1 #识别手写字体模块-图像转向量32x32 to 1x1024
2 def img2vector(filename):
3     returnVect = zeros((1,1024))
4     fr = open(filename)
5     for i in range(32):
6         lineStr = fr.readline()
7         for j in range(32):
8             returnVect[0,32*i+j] = int(lineStr[j])
9     return returnVect

 1 #---------------------------------------------
 2 #分类模块
 3 #@params
 4 #   inX:输入向量、手写体识别的测试向量
 5 #    dataSet:训练集样本、手写体识别的训练集向量
 6 #    labels:训练集对应的标签向量
 7 #    k:最近邻居数目、本实验为3
 8 #---------------------------------------------
 9 def classifiy0(inX, dataSet, labels, k):
10     dataSetSize = dataSet.shape[0]     #手写体样本集容量
11     #(以下三行)距离计算
12     diffMat = tile(inX, (dataSetSize,1)) - dataSet
13     sqDiffMat = diffMat**2
14     sqDistances = sqDiffMat.sum(axis=1)
15     distances = sqDistances**0.5   #欧氏距离开平方
16     sortedDistIndicies = distances.argsort()  #距离排序的索引排序
17     classCount = {}
18     #(以下两行)选择距离最小的k个点
19     for i in range(k):
20         voteIlabel = labels[sortedDistIndicies[i]]
21         classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
22     sortedClassCount = sorted(classCount.items(),
23     #排序
24     key = operator.itemgetter(1), reverse = True)
25     return sortedClassCount[0][0]            

 1 #手写识别的测试代码
 2 def handwritingClassTest():
 3     hwLabels = []
 4     trainingFileList = listdir(path='trainingDigits')  #获取目录内容
 5     m = len(trainingFileList)
 6     trainingMat = zeros((m,1024))
 7     for i in range(m):
 8         #一下三行，从文件名解析分类数字
 9         fileNameStr = trainingFileList[i]
10         fileStr = fileNameStr.split('.')[0]
11         classNumStr = int(fileStr.split('_')[0])
12
13         hwLabels.append(classNumStr)
14         trainingMat[i,:] = img2vector('trainingDigits/%s'%fileNameStr)
15     testFileList = listdir(path='testDigits')
16
17     errorCount = 0.0  #错误个数计数器
18     mTest = len(testFileList)
19
20     #从测试数据中提取数据
21     for i in range(mTest):
22         fileNameStr = testFileList[i]
23         fileStr = fileNameStr.split('.')[0]
24
25         classNumStr = int(fileStr.split('_')[0])
26         vectorUnderTest = img2vector('testDigits/%s'% fileNameStr)
27         classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
28
29         print("the classifier came back with:%d,the real answer is:%d"%(classifierResult,classNumStr))
30         if(classifierResult != classNumStr):
31             errorCount += 1.0
32  　 #输出结果
33     print("\nthe total number of errors is:%d"%errorCount)
34     print("\nthe total error rate is: %f"%(errorCount/float(mTest)))