F

8A

4F

D
29
7F
Paper / Subject Code: 42476 / BIG DATA ANALYTICS (DLOC - III)

0D
84
FB
5A
73

8A

4F

D
29
CE

7F

0D
84
FB
5A
73
68

8A

4F
Duration: 3hrs [Max Marks:80]

29
CE

7F
10

84
FB
5A
73
B9

68

A
29
N.B. : (1) Question No 1 is Compulsory.

CE

7F
0
ED

B8
91

5A
73
(2) Attempt any three questions out of the remaining five.

F
32

29
E

F
0
ED
(3) All questions carry equal marks.

8
DD

7
1

B
5A
3
B9

68
(4) Assume suitable data, if required and state it clearly.

9F
32

7
0D

CE

7F
10
D
DD

A2
E
F

73
B9

68
44

F5
1 Attempt any FOUR [20]

D3

E
10
ED
8

37
A What is Big Data? What is Hadoop? How are Big Data and Hadoop linked?

8A

4F

DD

B9

68
32

7
4
B Write the step of Grivan-Newman algorithm. Explain clustering of Social

FB

CE

7F
0
D
8

DD
0

1
8A

2E
F

3
9
Network Graph using GN algorithm with example.

68
44

E7
DB
A2

3
FB

10
C What is MapReduce ? Explain How Map and Reduce Work?

A8

DD
0

8C
F5

E
F

9
9
D Explain PCY algorithm with suitable examples.

2
B8

B
A2

06
D
37

D3

ED
A8

F0
E Explain NoSQL data Architecture patterns.

91
F
E7

F5

DD
29

44

32
B8

DB
F Explain Recommendation system & its various types with example.
8C

37

10
8

D
0
F
E7

F5

8A
06

E
4F

B9
9

32
2

0D
8C

37
1

84
2 a Describe the structure of HDFS in a Hadoop Ecosystem using a diagram [10]

FB
A

ED
B9

DD
E7

F5

8A
06

F
b What is NOSQL? What are the business drivers for NoSQL? Discuss any two [10]

29
ED

32
D
8C

37
1

4
FB
5A
architectural patterns of NoSQL.
B9

DD
F0
32

E7

8A
06

29
F
ED

44
DD

0D
C

7
1

B
5A
3
B9

8
8

3 a Explain Page Rank with Example. Can a Website’s Page rank Ever Increase? [10]

9F
32

A
06

4F
0D

CE

7F
ED

8
DD

What are its chances of Decreasing?

A2
1

84
FB
4F

73
B9

8
32

F5

8A
06
0D
84

29
b Evaluate PCY algorithm on the following transaction to find the candidate sets
E
[10]
ED
DD

7
91

FB
8A

4F

5A
73
(frequent sets).
68
32

DB
0D
84

29
FB

CE

7F
0

Given data: Threshold value or minimization value = 3

D

1
8A

E
4F

5A
3
DD

B9
29

68

Hush function = (i * j) mod 10.

32

E7
84
FB

7F
5A

10
D
D
F0

T1 = {1, 2, 3} T2 = {2, 3, 4} T3 = {3, 4, 5} 8C

8A

73
DD

9
29
7F

44

32

06
T4 = {4, 5, 6} T5 = {1, 3, 5} T6 = {2, 4, 6}
FB

CE
5A

ED
73

A8

D
F0

91

T7 = {1, 3, 4} T8 = {2, 4, 5} T9 = {3, 4, 6}

D
29
CE

68
7F

44

32
B8

DB
0D

T10 = {1, 2, 4} T11 = {2, 3, 5} T12= {3, 4, 6}

5A

10
73

A8
68

D
9F

E
F

B9
CE

7F
10

44

32
B8
A2

ED
73
B9

A8
68

DD
0
9F

4 a Explain the Role and effect of damping Factor(teleportation) in page rank [10]
F5

F
E
10
D

44

32
B8
2

D
8C

37

computation
2E

5A
B9

A8

DD
F0
9F
E7
6

b Calculate the Cosine distance measure for given vectors [10]

7F
10
D

44
B8
2

0D
C

d1 = 3 2 0 5 0 0 0 2 0 0
2E

5A
73
B9

8
68

9F

4F
D3

d2 = 1 0 0 0 0 0 0 1 0 2
7F
10
D

8
2
8C

84
FB
2E

5A
73
D

B9

8A
6
0D

29
E

7F
10
D

5 a Explain Clearly with diagram how the PCY algorithm helps to perform frequent [10]
DD

8C

FB
2E
4F

5A
73
B9

itemset mining for large datasets

6
0D

D3

29
E

7F
10
D

b Give the formal definition of Nearest Neighbor problem,Show how finding

8C

[10]
2E
F

5A
73
D

B9
44

plagiarism in a document is nearest Neighbour Problem. What similarity

0D

7F
10
D
A8

DD

8C

measure can be used

2E
4F

73
B9
B8

6
0D
84

CE
10
D
DD
9F

2E
F

B9

6 a Given a Dim Dataset (1,5,8,10,2} Use the agglomerative clustering [10]

68
44
B8

0D

10
D

algorithm with Euclidean distance to establish hierarchical grouping

A8

DD
9F

2E
F

B9

relationship. Draw the dendrogram.

44
B8
A2

0D

D
A8

DD

b Write a note on (Any Two) [10]

9F
F5

2E
F
44
B8
A2

i) HITS
0D
37

3
A8

DD
9F
E7

F5

ii) Distance measurement for Big data

F
44
B8
A2

0D
37

iii) Multistage Frequent Itemset Mining Algorithm

A8
9F
7

F5

____________________
CE

44
B8
A2
37

A8
8

9F
7

F5

15927 Page 1 of 1
06

CE

B8
A2
37
91

9F
7
DB

F5
06

CE

A2
37
91

68

7
DB

2EDB91068CE737F5A29FB8A844F0DDD3
CE

7F
10