KabaddiPy: A package to enable access to Professional Kabaddi Data

Abstract: Kabaddi, a contact team sport of Indian origin, has seen a dramatic rise in global popularity, highlighted by the upcoming Kabaddi World Cup in 2025 with over sixteen international teams participating, alongside flourishing national leagues such as the Indian Pro Kabaddi League (230 million viewers) and the British Kabaddi League. We present the first open-source Python module to make Kabaddi statistical data easily accessible from multiple scattered sources across the internet. The module was developed by systematically web-scraping and collecting team-wise, player-wise and match-by-match data. The data has been cleaned, organized, and categorized into team overviews and player metrics, each filterable by season. The players are classified as raiders and defenders, with their best strategies for attacking, counter-attacking, and defending against different teams highlighted. Our module enables continuous monitoring of exponentially growing data streams, aiding researchers to quickly start building upon the data to answer critical questions, such as the impact of player inclusion/exclusion on team performance, scoring patterns against specific teams, and break down opponent gameplay. The data generated from Kabaddi tournaments has been sparsely used, and coaches and players rely heavily on intuition to make decisions and craft strategies. Our module can be utilized to build predictive models, craft uniquely strategic gameplays to target opponents and identify hidden correlations in the data. This open source module has the potential to increase time-efficiency, encourage analytical studies of Kabaddi gameplay and player dynamics and foster reproducible research. The data and code are publicly available: https://github.com/kabaddiPy/kabaddiPy

• The paper introduces KabaddiPy, the first open-source Python package designed for aggregating and accessing statistical data for the Pro Kabaddi League.
• KabaddiPy provides unified access to scattered data sources, offering comprehensive team, player, and detailed play-by-play statistics for strategic analysis.
• By providing a Python-based interface and open data access, KabaddiPy facilitates reproducible research and data-driven strategies for coaches and analysts in Kabaddi.

Analysis of "KabaddiPy: A Package to Enable Access to Professional Kabaddi Data"

The paper introduces KabaddiPy, an open-source Python module designed to aggregate and provide easy access to statistical data for the sport of Kabaddi, with a focus on the Pro Kabaddi League (PKL). Kabaddi, a traditional Indian sport, has been growing rapidly in popularity, as evidenced by its increasing viewership and the formation of various regional and international leagues. Despite its popularity, the sport lacks the comprehensive data analytics infrastructure that is available for other prominent sports, which has been a barrier to strategic analysis and research. The authors attempt to bridge this gap by developing KabaddiPy, which aims to standardize and centralize scattered Kabaddi data for dissemination among researchers and analysts.

Core Contributions

1. Data Aggregation and Accessibility:
   • KabaddiPy offers the first unified platform for accessing Kabaddi data collected from various web sources, including the PKL website, sports data archives, and specialized Kabaddi sites. The data set covers team standings, player statistics, and detailed play-by-play (PBP) data, providing a richer database than previously available.
2. Support for Strategic Analysis:
   • The module extends support for numerous analytic functions that allow for the examination of both team-level and player-level tactics. These include analysis of raiding success versus the number of defenders, zone-specific performance metrics, and tactical effectiveness over time.
3. Use of Python:
   • By providing a Python-based interface, the module becomes more accessible to the computational research community, enabling seamless integration into existing workflows focused on statistical analysis and machine learning algorithms applied to sports data. Functions such as team and player zone plotting facilitate ease of visual interpretation of gameplay dynamics.
4. Enhancement of Reproducible Research:
   • KabaddiPy ensures that data collection processes are open and that methods can be easily replicated. This supports the broader goal of fostering a community around Kabaddi research and contributing to more sophisticated strategic and performance analyses in the domain.

Numerical Results and Claims

The authors claim that KabaddiPy provides critical insights into Kabaddi gameplay by improving time efficiency in tactical analysis and subsequent strategy formulation. It aids in answering research questions about the impact of player changes, scoring patterns, and defensive errors as demonstrated through queries of match data and visualizations that depict scoring zones and player efficiency.

Implications and Future Prospects

The development of KabaddiPy holds significant implications. Practically, it offers coaches a data-driven approach to optimize team strategies, lineup rotations, and training drills based on empirical game analyses rather than purely anecdotal evidence. Theoretically, it sets a precedent for similar data access initiatives for other underrepresented sports, which could lead to an increased body of sports-focused analytical research and better engagement with emerging sports. In the future, the authors plan to extend the KabaddiPy module to include global Kabaddi leagues, which would allow for broader cross-league analyses and further strategic insights at an international level.

Limitations

The current limitations of KabaddiPy relate largely to data availability. Positional and player skills data for earlier PKL seasons are sparse, primarily due to the lack of historical data logging and public access restrictions. The authors propose technological enhancements in data tracking and sharing as essential steps to mitigate these limitations.

In conclusion, KabaddiPy represents an important step forward for Kabaddi analytics by providing a structured and comprehensive database, promoting further research, and facilitating strategic advancements in the sport. As the sport continues to gain momentum on the international stage, tools like KabaddiPy will become invaluable for adopting a more analytical approach toward gameplay strategy and performance assessment.