verstack is a set of Machine learning tools to make a Data Scientist's work efficient.
The package contains multiple tools for: training & tuning machine learning models, creating ensembles, working with datetime objects, data transformation & wrangling, imputing missing values, concurrency work and many more.
Please refer to the official documentation for more information.
The project was created by Danil Zherebtsov in 2020.
It is currently maintained by a single contributor with occasional contributions by the active members of the community.
$ pip install verstack
$ pip install --upgrade verstack- Python (>= 3.6)
- numpy
- pandas<=2.0.3
- scikit-learn>=0.23.2,<=1.1.3
- lightgbm>=3.3.0,<=4.0.0
- optuna>=2.10.0,<=3.2.0
- plotly>=5.3.1,<=5.11.0
- matplotlib
- python-dateutil>=2.8.1,<=2.8.2
- holidays==0.11.3.1
- mlxtend
- category_encoders>=2.4.0,<=2.5.1
- fastparquet
I welcome new contributors of all experience levels. verstack community goals are to be helpful, welcoming, and effective.
Development Guide
based on scikit-learn best practices has detailed information about contributing code, documentation, tests, and more.
- Official source code repo: https://github.com/DanilZherebtsov/verstack
- Issue tracker: https://github.com/DanilZherebtsov/verstack/issues
You can check the latest sources with the command:
git clone https://github.com/DanilZherebtsov/verstack.git
Before opening a Pull Request, have a look at the full Contributing page to make sure your code complies with the following guidelines: https://scikit-learn.org/stable/developers/index.html
- Author email: danil.com@me.com
- Author profile
If you use verstack in a media/research publication, we would appreciate citations to this repository.
