R-package (#208)

* added the RGF R-package

* removed empty dir

* added submodule

* unsubmodule

* moved files in appropriate folder

* fixed DESCRIPTION FILE

* Revert "fixed DESCRIPTION FILE"

This reverts commit 561e9e7.

* I updated the DESCRIPTION file

* I updated the R package files as suggested

* I updated the R package files as suggested

* I updated the R package suggested

* I updated the R package as suggested

* I updated the R package as suggested

* I updated the R package as suggested

* I updated the R package as suggested

* I updated the R package as suggested

* I updated the R package as suggested

* I updated the R package as suggested

* I updated the R package as suggested

* added R-package test at Travis

* fixed R test at Travis

* fixed conflicts in library versions

* updated the DESCRIPTION and NEWS files

* updated the R-package files

* updated the R-package files

* fixed arxiv.org certificate error

* replaced problem link to r-pkg.org with link to package official page at cran

* fixed MinGW-w64 certificates problem

* update the R-package files

.travis.yml

@@ -8,13 +8,22 @@ os:
   - osx
 
 env:
-  - PYTHON_VERSION=2.7
-  - PYTHON_VERSION=3.4
-  - PYTHON_VERSION=3.5
-  - PYTHON_VERSION=3.6
+  global:
+    - R_LIB_PATH=~/Rlib
+  matrix:
+    - PYTHON_VERSION=2.7
+    - PYTHON_VERSION=3.4
+    - PYTHON_VERSION=3.5
+    - PYTHON_VERSION=3.6
+    - PYTHON_VERSION=3.6 TASK=R_PACKAGE
+
+matrix:
+  exclude:
+    - os: osx
+      env: PYTHON_VERSION=3.6 TASK=R_PACKAGE
 
 before_install:
-  - if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
+  - if [[ $TRAVIS_OS_NAME == "osx" ]]; then
       sudo softwareupdate -i "Command Line Tools (macOS High Sierra version 10.13) for Xcode-9.3";
       rm '/usr/local/include/c++';
       brew install gcc;
@@ -39,21 +48,25 @@ before_install:
   - RGF_VER=$(head -n 1 python-package/rgf/VERSION)
 
 install:
-  - cd python-package
+  - cd $TRAVIS_BUILD_DIR/python-package
   - python setup.py sdist --formats gztar
   - pip install dist/rgf_python-$RGF_VER.tar.gz -v
 
 script:
   - pytest tests/ -v
+  - if [[ $TASK == "R_PACKAGE" ]]; then
+      bash $TRAVIS_BUILD_DIR/R-package/.R.travis.sh;
+    fi
 
 before_deploy:
+  - cd $TRAVIS_BUILD_DIR/python-package
   - if [[ $TRAVIS_OS_NAME == "osx" ]]; then
       python setup.py bdist_wheel --plat-name=any --universal;
       mv dist/rgf_python-${RGF_VER}-py2.py3-none-any.whl dist/rgf_python-${RGF_VER}-py2.py3-none-macosx_10_6_x86_64.macosx_10_7_x86_64.macosx_10_8_x86_64.macosx_10_9_x86_64.macosx_10_10_x86_64.macosx_10_11_x86_64.macosx_10_12_x86_64.macosx_10_13_x86_64.whl;
     else
       python setup.py bdist_wheel --plat-name=manylinux1_x86_64 --universal;
       python setup.py bdist_wheel --plat-name=manylinux1_i686 --universal;
-      cd dist;
+      cd $TRAVIS_BUILD_DIR/python-package/dist;
       zip -d rgf_python-${RGF_VER}-py2.py3-none-manylinux1_i686.whl rgf/rgf rgf/forest_train rgf/forest_predict;
       mkdir rgf;
       wget https://github.com/RGF-team/rgf/releases/download/3.2.0/rgf -O rgf/rgf;
@@ -66,6 +79,10 @@ before_deploy:
 notifications:
   email: false
 
+cache:
+  directories:
+    - $R_LIB_PATH
+
 deploy:
   file_glob: true
   file: python-package/dist/*.whl

