When mining for association rules, to generate three-item sets efficiently, one uses

Question 19 options:

	two-item sets and one-item sets alone
	two-item sets and one-item sets and then the dataset to confirm support
	two-item sets alone
	two-item sets to get candidates and the dataset to confirm support
	the dataset alone

Question 20 (1 point)

Consider only Body temp, Give birth, Aquatic attributes in Table 1, and assume you are looking for association rules with minimum support 3. Which of the following association rules have confidence 100%?

Table 1: Vertebrate Dataset (modified from Introduction to Data Mining by Tan et al.)

Name	Body temp	Give birth	Aquatic	Class
human	warm	yes	no	mammal
echidna	warm	no	no	mammal
salmon	cold	no	yes	fish
whale	warm	yes	yes	mammal
eel	cold	no	yes	fish
bat	warm	yes	no	mammal
shark	cold	yes	yes	fish
cat	warm	yes	no	mammal

Question 20 options:

	If Aquatic = no, then Body temp = warm and Give birth = yes
	If Body temp = warm and Give birth = yes, then Aquatic = no
	If Give birth = yes, then Aquatic = no and Body temp = warm
	If Give birth = yes and Aquatic = no, then Body temp = warm
	If Body temp = warm, then Give birth = yes and Aquatic = no

Question 21 (1 point)

If we use the association rule mining algorithm on the dataset in Table 1, without considering the attribute Name, which of the following is a frequent two-item set (minimum support is 4)?

Table 1: Vertebrate Dataset (modified from Introduction to Data Mining by Tan et al.)

Name	Body temp	Give birth	Aquatic	Class
human	warm	yes	no	mammal
echidna	warm	no	no	mammal
salmon	cold	no	yes	fish
whale	warm	yes	yes	mammal
eel	cold	no	yes	fish
bat	warm	yes	no	mammal
shark	cold	yes	yes	fish
cat	warm	yes	no	mammal

Question 21 options:

	Body temp = warm, Give birth = yes
	Body temp = warm, Aquatic = no
	Body temp = warm, Class = mammal
	a, b
	a, b, c

Question 22 (1 point)

In instance-based learning, when using a kD-tree to locate a nearest neighbour of a target instance, the nearest neighbour is

Question 22 options:

	at the root of the tree
	at an internal node
	at a leaf node
	possibly any one of the above
	none of the above

(The following two questions are based on this figure)

When applying the instance-based learning algorithm, the kD-tree created for a dataset with 4 instances is shown below.

Question 23 (1 point)

Given a test instance (2, 5), which training instance is identified as the nearest neighbor?

Question 23 options:

	(2, 2)
	(3, 8)
	(6, 7)
	(7, 4)

Question 24 (1 point)

In the previous question (given the test instance (2, 5)), which instance is first located as the potential nearest neighbor (when falling through the root to the leaf without tracing back)?

Question 24 options:

	(6, 7)
	(2, 2)
	(7, 4)
	(3, 8)