Ryan Plain

breakerofchains or similar for Positron One of my all-time favorite R packages is Miles McBain's breakerofchains. You can put your cursor anywhere in a piped command, run a keyboard shortcut, and RStudio will run everything up to the curre...

If you use #tidyverse / dplyr, breakerofchains by @milesmcbain.bsky.social is one of my favorite productivity #rstats 📦

Very excited to learn that it works in #positron too! One more reason to keep using this IDE, absolutely loving it

forum.posit.co/t/breakerofc...

what software is that?

New #CMSAC #SportsAnalytics paper on evaluating change of direction in the #NFL by myself and @stat-ron.bsky.social

arxiv.org/pdf/2507.06122

Spoiler alert: DK Metcalf displays straight-line, less agile movement, while George Pickens exhibits erratic, more variable directional movement.

Data science junkies, get ready! 🚀 "The Test Set" #podcast trailer is here for your viewing pleasure.

Tune in July 1st and every Tuesday after for new episodes with hosts @mchow.com, @hadley.nz, and @wesmckinney.com as they welcome thought leaders in #DataScience.

Subscribe now: pos.it/thetestset

There is a decent amount of general NFL people here, but the NFL analytics community seems to still be using a twitter a lot.

yeah I didn't think about that because it took some fumbling for me to get used to it, but once I got the coordinates down it was nice to be able to map labels

do you build a custom class that wraps arviz.InferenceData to extend it?

What are some features in Arviz you like? I've been using PyMC to learn, it's a good tradeoff of complexity/abstraction for me, but I struggle with the posterior a lot. I'm typically porting it back to R via reticulate/parquet - but hearing you say that furthers its worth getting comfortable with

viz buzz 2025 featuring avery smith, damie pak, brett fraley, john edwards, tan ho, sam kirschner, quang nguyen, tony elhabr, and jacob patterson-stein. live at twitch.tv/nickwan_datasci 8pm ET, two games back to back

Huge week for competitive data visualization! Viz Buzz returns this Thursday! 9 data visualizers compete all through June to see who can replicate intricate and elaborate graphs in under 40 mins

Every Thursday starting at 8pm ET
twitch.tv/nickwan_datasci

See you there!!

Just a dumb little joke to brighten your day.

Casual Inference: The Art of Clarity with Andrew Heiss | Season 6 Episode 6 Andrew Heiss is an assistant professor in the Department of Public Management and Policy at the Andrew Young School of Policy Studies at Georgia State University. Vincent’s “What is your estimand” s...

I'm on a podcast! I had a blast talking with @lucystats.bsky.social and @epiellie.bsky.social on @casualinfer.bsky.social! We cover all sorts of fun things: {marginaleffects}, defining estimands, fixed vs. random effects, & how to teach all this stats stuff in accessible ways #databs #EpiSky #rstats

I love the name of this page ibis-project.org/reference/cu...

#rstats #thewideworldofr #datascience | Jeremy Allen | 132 comments R is so dead that there are thousands of economists, actuaries, statisticians, bioinformaticists, epidemiologists, biologists, ecologists, geologists, geographers, psychologists, demographers, sociolo...

Me and a lot of people from all over the world talk about just how dead R is; like so dead. www.linkedin.com/posts/jeremy...

R support on databricks can definitely be frustrating

Chart from The Economist showing the contribution to California's energy supply of natural gas, wind, hydro, batteries, nuclear and solar. There's a huge jump in solar from around 8am to 6pm

We have a "never use yellow if you can help it" rule for our charts. We couldn't help it on this one
www.economist.com/united-state...

Can see the valley that Arizona comes out of around the midway mark of the season. They do trend down a bit after that, but they had a great stretch there specifically against the Bears, Jets, and Seahawks.

open chart, keep scrolling down

www.gelliottmorris.com/p/republican...

TIL DuckDb Python has a relational API

oh yeah, I was referring to having the autonomous ergo chair pro! It is wide enough to sit with my legs crossed and I use that and its feature to put the seat back forward for a more active criss cross 😅

The meditation chair with no back is hard for meetings or more passive use

I have the same chair. It’s fine, allowing me to sit in different weird positions, but also not something that comes to mind when I think about recommending something

We also have the person meditation chair, which is fun - but idk if I could use it full time

For each NFL team (AFC), logos of their 2025 opponents by week show the opponent's Vegas win total and compare them to the team's in total.

For each NFL team (NFC), logos of their 2025 opponents by week show the opponent's Vegas win total and compare them to the team's in total.

NFL 2025 schedule is out! Let's have a look at each team's schedule and the strength of their opponents measured in expected wins through Vegas win totals. Red lines represent team win total. Opponents above red line are expected to win more games, opps below the red line are expected to win less.

Annual update of my post on draft curves. This uses 2nd contract value to estimate the value of each draft pick, including by position.

This update incorporates the 2020 draft class, which saw some huge hits at WR including Lamb, Jefferson, and Aiyuk.

opensourcefootball.com/posts/2023-0...

Today, we’re announcing the preview release of ty, an extremely fast type checker and language server for Python, written in Rust.

In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)

POV: I'm waking you up

also the video capture in the issue, when it autofills the package name instead of function is biggest inconveniences for me (i.e. {ggplot2} instead of ggplot() or {selectr} instead of select())

Curious if you have tried the new {air} package. It's been a game changer for me. Not sure what is configureable with it, but I assume it can match styler

I figured cowboys would be similar to jets, but I think a lot were excluded with a lot of tag and 5th year option use.

Interesting to see the bills slide more to signing earlier, and the inverse for the rams

I learned that do.call() exists and a lot about base R from your advent of code solutions, so yes

I assume the eagles have dots on the far left and the cowboys are a straight line of dots on the right

New blog post: drbenvincent.github.io/posts/mcmc_g...