def A31():
tree = dT.buildTree(m.monk1, m.attributes, 5)
print tree
draw.drawTree(tree)
for subset in sel:
for i in [0, 1, 2, 3, 5]:
sub.append(t.averageGain(subset, m.attributes[i]))
mC.append(t.mostCommon(subset))
# print(sub)
sub = []
"Highest information gain on second level of the tree # 2 - A4 , 3 - A6 , 4 - A1 #"
"""Assignment 3"""
tree1 = t.buildTree(m.monk1, m.attributes)
tree2 = t.buildTree(m.monk2, m.attributes)
tree3 = t.buildTree(m.monk3, m.attributes)
draw.drawTree(tree1)
# draw.drawTree(tree2)
# draw.drawTree(tree3)
print("Assignment 3: Decision tree performances")
print("Train errors:")
print(1 - round(t.check(tree1, m.monk1), 5))
print(1 - round(t.check(tree2, m.monk2), 5))
print(1 - round(t.check(tree3, m.monk3), 5))
print("Test errors:")
print(round(1 - t.check(tree1, m.monk1test), 5))
print(round(1 - t.check(tree2, m.monk2test), 5))
print(round(1 - t.check(tree3, m.monk3test), 5), "\n")
def A31(): tree = dT.buildTree( m.monk1, m.attributes, 5 ) print tree draw.drawTree( tree )
def draw_tree(dataset):
#Draws a decision tree from dataset
t = dt.buildTree(dataset, m.attributes)
dw.drawTree(t)
return t
import dtree as d
import monkdata as m
import drawtree as dt
def isLeaf(subset):
return d.allPositive(subset) or d.allNegative(subset)
def buildTree(subset,attrs):
global tree
if isLeaf(subset):
tree = (tree + '+') if d.allPositive(subset) else (tree + '-')
return
else:
root = d.bestAttribute(subset,attrs)
tree = tree + str(root) + "("
for value in root.values:
nextSubset = d.select(subset,root,value)
nextAttrs = attrs - set([root])
buildTree(nextSubset,nextAttrs)
tree = tree + ")"
tree = ""
buildTree(m.monk1,set(m.attributes))
#dt.drawTree(tree)
id3tree = d.buildTree(m.monk1,m.attributes)
dt.drawTree(id3tree)
import monkdata as m
import dtree as dt
import drawtree as draw
entropy = dt.entropy(m.monk1)
best_gain = 0
for attribute in m.attributes:
gain = dt.averageGain(m.monk1, attribute)
if gain > best_gain:
best_gain = gain
best_attribute = attribute
for v in best_attribute.values:
subset = dt.select(m.monk1, best_attribute, v)
majority_class = dt.mostCommon(subset)
values = {
v: dt.mostCommon(dt.select(m.monk1, best_attribute, v))
for v in best_attribute.values
}
print(best_attribute, values)
draw.drawTree(dt.buildTree(m.monk1, m.attributes, 2))
import monkdata as m
import dtree as dt
import drawtree as draw
entropy = dt.entropy(m.monk1)
best_gain = 0
for attribute in m.attributes:
gain = dt.averageGain(m.monk1, attribute)
if gain > best_gain:
best_gain = gain
best_attribute = attribute
for v in best_attribute.values:
subset = dt.select(m.monk1, best_attribute, v)
majority_class = dt.mostCommon(subset)
values = {v: dt.mostCommon(dt.select(m.monk1, best_attribute, v)) for v in best_attribute.values}
print(best_attribute, values)
draw.drawTree(dt.buildTree(m.monk1, m.attributes, 2))
