def classification(trainingName, positiveTestName, negativeTestName, cod, lenPositiveTraining, lenNegativeTraining, techniqueLow, techniqueMid):
#AUCs = open("referral/AUCs.txt","wb")
directory = "referral/" + techniqueLow + "/" + techniqueMid + "/classification/"
start = timeit.default_timer()
# define some variables
resultFileTrain = directory + "/resultTrain.dat"
scaledTraining = trainingName + ".scale"
model = directory + "/referral-" + cod + ".model"
scaledNegativeTest = negativeTestName + ".scale"
scaledPositiveTest = positiveTestName + ".scale"
resultFileNegative = directory + "/resultNegative" + cod + ".dat"
resultFilePositive = directory + "/resultPositive" + cod + ".dat"
rangeFile = directory + "/range-" + cod
# Scale the training data
command = SVM + "svm-scale -l -1 -u +1 -s " + rangeFile + " " + trainingName + " > " + scaledTraining
os.system(command)
# Escala os dados de teste das normais
command = SVM + "svm-scale -r " + rangeFile + " " + negativeTestName + " > " + scaledNegativeTest
os.system(command)
# Escala os dados de teste das doentes
command = SVM + "svm-scale -r " + rangeFile + " " + positiveTestName + " > " + scaledPositiveTest
os.system(command)
# Run the grid-search
print('Cross validation...')
cmd = '%s -svmtrain "%s" -gnuplot "%s" "%s"' % (SVM + "grid.py", SVM + "svm-train", "/usr/bin/gnuplot", scaledTraining)
os.system(cmd + " > tmp/info-referral-" + techniqueLow + "-" + techniqueMid + "-" + cod + ".txt 2> tmp/errors.txt")
line = open("tmp/info-referral-" + techniqueLow + "-" + techniqueMid + "-" + cod + ".txt","rb").readlines()
last_line = line[-1:][0]
c,g,rate = map(float,last_line.split())
print('Best c=%s, g=%s CV rate=%s' % (c,g,rate))
wnormais = (float(lenPositiveTraining/float(lenPositiveTraining + lenNegativeTraining)) * 2.0)
wdoentes = (2.0 - wnormais)
# Train the classifier
command = SVM + "svm-train -t 2 -c " + str(c) + " -g " + str(g) + " -w1 " + str(wdoentes) + " -w-1 " + str(wnormais) + " " + scaledTraining + " " + model
os.system(command + " > tmp/info.txt 2> tmp/errors.txt")
# Classify the training images
command = SVM + "svm-predict " + scaledTraining + " " + model + " " + resultFileTrain
os.system(command + " > tmp/info.txt 2> tmp/errors.txt")
# Classify the negative test images
command = SVM + "svm-predict " + scaledNegativeTest + " " + model + " " + resultFileNegative
os.system(command + " > tmp/info.txt 2> tmp/errors.txt")
# Classify the positive test images
command = SVM + "svm-predict " + scaledPositiveTest + " " + model + " " + resultFilePositive
os.system(command + " > tmp/info.txt 2> tmp/errors.txt")
# Shift the hyperplan
numberOfPoints = 500
# Record the offsets to allow a future choice of most adequate operating point
shifts = []
result = open(resultFileTrain,"rb").readlines()
upperBound = -9999999999
lowerBound = 9999999999
for i in result:
temp = i.split("\n")
res = float(temp[0])
if res > upperBound: upperBound = res
if res < lowerBound: lowerBound = res
interval = upperBound - lowerBound
variationFactor = interval/numberOfPoints
limiar = lowerBound
negativeResults = open(resultFileNegative,"rb").readlines()
positiveResults = open(resultFilePositive,"rb").readlines()
valuesOut = []
numero_tics = 0
while ((limiar <= upperBound) and (numero_tics < numberOfPoints)):
numero_tics = numero_tics + 1
acertosNormais = 0
acertosDoentes = 0
for i in negativeResults:
temp = i.split("\n")
res = float(temp[0])
if res <= limiar: acertosNormais = acertosNormais + 1
for i in positiveResults:
temp = i.split("\n")
res = float(temp[0])
if res > limiar: acertosDoentes = acertosDoentes + 1
shifts.append(limiar)
line = str(acertosNormais) + "\t" + str(acertosDoentes) + "\t\n"
valuesOut.append(line)
limiar = limiar + variationFactor
arqout = open(directory + "/operating-points-" + cod + ".dat","wb")
arqout.seek(0)
for i in valuesOut:
arqout.write(i)
arqout.close()
# Scale the operating points and calculate the area under the ROC curve (AUC)
lines = open(directory + "/operating-points-" + cod + ".dat", "rb").readlines()
max_x = -9999999999.0
max_y = -9999999999.0
for line in lines:
line = line.split()
x = float(line[0])
y = float(line[1])
