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['mlp.initial']),fulltrainset.numInstances(),(fulltrainset.numInstances() / int(p['mlp.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(trainset.numInstances()))
timefile.write(str(num))
for dataset in [testset, fulltrainset]:
algo = MultilayerPerceptron()
algo.setTrainingTime(int(p['mlp.N']))
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])
else:
evaluation.evaluateModel(algo, dataset, [output, attRange, outputDistribution])
log.write("Time to evaluate model: " + str(time.time() - x) + "\n")
log.write(evaluation.toSummaryString())
str(os.path.splitext(os.path.basename(sys.argv[1]))[0]) + "_wall.csv"
filewall=open(wallfile, 'w', bufsize) # open a file for wall clock time
filewall.write("epochs,seconds\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 number of training epochs
data.setClassIndex(data.numAttributes() - 1)
for num in range(1,1000,50):
log.write("---------------------------------\nEpoch: " + str(num) + "\n")
algo = MultilayerPerceptron()
algo.setTrainingTime(num)
x = time.time()
algo.buildClassifier(data)
log.write("Time to build classifier: " + str(time.time() - x) + "\n")
filewall.write(str(num) + "," + 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()
#evaluation.evaluateModel(algo, data, [output, attRange, outputDistribution])
evaluation.crossValidateModel(algo, data, 10, rand, [output, attRange, outputDistribution])
log.write("Time to evaluate model: " + str(time.time() - x) + "\n")
log.write(evaluation.toSummaryString())
file.write(str(num) + "," + str(evaluation.rootMeanSquaredError()) + "\n")
if (not (len(sys.argv) == 3)):
print "Usage: weka.py <ARFF-file>"
sys.exit()
file = FileReader(sys.argv[1])
file2 = FileReader(sys.argv[2])
data = Instances(file)
test = Instances(file2)
data.setClassIndex(data.numAttributes() - 1)
test.setClassIndex(test.numAttributes() - 1)
evaluation = Evaluation(data)
buffer = StringBuffer()
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
nn = MultilayerPerceptron()
nn.buildClassifier(data) # only a trained classifier can be evaluated
#print evaluation.evaluateModel(nn, ['-t', sys.argv[1], '-T', sys.argv[2]])#;, [buffer, attRange, outputDistribution])
res = evaluation.evaluateModel(nn, test,
[buffer, attRange, outputDistribution])
f = open('predictions/' + data.relationName(), 'w')
for d in res:
f.write(str(d) + '\n')
f.close()
SerializationHelper.write("models/" + data.relationName() + ".model", nn)
# print out the built model
#print "--> Generated model:\n"
#print nn
for num in range(int(p['mlp.initial']), fulltrainset.numInstances(),
(fulltrainset.numInstances() / int(p['mlp.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(trainset.numInstances()))
timefile.write(str(num))
for dataset in [testset, fulltrainset]:
algo = MultilayerPerceptron()
algo.setTrainingTime(int(p['mlp.N']))
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])
else:
evaluation.evaluateModel(algo, dataset,
if (not (len(sys.argv) == 3)):
print "Usage: weka.py <ARFF-file>"
sys.exit()
file = FileReader(sys.argv[1])
file2 = FileReader(sys.argv[2])
data = Instances(file)
test = Instances(file2)
data.setClassIndex(data.numAttributes() - 1)
test.setClassIndex(test.numAttributes() - 1)
evaluation = Evaluation(data)
buffer = StringBuffer()
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
nn = MultilayerPerceptron()
nn.buildClassifier(data) # only a trained classifier can be evaluated
#print evaluation.evaluateModel(nn, ['-t', sys.argv[1], '-T', sys.argv[2]])#;, [buffer, attRange, outputDistribution])
res = evaluation.evaluateModel(nn, test, [buffer, attRange, outputDistribution])
f = open('predictions/' + data.relationName(), 'w')
for d in res:
f.write(str(d) + '\n');
f.close()
SerializationHelper.write("models/" + data.relationName() + ".model", nn)
# print out the built model
#print "--> Generated model:\n"
#print nn
#print "--> Evaluation:\n"
