MODULE INFORMATION

OVERVIEW:

Module Name: Data Science Principles

Module Code: ITS65704

This module is designed to expose students with a range of topics related to data science. It covers various facets of data science practice, including
data collection, to processing, analysis and visualisation and effective communication. Focus in these topics will be on breadth, rather than depth, and
emphasis will be placed on integration and synthesis of concepts and its applications used to solve problems. The module delivery will include lecture
sessions, tutorials, hands -on exercises and invited talks from expert data science practitioners. Assessment for this module includes a test, a group
project which will give a platform for students to apply the knowledge of data science process and finally a 2 hours final exam to test the overall
principles and applications covered in this module

1
Name(s) of academic staff teaching the module, module leader and staff email:
Staff teaching the module: Dr Thulasyammal Ramiah Pillai
Module leader: Dr Thulasyammal Ramiah Pillai

Year-level: 2

Semester Offered: March (Long) / August (Long) (Choose 1 or more)

Credit Value: 4

Pre-requisite: Nil

Co-requisite: Nil

Anti-requisite: Nil

School offering the module: School of Computer Science and Engineering

Module offered as: Specialization, Minor, Free Elective, Extension (Choose 1 or more)

Programme Name: Bachelor of Computer Science (Hons), Bachelor of Software Engineering (BSE), Bachelor of Information Technology (BIT)

Domain Name (for free electives only): N/A

2
LEARNING OUTCOMES:

Upon completion of the module you should be able to:

Module Programme
Learning Learning Assessment/s
Outcome Outcomes
1 Describe principles, processes models and algorithms data science. 1/TGC1.1, 1.2 4
Apply exploratory data analysis on data with the help of summary statistic
2 2/TGC2a.3 1,4
and graphical interpretation
Apply suitable data science algorithms to solve a problem for a given data
3 7/TGC4.1,4.2 2
set from a specific domain
4 Interpret and present the output of implemented data science algorithms 5/TGC3.1 3

3
TEACHING, LEARNING AND ASSESSMENT

Description of assessment components:

Module Learning Programme Learning

Assessment Task Weight Due Date
Outcomes Assessed Outcomes Assessed

Assessment Task 1: In Class Test

20% 2 2 Week 5

Assessment Task 2: Group

Assignment 30% 3 7 Week 11

Assessment Task 3: Presentation

10% 4 5 Week 12

40%
Assessment Task 4:
MLO 1 - 20% 1,2 1 Final Exam Period
Final Exam
MLO 2 - 20%

4
Teaching and learning approach:

MLO 1 Assessment Task/Activities

Final Examination (20%)
Students are required demonstrate their understanding on data science principles for a given scenario
Describe principles, processes models and in the final examinations.
algorithms data science.
.

Teaching and Learning Activities:

MLO1 is achieved after students have been exposed to the principles in data science domain as well as its concept application for real world case
studies.
Each student is required to understand the concepts outlined in each topic and demonstrate the understanding during in the tutorial sessions. In the
tutorial sessions, students are required to confidently discuss data science problems, both orally and in writing.

MLO 2 Assessment Task/Activities

Apply exploratory data analysis on data with In Class Test and Final Examination
the help of summary statistic and graphical Students are required to apply problem solving skills to evaluate and solve a given problem or
interpretation scenario using data science principle. There are two assessments to be completed to achieve this
learning outcome.
In Class Test (20%)
Students are required to complete one written test during the semester to assess the knowledge
acquired on data science principles. Test will consist of short answer and discursive questions.
Students should be able to apply exploratory data analysis on a data set to test its hypothesis,
discuss and solve the given scenario presented in this test with the appropriate data science principles
and tools covered in the first 5 week of the semester.
Final Exam (20%)
Students are required to discuss in writing on the identified data science principles for a given state of
problem. They should be able to explain, illustrate or give appropriate examples to justify the answer.

