Sinfully Simple GPT-4 Prompting For Stunning Streamlit Interactive Maps
Author(s): John Loewen, PhD
Originally published on Towards AI.
Python Streamlit mapping code generation from NASA GIS data
Dall-E image: Impressionist style map of North America
Python Streamlit is a revelation for creating maps from GIS point data.
And as I recently discovered, if we prompt GPT-4 to help us create our Python Streamlit code, we can streamline the process.
To test this theory, today I am revisiting a story that I wrote back in April/2023 that leveraged GPT-4 for map creation.
I based the article on a static map that I viewed on LinkedIn, based on NASA data, showing forest fires for a region for a period of time.
A more useful representation for a static map is to provide the user/viewer with an interactive map — to let them choose the period of time to display.
Let’s give it a go!
The forest fire situation in Canada over the past 10 years or so has been pretty terrible, particularly in British Columbia, where I am from.
In the summer, there are many pollution days like this:
Forest fire smoke on the left, normal day on the right (Photo: David Loewen)
To show the monthly effects of forest fires, I want to create a data visual that shows forest fires over time (by month) for British Columbia, my home.
Now I know that NASA provides a comprehensive data… 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
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
