unravelsports Documentation — unravelsports 1.2.0 documentation

LinkedIn Profile: https://www.linkedin.com/in/joris-bekkers-33138288/

Sports Analytics meets Open Source | PySport

Football Match Intelligence is a Streamlit app that converts SkillCorner tracking plus event data into interactive tactical analysis. You can explore match overviews (pass networks, shot maps, momentum and xG), dive into player profiling (heatmaps, speed zones and movement patterns), analyze team structure (field tilt, defensive organization and possession chains), compare players head-to-head with pizza charts, and reconstruct key events frame by frame with a tactical board that highlights passing options. Live app: https://lnkd.in/eChbEpud Repository: https://lnkd.in/e-drHUD2

𝐇𝐨𝐰 𝐈 𝐥𝐞𝐚𝐫𝐧𝐞𝐝 𝐭𝐨 𝐰𝐨𝐫𝐤 𝐰𝐢𝐭𝐡 𝐟𝐨𝐨𝐭𝐛𝐚𝐥𝐥 𝐭𝐫𝐚𝐜𝐤𝐢𝐧𝐠 𝐝𝐚𝐭𝐚 (𝐚𝐧𝐝 𝐰𝐡𝐚𝐭 𝐢𝐭 𝐥𝐞𝐝 𝐭𝐨) A few months ago, I realized something: If you want to understand football tactics, event data isn’t enough. You have to learn from space, motion, and interaction. That curiosity sent me deep into research on transformers, graph neural networks, and spatiotemporal modeling — and directly led me to build my first transformer-based similarity retrieval system for the SkillCorner × PySport Analytics Cup. The system learns from full-pitch scenes (22 players + ball) to: • retrieve tactically identical plays • cluster recurring patterns • automatically classify team actions and sequences • make visual insights easier for analysts and coaches to use Papers that shaped my thinking 👇 1️⃣ A Graph Neural Network deep-dive into successful counterattacks Joris Bekkers Amod Sahasrabudhe https://lnkd.in/gnDwBm5a The purpose of this research is to build gender-specific Graph Neural Networks to model the likelihood of a counterattack being successful and uncover what factors make them successful in professional soccer. 2️⃣ Graph representations for the analysis of multi-agent spatiotemporal sports data Dominik Raabe Prof. Dr. Daniel Memmert Reinhard Nabben https://lnkd.in/g36xemtf Proposed Tactical Graphs, an alternative graph-based format capable of producing integrative, contextualized models for machine learning applications 3️⃣ 𝐃𝐞𝐭𝐞𝐜𝐭𝐢𝐨𝐧 𝐨𝐟 𝐭𝐚𝐜𝐭𝐢𝐜𝐚𝐥 𝐩𝐚𝐭𝐭𝐞𝐫𝐧𝐬 𝐮𝐬𝐢𝐧𝐠 𝐬𝐞𝐦𝐢-𝐬𝐮𝐩𝐞𝐫𝐯𝐢𝐬𝐞𝐝 𝐠𝐫𝐚𝐩𝐡 𝐧𝐞𝐮𝐫𝐚𝐥 𝐧𝐞𝐭𝐰𝐨𝐫𝐤𝐬 Pascal Bauer Gabriel Anzer https://lnkd.in/gvy9VyBe Presenting practical applications of approach using the detection of overlapping runs as a showcase 4️⃣ 𝐒𝐞𝐥𝐟-𝐒𝐮𝐩𝐞𝐫𝐯𝐢𝐬𝐞𝐝 𝐑𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧𝐬 𝐟𝐨𝐫 𝐓𝐫𝐚𝐜𝐤𝐢𝐧𝐠 𝐃𝐚𝐭𝐚 Karun Singh https://lnkd.in/gsKbiCrF Building tools that leverage tracking data to help accelerate video analysis workflows. 5️⃣ 𝐓𝐞𝐦𝐩𝐨𝐫𝐚𝐥 𝐆𝐫𝐚𝐩𝐡 𝐍𝐞𝐭𝐰𝐨𝐫𝐤 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 𝐟𝐨𝐫 𝐐𝐮𝐚𝐧𝐭𝐢𝐟𝐲𝐢𝐧𝐠 𝐏𝐚𝐬𝐬 𝐑𝐞𝐜𝐞𝐩𝐭𝐢𝐨𝐧 𝐏𝐫𝐨𝐛𝐚𝐛𝐢𝐥𝐢𝐭𝐢𝐞𝐬 𝐀𝐠𝐚𝐢𝐧𝐬𝐭 𝐃𝐞𝐟𝐞𝐧𝐬𝐢𝐯𝐞 𝐒𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞𝐬 Pegah Rahimian Laszlo Toka https://lnkd.in/gpAW5DEC Proposed a framework for evaluating passing decisions against defensive structures using temporal graph networks

𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝗶𝗻 𝗦𝗽𝗼𝗿𝘁𝘀 𝗔𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝘀 course at University of Toronto.

Football analytics often happens behind closed doors, both in science and in practice. I want to do the exact opposite: 𝗯𝗲 𝗮𝘀 𝗼𝗽𝗲𝗻 𝗮𝘀 𝗽𝗼𝘀𝘀𝗶𝗯𝗹𝗲. That’s why I’m proud that I was invited to present 𝐃𝐚𝐭𝐚𝐁𝐚𝐥𝐥𝐏𝐲 at the PyData Eindhoven X PySport Conference last December. 𝐃𝐚𝐭𝐚𝐁𝐚𝐥𝐥𝐏𝐲 is an open-source Python package for football analytics, focused on contextualized and tactical analysis by 𝗰𝗼𝗺𝗯𝗶𝗻𝗶𝗻𝗴 𝘁𝗿𝗮𝗰𝗸𝗶𝗻𝗴 𝗮𝗻𝗱 𝗲𝘃𝗲𝗻𝘁 𝗱𝗮𝘁𝗮. Since PyData and PySports share these values, they recorded the presentation (and all others!) and made it freely available: 🎥 𝗪𝗮𝘁𝗰𝗵 𝘁𝗵𝗲 𝗳𝘂𝗹𝗹 𝘁𝗮𝗹𝗸 𝗵𝗲𝗿𝗲: https://lnkd.in/ekQJSDt9 Open source isn’t just code—it’s collaboration, transparency, and progress. Thanks to the community, 𝐃𝐚𝐭𝐚𝐁𝐚𝐥𝐥𝐏𝐲 has grown further than I could have imagined (>45k downloads!). I’m excited to see what the future brings! 🔗 𝗦𝗼𝘂𝗿𝗰𝗲 𝗰𝗼𝗱𝗲: https://lnkd.in/ey6MxCjJ 📚 𝗗𝗼𝗰𝘂𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻: https://lnkd.in/en9jrX6U 👇 See the comments for the code to create a visualization like the one below using 𝐃𝐚𝐭𝐚𝐁𝐚𝐥𝐥𝐏𝐲. Thanks for the open source community for all your help, support, and guidance. Special thanks to Daan Grob who intially set up 𝐃𝐚𝐭𝐚𝐁𝐚𝐥𝐥𝐏𝐲 with me and to Tygo Nikamp for showcasing your pressure analysis at the conference with me.

2 October 2025

Sources: Mike Holcomb LinkedIn post

Want hands-on experience in OT cybersecurity?

Start with these FREE projects – no power plant required!

Getting started in OT/ICS cybersecurity doesn’t have to be hard.

And it doesn’t have to be expensive.

So start with these projects and build from there!

1. Setup Your Own “Attack & Defend” OT/ICS Lab with Labshock

Labshock is a new virtual OT environment that helps you get started!

Use it to explore defensive capabilities like detection and SEIM.

As well as having an OT environment to attack!

https://lnkd.in/eG-Y-Z2z

2. Hack Into a Power Plant with GRFICSv2

GRFICS takes a fun twist with virtual OT networks.

