write your solution please in (MS word,)
1. Suppose a group of 12 students with the test scores listed as follows:19,
71, 48, 63, 35, 85, 69, 81, 72, 88, 99, 95. Partition them into four bins
by
(a) equal-frequency (equi-depth) method
(b) equal-width method
(c) an even better method (such as clustering).
2. What are the value ranges of the following normalization methods,
respectively?
(a) min-max normalization,
(b) z-score normalization,
(c) normalization by decimal scaling?
3. Table below shows how many transactions containing beer and/or nuts
among 10000 transactions.
Beer No Beer total
Nuts 50 800 850
No Nuts 150 9000 9150
Total 200 9800 10000
(a) (roughly) calculate X^2 ,
(b) calculate lift,
(c) calculate all-con confidence,
(d) based on your calculations, how do you conclude the relationship
between buying beer and buying nuts?
Hint: The formulae to compute x^2 , lift and all-con dence are as follows.
X^2 =sum (observed expected)^2
expected
lif t =P(A U B)/P(A)P(B)
all conf(X) =sup(X)/max item sup(X)=sup(X)maxfsup(ij)j8ij 2 Xg
where maxfsup(ij)j8ij 2 Xg is the maximum (single) item support of
all the items in X.
2
Name:
Midterm Test
If you are solving the problems on paper scan or take a picture of your
complete solution and upload it to OnCourse. If you are taking a picture of
your solution make sure it is readable. If you are using computer software
to write your solution please upload the file (MS Office, LibreOffice or PDF
format only)
Each question is worth 10 points.
1. Suppose a group of 12 students with the test scores listed as follows:19,
71, 48, 63, 35, 85, 69, 81, 72, 88, 99, 95. Partition them into four bins
by
(a) equal-frequency (equi-depth) method
(b) equal-width method
(c) an even better method (such as clustering).
2. What are the value ranges of the following normalization methods,
respectively?
(a) min-max normalization,
(b) z-score normalization,
(c) normalization by decimal scaling?
3. Table below shows how many transactions containing beer and/or nuts
among 10000 transactions.
Beer No Beer total
Nuts
50
800
850
No Nuts 150
9000
9150
Total
200
9800
10000
(a) (roughly) calculate χ2 ,
(b) calculate lift,
(c) calculate all-confidence,
(d) based on your calculations, how do you conclude the relationship
between buying beer and buying nuts?
1
Hint: The formulae to compute χ2 , lift and all-confidence are as follows.
X (observed expected)2
2
χ =
expected
lif t =
all conf (X) =
P (A ∪ B)
P (A)P (B)
sup(X)
sup(X)
=
max item sup(X)
max{sup(ij )|∀ij ∈ X}
where max{sup(ij )|∀ij ∈ X} is the maximum (single) item support of
all the items in X.
2
Name:
Midterm Test
If you are solving the problems on paper scan or take a picture of your
complete solution and upload it to OnCourse. If you are taking a picture of
your solution make sure it is readable. If you are using computer software
to write your solution please upload the file (MS Office, LibreOffice or PDF
format only)
Each question is worth 10 points.
1. Suppose a group of 12 students with the test scores listed as follows:19,
71, 48, 63, 35, 85, 69, 81, 72, 88, 99, 95. Partition them into four bins
by
(a) equal-frequency (equi-depth) method
(b) equal-width method
(c) an even better method (such as clustering).
2. What are the value ranges of the following normalization methods,
respectively?
(a) min-max normalization,
(b) z-score normalization,
(c) normalization by decimal scaling?
3. Table below shows how many transactions containing beer and/or nuts
among 10000 transactions.
Beer No Beer total
Nuts
50
800
850
No Nuts 150
9000
9150
Total
200
9800
10000
(a) (roughly) calculate χ2 ,
(b) calculate lift,
(c) calculate all-confidence,
(d) based on your calculations, how do you conclude the relationship
between buying beer and buying nuts?
1
Hint: The formulae to compute χ2 , lift and all-confidence are as follows.
X (observed expected)2
2
χ =
expected
lif t =
all conf (X) =
P (A ∪ B)
P (A)P (B)
sup(X)
sup(X)
=
max item sup(X)
max{sup(ij )|∀ij ∈ X}
where max{sup(ij )|∀ij ∈ X} is the maximum (single) item support of
all the items in X.
2
Purchase answer to see full
attachment
