KNN算法源码解析

''
Created on Sep 16, 2010
kNN: k Nearest Neighbors

Input:      inX: vector to compare to existing dataset (1xN)
            dataSet: size m data set of known vectors (NxM)
            labels: data set labels (1xM vector)
            k: number of neighbors to use for comparison (should be an odd number)

Output:     the most popular class label

@author: pbharrin
'''
from numpy import *
import operator
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]#得到数组的行数,即知道有几个训练数据.
    #tile:numpy中的函数.tile将原来的一个数组,扩充成了4个一样的数组.diffMat得到了目标与训练数值之间的差值.
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2#各个元素分别平方.
    sqDistances = sqDiffMat.sum(axis=1)#对应列相乘,即得到了每一个距离的平方.
    distances = sqDistances**0.5#开方,得到距离.
    sortedDistIndicies = distances.argsort()#升序排列.
    #选择距离最小的k个点.     
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        #排序
        #sorted(iterable[,cmp,[,key[,reverse=True]]])
#作用：Return a new sorted list from the items in iterable.
  #第一个参数是一个iterable，返回值是一个对iterable中元素进行排序后的列表(list)。
#可选的参数有三个，cmp、key和reverse。
#1)cmp指定一个定制的比较函数，这个函数接收两个参数（iterable的元素），如果第一个参数小于第二个参数，返回一个负数；如果第一个参数等于第二个参数，返回零；如果第一个参数大于第二个参数，返回一个正数。默认值为None。
#2)key指定一个接收一个参数的函数，这个函数用于从每个元素中提取一个用于比较的关键字。默认值为None。
#3)reverse是一个布尔值。如果设置为True，列表元素将被倒序排列。
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]
#创建数据集
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

#函数file2matrix把字符串转换为整数存入classLabelVector。
def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #获得文件的行数
    returnMat = zeros((numberOfLines,3))        #准备返回的矩阵
    classLabelVector = []                       #准备返回的标签   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()#去除文件空行
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

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))   #元素分割
    return normDataSet, ranges, minVals

def datingClassTest():
    hoRatio = 0.50      #拿出10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #从文件中加载数据集
    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: %d" % (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

def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #加载训练集
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #迭代测试集
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]    
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('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))