Uploaded April 2026 | Updated November 2026, 11 hours ago
The Data Science Lab is a live weekly call every Tuesday at 12pm US Eastern. Register at pos.it/dslab! Discord invites go out each week on lives calls. We'd love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Joey Marshall, who walks through how he uses Claude Code for data science workflows and building interactive data applications.
Joey shows us how he uses Claude Code, Wispr Flow, cmux, and the 1Password CLI to do data science in his everyday. He uses a TidyTuesday dataset about frog call observations in Australia to build an interactive web app called "Frog Finder" - complete with a cottagecore aesthetic, radius-based species search, and deployment to Vercel - all in about 30 minutes total (we ask Joey a lot of questions the rest of the time)! The dataset is publicly available, so you can try this at home, too!
Hosting crew from Posit: Libby Heeren, Isabella Velasquez
Joey Marshall's LinkedIn: linkedin.com/in/joeymarshall
Resources mentioned in the video and chat:
π Frog Finder App (built live during the session): https://frog-finder-iota.vercel.app/
π Australian Frogs TidyTuesday Dataset: github.com/rfordatascience/tidytuesday/tree/master/data/2024/2024-08-27
π Claude Code: anthropic.com/claude/code
π wispr flow for dictation: wisprflow.ai
π cmux Terminal: github.com/aca/cmux
π 1Password CLI: developer.1password.com/docs/cli
π Vercel: vercel.com
π Positron IDE: positron.posit.co
π Simon Couch's LLM Evaluation Blog: simonpcouch.com/blog
π Anthropic Course Marketplace: anthropic.com/courses
π Posit Data Science Hangout every Thursday: https://pos.it/dsh
βΊ Subscribe to Our Channel Here: bit.ly/2TzgcOu
Follow Us Here:
Website: posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps of Questions / Topics:
00:00 Introduction
02:30 "How long have you been using LLMs for your data workflows?"
04:00 "For someone who's bearish on AI, what benefit does using something like Claude Code bring?"
07:00 Starting the Claude Code demo with the frogs dataset
08:00 Setting up terminal environment and cmux
10:00 Using 1Password CLI for secrets management
12:17 Asking Claude to explore the Australian frogs dataset
13:00 Managing secrets with 1Password vs plain text environment files
17:22 "Have you done any analysis of how different generative AIs perform for the kind of work you're doing?"
18:00 Using Opus vs Sonnet vs Haiku models in Claude Code
19:20 "With your Claude prompts, what components are you intentionally saying versus what did you feel free to be more liberal about?"
21:00 "How does the computer know you're talking to the AI versus just talking?"
22:00 Reviewing Claude's three project proposals for the frog data
24:30 Going into planning mode and setting up deployment to GitHub and Vercel
26:00 "Do voice-to-text things require a lot of hardware to work fine?"
28:00 Choosing a cottagecore aesthetic and color scheme
28:30 "Do you have advice on setting up agents that are working on the same folder?"
34:00 "Is there an equivalent to the CLI 1Password functionality in Apple passwords on Mac?"
35:00 Reviewing the implementation plan from Claude's planning mode
36:30 "What does the four percent context mean?"
41:00 Skills in Claude Code and system prompts
41:30 Frog Finder app is live and deployed
42:30 Viewing the deployed Frog Finder app in the browser
45:30 "Can you switch back and forth between models during the same session?"
46:30 "What resources would you recommend to learn all of this stuff?"
48:30 Verifying where Claude got the frog images (Wikipedia)
49:00 Asking Claude to use frog emojis instead of dots on the map
51:00 "How accurately did Claude pull the images from Wikipedia?"
52:30 Frog emojis are live on the map
The Data Science Lab is a live weekly call every Tuesday at 12pm US Eastern. Register at pos.it/dslab! Discord invites go out each week on lives calls. We'd love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Joey Marshall, who walks through how he uses Claude Code for data science workflows and building interactive data applications.