5
Teaching and Learning Activities:
MLO 2 is achieved after students have demonstrated the understanding of the concepts introduced in each chapter via implementation. The tutor
facilitates students through tutorial and practical computer laboratory tasks

MLO 3 Assessment Task/Activities

Apply suitable data science algorithms to Group Assignment 20%
solve a problem for a given data set from a Students are required to apply problem solving skills to evaluate and solve a given problem data
specific domain science algorithms. Students will work in a group and pick problems from a pre-prepared set. They will
be assessed on their problem-solving ability, understanding of data science techniques and
communication skills.
Teaching and Learning Activities:

To achieve MLO 3, students are required to work in a team to design, develop and solve identified problem in each domain using data science
algorithms which they have learned in this module. Interim review and critique of design are conducted progressively to provide feedback on
students’ conceptual ideas / design strategy and its development to solve the given problem.

MLO 4 Assessment Task/Activities

Students are required to present orally and submit a written documentation explaining the
application the data science algorithms identified to solve the given problem. Student should also be
Interpret and present the output of
able to demonstrate their ability to interpret the output of data science algorithms used in the group
implemented data science algorithms
assignment. The report must have a section which shows the critical thinking and logical thinking skills
used to solve the given problem
Teaching and Learning Activities:
MLO4 is achieved by asking students to present the program which has been developed earlier. Students are required to present and show the
achievement of solving the problem using the appropriate algorithm. The results should be clearly discussed and justified in an appropriate
documentation.

6
Details of each assessment task:

In Class Test: 20%

Each student is required to take a 2 hours test testing them on the topics covered in the first five week of this module. In the test, they have to solve the 2
to 3 problems using data science principles, process and tools.

Assessment 2: Group Assignment: Implementing Data Science Algorithms for a data set from a given domain: 20%

Students are required extract or collect a set of data from a repository and perform the analysis based on the given scenario to solve a problem in the
identified area. Once the data is extracted the appropriate data cleaning methods should be applied to clean the raw data before the analysis is performed.
Once the clean set of data obtained students are required to use the appropriate model and algorithms derive the data model which will be further used in
the data visualization phase. The data model is derived and should be used for data visualisation. Students are required to prove the developed data model
can be used for decision making or solve the specific problem identified at the beginning of the assignment. This is a group assignment.

Assessment 3: Program Presentation 20%

Project presentation. Each group is given 15 minutes for project presentation. All members of the project MUST participate on the project presentation.
The students must be able to confidently explain and justify how they used data science principles, process, algorithms and tools to solve the problem.
Project Report: Each group must submit a detailed report explaining the details of the data science process applied, the algorithms
implemented to solve the problem. The report should also extensively discuss the results of the algorithm implementation

Assessment 4: Final Exam 40%

This assessment is a 2-hour closed book examination which will test the concept and implementation covered in this module. Students are required to
answer 4 out of 5 question.

7
8
 Rubrics for Each Assessment Task

Assessment 1: Test (20%)

Test will be marked according to the marking scheme.

Assessment 2: Group Assignment (20%)

 Data Extraction: 5%
 Data Cleaning: 5%
 Data Analysis using the appropriate algorithm: 5%
 Data Visualisation: 5%

Assessment 3: Program Presentation (20%)

 Project Report: 10%

 Oral Presentation: 10%

Assessment 4: Final Examination (40%)

Scoring will be following marking scheme provided.

Hurdle assessment guideline for the module:

A student must achieve at least 50% for the overall assessment and a final grade of C to pass the module. A student who obtains a minimum of 40% for the
overall assessment and overall grade of D or higher for the module may be allowed to resit the examination. The maximum passing grade awarded for the
resit examination will be a grade C.
A student who obtains 39% and below for the final assessment, will result in failing the module irrespective of the overall marks earned, even though
he/she has achieved 50% or more in the overall assessment. He/she will not be allowed to resubmit the final assessment

9
STUDENT LEARNING TIME

Student Learning Time (SLT) per topic/week of the content outline (SLT mapping against MLO, Teaching & Learning Activities [Guided Learning F2F
(L,T,P,O), NF2F & Independent Student Learning Time]:

Guided Learning: Guided Learning: Independent Assessment Assessment Assessment Student

Face-to-Face Non-Face-to-Face Student Learning Tasks Tasks Tasks Learnin
Lecture, Tutorial Online Learning Time (Face-to-Face) (Online) (Independent g Time
Date/Week Practical, Other Student (SLT)
Learning Time)

