Module and Programme Catalogue

Search site

Find information on

2022/23 Taught Postgraduate Module Catalogue

GEOG5402M Data Science for Urban Systems

15 creditsClass Size: 50

Module manager: Vikki Houlden

Taught: Semester 1 (Sep to Jan) View Timetable

Year running 2022/23

Pre-requisite qualifications


Module replaces


This module is not approved as an Elective

Module summary

This module will provide a foundation in data science training, introducing concepts in data handling, exploratory data analysis, machine learning, and visualisation. The course will provide students with opportunities to work with a variety of spatial and spatiotemporal datasets relating to urban systems (e.g. transport data, demographics, morphologies). The course will embed good practice in data science production through code notebooks, and in open science methods (e.g. through GitHub). The course will aim to become language agnostic, but beginning by providing code and opportunities to submit assessments in a specified programming language, which will allow students to shape their learning to match optional course requirements.


This module will introduce students to urban data science, providing a thorough foundation of data sets, analytics and applications across a diverse range of contemporary urban contexts. It will develop an understanding of the appropriate steps and techniques for effective data processing and visualisation, fostering independence and confidence in coding though practical approaches, utilising notebooks and open science methods

Learning outcomes
1. Understand and apply all steps of data handling and analytics, including wrangling, description, analysis, machine learning and visualisation

2. Understand the core concepts and applications of regression, clustering and classification methods and machine learning techniques, to identify and perform the appropriate implementation of each

3. Become comfortable working with a range of non-spatial, spatial, and temporal datasets, understanding their application to a range of different urban systems

4. Be able to select and perform appropriate visualisations according to the data, and utilise these to clearly present their data and findings

5. Be proficient in creating and presenting comprehensive code notebooks in Python

6. Understand the benefits and practical applications of working with and creating their own open science methods


1. Introduction to Urban Data Science
2. Data Wrangling
3. Statistics and Visualisation
4. Regression
5. Clustering
6. Classification and Machine Learning
7. APIs and Social Media
8. Spatial Analysis
9. Temporal Analysis
10. Evaluation and Validation

Teaching methods

Delivery typeNumberLength hoursStudent hours
Private study hours120.00
Total Contact hours30.00
Total hours (100hr per 10 credits)150.00

Private study

Private study will involve some background reading on urban data science applications, consolidation of the lecture content, and completion of the data science tasks set during the practical lab sessions.

Opportunities for Formative Feedback

Follow up tasks will be provided during each lab for self-study. Three of these will be practice tasks and/or reading, to gain practice and build confidence, 4 will be short data exercises which will be submitted the following week for formative feedback. Students will have chance to ask any questions and begin these during the labs. The remainder of the weekly tasks will be summative.

Methods of assessment

Assessment typeNotes% of formal assessment
ReportData analytics project task, addressing an urban issue, presented as a markdown notebook (3000 words equivalent)80.00
Computer ExerciseData science tasks with lab support20.00
Total percentage (Assessment Coursework)100.00

Labs will include tutorials for implementing lecture content through Python in a notebook The assessment will comprise 2 summative tasks, worth 10% each, and a larger data task worth 80%. The two 10% tasks will be based on content from multiple weeks and building on previous labs; they will be set during weeks 6 and 9 and due the following week. The data task will be a larger, independent project where students will put all their skills into practice and do some real-world urban data science! This will be set during week 7, with time during the week 7 and 9 labs to get feedback and begin making progress. They will collect/obtain their own data, generate hypotheses, and perform data-wrangling, visualisation and appropriate analyses to test their hypotheses. They will submit their fully described (including introduction, background literature, data, methods, results and reflection) code notebook in S2W2, which allows time after the winter vacation for any additional support before the deadline.

Reading list

The reading list is available from the Library website

Last updated: 29/04/2022 15:32:21


Browse Other Catalogues

Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD

© Copyright Leeds 2019