Having some fun with football stats and data science
This project is written mostly in Python using the Miniconda distribution for Windows. To this end, I have a script to automate the build - setting up environment, running tests, processing data and launching applications.
- World Cup 2018 predictions notebook report
- Analysis of goals in European leagues notebook report
- Predicting market value of Middlesbrough FC players notebook report
- Shots analysis of Lionel Messi at Barcelona notebook report
- Euro 2020 (2021) predictions notebook report
Directory/File | Description |
---|---|
app/ | Web app for Dash dashboards, with assets |
data/ | All the data, from the original raw data dump through to the final processed data |
models/ | Trained and serialized models, model predictions, or model summaries |
notebooks/ | Jupyter notebooks. Naming convention is a project area, a number (for ordering), and a short description |
references/ | Data dictionaries, manuals, and all other explanatory materials |
reports/ | Writen reports, with figures |
src/ | Source code for use in this project |
tests/ | Test scripts |
build_automation.bat | Script to automate enviroment setup, testing, data processing and application startups |
LICENSE | Project license |
README.md | This page :) |
requirements.txt | Standard Python dependencies file |
setup.py | Standard Python packaging script |
Credit to all the data sources, not least...
- FBref
- Penn World Tables Feenstra, Robert C., Robert Inklaar and Marcel P. Timmer (2015), "The Next Generation of the Penn World Table" American Economic Review, 105(10), 3150-3182, available for download at www.ggdc.net/pwt
- Wikipedia
- World Football Elo Ratings
Shoutouts to all the creators and maintainers of libraries that made this work possible.
Project based on the cookiecutter data science project template. #cookiecutterdatascience