1) Consider the transaction database below. Suppose minsup = 40%. Transaction ID

Question

1) Consider the transaction database below. Suppose minsup = 40%.

Transaction ID

Items Bought

1

{B, D, E}

2

{B, C, D}

3

{B, D, E}

4

{A, C, D, E}

5

{B, C, D, E}

6

{B, D, E}

7

{C, D}

8

{A, B, C}

9

{A, D, E}

10

{B, D}

a. List all frequent 1-itemsets with their support measures

b. List all frequent 2-itemsets with their support measures. Generate candidates by applying the Apriori principle.

c. List all candidate 3-itemsets using the following candidate generation strategies:

1. Fk-1 x F1

2. Fk-1 x Fk-1

d. List all frequent 3-itemsets after pruning (use the candidate 3-itemsets you generated in c(2) above). Show their support measures.

e. Suppose minconf = 50%. List all association rules from the previous problem that survive the pruning. Show their confidence measures.

Transaction ID

Items Bought

1

{B, D, E}

2

{B, C, D}

3

{B, D, E}

4

{A, C, D, E}

5

{B, C, D, E}

6

{B, D, E}

7

{C, D}

8

{A, B, C}

9

{A, D, E}

10

{B, D}

Explanation / Answer

Support is calculated as (Number of transaction the itemsets appears iN)/Total Number of transactions.

Frequent _1 Itemsets based on the threshold are :

Since A is not frequent any Transaction with A in it can not be frequent (Apriori)

Generating Frequent_2 Itemsets by F1 X F1

Frequent_3 can be generated either by F2 X F1 or F2 X F2.

A 0.3 B 0.7 C 0.5 D 0.9 E 0.6

Related Questions

Navigate

• Browse (All)
• Browse 1
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.