R-package/.R.travis.sh

@@ -0,0 +1,60 @@
+mkdir -p $R_LIB_PATH
+cd $TRAVIS_BUILD_DIR/R-package
+echo "R_LIBS=$R_LIB_PATH" > .Renviron
+echo 'options(repos = "https://cran.rstudio.com")' > .Rprofile
+
+export PATH="$R_LIB_PATH/R/bin:$PATH"
+
+sudo apt-get install gfortran-5
+sudo update-alternatives --install /usr/bin/gfortran gfortran /usr/bin/gfortran-5 10
+# use system-wide libraries (fix error "symbol _ZTINSt8ios_base7failureB5cxx11E, version GLIBCXX_3.4.21 not defined in file libstdc++.so.6 with link time reference")
+conda remove --force libgfortran-ng libgcc-ng libstdcxx-ng
+
+# install packages to build and check documentation
+conda install --no-deps pandoc
+sudo apt-get install texlive-latex-recommended texlive-fonts-recommended texlive-fonts-extra qpdf
+
+# fix "libcurl error code 60: server certificate verification failed. CAfile: /etc/ssl/certs/ca-certificates.crt CRLfile: none"
+echo -n | openssl s_client -connect arxiv.org:443 2>/dev/null | sed -ne '/-BEGIN CERTIFICATE-/,/-END CERTIFICATE-/p' | sudo tee -a /etc/ssl/certs/ca-certificates.crt
+
+if ! command -v R &> /dev/null; then
+    R_VER=3.5.1
+    cd $TRAVIS_BUILD_DIR
+    wget https://cran.r-project.org/src/base/R-3/R-$R_VER.tar.gz
+    tar -xzf R-$R_VER.tar.gz
+    R-$R_VER/configure --enable-R-shlib --prefix=$R_LIB_PATH/R
+    make
+    make install
+    cd $TRAVIS_BUILD_DIR/R-package
+fi
+
+Rscript -e 'if(!"devtools" %in% rownames(installed.packages())) { install.packages("devtools", dependencies = TRUE) }'
+Rscript -e 'if(!"roxygen2" %in% rownames(installed.packages())) { install.packages("roxygen2", dependencies = TRUE) }'
+Rscript -e 'if(!"testthat" %in% rownames(installed.packages())) { install.packages("testthat", dependencies = TRUE) }'
+Rscript -e 'if(!"knitr" %in% rownames(installed.packages())) { install.packages("knitr", dependencies = TRUE) }'
+Rscript -e 'if(!"covr" %in% rownames(installed.packages())) { install.packages("covr", dependencies = TRUE) }'
+Rscript -e 'if(!"rmarkdown" %in% rownames(installed.packages())) { install.packages("rmarkdown", dependencies = TRUE) }'
+Rscript -e 'if(!"reticulate" %in% rownames(installed.packages())) { install.packages("reticulate", dependencies = TRUE) }'
+Rscript -e 'if(!"R6" %in% rownames(installed.packages())) { install.packages("R6", dependencies = TRUE) }'
+Rscript -e 'if(!"Matrix" %in% rownames(installed.packages())) { install.packages("Matrix", dependencies = TRUE) }'
+
+Rscript -e 'update.packages(ask = FALSE, instlib = Sys.getenv("R_LIB_PATH"))'
+
+Rscript -e 'devtools::install_deps(pkg = ".", dependencies = TRUE)'
+
+R CMD build . || exit -1
+
+PKG_FILE_NAME=$(ls -1t *.tar.gz | head -n 1)
+PKG_NAME="${PKG_FILE_NAME%%_*}"
+LOG_FILE_NAME="$PKG_NAME.Rcheck/00check.log"
+
+R CMD check "${PKG_FILE_NAME}" --as-cran || exit -1
+if grep -q -R "WARNING" "$LOG_FILE_NAME"; then
+    echo "WARNINGS have been found in the build log!"
+    exit -1
+#elif grep -q -R "NOTE" "$LOG_FILE_NAME"; then
+#    echo "NOTES have been found in the build log!"
+#    exit -1
+fi
+
+Rscript -e 'covr::codecov(quiet = FALSE)'

R-package/.Rbuildignore

@@ -0,0 +1 @@
+^\.R\.travis\.sh$

R-package/.gitignore

@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata

R-package/DESCRIPTION

@@ -0,0 +1,25 @@
+Package: RGF
+Type: Package
+Title: Regularized Greedy Forest
+Version: 1.0.5
+Date: 2018-08-15
+Authors@R: c( person("Lampros", "Mouselimis", email = "mouselimislampros@gmail.com", role = c("aut", "cre")), person("Ryosuke", "Fukatani", role = "cph", comment = "Author of the python wrapper of the 'Regularized Greedy Forest' machine learning algorithm"), person("Nikita", "Titov", role = "cph", comment = "Author of the python wrapper of the 'Regularized Greedy Forest' machine learning algorithm"), person("Tong", "Zhang", role = "cph", comment = "Author of the 'Regularized Greedy Forest' and of the Multi-core implementation of Regularized Greedy Forest machine learning algorithm"), person("Rie", "Johnson", role = "cph", comment = "Author of the 'Regularized Greedy Forest' machine learning algorithm") )
+Maintainer: Lampros Mouselimis <mouselimislampros@gmail.com>
+BugReports: https://github.com/RGF-team/rgf/issues
+URL: https://github.com/RGF-team/rgf/tree/master/R-package
+Description: Regularized Greedy Forest wrapper of the 'Regularized Greedy Forest' <https://github.com/RGF-team/rgf/tree/master/python-package> 'python' package, which also includes a Multi-core implementation (FastRGF) <https://github.com/RGF-team/rgf/tree/master/FastRGF>.
+License: MIT + file LICENSE
+SystemRequirements: Python (2.7 or >= 3.4), rgf_python, scikit-learn (>= 0.18.0), scipy, numpy. Detailed installation instructions for each operating system can be found in the README file.
+Depends:
+    R(>= 3.2.3)
+Imports:
+    reticulate, R6, Matrix
+Suggests:
+    testthat,
+    covr,
+    knitr,
+    rmarkdown
+Encoding: UTF-8
+LazyData: true
+RoxygenNote: 6.0.1
+VignetteBuilder: knitr

