iiinova — where your digital self keeps evolving

Andy Rowlinson @numberstorm.bsky.social · 27/09/2026

Looking for a tester with statsbomb api access. I am planning to release this in the next couple of days. It's pretty neat and works on the open data too.

260

Reposted by Andy Rowlinson

PySport @pysport.org · 09/09/2026

𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐂𝐮𝐩 𝟐.𝟎 𝐢𝐬 𝐡𝐞𝐫𝐞. 🇪🇺🇺🇸 Following the success of the first edition, PySport and @skillcorner.bsky.social are inviting the analytics community to work with open-source 𝐟𝐨𝐨𝐭𝐛𝐚𝐥𝐥 𝐝𝐚𝐭𝐚 (including body pose data) and 𝐛𝐚𝐬𝐤𝐞𝐭𝐛𝐚𝐥𝐥 𝐝𝐚𝐭𝐚 to turn new ideas into open-source projects with real value.

189

Reposted by Andy Rowlinson

Andy Rowlinson @numberstorm.bsky.social · 01/09/2026

The demo is available now here 🚀 andrewrowlinson.github.io/soccerviewer/

2133

Andy Rowlinson @numberstorm.bsky.social · 13/08/2026

If anyone is willing to lend some tracking data with player orientation, please DM.

011

Andy Rowlinson @numberstorm.bsky.social · 05/08/2026

Next up in mplsoccer... animations using @kubamichalczyk.bsky.social line tracking method 🚀

1112

Andy Rowlinson @numberstorm.bsky.social · 31/07/2026

🚀 mplsoccer v1.8.0 Adds custom heatmaps and sonars. Now you can plot on any tiling of rectangles you want.

293

Andy Rowlinson @numberstorm.bsky.social · 24/07/2026

🚀 I just pushed a new mplsoccer version: 1.7.1. It adds curved parameter labels to Radar charts and Pizza charts. Thanks to Palash Gupta for collaborating on this release.

1102

Andy Rowlinson @numberstorm.bsky.social · 17/07/2026

Yay finally have some firepower to tackle some new features for mplsoccer. Thank you @anthropic.com

1121

Andy Rowlinson @numberstorm.bsky.social · 04/06/2026

Reading someone's blog and saw this "distinction matters" tell tale Claude and just gave up. Is it worth reading stuff when you don't know the author might not have done any thinking?

140

Andy Rowlinson @numberstorm.bsky.social · 13/04/2026

Oops my new favourite typo: gut status

030

Andy Rowlinson @numberstorm.bsky.social · 30/03/2026

One quarter down.. some reflections a) the new models are so good and fast, even for analysis. b) meetings have gone from context switch problems, to oh fuck I could have done so much in that half an hour/hour c) it's hard to turn off the PC at the end of the day, you can get loads done in 15 mins

110

Andy Rowlinson @numberstorm.bsky.social · 22/03/2026

Claude Opus loves to say "good instinct" and then completely burn your idea to the ground 🔥🔥🔥

120

Reposted by Andy Rowlinson

Jane Mayl🍷n 🍇 @janetrad.bsky.social · 22/02/2026

"As his post goes on, his language gets older. 100 years older with each jump. The spelling changes. The grammar changes. Words you know are replaced by unfamiliar words" Fascinating. So how far back in time can YOU go?

deadlanguagesociety.com

How far back in time can you understand English?

An experiment in language change

33326147

Andy Rowlinson @numberstorm.bsky.social · 01/01/2026

New year, new resolution. I hand craft a lot of data insights and datasets. Hoping to use agents more to help. Thinking of writing a skill.md for each database schema (dataset) so an agent knows how to join views and tables, the main filters to use, and the key columns. #databs

130

Andy Rowlinson @numberstorm.bsky.social · 26/10/2025

I released an update to mplsoccer that should make it easier to add other sports.

130

Andy Rowlinson @numberstorm.bsky.social · 08/10/2025

I can confirm this works and looks ace. I may be able to finally release a Statsbomb football data parser with no dependencies apart from duckdb.

0100

Reposted by Andy Rowlinson

Matthew Mullins @mmullins.coginiti.co · 08/10/2025

We've open sourced QuackStore - a block-based caching extension for DuckDB! 🦆 QuackStore dramatically speeds up queries on remote data by intelligently caching only the blocks you need. Now available as a DuckDB community extension: github.com/coginiti-dev...

github.com

GitHub - coginiti-dev/QuackStore

Contribute to coginiti-dev/QuackStore development by creating an account on GitHub.