Joey shows us how he uses Claude Code, Wispr Flow, cmux, and the 1Password CLI to do data science in his everyday. He uses a TidyTuesday dataset about frog call observations in Australia to build an interactive web app called "Frog Finder" - complete with a cottagecore aesthetic, radius-based species search, and deployment to Vercel - all in about 30 minutes total (we ask Joey a lot of questions the rest of the time)! The dataset is publicly available, so you can try this at home, too!
Hosting crew from Posit: Libby Heeren, Isabella Velasquez
Joey Marshall's LinkedIn: linkedin.com/in/joeymarshall
Resources mentioned in the video and chat:
π Frog Finder App (built live during the session): https://frog-finder-iota.vercel.app/
π Australian Frogs TidyTuesday Dataset: github.com/rfordatascience/tidytuesday/tree/master/data/2024/2024-08-27
π Claude Code: anthropic.com/claude/code
π wispr flow for dictation: wisprflow.ai
π cmux Terminal: github.com/aca/cmux
π 1Password CLI: developer.1password.com/docs/cli
π Vercel: vercel.com
π Positron IDE: positron.posit.co
π Simon Couch's LLM Evaluation Blog: simonpcouch.com/blog
π Anthropic Course Marketplace: anthropic.com/courses
π Posit Data Science Hangout every Thursday: https://pos.it/dsh
βΊ Subscribe to Our Channel Here: bit.ly/2TzgcOu
Follow Us Here:
Website: posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps of Questions / Topics:
00:00 Introduction
02:30 "How long have you been using LLMs for your data workflows?"
04:00 "For someone who's bearish on AI, what benefit does using something like Claude Code bring?"
07:00 Starting the Claude Code demo with the frogs dataset
08:00 Setting up terminal environment and cmux
10:00 Using 1Password CLI for secrets management
12:17 Asking Claude to explore the Australian frogs dataset
13:00 Managing secrets with 1Password vs plain text environment files
17:22 "Have you done any analysis of how different generative AIs perform for the kind of work you're doing?"
18:00 Using Opus vs Sonnet vs Haiku models in Claude Code
19:20 "With your Claude prompts, what components are you intentionally saying versus what did you feel free to be more liberal about?"
21:00 "How does the computer know you're talking to the AI versus just talking?"
22:00 Reviewing Claude's three project proposals for the frog data
24:30 Going into planning mode and setting up deployment to GitHub and Vercel
26:00 "Do voice-to-text things require a lot of hardware to work fine?"
28:00 Choosing a cottagecore aesthetic and color scheme
28:30 "Do you have advice on setting up agents that are working on the same folder?"
34:00 "Is there an equivalent to the CLI 1Password functionality in Apple passwords on Mac?"
35:00 Reviewing the implementation plan from Claude's planning mode
36:30 "What does the four percent context mean?"
41:00 Skills in Claude Code and system prompts
41:30 Frog Finder app is live and deployed
42:30 Viewing the deployed Frog Finder app in the browser
45:30 "Can you switch back and forth between models during the same session?"
46:30 "What resources would you recommend to learn all of this stuff?"
48:30 Verifying where Claude got the frog images (Wikipedia)
49:00 Asking Claude to use frog emojis instead of dots on the map
51:00 "How accurately did Claude pull the images from Wikipedia?"
52:30 Frog emojis are live on the map

![Fun data science side projects | Damie Pak, Mark Rieke, & Sam Parmar | Data Science Lab
The Data Science Lab is a live weekly call. Register at pos.it/dslab! Discord invites go out each week on lives calls. Wed love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Damie Pak, Mark Rieke, and Sam Parmar in a special community project showcase where three data scientists share their creative side projects.
Damie walks through her Mambo No. 5 Bayesian analysis project, showing how she used baby name data to predict when the song was released based on the womens names in the lyrics. Mark presents his Bayesian model analyzing player skill in Dropout TVs Um, Actually game show, revealing who truly is the best contestant when accounting for factors beyond simple win counts. Sam demonstrates his impressive collection of Quarto extensions (so prolific!!), including flashcards, quizzes, Easter eggs, and voice-controlled slides (yes, really). All three showcase the importance of working out loud, making mistakes publicly, and building silly projects to learn new skills.
