Chapter 9. Using APIs for Data Analytics
Your eyes see the game much better than the numbers. But the numbers see all the games.
Dean Oliver, sports statistician
The sports world loves all forms of data analytics—charts, graphs, and statistics that describe the results of events or predict what will happen next. When a sports fan views those data analytics, they probably never consider what data source was used to create them. In many cases, the data source is an API. In this chapter, you will learn best practices for consuming APIs and creating data analytics products using Jupyter Notebooks, a popular tool used by data scientists.
Custom Metrics for Sports Analytics
One of the most celebrated forms of analytics is the custom metric, a calculation that summarizes complicated behavior, ability, and outcomes as a number. Every sport has metrics that players, coaches, managers, and fans pay attention to. Baseball has the longest history with metrics, from the historical earned run average (ERA) to the modern weighted runs created plus (wRC+) and wins against replacement (WAR). Soccer fans and professionals alike focus on the expected goals (xG), a method of defining quality shots that has motivated a variety of secret-sauce models. The NBA uses the player efficiency rating (PER) to measure a basketball player’s all-around value.
Some of the most interesting work in custom metrics is happening in football, where the NFL has sponsored an annual analytics contest called the Big ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access