REP is environment for conducting data-driven research in a consistent and reproducible way.
Main REP features include:
- unified classifiers wrapper for variety of implementations (TMVA, Sklearn, XGBoost, Uboost)
- parallel training of classifiers on cluster
- classification/regression reports with plots
- support of interactive plots
- grid-search with parallelized execution on a cluster
- git, versioning of research
- computation of different classification metrics
We provide the docker container with REP and all it's dependencies
https://github.com/yandex/rep/wiki/Running-REP-using-Docker/
However, if you want to install REP on your machine, follow this manual:
https://github.com/yandex/rep/wiki/Installing-manually
and https://github.com/yandex/rep/wiki/Running-manually
To get started with the framework, look at the notebooks in /howto/
Notebooks in repository can be viewed (not executed) online at nbviewer: http://nbviewer.ipython.org/github/yandex/rep/tree/master/howto/
There are basic introductory notebooks (about python, IPython) and more advanced ones (about the REP itself)