以Python代碼實(shí)例展示kNN算法的實(shí)際運(yùn)用_基礎(chǔ)知識(shí)

X1,1，X1,2，X1,3，X1,4……X1,36，X1,37，Y1
X2,1，X2,2，X2,3，X2,4……X2,36，X2,37，Y2
…………
X274,1，X274,2，X274,3，X274,4……X274,36，X274,37，Y274

0,0,0,3,1,34,5,0,0,0,11,31,0,0,38,40,0,0,15,8,3,9,14,2,3,0,4,1,1,15,0,0,1,13,0,0,1,1 0,1,0,2,2,24,8,0,0,0,10,37,0,0,44,34,0,0,3,0,4,10,15,5,3,0,0,7,2,13,0,0,2,12,0,0,0,0

#coding:utf-8

from numpy import *
import operator

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]

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)) #element wise divide
 return normDataSet, ranges, minVals

def file2matrix(filename):
 fr = open(filename)
 numberOfLines = len(fr.readlines()) #get the number of lines in the file
 returnMat = zeros((numberOfLines,37)) #prepare matrix to return
 classLabelVector = [] #prepare labels return 
 fr = open(filename)
 index = 0
 for line in fr.readlines():
 line = line.strip()
 listFromLine = line.split(',')
 returnMat[index,:] = listFromLine[0:37]
 classLabelVector.append(int(listFromLine[-1]))
 index += 1
 fr.close()
 return returnMat,classLabelVector

def genderClassTest():
 hoRatio = 0.10 #hold out 10%
 datingDataMat,datingLabels = file2matrix('doubanMovieDataSet.txt') #load data setfrom file
 normMat,ranges,minVals=autoNorm(datingDataMat)
 m = normMat.shape[0]
 numTestVecs = int(m*hoRatio)
 testMat=normMat[0:numTestVecs,:]
 trainMat=normMat[numTestVecs:m,:]
 trainLabels=datingLabels[numTestVecs:m]
 k=3
 errorCount = 0.0
 for i in range(numTestVecs):
 classifierResult = classify0(testMat[i,:],trainMat,trainLabels,k)
 print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])
 if (classifierResult != datingLabels[i]):
 errorCount += 1.0
 print "Total errors:%d" %errorCount
 print "The total accuracy rate is %f" %(1.0-errorCount/float(numTestVecs))