def readFeature(num_features,type,select_feature,numtrees):
#filename1=resultFileTest
#filename2=resultFileTest2
filename1=resultFile+'_'+type+'_'+num_features+'_'+select_feature+'_train.csv'
filename2=resultFile+'_'+type+'_'+num_features+'_'+select_feature+'_test.csv'
#print filename1
loader=CSVLoader()
loader.setSource(File(filename1))
data=loader.getDataSet()
#print data.numAttributes()
data.setClassIndex(data.numAttributes()-1)
rf=RF()
rf.setNumTrees(numtrees)
rf.buildClassifier(data)
#print rf
loader.setSource(File(filename2))
test_data=Instances(loader.getDataSet())
test_data.setClassIndex(test_data.numAttributes()-1)
''' num=test_data.numInstances()
print num
for i in xrange(num):
r1=rf.distributionForInstance(test_data.instance(i))
r2=rf.classifyInstance(test_data.instance(i))
ptrixrint r1
print r2'''
buffer = StringBuffer() # buffer for the predictions
output=PlainText()
output.setHeader(test_data)
output.setBuffer(buffer)
attRange = Range() # attributes to output
outputDistribution = Boolean(True)
evaluator=Evaluation(data)
evaluator.evaluateModel(rf,test_data,[output,attRange,outputDistribution])
#print evaluator.evaluateModel(RF(),['-t',filename1,'-T',filename2,'-I',str(numtrees)])
#evaluator1=Evaluation(test_data)
print evaluator.toSummaryString()
print evaluator.toClassDetailsString()
print evaluator.toMatrixString()
return [evaluator.precision(1),evaluator.recall(1),evaluator.fMeasure(1),evaluator.matthewsCorrelationCoefficient(1),evaluator.numTruePositives(1),evaluator.numFalsePositives(1),evaluator.numTrueNegatives(1),evaluator.numFalseNegatives(1),evaluator.areaUnderROC(1)]
def load_arff(self, arff):
file = FileReader(arff)
#fis = FileInputStream(arff)
#file = InputStreamReader(fis, "UTF-8");
#fr = FileReader(arff)
#file = BufferedReader(fr)
data = Instances(file)
data.setClassIndex(data.numAttributes() - 1)
return data
weka.classifiers.Evaluation class)
"""
# check commandline parameters
if (not (len(sys.argv) == 2)):
print "Usage: UsingJ48Ext.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)
# create the model
evaluation = Evaluation(data)
buffer = StringBuffer() # buffer for the predictions
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, [buffer, attRange, outputDistribution])
# print out the built model
print "--> Generated model:\n"
print j48
print "--> Evaluation:\n"
sys.exit()
crossvalidate = sys.argv[2]
rand = Random() # seed from the system time
# load properties
p = Properties()
p.load(open('./ml.properties'))
# load data file
print "Loading data..."
trainfile = FileReader(sys.argv[1] + "-train.arff")
print "Loading " + sys.argv[1] + "-train.arff"
testfile = FileReader(sys.argv[1] + "-test.arff")
print "Loading " + sys.argv[1] + "-test.arff"
fulltrainset = Instances(trainfile)
fulltrainset.setClassIndex(fulltrainset.numAttributes() - 1)
testset = Instances(testfile)
testset.setClassIndex(testset.numAttributes() - 1)
# open output files
bufsize=0
classifiername = str(os.path.splitext(os.path.basename(__file__))[0])
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,pctincorrecttest,pctincorrecttrain\n")
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))
if (numReqOpt < 2):
usage()
return 1
options = {'idFlag':True, 'weightFlag': False, 'rmClassFlag': False, 'rmClass': 0}
# read the first dataset
fn = inputList[0]
fid = FileReader(fn)
Data = Instances(fid)
Data, IDs = PreprocessData(Data,options)
# remove class label
attributeremove = AttributeRemove()
attributeremove.setInvertSelection(Boolean(False)) # remove class labels from dataset
attributeremove.setAttributeIndices(String(str(Data.numAttributes())))
attributeremove.setInputFormat(Data)
newData = Filter.useFilter(Data, attributeremove)
# loop over input arff file
cnt = Data.numAttributes()
for fnCnt in range(1,len(inputList)):
fn = inputList[fnCnt]
fid = FileReader(fn)
