CM3005 Data Science: Course Description
CM3005 Data Science: Course Description
CM3005 Data Science: Course Description
Course description
Data science is a significant subfield in computer science. Data science has many application
areas ranging from medicine to climate science and business analytics. This module builds on
several topics covered in earlier parts of the computer science programme including
mathematics, databases, programming and graphics. It provides the skillset required to gather,
analyse and present data.
Target Audience
Students enrolled on BSc in Computer Science course
1
BSc Computer Science programme
Course outline
The course consists of ten topics that focus on key areas of the fundamentals of data science:
Key concepts:
1. Data Science in academia and industry
Topic 1. 2. Data types, data points and datasets
3. Python and Jupyter
Learning outcomes:
1. Understand the scope and impact of Data
Science
2. Familiarise with different types of data
3. Recognise structured and unstructured
data
4. Familiarise with the Python programming
language
5. Understand and use key features of
Python syntax
6. Familiarise with the Jupyter IDE
Key concepts:
1. Data points and datasets, qualitative and
Topic 2. quantitative data
2. Exploratory and Explanatory Data
Visualisation
Learning outcomes:
1. Manipulate data with NumPy
2. Use indices to extract sub-tables
3. Use NumPy functionality to obtain statistical
information from datasets
4. Perform basic Linear Algebra operations
involving vectors and matrices
5. Evaluate determinants, ranks and traces of
matrices
6. Use the pandas library to manipulate
datasets
2
BSc Computer Science programme
Key concepts:
1. Data points and datasets, qualitative and
Topic 3. quantitative data
2. Exploratory and Explanatory Data
Visualisation
Learning outcomes:
1. Define data visualisation
2. Articulate the importance and value of
visualising data
3. Describe the similarities and differences
between information and scientific data
visualisation
4. Explain how data visualisation can be
used at different stages in a data science
investigation
5. Identify practical applications of data
visualisation in a range of different
contexts
6. Articulate core principles of good
visualisation design
Key concepts:
1. Data points and datasets, qualitative and
Topic 4. quantitative data
2. Measures of central tendency, measures
of spread
Learning outcomes:
1. Define population and sample and
explain how these concepts are crucial in
making valid visual representations of
data
2. Distinguish descriptive and inferential
statistics
3. Apply appropriate visualisation
techniques to individual variables of each
variable type
3
BSc Computer Science programme
Learning outcomes:
1. Understand ML fundamentals
2. Use scikit-learn to apply ML techniques
3. Understand feature engineering and
model validation
Learning outcomes:
1. Understand text processing fundamentals
2. Apply text processing techniques
3. Manipulate unstructured data
Learning outcomes:
1. Understand NLP fundamentals
2. Use nltk to apply NLP techniques
3. Manipulate and analyse language data
4
BSc Computer Science programme
Learning outcomes:
1. Understand the underpinning theory of
graphs and networks
2. Use algorithms to traverse graphs and to
identify shortest and optimal routes
3. Use the Python programming language
and libraries such as Matplotlib and
NetworkX to build and visualise networks
4. Use the acquired knowledge and skills to
solve real-world network-related problems
and to develop and visualise large and
complex networks
5. Design and develop visualisation tools
presenting large and multidimensional
datasets
6. Evaluate visualisation approaches based
on their aesthetic, usefulness and the
ability to convey information
7. Choose appropriate visualisation
approaches based on the types of the
data points
8. Work with datasets with various
dimensions and sizes
5
BSc Computer Science programme
Learning outcomes:
1. Understand ML algorithms
2. Apply ML techniques to real-world data
3. Evaluate ML solutions
Learning outcomes:
1. Understand how data science concepts
and principles are applied in industry
2. Gain insight into the challenges faced by
data science practitioners
3. Compare and contrast different contexts
for data science practice
● Lecture videos introduce the main concepts of the topics and illustrate them with examples
● Practice quizzes will be used to reinforce your learning and understanding
● Activities drive the work that you do for each topic, where you are asked to solve
challenges of different types
● Graded assignments include a practical coursework assignment and a written exam.
● Discussions with your peers will help to guide your work and encourage you to explore
different types of solutions to problems
● Readings will help to reinforce your learning of concepts
6
BSc Computer Science programme
● Coursework: this will be assessed mid way through course. The coursework comprises a
variety of exercises which in total will take up to 25 hours of study time to complete.
● The examination will be two hours long, and consist of multiple choice questions and
longer written answers.