Still Work in progress!
Practice project made for learning purposes
Project is made of three part.
First part scrapes past statistic for LoL, Dota and CSGO.
Second part predicts winner of a match based on scraped statistics.
Third hits selected CZ bookies, and if a games are played, compares the odds of
predictor against bookie odds and suggest appropriate action. Does not bet itself.
Currently LoL and CS:GO seems to be working reasonably well.
Accuracy score (.score, one of the metrics used) for games:
- LoL ~73% (RandomForrest)
- Dota ~68% (RandomForrest)
- CS:GO ~70% (GradientBoosting)
Dota does not deliver in real scenario.
Run main.py --help for possible actions.
OR
run X_main.py in scrape folder of the game to download the statistics ( which might take a while...), then run main
main.py --compare_odds name_of_game : Checks if any games are being offered at implemented bookies and if so, compares predicted odds against bookie odds, and then sends email with recommended action.
Just install dependencies from environment.yaml .
- Project is not intended for production
Pavel Klammert – @LavinaVRovine – [email protected]
https://github.com/LavinaVRovine
Distributed under the MIT license. See LICENSE for more information.
- Fork it (https://github.com/yourname/yourproject/fork)
- Create your feature branch (
git checkout -b feature/fooBar) - Commit your changes (
git commit -am 'Add some fooBar') - Push to the branch (
git push origin feature/fooBar) - Create a new Pull Request