Blogs
NBA Machine Learning #1 - Introduction to modelling
About series
What is machine learning modelling about?
Define Problem
Data preparation
Visual analysis
Data cleaning
Feature engineering
Feature selection
Class imbalance
Choose modelling techniques
Why one should always start with simpler solutions?
Bias - Variance tradeoff
Bootstrapping
Model evaluation
Conclusion
About series
So I came up with an idea to write series of articles describing how to apply machine learning algorithms on some examples of NBA data.
... Read more …
Playoff Matchup Dashboard 1.0 is online!
I am super happy to announce that my Playoff Matchups Dashboard is online and ready to be used! Best part of that fact? Playoffs haven’t officially started yet…
(I am writing this in hurry, because Tip-off is in 25 minutes…)
Anyway, Dashboard gathers information about playtypes distribution, various tracking data, most important matchups, most common lineups from regular season and also all the shotcharts.
You can check it out here
... Read more …
NBAr 1.1 update
Hola!
Just wanted to let you all know that I recently updated NBAr with couple of new functions:
getAllPlaytypes
getAllTracking
getHustleBoxscore
getMatchups
Interesting story with getAllPlaytypes and getAlltracking - I just recently started to using player tracking and playtypes data and realized they really need wrapping functions to download and combine all at once. Here they are - quite simple, quite good. Both create datasets with +120 columns but I made sure there are no duplicates or some dissapearing players.
... Read more …
NBA Player stats dashboard v1.0
Have you ever had that feeling that you really need another dashboard with NBA player’s data in your life?
Me neither.
Well, actually, I had! So I developed one! You can find it here
All data collected using NBAr package - check it out here!
I use it mostly for analysis I do and I found it is actually useful tool to access player’s data easily - I tried to keep as much information in one place as I could so I don’t have to jump around pages and filters like I need on nba.
... Read more …
Detecting outlying statlines in NBA
We all know what happens on social media after - insert name of random/unknown/boring/funny/weird/forgotten player - all of sudden makes all 8 of his 3 point attempts, scores thousands of points and wins that very important game in mid-January for his team. You know, the monthly-Jeff-Green-can-be-a-factor-in-the-playoffs game.
We have seen the Brandon-Jennings-scoring-55-as-a-rookie game. That Kendrick-Perkins-owns-Nuggets-in-the-paint-with-16pts performance (that, for me as a Nuggets fan, was heartbreaking). All those Dwight-Howard-after-years-of-struggle-is-finally-back games. Jonas Valanciunas pump-fake finally fools a defender.
... Read more …
Cavaliers - Warriors offense-defense analysis
Lets try to predict what will happen in NBA finals. On one side - uber team with perennial all stars, 2 of top3 NBA players, 3 of top10, 4 of top15. Golden State is a monster. They can shoot from anywhere, contested or not, pull up, spot up, you name it. On defense they switch on screens in the blink of an eye, with every member of their death lineup able to guard almost all positions (Curry will not guard frontcourt guys).
... Read more …