Master LLMs with our FREE course in collaboration with Activeloop & Intel Disruptor Initiative. Join now!


The Art of Prompting GPT-4: Python CSV Cleaning and Data Visual Code
Data Analysis   Data Visualization   Latest   Machine Learning

The Art of Prompting GPT-4: Python CSV Cleaning and Data Visual Code

Last Updated on April 3, 2024 by Editorial Team

Author(s): John Loewen, PhD

Originally published on Towards AI.

Simple creation of Python scripts for interactive choropleth maps
Dall-E image: image of an interactive choropleth map on a computer screen.

With simple modular prompting, GPT-4 is an awesome tool for generating Python code to clean and to visualize your data.

In combination with the right libraries, Pandas and Plotly, you can create interactive charts, and maps.

Let’s work through 3 steps together on how to do this:

cleaning a datasetcreating a choropleth mapcreating an animated choropleth map that illustrates data over time

Let’s get to it!

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

The file we want to download is the one highlighted below:

This UN dataset models projected population growth for the years 2022 to 2100.

After a quick first look, we can see that some data cleaning is in order. The actual data headers start on Row 17. So we can remove the first 16 rows of data (or just start our data retrieval in this row).

Now if we want to do a choropleth map to show each country over time (by heat map), then we really only want the rows that actually have a value for the 3-letter ISO field. We can see by the observation that if 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 ↓