Towards AI Can Help your Team Adopt AI: Corporate Training, Consulting, and Talent Solutions.

Publication

Simple Streamlit Sliders: Intaractive Map Visuals with GPT-4 Prompting
Data Visualization   Latest   Machine Learning

Simple Streamlit Sliders: Intaractive Map Visuals with GPT-4 Prompting

Author(s): John Loewen, PhD

Originally published on Towards AI.

Prompt engineering for interactive Python Streamlit maps
Dall-E image: A choropleth map on a screen with a pleasing view in the background

Interactive choropleth maps are powerful tools for visualizing and understanding complex datasets related to geographical areas.

Streamlit turns Python scripts into shareable web apps in minutes, no front-end experience required.

For data scientists and developers looking to provide interactivity for their users, Streamlit is the Python framework that can easily provide it.

And better yet, if we have a data set that we want to use, we can prompt GPT-4 to generate the Python code for us to create a pandas data frame — and to plug it into our Streamlit code!

Let’s step through how to do this with two awesome choropleth map examples:

single slider for yearly global choropleth map visualizationdual slider for year range global choropleth map visualization

For our first example, let’s create a choropleth map that uses a slider to navigate through yearly UN Global Peace Index (GPI) data.

This dataset can be downloaded from the website visionofhumanity.org. The GPI contains a numerical value indicating the relative peacefulness of 163 countries over a 15 year period (2008–2022).

This allows users to see how peace levels in different countries have evolved over time. Once we have downloaded the file, we… 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

Feedback ↓