update to CRAN version 1.0.7

.ci/r_tests.sh

@@ -14,7 +14,9 @@ if [[ $OS_NAME == "macos-latest" ]]; then
   echo 'options(install.packages.check.source = "no")' >> .Rprofile
 else
   tlmgr --verify-repo=none update --self
-  tlmgr --verify-repo=none install ec
+  tlmgr --verify-repo=none install ec hyperref iftex infwarerr kvoptions pdftexcmds
+
+  echo "Sys.setenv(RETICULATE_PYTHON = '$CONDA_PREFIX/bin/python')" >> .Rprofile
 fi
 
 R_LIB_PATH=$HOME/R
@@ -26,6 +28,13 @@ echo "R_LIBS=$R_LIB_PATH" > .Renviron
 export _R_CHECK_CRAN_INCOMING_=0
 export _R_CHECK_CRAN_INCOMING_REMOTE_=0
 
+# increase the allowed time to run the examples
+export _R_CHECK_EXAMPLE_TIMING_THRESHOLD_=30
+
+# fix the 'unable to verify current time' NOTE
+# see: https://stackoverflow.com/a/63837547/8302386
+export _R_CHECK_SYSTEM_CLOCK_=0
+
 if [[ $OS_NAME == "macos-latest" ]]; then
   Rscript -e "install.packages('devtools', dependencies = TRUE, repos = 'https://cran.r-project.org')"
 fi

.ci/r_tests_windows.ps1

@@ -24,6 +24,13 @@ Remove-Item C:\rtools40 -Force -Recurse -ErrorAction Ignore
 $env:_R_CHECK_CRAN_INCOMING_ = 0
 $env:_R_CHECK_CRAN_INCOMING_REMOTE_ = 0
 
+# increase the allowed time to run the examples
+$env:_R_CHECK_EXAMPLE_TIMING_THRESHOLD_ = 30
+
+# fix the 'unable to verify current time' NOTE
+# see: https://stackoverflow.com/a/63837547/8302386
+$env:_R_CHECK_SYSTEM_CLOCK_ = 0
+
 $R_VER = "4.0.4"
 $ProgressPreference = "SilentlyContinue"  # progress bar bug extremely slows down download speed
 Invoke-WebRequest -Uri https://cloud.r-project.org/bin/windows/base/old/$R_VER/R-$R_VER-win.exe -OutFile R-win.exe -MaximumRetryCount 3

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: RGF
 Type: Package
 Title: Regularized Greedy Forest
-Version: 1.0.6.3
-Date: 2019-12-12
+Version: 1.0.7
+Date: 2021-03-17
 Authors@R: c( person("Lampros", "Mouselimis", email = "[email protected]", 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 <[email protected]>
 BugReports: https://github.com/RGF-team/rgf/issues
@@ -21,5 +21,5 @@ Suggests:
     rmarkdown
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.0.2
+RoxygenNote: 7.1.1
 VignetteBuilder: knitr

R-package/NEWS.md

@@ -2,6 +2,10 @@
 * We've modified the *package.R* file so that messages are printed to the console whenever Python or any of the required modules is not available. Moreover, for the R-package testing the conda environment parameter is adjusted ( this applies to the RGF-team Github repository and not to the CRAN package directly )
 * We've modified the *.appveyor.yml* file to return the *artifacts* in order to observe if tests ran successfully ( this applies to the RGF-team Github repository and not to the CRAN package directly )
 * We've added tests to increase the code coverage.
+* We've dropped support for Python 2.7
+* We've fixed also the invalid URL's in the README.md file
+* We removed the 'zzz.R' file which included the message: 'Beginning from version 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)' as after 4 version updates is no longer required
+* We've modified the '.onLoad' function in the 'package.R' file by removing 'reticulate::py_available(initialize = TRUE)' which forces reticulate to initialize Python and gives the following NOTE on CRAN 'Warning in system2(command = python, args = shQuote(config_script), stdout = TRUE,  : ..."' had status 2' (see: https://github.com/rstudio/reticulate/issues/730#issuecomment-594365528)
 
