logfile = "logs/" + classifiername + "_" + dataname + crossvalidate + ".log"
log=open(logfile, 'w', bufsize) # open general log file
for num in range(int(p['j48.initial']),fulltrainset.numInstances(),(fulltrainset.numInstances() / int(p['j48.numdatapoints']))):
filelimit.write(str(num))
trainset = Instances(fulltrainset,0,num) # create training set
trainset.setClassIndex(trainset.numAttributes() - 1)
log.write("---------------------------------\nTraining Set Size: " + str(trainset.numInstances()) + ", Test Set Size: " + str(testset.numInstances()) + ", Full data set size: " + str(fulltrainset.numInstances()) + "\n")
for dataset in [testset, fulltrainset]:
algo = J48()
algo.buildClassifier(trainset)
algo.setConfidenceFactor(float(p['j48.C']))
evaluation = Evaluation(trainset)
output = PlainText() # plain text output for predictions
output.setHeader(trainset)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
x = time.time()
if (int(crossvalidate)):
evaluation.crossValidateModel(algo, dataset, 10, rand, [output, attRange, outputDistribution])
else:
evaluation.evaluateModel(algo, dataset, [output, attRange, outputDistribution])
log.write("Time to evaluate model: " + str(time.time() - x) + "\n")
log.write(evaluation.toSummaryString())
filelimit.write("," + str(evaluation.pctIncorrect()))
filelimit.write("\n")
filelimit.close()
log.close()
str(fulltrainset.numInstances()) + "\n")
for dataset in [testset, fulltrainset]:
algo = LibSVM()
tag = SelectedTag(
str(kerneltype), algo.TAGS_KERNELTYPE
) # 0 = linear, 1 = polynomial, 2 = radial basis function, 3 = sigmoid
algo.setKernelType(tag)
algo.setCost(int(p['svm.C']))
algo.buildClassifier(trainset)
evaluation = Evaluation(trainset)
output = PlainText() # plain text output for predictions
output.setHeader(trainset)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
x = time.time()
if (int(crossvalidate)):
evaluation.crossValidateModel(
algo, dataset, 10, rand,
[output, attRange, outputDistribution])
else:
evaluation.evaluateModel(
algo, dataset, [output, attRange, outputDistribution])
log.write("Time to evaluate model: " + str(time.time() - x) + "\n")
log.write(evaluation.toSummaryString())
filelimit.write("," + str(evaluation.pctIncorrect()))
filelimit.write("\n")
filelimit.close()
log.close()
