do not run tests on cran and fix broken URLs

DESCRIPTION

@@ -254,6 +254,7 @@ Suggests:
     sda,
     sf,
     smoof,
+    snow,
     sparseLDA,
     stepPlr,
     survAUC,

R/makeLearner.R

@@ -72,7 +72,7 @@
 #' `ntree = se.ntree`, the latter of which controls the number of trees in the
 #' individual random forests which are bootstrapped. The "noisy bootstrap" is
 #' executed when `se.ntree < ntree` which is less computationally expensive. A
-#' Monte-Carlo bias correction may make the latter option prefarable in many
+#' Monte-Carlo bias correction may make the latter option preferable in many
 #' cases. Defaults are `se.boot = 50` and `se.ntree = 100`.
 #'
 #' \item If `se.method = "sd"`, the default, the standard deviation of the
@@ -105,20 +105,21 @@
 #' the target feature in training data, respectively.
 #'
 #' The default method is \dQuote{mean} which corresponds to the ZeroR algorithm
-#' from WEKA, see <https://weka.wikispaces.com/ZeroR>.
+#' from WEKA.
 #'
 #' @section classif.featureless:
 #'
 #' Method \dQuote{majority} predicts always the majority class for each new
-#' observation. In the case of ties, one randomly sampled, constant class is predicted
-#' for all observations in the test set.
-#' This method is used as the default. It is very similar to the ZeroR classifier
-#' from WEKA (see <https://weka.wikispaces.com/ZeroR>). The only difference is
+#' observation. In the case of ties, one randomly sampled, constant class is
+#' predicted for all observations in the test set.
+#' This method is used as the default. It is very similar to the ZeroR
+#' classifier from WEKA. The only difference is
 #' that ZeroR always predicts the first class of the tied class values instead
 #' of sampling them randomly.
 #'
-#' Method \dQuote{sample-prior} always samples a random class for each individual test
-#' observation according to the prior probabilities observed in the training data.
+#' Method \dQuote{sample-prior} always samples a random class for each
+#' individual test observation according to the prior probabilities observed in
+#' the training data.
 #'
 #' If you opt to predict probabilities, the class probabilities always
 #' correspond to the prior probabilities observed in the training data.

R/measures.R

@@ -1375,7 +1375,7 @@ cindex = makeMeasure(
 #' @references
 #' H. Uno et al.
 #' *On the C-statistics for Evaluating Overall Adequacy of Risk Prediction Procedures with Censored Survival Data*
-#' Statistics in medicine. 2011;30(10):1105-1117. <https://doi.org/10.1002/sim.4154>.
+#' Statistics in medicine. 2011;30(10):1105-1117. \doi{10.1002/sim.4154}.
 cindex.uno = makeMeasure(
   id = "cindex.uno", minimize = FALSE, best = 1, worst = 0,
   properties = c("surv", "req.pred", "req.truth", "req.model", "req.task"),

README.md

@@ -1,6 +1,6 @@
 # mlr <img src="man/figures/logo.png" align="right" />
 
-Package website: [release](https://mlr.mlr-org.com/) | [dev](https://mlr.mlr-org.com/dev)
+Package website: [release](https://mlr.mlr-org.com/) | [dev](https://mlr.mlr-org.com/dev/)
 
 Machine learning in R.
 
@@ -9,9 +9,9 @@ Machine learning in R.
 [![tic](https://github.com/mlr-org/mlr/workflows/tic/badge.svg?branch=main)](https://github.com/mlr-org/mlr/actions)
 [![CRAN_Status_Badge](https://www.r-pkg.org/badges/version-ago/mlr)](https://cran.r-project.org/package=mlr)
 [![cran checks](https://cranchecks.info/badges/worst/mlr)](https://cran.r-project.org/web/checks/check_results_mlr.html)
-[![CRAN Downloads](https://cranlogs.r-pkg.org/badges/mlr)](https://cran.rstudio.com/web/packages/mlr/index.html)
+[![CRAN Downloads](https://cranlogs.r-pkg.org/badges/mlr)](https://cran.r-project.org/package=mlr)
 [![StackOverflow](https://img.shields.io/badge/stackoverflow-mlr-blue.svg)](https://stackoverflow.com/questions/tagged/mlr)
-[![lifecycle](https://img.shields.io/badge/lifecycle-retired-orange.svg)](https://www.tidyverse.org/lifecycle/#retired)
+[![lifecycle](https://img.shields.io/badge/lifecycle-retired-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html)
 [![codecov](https://codecov.io/gh/mlr-org/mlr/branch/main/graph/badge.svg)](https://codecov.io/gh/mlr-org/mlr)
 
 <!-- badges: end -->
@@ -50,7 +50,7 @@ remotes::install_github("mlr-org/mlr")
 
 ## Citing {mlr} in publications
 
-Please cite our [JMLR paper](http://jmlr.org/papers/v17/15-066.html) [[bibtex](http://www.jmlr.org/papers/v17/15-066.bib)].
+Please cite our [JMLR paper](https://jmlr.org/papers/v17/15-066.html) [[bibtex](https://www.jmlr.org/papers/v17/15-066.bib)].
 