Hours Hours Hours Hours Hours Hours Hours

Week 1 1h 2 3
L: Introduction to
Introduction to Data Science Data Science
Processes Processes

Week 2 2h (1L, 1P) 2h 8 12

L: Basics of Statistical
Basics of Statistical Inference Basics of Statistical Inference
 Populations and samples Inference
 Statistical modelling,
probability distributions,
fitting a model
P:
Basics statistical tools

Week 3 2h (1L, 1P) 2h 8 12

L: Exploratory Data Exploratory Data
Exploratory Data Analysis (EDA) Analysis (EDA) Analysis (EDA)
 Philosophy of EDA
 Data Science Process
P:
 Basic tools (plots, graph and
summary statistics) of EDA

10
Week 4 2h (1L, 1P) 2h 8 12
L: Exploratory Data Exploratory Data
Exploratory Data Analysis (EDA) Analysis (EDA) Analysis (EDA)
 Philosophy of EDA
Data Science Process
P:
 Basic tools (plots, graph and
summary statistics) of EDA

Week 5 2h (1L, 1P) 2h 8 2 14

L: Machine Learning Machine Learning Assessment 1:
Machine Learning Algorithms Algorithms Algorithms Practical Test
 Linear Regression (20%)
 K-Nearest Neighbours
 K-means
P:
Machine learning tools and
libraries

Week 6 2h (1L, 1P) 2h 8 12

L: Machine Learning
Machine Learning Algorithms Algorithms
 Linear Regression Machine Learning
 K-Nearest Neighbours Algorithms
 K-means
P:
Machine learning tools and
libraries

Week 7 2h (1L, 1P) 2h 8 12

L: Machine Learning Machine Learning
Machine Learning Algorithms Algorithms Algorithms
 Linear Regression
 K-Nearest Neighbours
 K-means

11
 P:
Machine learning tools and
libraries

Week 8 5h 10 15
Extracting Meaning Extracting Meaning
from Data from Data

Feature selection
algorithms

Feature extraction
libraries and tools

Week 9 2h (1L, 1P) 2h 8 12

L: Extracting Meaning Extracting Meaning
Extracting Meaning from Data from Data from Data
 Feature selection algorithms
P:
Feature extraction libraries and
tools

Week 10 2h (1L, 1P) 2h 8 12

L: Data Visualization Data Visualization
Data Visualization
Basic principles, ideas and tools
for data visualization
P:
Data Visualization tools

Week 11 2h (1L, 1P) 2h 8 12

L: Data Visualization Data Visualization
Data Visualization
Basic principles, ideas and tools
for data visualization

12
 P:
Data Visualization tools
Week 12 2h (1L, 1P) 2h 8 1 13
L: Graph Processing Graph Processing Assessment 2:
Graph Processing Group
 Social Network as graphs Assignment-
 Clustering graphs (30%)
 Directory discovery of Assessment 3:
community in graphs Presentation
 Partitioning in graphs (10%)
 Neighbourhood properties
in graphs
P:
Graph processing and
visualization (tools and libraries)

Week 13 2h (1L, 1P) 2h 8 12

L: Graph Processing
Graph Processing Graph Processing
 Social Network as graphs
 Clustering graphs
 Directory discovery of
community in graphs
 Partitioning in graphs
 Neighbourhood properties
in graphs
P:
Graph processing and
visualization (tools and libraries)

Week 14 2h (1L, 1P) 2h 8 12

L: Data Science and Data Science and
Data Science and Ethical Issues Ethical Issues Ethical Issues

P:
Data Science and Ethical Issues

13
 case study and discussion
Week 15
Preparation of
final exam
Week 16
Assessment 4:
Final Exam (40%)

29 108 3 160
TOTAL 25
Hours

14
REFERENCES:

Main References supporting the module:

1. Cathy O’Neil abd Rachek Schutt.(2014) Doing Data Science , Straight Talk from the FrontLine. O’Reilly Media

OTHER:

Other additional information:

1. Ozdemir, S. (2016). Principles of Data Science. Birmingham: Packt Publishing
2. Provost, F., Fawcett, T. Data Science for Business: What You Need to Know about Data Mining and Data-analytic Thinking. O’Reilly Media

Special requirements to deliver the module: NIL

15