k近邻算法识别手写数字Python实现

数据集：（参见python实战教程）

训练数据：trainingDigits 2000多个.txt文件

测试数据：testDigits  约900个.txt文件

均为32*32大小

test_handWritting.py：

from numpy import *
import os
import knnOperator
import pdb

def img2vector(filename,d): #d=32
returnVector = zeros((1,d*d))
fr = open(filename)
for i in range(d):
linstr = fr.readline()
for j in range(d):
returnVector[0,i*d+j] = int(linstr[j])
return returnVector

def handwritingClassTest(filepath,d):
trainFilePath = filepath + 'trainingDigits\\'
trainFileList = os.listdir(trainFilePath)
nTrain = len(trainFileList)
trainData = zeros((nTrain,d*d))
trainlabels = []
for i in range(nTrain):
trainFilei = trainFileList[i]
trainFileName = trainFilePath + trainFilei
vector = img2vector(trainFileName,d)
trainData[i,:] = vector
trainFileClass = trainFilei.split('_')[0]
trainlabels.append(trainFileClass)

testFilePath = filepath + 'testDigits\\'
testFileList = os.listdir(testFilePath)
nTest = len(testFileList)
k = 4
count = 0
for j in range(nTest):
#pdb.set_trace()
testFilej = testFileList[j]
testFileName = testFilePath + testFilej
testSample = img2vector(testFileName,d)
test_label = knnOperator.knnOperator(testSample,trainData,trainlabels,k)
truth_label = testFilej.split('_')[0]
if (truth_label == test_label):
count += 1
rate = float(count) / float(nTest)
print rate

knnOperator函数参见：http://blog.csdn.net/u013593585/article/details/51284537
主实现：

import test_handWritting
filepath = 'E:\\ZForWorks\\MLPython\\knn\\digits\\'
d = 32
handwritingClassTest(filepath,d)准确率：98.3%