Sure Fire GPT-4 Prompting For Better Python Voila Data Viz Results

Author(s): John Loewen, PhD

Originally published on Towards AI.

Displaying UN human rights data with Voila, GitHub and myBinder.org

This member-only story is on us. Upgrade to access all of Medium.

Sharing data visualizations from Jupyter Notebooks can be challenging, especially for non-technical users who struggle with running Python code.

The combination of GPT-4’s coding capabilities and Voila’s ability to convert Jupyter Notebooks into interactive dashboards opens up a useful workflow for creating and sharing data visualizations — even for users with limited coding experience.

By prompting GPT-4 to generate complete, working Python code, you can skip manual setup and jump straight to customizing and deploying interactive data visualizations.

With GPT-4 handling the code, your focus can stay on the data.

Pairing Voila with GitHub and MyBinder.org allows you to publicly host and share these dashboards with only a few clicks.

Let me walk you through using GPT-4 prompts to create a fully functional interactive data visualization from the CIRIGHTS Human Rights dataset, powered by Plotly for visualizations and Voila for sharing the final product through GitHub and MyBinder.org.

Before we begin, you need to have Jupyter Notebook and Voila installed. You can install Jupyter from a command (terminal) prompt using “pip install jupyter”.

Once installed, you can create a new notebook within your Jupyter environment, and then add the Voila library:

Now that we have the right… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI