4A

C9
12
0

92
DE
Paper / Subject Code: 37471 / Data Analytics and Visualization

CB

AA

8B
10
C4

12
E0

92
1T01876 - T.E. Computer Science and Engineering (Artificial Intelligence and Machine Learning) (Choice Based)

B4

C
DA

AA

8B
10
4D
(R-19-20 'C' Scheme)SEMESTER - VI / 37471 - Data Analytics and Visualization

0C

92
77

AC

B4

1
E
QP CODE: 10029185 DATE: 08/05/2023

AA

10
4D
0A

0C
D

2
77

4
DA

1
DE
Duration: 3 Hrs [Max Marks: 80]

B
A

AA
0A

0C
7D
03

4
AC

4
A

A1
E
92

CB
D
Notes: (1) Question No. 1 is Compulsory.

D
0A

7D
C9

4A
03

C4

E0
(2) Attempt any THREE questions out of the remaining FIVE.

DA
2
8B

A7

CB
A

4D
99
(3) All questions carry equal marks.

7D
3
92

A0

E0
C

20

C
8B

7
10
(4) Assume suitable data, if required, and state it clearly.

DA
D

D
9

A
9
12

03

C4
2

0
(5) Figures to the right indicate full marks.

BC

7
9

DA

DE
AA

7
0

DA
99

A
21

03

C4
92

A0
B4

C
1

77
Q1 a) What is an analytic sandbox, and why is it important? 5

AA

2
8B
0

DA
D
0C

99

0A
21

03
2
B4

BC
1
b) Why use autocorrelation instead of autocovariance when examining stationary 5
DE

77
09

DA
AA

92
0C

A
1

8
C4

C9
2

03
92
time series?

A0
4

A1
DE

7
B
DA

2
8B

A7
10

3D
0C

99
4A
4

c) Difference between Pandas and NumPy. 5

12

92

A0
77

BC

20
E

CB
A

AA

0
4D
0A

3D
99
21
D

28
d) What is regression? What is simple linear regression? E0 5
7

B4
DA

BC
A1

20
09
7

4D
0A

99
21
7D

4A

28
03

Q2 a) Explain in detail how dirty data can be detected in the data exploration phase 10
0
C
A

BC
A1
E

9
92

CB
DA
D

10
D
A
C9

with visualizations.

4A

28
03

C4
0

12
E0
7
DA

09
2
8B

CB
DA

AA
4D
99

b) List and explain methods that can be used for sentiment analysis. 10

21
3
92

A0

E0
C

77

AC

B4

A1
2
8B
10

Q3 a) List and explain the main phases of the Data Analytics Lifecycle.
D

10
D
99

0A

0C
7D

4A
12

03

C4
2

BC
9

DA

DE
AA

92

b) Describe how logistic regression can be used as a classifier.

0

10

CB
DA
A
1

C9
2

03

C4
92

A0
B4

E0
A1

77

Q4 a) Suppose everyone who visits a retail website gets one promotional offer or no 10
2
8B
0

DA
3D
0C

4D
99

0A
21
4A

BC

promotion at all. We want to see if making a promotional offer makes a

1

20
DE

77

AC
9

DA
CB

AA

99

A
21

8
C4

7D
03
0

92

difference. What statistical method would you recommend for this analysis?
A0
4

BC
A1
DE

B
DA

92

A7
10

3D
C

4A

28
4

b) List and explain the steps in the Text Analysis. 10

C9
2
0

A0
77

20
DE

9
CB
A

AA

B
0
A

3D
99
21
D

Q5 a) How does the ARMA model differ from the ARIMA model? In what situation is 10
28
C4
A0

E0
7

B4

C
A1

20
09
7

DA

8B
4D
0A

the ARMA model appropriate?

0C

99
21
4A

92
7

C
A

BC
A1
E
A7

CB
A
D

b) Explain with suitable example how the Term Frequency and Inverse Document 10
10
D
7D

4A

28
3

C4
0

12
E0
20

09
A7

Frequency are used in information retrieval.

B
DA

AA
3D

4D
99

0C

21
A0
BC

20

77

B4

Q6 Write short notes on:

A1
DE
A
3D
99

0C
7D

4A
C4
A0
BC

DE
92

a) Evaluating the Residuals in Linear regression.

7

5
CB
A
D

A
8

D
C9

03

C4
2

A0

E0
7
09

92
8B

A7

DA

b) Box-Jenkins Methodology 5
3D

4D
21

C9
2

A0
A1

20

77

AC
9

B
0

D
99

A
21

c) Seaborn Library. 5
28

7D
03

A0
BC
A1

92

A7
10

3D
A

d) Data import and Export in R

C9

5
12

92

A0
B4

20
AA

B
10

3D
0C

99
28
12
B4

BC

20
DE

09
A

**************************
0C

99
21
4A

8
92

BC
A1
E

CB

10
4D

4A

28
12
E0
C

09
CB
DA

AA
4D

29185 Page 1 of 1
21
E0
77

AC

B4

A1
4D

0C
7D

4A
AC

DE
A7

DA0A77DAC4DE0CB4AA1210928BC99203
CB