手写识别系统和前面的例子差不多,我们所需要做的就是把图数据转换成一维数组数据:
数据准备:
def img2vector(filename):
returnVect = zeros((1,1024))#创建一行1024列的数组
fr = open(filename)
for i in range(32):
lineStr = fr.readline()#按行读入数据
for j in range(32):
returnVect[0,32*i+j] = int(lineStr[j])#将字符型数字转换为整型
return returnVect
内容也比较容易,将二维数组循环读入,保存为一维行:
结果如下。
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
import kNN
testVector = kNN.img2vector(‘testDigits/0_13.txt’)
testVector[0,0:32]
array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0.])
测试算法
转换为一维的以后就和前面的一样了,
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir(‘trainingDigits’) #load the training set读取文件名
m = len(trainingFileList)#m等于文件的个数
trainingMat = zeros((m,1024))#建立m行1024列数组
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split(‘.’)[0] #take off .txt去掉.txt
classNumStr = int(fileStr.split(‘‘)[0])#前的数字,表示的就是该图对应的数字
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector(‘trainingDigits/%s’ % fileNameStr)
testFileList = listdir(‘testDigits’) #iterate through the test set
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)
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))
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the total number of errors is: 11
the total error rate is: 0.011628