The main reason behind our topic other than the popularity of football is the possibility to directly compare two separate datasets with each other to discover patterns that may not be visible without any data analysis.
After some data cleaning we were able to efficiently use the two datasets to answer our questions.
Our source code and results can be viewed in the Jupyter Notebook file here
- Stelios Pafitis
- Giorgos Nikiforou
- Michalis Thomas
- Mahan Fathi