if __name__ == '__main__' :
# for loading the existing data set pickle
# pickledata = open('pickledata','rb')
# attrs = pickle.load(pickledata)
# data = pickle.load(pickledata)
# for loading the new data set
# dataset = 'tennis.arff'
# dataset = 'restaurant.arff'
dataset = 'breast-cancer.arff'
# dataset = 'nursery.arff'
# dataset = 'lymphography.arff'
attrs, data = readARFF.readArff(open(dataset))
print '##### %s dataset #####' %dataset
#
# print len(data)
# attrslist = readARFF.getAttrList(attrs)
# root = makeTree(data, attrslist, attrs, readARFF.computeZeroR(data))
# root.printTree()
evaluation(5, attrs, data)
evaluation_zeroR(5, data)
p = computePrecision(TPCount,FPCount,TNCount,FNCount)
r = computeRecall(TPCount,FPCount,TNCount,FNCount)
a = computeAccuracy(TPCount,FPCount,TNCount,FNCount)
evalResult[c] = (p,r,a)
drawChart(evalResult)
return evalResult
if __name__ == '__main__' :
if len(sys.argv) < 2 :
print "Usage: decisionTree.py #datasetName"
sys.exit(-1)
fname = sys.argv[-1]
(attrs, data, classification) = readARFF.readArff(open(fname))
resultTest = {}
resultTrain = {}
resultZeroR = {}
for time in range(5):
print "Round ",time+1,":"
index = range(len(data))
trainSample = random.sample(index,int(len(data)*0.8))
testSample = [i for i in index if i not in trainSample]
trainDataset = [data[i] for i in trainSample]
testDataset = [data[i] for i in testSample]
print "\nUsing ZeroR:"
rz = evalZeroR(trainDataset,testDataset,classification,attrs)
print ' training_precision:'
print_pr_re(train_precision_average)
print ' training_recall:'
print_pr_re(train_recall_average)
print ' training_accuracy: %f%%' % (train_accuracy_average * 100)
if __name__ == '__main__':
# for loading the existing data set pickle
# pickledata = open('pickledata','rb')
# attrs = pickle.load(pickledata)
# data = pickle.load(pickledata)
# for loading the new data set
# dataset = 'tennis.arff'
# dataset = 'restaurant.arff'
dataset = 'breast-cancer.arff'
# dataset = 'nursery.arff'
# dataset = 'lymphography.arff'
attrs, data = readARFF.readArff(open(dataset))
print '##### %s dataset #####' % dataset
#
# print len(data)
# attrslist = readARFF.getAttrList(attrs)
# root = makeTree(data, attrslist, attrs, readARFF.computeZeroR(data))
# root.printTree()
evaluation(5, attrs, data)
evaluation_zeroR(5, data)
if correctPredicted[item] == 0:
Precision[item] = 0
Recall[item] = 0
else:
Precision[item] = float(correctPredicted[item]) / float(timesPredicted[item])
Recall[item] = float(correctPredicted[item]) / float(exampleLabeled[item])
allCorrect += correctPredicted[item]
accuracy = float(allCorrect) / len(testingData)
print "For multi-class -----------"
print "Precision: ", Precision
print "Recall: ", Recall
print "Accuracy: ", accuracy
### This part need be modified for different dataset
def isPositive(result) :
return "no-recurrence-events" in result
if __name__ == '__main__' :
filename = 'nursery.arff'
attributes = readARFF.readArff(open(filename))[0]
data = readARFF.readArff(open(filename))[1]
alist = readARFF.getAttrList(attributes)
trainingData, testingData = createTrainAndTestData(data)
#runEvaluation5times(data, attributes, None)
#runZeroREvaluation5times(data, attributes, None)
calculateForMultiClass(trainingData, testingData, attributes, None)
else:
node.children[value] = makeTree(subSet, aList, attributes, readARFF.computeZeroR(attributes, subSet))
return node
def printNode(root):
print root
if len(root.children) != 0:
for k in root.children:
child = root.children[k]
printNode(child)
if __name__ == '__main__':
fileName = sys.argv[-1]
attributes, data = readARFF.readArff(open(fileName))
listAttributes = readARFF.getAttrList(attributes)
times = 5
total = zero = 0
precision = recall = precisionZero = recallZero = 0
for i in range(times):
trainData = random.sample(data, int(len(data) * 0.8))
defaultValue = readARFF.computeZeroR(attributes, data)
zeroRValue = readARFF.computeZeroR(attributes, trainData)
root = makeTree(trainData, listAttributes, attributes, defaultValue)
#printNode(root)
TP = tp = 0
testData = []
for d in data:
if d not in trainData:
testData.append(d)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="""
Simply use to test:
`python decisionTree.py ARFF_FILE`
Wanzhang Sheng, Copyright 2013, GPL
""")
parser.add_argument('arff_file', help='The source ARFF file.')
parser.add_argument('--verbose', dest='verbose', action='store_true', help="Be verbose to debug.")
args = parser.parse_args()
VERBOSE = args.verbose
(attrs, data, classify_attr) = readARFF.readArff(open(args.arff_file))
domain = classify_attr.values()[0]
random.seed()
print ('=' + args.arff_file).ljust(25,'=')
total = init_statistics(domain)
total_noise = 0
for time in range(0,5):
print " \033[93m-%d time-\033[0m" % (time+1)
random.shuffle(data)
sp = int(len(data)*4/5)
train_data = data[:sp]
test_data = data[sp+1:]
root = makeTree(train_data, attrs)
# noise
