i'm looking for interesting teaching examples where (1) random effects/multilevel models predict better than glmnet (2) glmnet predicts better than random effects #rstats #statistics

Most charities and nonprofits have more data than they know what to do with. The capacity and expertise to use it is the missing piece. That's the gap we want to help close, learn more and apply for our Pro bono support: www.jumpingrivers.com/pro-bono/

On my way to #EGU26, perfect time to drop a new post! 🗺️ Something I've been wanting to write about: Mercator projections still showing up in high-profile journals. So here it is: projections you should stop using (for most things) 👇 #gis #rstats #dataviz dominicroye.github.io/blog/map-pro...

Seconded! ggauto - a new #rstats package - works really well 🥳

As someone who already has 5 IDEs on their computer, this sounds like a string contender for 6th. #idepolygamy #rstats #pydata

I have a new favorite editor/IDE: Zed. Open-source, blazing fast, built-in AI operability, easy to use. Heard that lots of developers are dropping Visual Studio Code for Zed. Has R and Quarto extensions. zed.dev

They grow up so fast 🥹 I still remember when Quarto was first released and I hopped on the new wagon immediately of course 🥳

Counting the times I thought I was opening a clean dataset that was in fact not clean.

Recommendations for a tidy #rstats package that creates dummy data from a data dictionary? Thank you!

Rebase Another Day 😂

Can't wait to try this out. Always an Alpha tester 👋🏻

#AdventOfCode Day 09 both parts #rstats I used plotly to guide my search. Sue me 🙃

#AdventOfCode Day 08 - both parts using igraph! #rstats igraph is superspeedy. pivot_wider() is slow, which to be fair creates 1k columns so that I can get the pairings. Will be a better way, but I was keen to get to igraph asap. First for loop this year 😀 (but I failed Day 03 and skipped Day 04).

#AdventOfCode Day 07 Part I & Test data only Can I please get 0.25 ⭐ for solving it for the test input, but running out of memory for the real input 😅

#AdventOfCode Day 06 - both parts 🥳💃 Knew I wanted to do today's in #rstats instead of #pydata as soon as I saw it. Nice wrangling. Some duplication in code, but don't have time to reduce. Pun intended.

#AdventOfCode Day 05 Part I only in #pydata

#AdventOfCode Day 02 Part I only. Not sure I could do Part II even if I was using beloved #rstats, and not struggling through with #pydata. Anyway, tomorrow is another day. Happy to do what I can given the time restrictions that I have 🚸

It's most wonderful time of the year - #AdventOfCode Day 01🎄 Having abandoned #pydata in favour of #rstats 13 years ago, I am keen to give our relationship another go. Especially as I left pre-pandas 🐼 Will revert to R as soon as the going gets tough. Probably in a day or two 😅

Perfect for me 🥳😅🤩

Hello, friends! After 10(!) years of #AdventOfCode, I've made some changes to preserve my sanity: there will be 12 days of puzzles each December (still starting Dec 1) and there is no longer a global leaderboard. Read more: adventofcode.com/2025/about#f... adventofcode.com/2025/about#f...

New #QuartoPub extension! Quarto output styling adds CSS rules for computational output, warnings, and messages for #rstats, #python, #julialang, and #observablejs - use the default styles, minimal styles, or add your own custom CSS andrewheiss.github.io/quarto-outpu...

📢Accurate != precise📢 Not precise, but accurate is also known as roughly right - Figure (a). Not accurate, but precise is also known as precisely wrong - Figure (d). www.riinu.me/2025/08/accu... #rstats code in blog post

It's shameful that we are so behind with endometriosis, but a landmark $50 million donation offers new hope. vajenda.substack.com/p/decades-be...

