Nick Tierney
LightNews LightNews
banner
njtierney.bsky.social
Nick Tierney
@njtierney.bsky.social
570 followers 180 following 190 posts
|| PhD Statistics | Research Software Engineer | Loves #rstats | Outdoors person | Coffee person | Photography person | Serial Hobbiest | he/him ||
Posts Replies Media Videos
Pinned
njtierney.bsky.social
Nick Tierney @njtierney.bsky.social · Oct 3
I'm giving a talk next week about my favourite thing: functions! Come along!

What: Practical Functions - Practically Magic
When: 8th/9th October - www.timeanddate.com/worldclock/f...
Where: Online, via Salt Lake City R User Group www.meetup.com/slc-rug/even...
How: @juliasilge.com

#rstats
Event Time Announcer - Salt Lake City talk: Practical Functions, Practically Magic
Event Time Announcer shows time for Salt Lake City talk: Practical Functions, Practically Magic in locations all over the world. In Salt Lake City it happens on Tuesday, October 7, 2025 at 4:00:00 pm.
www.timeanddate.com
Reposted by Nick Tierney
analyticaledge.bsky.social
OK nothing like proclaiming in a public space and then quickly finding solution 🤪 If anyone else is stuck on this, sf seems to not work with plotly. If you put your coords in as a df, and use geom_path to plot with geom_tile it renders (and saves output correctly with .png) #rstats soln next comment
analyticaledge.bsky.social Jo Potts @analyticaledge.bsky.social · 1d
Ok #rstats #shiny hive mind.
When rendering geom_tile to a plotly in shiny, and press the download button the resulting .png is missing the tiles? What gives! Any advice gratefully received

(These data are fake!)
November 13, 2025 at 2:26 AM
Reposted by Nick Tierney
chrbknudsen.bsky.social
An #rstats mystery. Or maybe more #ggplot2. These histograms are generated with the exact same code and data. What has changed from R 4.5.1 to 4.5.2 that caused this change?
November 13, 2025 at 7:42 AM
Reposted by Nick Tierney
libbyheeren.bsky.social
new #dplyr filtering function who dis 😍 meet filter_out()!

👍 GO PUT A THUMBS UP ON DAVIS'S TIDYUP THINGY ON GITHUB TO SHARE MY ENTHUSIASMMMM!! #rstats #databs

And, you know, provide your thoughts on this newly-proposed function if you have them 😌
A screenshot of code that uses the dplyr function called filter, which is built to include rows, in order to exclude them instead. The result also filters out rows where values are NA, which isn't helpful usually. It then shows the messy code you'd need to use to not exclude those NAs, and compares it to some very clean code using a newly proposed function called filter_out, which does not exclude NAs. Libby has drawn silly illustrations all over this screenshot, like yucky faces for dropping NAs and a smily face saying, "new filtering function?"
November 7, 2025 at 11:16 PM
Reposted by Nick Tierney
gsimpson.bsky.social
A new release of the mgcv #RStats 📦 is out on CRAN and Simon Wood (U Edinburgh) has added some significant new features despite the small bump in version number:

🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
Model is: b3 <- scasm( y ~ s(x0, bs = "bs", k= k) + s(x1, bs = "sc", xt = "m+", k = k) + s(x2, bs = "bs", k = k) + s(x3, bs = "bs", k = k), family=poisson, bs=200 ) The second smooth `s(x1) is a shape constrained smooth with a positive monotonicity constraint (xt = "m+"). The `bs = 200` arguments uses 200 boostrap samples, which generates bootstrap distributions for each coefficient in the model. These bootstrap samples respect the shape constraints, while the usual +/- 2 SE credible intervals may not. The uncertainty in the partial effects is shown by two credible interval bands; a dark blue central band is a 68% Bayesian credible interval, while the lighter blue outer interval is a 95% Bayesian credible interval. The background of each panel is light grey with white grid lines, in a similar style to ggplot2's default theme.
November 12, 2025 at 11:28 AM
Reposted by Nick Tierney
topepo.bsky.social
We've made a blog post about a new major version of the #rstats tune package! Two main changes: parallel processing frameworks and the ability to tune postprocessors.

tidyverse.org/blog/2025/11...
tune version 2.0.0
A new version of tune brings significant updates for model tuning and parallel processing.
tidyverse.org
November 5, 2025 at 7:06 PM
Reposted by Nick Tierney
henrikbengtsson.bsky.social
The detectCores() apocalypse is creeping up on us 👻🐛

As more people are getting access to 128+ CPU cores, code spinning up parallel cluster with detectCores() workers fails - not enough #RStats connections available

Friends, do *not* default to detectCores(), bc www.jottr.org/2022/12/05/a...
Please Avoid detectCores() in your R Packages
The detectCores() function of the parallel package is probably one of the most used functions when it comes to setting the number of parallel workers to use in R. In this blog post, I’ll try to explai...
www.jottr.org
November 5, 2025 at 11:55 PM
Reposted by Nick Tierney
walinchus.bsky.social
There are a lot of great posts out there that aren't very highly ranked.

Don't rely on bluesky to find you great content; you can find it on your own! Here's how:

#Rstats via @northeasternu.bsky.social's Storybench

www.storybench.org/how-to-analy...
How to Analyze bluesky Posts and Trends with R - Storybench
If all you're doing on bluesky is scrolling, liking and posting, then you're riding a bike with training wheels. Here are simple tools using its open-source skeleton.
www.storybench.org
November 5, 2025 at 7:58 PM
Reposted by Nick Tierney
libbyheeren.bsky.social
Oh. My. Gosh. Data Science Lab was SO FUN today! Just casually sharing screens to walk through settings live was incredible.

I'm gonna start a thread here of some of the stuff we shared/learned together as a community. Great stuff was shared by all! #databs #rstats #python

🧵 1/n
November 5, 2025 at 7:59 PM
Reposted by Nick Tierney
jenrichmondphd.bsky.social
Day 2: Lines #30DayMapChallenge

Sticking with walks of NZ, this time plotting the Te Araroa Trail, a 3000km hike that goes from the top of the North Island to the bottom of the South Island. #rstats

jenrichmond.github.io/maps/2025-11...
Map of Te Araroa Trail showing the 3000 km walking route through New Zealand from Cape Reinga in the north to Bluff in the south. The trail is depicted as a colored line indicating elevation changes, with deep blue representing sea level areas, transitioning through purple and pink to yellow at higher elevations up to 2000m. Two key landmarks are labeled: Tongariro Alpine Crossing at Red Crater (1861m) in the North Island, and Two Thumb Track at Stag Saddle (1934m) in the South Island. The trail winds along both islands, showing significant elevation variations throughout the journey.
November 4, 2025 at 3:41 AM
Reposted by Nick Tierney
transport-talk.bsky.social
{brandthis} is ready to install. Try it and let me know if anything breaks: github.com/durraniu/bra...

Here's an example site that uses the generated _brand.yml and color palettes: dru.quarto.pub/brandthis-de...
#RStats
November 4, 2025 at 4:06 AM
Reposted by Nick Tierney
etiennebacher.bsky.social
#rstats tidypolars 0.15.0 is available!

tidypolars provides the tidyverse syntax while using polars for efficient computations.

This release:
- more support for string and date func.
- two func. to export partitioned output
- bug fixes

Changelog: www.tidypolars.etiennebacher.com/news/#tidypo...
Changelog
www.tidypolars.etiennebacher.com
November 3, 2025 at 8:06 PM
Reposted by Nick Tierney
mdsumner.bsky.social
I can see {targets} evolving past tar_assign to an actual new language syntax that's just R (its successor)

I bet some are already thinking about this #rstats it's been an inexorable series of improvs and the foundation's so solid

This is the edge, actual reproducibility and scaling
November 3, 2025 at 6:36 AM
Reposted by Nick Tierney
freerangestats.info
#rstats people I'm sure I remember someone had recently developed a package or at least a hack for getting around the fact that geom_ribbon can't map the fill aesthetic to a variable (continuous or not), but now I can't find it, can anyone point me to it?
October 31, 2025 at 9:46 PM
Reposted by Nick Tierney
bharrap.bsky.social
Come along to my slightly silly and hopefully informative talk on how data go from some scribbles on a paper questionnaire to a nice, clean dataset

Thanks to the ARDC for having me!

#databs #rstats

📅 Nov 5 at 12pm AEDT
📍 Online webinar
🔗 www.eventbrite.com.au/e/where-do-d...
Where do data come from & other difficult questions your children might ask
Join us to learn about data cleaning and management in the Mayi Kuwayu study.
www.eventbrite.com.au
October 30, 2025 at 2:39 AM
Reposted by Nick Tierney
nrennie.bsky.social
Looking for an overview of different #RStats packages for visualising spatial data? 📊 Here's a previous blog post of mine: nrennie.rbind.io/blog/r-packa...

This blog post is almost three years old now, but all of the code still works!

