Gym for predictive models
.. image:: https://img.shields.io/badge/run%20me-@everware-blue.svg?style=flat :target: https://everware.ysda.yandex.net/hub/oauth_login?repourl=https://github.com/yandexdataschool/modelgym :alt: run at everware
.. image:: https://readthedocs.org/projects/modelgym/badge/?version=latest :target: http://modelgym.readthedocs.io/en/latest/?badge=latest :alt: Documentation Status
.. please change make_modelgym_great_again -> master and fminkin -> yandexdataschool after merge .. image:: https://travis-ci.org/fminkin/modelgym.svg?branch=make_modelgym_great_again :target: https://travis-ci.org/fminkin/modelgym :alt: Build Status
Modelgym is a place (a library?) to get your predictive models as meaningful in a smooth and effortless manner. Modelgym provides the unified interface for
Usually it starts with a data sample that you can be evaluate with our Guru interface and maybe get a few hints on preprocessing it before starting the training. In the end of the trials you get a report of the model performance on both cross-validation and hold-out samples. So you can pick the top model along the best hyperparameters for your case.
Documentaion <http://modelgym.readthedocs.io/en/latest/index.html>_Installaion <http://modelgym.readthedocs.io/en/latest/install.html>_Example <http://modelgym.readthedocs.io/en/latest/train_example.html>_