New blog post: high quality figures from R Markdown or Quarto to Word: R Markdown set-up chunk: dpi = 300 Quarto YAML: fig-dpi: 300 www.riinu.me/2025/07/dpi/ #rstats #quarto

#rstats #github #datascience

Mastering typefaces and fonts in #rstats has always been harder than it should. I have tried to collect much of my relevant knowledge in this deep-dive blog post so you can spend your time picking the right typeface instead of cursing at the computer

Emil!!! I think you're my guardian angel. Just today I was completely puzzled by a Shiny app that loaded in <2 seconds for me, but up to 40 seconds for users! Used profvis and reactlog to no avail... But then as I was scrolling on BlueSky whilst expressing in the parenting room at my workplace...

Nothing is more humbling than raising a toddler.

This is a really pragmatic write-up on customising system prompts 👍🏻

IYKYK

I've been thinking about *where* I've learned various skills that I have found extremely helpful in my life/career and perhaps the top 3 for me are: - formal education in physics & astronomy - stint in an improv troupe - training and then experience as a teen leading a Bible study group

Playing in orchestras and ensembles - being at the right place at the right time, bringing the right music and wearing appropriate attire. Things similar to these now take up less headspace than they would without the extensive experience.🎻 + formal education in physics 😍 + parenting 🤯

#AdventOfCode Day 11 in #rstats and #tidyverse Part II runs 3x faster than Part I 😉 First time using memoise although that's not the speed-up, as using that in both parts. Even the compulsive R-Restarter that I am (command+shift+R), it still bit me a few times 😂 Coding is joy 🥳🎄

#AdventOfCode Day 08 in #rstats and #tidyverse Function of the day: unnest() github.com/riinuots/adv...

#AdventOfCode Day 07 #rstats and #tidyverse Both parts today 🥳 github.com/riinuots/adv...

#AdventOfCode Day 06 in #rstats and #tidyverse Again just Part I, don't even have time to read the instructions for Part II 😅🎄

#AdventOfCode Day 05 in #rstats and #tidyverse Part I only - probably won't have time for Part II. Broke out crossing() for the first time this year - another function I only use in December 🙃

I have NOT just completed #AdventOfCode Day 04 in #rstats Stuck at Part I. Right answer for test, but not my input. Thoughts/ideas/hints anyone? github.com/riinuots/adv...

#AdventOfCode 2024, Day 03 in #rstats and #tidyverse fill() probably the most useful function here. First time using co-pilot, it was very helpful with the first regular expression, but weirdly lost the plot when I asked for the second one.

Nice one!

#AdventOfCode 2024, Day 02 in #rstats and #tidyverse I wish I could say no for loops were harmed in solving today's puzzle...but I can't. I briefly envisioned something with maps and filters, but this is probably easier to read and understand. Having fun either way 🥳

#AdventOfCode 2024, Day 01 in #rstats and #tidyverse Hmmm....a bit early for having to bring in rowwise(), but it's done.

One more sleep until #AdventOfCode 🥳🎄 In #rstats and #tidyverse for me of course 🤩😍

I'm happy to share it's now a whole lot easier to theme your #Shiny for #Python apps! brand.yml is a new project: one YAML file holds your brand's colors, theme, logos and fonts and can be used to theme Shiny apps and #QuartoPub sites, slides, and more! shiny.posit.co/blog/posts/s...

Pie charts are a popular choice here 😉

Patient flow (CONSORT) diagrams in R using library(consort) now easier than ever. Thanks Alim Dayim! 🤩 neat syntax 🔢 takes patient-level data 🖼️exports well to Word/PDF/PNG ✍️ a few options: number of side boxes, arms, font size Full example: www.riinu.me/2024/02/cons... #rstats

🙏 please read and sponsor Yihui. yihui.org/en/2024/01/b...

#AdventOfCode #rstats Day 11 (other days in repo too) github.com/riinuots/adv...

#AdventOfCode #rstats Day 08 github.com/riinuots/adv...

#AdventOfCode #rstats Day 07 Not bad this one. Part II: first got right answer for test, but wrong for real input. Issue was mishandling of the 5-joker hand. MVP: using a named vector in str_replace_all()