— In the News —
Most people know that trackers follow them around the web but most people don't realize just how deep that rabbit hole goes. This deep dive into the world of online tracking will help you understand who's tracking you, what they do with your data and how to protect yourself.
— Tools and Techniques —
The availability of giant datasets and faster computers is making it harder to collect and study private data without inadvertently violating people’s privacy. In this interactive post, Adam Pearce and Ellen Jiang take a look at how random numbers can help.
Great insights into the data team at Netflix. Here's an inside look at what they do exactly and how they're organized.
Which is more important? Getting the answer quickly or getting an accurate answer? It's never that easy but the question is a great starting point for discussion. Ultimately, this post by Caitlin Hudon leads to a well thought-out intake form to consider for your own data team.
or anyone interested in getting started with sports analytics, this is an awesome collection of tutorials to explore. Topics include coding, analysis techniques, data access and libraries for 🏈 ⚾ ⚽ 🏒 🏀 & more!
- DuckDB – an embeddable SQL OLAP database management system, optimized for analytics.
- Deequ - library built on top of Apache Spark for defining "unit tests for data", which measure data quality in large datasets.
- Norfair - customizable lightweight Python library for real-time 2D object tracking.
- Eiten - open source Python toolkit that implements a variety of statistical and algorithmic investing strategies.
— Resources —
NumPy is a key component of nearly every Python library that does scientific or numerical computation. This is a very readable paper that explores how NumPy became so important, the ecosystem around it and a high-level view of how it works. This paper will be widely cited.
This new online book introduces a new collection of R software for model building. Covers modeling fundamentals, feature engineering, tools, tips and lots of examples along the way. The last chapters aren't finished yet but the book is far enough along to be useful.
— Data Viz —
Sony Music asked Nadieh Bremer to design a data-driven alternative to the customary gold and platinum discs that popular artists receive and the result is AWESOME. Here's a detailed look at the considerations for the new design with lots of graphics along the way. Stunning.