How to R code faster with ChatGPT

Written by Matt Dancho

Writing code is a slow process especially when you are first learning data science. What if you could speed it up? You can and this is how. In this free R-tip, I share a real case study where I made the working R code for my data analysis in under 30 seconds with ChatGPT.

Today I share how to automate R coding with ChatGPT. Here’s what you’re learning today:

ChatGPT Prompts: The mistake you’ll make and how to get ChatGPT to write your code correctly.
2-Minute Case Study: How I connect to an API, Downloaded Data, and Visualized on a Map with ChatGPT.
Bonus: Sneak Peek At My NEW Shiny App that extends this ChatGPT tutorial

ChatGPT Made This Shiny App

SPECIAL ANNOUNCEMENT: AI for Data Scientists Workshop on December 18th

Inside the workshop I’ll share how I built a SQL-Writing Business Intelligence Agent with Generative AI:

Generative AI for Data Scientists

What: GenAI for Data Scientists

When: Wednesday December 18th, 2pm EST

How It Will Help You: Whether you are new to data science or are an expert, Generative AI is changing the game. There’s a ton of hype. But how can Generative AI actually help you become a better data scientist and help you stand out in your career? I’ll show you inside my free Generative AI for Data Scientists workshop.

Price: Does Free sound good?

How To Join: 👉 Register Here

R-Tips Weekly

This article is part of R-Tips Weekly, a weekly video tutorial that shows you step-by-step how to do common R coding tasks. Pretty cool, right?

Here are the links to get set up. 👇

This Tutorial is Available in Video

I have a companion video tutorial that walks you through how to use chatGPT for this analysis. And, I’m finding that a lot of my students prefer the dialogue that goes along with coding. So check out this video to see me running the code in this tutorial. 👇

ChatGPT: And the Importance of Your Prompts

In my last R-Tip, I showed you how ChatGPT I made a full R Shiny App in under 10-minutes. That was insane!

But, after that R-tip, I felt a bit of a let down.

I began to try more and more complex stuff.

I failed building high-end Shiny apps.
I failed doing machine learning and integrating it into apps.
And I got so frustrated that I even made a learning lab 82: ChatGPT for Data Scientists, where I showed every mistake I made in building a Production Shiny App (including the prompts, the 11 things I needed to fix in a live workshop, plus my debugging process).

But, now I’m 12 weeks into chatGPT and I’ve realized 1 thing…

How important `chatgpt` prompting is.

Take a look at this prompt. It’s just 2 sentences:

ChatGPT Prompt

Looks fairly straightforward, but I need to show you why this prompt works (and what mistakes I was making in the last 11 weeks of using ChatGPT).

Chatgpt Prompt Guide (for R users)

The mistake I was making was not being specific enough in directing chatgpt what R code I want it to write for me.

If you look at what I’m doing now…

ChatGPT Prompt Guide for R Users

…I specify:

Which R Libraries <– always do this
For this case study I want to know locations of all business types in a certain area:
- Which Business Types
- Which Geographic Location

And it generates the code for me:

ChatGPT Code OSMdata Example