From Rules to Reality: Python's Role in Shaping Roundnet
summary
Data pipeline uses Google Sheets + Colab to ingest and analyze annotated match video data, producing a baseline from 73 games annotated (17+ hours) that shows less than 10% rallies and nearly 50% of points as aces or double faults. Two global rule test packages (A/B) run across ~22 events; early Package A data shows higher touches and rally counts but also increased double faults and too-small samples for statistical significance. Player surveys are translated and summarized with an LLM.
AI-written summary · about
chapters (8)
- 0:00Roundnet and Python's role
- 3:23Problem with aces and side outs
- 7:18Data-driven rule changes
- 11:03Baseline gameplay analysis
- 15:46Goals for satisfaction
- 18:14First results from package A
- 20:25Community plans
- 21:50Q&A
related talks
41mFootball's data analytics in python
44mAutomating Analysis
19mFootball Analytics with the Soccermatics Package
48mHuman data interactions: experiments in how humans analyze data
02h 02mUsing Open Game Data to Understand Game-Based Learning
01h 26mData Driven Action: a primer on Data Science
28mUsing Python in a Data Hackathon
39mSoftware Analytics with Data Science on Software Data