3214

Andy Rowlinson @numberstorm.bsky.social · 29/09/2025

Has anyone got any good examples where they've used AI in data work? #databs

420

Andy Rowlinson @numberstorm.bsky.social · 17/09/2025

I herby restart my campaign for my modest proposal to reduce the size of the penalty area to 30m wide. It might be more palatable to fans than Ted's arc from this pod.

341

Reposted by Andy Rowlinson

Emily Riederer @emilyriederer.bsky.social · 16/08/2025

Dev and deploy require of diff skills. @getdbt.com bridges the gap for #data pipelines, but what about MLOps? I explored how @posit.co {orbital} + dbt delivers "good enough" zero-infra MLOps for batch model scoring in database from python or #rstats models www.emilyriederer.com/post/orbital... 1/

emilyriederer.com

MLOrbs?: MLOps in the database with orbital and dbt | Emily Riederer

Playing with the potential, perils, and design principles of deploying ML models into the analytical database using orbital’s sklearn-to-sql translation, sqlglot, and dbt

5309

Reposted by Andy Rowlinson

DJ Pardis @djpardis.com · 24/07/2025

I have finally published my post about Moneyball, as promised (a long time ago). If you're interested in baseball, numbers, or movies, please take a look. I'd love to know what you think. cc @matsonj.com @alexnoonan.bsky.social djpardis.medium.com/revisiting-m...

djpardis.medium.com

Revisiting Moneyball

Data, sports, payrolls, and memes

2123

Andy Rowlinson @numberstorm.bsky.social · 10/07/2025

🚀 mplsoccer 1.5.1 released @dmitry.mclachbot.com adds the capability to use custom slice labels in the pizza charts

Use the alt_text_values argument to add custom slice labels.

Example showing the pizza chart with custom labels instead of percentiles.

041

Reposted by Andy Rowlinson

Joris Bekkers @unravelsports.bsky.social · 07/07/2025

🌀 𝐄𝐅𝐏𝐈: 𝐄𝐥𝐚𝐬𝐭𝐢𝐜 𝐅𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 𝐚𝐧𝐝 𝐏𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐈𝐝𝐞𝐧𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧 ⚽ The newest release of the 𝒖𝒏𝒓𝒂𝒗𝒆𝒍𝒔𝒑𝒐𝒓𝒕𝒔 Python package (v1.1.0) now includes the functionality of my latest research paper. 🔗https://tinyurl.com/unravel-efpi

1122

Andy Rowlinson @numberstorm.bsky.social · 22/06/2025

Tried this out on mplsoccer. Definitely impressive deepwiki.com/andrewRowlin... But , I think the generated docs are more interesting for someone looking to contribute to the codebase, rather than users.

deepwiki.com

andrewRowlinson/mplsoccer | DeepWiki

mplsoccer is a Python library for plotting soccer/football charts in Matplotlib and loading StatsBomb open-data. This page provides a high-level overview of the library's architecture, components, and

140

Andy Rowlinson @numberstorm.bsky.social · 13/06/2025

🚀 @unravelsports.com added some new formations to mplsoccer for his formation detection work. Hopefully will see some results some day.

230

Andy Rowlinson @numberstorm.bsky.social · 12/06/2025

@unravelsports.com just seen your PR today. Of course adding extra formations is helpful and happy to add it in. I'll try and look at it soon 🙏

100

Andy Rowlinson @numberstorm.bsky.social · 01/05/2025

Yamal is so good he pretty much broke my axes when I looked at young attacking outliers. Streets ahead.

091

Andy Rowlinson @numberstorm.bsky.social · 24/04/2025

It's early days, but seeing if I can adapt mplsoccer to other sports

130

Andy Rowlinson @numberstorm.bsky.social · 22/04/2025

I have successfully switched mplsoccer docs to install via uv rather than conda. It took a while to fix some install problems with lxml. I think Conda still wins is installing the complex C dependencies in some data science projects (e.g. PyMc), but worked around it here with apt install.

030

Andy Rowlinson @numberstorm.bsky.social · 17/04/2025

The margins between winning the Premier League and being runner up are incredibly tight, just seven points separates the teams on average.