 
 ## RGF 1.0.6

R-package/R/FastRGF_Classifier.R

@@ -51,7 +51,7 @@
 #'                                     min_child_weight = 5.0, data_l2 = 2.0,
 #'                                     sparse_max_features = 80000,
 #'                                     sparse_min_occurences = 5,
-#'                                     calc_prob="sigmoid", n_jobs = 1,
+#'                                     calc_prob = "sigmoid", n_jobs = 1,
 #'                                     verbose = 0)}}{}
 #'
 #'  \item{\code{--------------}}{}
@@ -89,25 +89,29 @@
 #' #                                      min_child_weight = 5.0, data_l2 = 2.0,
 #' #                                      sparse_max_features = 80000,
 #' #                                      sparse_min_occurences = 5,
-#' #                                      calc_prob="sigmoid", n_jobs = 1,
+#' #                                      calc_prob = "sigmoid", n_jobs = 1,
 #' #                                      verbose = 0)
 #' @examples
 #'
-#' if (reticulate::py_available() && reticulate::py_module_available("rgf.sklearn")) {
+#' try({
+#'     if (reticulate::py_available(initialize = TRUE)) {
+#'         if (reticulate::py_module_available("rgf.sklearn")) {
 #'
-#'   library(RGF)
+#'             library(RGF)
 #'
-#'   set.seed(1)
-#'   x = matrix(runif(100000), nrow = 100, ncol = 1000)
+#'             set.seed(1)
+#'             x = matrix(runif(100000), nrow = 100, ncol = 1000)
 #'
-#'   y = sample(1:2, 100, replace = TRUE)
+#'             y = sample(1:2, 100, replace = TRUE)
 #'
-#'   fast_RGF_class = FastRGF_Classifier$new(max_leaf = 50)
+#'             fast_RGF_class = FastRGF_Classifier$new(max_leaf = 50)
 #'
-#'   fast_RGF_class$fit(x, y)
+#'             fast_RGF_class$fit(x, y)
 #'
-#'   preds = fast_RGF_class$predict_proba(x)
-#' }
+#'             preds = fast_RGF_class$predict_proba(x)
+#'         }
+#'     }
+#' }, silent = TRUE)
 
 FastRGF_Classifier <- R6::R6Class(
     "FastRGF_Classifier",

R-package/R/FastRGF_Regressor.R

@@ -83,21 +83,25 @@
 #' #                                      n_jobs = 1, verbose = 0)
 #' @examples
 #'
-#' if (reticulate::py_available() && reticulate::py_module_available("rgf.sklearn")) {
+#' try({
+#'     if (reticulate::py_available(initialize = TRUE)) {
+#'         if (reticulate::py_module_available("rgf.sklearn")) {
 #'
-#'   library(RGF)
+#'             library(RGF)
 #'
-#'   set.seed(1)
-#'   x = matrix(runif(100000), nrow = 100, ncol = 1000)
+#'             set.seed(1)
+#'             x = matrix(runif(100000), nrow = 100, ncol = 1000)
 #'
-#'   y = runif(100)
+#'             y = runif(100)
 #'
-#'   fast_RGF_regr = FastRGF_Regressor$new(max_leaf = 50)
+#'             fast_RGF_regr = FastRGF_Regressor$new(max_leaf = 50)
 #'
-#'   fast_RGF_regr$fit(x, y)
+#'             fast_RGF_regr$fit(x, y)
 #'
-#'   preds = fast_RGF_regr$predict(x)
-#' }
+#'             preds = fast_RGF_regr$predict(x)
+#'         }
+#'     }
+#' }, silent = TRUE)
 