Hosting crew from Posit: Libby Heeren, Isabella Velasquez
Damie Paks GitHub: https://github.com/pakdamie
Damie Paks Bluesky: https://bsky.app/profile/damiepak.bsky.social
Damie Paks LinkedIn: https://www.linkedin.com/in/damie-pak/
Mark Riekes GitHub: https://github.com/markjrieke
Mark Riekes Bluesky: https://bsky.app/profile/markjrieke.bsky.social
Mark Riekes LinkedIn: https://www.linkedin.com/in/markjrieke/
Sam Parmars GitHub: https://github.com/parmsam
Sam Parmars LinkedIn: https://www.linkedin.com/in/sam-parmar-/
Resources mentioned in the video and chat:
π Mambo No. 5 Bayesian Analysis (Damies project): https://yawpr.substack.com/p/project-a-little-bit-of-reverend
π Um, Actually Player Skill Analysis (Marks project): https://www.thedatadiary.net/posts/2024-10-06-actually/
π Statistical Rethinking book by Richard McElreath: https://xcelab.net/rm/
π Quarto Extensions Listing: https://quarto.org/docs/extensions/
π Mickaels Quarto Extensions Registry: https://m.canouil.dev/quarto-wizard/getting-started/
π Quarto Wizard Extension (by Mickael Canouil): https://m.canouil.dev/quarto-wizard/getting-started/
π Sam Parmars Quarto Extensions: https://github.com/parmsam/
π Quarto Easter Eggs Extension: https://parmsam.github.io/quarto-easter-eggs/
π Quarto Flashcards Extension: https://github.com/parmsam/quarto-flashcards
π Quarto Quiz Extension: https://github.com/parmsam/quarto-quiz
π Marcos Huertas Discord-style Spoiler Tags Extension: https://github.com/astrowonk/spoiler_shortcode
π Marcos Huertas Bootstrap Tooltips Extension: https://github.com/astrowonk/quarto_tooltips
π Rich Iannones Posit::conf 2023 talk on Quarto Extensions: https://www.youtube.com/watch?v=EihuM4oyOvs
π Anki Flashcard app: https://apps.ankiweb.net/
βΊ Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here:
Website: https://www.posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: https://www.linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps of Questions / Topics:
00:00 Introduction
00:22 Damie Pak Intro: Mambo No. 5 project philosophy
03:03 Demoing the mathematical model and Bayesian statistics
04:11 Walking through project functions and US Social Security name data
08:13 Live coding: Testing if the analysis script runs
13:34 Did you use Claude or any other tools to help you with this?
16:44 Mark Rieke Intro: Bayesian stats and Um, Actually
22:34 Demoing the Bayesian model for player skill
25:14 How do you figure out what points were awarded to in a team game?
27:38 Have you shared your analysis with the Dropout of Actually people?
30:34 Does that mean that if somebody of high skill is playing against other contestants of low skill that that win is discounted?
34:04 Comparing statistical vs. geometric models for golf putts
35:46 What do you think about doing something like this for Game changer?
37:17 Sam Parmar Intro: Quarto extension adventures
40:06 How did you learn about all these extensions?
40:34 Navigating the Quarto extensions gallery
41:42 Demoing the Quarto Wizard extension in Positron
43:32 Demoing the Easter Eggs extension
45:52 Demoing the Flashcards extension
48:35 Demoing the Quiz extension
50:24 Is there a way to make it [flashcards] three sided?
51:10 Demoing the Quarto Excalidraw extension
51:55 Demoing the Speech extension for voice-controlled slides
53:29 How do extensions even work? Fun data science side projects | Damie Pak, Mark Rieke, & Sam Parmar | Data Science Lab](https://i.ytimg.com/vi/tFBDWLZpJuA/mqdefault.jpg)