#DataViz #RSpatial #30DayMapChallenge
R packages for visualising spatial data – Nicola Rennie
Throughout the #30DayChartChallenge I made most of my maps with R. This blog post details the R packages I find myself using most often when visualising spatial data.
nrennie.rbind.io
October 28, 2025 at 9:23 PM
Reposted by Nick Tierney
nanxstats.bsky.social
revdeprun: Rust CLI for #rstats package reverse dependency check automation nanx.me/blog/post/re...
revdeprun: Rust CLI for R package reverse dependency check automation
revdeprun is a Rust CLI tool that makes running reverse dependency checks on cloud instances as easy as a single command. Learn why this matters for R package maintainers and how it can save you hours...
nanx.me
October 27, 2025 at 10:43 PM
Reposted by Nick Tierney
obrien.page
Fun fact: you can host PMTiles on GitHub pages, so if you are on Windows you can move the creation to a GH Actions runner.

👇🏻Toy #rstats code that scrapes @oceantracking.bsky.social receiver locations, converts them to PMTiles using sf/GDAL, and pops it up on GH Pages for use elsewhere.
October 28, 2025 at 2:17 AM
Reposted by Nick Tierney
datavisfriendly.bsky.social
#rstats I'm looking for tidy tools for categorical / frequency data.
Data sets in frequency form or case form can be tidy, but have different model & graphics syntax.
What about tables, matrices and arrays, often so convenient frequency data?
Does anything exist? Seems like a big tidy gap.
October 20, 2025 at 12:14 AM
Reposted by Nick Tierney
transport-talk.bsky.social
I am giving 2 talks abt making your data analysis outputs into polished products with the power of #RStats and #Python pkgs + my pkg {brandthis}.
Talk 1: DevFest 2025. Register here: wedevfest.com
Talk 2: R+AI 2025 organized by R Consortium. Register here: rconsortium.github.io/RplusAI_webs...
October 20, 2025 at 3:43 AM
Reposted by Nick Tierney
nzcoops.bsky.social
Here's to World Statistics Day 📊

Yes that's right, we've already got our eye on wrapping up 2025.

#RStats #Statistics #Statssky #DataScience
October 20, 2025 at 12:05 AM
Reposted by Nick Tierney
transport-talk.bsky.social
{brandthis} progress: Generate _brand.yml and see the results in the live app. Still work-in-progress. Building on the brand.yml app from {bslib}. #rstats
October 19, 2025 at 9:03 PM
Reposted by Nick Tierney
zeileis.org
R package on CRAN #rstats

cran.r-project.org/package=qual...
qualpalr: Automatic Generation of Qualitative Color Palettes
Automatic generation of maximally distinct qualitative color palettes, optionally tailored to color deficiency. A list of colors or a subspace of a color space is used as input and then projected to t...
CRAN.R-project.org
October 17, 2025 at 9:14 AM
Reposted by Nick Tierney
zeileis.org
💡 Came across this nice tool today:

🎨 qualpal for algorithmically choosing maximally distinct colors under certain restrictions #dataviz

JOSS paper, online tool, R package #rstats

joss.theoj.org/papers/10.21...
Qualpal: Qualitative Color Palettes for Everyone
Larsson, J., (2025). Qualpal: Qualitative Color Palettes for Everyone. Journal of Open Source Software, 10(114), 8936, https://doi.org/10.21105/joss.08936
joss.theoj.org
October 17, 2025 at 9:12 AM
Reposted by Nick Tierney
benzipperer.org
#RStats question:

Is there a package or site that provides alternative, more explanatory help files?

I swear a project like this exists, perhaps targeted to beginning R users, maybe centered around common data analysis functions, but I can't find it...
October 17, 2025 at 3:47 PM
Reposted by Nick Tierney
freerangestats.info
Countries with more economic inequality have higher homicide rates. But for any given country, the relationship isn't as strong. This poses a multilevel modelling problem that it's easy to trip over. I tripped, righted (I hope), and blogged about it with #rstats. freerangestats.info/blog/2025/10...
12 facet scatter plots for Australia, US, Mexico and other countries up to Japan. Showing relationship of inequality (x axis) to homicide rate (y axis). Relationships start negative for Australia, USA, but are very positive by the bottom row with UK, Russia and Japan. 3x3 scatter plot matrix of country-level residuals from two different types of multilevel models and country average inequality. Scatterplot of inequality (x axis) and homicide rate (y axis), each dot is a country, multiple dots per country with the most recent marked. some countries are labelled. There is a strong positive relationship between the two variables, and two models, one satisfactory and one not.
October 18, 2025 at 6:56 AM