SoFIFA

A SoFIFA webcrawler and Machine Learning prediction

Generate Convert Improve

Install / Use

/learn @DiogoDantas/SoFIFA

About this skill

Quality Score

0/100

README

MLFIFA

Coming soon: We are currently developing a website to compare players using statistical visualization.

This repo helps addicted FIFA players (like us) build a Dream Team in Manager mode using player statistics from the SoFIFA platform.

Repo Contents

A Web Crawler to scrape SoFIFA website.
An API to search through SoFIFA data.
A Mixed-Integer Linear Optimization algorithm for help you choose the best players and teams based on their potential and your budget.

Implementation

🕷️ Web Crawler

We built a web crawler to collect and parse information on all 18000+ FIFA players avaliable at SoFIFA.

☁️ API

Do you want to have easy access to all SoFIFA data? We provide an API for that! Check out the API folder for examples.

🎯 Optimization Algorithm

We determine optimized player configurations using the data collected from SoFIFA. A subset of player information is used to form an Integer Programming optimization problem. For optimization we use the Pulp python module.

Please see the example Jupyter notebook for implementation details.

👥 Authors

🧔 Diogo Dantas:

diogoventura@cc.ci.ufpb.br
Github

🤵 Arnaldo Gualberto:

arnaldo.g12@gmail.com
Github
Personal Website

Related Skills

claude-opus-4-5-migration

84.5k

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5

model-usage

341.2k

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

feishu-drive

341.2k

things-mac

341.2k

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database)