{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# a2sol - Question 1 Problem 2 a support(cfw_E = 8 10 = 0.8...

This preview shows pages 1–2. Sign up to view the full content.

Question 1: Problem 2 a) support({E}) = 8 / 10 = 0.8 support({B, D}) = 2 / 10 = 0.2 support({B, D, E}) = 2 / 10 = 0.2 b) confidence(BD → E) = support({B, D, E}) / support({B, D}) = 0.2 / 0.2 = 1.0 confidence(E → BD) = support({B, D, E}) / support({E}) = 0.2 / 0.8 = 0.25 No, confidence is not a symmetric measure. As seen in the above example, the numerators are the same, however, the denominators are different values. c) support({E}) = 4 / 5 = 0.8 support({B, D}) = 5 / 5 = 1.0 support({B, D, E}) = 4 / 5 = 0.8 d) confidence(BD → E) = support({B, D, E}) / support({B, D}) = 0.8 / 1.0 = 0.8 confidence(E → BD) = support({B, D, E}) / support({E}) = 0.8 / 0.8 = 1.0 e) s1 ≤ s2. There is no relationship between c1 and c2. Question 2: Problem 6 a) Total number of items in the data set {Beer, Bread, Butter, Cookies, Diaper, Milk}, d = 6 Therefore, total possible association rules = 3 d – 2 d+1 + 1 = 3 6 – 2 7 + 1 = 729 – 128 + 1 = 602 b) 4 c) 6 C 3 = 20 d) Support: {Bread, Butter} = 0.5 e) One of the possible answers is a = {Bread}, and b = {Butter} Question 3: Problem 9 a) Leaf nodes visited for transaction {1, 3, 4, 5, 8} are L1, L3, L5, L9 and L11.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}