def getEntropy(attribute, examples):
entropy = 0
#TODO:can be optimized further
for attribVal in Attribute.getAttributes()[attribute]:
posEx = 0
negEx = 0
for example in examples:
if example.attributes[attribute] == attribVal:
if example.label == True:
posEx += 1
else:
negEx += 1
totalAttribEx = float(posEx + negEx)
if totalAttribEx != 0:
aInfo, bInfo = float(posEx)/totalAttribEx, float(negEx)/totalAttribEx
entropy += ( totalAttribEx/len(examples) )\
*getInfoConent([aInfo, bInfo])
return entropy
def decisionListLearning(examples):
#if examples are empty then return trivial list node
#with predicted label as 'No'/False
if len(examples) == 0:
return ListNode({}, {}, {}, False)
#find a test S.T. subset of examples either all +ve or -ve
(selectedAttributes, isSelectedIncl, selectedPureLabel, selectedOp) \
= findTest(examples, Attribute.getAttributes())
if not len(selectedAttributes):
raise (DListCreationErr('couldn\'t find attributes for even split.'))
listNode = ListNode(selectedAttributes, isSelectedIncl, selectedOp,\
selectedPureLabel)
#set next node from list learned by remaining examples
listNode.setNextNode(decisionListLearning(filterExamples(examples,\
selectedAttributes,\
isSelectedIncl,\
selectedOp)))
return listNode
def decisionListLearning(examples):
#if examples are empty then return trivial list node
#with predicted label as 'No'/False
if len(examples) == 0:
return ListNode({}, {}, {}, False)
#find a test S.T. subset of examples either all +ve or -ve
(selectedAttributes, isSelectedIncl, selectedPureLabel, selectedOp) \
= findTest(examples, Attribute.getAttributes())
if not len(selectedAttributes):
raise(DListCreationErr('couldn\'t find attributes for even split.'))
listNode = ListNode(selectedAttributes, isSelectedIncl, selectedOp,\
selectedPureLabel)
#set next node from list learned by remaining examples
listNode.setNextNode(decisionListLearning(filterExamples(examples,\
selectedAttributes,\
isSelectedIncl,\
selectedOp)))
return listNode
def decisionTreeLearning(examples, attribs, default):
if len(examples) == 0:
#if example list empty then return the majority value
#computed previously
return TreeNode(None, default)
elif checkIfSameClass(examples):
#if all examples same class then return the class
return TreeNode(None, examples[0].label)
elif len(attribs) == 0:
#if attributes empty then return majority value
return TreeNode(None, majorityValue(examples))
else:
bestAttrib = chooseAttribute(attribs, examples)
tree = TreeNode(bestAttrib)
majorityVal = majorityValue(examples)
#for each possible value of attribute
for attribVal in Attribute.getAttributes()[bestAttrib]:
filteredExamples = filterExamples(bestAttrib, attribVal, examples)
subTree = decisionTreeLearning(filteredExamples, \
filterAttributes(attribs, bestAttrib), majorityVal)
tree.addSubtree(attribVal, subTree)
return tree
def main():
examples = []
examples.append(Example({'alt':True, 'bar':False, 'fri':False, 'hun':True,\
'pat':'some', 'price':'$$$', 'rain':False,\
'res':True, 'type':'french', 'est':'0-10'},\
True))
examples.append(Example({'alt':True, 'bar':False, 'fri':False, 'hun':True,\
'pat':'full', 'price':'$', 'rain':False,\
'res':False, 'type':'thai', 'est':'30-60'},\
False))
examples.append(Example({'alt':False, 'bar':True, 'fri':False, 'hun':False,\
'pat':'some', 'price':'$', 'rain':False,\
'res':False, 'type':'burger', 'est':'0-10'},\
True))
examples.append(Example({'alt':True, 'bar':False, 'fri':True, 'hun':True,\
'pat':'full', 'price':'$', 'rain':True,\
'res':False, 'type':'thai', 'est':'10-30'},\
True))
examples.append(Example({'alt':True, 'bar':False, 'fri':True, 'hun':False,\
'pat':'full', 'price':'$$$', 'rain':False,\
'res':True, 'type':'french', 'est':'>60'},\
False))
examples.append(Example({'alt':False, 'bar':True, 'fri':False, 'hun':True,\
'pat':'some', 'price':'$$', 'rain':True,\
'res':True, 'type':'italian', 'est':'0-10'},\
True))
examples.append(Example({'alt':False, 'bar':True, 'fri':False, 'hun':False,\
'pat':'none', 'price':'$', 'rain':True,\
'res':False, 'type':'burger', 'est':'0-10'},\
False))
examples.append(Example({'alt':False, 'bar':False, 'fri':False, 'hun':True,\
'pat':'some', 'price':'$$', 'rain':True,\
'res':True, 'type':'thai', 'est':'0-10'},\
True))
examples.append(Example({'alt':False, 'bar':True, 'fri':True, 'hun':False,\
'pat':'full', 'price':'$', 'rain':True,\
'res':False, 'type':'burger', 'est':'>60'},\
False))
examples.append(Example({'alt':True, 'bar':True, 'fri':True, 'hun':True,\
'pat':'full', 'price':'$$$', 'rain':False,\
'res':True, 'type':'italian', 'est':'10-30'},\
False))
examples.append(Example({'alt':False, 'bar':False, 'fri':False, 'hun':False,\
'pat':'none', 'price':'$', 'rain':False,\
'res':False, 'type':'thai', 'est':'0-10'},\
False))
examples.append(Example({'alt':True, 'bar':True, 'fri':True, 'hun':True,\
'pat':'full', 'price':'$', 'rain':False,\
'res':False, 'type':'burger', 'est':'30-60'},\
True))
rootNode = decisionTreeLearning(examples, Attribute.getAttributes().keys(),\
False)
printDecisionTree(rootNode)
print predictFromDecisionTree(rootNode, {'alt':True, 'bar':True, 'fri':True, 'hun':True,\
'pat':'full', 'price':'$', 'rain':False,\
'res':False, 'type':'burger', 'est':'30-60'})
print '**** prediction accuracy ****'
trainAccuracy = getAccuracy(examples, rootNode)
print 'training set error: ' + str(100-trainAccuracy) + '%'
