Update README.md

parent c114d0e7
# BasketballPlayers Dataset
Classification dataset for identifying/recognizing roles of basketball players. It has been used in the following paper:
Classification dataset for identifying/recognizing roles of basketball players.
We have built two versions of this dataset:
* sel-players
* ACB
## sel-players dataset
It has been used in the following Scratch project:
* [xai4all on Scratch](https://scratch.mit.edu/projects/303945261/)
The dataset is made up of 80 samples corresponding to five classes (Point Guard, Shooting Guard, Small Forward, Power Forward, Center) which are lilnked to 11 attributes (Height, Minutes, Points, 2P-Field-Goals-Perc, 3P-Field-Goals-Perc, Free-Throws, Rebounds, Assists, Blocks, Turnovers, , and Global Assessment).
The dataset is perfectly balanced with 20 samples belonging to each class. Numerical values associated to each sample correspond to statistics available online at the website of the Spanish Male and Female Basketball League:
* [Spanish Male Basketball League](http://acb.com/)
* [Spanish Female Basketball League](http://competiciones.feb.es/estadisticas/)
For each player, we have taken statistics related to their entire career.
In the repository you can find 10 files (all of them in *.arff format, i.e., the Weka format):
* sel-players-EN.txt.arff.all.arff (the whole dataset with header in English)
* sel-players-ES.txt.arff.all.arff (the whole dataset with header in Spanish)
* sel-players-EN.txt.arff.men.arff (only male players from the whole dataset with header in English)
* sel-players-ES.txt.arff.men.arff (only male players from the whole dataset with header in Spanish)
* sel-players-EN.txt.arff.women.arff (only female players from the whole dataset with header in English)
* sel-players-ES.txt.arff.women.arff (only female players from the whole dataset with header in Spanish)
* sel-players-EN.txt.arff.black.arff (only black players from the whole dataset with header in English)
* sel-players-ES.txt.arff.black.arff (only black players from the whole dataset with header in Spanish)
* sel-players-EN.txt.arff.white.arff (only white players from the whole dataset with header in English)
* sel-players-ES.txt.arff.white.arff (only white players from the whole dataset with header in Spanish)
Notice that Weka (https://www.cs.waikato.ac.nz/ml/weka/) is the Waikato Environment for Knowledge Analysis. We selected the Weka format because Weka is a very well-known open source Data Mining project, leaded by researchers affiliated to the University of Waikato (New Zeland), and with a huge community of users and developers worldwide.
## ACB dataset
It has been used in the following paper:
* Jose M. Alonso, [Explainable Artificial Intelligence for Kids](https://dx.doi.org/10.2991/eusflat-19.2019.21), 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), pp. 134-141, Atlantis Press, 2019.
And also in the following Scratch project:
* [xai4kids on Scratch](https://scratch.mit.edu/projects/303945261/)
The dataset is made up of 80 samples corresponding to four classes (Point Guard, Shooting Guard, Small Forward, Center) which are linked to 13 attributes (Height, Blocks, Rebounds, Assists, Points, Personal Fouls Made, Personal Fouls Received, Free Throws Percentage, 2-point Field Goals Percentage, 3-point Field Goals Percentage, Turnovers, Steals, and Global Assessment).
The dataset is perfectly balanced with 20 samples belonging to each class. Numerical values associated to each sample correspond to statistics available online at the website of the Spanish Basketball League ACB (http://www.acb.com/). For each player, we have taken statistics related to season 2017-2018.
......@@ -17,5 +70,3 @@ In the repository you can find 4 files (all of them in *.arff format, i.e., the
* ACB.train.csv.arff (80% of samples taken from the orginal dataset)
* ACB.test.csv.arff (the remaining 20% of samples from the orginal dataset)
Notice that Weka (https://www.cs.waikato.ac.nz/ml/weka/) is the Waikato Environment for Knowledge Analysis. We selected the Weka format because Weka is a very well-known open source Data Mining project, leaded by researchers affiliated to the University of Waikato (New Zeland), and with a huge community of users and developers worldwide.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment