DSM050 Data Visualisation Coursework 2 – October 2024 to March 2025 Study Session

Programme: MSc Data Science, University of London

Module: Data Visualisation (DSM050)

Submission deadline: Monday 10 March 2025, 13:00 BST

Weighting: 70% of the final module mark

Word limit: 3,500–4,500 words (maximum 4,500 words, excluding references and appendices)

Assignment Specification

Produce a report as a PDF file (3,500–4,500 words) based on a Jupyter Notebook of a data visualisation-led investigation that is different from coursework assignment 1. Your project must be based on the analysis of two datasets found online and publicly accessible. Be careful with Kaggle datasets that already have multiple Python analyses, as this will reduce your score.

• Write your report as a Jupyter Notebook using inline markdown.
• Submit a PDF hard copy of the notebook (using “print to PDF” in the browser is fine).
• Submit a ZIP file containing your notebook (.ipynb), a copy of the public data used, and any supplementary scripts. Do not put the PDF inside the ZIP.
• Put supplementary information not essential to the main report in appendices. References and appendices do not count towards the word limit, and no marks are awarded for material in appendices.
• No marks will be awarded for analysis discussion written as comments in code cells.

Report Guidelines

1. Research Topic and Background (15%)

• Introduction: overview of the topic, relevant news or research articles, research objectives and motivation, and an overview of key findings.
• Research question(s): population and sampling method, explicitly stated research question(s), and a scope appropriate for the assignment.
• Domain concepts: clearly define important terms and concepts in the study.

2. Data Sources (5%)

Briefly explain how you use the two datasets in this project:

• Where and how did you find them?
• How and why was the data initially collected?
• Are there any ethical or legal issues?
• Critically evaluate your data: is it trustworthy and valid for your purposes?

3. Data Overview and Pre-processing (10%)

• Data types and pre-processing: brief description of key variables, justification of data cleaning and pre-processing (tidy data), and handling of missing or erroneous data.
• Data summary statistics: number of observations, summary of demographics and key variables, using tables or easily understandable quantities in prose.

4. Analysis (50%)

• Visualise key variables and the relationships between variables.
• Aim for high-quality explanatory visualisations that describe or tell a story about the behaviour or phenomena under investigation.
• Aim for one high-quality advanced visualisation (chosen from topics 6–10).
• Marks are awarded for appropriate plots for variable data types, presentation quality, visual communication, and a methodical data visualisation process.

5. Conclusion and Evaluation (10%)

• Summarise key findings.
• Discuss future directions.
• Evaluate your process and visualisations.
• Identify things to improve and/or pointers to future research.

6. Code (10%)

• Submit all Python code in your notebook (.ipynb file).
• Implement all pre-processing and data cleaning in code for transparency and reproducibility – do not manually edit data in a spreadsheet or hard-code data values.
• Keep code legible, with brief comments.
• Re-using and adapting code from documentation or online is acceptable if sources are attributed (web link and date accessed); re-using code covered in the module is encouraged.
• Make sure all code runs correctly before submission.

Word Count Penalties

You must state an accurate word count (excluding the reference list) at the end of your work, or 5 marks will be deducted.