|
#coding=utf-8
from numpy import *
import operator
import os
import time
def createDataSet():
group = array([[1.0, 0.9], [1.0, 1.0], [0.1, 0.2], [0.0, 0.1]])
labels = ['A','A','B','B']
return group,labels
#inputX表示输入向量（也就是我们要判断它属于哪一类的）
#dataSet表示训练样本
#label表示训练样本的标签
#k是最近邻的参数，选最近k个
def kNNclassify(inputX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]#计算有几个训练数据
#开始计算欧几里得距离
diffMat = tile(inputX, (dataSetSize,1)) - dataSet
#diffMat = inputX.repeat(dataSetSize, aixs=1) - dataSet
sqDiffMat = diffMat ** 2
sqDistances = sqDiffMat.sum(axis=1)#矩阵每一行向量相加
distances = sqDistances ** 0.5
#欧几里得距离计算完毕
sortedDistance = distances.argsort()
classCount = {}
for i in xrange(k):
voteLabel = labels[sortedDistance[i]]
classCount[voteLabel] = classCount.get(voteLabel,0) + 1
res = max(classCount)
return res
def img2vec(filename):
returnVec = zeros((1,1024))
fr = open(filename)
for i in range(32):
lineStr = fr.readline()
for j in range(32):
returnVec[0,32*i+j] = int(lineStr[j])
return returnVec
def handwritingClassTest(trainingFloder,testFloder,K):
hwLabels = []
trainingFileList = os.listdir(trainingFloder)
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileName = trainingFileList[i]
fileStr = fileName.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vec(trainingFloder+'/'+fileName)
testFileList = os.listdir(testFloder)
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileName = testFileList[i]
fileStr = fileName.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vec(testFloder+'/'+fileName)
classifierResult = kNNclassify(vectorUnderTest, trainingMat, hwLabels, K)
#print classifierResult,' ',classNumStr
if classifierResult != classNumStr:
errorCount +=1
print 'tatal error ',errorCount
print 'error rate',errorCount/mTest
def main():
t1 = time.clock()
handwritingClassTest('trainingDigits','testDigits',3)
t2 = time.clock()
print 'execute ',t2-t1
if __name__=='__main__':
main()
|