The Evolution of GPT-4: Crafting Python Plotly Dashboards With Ease

Author(s): John Loewen, PhD

Originally published on Towards AI.

How much has GPT-4 improved at this task? Let’s find out!
Dall-E 2 image: impressionist style of a dashboard with a global map and 2 charts

A few months ago, I wrote a series of (moderately successful) articles on how to prompt GPT-4 for Python plotly dashboard creation.

Back then, I ran into some limitations on the capabilities available.

Recently, GPT-4 has made some great strides forward in analyzing CSV files and visualizing data in the main GPT window.

Now GPT-4 can handle on-the-fly visualizations using the matplotlib library. But not using the Plotly library — at least not yet.

Knowing that GPT-4 it is not yet able to handle Plotly visualizations, can it do the next best thing —can it handle the task of seamlessly creating complex plotly dashboard code?

Can it create Python code that I can just copy/paste into my Python editor, Save, and click Run?

My task (and hope) with this exercise is that with GPT-4 it is now truly that simple.

Let’s give it a go.

To accomplish this complex data visualization task, let’s start with a useful dataset, similar in structure to what I used in my old series of articles.

I have downloaded a useful dataset on global literacy rates over time, as a CSV file. It can be found HERE.

Now I know from… 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