if (x > max_x): max_x = x
if (y > max_y): max_y = y
x = []
y = []
last_x = -1
last_y = -1
operatingPointsFile = open(directory + "/operating-points-" + cod + "-scale.dat", "wb")
shiftsSensSpec = []
shiftsSensSpecFile = open(directory + "/shifts-sens-spec-" + cod + ".dat", "wb")
indShifts = 0
for line in lines:
line = line.split()
xx = 1 - float(line[0])/float(max_x)
yy = float(line[1])/float(max_y)
if xx != last_x or yy != last_y:
x.append(xx)
y.append(yy)
last_x = xx
last_y = yy
operatingPointsFile.write(str(xx) + "\t" + str(yy) + "\n")
if xx <= 0.5 and yy > 0.5:
shiftsSensSpec.append((str(shifts[indShifts]), " {0:0.1f}%".format(yy*100), " {0:0.1f}%".format((1-xx)*100)))
indShifts += 1
operatingPointsFile.close()
sens_aux = ""
(last_shift, last_sens, last_spec) = shiftsSensSpec[0]
for (shift, sens, spec) in shiftsSensSpec[1:]:
if sens != last_sens:
shiftsSensSpecFile.write(last_shift + " " + last_sens + " " + last_spec + "\n")
if spec == " 100.0%": break
last_shift = shift
last_sens = sens
last_spec = spec
shiftsSensSpecFile.write(shift + " " + sens + " " + spec + "\n")
shiftsSensSpecFile.close()
stop = timeit.default_timer()
print "Model created in " + common_functions.convertTime(stop - start)
auc = np.trapz(y, x) * -100
print u"AUC = {0:0.1f}%\n\n".format(auc)
#AUCs.write(u"\nAUC = {0:0.1f}%\n\n".format(auc))
# Clear
name = trainingName.split("/")[-1:][0]
if os.path.exists(name + ".scale.png"):
os.system("rm " + name + ".scale.png")
if os.path.exists(name + ".scale.out"):
os.system("rm " + name + ".scale.out")
return u"\nAUC = {0:0.1f}%\n\n".format(auc)
# run k-means
start = timeit.default_timer()
if technique == "sparse":
os.system(KMEANS + " -i codebooks/" + technique + "/" + str(size) +
"-codewords-" + lesion + ".in -o codebooks/" +
technique + "/codebook-" + lesion + ".cb")
else:
for diametro in [12, 19, 31, 50, 80, 128]:
radius = diametro / 2.0
os.system(KMEANS + " -i codebooks/" + technique + "/" +
str(size) + "-codewords-" + lesion + "-" +
str(radius) + ".in -o codebooks/" + technique +
"/codebook-" + lesion + "-" + str(radius) + ".cb")
stop = timeit.default_timer()
sys.stdout.write(" - codebook created in " +
common_functions.convertTime(stop - start) + "\n")
sys.stdout.flush()
for lesion in lesions:
if lesion == "imagem-normal": continue
sys.stdout.write("Concatenating the codebooks")
sys.stdout.flush()
start = timeit.default_timer()
for technique in techniques:
if not sizeFlag: # if the used did not pass a size, use the default
if technique == "sparse":
size = 250 # 250 * 2 (normal and disease) = 500
else:
size = 125 # 125 * 2 (normal and disease) * 6 (scales) = 1500
common_functions.mergeCodebooks(lesion, size, technique)
stop = timeit.default_timer()
else: listImages = [image]
for im in listImages:
im_special = common_functions.specialName(im)
if os.path.exists(OutDir + im[:-3] + "hist"): continue
# define the output file (histogram)
OutFile = OutDir + im[:-3] + "hist"
f = open(OutFile,"wb")
# get the points of interest
PoIsTemp = open(PoIsDir + im[:-3] + "key","rb").readlines()
PoIs = []
for i in range(2,len(PoIsTemp),2):
PoIs.append([ float(p) for p in PoIsTemp[i].split() ])
PoIs = numpy.asarray(PoIs)
sys.stdout.write(". ")
sys.stdout.flush()
if techniqueMid == "hard":
hardSum(PoIs, Codebook, OutFile, size, label)
elif techniqueMid == "soft":
softMax(PoIs, Codebook, OutFile, size, label)
else: #if techniqueMid == "semi":
semiSoft(PoIs, Codebook, OutFile, size, label)
stop = timeit.default_timer()
sys.stdout.write(" Done in " + common_functions.convertTime(stop - start) + "\n")
################################################
"key")
common_functions.filterPoints(type, technique, im)
else:
denseExtraction(
im, im_special, technique, type,
"datasets/" + type + "-images-by-lesions/" +
common_functions.specialName(lesion_en))
common_functions.organizeFileSurfToDescriptor(directory +
technique +
"/" + type +
"/" +
im[:-3] +
"key")
stop = timeit.default_timer()
sys.stdout.write(common_functions.convertTime(stop - start) + "\n")
################################################
################################################
