COMP3260 Data Science Foundations

Computing & Information Systems · Core course

COMP3260 Data Science Foundations

Learn how data is collected, cleaned, explored, analysed and communicated. Build the practical foundations in Python, statistics and visualisation that carry you into machine learning, generative AI and evidence-based decision-making.

Explore the curriculum View syllabus
6 modules 18 units 153 tutorial pages 15 credits

Course overview

From raw data to defensible decisions

COMP3260 introduces the principles, methods, tools and practices of modern data science, with an emphasis on practical analysis using Python and contemporary data science workflows.

Data is only useful when it can be trusted, understood and explained. This course follows the full data science lifecycle: finding and acquiring data, preparing it for analysis, exploring it statistically and visually, and communicating what it means to a real audience.

Every unit pairs concept tutorials with hands-on work in Jupyter notebooks using authentic datasets. You will write code from the first week, but the focus stays on judgement — knowing which method is appropriate, why it works, and how to describe your results honestly.

COMP3260 deliberately stops short of machine learning. Instead, it builds the data literacy, statistical reasoning and communication skills that COMP328 and COMP329 assume you already have.

No machine learning required

This is a foundations course. Statistical regression is covered as a descriptive and inferential technique — predictive modelling and ML algorithms are introduced in COMP328.

Prerequisites

COMP101 or equivalent programming experience. Familiarity with basic Python syntax is helpful but not required — Unit 3 includes a full refresher.

Course details

Level
Undergraduate · Year 2
Credits
15 credits, one semester
Delivery
2 lectures and 1 laboratory session per week, plus guided self-study
Language & tools
Python 3, Jupyter, pandas, NumPy, Matplotlib, Seaborn
Assessment
5 assignments, 18 unit quizzes, midterm, final exam and a capstone project
Python Statistics Visualisation Ethics
Course structure at a glance
Module Focus Units Lessons
1 · Introduction to Data Science Data literacy, the data science lifecycle and the practitioner's toolkit 3 27
2 · Data Collection & Preparation Acquiring, cleaning and transforming real-world datasets 3 25
3 · Exploratory Data Analysis Descriptive statistics, visualisation and pattern discovery 3 27
4 · Statistical Foundations Probability, sampling, inference and statistical regression 3 25
5 · Applied Analytics Business, public-sector and time-series analytics 3 25
6 · Professional Practice Ethics, governance, storytelling and the capstone project 3 24
Total Six modules · eighteen units 18 153

Curriculum position

Where COMP3260 fits

COMP3260 is the first course in a four-course sequence that separates data science, AI literacy, machine learning foundations and advanced AI engineering.

  1. COMP3260 · Data Science Foundations
  2. COMP327 · Generative AI
  3. COMP328 · Machine Learning
  4. COMP329 · Advanced ML & Deep Learning

Learning outcomes

What you will be able to do

On successful completion of COMP3260 you will be able to work confidently across the entire data science lifecycle.

Data understanding

  • Explain the data science lifecycle and where each stage adds value.
  • Differentiate structured, semi-structured and unstructured data.
  • Identify appropriate data sources and collection methods.

Data preparation

  • Clean and preprocess datasets for analysis.
  • Handle missing, noisy and inconsistent data.
  • Perform feature engineering and transformation.

Statistical analysis

  • Apply descriptive statistical methods correctly.
  • Apply inferential techniques including hypothesis testing.
  • Interpret analytical results without overclaiming.

Data visualisation

  • Create effective, honest visualisations.
  • Select suitable charts and assemble dashboards.
  • Communicate data-driven insights clearly.

Data analytics

  • Conduct exploratory data analysis on real datasets.
  • Apply basic predictive analytics techniques.
  • Analyse messy, real-world data end to end.

Professional practice

  • Evaluate data quality and reliability.
  • Address ethical, privacy and governance considerations.
  • Produce professional analytical reports.

Curriculum

Six modules, eighteen units

Each unit is delivered as a sequence of tutorial pages: concepts, worked examples, Python walkthroughs, practice activities and a knowledge check.

How it works

A consistent rhythm for every unit

Each unit follows the same four-part structure, so you always know what is expected and how to prepare for assessment.

  1. Study the concept

    Each tutorial opens with objectives and a plain-language explanation, illustrated with worked examples.

  2. Run the code

    Follow along in Jupyter using provided notebooks and authentic, messy datasets.

