Postgraduate Course: Data Science for Design (DESI11100)
|School||Edinburgh College of Art
||College||College of Arts, Humanities and Social Sciences
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||This course provides an introduction to programming, used in support of the development of data science techniques, to give a practical facility in manipulating, analysing, visualising and contextualising data.
Through a series of lectures, practical sessions and a group project, you will be introduced to the importance of data, the details of how to work with it in a robust, communicative and defensible manner, and the computational grounding that underpins this work.
The ability to program fluently brings a qualitatively different view of the world, one which designers are increasingly required to be familiar with. Similarly, the ability understand the structure and meanings of data, and communicate this while maintaining awareness of the social context from which the data came is a key part of working in this field.
Through a series of lectures and workshops, you will be supported in developing a computational mindset, learning the tools of software carpentry, and developing a competence in writing and managing software. Building on this, you will develop an understanding of data, from the microformats used in individual fields to tools for engaging with large datasets. This includes: simple descriptive statistics; exploratory visual analysis; finding, combining and relating datasets (data wrangling); and an understanding of Open Data; and how to draw inferences from data. Data visualisation will be used for both exploration and presentation, drawing on techniques from data journalism. Alongside this, you will build up an understanding of the ways in which data relates to the world: the social and political structures of its collection and use, personal data, aesthetics and communication of findings.
Bringing this together around a particular problem will help you to understand how to collaboratively create software around data, and how to work with a problem holder to collect, analyse and present data sets of social relevance.
This course will:
1. Give a solid grounding in programming with Python, version control with Git and github and other key software practices.
2. Develop a comprehensive understanding of data formats, their wrangling and management, including CSV and relational databases (SQL)
3. Develop skills in the analysis and visualisation of a range of data using descriptive statistics and exploratory data analysis.
4. Introduce you to the socio-political ramifications of data collection and use.
5. Introduce rich collaborative practices around data collection, analysis and presentation.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| None
|Additional Costs|| Students must have a laptop.
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2020/21, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 11,
Seminar/Tutorial Hours 5,
Supervised Practical/Workshop/Studio Hours 16.5,
Formative Assessment Hours 2,
Summative Assessment Hours 1,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Additional Information (Learning and Teaching)
Tutorials and Supervised Practical hours will be taught in groups.
|Assessment (Further Info)
|Additional Information (Assessment)
||Assessment consists of 4 Components:
Component 1 (30% of course mark): Individual Report 1
You will design and implement in Python a scripted analysis of assigned datasets. Your work will be submitted as a Jupyter notebook. This Component addresses LO1, LO2, and LO3. Submission is around mid-semester.
Component 2 (30% of course mark): Individual Report 2
You will design and implement in Python an open-ended, scripted analysis of datasets that you may select from a range of peer contributions. Your work will be submitted as a Jupyter notebook. This Component addresses LO1, LO2, and LO3. Submission is towards the end of semester.
Component 3 (30% of course mark): Group Project
Working in a small team, you will analyse a particular problem holder┐s dataset and communicate the results by appropriate means. A single mark is given to all members of your group. The submission may be a detailed report, or a short report plus an appropriate artefact(s). This Component addresses LO1, LO2, and LO3. Submission is towards the end of semester.
Component 4 (10% of course mark): Repo Contributions
Throughout the course you will contribute to shared code and data repositories, and online group discussions, in line with LO4. Your various contributions will be assessed, leading to an overall mark for the Repo Contributions Component.
||Formative feedback will be provided verbally during weekly tutorials.
Written formative feedback will be provided on initial submission of 1st and 2nd outputs.
Summative feedback will be provided following the submission of all outputs (individual reports and group work) at the end of the course.
|No Exam Information
On completion of this course, the student will be able to:
- Program: Identify and deploy strategies for writing, understanding and managing computer programs using Python and version control
- Data: The ability to wrangle, analyse, learn from and visualise a range of data, in a way that demonstrates its relevance to particular contexts of enquiry
- Communicate: Communicate around socially relevant issues, supported by the use of multiple data sources and appropriate analysis
- Professionalism: Working in collaborative, interdisciplinary teams to a high professional standard.
|Creative Code, John Maeda|
R for Data Science, Garret Grolemund and Hadley Wickham
Python for Software Design: How to Think Like a Computer Scientist, Allen B. Downey, Jeff Elkner and Chris Meyers, Green Tea Press
Doing Data Science: Straight Talk from the Frontline, Cathy O'Neil and Rachel Schutt
The Visual Display of Quantitative Information, E. Tufte
Effective Computation In Physics - Field Guide to Research with Python, Scopatz and Huff
Data Flow 2: Visualizing Information in Graphic Design, Klanten, Ehmann, Bourquin and Tissot
|Graduate Attributes and Skills
expertise in tabular data and relational databases (SQL)
exploratory data analysis
|Keywords||data science,data analysis,computer programming,visualisation,software carpentry
|Course organiser||Dr David Murray-Rust
|Course secretary||Ms Jane Thomson
Tel: (0131 6)51 5713