McKay Johns Profile picture
Feb 17, 2021 29 tweets 7 min read Read on X
Here is a list of all of the tutorials I have created so far to make it easier to find and access them:
How to scrape understat:

How to create a pitch:

How to create pass maps:

How to create heatmaps:

How to create shot maps:

How to create pass networks:

How to create xG flow charts:

Linear Regression:



How to create convex hulls:

How to create beeswarm plots:

How to create waffle plots:

Voronoi Diagrams

Player dashboards pt 1 - intro to grid spec
How to Get Data From FBREF
Ultimate Guide to Pandas for Data Science/Analytics

Methods for cleaning data in Python
Updated pitch creation with mplsoccer

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with McKay Johns

McKay Johns Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @mckayjohns

May 5
Sports analytics can be hard and competitive

Knowing what to work on to help yourself standout can be just as tough

Here are 5 project ideas to give you some ideas
1. A data collection project

Data collection is a great beginner project

- Scrape data from a site
- Clean, transform and prepare that data
- Store that data into a database of some sort
2. Scouting project

Scouting is a key part of any sport to find undervalued players or players to improve a team

The goal here is to use statistics and data analysis to create reports and analysis on players that would be good for a team
Read 10 tweets
Apr 14
I've been teaching myself prompt engineering and working with LLMs over the past year and a half

Here are my favorite resources to learn & get started
1.

Prompting Engineering Guide is so comprehensive and I find myself referring to it constantly as I work with different prompts and LLMs

Great resource to get started with promptingpromptingguide.ai
2.

has amazing free video courses that are hosted and taught by industry professionals

When prompt engineering and LLMs first started to make an appearance I was doing basically every course they came out withdeeplearning.ai/short-courses/
deeplearning.ai
Read 6 tweets
May 16, 2022
Maybe a hot take --

Learning data & software engineering skills will help you improve as a data scientist a lot faster than just knowing how to run code in a Jupyter Notebook
To clarify, being able to run and test in a Jupyter Notebook is great. I love notebooks.

But if you have an understanding of software and building actual pipelines you'll be far more valuable to a company/employer.
Learning how things all work together in pipelines has helped me understand a lot more of how stuff actually works in business and how I can improve my code, models, and ideas to fit business needs.
Read 4 tweets
Jul 19, 2021
10 things I would do differently if I were to start data science/sports analytics over: 🧮 ⬇️
1. Focus on learning coding fundamentals

Learning the basics of how a coding language actually works and building a base on the fundamentals of that language will take you very far.
2. Not take gaps

I started coding by learning c++ and hated it.

Took a 2-year gap.

Found python and loved it.

I'd probably be a lot further along if I would have just kept trying out different things until something stuck.
Read 11 tweets
Mar 9, 2021
Before I first started getting into sports analytics I didn’t know how people were creating such cool graphics and visualizations.

For everyone who wonders how it all works, here’s the inside scoop on how to create them and resources for each:
1. Python 🐍

Definitely the most popular programming language. Packages such as @matplotlib and seaborn make it easy to create great visualizations

mplsoccer (@numberstorm), @FC_Python, and my YouTube channel are great Python guides for getting started
2. R 📐

Another programming language that excels in statistical analysis and data visualization. A little bit of a steeper learning curve in my opinion, but ggplot is great for creating visualizations.

Check out @FC_rstats, as well as @MishraAbhiA who is doing a tutorial soon
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(