If you’d like an LLM to act more like a partner than a tool, Databot is an experimental alternative to querychat that also works in both R and Python. Databot is designed to analyze data you’ve imported into your working session and suggest questions you might want to ask. After you decide what to ask, Databot will write the code to generate your answer. Posit CTO Joe Cheng, creator of querychat, also wrote this package. It’s now available as an add-on for the Positron IDE.

Also see the introduction to querychat that accompanies this sidebar.

Databot is “an experimental AI assistant that is designed to come alongside you, and help you by performing tasks within your R session,” according to the R documentation. “Point Databot at some data and it will come up with plenty of ideas of how to analyze it.” It currently only uses Anthropic’s Claude Sonnet 3.5, so you’ll need an Anthropic API key to use it.

Note that when the docs say “experimental,” they mean it. “Pretty fragile currently,” the README warns.

With that in mind, I installed databot with remotes::install_github("jcheng5/databot"), loaded my NFL games data set and data dictionary file into my R session along with the package, and created the following chat:

games <- feather::read_feather("games.feather")
data_dictionary <- readLines("data_dictionary.txt")
databot::chat()

A chatbot popped up asking what I’d like help with

Sharon Machlis

I asked for visualizations, and it responded:

There are many interesting variables we could visualize. Let me suggest a few possibilities:

Suggested next steps:

Can you create a histogram of game total scores to see the distribution of scoring?   
Could you make a box plot comparing home vs away team scores?   
Let's create a scatter plot of temperature vs total score to see if weather affects scoring.   
Can you show me the distribution of betting spreads and how they relate to actual game results?   
Could you create a visualization showing win/loss records by team?   

Which of these interests you, or would you like to explore something else in the data? I can help create any type of visualization you'd find useful!

I asked for the weather versus scoring plot, and it wrote R code that unfortunately didn’t show an interesting trend. Next, I tried the histogram of total scoring, which returned R code, the bot’s observations, and a plot. Databot then provided the following analysis:

This visualization reveals several interesting patterns about NFL scoring:

1. The distribution looks approximately normal (bell-shaped), with some slight right skew   
2. The mean total score is about 44.5 points   
3. The median is very close to the mean at about 44 points   
4. Most games fall between roughly 30 and 60 total points   
5. There are a few outlier games with very high scoring (80+ points) and very low scoring (<20 points)

Sharon Machlis

While many mainstream chatbots have similar capabilities, few write and run R code like this; generative AI data analysis code is typically done in Python.

The Python version of Databot may be less compelling because of alternatives like ChatGPT’s Data Analyst. Agents may also have some similar capabilities. But if you are interested in using a chatbot specifically for data analysis in either R or Python, you can check out the Python Databot or R Databot GitHub repos.

Posit has also made Databot available as an add-on for its Positron IDE, which is a convenient way to use the tool in a data science workflow. Users must acknowledge that they understand it is an experimental research preview in order to use it, but you do have the power to steer its analysis and check its code.

Sharon Machlis