XGBoost R Package for Scalable GBM

Resources

• XGBoost R Package Online Documentation
  • Check this out for detailed documents, examples and tutorials.

Installation

We are on CRAN now. For stable/pre-compiled(for Windows and OS X) version, please install from CRAN:

install.packages('xgboost')

You can also install from our weekly updated drat repo:

install.packages("xgboost", repos=c("http://dmlc.ml/drat/", getOption("repos")), type="source")

Important Due to the usage of submodule, install_github is no longer support to install the latest version of R package. For up-to-date version, please install from github.

Windows users will need to install RTools first. They also need to download MinGW-W64 using x86_64 architecture during installation.

Run the following command to add MinGW to PATH in Windows if not already added.

PATH %PATH%;C:\Program Files\mingw-w64\x86_64-5.3.0-posix-seh-rt_v4-rev0\mingw64\bin

To compile xgboost at the root of your storage, run the following bash script.

git clone --recursive https://github.com/dmlc/xgboost
cd xgboost
git submodule init
git submodule update
alias make='mingw32-make'
cd dmlc-core
make -j4
cd ../rabit
make lib/librabit_empty.a -j4
cd ..
cp make/mingw64.mk config.mk
make -j4

Run the following R script to install xgboost package from the root directory.

install.package('devtools') # if not installed
setwd('C:/xgboost/')
library(devtools)
install('R-package')

For more detailed installation instructions, please see here.

Examples

• Please visit walk through example.
• See also the example scripts for Kaggle Higgs Challenge, including speedtest script on this dataset and the one related to Otto challenge, including a RMarkdown documentation.