《机器学习实战》之k-近邻算法（手写识别系统）

这个玩意和改进约会网站的那个差不多，它是提前把所有数字转换成了32*32像素大小的黑白图，然后转换成字符图（用0,1表示），将所有1024个像素点用一维矩阵保存下来，这样就可以通过knn计算欧几里得距离来得到最接近的答案。

 import os
 import operator
 from numpy import *
 
 def classify0(inX, dataSet, labels, k):
     dataSetSize = dataSet.shape[0]
     diffMat = tile(inX, (dataSetSize,1)) - dataSet  #统一矩阵，实现加减
     sqDiffMat = diffMat**2
     sqDistances = sqDiffMat.sum(axis=1)  #进行累加，axis=0是按列，axis=1是按行
     distances = sqDistances**0.5  #开根号
     sortedDistIndicies = distances.argsort()  #按升序进行排序，返回原下标
     classCount = {}
     for i in range(k):
         voteIlabel = labels[sortedDistIndicies[i]]
         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  #get是字典中的方法，前面是要获得的值，后面是若该值不存在时的默认值
     sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
     return sortedClassCount[0][0]
 
 def img2vector(filename):
     f = open(filename)
     returnVect = zeros((1,1024))
     for i in range(32):
         line = f.readline()
         for j in range(32):
             returnVect[0,i*32+j] = int(line[j])
     return returnVect
 
 def handwritingClassTest():
     fileList = os.listdir('trainingDigits')
     m = len(fileList)
     traingMat = zeros((m, 1024))
     hwlabels = []
     for i in range(m):
         fileName = fileList[i]
         prefix = fileName.split('.')[0]
         number = int(prefix.split('_')[0])
         hwlabels.append(number)
         traingMat[i,:] = img2vector('trainingDigits/%s' %fileName)
     testFileList = os.listdir('testDigits')
     m = len(testFileList)
     errorNum = 0.0
     for i in range(m):
         testFileName = testFileList[i]
         prefix = testFileList[i].split('.')[0]
         realNumber = int(prefix.split('_')[0])
         testMat = img2vector('testDigits/%s' %testFileName)
         testResult = classify0(testMat, traingMat, hwlabels, 3)
         if testResult != realNumber:
             errorNum += 1
         print('The classifier came back with: %d, the real answer is: %d' %(testResult, realNumber))
     print('错误率为%f' %(errorNum/float(m)))
 
 if __name__ == '__main__':
     handwritingClassTest()