Welcome to my NBA Game Performance Analytics project! This repository showcases my journey in sports data analytics by analyzing team performance during the 2022-2023 NBA season. By leveraging Python, APIs, and data visualization, I derived meaningful insights into team dynamics and game performance.
- Extract real-time game data from the NBA API.
- Process and clean the data to ensure accuracy and consistency.
- Analyze team performance metrics, with a focus on average points scored per game.
- Visualize findings to provide actionable insights into NBA team performance.
-
Data Extraction:
- Utilized the NBA API to collect detailed game data from the 2022-2023 season.
- Ensured real-time relevance and data accuracy for analysis.
-
Data Cleaning & Transformation:
- Handled missing and inconsistent values.
- Transformed raw data into structured, actionable datasets.
-
Performance Analysis:
- Ranked teams based on average points scored per game.
- Identified the top 10 teams with standout offensive performances.
-
Visualization:
- Designed clear, visually appealing graphs to represent team performance metrics.
- Focused on making insights accessible to both technical and non-technical audiences.
- Programming: Python
- Data Analysis Libraries: Pandas, NumPy
- Visualization Tools: Matplotlib, Seaborn
- APIs: NBA API
- Data Wrangling: Cleaning, Transforming, and Structuring Data
- The top-performing teams in the 2022-2023 NBA season were identified based on average points per game.
- Offensive strategies and game dynamics were highlighted through data-driven insights.
As a passionate follower of sports, I am motivated to contribute my skills in data engineering and analysis to the field of sports analytics. This project is a stepping stone towards a career where I can merge my technical expertise with my love for sports to create impactful insights that drive decisions.
My ultimate goal is to work as a Sports Data Analyst, contributing to the evolving landscape of sports by combining data-driven insights with strategic decision-making.
- Expanding this project to include advanced metrics such as player efficiency ratings (PER) and defensive stats.
- Incorporating machine learning techniques for predictive analysis (e.g., game outcomes, player performance).
- Collaborating on open-source sports data projects to further enhance my portfolio.
- LinkedIn: ysayaovong
- GitHub: YSayaovong
- Email: ysayaovong@gmail.com
Feel free to explore this repository and provide any feedback or suggestions. I'm excited to grow and learn as I continue my journey into sports data analytics!