Set- B
Register
Number
SRM Institute of Science and Technology
College of Engineering and Technology
School of Computing
SRM Nagar, Kattankulathur– 603203, Chengalpattu District, TamilNadu
AcademicYear:2025-26(Even)
Test: FT II Date: 24-02-2026
Course Code & Title: 21CSS303T & Data Science Duration: 50 Minutes
Year& Sem: III Year /VI Sem Marks: 25
Course Articulation Matrix:
Course
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
Outcome
CO1 - - - - 1 - - - - - - -
CO2 - - - - 1 - - - - - - -
Note:
CO1 - To understand the relationship between data
CO2 - Identify the different data structures to represent data
Part– A
(5x2= 10 Marks)
Answer ALL the questions
[Link] Question Marks B CO PO PI.
L Code
1 Distinguish data lake and data warehouse. 2 2 1 5 5.1.1
2 Define numerical and categorical data. 2 1 1 5 5.1.1
Numerical Data:
Numerical data represents quantitative values that
can be measured and expressed in numbers. It can be
discrete (e.g., number of students) or continuous (e.g.,
height, weight).
Categorical Data:
Categorical data represents qualitative values that
describe categories or groups. It cannot be measured
numerically (e.g., gender, color, department).
3 Recall the purpose of NumPy arrays compared to Python 2 1 2 5 5.1.1
lists?
NumPy arrays are used for efficient numerical
computations and support vectorized operations, making
them faster and memory-efficient for large datasets.
Python lists are general-purpose data structures that can
store different data types but are slower for mathematical
and scientific calculations.
4 Infer the function [Link]((2, 3)) return? 2 2 2 5 5.1.1
[Link]((2, 3)) returns a 2 × 3 NumPy array filled with
zeros.
That is, it creates 2 rows and 3 columns where all
elements are 0.0 (by default, float type).
5 Illustrate on how do you select multiple columns from a 2 2 2 5 5.1.2
Pandas DataFrame?
df[['Column1', 'Column2']]
Part– B
(3x5= 15 Marks)
Answer ALL the questions
Q.N Question Mark B CO P PI.
o s L O Cod
e
1. Illustrate the different types of data used in Data Science. 5 3 1 5 5.3.2
Illustrate each type with real-world examples and discuss
how the nature of data influences the choice of storage,
processing, and analysis techniques.
2. A teacher stores the marks of 10 students in a 5 3 2 5 5.3.2
NumPy array for easy analysis. She wants to check
the mark of a particular student, view the marks of a
group of students, and understand how NumPy helps
in handling such numerical data efficiently.
a) How can the teacher create a NumPy array
and use indexing to access the mark of a
specific student? (3 marks)
The teacher can first import NumPy and create an array
to store the marks of 10 students.
import numpy as np
marks = [Link]([78, 85, 92, 67, 88, 73, 90, 81, 76, 84])
To access the mark of a specific student, she can use
indexing (index starts from 0).
Example:
To get the mark of the 3rd student:
marks[2]
This returns 92.
Thus, NumPy allows fast and easy access to numerical
data using indexing, making analysis efficient.
b) How can slicing be used to obtain the marks
of the first five students or any selected group
of students? (2 marks)
Slicing in NumPy is used to access a range of elements
using the format:
array[start:end]
To obtain the marks of the first five students:
marks[0:5]
This returns the marks of students from index 0 to 4.
Similarly, any selected group can be accessed by
changing the start and end index values.
3. A company maintains employee data in a Pandas 5 4 2 5 5.2.1
DataFrame with columns such as Employee ID,
Name, Department, Salary, and Experience. During
analysis, the HR team wants to examine the data,
perform basic operations, and extract meaningful
insights. Demonstrate on the following:
a) How can you load the dataset into a Pandas
DataFrame and display the first few records?
(1 mark)
The dataset can be loaded using read_csv() and the first
few records can be displayed using head().
import pandas as pd
df = pd.read_csv("employee_data.csv")
[Link]()
This loads the dataset into a Pandas DataFrame and
displays the first five records.
b) How can you select specific columns (for
example, Name and Salary) and filter
employees with Salary greater than 50,000? (2
marks)
You can select specific columns using double brackets
and apply a condition for filtering.
df[['Name', 'Salary']][df['Salary'] > 50000]
This displays only the Name and Salary columns for
employees whose salary is greater than 50,000.
c) How can you compute basic statistical
measures (such as mean salary) using
Pandas? (2 marks)
You can compute the mean salary using the mean()
function in Pandas.
df['Salary'].mean()
This calculates and returns the average salary of all
employees.
Alternatively, to get multiple statistics:
df['Salary'].describe()
This provides count, mean, standard deviation,
minimum, and maximum values.
Course Outcome (CO) and Bloom’s level (BL) Coverage in Questions