def Branch(dataset, default, attributes):
if not dataset:
return dtree.TreeLeaf(default)
if dtree.allPositive(dataset):
return dtree.TreeLeaf(True)
if dtree.allNegative(dataset):
return dtree.TreeLeaf(False)
return Tree(dataset, attributes, maxdepth - 1)
def makeTree(set, level, attributes):
if level >= depth:
return dtree.TreeLeaf(dtree.mostCommon(set))
attr = dtree.bestAttribute(set, attributes)
node = []
branches = []
for val in attr.values:
subset = dtree.select(set, attr, val)
attributes_left = [a for a in attributes if a != attr]
if dtree.allPositive(subset):
node = dtree.TreeLeaf(True)
elif dtree.allNegative(subset):
node = dtree.TreeLeaf(False)
else:
node = makeTree(subset, level + 1, attributes_left)
branches.append((val, node))
node = dtree.TreeNode(attr, dict(branches), dtree.mostCommon(set))
return node
def buildtree(dataset, remaining_attr, level):
if level == 2:
return dtree.TreeLeaf(dtree.mostCommon(dataset))
max_attr, _ = getMaxGain(dataset, remaining_attr)
branches_dict = dict([(value, dtree.select(dataset, max_attr, value))
for value in max_attr.values])
_remaining_attr = [a for a in remaining_attr if a != max_attr]
branches_nodes = {}
print(max_attr)
for value, branch_data in branches_dict.items():
branches_nodes[value] = buildtree(branch_data, _remaining_attr,
level + 1)
return dtree.TreeNode(max_attr, branches_nodes,
dtree.TreeLeaf(dtree.mostCommon(dataset)))
def caspersky(dataset):
print("Assignment 3")
a = d.bestAttribute(dataset, m.attributes)
branches = []
for v in a.values:
s = d.select(dataset, a, v)
tf = d.mostCommon(s)
if tf == True:
branches.append((v, d.TreeLeaf(s)))
else:
a2 = d.bestAttribute(s, m.attributes)
branches2 = []
for v2 in a2.values:
s2 = d.select(s, a2, v2)
branches2.append((v2, d.TreeLeaf(d.mostCommon(s2))))
branches.append((v, d.TreeNode(a2, dict(branches2),
d.mostCommon(s))))
drawtree.drawTree(d.TreeNode(a, dict(branches), d.mostCommon(dataset)))
def Tree(dataset, attributes, maxdepth=3):
def Branch(dataset, default, attributes):
if not dataset:
return dtree.TreeLeaf(default)
if dtree.allPositive(dataset):
return dtree.TreeLeaf(True)
if dtree.allNegative(dataset):
return dtree.TreeLeaf(False)
return Tree(dataset, attributes, maxdepth - 1)
default = dtree.mostCommon(dataset)
if maxdepth < 1:
return dtree.TreeLeaf(default)
a = dtree.bestAttribute(dataset, attributes)
attributesLeft = [x for x in attributes if x != a]
branches = [(v, Branch(dtree.select(dataset, a, v), default,
attributesLeft)) for v in a.values]
return dtree.TreeNode(a, dict(branches), default)