVecs:m],3)
print "the predict result is:%d, the real answer is: %d" %(classifierResult, labelVec[i])
if (classifierResult!=labelVec[i]): errorCount+=1.0
print "the total error rate is: %f" %(errorCount/float(numTestVecs))
def classifyPerson():
resultList=['not at all','in small doses','in large doses']
percentTats=float(raw_input("percentage of time spent playing video games?"))
ffMiles=float(raw_input("frequent fliter miles earned per year?"))
iceCream=float(raw_input("liters of ice cream consumed per year?"))
returnMat, labelVec=file2matrix('datingTestSet2.txt')
nromDataSet, minVals, ranges=autoNorm(returnMat)
inArr=array([percentTats, ffMiles, iceCream])
classifierResult=classify0((inArr-minVals)/ranges, returnMat, labelVec, 3)
print "you will probably like this person:", resultList[classifierResult-1]