  3. Practise and apply

    Complete guided lab activities, then apply the same techniques in graded assignments.

  4. Check your understanding

    Finish with self-check questions, a unit quiz and a short reflective summary.

Assessment

How your work is assessed

Assessment is weighted towards practical work. Five assignments build towards the capstone, with quizzes and exams confirming your conceptual understanding.

40%

Five assignments

Collection, cleaning, EDA, statistical analysis and a visualisation dashboard.

25%

Capstone project

An end-to-end data science project from problem definition to presentation.

15%

Final exam

Cumulative, covering all six modules with an emphasis on interpretation.

10%

Midterm

Modules 1–3: data literacy, preparation and exploratory analysis.

10%

Unit quizzes

Eighteen short online quizzes, one per unit, with unlimited attempts.

Weightings are indicative and confirmed in the course syllabus.

  • Assignment 1 Data Collection Project — collect and document an original dataset Brief
  • Assignment 2 Data Cleaning and Preparation — improve the quality of a supplied dataset Brief
  • Assignment 3 Exploratory Data Analysis — discover and interpret patterns in real data Brief
  • Assignment 4 Statistical Analysis Project — hypothesis testing and recommendations Brief
  • Assignment 5 Data Visualisation Dashboard — build and justify a professional dashboard Brief

Capstone

End-to-end data science project

The capstone runs across the second half of the course. You complete the entire data science lifecycle on a problem and dataset of your choosing, supported by twelve structured phases.

What you submit

  • Project proposal and stakeholder analysis
  • Dataset documentation and metadata record
  • Analysis notebook (cleaning through to statistics)
  • Visualisation package and dashboard
  • Final written report
  • Oral presentation

Portfolio ready

The capstone is designed to be published. With documentation and a reproducible notebook, it becomes a portfolio piece you can take to interviews.

  1. Problem IdentificationDefine a question worth answering and the decision it informs.
  2. Stakeholder AnalysisIdentify who needs the result and what they will do with it.
  3. Dataset SelectionFind, evaluate and justify an appropriate data source.
  4. Data CollectionAcquire the data and document its provenance.
  5. Data CleaningResolve missing values, duplicates and inconsistencies.
  6. Data TransformationEncode, normalise and engineer the features you need.
  7. Exploratory AnalysisDescribe, visualise and probe the data for structure.
  8. Statistical AnalysisTest your hypotheses and quantify uncertainty.
  9. Visualization DesignChoose charts and layouts that communicate honestly.
  10. Findings and InsightsTurn results into defensible, useful conclusions.
  11. Final ReportWrite up the project to a professional standard.
  12. PresentationPresent your findings and defend your method.

Tools & technology

The modern data science stack

Everything in COMP3260 uses free, open-source tools you can install on your own machine and keep using after the course ends.

Python 3 The core language for the entire course.
Jupyter Notebook environment for analysis and reporting.
pandas Loading, cleaning and reshaping tabular data.
NumPy Numerical Computing and array operations.
Matplotlib Foundational plotting and figure control.
Seaborn Statistical visualisation and distribution plots.

Questions

Frequently asked questions

Do I need prior experience with Python?

No. Unit 3 begins with a full Python review and an introduction to Jupyter notebooks. If you have programmed in any language before, you will be comfortable within the first two weeks.

Is machine learning covered in this course?

No — deliberately so. COMP3260 covers statistical regression as a descriptive and inferential technique, not predictive modelling. Machine learning algorithms are introduced in COMP328.

How much time should I expect to spend each week?

Plan for roughly 10–12 hours per week: two hours of lectures, two hours of laboratory work, and the remainder on tutorial pages, practice activities and assignment work.

What software do I need?

All required software is free and open source. We recommend the Anaconda distribution, which bundles Python, Jupyter, pandas, NumPy, Matplotlib and Seaborn in a single installer.

How is the course assessed?

Five assignments build progressively towards the capstone project, which carries the largest single weighting. Eighteen short unit quizzes, a midterm and a final exam confirm your conceptual understanding.

Can I choose my own dataset for the capstone?

Yes, and you are encouraged to. The only requirements are that the dataset is legitimately obtained, adequately documented, and suitable for the analytical techniques covered in the course.

Ready to start working with data?

Begin with Module 1, Unit 1 — an introduction to what data science is, what data scientists actually do, and how the field developed.

Start Unit 1 Download syllabus
👤