GithubHelp home page GithubHelp logo

jieguangzhou / fifa-world-cup-2022 Goto Github PK

View Code? Open in Web Editor NEW
10.0 4.0 3.0 5.11 MB

DolphinScheduler machine learning "FIFA World Cup 2022 Predictions" betting workflow

License: MIT License

Python 97.94% Dockerfile 0.69% Shell 1.36%
machine-learning dolphinscheduler world-cup-2022 data-science

fifa-world-cup-2022's Introduction

FIFA-World-Cup-2022

DolphinScheduler machine learning "FIFA World Cup 2022" betting workflow

YouTube: Predict FIFA World Cup 2022 champion and get a daily betting strategy by DolphinScheduler!

In this project, we will use machine learning to predict which country will win the FIFA World Cup 2022 and get a betting strategy every day.

World Cup predictions

Here are the results of two different forecasting methods

Simulate 1000 World Cup qualification results based on team win probability

Probability of championship

Brazil       0.193
Argentina    0.160
France       0.140
Spain        0.137
England      0.131

The top four

No.1: Brazil
No.2: France
No.3: Argentina
No.4: Belgium

Choose the team with a high probability of winning

No.1: Argentina
No.2: France
No.3: Spain
No.4: Belgium

All competition results can be viewed in the following two files

https://github.com/jieguangzhou/FIFA-World-Cup-2022/blob/workflow-pro/results/predict.txt

The above results are from the branch workflow-pro. This branch will train longer models and run more simulations

Building a prediction system in three steps

Step-1 start DolphinScheduler

we can start a Dolphinscheduler standalone server using Docker

docker run --name dolphinscheduler-standalone-server -p 12345:12345 -p 25333:25333 -d jalonzjg/dolphinscheduler-fifa

And then, you can log in to the DolphinScheduler at http://localhost:12345/dolphinscheduler/ui

user: admin password: dolphinscheduler123

image-20221124232236471

Step-2 submit workflow

python3 -m pip install apache-dolphinscheduler==3.1.1
export PYDS_HOME=./
python3 pyds.py

You can click the Project -> FIFA

image-20221124231716302

Then, we can see 3 workflow

  • training: Use FLAML to train model
  • predict: Use the model to predict which country will win the World Cup
  • betting-strategy: Get betting strategy every day

image-20221124231751744

Step-3 run workflow

start training workflow

image-20221124231816267

We can view log after the workflow had finished

image-20221124231849652

Start predict workflow

We can view log after the workflow had finished

image-20221124232014546

Start betting strategy workflow

image-20221124232037988

$[yyyy-MM-dd]mean dolphinscheduler will use the current year, month and day as a parameter, we can also set it to 2022-12-01 or other date.

image-20221124232109784

Some Notes

fifa-world-cup-2022's People

Contributors

jieguangzhou avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

fifa-world-cup-2022's Issues

get_odds error

the API only supports two days' odds data, If you request data after the day after tomorrow, there may be an error

Can not access data in some region

Add https://ghproxy.com/ to be proxy, fix the download_data.sh like below

mkdir -p /tmp/fifa
wget https://ghproxy.com/https://raw.githubusercontent.com/jieguangzhou/FIFA-World-Cup-2022/master/data/international_matches.csv -O /tmp/fifa/international_matches.csv
wget https://ghproxy.com/https://raw.githubusercontent.com/jieguangzhou/FIFA-World-Cup-2022/master/data/schedule.csv -O /tmp/fifa/schedule.csv

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.