Skip to content
Files from MecaFootCo project
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.ipynb_checkpoints gathering data Oct 3, 2019
Images conclusion of notebook 3 Oct 7, 2019
__pycache__ restructuration Sep 26, 2019
data gathering data Oct 3, 2019
python_files conclusion of notebook 3 Oct 7, 2019
.gitignore add files to gitignore Oct 8, 2019
1_Introduction_to_space_occupation.ipynb notebook 3 Sep 30, 2019
2_Time_calculation.ipynb
3_Comparison_of_ways_to_quantify_free_space.ipynb
4_Free_space_and_3-points_efficiency.ipynb
5_video_space_occupation.mp4 add video Sep 30, 2019
Bibliography.md
Closest_player_to_a_point.pdf restructuration Sep 26, 2019
README.md

README.md

MecaSportCo

Introduction

Today, technology is increasingly used in sport. Indeed, the players' statistics are more and more accurate and more and more numerous. Clubs employ people to acquire data and use it to improve performance. It is in this context that the MecaSportCo Research Application Project, conducted at the Ecole Centrale de Lyon by Gabin Rolland and Nathan Rivière, under the supervision of Wouter Bos and Romain Vuillemot.

The aim of this study is to quantify how "free" a basketball player is and how this influences his 3-points shot performance.

Data

The dataset we use is derived from Stats company data and SportsVU technology. These are the 632 men's basketball games in the NBA between the 2013-2014 and 2016-2017 seasons. For each match we have the movement data for the ball and players taken 25 times per second and stored in the form JavaScript Object Notation (JSON). The following figure shows the general structure of the data:
dataschema

Work performed

Bibliography

References of the project can be found in Bibliography

You can’t perform that action at this time.