[R] maintenance Apr 2017 (#2237)

* [R] make sure things work for a single split model; fixes #2191

* [R] add option use_int_id to xgb.model.dt.tree

* [R] add example of exporting tree plot to a file

* [R] set save_period = NULL as default in xgboost() to be the same as in xgb.train; fixes #2182

* [R] it's a good practice after CRAN releases to bump up package version in dev

* [R] allow xgb.DMatrix construction from integer dense matrices

* [R] xgb.DMatrix: silent parameter; improve documentation

* [R] xgb.model.dt.tree code style changes

* [R] update NEWS with parameter changes

* [R] code safety & style; handle non-strict matrix and inherited classes of input and model; fixes #2242

* [R] change to x.y.z.p R-package versioning scheme and set version to 0.6.4.3

* [R] add an R package versioning section to the contributors guide

* [R] R-package/README.md: clean up the redundant old installation instructions, link the contributors guide

R-package/tests/testthat/test_basic.R

@@ -189,3 +189,36 @@ test_that("xgb.cv works", {
   expect_false(is.null(cv$callbacks))
   expect_false(is.null(cv$call))
 })
+
+test_that("train and predict with non-strict classes", {
+  # standard dense matrix input
+  train_dense <- as.matrix(train$data)
+  bst <- xgboost(data = train_dense, label = train$label, max_depth = 2,
+                 eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic", verbose = 0)
+  pr0 <- predict(bst, train_dense)
+  
+  # dense matrix-like input of non-matrix class
+  class(train_dense) <- 'shmatrix'
+  expect_true(is.matrix(train_dense))
+  expect_error(
+    bst <- xgboost(data = train_dense, label = train$label, max_depth = 2,
+                   eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic", verbose = 0)
+    , regexp = NA)
+  expect_error(pr <- predict(bst, train_dense), regexp = NA)
+  expect_equal(pr0, pr)
+  
+  # dense matrix-like input of non-matrix class with some inheritance
+  class(train_dense) <- c('pphmatrix','shmatrix')
+  expect_true(is.matrix(train_dense))
+  expect_error(
+    bst <- xgboost(data = train_dense, label = train$label, max_depth = 2,
+                   eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic", verbose = 0)
+    , regexp = NA)
+  expect_error(pr <- predict(bst, train_dense), regexp = NA)
+  expect_equal(pr0, pr)
+  
+  # when someone inhertis from xgb.Booster, it should still be possible to use it as xgb.Booster
+  class(bst) <- c('super.Booster', 'xgb.Booster')
+  expect_error(pr <- predict(bst, train_dense), regexp = NA)
+  expect_equal(pr0, pr)
+})