Machine Learning in Action_CH2_3_使用kNN手写数字识别

from numpy import *
import operator
from os import listdir

# kNN
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0] # 获得向量第一维长度
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet # 纵向扩大dataSetSize倍
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1) # 按行求和
    distances = sqDistances ** 0.5
    sortedDistIndicies = distances.argsort() # 从小到大排序，返回的是索引值的列表
    classCount = {} # python字典
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 # 数频度，每次加1
    # 对字典进行排序
    # Python 2 才能使用classCount.iteritems()
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]

# 将32*32二进制图像矩阵转换为1*1024的向量
def img2vector(filename):
    fr = open(filename)
    returnVect = zeros((1, 1024))
    for i in range(32):
        # 每次读一行
        lineStr = fr.readline()
        # 错误
        # returnVect[32 * i, 32 * (i + 1)] = lineStr[0 : 32]
        for j in range(32):
            returnVect[0, 32 * i + j] = int(lineStr[j]) # 要强转为int类型，所以不能列表整体赋值
    return returnVect

# 手写数字识别系统
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits') # 得到一个列表
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0] # 将文件名截断
        classNameStr = int(fileStr.split('_')[0])
        hwLabels.append(classNameStr)
        trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
    errorCount = 0.0
    testFileList = listdir('testDigits')
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNameStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        # k=4时，errorrate=0.014799
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNameStr))
        if(classifierResult != classNameStr):
            errorCount += 1.0
    print("the total number of errors is: %d" % errorCount)
    print("the total error rate is: %f" % (errorCount / float(mTest)))

if __name__ == "__main__":
    # 测试img2vector函数
    testVector = img2vector('testDigits/0_0.txt')
    print(testVector[0, 0 : 32])
    print(testVector[0, 32 : 64])

    # 测试
    print("-------------测试开始--------------")
    handwritingClassTest()