机器学习-KNN算法代码详解

from numpy import *
import operator
from os import listdir

def classify0(inX, dataSet, labels, k):  #inx 是输入的数据杭矩阵，dateset是已经知道标签的数据集，lables是该标签，k是距离最精需要比较的个数
    dataSetSize = dataSet.shape[0]          #获取训练数据的个数，在这里也是行数
    diffMat = tile(inX, (dataSetSize,1)) - dataSet          #将inx复制了datesetsize行，与训练矩阵相-
    sqDiffMat = diffMat**2                                      #将diffmat矩阵中的每个数平方
    sqDistances = sqDiffMat.sum(axis=1)                     #axis=1，将各自行中的数据求和，得到多行一列矩阵
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()                #从小到大排序，返回的是他们的索引
    classCount={}                                           #字典，key为v哦忒喇叭了，值为出现的次数
    for i in range(k):                                      #统计前k个距离最近的数据，统计相应标签出现的频次，并返回标签频次最高的训练数据的标签
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1#.get（）函数当voteilable存在时，返回他的值，不存在时返回默认的0
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)#key=1,以字典的值降序排列
    return sortedClassCount[0][0]#返回频次最高的标签






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()  #去除前后空格
        listFromLine = line.split('\t')#以tab将数据分开送给列表listfromline
        returnMat[index,:] = listFromLine[0:3]#将列表中的前3个数据送给returnmat
        classLabelVector.append(int(listFromLine[-1]))#将每行的最后一列追加给标签矩阵
        index += 1
    return returnMat,classLabelVector
    
def autoNorm(dataSet):                  #dateset 为多为矩阵
    minVals = dataSet.min(0)            #minvals是一行多列，每列的最小值组成
    maxVals = dataSet.max(0)            #maxvals是一行多列，每列的最大值组成
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]                #得到数据的行
    normDataSet = dataSet - tile(minVals, (m,1))
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals
   
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('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: %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))#将32*32的图像矩阵转换为1*1024的杭矩阵，此处创建他的容器
    fr = open(filename)
    for i in range(32):         #便利每一行
        lineStr = fr.readline()    #仅读取当前的一行
        for j in range(32):         #将该行中每一列的元素强制类型转换为int类型，并伏值给returnvec矩阵
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect


def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set  trainingDigits这是一个路径
    m = len(trainingFileList)                               #获取文件的各数
    trainingMat = zeros((m,1024))                           #每个文件代表举证中的一行
    for i in range(m):
        fileNameStr = trainingFileList[i]                               #得到文件名
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])                #将文件命中_之前的数字作为标签lables
        hwLabels.append(classNumStr)                            #将所有的文件名中得到的标签追加到hwlables中去
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)   #调用函数将所有文件中的内容转换为一行数据
    testFileList = listdir('testDigits')        #iterate through the test set得到测试序列目录下的文件名
    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('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)#括号内依次为测试用的单行数据；上一循环中得到的多行数据矩阵；以及他的标签列，k值等于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 number of errors is: %d" % (errorCount/float(mTest)))