Using historical MLB (Major League Baseball) data retrieved from Sean Lahman’s baseball database, this application provides visualizations of team and player statistics dating from 1903 to 2020. Based on 2020 team rosters, the MLB Data Explorer also provides player batting projections and a light implementation of Machine Learning with a linear regression analysis of current players performance. Powered by Plotly’s Dash, with the layout designed using faculty.ai’s Dash Bootstrap Components, and analytics conducted using Pandas, SKLearn, and custom functions. This project is in continuous development and is subject to change.
This application was featured by Plotly in their April 2021 Sports Analytics webinar and included in their Medium article.
Source code and Jupyter Notebook for this project can be found in my GitHub.
Live website is hosted on Heroku.