[Online] AI has become a reasonable tool for producing data visualizations without coding or learning Excel, Tableau, or other software, but expertise is still required to guide it to an effective chart. In this introductory workshop we'll show you an example of uploading public data to ChatGPT, prompting past the initial (usually pretty bad) first draft, then finishing by downloading the script that produced the final chart as a record for reproducibility. We'll also discuss strategies for checking the results and things to watch out for so you can verify the LLM's output. Finally, if you have access to a LLM (e.g., ChatGPT, DukeGPT, Claude.ai, MS Copilot) that lets you upload a CSV or PDF file, we'll give you some new data and a chance to try the process yourself. This event is open to non-Duke participants.

A zoom link will be sent via email to registered participants to join the workshop.

The content of the workshop may be recorded. If you are uncomfortable with a recording being published, please contact the instructor at anytime prior to the conclusion of the workshop.

Data Visualization