Maximum margin Interval Trees

License: GPL v3 Build Status

Decision trees for interval regression

Drouin, A., Hocking, T.D. & Laviolette, F. (2017). Maximum Margin Interval Trees. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.

Python package installation and usage

The source code of the mmit Python package is located in the mmit sub-directory, and can be installed via the following command.

python setup.py install

The package includes a scikit-learn style class to learn Maximum Margin Interval Trees.

R package installation and usage

The source code of the mmit R package is located in the Rpackage sub-directory, and can be installed via the following R commands.

if(!require(devtools))install.package("devtools")
devtools::install_github("aldro61/mmit/Rpackage")

The package currently provides an interface for the dynamic programming algorithm used to train Maximum Margin Interval Trees. Support for learning trees in R will be implemented in the near future.