def copyDataFile(options):
dataFileName = utils.getCDSDataFileName(options)
print dataFileName
dim = options['numberOfDimension']
if not os.path.exists(dataFileName):
print 'copyDataFile error:%s is not exists'%dataFileName
exit(-1)
command = 'cp %s kd_tree/data.txt'%dataFileName
utils.executeCommand(command)
print 'copyDataFile complete'
def copyDataFile(options):
dataFileName = utils.getCDSDataFileName(options)
print dataFileName
dim = options['numberOfDimension']
if not os.path.exists(dataFileName):
print 'copyDataFile error:%s is not exists' % dataFileName
exit(-1)
command = 'cp %s kd_tree/data.txt' % dataFileName
utils.executeCommand(command)
print 'copyDataFile complete'
def convertNDDSToCDS(options):
size = options['numberOfData']
dim = options['numberOfDimension']
distribution = options['distribution']
cardinality = options['numberOfAlphabet']
numberOfVP = options['numberOfVP']
typeOfVP = options['typeOfVP']
dataFileName = 'data/data_%d_%d_%s_%d.txt' % (size, dim, distribution,
cardinality)
queryFileName = 'query/query_%d_%d_%s_%d.txt' % (size, dim, distribution,
cardinality)
vpFileName = 'vp/vp_%d_%d_%d_%s.txt' % (dim, numberOfVP, cardinality,
typeOfVP)
cdsDataFileName = utils.getCDSDataFileName(options)
cdsQueryFileName = utils.getCDSQueryFileName(options)
# cdsDataFileName = 'cds_data/data_%d_%d_%s_%d_%s.txt'%(size,numberOfVP,distribution,cardinality,typeOfVP)
# cdsQueryFileName = 'cds_query/query_%d_%d_%s_%d_%s.txt'%(size,numberOfVP,distribution,cardinality,typeOfVP)
datas = utils.getDataInFile(dataFileName)
querys = utils.readDataFromFile(queryFileName)
vps = utils.readDataFromFile(vpFileName)
print len(datas), len(querys), len(vps)
cdsDatas = []
for i in xrange(len(datas)):
t = []
for j in xrange(len(vps)):
t.append(utils.hammingDistance(datas[i], vps[j]))
cdsDatas.append(t)
utils.writeDataToFile(cdsDataFileName, cdsDatas)
cdsQuerys = []
for i in xrange(len(querys)):
t = []
for j in xrange(len(vps)):
t.append(utils.hammingDistance(querys[i], vps[j]))
cdsQuerys.append(t)
utils.writeDataToFile(cdsQueryFileName, cdsQuerys)
print cdsDataFileName, cdsQueryFileName
def convertNDDSToCDS(options):
size = options['numberOfData']
dim = options['numberOfDimension']
distribution = options['distribution']
cardinality = options['numberOfAlphabet']
numberOfVP = options['numberOfVP']
typeOfVP = options['typeOfVP']
dataFileName = 'data/data_%d_%d_%s_%d.txt'%(size,dim,distribution,cardinality)
queryFileName = 'query/query_%d_%d_%s_%d.txt'%(size,dim,distribution,cardinality)
vpFileName = 'vp/vp_%d_%d_%d_%s.txt'%(dim,numberOfVP,cardinality,typeOfVP)
cdsDataFileName = utils.getCDSDataFileName(options)
cdsQueryFileName= utils.getCDSQueryFileName(options)
# cdsDataFileName = 'cds_data/data_%d_%d_%s_%d_%s.txt'%(size,numberOfVP,distribution,cardinality,typeOfVP)
# cdsQueryFileName = 'cds_query/query_%d_%d_%s_%d_%s.txt'%(size,numberOfVP,distribution,cardinality,typeOfVP)
datas = utils.getDataInFile(dataFileName)
querys = utils.readDataFromFile(queryFileName)
vps = utils.readDataFromFile(vpFileName)
print len(datas),len(querys),len(vps)
cdsDatas = []
for i in xrange(len(datas)):
t = []
for j in xrange(len(vps)):
t.append(utils.hammingDistance(datas[i],vps[j]))
cdsDatas.append(t)
utils.writeDataToFile(cdsDataFileName,cdsDatas)
cdsQuerys = []
for i in xrange(len(querys)):
t = []
for j in xrange(len(vps)):
t.append(utils.hammingDistance(querys[i],vps[j]))
cdsQuerys.append(t)
utils.writeDataToFile(cdsQueryFileName,cdsQuerys)
print cdsDataFileName, cdsQueryFileName
