Made for the Women In Sports Data Hackaton
Working with data from Euro 2020. Get insightful charts and informations from player and team performance during the competition using statsbomb and fbref data to generate Machine Learning models to recommend players and predict good passers.
Libraries needed
pip install pandas
pip install time
pip install matplolib.pyplot
pip install seaborn
pip install numpy
pip install sklearn
pip install math
pip install mplsoccer
pip install soccerpllots
Installing the API
pip install Euro2020_API
Importing the API
from Euro2020_API import Stats
| Method: | What the method does: |
|---|---|
SimilarOffense(player_name) |
Returns a dataset with similar players(Forwards and Midfileders) related to the one you choose by a KMeans model. |
SimlarDefense(player_name) |
Returns a dataset with similar players(Defenders and Midfileders) related to the one you choose by a KMeans model. |
RadarChartOff(player1, player2) |
Returns a Radar chart comparing two offensive players performance and a scatterplot that shows their grade and salary. |
RadarChartDef(player1, player2) |
Returns a Radar chart comparing two defensive players performance and a scatterplot that shows their grade and salary. |
RadarChartGK(player1, player2) |
Returns a Radar chart comparing two Goalkeepers performance and a scatterplot that shows their grade and salary. |
Scorers() |
Returns a dataframe with the players who had high number of goals. |
Passers() |
Returns a dataframe with the players who had high number of assists and passing percentage. |
get_player(player_name) |
Returns a dataframe with every Fbref info abouth them during the Euro. |
Parameters:
Example of Outcome plots
Repository with the documentation and examples of how to use the package.
- https://github.com/AnabeatrizMacedo241/Euro2020_API
- https://github.com/AnabeatrizMacedo241/women_in_sports_hackathon