def testExtraCredit(setFunc=setEntropy, infoFunc=infoGain):
examples, attrValues, labelName, labelValues = getExtraCreditDataset()
print 'Testing Nursery dataset. Number of examples %d.' % len(examples)
tree = makeTree(examples, attrValues, labelName, setFunc, infoFunc)
f = open('nursery.out', 'w')
f.write(str(tree))
f.close()
print 'Tree size: %d.\n' % tree.count()
print 'Entire tree written out to nursery.out in local directory\n'
dataset = getExtraCreditDataset()
evaluation = getAverageClassificaionRate(
(examples, attrValues, labelName, labelValues), runs=10, testSize=2000)
print 'Results for training set:\n%s\n' % str(evaluation)
printDemarcation()
return (tree, evaluation)
def testAdultSet(setFunc=setEntropy, infoFunc=infoGain):
"""Correct classification averate rate is about 0.95"""
examples, attrValues, labelName, labelValues = getExtraCreditDataset()
print 'Testing Adult dataset. Number of examples %d.' % len(examples)
start = time.time()
tree = makeTree(examples, attrValues, labelName, setFunc, infoFunc)
end = time.time()
print "Training time: ", (end - start)
f = open('adult.out', 'w')
f.write(str(tree))
f.close()
print 'Tree size: %d.\n' % tree.count()
print 'Entire tree written out to adult.out in local directory\n'
dataset = getExtraCreditDataset()
evaluation = getAverageClassificaionRate(
(examples, attrValues, labelName, labelValues))
print 'Results for training set:\n%s\n' % str(evaluation)
printDemarcation()
return (tree, evaluation)
def testextra(setFunc=setEntropy, infoFunc=infoGain):
"""Correct classification averate rate is about 0.75"""
examples, attrValues, labelName, labelValues = getExtraCreditDataset()
print 'Testing Connect4 dataset. Number of examples %d.' % len(examples)
tree = makeTree(examples, attrValues, labelName, setFunc, infoFunc)
f = open('extra.out', 'w')
print 'Tree size: %d.\n' % tree.count()
print 'Entire tree written out to extra.out in local directory\n'
f.write(str(tree))
f.close()
evaluation = getAverageClassificaionRate(
(examples, attrValues, labelName, labelValues))
print 'Results for training set:\n%s\n' % str(evaluation)
printDemarcation()
return (tree, evaluation)