GPT-4o Python Charting Insanity: Prompting For Instant Data Visuals

Author(s): John Loewen, PhD

Originally published on Towards AI.

Hands-on no-code visuals from the UN population projection dataset

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

The automatic data visualization generation tools for GPT-4o keep getting better and better.

You can upload multiple CSV (and XSLX) files and ask GPT-4o to look at them and provide you with a list of the structure and data values in the file.

AND you can then prompt this LLM to create Python code to clean the data AND provide data visualizations of charts and maps.

This is incredibly useful. Let me show you how it works.

For this exercise, we will be using a population projection dataset from the UN Department of Economic and Social Affairs website (HERE).

You can click on the “Probabilistic Projections”, “Population Percentage” and then “Population by Age — both sexes” . Visually, this is what you should see:

Downloading XLSX worksheets for probablistic population projections by age

The file downloads as an xlsx with multiple worksheets. I selected the “Median” worksheet, deleted the first 15 rows of descriptive information and exported this as a CSV called “pp_median_country.csv”

A recent article in the New York Times used this data set to highlight countries that are projected to have “aging” populations — putting a heavier strain on such things as national pension plans… 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