Analyzing Amateur Esports: Descriptive Statistics and EDA for Ld2L.GG
ld2l.gg
The world of esports is vast and dynamic, with a passionate community and fierce competition across all levels. While much of the spotlight shines on professional leagues, amateur esports leagues offer a unique and evolving space for aspiring players. To better understand and gain insights into these competitive environments, I embarked on a personal project focusing on descriptive statistics and exploratory data analysis (EDA) of an amateur esports league.
Esports at the amateur level presents an opportunity to uncover trends, patterns, and potential performance indicators that can help players, teams, and organizers gain a deeper understanding of their scene. This project focuses on collecting and analyzing data from an amateur esports league to reveal hidden stories and metrics behind the matches.
Using Python and a robust suite of data science libraries, I performed extensive exploratory data analysis (EDA) to uncover key statistics, identify outliers, and create visualizations that offer a comprehensive view of league dynamics. By leveraging descriptive statistics, the analysis highlights trends in player performance, team composition, win rates, and more, providing an in-depth look at what makes a successful amateur team or player.
The final CSV structure of the project can also be used for machine learning across differing seasons or to quickly load into a common visualization tool like PowerBI or Tableau.
The insights gained from this analysis can be used by league organizers for better structuring competitions, by players seeking to improve their gameplay, or by anyone interested in understanding the nuances of amateur esports through a data-driven lens.
The project serves as a testament to the power of data analysis in revealing hidden insights and improving understanding in diverse areas such as esports. Feel free to explore the project and contribute on GitHub: ld2l-data.
Example visualization showing rolling averages for teams.
A distribution of players based on ranked category to determine spread of skill.