k-Nearest Neighbors(KNN)算法—程序和总结篇

下面是python3.4代码，我修改过。是根据《machine learning in action》中第二章的算法改变的。

from numpy import *
import operator
from os import listdir

def file2matrix(filename):
	fr = open(filename)
	numberOfLines = len(fr.readlines())
	returnMat = zeros((numberOfLines, 3))
	classLabelVector = []
	fr = open(filename)
	index = 0
	for line in fr.readlines():
		line = line.strip()
		listFromLine = line.split('\t')
		returnMat[index,:] = listFromLine[0:3]
		classLabelVector.append(str(listFromLine[3]))
		index += 1
	return returnMat, classLabelVector
#测试案例
def classifyPerson():
	resultList = ['not at all', 'in small doses', 'in large doses']
	percentTats = float(input("percentage of time spent playing video games?"))
	ffMiles = float(input("frequent filer miles earned per year?"))
	iceCream = float(input("liters of ice cream consumed per year?"))
	datingDataMat, datingLabels = file2matrix('D:\machinelearninginaction\Ch02\datingTestSet.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:  numbers of results:", resultList[2])
#简单的knn算法	
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.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

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 file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(str(listFromLine[3]))
        index += 1
    return returnMat,classLabelVector
#正规化    
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
#测试案例   
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('D:\machinelearninginaction\Ch02\datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    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: %s" % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    print (errorCount)
    
def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect
#测试案例
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('D:\\machinelearninginaction\\Ch02\\trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('D:\machinelearninginaction\Ch02\\trainingDigits\%s' % fileNameStr)
    testFileList = listdir('D:\\machinelearninginaction\\Ch02\\testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('D:\machinelearninginaction\Ch02\\testDigits\%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr))
        if (classifierResult != classNumStr): errorCount += 1.0
    print ("\nthe total number of errors is: %d" % errorCount)
    print ("\nthe total error rate is: %f" % (errorCount/float(mTest)))

在python3.4控制是台输入下面的代码进行测试：

>>>kNN.classify0([0,0], group, labels, 3)

>>> reload(kNN)
>>> datingDataMat,datingLabels = kNN.file2matrix('datingTestSet.txt')

>>> kNN.datingClassTest()

>>> kNN.classifyPerson()

>>> testVector = kNN.img2vector('testDigits/0_13.txt')

>>> kNN.handwritingClassTest()

下面的图片是我实现程序例子的部分图片：

总结：kNN是一个简单和有效的数据分类的算法。它是基于实例的机器学习算法，只是需要手边有数据进行学习。它需要遍历整个数据集，对于大量的数据，需要将待预测的一条数据同整个数据集中的每一条数据都要进行距离计算，这是有些棘手的（耗时），而且占用存储资源。

kNN的第一个缺点就是，我们对数据的底层结构（符合正态是还是伯努利分布）没有清晰的看法；而且，也不知道均值，和在某一个分类中的案例看起来应该有什么样的特点。