There were three main ideas throughout the completion of the MLB Statistics Project. Main topics of code include data visualization, web scraping, and machine learning fundamentals. Zach Hracho was responsible for data visualization, Eric Powers worked on webscraping, and Minato Myers completed the machine learning fundamentals section. Our group focused on a general overview of MLB statistics and its applications. This project can be helpful in determining drafts for fantasy baseball and useful for overall analysis of the top MLB players. All of the code was run through Jupyter Notebook using Anaconda. Certain modules may have already been present on our computers, but running on another computer may not have specific libraries present. We tried to take care of this problem by installing these libraries with the pip install magic command through Jupyter Notebook. However, if there are additional Module Not Found Errors, the library will have to be installed manually. BeautifulSoup, Seaborn, Matplotlib, Numpy, Requests, PyBaseball, scikit-learn, and Statsmodels were the main libraries utilized for this project.
Feel free to download the MLB_Statistics.zip file, unzip it, and run the MLB_Statistics.ipynb Jupyter Notebook file using Anaconda.
Documentation and report available in PDF format.