This project explores the utilization of machine learning techniques in the context of the National Basketball Association (NBA). The project focuses on leveraging data analysis and machine learning algorithms to gain insights into various aspects of NBA games, players, and teams.
The project consists of two main components:
-
Exploratory Data Analysis (EDA): In this phase, the project involves the exploration and visualization of NBA datasets to uncover patterns, trends, and relationships within the data. Various statistical techniques are employed to gain a deeper understanding of the dataset.
-
Machine Learning Implementation: The second phase of the project involves the application of machine learning algorithms to develop predictive models and make data-driven predictions in the NBA domain. These models are trained on historical NBA data and used to forecast game outcomes, player performance, and team rankings.
To run the code and reproduce the results of this project, the following dependencies are required:
- Python (version 3.0 or higher)
- Pandas (version 1.0.0 or higher)
- NumPy (version 1.18.0 or higher)
- Scikit-learn (version 0.23.0 or higher)
- Matplotlib (version 3.2.1 or higher)
The project repository is organized as follows:
nbafinals/ |- scraper/ |- scraper.ipynb |- preprocessingdata.ipynb |- workinprogress/ |- TwitterAPI.ipynb |- WIPmlmodels.ipynb |- WIPplayerclustering.ipynb |- wipxB.ipynb |- finals_project.ipynb |- machine_learning.csv |- README.md