AI Tools for R

Day 1 - Introduction to Data Analysis with R

Selina Baldauf

Freie Universität Berlin - Theoretical Ecology

March 14, 2025

Motivation

  • AI tools assist programmers with
    • Coding
    • Debugging
    • Learning
    • …
  • Higher productivity and efficiency
  • More motivation
  • But careful: You still need to understand what’s going on!

Overview of tools

  • Browser-based chat bots (ChatGPT, Bard, …)
    • General-purpose
  • Data-analysis tools (Julius AI, RTutor, …)
    • Upload data and ask questions about it
    • Can also execute code
    • Chat with your data
  • Integrated AI tools (GitHub Copilot, Codium AI, …)
    • Integrated directly in programming environment
    • Real-time suggestions, chat, debugging, …

Find the tools that best fit your workflow!

R Tutor

  • https://rtutor.ai/
  • Free browser tool
  • Upload data and ask questions about it
  • Use the demo data

Julius AI

  • https://julius.ai/
  • Try for free
  • Basic plan ~20€ per months (-50% academic discount)
  • Upload data and ask questions about it

Github Copilot

  • https://github.com/features/copilot
  • Model based on GPT-4 and OpenAI’s Codex
    • Specifically trained on source code
  • Basic idea: Integrate directly into R Studio (or other IDEs)
  • Works best for well-represented languages (Python, JS, …)

How to get GitHub Copilot

See this website for step-by-step guide and more information.

It’s really easy, but you need:

  • GitHub Account
  • Active GH Copilot subscription (10$ per month)
    • Get it for free as an academic with an educational account
  • IDE that supports Copilot
    • Full support: Visual Studio (Code), Vim, Neovim, JetBrains IDEs (e.g. PyCharm)
    • Limited support: RStudio, ?

GH Copilot: Inline code suggestions

  • Copilot tries to predict what you want to do next
  • Suggestions are based on the context
    • Previous code
    • Comments
    • Variable and function names
    • …

Get better suggestions

  • Provide context
    • Open other files
    • Add top level comments explaining the purpose of the script
    • Name variables and functions properly
    • Copy-paste sample code and delete it later
  • Be consistent
    • “Garbage in, garbage out”
    • Have a nice and consistent coding style

Nice side effect of using Copilot: More good-practice coding

Chat with GH copilot in R Studio

Concerns to consider

  • Privacy
    • Chose whether your prompts and suggestions will be used by Github (Github -> Seetings -> Copilot -> Policies)
    • Check privacy guidelines before you upload data
  • Plagiarism
    • Block suggestions matching public code (Github -> Seetings -> Copilot -> Policies)
  • Ethical concerns
    • For-profit tool trained on open-source
  • Environmental concerns
    • Water and energy usage

Usage guidelines

  • No definite guidelines, but see examples listed here
  • Responsibility
    • You are responsible for your scientific output
    • Stay critical, double-check
  • Transparency
    • Make clear for which tasks you used which AI
  • Know relevant guidelines
    • Journals
    • Your university
  • Still understand what is happening!