[WORKSHOP 1]
Data Exploration and Visualization with Python and generative AI - by Enrico Glerean
Tickets↵
Duration:
Half-day workshop (4 hours) 09-13 on 05.06.2025
Half-day workshop (4 hours) 09-13 on 05.06.2025
Target Audience:
Anyone who wants to learn how to analyse and visualise data by themselves.
Anyone who wants to learn how to analyse and visualise data by themselves.
Prerequisites:
No prerequisites. This is a full hands-on workshop so you must bring a laptop with an internet connection. Only a web-browser is needed for completing the tasks. We will use popular python libraries like numpy, pandas, matplotlib, Altair, networkX.
No prerequisites. This is a full hands-on workshop so you must bring a laptop with an internet connection. Only a web-browser is needed for completing the tasks. We will use popular python libraries like numpy, pandas, matplotlib, Altair, networkX.
This workshop introduces participants to the fundamentals of data exploration and visualization with Python by using generative AI to write code. Generative AI tools based on large language models have been a fantastic technology that has empowered cognitive workers with skills that they did not have before. Great power comes with great responsibility, and while everyone can become a software programmer or data scientist after a vibe-coding conversation with ChatGPT, it does not mean that we can blindly trust these tools and stop learning how to code or work with research software engineers.
In this workshop we will use Python and ChatGPT to show how to analyse data including preprocessing, data exploration, and visualisation, without typing a single line of code (or almost).
Attendees will learn how to manipulate and visualize data effectively while understanding the risks of coding with generative AI assisted tools.
By the end of this workshop, participants will be able to:
Understand the limitations of code generated with large language models and the cybersecurity risks associated with it Manipulate and prepare data using Python Explore a variety of visualizations with the help of generative AI Develop the necessary critical mindset when working with data, code, and generative AI tools.
[WORKSHOP 2]
Introduction to Data Sonification with SuperCollider - by Andrea Valle
Tickets↵
Duration:
Full-day workshop (5 hours) | 09:00–12:00 13:00-15:00 on 05.06.2025
Full-day workshop (5 hours) | 09:00–12:00 13:00-15:00 on 05.06.2025
Target Audience:
Researchers, designers, artists, musicians, data analysts, and anyone interested in exploring sound as a medium for data representation.
Researchers, designers, artists, musicians, data analysts, and anyone interested in exploring sound as a medium for data representation.
Prerequisites:
No prior experience with SuperCollider is required. Basic programming knowledge is helpful but not necessary.
No prior experience with SuperCollider is required. Basic programming knowledge is helpful but not necessary.
This workshop introduces participants the process of transforming data into sound using SuperCollider, a powerful open-source environment for real-time audio synthesis. Participants will learn how to map data to sound parameters, create auditory representations of datasets, and explore algorithmic composition techniques to convey information through sound.
Key topics:
Introduction to Data Sonification: Understanding how data can be represented through sound and its applications in science, art, and design. SuperCollider Basics: Overview of the SuperCollider environment, syntax, and essential tools for working with sound. Mapping Data to Sound Parameters: Techniques for converting numerical data into pitch, rhythm, timbre, and spatialization. Algorithmic Sonification: Using SuperCollider’s pattern system to generate evolving, data-driven soundscapes. Hands-On Sonification Exercises: Practical examples using real-world datasets to reinforce concepts.
By the end of this workshop, participants will be able to:
Understand the principles and applications of data sonification. Use SuperCollider to generate and manipulate sound. Map datasets to sound parameters to create meaningful auditory representations. Experiment with algorithmic approaches to sonification.
[WORKSHOP 3]