All Projects → khanhnamle1994 → world-cup-2018

khanhnamle1994 / world-cup-2018

Licence: MIT license
An exploratory data analysis and data visualization project for World Cup 2018

Programming Languages

Jupyter Notebook
11667 projects

World Cup 2018 Data Analysis

In this project, I did an in-depth analysis and visualization on the FIFA18 dataset. The dataset is collected at this GitHub Repo. The goal is to predict the best possible international squad lineups for these 10 teams: France, Germany, Spain, England, Brazil, Argentina, Belgium, Portugal, Uruguay, and Croatia at the 2018 World Cup this summer in Russia.

The complete notebook can be accessed here.

I also wrote an accompanied blog post: FIFA World Cup 2018: A Data-Drive Approach to Ideal Team Line Up.

world-cup

Dataset

  • Every player featuring in FIFA 18
  • 70+ attributes
  • Player and Flag Images
  • Playing Position Data
  • Attributes based on actual data of the latest EA's FIFA 18 game
  • Attributes include on all player style statistics like Dribbling, Aggression, GK Skills etc.
  • Player personal data like Nationality, Photo, Club, Age, Wage, Salary etc.

The dataset contains all the statistics and playing attributes of all the players in the Full version of FIFA 18.

Data Source

The data is scraped from the website [https://sofifa.com][1] by extracting the Player personal data and Player Ids and then the playing and style statistics.

Requirements

License

MIT. See the LICENSE file for the copyright notice.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].