R-package/LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2018
+COPYRIGHT HOLDER: Mouselimis Lampros <mouselimislampros@gmail.com>

R-package/LICENSE.note

@@ -0,0 +1,24 @@
+#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#       Regularized Greedy Forest (RGF)
+#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+
+See file COPYING: https://github.com/RGF-team/rgf/blob/master/RGF/COPYING
+
+
+
+#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#     Fast Regularized Greedy Forest (FastRGF)
+#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+
+See file LICENSE: https://github.com/RGF-team/rgf/blob/master/FastRGF/LICENSE
+
+
+
+#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#     Python wrapper of RGF and FastRGF     
+#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+
+See file LICENSE: https://github.com/RGF-team/rgf/blob/master/python-package/LICENSE

R-package/NAMESPACE

@@ -0,0 +1,10 @@
+export(RGF_cleanup_temp_files)
+export(mat_2scipy_sparse)
+export(TO_scipy_sparse)
+export(RGF_Regressor)
+export(RGF_Classifier)
+export(FastRGF_Regressor)
+export(FastRGF_Classifier)
+import(reticulate)
+importFrom(R6,R6Class)
+importFrom(Matrix,Matrix)

R-package/NEWS.md

@@ -0,0 +1,33 @@
+## RGF 1.0.5
+
+The RGF R package was integrated in the home repository for the Regularized Greedy Forest (RGF) library (https://github.com/RGF-team).
+
+
+## RGF 1.0.4
+
+* We modified the license from GPL-3 to MIT to go in accordance with the new structure of the *rgf_python* package. The package includes two files : *LICENSE* (for the RGF R package) and *LICENSE.note* (for the *RGF*, *FastRGF* and *rgf_python* packages).
+* We added the following new features of RGF estimators : *feature_importances_* and *dump_model()*
+* We modified the README.md file and especially the installation instructions for all operating systems (Linux, Mac OS X, Windows)
+* We created an R6 class (*Internal_class*) for all secondary functions which are used in RGF and FastRGF
+
+
+## RGF 1.0.3
+
+* The *dgCMatrix_2scipy_sparse* function was renamed to *TO_scipy_sparse* and now accepts either a *dgCMatrix* or a *dgRMatrix* as input. The appropriate format for the RGF package in case of sparse matrices is the *dgCMatrix* format (*scipy.sparse.csc_matrix*)
+* We added an onload.R file to inform the users about the previous change
+* Due to the previous changes we modified the Vignette and the tests too
+
+
+## RGF 1.0.2
+
+We commented the example(s) and test(s) related to the *dgCMatrix_2scipy_sparse* function [ *if (Sys.info()["sysname"] != 'Darwin')* ], because the *scipy-sparse* library on CRAN is not upgraded and the older version includes a bug (*TypeError : could not interpret data type*). This leads to an error on *Mac OS X* ( *reference* : https://github.com/scipy/scipy/issues/5353 ).
+
+
+## RGF 1.0.1
+
+We added links to the GitHub repository (master repository, issues).
+
+
+## RGF 1.0.0
+
+Initial version.

R-package/R/package.R

@@ -0,0 +1,28 @@
+#-------------------------
+# Load the python-modules
+#-------------------------
+
+
+RGF_mod <- NULL; RGF_utils <- NULL; SCP <- NULL;
+
+
+.onLoad <- function(libname, pkgname) {
+
+  if (reticulate::py_available(initialize = TRUE)) {
+
+    if (reticulate::py_module_available("rgf.sklearn")) {
+
+      RGF_mod <<- reticulate::import("rgf.sklearn", delay_load = TRUE)
+    }
+
+    if (reticulate::py_module_available("rgf.utils")) {
+
+      RGF_utils <<- reticulate::import("rgf.utils", delay_load = TRUE)
+    }
+
+    if (reticulate::py_module_available("scipy")) {
+
+      SCP <<- reticulate::import("scipy", delay_load = TRUE, convert = FALSE)
+    }
+  }
+}