SOLVED MODEL QUESTION PAPER

(As Per New Syllabusl

Foundations of Data Science
Semester - II (CSE/ IT)
Time:Three Hours) IMaximum Marks: 100
Answer ALL Questions

PART A - (10 x 2 = 20 Marks)

01
Define data mining.
extracting or mining knowledge from largeamounts of data. It is a
mining refers to
: Data
praCSsof
discovering interesting patterns or Knowledge from alarge amount of data stored
databases, data warehouses or other information repositories.
eitherin
structureddata.
02 Define
Structured data is arranged in rows and column format. It helps for application
to

retrmeve and process

data easily. Database management system is used for storing structured
structured data refers to data that is identifiable because it is organized in a
ata. The term
structure.
nominal data ?
Q3 What is
S
serve as
inc "A nominal data is the 1 level of measurement scale in which the numbers
qualitative data.
Tags" or "labels" to classify or identify the objects. Nominal data is type of
numbers that do not have
Anominal data usually deals with the non-numeric variables or the
transformed before
any value. While developing statistical models, nominal data are usually
building the model.
Q4 Explain frequency polygon.
shapes ot
As. : Frequency polygons are a graphical device for understanding the
Usibutions. They serve the same purpose as histograms, but are especially helpful for
mparing sets of data. Frequency polygons are also a good choice for displaying cumulative
Irequency distributions.
05 What is correlation analysis ?
Ans. relationship
Oneiatlon is a statistical analysis used to measure and describe the
beween
two variables, A correlation plot will display eorrelations between the values ot
Variables in the dataset. If two variables are correlated, Xand Ythen aregression can be done
norder
to predict Scores on Yfrom the scores on X.

(M- 1)
Foundations of Data Science M-2
Solved Model
Q.6 What is cause and effect relationship ? Question Paper
Ans. : Iftwo variables vary in such a way that movement in one are
movement in other, these variables are caled cause and effect relationshin
Q.7 What is an aggregationfnction ?
Ans. : In aggregation fnction is one which takes multiple
ac ompaniet by

individual
summary. In the majority of the cases, this summary is a single value. values and
The most rCommon
eturnis a
aggregation functions are asinnple average or summation of values.
Q.8 Definc data wrangling ?
Ans. : Data wrangling is the process of transforming data from its
more digestible fomat and organizing sets from various original raw"
form intoa
sources into a
whole for further processing.
Q.9 Wh¡t is seaborn?
singular coherent
Ans. :

Seabom is aPython data visualization library based on

interface for drawing attractive and Matplotlib. It provides a high-level
opensource Python library. informative statistical graphics. Seabom is an
Its dataset-oriented,
declarative API. User should focus on what the
your plots mean, rather than on the details of how to draw different elements of
them.
Q.10 Which concept is used in data
visualization ?
Ans. : Data visualization based on
twO concepts:
1. Each attribute of
training data is visualized in a separate part of
2. Different class labels of screen.
training objects are represented by different colors.
PART B - (5 x 13 = 65 Marks)
Q.11 a) i) What is data science ?
Explain data science life cycle. |Refer section 1.1|
ii) How to define research
goals in datascience project ?
|Refer section 1.4]
|7+6]
OR
b) Discuss briefly data preparation. Explain each
|Refer section 1.6| steps indetails.
|13)
Q.12 (a) )What is qualitative and
quantitative data ? Explain diference berween qualitelne
and quantilutive data. |Refer
sections 2.1.1 and 2.1.2]
ii) Explain the
following
range. |Refer section
:
2.8| Runge, variance, standard deviation, interquartile
|7 +6]

TECHNICAL PUBLICATIONS0 an up-thust for knowledge

 Data Science
M-3 Solved Model Question Paper
of
Fonaatons,

OR

i)How draw graphs by using quntitative dhutu ?Eplain. |Refer section 2.4|
to
b Eyplainfrrqueny distributions for quantitutive duta.
|Refer section2,3.1| (6 +7|
a)
a13
i) Calculate coelicient of correlation fromthe following dautu.
12 8 10 11 13 7

14 8 6 9 11 12
|Refer example 3.1.4)
) What is linear regression ? List its advantages and disadvantages.
|Refer section 3.4.1] |6 +7|
OR

i) Compue Pearson's coefficient of correlation between maintains cost and sales as

below.
per the data given
Maintains cost 39 65 62 90 75 78 82 98 2536
Sales 58 6091 84 51 62 53 47 86 68
|Refer example 3.3.1]
i) What is correlation ? Explain coeficient and properties of correlation.
|Refer sections 3.1, 3.1.2 and 3.1.3] [6 +7|
04 al What is structured array? How to create structure array ? [Refer section 4.9]
i) Explain hierarchical indexing with example. (Refer section 4.11] [6 + 7|
OR
b) What is data wrangling ? Explain iterative steps of data wrangling.
|Refer section 4.1] |13)
Q15 a) What is scatter plots ? How tocreate scatter plot by using plt.scatter)and plt.plot
method ?Explain with example. (Refer section 5.2] |13]
OR
b) What is legend ? How legend helps for data visulation ? Explain various example.
|Refer section 5.6| |13)
PART C -(1 x 15 = 15 Marks)
Q16 a) i) Explain basic array manipulation of NumPy array. |Refer section 4.4|
) Define linear and nonlinear regression using figures. Calculate the value of 1
Jor X =100based on linear regression prediction method.
|Refer example 3.4.2] |15)

TECHNICAL PUBLICATIONS"- an up-thrust for nowledge

Foundations of Data Science M-4 Solved M
Model Question Paper
X
4 390
580
10 650
14 730
4 410
7 530
12 600
22 790
350
3 400
8
590
11 640
5
450
520
10
690
11
690
16
770
13
700
13
730
10
640

b) Explain various types of data OR

manipulation with Pandas. (Refer section 4.10) |1>]
DO0

TECHNICAL
PUBLICATIONS- an
up-thrust for knowledge