120

Andy Rowlinson @numberstorm.bsky.social · 27/03/2025

If learning from survey data, how do you feed in the non-response weights? #databs

100

Andy Rowlinson @numberstorm.bsky.social · 18/03/2025

Musing about the dark patterns you could build into a stadium design to cement home advantage 1/ screens showing the opposition making mistakes or missing penalties around their dressing room

Concept art of the new Manchester United stadium by Foster and Partners

211

Reposted by Andy Rowlinson

Gaël Varoquaux @gaelvaroquaux.bsky.social · 10/03/2025

🔥🎉New library: boosting for survival analysis, including multiclass (competing risks) Survival = missing outcomes because limited observation window (common in medicine, marketting...) soda-inria.github.io/hazardous Gives very fast boosted-trees for survival

14811

Reposted by Andy Rowlinson

PySport @pysport.org · 13/02/2025

🚀 Great to see this improved data structure! Glad we could be of some help with this. Thanks @pff-fc.bsky.social!

183

Andy Rowlinson @numberstorm.bsky.social · 13/01/2025

👏streamlit-soccer will solve some things mplsoccer isn't great at like animations and interactivity.

040

Andy Rowlinson @numberstorm.bsky.social · 06/01/2025

Set pieces seem to be hot at the moment 🔥 so I decided to investigate whether lumping it long into touch is a good ⚽️ strategy andrewrowlinson.github.io/blog/footbal...

andrewrowlinson.github.io

Kicking For Touch – numberstorm blog

Is kicking for touch a viable football (soccer) strategy?

191

Andy Rowlinson @numberstorm.bsky.social · 23/12/2024

This holidays, I'm going to attempt to learn enough javascript/typescript to build an API 🤞.

260

Andy Rowlinson @numberstorm.bsky.social · 06/12/2024

Anyone have a good resource for customers who bought this product also bought these products. How is it usually implemented in practice? #databs

520

Andy Rowlinson @numberstorm.bsky.social · 02/12/2024

I just played floorball/ salibandy and most of the goals came from wide areas. Does anyone know is there any similar expected goals metrics for floorball?

An image of people playing floorball, which is also called salibandy in Finnish.

In football most goals are scored in a relatively small area because the chance of scoring outside the penalty area is low. Around the penalty arc, there is an 8% chance of scoring which increases to around 50% when you are close to goal. Around the penalty spot there is a 17% chance of scoring.

110

Andy Rowlinson @numberstorm.bsky.social · 24/11/2024

Often details make a great #dataviz. A few things I noticed here: a) the pentagons are facing the flow of the lines b) the group A..H are left/right aligned c) the bold font for the knockout and group so it's easy to see 👀 d) choice or circle for representing the group stage

120

Andy Rowlinson @numberstorm.bsky.social · 23/11/2024

I'm the king of unfinished side project.. mplgrid is 80% there just need to figure out a better API 1/3 github.com/andrewRowlin...

100

Andy Rowlinson @numberstorm.bsky.social · 23/11/2024

Could be useful for the football crowd. The code is available too. Who is going to be the first to try it with @carloncarpenter.bsky.social wide angle footage?

260

Reposted by Andy Rowlinson

Evan Peck @peck.phd · 20/11/2024

Trying something new: A 🧵 on a topic I find many students struggle with: "why do their 📊 look more professional than my 📊?" It's *lots* of tiny decisions that aren't the defaults in many libraries, so let's break down 1 simple graph by @jburnmurdoch.bsky.social 🔗 www.ft.com/content/73a1...

921577458

Reposted by Andy Rowlinson

Maija Karala @maijakarala.bsky.social · 21/11/2024

Where did our lost rhinos roam? Distribution charts based on bone finds (individual dots) and habitat suitability for the four fluffy rhinos of late Pleistocene. These are of course approximate and might not include all obscure finds. #Sciart

Illustration of extinct narrow-nosed rhino with a map in the background showing it lived in central and southern Europe, northern Africa and some way into western Asia

Illustration of ”Siberian unicorn” or Elasmotherium sibiricum with a map on the background showing it lived in Eastern Europe and central Asia

Illustration of a woolly rhinoceros with a map in the background showing it had a very wide distribution from southwestern Europe all the way through Europe and Russia to the Pacific coast and northern China.

Illustration of a merck’s rhinoceros with a map in the background showing it lived in a large area from southwestern and central Europe to western Asia, parts of Siberia and northern and eastern China.

24942258