Merge pull request #506 from h2oai/cran-submission

CRAN submission minor fixes/updates

src/interface_r/DESCRIPTION

@@ -1,18 +1,20 @@
 Package: h2o4gpu
 Type: Package
-Title: R Interface to 'H2O4GPU'
+Title: Interface to 'H2O4GPU'
 Version: 0.2.0
 Authors@R: c(
-  person("Yuan", "Tang", role = c("aut", "cre"), email = "terry@h2o.ai"),
+  person("Yuan", "Tang", role = c("aut", "cre"),
+         email = "terrytangyuan@gmail.com",
+         comment = c(ORCID = "0000-0001-5243-233X")),
   person("Navdeep", "Gill", role = c("aut"), email = "navdeep@h2o.ai"),
   person("Erin", "LeDell", role = c("aut"), email = "erin@h2o.ai"),
   person("H2O.ai", role = c("cph", "fnd")))
-Description: R Interface to 'H2O4GPU' - A collection of 'GPU' solvers for machine learning algorithms.
+Description: Interface to 'H2O4GPU' <https://github.com/h2oai/h2o4gpu>, a collection of 'GPU' solvers for machine learning algorithms.
 License: Apache License 2.0
 URL: https://github.com/h2oai/h2o4gpu
 BugReports: https://github.com/h2oai/h2o4gpu/issues
 SystemRequirements: Python (>= 3.6) with header files and shared library;
-    h2o4gpu (https://github.com/h2oai/h2o4gpu)
+    H2O4GPU (https://github.com/h2oai/h2o4gpu)
 Encoding: UTF-8
 LazyData: true
 Depends:

src/interface_r/NEWS.md

@@ -1,3 +1,3 @@
-## h2o4gpu 0.0.1 (CRAN)
+## h2o4gpu 0.2.0 (CRAN)
 
 * Initial release.

src/interface_r/R/model.R

@@ -73,6 +73,18 @@ print.h2o4gpu_model <- function(x, ...) {
 #' @param ... Additional arguments (unused for now).
 #' 
 #' @export
+#' @examples 
+#' \dontrun{
+#' 
+#' library(h2o4gpu)
+#' 
+#' # Setup dataset
+#' x <- iris[1:4]
+#' y <- as.integer(iris$Species) - 1
+#' 
+#' # Train the classifier
+#' h2o4gpu.random_forest_classifier() %>% fit(x, y)
+#' }
 fit.h2o4gpu_model <- function(object, x, y = NULL, ...) {
   if (inherits(object$model, "h2o4gpu.solvers.elastic_net.ElasticNet") && object$params$family == "logistic"){
     if (length(unique(y)) > 2){
@@ -94,6 +106,23 @@ fit.h2o4gpu_model <- function(object, x, y = NULL, ...) {
 #' @param type One of "raw" or "prob", indicating the type of output: predicted values or probabilities
 #' @param ... Additional arguments (unused for now).
 #' @export
+#' @examples 
+#' \dontrun{
+#' 
+#' library(h2o4gpu)
+#' 
+#' # Setup dataset
+#' x <- iris[1:4]
+#' y <- as.integer(iris$Species) - 1
+#' 
+#' # Initialize and train the classifier
+#' model <- h2o4gpu.random_forest_classifier() %>% fit(x, y)
+#' 
+#' # Make predictions
+#' predictions <- model %>% predict(x)
+#' 
+#' }
+#' 
 predict.h2o4gpu_model <- function(object, x, type="raw", ...) {
   if (type == "raw") {
     preds <- object$model$predict(X = resolve_model_input(x), ...)
@@ -122,6 +151,27 @@ predict.h2o4gpu_model <- function(object, x, type="raw", ...) {
 #' be used in generating predictions.
 #' @param ... Additional arguments (unused for now).
 #' @export
+#' @examples 
+#' \dontrun{
+#' 
+#' library(h2o4gpu)
+#' 
+#' # Prepare data
+#' iris$Species <- as.integer(iris$Species) # convert to numeric data
+#' 
+#' # Randomly sample 80% of the rows for the training set
+#' set.seed(1)
+#' train_idx <- sample(1:nrow(iris), 0.8*nrow(iris)) 
+#' train <- iris[train_idx, ]
+#' test <- iris[-train_idx, ]
+#' 
+#' # Train a K-Means model
+#' model_km <- h2o4gpu.kmeans(n_clusters = 3L) %>% fit(train)
+#' 
+#' # Transform test data
+#' test_dist <- model_km %>% transform(test)
+#' 
+#' }
 transform.h2o4gpu_model <- function(object, x, ...) {
   object$model$transform(X = resolve_model_input(x), ...)
 }

src/interface_r/R/package.R

@@ -2,6 +2,23 @@
 #' 
 #' @docType package
 #' @name h2o4gpu
+#' 
+#' @examples 
+#' \dontrun{
+#' 
+#' library(h2o4gpu)
+#' 
+#' # Setup dataset
+#' x <- iris[1:4]
+#' y <- as.integer(iris$Species) - 1
+#' 
+#' # Initialize and train the classifier
+#' model <- h2o4gpu.random_forest_classifier() %>% fit(x, y)
+#' 
+#' # Make predictions
+#' predictions <- model %>% predict(x)
+#' 
+#' }
 NULL
 
 h2o4gpu <- NULL

src/interface_r/cran-comments.md

@@ -7,17 +7,10 @@
 
 0 errors | 0 warnings | 1 note
 
+New submission
+
 * This is a new release.
 
 ## Reverse dependencies
 
 This is a new release, so there are no reverse dependencies.
-
----
-
-* I have run R CMD check on the NUMBER downstream dependencies.
-  (Summary at ...). 
-
-* FAILURE SUMMARY
-
-* All revdep maintainers were notified of the release on RELEASE DATE.

src/interface_r/vignettes/getting_started.Rmd

@@ -4,7 +4,7 @@ author: "Navdeep Gill, Erin LeDell, Yuan Tang"
 date: "`r Sys.Date()`"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{Vignette Title}
+  %\VignetteIndexEntry{H2O4GPU: Machine Learning with GPUs in R}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -74,7 +74,7 @@ ce(actual = y, predicted = pred)
 
 The tree based models (Random Forest and GBM) are built on top of the very powerful [XGBoost](https://xgboost.readthedocs.io/en/latest/) library, and the Elastic Net GLM has been built upon the POGS solver.  [Proximal Graph Solver (POGS)](http://stanford.edu/%7Eboyd/papers/pogs.html) is a solver for convex optimization problems in graph form using Alternating Direction Method of Multipliers (ADMM).  We have found that this method is not as fast as we'd like it to be, so we are working on implementing an entirely new GLM from scratch (follow progress [here](https://github.com/h2oai/h2o4gpu/issues/356)).
 
-The **h2o4gpu** R package does not include a suite of internal model metrics functions, therefore we encourage users to use a third-party model metrics package of their choice.  For all the examples below, we will use the [Metrics](https://cran.r-project.org/web/packages/Metrics/index.html) R package.  This package has a large number of model metrics functions, all with a very simple, unified API.
+The **h2o4gpu** R package does not include a suite of internal model metrics functions, therefore we encourage users to use a third-party model metrics package of their choice.  For all the examples below, we will use the [Metrics](https://CRAN.R-project.org/package=Metrics) R package.  This package has a large number of model metrics functions, all with a very simple, unified API.
 
 ### Binary Classification