logfile = (
"logs/"
+ str(os.path.splitext(os.path.basename(__file__))[0])
+ "_"
+ str(os.path.splitext(os.path.basename(sys.argv[1]))[0])
+ "_tunable.log"
)
log = open(logfile, "w", bufsize) # open general log file
# loop for different values of c
data.setClassIndex(data.numAttributes() - 1)
for num in range(-10, 10, 2):
c = 2 ** (num)
file.write(str(c))
for kerneltype in range(0, 4):
algo = LibSVM()
tag = SelectedTag(
str(kerneltype), algo.TAGS_KERNELTYPE
) # 0 = linear, 1 = polynomial, 2 = radial basis function, 3 = sigmoid
algo.setKernelType(tag)
algo.setCost(c)
log.write("---------------------------------\nC: " + str(c) + ", KernelType: " + str(kerneltype) + "\n")
x = time.time()
algo.buildClassifier(data)
log.write("Time to build classifier: " + str(time.time() - x) + "\n")
evaluation = Evaluation(data)
output = PlainText() # plain text output for predictions
output.setHeader(data)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
sys.exit()
# load data file
print "Loading data..."
file = FileReader(sys.argv[1])
data = Instances(file)
# set the class Index - the index of the dependent variable
data.setClassIndex(data.numAttributes() - 1)
# define the algorithms to be used.
algo_list = [(NaiveBayes(), 'NaiveBayes'), (BayesNet(), 'BayesNet'),
(J48(), 'J48'), (JRip(), 'JRip'), (KStar(), 'KStar'),
(RandomForest(), 'RandomForest'), (AdaBoostM1(), 'AdaBoostM1'),
(MultilayerPerceptron(), 'MultilayerPerceptron'),
(LibSVM(), 'LibSVM')]
algo_dict = dict([(x[1], x[0]) for x in algo_list])
algo_keys = [
'NaiveBayes', 'J48', 'BayesNet', 'JRip', 'RandomForest', 'KStar',
'AdaBoostM1', 'LibSVM', 'MultilayerPerceptron'
]
# example to set kernal type on libsvm. Default is 2
#algo = algo_dict['LibSVM']
#tag = SelectedTag("1",algo.TAGS_KERNELTYPE) # 0 = linear, 1 = polynomial, 2 = radial basis function, 3 = sigmoid
#algo.setKernelType(tag)
# train classifiers but filter out the name column first
print "Training classifiers..."
for key in algo_keys:
algo = algo_dict[key]
logfile = "logs/" + classifiername + "_" + dataname + crossvalidate + ".log"
log = open(logfile, 'w', bufsize) # open general log file
for num in range(int(p['svm.initial']), fulltrainset.numInstances(),
(fulltrainset.numInstances() / int(p['svm.numdatapoints']))):
trainset = Instances(fulltrainset, 0, num) # create training set
trainset.setClassIndex(trainset.numAttributes() - 1)
filelimit.write(str(num))
for kerneltype in range(0, 4):
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 = 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)):
dataname = str(os.path.splitext(os.path.basename(sys.argv[1]))[0])
datafilelimit = "data/plot/" + classifiername + "_" + dataname + crossvalidate + "_instances.csv"
filelimit=open(datafilelimit, 'w', bufsize)
filelimit.write("instances,lineartest,lineartrain,polytest,polytrain,radialtest,radialtrain,sigmoidtest,sigmoidtrain\n")
logfile = "logs/" + classifiername + "_" + dataname + crossvalidate + ".log"
log=open(logfile, 'w', bufsize) # open general log file
for num in range(int(p['svm.initial']),fulltrainset.numInstances(),(fulltrainset.numInstances() / int(p['svm.numdatapoints']))):
trainset = Instances(fulltrainset,0,num) # create training set
trainset.setClassIndex(trainset.numAttributes() - 1)
filelimit.write(str(num))
for kerneltype in range(0,4):
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 = 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:
datafile = "data/plot/" + str(os.path.splitext(os.path.basename(__file__))[0]) + "_" + \
str(os.path.splitext(os.path.basename(sys.argv[1]))[0]) + "_rmse.csv"
file=open(datafile, 'w', bufsize) # open a file for rmse data
file.write("c,linear,polynomial,radial,sigmoid\n")
logfile = "logs/" + str(os.path.splitext(os.path.basename(__file__))[0]) + "_" + \
str(os.path.splitext(os.path.basename(sys.argv[1]))[0]) + "_tunable.log"
log=open(logfile, 'w', bufsize) # open general log file
# loop for different values of c
data.setClassIndex(data.numAttributes() - 1)
for num in range(-10,10,2):
c = 2 ** (num)
file.write(str(c))
for kerneltype in range(0,4):
algo = LibSVM()
tag = SelectedTag(str(kerneltype),algo.TAGS_KERNELTYPE) # 0 = linear, 1 = polynomial, 2 = radial basis function, 3 = sigmoid
algo.setKernelType(tag)
algo.setCost(c)
log.write("---------------------------------\nC: " + str(c) + ", KernelType: " + str(kerneltype) + "\n")
x = time.time()
algo.buildClassifier(data)
log.write("Time to build classifier: " + str(time.time() - x) + "\n")
evaluation = Evaluation(data)
output = PlainText() # plain text output for predictions
output.setHeader(data)
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 (not (len(sys.argv) == 2)):
print "Usage: supervised.py <ARFF-file>"
sys.exit()
# load data file
print "Loading data..."
file = FileReader(sys.argv[1])
data = Instances(file)
# set the class Index - the index of the dependent variable
data.setClassIndex(data.numAttributes() - 1)
# define the algorithms to be used.
algo_list = [(NaiveBayes(), 'NaiveBayes'), (BayesNet(),'BayesNet'), (J48(),'J48'), (JRip(), 'JRip'),
(KStar(), 'KStar'), (RandomForest(), 'RandomForest'), (AdaBoostM1(),'AdaBoostM1'),
(MultilayerPerceptron(),'MultilayerPerceptron'), (LibSVM(), 'LibSVM')]
algo_dict = dict([(x[1], x[0]) for x in algo_list])
algo_keys = ['NaiveBayes', 'J48', 'BayesNet', 'JRip', 'RandomForest', 'KStar', 'AdaBoostM1', 'LibSVM', 'MultilayerPerceptron']
# example to set kernal type on libsvm. Default is 2
algo = algo_dict['LibSVM']
tag = SelectedTag("1",algo.TAGS_KERNELTYPE) # 0 = linear, 1 = polynomial, 2 = radial basis function, 3 = sigmoid
algo.setKernelType(tag)
# train classifiers
print "Training classifiers..."
for key in algo_keys :
algo = algo_dict[key]
algo.buildClassifier(data)
# evaluate classifiers and print a result summary including confusion matrix