NBA
A database with information about basketball matches from the National Basketball Association. Lists Players, Teams, and matches with action counts for each player.
Original source: www.nba.com
Versions
NBA (by Oliver Schulte)
- There are factual errors in the database. For example, "3pm-a" attribute is constant in the database, but it shouldn't be. Some records contain wrong values, like the record for Stephen Curry (PlayerId=31) in a game of Golden State Warriors against Dallas (GameId=11). Action table in the database says that he scored 27 points, but the results at http://www.nba.com/games/20140331/MEMDEN/gameinfo.html says he scored 23 points. The difference is either caused by missalignment of lines during data preprocessing or by a late fix of the errors at nba.com. Unfortunatelly, this is not the only row with errors. Another error is in the line with James Harden (PlayerId=55) in GameID=12. Further differences are possible.
Dataset details
- Associated task:
- Classification
- Domain:
- Sport
- Data types:
- Size:
- 300 KB
- Count of tables:
- 5
- Count of rows:
- 1,221
- Count of columns:
- 72
- Missing values:
- No
- Compound keys:
- No
- Loops:
- Yes
- Type:
- Real
- Instance count:
- 30
- Target table:
- Game
- Target column:
- ResultOfTeam1
- Target ID:
- GameId
- Target timestamp:
- Date
Algorithms
Dataset version | Target | Algorithm | Author text | Measure | Value |
---|---|---|---|---|---|
NBA | ResultOfTeam1 | Predictor Factory | Predictor Factory | Accuracy | 0.6 |
How to download the dataset
The datasets are publicly available directly from MariaDB database.
- Open your favourite MariaDB client (MySQL Workbench works, but see FAQ)
- Use following credentials:
- hostname: relational.fel.cvut.cz
- port: 3306
- username: guest
- password: ctu-relational
- Export "NBA" database (or other version of the dataset, if available) in your favourite format (e.g. CSV or SQL dump).