Data = Instances(fid)
Data, IDs = PreprocessData(Data,options)
# remove class label
attributeremove = AttributeRemove()
attributeremove.setInvertSelection(Boolean(True)) # remove every attribute but the last one which is class label
attributeremove.setAttributeIndices(String(str(Data.numAttributes())))
attributeremove.setInputFormat(Data)
labels = Filter.useFilter(Data, attributeremove)
# load data file print "Loading data..." datafile = FileReader(sys.argv[1]) data = Instances(datafile) rand = Random() # seed from the system time data.randomize(rand) # randomize data with number generator # open output files bufsize=0 dataname = str(os.path.splitext(os.path.basename(sys.argv[1]))[0]) # loop for different amounts of data with fixed test set datasize = data.numInstances() limit = (datasize*2)/3 # loop until we use 2/3 data as training set testset = Instances(data,limit,datasize-limit) # create training set using the last 1/3 of data testset.setClassIndex(testset.numAttributes() - 1) saver = ArffSaver() saver.setInstances(testset) testsetfile = "./data/split/" + dataname + "-" + "test.arff" file = File(testsetfile) saver.setFile(file) saver.writeBatch() trainset = Instances(data,0,limit) # create training set saver = ArffSaver() saver.setInstances(trainset) trainsetfile = "./data/split/" + dataname + "-" + "train.arff" file = File(trainsetfile) saver.setFile(file) saver.writeBatch()
Based on this code example:
http://www.btbytes.com/2005/11/30/weka-j48-classifier-example-using-jython/
Commandline parameter(s):
first parameter must be the ARFF file one wants to process with J48
"""
# check commandline parameters
if (not (len(sys.argv) == 2)):
print "Usage: UsingJ48.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)
# create the model
print "Training J48..."
j48 = J48()
j48.buildClassifier(data)
# print out the built model
print "Generated model:\n"
print j48
print "Loading data..."
datafile = FileReader(sys.argv[1])
data = Instances(datafile)
rand = Random() # seed from the system time
data.randomize(rand) # randomize data with number generator
# open output files
bufsize = 0
dataname = str(os.path.splitext(os.path.basename(sys.argv[1]))[0])
# loop for different amounts of data with fixed test set
datasize = data.numInstances()
limit = (datasize * 2) / 3 # loop until we use 2/3 data as training set
testset = Instances(data, limit, datasize -
limit) # create training set using the last 1/3 of data
testset.setClassIndex(testset.numAttributes() - 1)
saver = ArffSaver()
saver.setInstances(testset)
testsetfile = "./data/split/" + dataname + "-" + "test.arff"
file = File(testsetfile)
saver.setFile(file)
saver.writeBatch()
trainset = Instances(data, 0, limit) # create training set
saver = ArffSaver()
saver.setInstances(trainset)
trainsetfile = "./data/split/" + dataname + "-" + "train.arff"
file = File(trainsetfile)
saver.setFile(file)
saver.writeBatch()
sys.exit()
crossvalidate = sys.argv[2]
rand = Random() # seed from the system time
# load properties
p = Properties()
p.load(open('./ml.properties'))
# load data file
print "Loading data..."
trainfile = FileReader(sys.argv[1] + "-train.arff")
print "Loading " + sys.argv[1] + "-train.arff"
testfile = FileReader(sys.argv[1] + "-test.arff")
print "Loading " + sys.argv[1] + "-test.arff"
fulltrainset = Instances(trainfile)
fulltrainset.setClassIndex(fulltrainset.numAttributes() - 1)
testset = Instances(testfile)
testset.setClassIndex(testset.numAttributes() - 1)
# open output files
bufsize = 0
classifiername = str(os.path.splitext(os.path.basename(__file__))[0])
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,letest,letrain,lmtest,lmtrain,kdtest,kdtrain,balltest,balltrain,covertest,covertrain\n"
)
logfile = "logs/" + classifiername + "_" + dataname + crossvalidate + ".log"
log = open(logfile, 'w', bufsize) # open general log file