DSA 2019 Summer School on Machine Learning and Data Science

In the tradition of previous Africa Data Science workshops, a summer school on machine learning and data science was held prior to the main workshop. This summer school targeted graduate students, researchers, and professionals working with large amounts of data or unique datasets.

The summer school focused on introductory and advanced lectures in data science and machine learning, as well as moderate to advanced practical and tutorial sessions where participants got hands-on experience wrangling and processing datasets and applying cutting-edge machine learning techniques to derive insights from data. Lectures were delivered by distinguished, world-renowned researchers and practitioners, including experts from Sheffield University, Amazon, Swansea University Medical School, Facebook, Pulse Lab Kampala, the AI and Data Science (AIR) Lab–Makerere University, ARM, and Dedan Kimathi University of Technology (DeKUT).

The school also involved end-to-end tutorial sessions led by professionals who guided participants through real data analytics problems, from data acquisition to data presentation.

Lecture Schedule
Pre-workshop
Software Installation
To ensure participants were well-prepared, they were required to install the prerequisite software and test it beforehand to confirm it was working on their computers. Although the summer school venue provided some computers with the software preinstalled, participants were advised to bring their own laptops with the software ready.

Anaconda
All the required software had been prepackaged in a bundle called Anaconda. Participants downloaded the appropriate versions for their laptop operating systems and architectures from the Anaconda website, specifically the Python 3.6 version. Detailed installation instructions were provided alongside the download links on the website.

Preliminary Exercises
To ensure everything worked correctly and to get participants familiar with the tools, they were required to download a Jupyter notebook file (via “right click and save as”) and complete the exercises provided. To access the notebook, participants launched Jupyter Notebook following the provided instructions.

Troubleshooting and Comments
Participants used the comment section to ask questions that had not already been addressed and to help their peers by providing answers whenever possible.

Summer School Day 1
The first day of the summer school introduced participants to Jupyter Notebook and provided an overview of using Python for data analysis. The day also introduced the machine learning technique of classification and included lab practicals exploring these methods, along with an introduction to the fundamentals of the Internet of Things (IoT).