def ccTopic():
(options, args) = parser.parse_args(sys.argv[1:]) #@UnusedVariable
dataset = options.dataset
nRowCluster = options.nRowCluster
nTopic = options.nTopic
ccType = options.ccType
kernelType = options.kernelType
nFold = options.nFold
nCodeword = options.nCodeword
beta = options.beta
if (options.verbose):
print dataset, nRowCluster, nTopic, ccType, kernelType, beta, nFold, nCodeword
print options
dataPath = rootDir + dataset + bofDir
catmap = getCatMap(dataset)
catList = catmap.keys()
dataext = str(nCodeword) + bofext
nCategory = len(catList)
perfMean = np.zeros(nCategory)
perfStd = np.zeros(nCategory)
for iCategory, catName in enumerate(catList):
fileName = dataPath + catName + dataext
catpos = np.genfromtxt(fileName, dtype=np.int)
if (options.verbose): print catName
catpos = catpos[:, :nCodeword + 1]
catpos[:, nCodeword] = 1
#read the category data of remaining classes
for cats in catList:
if (cats != catName):
firstvisit = True
if (firstvisit):
catneg = np.genfromtxt(fileName, dtype=np.int)
firstvisit = False
else:
catneg = np.concatenate(
(catneg, np.genfromtxt(fileName, dtype=np.int)),
axis=0)
#sample the negative data to have equal size as the positive
nPos = catpos.shape[0]
nNeg = catneg.shape[0]
catneg = catneg[np.random.randint(0, nNeg, nPos), :]
catneg = catneg[:, :nCodeword + 1]
catneg[:, nCodeword] = 0
#combine positive and negative data
bofData = np.concatenate((catpos, catneg), axis=0)
if (options.verbose):
print 'co-clustering...'
ccData = cocluster.coclust(bofData, dataset, nRowCluster, nTopic,
ccType)
ccCol = np.array([int(i) for i in ccData[1].split()])
tempCC = np.zeros((bofData.shape[0], nTopic))
for i in np.arange(bofData.shape[0]):
for j in sorted(set(ccCol)):
tempCC[i, j] = np.sum(bofData[i, ccCol == j])
botData = np.vstack((tempCC.T, bofData[:, -1])).T
if (options.verbose):
print 'classifying...'
#catPerfSVM = classify.ccClassify(botData, kernelType, nFold, beta, nMetrics)
catPerfKNN = classify.knnClassify(botData, 10, nFold, beta, nMetrics)
#perfMean[iCategory,0] = np.mean(catPerfSVM)
#perfStd[iCategory,0] = np.std(catPerfSVM)
perfMean[iCategory] = np.mean(catPerfKNN)
perfStd[iCategory] = np.std(catPerfKNN)
if (options.verbose):
print perfMean
print perfStd
return [perfMean, perfStd]
def ccUniversalTopicDictionary(wordn, topicn):
#acquire program agruments
(options, args) = parser.parse_args(sys.argv[1:]) #@UnusedVariable
dataset = options.dataset
nRowCluster = options.nRowCluster
ccType = options.ccType
#nCodeword = options.nCodeword
#nTopic = options.nTopic
nCodeword = wordn
nTopic = topicn
#echo arguments
if (options.verbose):
print dataset, nRowCluster, nTopic, ccType, nCodeword
print options
#configure data path and other parameters
dataPath = rootDir + dataset + imgWrdDir
resultPath = rootDir + dataset + utdDir + ccType + dataset
catmap = getCatMap(dataset)
catList = catmap.keys()
dataext = str(nCodeword) + imgWrdext
resultext = str(nCodeword) + str(nTopic) + utdext
resultFileName = resultPath + resultext
if (os.path.exists(resultFileName)):
print '%s already written' % (resultFileName)
return
#flag if incomplete data
incompleteData = False
for catName in catList:
iwmFileName = dataPath + catName + dataext
if (os.path.exists(iwmFileName) == False):
incompleteData = True
print '%s missing in %s,%d' % (catName, dataset, wordn)
return
else:
pass
# initialise empty iwm matrix and append each category to it
iwmData = None
for catName in catList:
iwmFileName = dataPath + catName + dataext
try:
iwmCatData = np.loadtxt(iwmFileName, dtype=np.int16, delimiter=' ')
if (options.verbose): print 'reading %s' % (iwmFileName)
except:
print 'unable to read %s' % (iwmFileName)
incompleteData = True
return
#stack the category data to the existing data-set data
if (iwmData == None):
iwmData = iwmCatData
else:
iwmData = np.concatenate((iwmData, iwmCatData), axis=0)
pass
if (incompleteData == False):
if (options.verbose): print 'co-clustering...'