# Describe additional images
# (with marked regions but not labeled as normal or disease)
# Only when DR1 is defined as the training dataset
################################################
if train == "DR1":
print "Low-level feature extraction for additional images (DR1) - used just because contain marked regions"
start = timeit.default_timer()
listImages = os.listdir("datasets/DR1-additional-marked-images/")
for im in listImages:
sys.stdout.write(". ")
listImages = os.listdir("datasets/" + type + "-images-by-lesions/" + lesion_en)
else: listImages = [image]
for im in listImages:
im_special = common_functions.specialName(im)
if os.path.exists(OutDir + im[:-3] + "hist"): continue
# define the output file (histogram)
OutFile = OutDir + im[:-3] + "hist"
f = open(OutFile,"wb")
# get the points of interest
PoIsTemp = open(PoIsDir + im[:-3] + "key","rb").readlines()
PoIs = []
for i in range(2,len(PoIsTemp),2):
PoIs.append([ float(p) for p in PoIsTemp[i].split() ])
PoIs = numpy.asarray(PoIs)
sys.stdout.write(". ")
sys.stdout.flush()
if techniqueMid == "hard":
hardSum(PoIs, Codebook, OutFile, size, label)
else: # techniqueMid == "soft":
softMax(PoIs, Codebook, OutFile, size, label)
stop = timeit.default_timer()
sys.stdout.write(" Done in " + common_functions.convertTime(stop - start) + "\n")
################################################
candidatesFile.close()
else: common_functions.getCandidateRegions(lesion, train, technique)
# define the parameters of k-means
common_functions.adjustParametersKmeans(lesion, size, technique)
# run k-means
start = timeit.default_timer()
if technique == "sparse":
os.system(KMEANS + " -i codebooks/" + technique + "/" + str(size) + "-codewords-" + lesion + ".in -o codebooks/" + technique + "/codebook-" + lesion + ".cb")
else:
for diametro in [12, 19, 31, 50, 80, 128]:
radius = diametro/2.0
os.system(KMEANS + " -i codebooks/" + technique + "/" + str(size) + "-codewords-" + lesion + "-" + str(radius) + ".in -o codebooks/" + technique + "/codebook-" + lesion + "-" + str(radius) + ".cb")
stop = timeit.default_timer()
sys.stdout.write(" - codebook created in " + common_functions.convertTime(stop - start) + "\n")
sys.stdout.flush()
for lesion in lesions:
if lesion == "imagem-normal": continue
sys.stdout.write("Concatenating the codebooks")
sys.stdout.flush()
start = timeit.default_timer()
for technique in techniques:
if not sizeFlag: # if the used did not pass a size, use the default
if technique == "sparse": size = 250 # 250 * 2 (normal and disease) = 500
else: size = 125 # 125 * 2 (normal and disease) * 6 (scales) = 1500
common_functions.mergeCodebooks(lesion, size, technique)
stop = timeit.default_timer()
sys.stdout.write(" - done in " + common_functions.convertTime(stop - start) + "\n")
im_special = common_functions.specialName(im)
for technique in techniques:
if os.path.exists(directory + technique + "/" + type + "/" + im[:-3] + "key"): continue
fAux = open(directory + technique + "/" + type + "/" + im[:-3] + "key","wb")
if technique == "sparse":
sparseExtraction(im_special, technique, type, "datasets/" + type + "-images-by-lesions/" + common_functions.specialName(lesion_en))
common_functions.organizeFileSurfToDescriptor(directory + technique + "/" + type + "/" + im[:-3] + "key")
common_functions.filterPoints(type, technique, im)
else:
denseExtraction(im, im_special, technique, type, "datasets/" + type + "-images-by-lesions/" + common_functions.specialName(lesion_en))
common_functions.organizeFileSurfToDescriptor(directory + technique + "/" + type + "/" + im[:-3] + "key")
stop = timeit.default_timer()
sys.stdout.write(common_functions.convertTime(stop - start) + "\n")
################################################
################################################
# Describe additional images
# (with marked regions but not labeled as normal or disease)
# Only when DR1 is defined as the training dataset
################################################
if train == "DR1":
print "Low-level feature extraction for additional images (DR1) - used just because contain marked regions"
start = timeit.default_timer()
listImages = os.listdir("datasets/DR1-additional-marked-images/")
