REP is environment for conducting data-driven research in a consistent and reproducible way. It has a unified classifiers wrapper for variety of implementations like TMVA, Sklearn, XGBoost, uBoost. It can train classifiers parallely on a cluster. It support of interactive plots.

It includes:

• Data provides operations with data
• Estimators (classification and regression) is sklearn-like wrappers for variety of machine learning libraries (Sklearn, uBoost, XGBoost, TMVA). These can be used as base estimators in sklearn.
• Meta Machine Learning contains factory (the set of estimators), grid search, folding algorithm. Also parallel execution on a cluster is supported
• Report for models contains helpful classes to get model result information on any dataset
• Plotting is wrapper for different plotting libraries including interactive plots (matplotlib, bokeh, tmva, plotly)
• Utilities contains additional functions

Information

• Website: http://yandex.github.io/rep/
• GitHub: https://github.com/yandex/rep
• Documentation: http://yandex.github.io/rep/
• Getting started: http://nbviewer.ipython.org/github/yandex/rep/tree/master/howto/