def init(train_path, test_path, validation_path, l, k, toprint):
featureSet = util.parseLines(train_path)
rootNode = id3(list(util.headers), None, featureSet)
if(toprint=="yes"):
rootNode.printTree(0)
testSet = util.parseLines(test_path)
accuracy1 = classifySet(rootNode, testSet)
accuracy = accuracy1+0.2
print "Accuracy before pruning:", accuracy1
for i in range(0,10):
ll = random.randint(1,l)
kk = random.randint(1,k)
dbest = rootNode.postpruning(ll, kk, validation_path)
accuracy2 = classifySet(dbest, testSet)
if(accuracy2 > accuracy1):
accuracy = accuracy2
print "Accuracy after pruning:", accuracy
def postpruning(self, l, k, validation_path):
validationSet = util.parseLines(validation_path)
dbest = copyTree(self)
for i in range(1, l):
ddash = copyTree(dbest)
m = random.randint(1, k)
for j in range(1,m):
global nonleaf
nonleaf = []
getNonLeafNodes(ddash)
n = len(nonleaf)
if(n>1):
p = random.randint(1, n-1)
chosenNode = nonleaf.pop()
class0 = chosenNode.classSet.count(0)
class1 = chosenNode.classSet.count(1)
chosenNode.childNode0 = None
chosenNode.childNode1 = None
chosenNode.name = "Yes" if class0 > class1 else "No"
dbestacc = classifySet(dbest, validationSet)
ddashacc = classifySet(ddash, validationSet)
if(ddashacc>dbestacc):
dbest = copyTree(ddash)
return dbest