 FastRGF_Regressor <- R6::R6Class(
     "FastRGF_Regressor",

R-package/R/RGF_Classifier.R

@@ -22,7 +22,7 @@
 #' @param memory_policy a character string. One of \emph{"conservative"} (it uses less memory at the expense of longer runtime. Try only when with default value it uses too much memory) or \emph{"generous"} (it runs faster using more memory by keeping the sorted orders of the features on memory for reuse). Memory using policy.
 #' @param verbose an integer. Controls the verbosity of the tree building process.
 #' @param init_model either NULL or a character string, optional (default=NULL). Filename of a previously saved model from which training should do warm-start. If model has been saved into multiple files, do not include numerical suffixes in the filename. \emph{NOTE:} Make sure you haven't forgotten to increase the value of the max_leaf parameter regarding to the specified warm-start model because warm-start model trees are counted in the overall number of trees.
-#' @param filename a character string specifying a valid path to a file where the fitted model should be saved 
+#' @param filename a character string specifying a valid path to a file where the fitted model should be saved
 #' @export
 #' @details
 #'
@@ -41,7 +41,7 @@
 #' the \emph{feature_importances} function returns the feature importances for the data.
 #'
 #' the \emph{dump_model} function currently prints information about the fitted model in the console
-#' 
+#'
 #' the \emph{save_model} function saves a model to a file from which training can do warm-start in the future.
 #'
 #' @references \emph{https://github.com/RGF-team/rgf/tree/master/python-package}, \emph{Rie Johnson and Tong Zhang, Learning Nonlinear Functions Using Regularized Greedy Forest}
@@ -93,7 +93,7 @@
 #'  \item{\code{dump_model()}}{}
 #'
 #'  \item{\code{--------------}}{}
-#'  
+#'
 #'  \item{\code{save_model(filename)}}{}
 #'
 #'  \item{\code{--------------}}{}
@@ -109,21 +109,25 @@
 #' #                                  verbose = 0, init_model = NULL)
 #' @examples
 #'
-#' if (reticulate::py_available() && reticulate::py_module_available("rgf.sklearn")) {
+#' try({
+#'     if (reticulate::py_available(initialize = TRUE)) {
+#'         if (reticulate::py_module_available("rgf.sklearn")) {
 #'
-#'   library(RGF)
+#'             library(RGF)
 #'
-#'   set.seed(1)
-#'   x = matrix(runif(1000), nrow = 100, ncol = 10)
+#'             set.seed(1)
+#'             x = matrix(runif(1000), nrow = 100, ncol = 10)
 #'
-#'   y = sample(1:2, 100, replace = TRUE)
+#'             y = sample(1:2, 100, replace = TRUE)
 #'
-#'   RGF_class = RGF_Classifier$new(max_leaf = 50)
+#'             RGF_class = RGF_Classifier$new(max_leaf = 50)
 #'
-#'   RGF_class$fit(x, y)
+#'             RGF_class$fit(x, y)
 #'
-#'   preds = RGF_class$predict_proba(x)
-#' }
+#'             preds = RGF_class$predict_proba(x)
+#'         }
+#'     }
+#' }, silent = TRUE)
 
 RGF_Classifier <- R6::R6Class(
     "RGF_Classifier",

R-package/R/RGF_Regressor.R

@@ -20,7 +20,7 @@
 #' @param memory_policy a character string. One of \emph{"conservative"} (it uses less memory at the expense of longer runtime. Try only when with default value it uses too much memory) or \emph{"generous"} (it runs faster using more memory by keeping the sorted orders of the features on memory for reuse). Memory using policy.
 #' @param verbose an integer. Controls the verbosity of the tree building process.
 #' @param init_model either NULL or a character string, optional (default=NULL). Filename of a previously saved model from which training should do warm-start. If model has been saved into multiple files, do not include numerical suffixes in the filename. \emph{NOTE:} Make sure you haven't forgotten to increase the value of the max_leaf parameter regarding to the specified warm-start model because warm-start model trees are counted in the overall number of trees.
-#' @param filename a character string specifying a valid path to a file where the fitted model should be saved 
+#' @param filename a character string specifying a valid path to a file where the fitted model should be saved
 #' @export
 #' @details
 #'
@@ -37,7 +37,7 @@
 #' the \emph{feature_importances} function returns the feature importances for the data.
 #'
 #' the \emph{dump_model} function currently prints information about the fitted model in the console
-#' 
+#'
 #' the \emph{save_model} function saves a model to a file from which training can do warm-start in the future.
 #'
 #' @references \emph{https://github.com/RGF-team/rgf/tree/master/python-package}, \emph{Rie Johnson and Tong Zhang, Learning Nonlinear Functions Using Regularized Greedy Forest}
@@ -99,21 +99,26 @@
 #' #                                  verbose = 0, init_model = NULL)
 #' @examples
 #'
-#' if (reticulate::py_available() && reticulate::py_module_available("rgf.sklearn")) {
+#' try({
+#'     if (reticulate::py_available(initialize = TRUE)) {
+#'         if (reticulate::py_module_available("rgf.sklearn")) {
 #'
-#'   library(RGF)
+#'             library(RGF)
 #'
-#'   set.seed(1)
-#'   x = matrix(runif(1000), nrow = 100, ncol = 10)
+#'             set.seed(1)
+#'             x = matrix(runif(1000), nrow = 100, ncol = 10)
 #'
-#'   y = runif(100)
+#'             y = runif(100)
 #'
-#'   RGF_regr = RGF_Regressor$new(max_leaf = 50)
+#'             RGF_regr = RGF_Regressor$new(max_leaf = 50)
 #'
-#'   RGF_regr$fit(x, y)
+#'             RGF_regr$fit(x, y)
 #'
-#'   preds = RGF_regr$predict(x)
-#' }
+#'             preds = RGF_regr$predict(x)
+#'         }
+#'     }
+#' }, silent = TRUE)
+
 RGF_Regressor <- R6::R6Class(
     "RGF_Regressor",
     inherit = Internal_class,

