Scribd
Upload
168 views4 pages

Tutorial 7 Part 2 - Answer

The document contains 3 questions related to association analysis and frequent pattern mining. Question 1 involves constructing a conditional pattern base, conditional tree, and frequent pattern tree for an item and identifying the largest k-itemset. Question 2 involves generating a frequent pattern tree from transaction data and generating association rules for an item. Question 3 involves constructing conditional pattern bases and conditional trees for frequent items from a frequent pattern tree and identifying the largest k-itemset.

Uploaded by

Puteri Yasmin Syazwani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
168 views4 pages

Tutorial 7 Part 2 - Answer

The document contains 3 questions related to association analysis and frequent pattern mining. Question 1 involves constructing a conditional pattern base, conditional tree, and frequent pattern tree for an item and identifying the largest k-itemset. Question 2 involves generating a frequent pattern tree from transaction data and generating association rules for an item. Question 3 involves constructing conditional pattern bases and conditional trees for frequent items from a frequent pattern tree and identifying the largest k-itemset.

Uploaded by

Puteri Yasmin Syazwani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

ITS665 || Data Mining

Tutorial 7 Part 2 – Topic 7 Part 2 (Association Analysis)

Question 1 (2019-06)

Given the following tree:

a) Determine the conditional pattern base, conditional tree and frequent pattern tree
for item T only. Let minimum count = 2 and item N occurs in all transactions.

Item Conditional Pattern Conditional Tree Frequent Pattern Tree


Base
T {N,S,A:2},{N:1} {N:3, S:2, A:2} {N,T:3}
{S,T:2}
{A,T:2}
{N,S,T:2}
{N,A,T:2}
{S,A,T:2}
{N,S,A,T:2}

b) Identify the largest k-itemsets and count the support for that itemset.

k=4
support = 2/5 = 40%
ITS665 || Data Mining

Question 2 (2016-12)

The following table shows a database D = {111, 112, …, 151} at one grocery store
purchased by customers on five different products: P, Q, R, S and T. Let minimum support
= 33.33% and minimum confidence = 80%. The tick () symbol represents the product
bought by the customer.

TID P Q R S T
111  
112  
121   
122   
131   
132  
141   
142    
151   

a) Generate a Frequent Pattern (FP) Tree. Clearly show the steps involved.

TID Items Bought Items Bought (Sorted)


111 P, Q P, Q
112 Q, S Q, S
121 P, Q, T P, Q, T
122 P, Q, S P, Q, S
131 P, R, S P, R, S
132 Q, R Q, R
141 P, R, S P, R, S
142 P, Q, R, T P, Q, R, T
151 P, Q, R P, Q, R

TID P Q R S T
111  
112  
121   
122   
131   
132  
141   
142    
151   
Total 7 7 5 4 2
ITS665 || Data Mining

Count the number of occurrences of each item:

L = {{P:7},{Q:7},{R:5},{S:4},{T:2}}

Minimum support = (33/100) x 9 = 2.97 = 3

Remove T

Therefore L = {{P:7},{Q:7},{R:5},{S:4}}

b) Generate TWO (2) rules for item R and calculate its confidence value.

Item Conditional Pattern Conditional Tree Frequent Pattern Tree


Base
R {P,Q:2}, {P:2},{Q:1} {P:4} {P,R:4}

P  R (Confidence value = 4/7)


R  P (Confidence value = 4/5)
ITS665 || Data Mining

Question 3 (2014-12)

Given the following frequent-pattern (FP) tree with minimum support and threshold=3.

a) For each frequent item, construct its conditional pattern base and conditional FP-
tree.

Item Conditional Pattern Conditional FP-Tree FP Generated


Base
Z {s,d,b,n:2}{d,c:1} {s:2,d:2,b:2,n:2}{d:1,c:1} empty
N {s,d,b:2},{s,d,b,c:1} {s:3,d:3,b:3,c:1} {s,d,b,n}
C {s,d,b:1},{s:1},{d:1} {s:2,d:1,b:1}{d:1} Empty
B {s,d:3} {s:3,d:3} {s,d,b}
D {s:3} {s:3} {s,d}
S empty empty empty

b) What is the largest k-itemset from question (a)

k=4

You might also like