ccData = coclust(iwmData, dataset, nRowCluster, nTopic, ccType)
# the indices of co-clusters columns
ccarray = ccData[1].split()
ccCol = np.array(ccarray, dtype=np.int16)
if (options.verbose): print 'writing %s' % (resultFileName)
np.savetxt(resultFileName, ccCol, fmt='%d', delimiter=' ')
else:
print 'incomplete data for %s' % (resultFileName)
def ccWord():
(options, args) = parser.parse_args(sys.argv[1:]) #@UnusedVariable
dataset = options.dataset
nRowCluster = options.nRowCluster
nColCluster = options.nColCluster
ccType = options.ccType
kernelType = options.kernelType
beta = options.beta
figfmt = options.figfmt
nFold = options.nFold
desc = options.desc
nClusterSample = options.nClusterSample
if (options.verbose):
print dataset, nRowCluster, nColCluster, ccType, kernelType, beta, figfmt, nFold, nClusterSample
dataPath = rootDir + dataset + dataDir
catmap = getCatMap(dataset)
catList = catmap.keys()
dataext = '.' + desc
nCategory = len(catList)
dim = descdim.get(desc)
nSamplePerCategory = int(np.round(nClusterSample / nCategory))
if (options.verbose): print 'collating cluster data...'
clusterData = collateClusterData(dataPath, dataext, catList,
nSamplePerCategory, dim)
if (options.verbose): print 'coclustering...'
ccData = cocluster.coclust(clusterData, dataset, nRowCluster, nColCluster,
ccType)
ccRow = np.array([int(i) for i in ccData[0].split()])
ccCol = np.array([int(i) for i in ccData[1].split()])
cctemp = np.zeros((clusterData.shape[0], nColCluster))
codebook = np.zeros((nRowCluster, nColCluster))
for i in np.arange(clusterData.shape[0]):
for j in sorted(set(ccCol)):
cctemp[i, j] = np.linalg.norm(clusterData[i, ccCol == j], 2)
for i in sorted(set(ccRow)):
codebook[i, :] = np.mean(cctemp[ccRow == i, :], 0)
if (options.verbose): print 'writing bof...'
writebof(dataset, catList, codebook, ccCol, nRowCluster, desc)
perfMean = np.zeros(nCategory)
perfStd = np.zeros(nCategory)
for iCategory, catName in enumerate(catList):
catboffilepath = rootDir + dataset + bofDir + catName + '_cc' + bofext
catpos = np.genfromtxt(catboffilepath, dtype=np.int) # catpos
catpos = catpos[:, :nColCluster + 1]
catpos[:, nColCluster] = 1
for catname in catList:
if (catname != catName):
firstvisit = True
catboffilepath = rootDir + dataset + bofDir + catname + '_cc' + bofext
if (firstvisit):
catneg = np.genfromtxt(catboffilepath, dtype=np.int)
firstvisit = False
else:
catneg = np.concatenate(
(catneg, np.genfromtxt(catboffilepath, dtype=np.int)),
axis=0)
nPos = catpos.shape[0]
nNeg = catneg.shape[0]
catneg = catneg[np.random.randint(0, nNeg, nPos), :] #catneg
catneg = catneg[:, :nColCluster + 1]
catneg[:, nColCluster] = 0
#combine positive and negative data
catData = np.concatenate((catpos, catneg), axis=0)
#shuffle the rows to aid in random selection of train and test
np.random.shuffle(catData)
catPerf = classify.ccClassify(catData, kernelType, nFold, beta,
nMetrics)
perfMean[iCategory] = np.mean(catPerf)
perfStd[iCategory] = np.std(catPerf)
if (options.verbose):
print perfMean
print perfStd
plotresult.ccPlot(dataset, catList, perfMean, perfStd, figfmt, 'BoW',
ccType)
