def learn(self, classAttr, unpruned=False, minNumObj=2):
self.instances = self._getInstances(classAttr)
j48 = J48()
j48.setUnpruned(unpruned)
j48.setMinNumObj(minNumObj)
#self.j48.setConfidenceFactor(1.0)
j48.buildClassifier(self.instances)
self.classifier = j48
print j48
def learn(self, classAttr, unpruned=False, minNumObj=2):
self.instances = self._getInstances(classAttr)
j48 = J48()
j48.setUnpruned(unpruned)
j48.setMinNumObj(minNumObj)
classifier = Bagging() #RandomForest()
classifier.setClassifier(j48)
classifier.buildClassifier(self.instances)
self.classifier = classifier
print classifier
def learn(self, classAttr, unpruned=False, minNumObj=2):
self.instances = self._getInstances(classAttr)
tree = J48() # DecisionStump() #J48
classifier = AdaBoostM1()
#classifier.setDebug(true);
classifier.setClassifier(tree)
#classifier.setNumIterations(50)
#self.j48.setConfidenceFactor(1.0)
classifier.buildClassifier(self.instances)
self.classifier = classifier
print "numIterations", classifier.getNumIterations()
print classifier
# 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) # create the model 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 j48 = J48() j48.buildClassifier(data) # only a trained classifier can be evaluated evaluation.evaluateModel(j48, data, [output, attRange, outputDistribution]) # print out the built model print "--> Generated model:\n" print j48 print "--> Evaluation:\n" print evaluation.toSummaryString() print "--> Predictions:\n" print buffer
# check commandline parameters
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 but filter out the name column first
bufsize = 0
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)
file.write("cf,rmse\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 x using full dataset
data.setClassIndex(data.numAttributes() - 1)
for num in [x * 0.05 for x in range(0, 10)]:
log.write("---------------------------------\nCF: " + str(num) + "\n")
algo = J48()
x = time.time()
algo.buildClassifier(data)
log.write("Time to build classifier: " + str(time.time() - x) + "\n")
algo.setConfidenceFactor(num)
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()
evaluation.evaluateModel(algo, data,
[output, attRange, outputDistribution])
#evaluation.crossValidateModel(algo, data, 10, rand, [output, attRange, outputDistribution])
filelimit.write("instances,pctincorrecttest,pctincorrecttrain\n")
logfile = "logs/" + classifiername + "_" + dataname + crossvalidate + ".log"
log=open(logfile, 'w', bufsize) # open general log file
timefilename = "data/plot/" + classifiername + "_" + dataname + crossvalidate + "_traintime.csv"
timefile = open(timefilename, 'w', bufsize)
timefile.write("instances,timetest,timetrain\n")
for num in range(int(p['adaboost.initial']),fulltrainset.numInstances(),(fulltrainset.numInstances() / int(p['adaboost.numdatapoints']))):
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")
filelimit.write(str(num))
timefile.write(str(num))
for dataset in [testset, fulltrainset]:
algo = AdaBoostM1()
weaklearner = J48()
algo.setClassifier(weaklearner)
algo.setNumIterations(int(p['adaboost.iterations']))
x = time.time()
algo.buildClassifier(trainset)
evaluation = Evaluation(trainset)
timefile.write("," + str(time.time() - x))
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])
# check commandline parameters
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)