R-package/R/TO_scipy_sparse.R

@@ -13,45 +13,50 @@
 #' @references https://stat.ethz.ch/R-manual/R-devel/library/Matrix/html/dgCMatrix-class.html, https://stat.ethz.ch/R-manual/R-devel/library/Matrix/html/dgRMatrix-class.html, https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.csc_matrix.html#scipy.sparse.csc_matrix
 #' @examples
 #'
-#' if (reticulate::py_available() && reticulate::py_module_available("scipy")) {
+#' try({
+#'     if (reticulate::py_available(initialize = TRUE)) {
+#'         if (reticulate::py_module_available("scipy")) {
 #'
-#'   if (Sys.info()["sysname"] != 'Darwin') {
+#'             if (Sys.info()["sysname"] != 'Darwin') {
 #'
-#'     library(RGF)
+#'                 library(RGF)
 #'
 #'
-#'     # 'dgCMatrix' sparse matrix
-#'     #--------------------------
+#'                 # 'dgCMatrix' sparse matrix
+#'                 #--------------------------
 #'
-#'     data = c(1, 0, 2, 0, 0, 3, 4, 5, 6)
+#'                 data = c(1, 0, 2, 0, 0, 3, 4, 5, 6)
 #'
-#'     dgcM = Matrix::Matrix(
-#'         data = data
-#'         , nrow = 3
-#'         , ncol = 3
-#'         , byrow = TRUE
-#'         , sparse = TRUE
-#'     )
+#'                 dgcM = Matrix::Matrix(
+#'                     data = data
+#'                     , nrow = 3
+#'                     , ncol = 3
+#'                     , byrow = TRUE
+#'                     , sparse = TRUE
+#'                 )
 #'
-#'     print(dim(dgcM))
+#'                 print(dim(dgcM))
 #'
-#'     res = TO_scipy_sparse(dgcM)
+#'                 res = TO_scipy_sparse(dgcM)
 #'
-#'     print(res$shape)
+#'                 print(res$shape)
 #'
 #'
-#'     # 'dgRMatrix' sparse matrix
-#'     #--------------------------
+#'                 # 'dgRMatrix' sparse matrix
+#'                 #--------------------------
 #'
-#'     dgrM = as(dgcM, "RsparseMatrix")
+#'                 dgrM = as(dgcM, "RsparseMatrix")
 #'
-#'     print(dim(dgrM))
+#'                 print(dim(dgrM))
 #'
-#'     res_dgr = TO_scipy_sparse(dgrM)
+#'                 res_dgr = TO_scipy_sparse(dgrM)
 #'
-#'     print(res_dgr$shape)
-#'   }
-#' }
+#'                 print(res_dgr$shape)
+#'             }
+#'         }
+#'     }
+#' }, silent = TRUE)
+
 TO_scipy_sparse = function(R_sparse_matrix) {
 
     if (inherits(R_sparse_matrix, "dgCMatrix")) {

R-package/R/mat_2scipy_sparse.R

@@ -9,20 +9,24 @@
 #' @references https://docs.scipy.org/doc/scipy/reference/sparse.html
 #' @examples
 #'
-#' if (reticulate::py_available() && reticulate::py_module_available("scipy")) {
+#' try({
+#'     if (reticulate::py_available(initialize = TRUE)) {
+#'         if (reticulate::py_module_available("scipy")) {
 #'
-#'   library(RGF)
+#'             library(RGF)
 #'
-#'   set.seed(1)
+#'             set.seed(1)
 #'
-#'   x = matrix(runif(1000), nrow = 100, ncol = 10)
+#'             x = matrix(runif(1000), nrow = 100, ncol = 10)
 #'
-#'   res = mat_2scipy_sparse(x)
+#'             res = mat_2scipy_sparse(x)
 #'
-#'   print(dim(x))
+#'             print(dim(x))
 #'
-#'   print(res$shape)
-#' }
+#'             print(res$shape)
+#'         }
+#'     }
+#' }, silent = TRUE)
 
 mat_2scipy_sparse = function(x, format = 'sparse_row_matrix') {