Giving you a CCTV feed to watch over the environment.

And then allowing you to see what changes happen due to your “testing.”

Is that smoke I see coming out of the power plant???

https://lnkd.in/eam3eQDx

3. Setup an OT/ICS Honeypot

Honeypots are systems that are designed to be hacked.

Set one of these virtual honeypots up for target practice.

Take your time to interact with different OT protocols like Modbus.

github.com/mushorg/conpot
Probably the most popular OT/ICS honeypot to get started with

https://lnkd.in/emiiasR3
Another OT/ICS honeypot from T-Mobile (yes, THAT T-Mobile)

4. Analyze Real World OT/ICS Cyber Incidents

While this might not be as exciting as some of the others…

Learning from real world incidents can help you learn.

-> Understand how attackers break into OT environments
-> Learn what attackers do once they are inside OT networks
-> Figure out how to prevent the same attacks from occuring again

OT/ICS cybersecurity companies such as Dragos and Mandiant release some incredible research on the latest incidents.

Need help getting started?

Lookup Stuxnet, TriSIS, Colonial and Fuxnet.

And don’t stop!

5. Find OT/ICS Assets Exposed to the Internet and Contact the Owners

Want to learn more about finding OT/ICS assets on the Internet?

Check out my YouTube video here:

https://lnkd.in/e7e2VkbA

Once you find these assets without obtrusive means, see if you can determine who the asset owner is.

If you’re really feeling brave, reach out and contact them.

Honestly, most of the time your work will fall on deaf ears.

But every once in a while it has a significant impact!

Just don’t share sensitive information with others.

6. Write Your Own Modbus Scanner with Python and/or ChatGPT

Writing defensive and offensive tools can be a great way to learn!

Not a developer like me? Use ChatGPT or other GenAI tools.

Interested in using ChatGPT to create security tools?

Watch “Hacking ICS/OT (& IT) with ChatGPT”

https://lnkd.in/eVduTgcC

Don’t forget – the best way to learn is to share!

As you work through your projects…

-> Document your steps
-> Take screenshots
-> Post and share
-> Have fun!
-> 🙂

P.S. What would you start with first?

🔔 Follow Mike Holcomb for more OT/ICS cybersecurity
♻️ Useful? Share to help others!

Sumber: Post LinkedIn Gilang Bhagaskara

Dulu saya kenal dua orang programmer.

Yang satu jago banget. Web dev, frontend-nya rapi, backend-nya efisien, debugging cepet. Tapi dia punya satu kebiasaan:
nggak mau belajar hal baru.
Udah nyaman di stack lama, ogah ngulik bahasa lain, bahkan anti banget sama hal-hal di luar “zona aman” dia.
“Ngapain belajar lagi? Gue udah cukup senior kok.”
Dan iya, saat itu… dia memang salah satu yang paling top di tim.

Yang satu lagi, anak baru.
Skillnya waktu itu pas-pasan. Tapi attitude-nya? Luar biasa.
Apapun dilempar, dia coba.
Disuruh ngulik Rust? Digas.
Dapet proyek mobile? Buka docs Flutter, mulai dari nol.
Sempat salah, sempat di-review habis-habisan, tapi nggak pernah berhenti belajar.

Fast forward 5 tahun…

Yang pertama masih di tempat yang sama.
Masih web dev, masih stack lama, dan gajinya stagnan.
Sementara yang kedua, sekarang lead engineer di perusahaan multinasional, megang sistem skala besar, dan gajinya?
Di atas 50 juta per bulan.

Kenapa?
Karena skill itu bisa diasah. Tapi growth mindset nggak bisa dipaksain.
Dan di dunia tech yang berubah setiap hari, yang tahan lama bukan yang paling jago, tapi yang paling mau belajar.

Kita nggak selalu butuh orang yang “bisa segalanya.”
Tapi kita butuh orang yang nggak takut belajar apa aja.