We'll be using Pandas to perform EDA and to clean the dataset. Python will be used for further analysis.
We'll be running the data on an OVH server using AlmaLinux as the distro, and we'll connect it to a Postgres database. In addition, a web scraper will be created with Python to ensure the most recent UFC data available will be stored.
We'll be using SciKitLearn as our ML library in order to create a classifier. To start, this will be a simple logistic regression to make sure the model works properly with the dataset. Our training and testing data will be split using the standard 80:20 ratio. We will also be experimenting with Python's AutoML libraries in an attempt to increase performance.
We'll be creating an interactive dashboard using Streamlit.