saiemgilani.me
SG

SG

Building the SportsDataverse.

Hi, I'm Saiem! ML Engineer

I gave a presentation on the projects below at the Carnegie Mellon Sports Analytics Conference. The paper I wrote for the conference was selected as the winner for the Data and Software contribution, Open Track for their reproducible research competition.

The conference materials can be found here:

  • Slides
  • Repository
  • Paper

Honestly, I am working on so many sports data projects that should have only taken me a couple weeks.

  • sportsdataverse node.js source (Docs)
  • sportsdataverse-py source (Docs, PyPI)
  • cfbfastR source (Docs, Data)
  • hoopR source (Docs, Data)
  • wehoop source (Docs, Data)
  • recruitR source (Docs)
  • usfootballR source (Docs)
  • @sportsdataverse/nhl

Projects I contribute to:

  • baseballr source (Docs)
  • fastRhockey source (Docs)
  • ncaascrapR source (Docs)

They generally fall under the umbrella of the concept of the SportsDataverse. The general goal is to make sports data significantly more open and accessible, streamlining the process of gathering public data for research.

Python packages

sportsdataverse

sportsdataverse

All - Python

Python package for working with Sports data.

Node.js modules

sportsdataverse

sportsdataverse

All collegiate and 6 Professional sports - Node.js

Node.js module with access to ESPN, 247Sports, and the NCAA website

R packages

cfbfastR

cfbfastR

College Football - R

Functions to Access College Football Play by Play Data.

hoopR

hoopR

Men's Basketball (NBA and MBB) - R

Functions to Access Men's Basketball Play by Play Data.

wehoop

wehoop

Women's Basketball (WNBA and WBB) - R

Functions to Access Women's Basketball Play by Play Data.

baseballr

baseballr

MLB, MiLB, NCAA Baseball - R

Functions for Acquiring and Analyzing Baseball Data.

fastRhockey

fastRhockey

PHF - R

Functions to Access Premier Hockey Federation Play by Play Data.

recruitR

recruitR

College Sports Recruiting - R

Functions to access college sports recruiting data.

Data Repositories supporting my packages:

cfbfastR-data

cfbfastR-data

College Football - Data

Repository containing data for working with CFB data. 2002-present data included in csv, rds, and parquet format.

hoopR-data

hoopR-data

Men's Basketball (NBA and MBB) - Data

Repository containing data for most teams, players and coaches from 2002-present. All data provided in csv, rds, and parquet format.

wehoop-data

wehoop-data

Women's Basketball (WNBA and WBB) - Data

Repository containing data for most teams and games from 2002-present. All data provided in csv, rds, and parquet format.

fastRhockey-data

fastRhockey-data

Hockey (NHL and PHF) - Data

Repository containing data for most teams and games from 2010-present for NHL, 2016-present for PHF. All data provided in csv, rds, and parquet format.

Talk Data to Me

I am always looking to add more developers to the SportsDataverse developer group who share common cause with the aim to make the sports data industry more diverse and inclusive.

The SportsDataverse is a concept I have been working on with a handful of other people to create and develop packages in Python, R and Node.js. Among the goals of the SportsDataverse is to flatten the learning curve the average user has to go through to get access to the highest quality open-source data and analytics

Work with us

Are you interested in working with sports data, developing open-source packages and helping teach others to do the same? Our group is dedicated to the cause of trying to include people from more diverse backgrounds and underrepresented groups in sports.

Additionally, we are making the publicly available sports data much more accessible to the common person. The desired goal is to create a supportive community that will provide guidance and mentor those who want to be a part of the solution. Drop me a brief message below so that I can reach out to you!

Copyright © 2021 Saiem Gilani

Copyright © 2021 Saiem Gilani