eddwebster Goto Github PK

followers: 608.0 following: 444.0 repos: 149.0 gists: 0.0

Name: Edd Webster

Type: User

Company: @lcfc-analytics

Bio: Football Data Scientist @lcfc-analytics. Previously data @LEGO and @analytics-fc. For open source, see: github.com/eddwebster/football_analytics

Twitter: eddwebster

Location: UK

Blog: www.eddwebster.com

Hi, I'm Edd

Football Data Scientist ⚽📊.

Expertise in:

Football Analytics
Data Science and Machine Learning
Python
R
SQL
Tableau

👋 About Me

I am an experienced Data Science and Football Analytics professional with 5+ years of professional data science experience, currently working in my second season in elite sport. Previously I was the First Team Lead Data Scientist at Leicester City Football Club, and Data Scientist for Analytics FC and the LEGO Group.

I enjoy exploring and working in the fields of data science, machine learning, statistics, data engineering, data visualisation, and football analytics, for which this GitHub profile includes much of my publicly available work around these topics.

Please see my football_analytics repository for a collection of football analytics projects, data, and analysis that I have created, with links to publicly available resources in the football analytics community.

For more information:

📚 Code

Although a little out of date now (with code I would dearly like to refactor), the code in my football_analytics GitHub repository can be found in the notebooks subfolder, of which the workflow is divided into the following:

📊 Data Visualisation and Tableau

For Tableau dashboards produced, please see my Tableau Public profile: public.tableau.com/profile/edd.webster.

Examples dashboards:

⚒️ Tech Stack

I am comfortable working with the following languages and software:

Python:

Python

Jupyter Notebooks

pandas

NumPy

Scikit Learn

matplotlib

PySpark

Other Data Science languages and tools:

R Studio

Tidyverse

Tableau

Power BI

Databricks

Airflow

AWS

Docker

📰 Articles

🧑‍🎓 Courses

SQL Masterclass

📈 GitHub Stats

⭐ Football Analytics GitHub Stars History

Star tracker for the football_analytics repository of open-source football analysis projects and resources.

📫 Contact

For more information, I am available through all the following channels:

Edd Webster's Projects

mapping-match-events-in-python

Luca Pappalardos code for working with and plotting Wyscout data

marcosdiak

mathematical-modelling-of-football-assignments

Contains code and content output for assignments for the Uppsala University Mathematical Modelling of Football course.

matplotblog

Matplotlib blog

matplotlib-tutorials

The Jupyter notebooks behind my my matplotlib tutorials.

matplotsoccer

Package to visualize soccer data

metrica-pitch-control

A python implementation of the paper Wide Open Spaces: A statistical technique for measuring space creation in professional soccer

ml-coursera-python-assignments

Python assignments for the machine learning class by andrew ng on coursera with complete submission for grading capability and re-written instructions.

mplsoccer

Football pitch plotting library for matplotlib

msc-applied-statistics-project-code

narya

The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository contains the implementation of the flowing paper https://arxiv.org/abs/2101.05388. We also make available all of our pretrained agents, and the datasets we used as well.

nbastatr

NBA Stats API Wrapper and more for R

non-shot-xg

Using a StatsBomb event based expected goals model with Metrica's tracking data to attribute non-shot-xG to every possession of each team.

northpitch

Soccer Plotting Library

open-data

Free football data from StatsBomb

opendata

SkillCorner Open Data with 9 matches of broadcast tracking data.

optaeventdata

pacman-game

In this project, the Pacman agent will find paths through his maze world, both to reach a particular location and to collect food efficiently. I implemented general search algorithms such as depth-first, breadth-first, uniform cost, and A* search algorithms which are used to solve navigation problems in the Pacman world.