Skip to content

GreenPlanet-Capital/jesse-optuna

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is a fork of cryptocoinserver/jesse-optuna, updated to be compatible with newer versions of Jesse.

Jesse optuna

Only works with the new GUI version of jesse. Use optuna directly to work with the results and create visualisations of the results. Jupyter Notebook might be usefull here.

You need the study name and storage, which you set in the config.yml, to load it for that:

    study_name = f"{cfg['strategy_name']}-{cfg['exchange']}-{cfg['symbol']}-{cfg['timeframe']}"
    storage = f"postgresql://{cfg['postgres_username']}:{cfg['postgres_password']}@{cfg['postgres_host']}:{cfg['postgres_port']}/{cfg['postgres_db_name']}"

The config.yml should be self-explainatory.

Installation

# install from git
pip install git+https://github.com/siglun88/jesse-optuna.git

# cd in your Jesse project directory

# create the config file
jesse-optuna create-config

# create the database for optuna 
jesse-optuna create-db optuna_db

# edit the created yml file in your project directory 

# run
jesse-optuna run

Optuna dashboard

Install and run optuna dashboard to analyze and evaluate results.

# Install Optuna dashboard and dependencies to make the dashboard faster
pip install optuna-dashboard
pip install optuna-fast-fanova gunicorn

# Run optuna dashboard
optuna-dashboard postgresql+psycopg2://jesse_user:password@postgres:5432/optuna_db

Disclaimer

This software is for educational purposes only. USE THE SOFTWARE AT YOUR OWN RISK. THE AUTHORS AND ALL AFFILIATES ASSUME NO RESPONSIBILITY FOR YOUR TRADING RESULTS. Do not risk money which you are afraid to lose. There might be bugs in the code - this software DOES NOT come with ANY warranty.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%