 Some parts of the package were created as part of other publications.
 If you use these parts, please cite the relevant work appropriately.

tests/testthat.R

@@ -1,2 +1,5 @@
 library(testthat)
-test_check("mlr")
+if (identical(Sys.getenv("NOT_CRAN"), "true")) {
+  set.seed(getOption("mlr.debug.seed"))
+  test_check("mlr")
+}

tests/testthat/test_parallel_mpi.R

@@ -2,6 +2,8 @@
 test_that("parallel resampling", {
   skip_on_os("mac")
   skip_on_ci()
+  skip_on_cran()
+
   doit = function(mode, level) {
     lrn = makeLearner("classif.rpart")
     rdesc = makeResampleDesc("CV", iters = 2L)
@@ -20,6 +22,8 @@ test_that("parallel resampling", {
 test_that("parallel tuning", {
   skip_on_os("mac")
   skip_on_ci()
+  skip_on_cran()
+
   doit = function(mode, level) {
     lrn = makeLearner("classif.rpart")
     rdesc = makeResampleDesc("CV", iters = 2L)
@@ -40,6 +44,7 @@ test_that("parallel tuning", {
 test_that("parallel featsel", {
   skip_on_os("mac")
   skip_on_ci()
+  skip_on_cran()
   doit = function(mode, level) {
     lrn = makeLearner("classif.rpart")
     rdesc = makeResampleDesc("CV", iters = 2L)
@@ -59,6 +64,8 @@ test_that("parallel featsel", {
 test_that("parallel exporting of options works", {
   skip_on_os("mac")
   skip_on_ci()
+  skip_on_cran()
+
   doit = function(mode, level) {
 
     data = iris
@@ -82,6 +89,8 @@ test_that("parallel exporting of options works", {
 test_that("parallel partial dependence", {
   skip_on_os("mac")
   skip_on_ci()
+  skip_on_cran()
+
   doit = function(mode) {
     lrn = makeLearner("regr.rpart")
     fit = train(lrn, regr.task)
@@ -98,6 +107,8 @@ test_that("parallel partial dependence", {
 test_that("parallel ensembles", {
   skip_on_os("mac")
   skip_on_ci()
+  skip_on_cran()
+
   doit = function(mode, level) {
 
     on.exit(parallelStop())

tests/testthat/test_surv_measures.R

@@ -34,6 +34,8 @@ test_that("survival measures do not do stupid things", {
 })
 
 test_that("setting measure pars works", {
+  requirePackagesOrSkip("survAUC", default.method = "load")
+
   mod = train("surv.rpart", wpbc.task)
   pred = predict(mod, wpbc.task)
 
@@ -58,6 +60,8 @@ test_that("setting measure pars works", {
 
 test_that("hand constructed tests", {
   requirePackagesOrSkip("Hmisc", default.method = "load")
+  requirePackagesOrSkip("survAUC", default.method = "load")
+
   n = 100
   time = sort(rexp(n, 0.1)) + 1
   data = data.frame(time = time, status = 1, x1 = order(time))
@@ -76,8 +80,10 @@ test_that("hand constructed tests", {
   expect_equal(unname(perf), c(1, 1, 0.99))
 })
 
-
 test_that("ibrier measure works with surv tasks", {
+  requirePackagesOrSkip("survAUC", default.method = "load")
+  requirePackagesOrSkip("pec", default.method = "load")
+
   set.seed(getOption("mlr.debug.seed"))
   rin = makeResampleInstance(makeResampleDesc("CV", iters = 2), task = wpbc.task)
   lrn = makeLearner("surv.coxph", x = TRUE)

tests/testthat/test_tuneParams.R

@@ -14,6 +14,8 @@ test_that("names for minimize are set correctly", {
 })
 
 test_that("tuneParams with resample.fun", {
+  cl =
+
   lrn = makeLearner("classif.rpart")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(
@@ -63,6 +65,7 @@ test_that("tuneParams with resample.fun", {
 })
 
 test_that("tuneParams output works as documented", {
+  cl =
   lrn = makeLearner("classif.ksvm")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(
@@ -96,6 +99,8 @@ test_that("tuneParams output works as documented", {
 })
 
 test_that("tuneParams output works as documented", {
+  cl =
+
   lrn = makeLearner("classif.ksvm")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(
@@ -130,6 +135,8 @@ test_that("tuneParams output works as documented", {
 
 test_that("tuning with a fixed ensemble methods and varying base methods works", {
 
+  cl =
+
   # TODO: make it possible to choose arbitrary number of base.methods -> cannot
   # tune an argument of a param. We need to make makeDiscreteVectorParam more
   # flexible to allow more than one ensemble.method
@@ -161,6 +168,8 @@ test_that("tuning with a fixed ensemble methods and varying base methods works",
 
 test_that("tuning with a fixed ensemble methods and varying base methods works", {
 
+  cl =
+
   # TODO: choose arbitrary number of base.methods -> cannot tune an argument of
   # a param. We need to make makeDiscreteVectorParam more flexible. allow more
   # than one ensemble.method

tests/testthat/test_tune_tuneMBO.R

@@ -1,5 +1,6 @@
 
 test_that("tuneMBO", {
+  requirePackagesOrSkip("rgenoud", default.method = "load")
   n.des = 8
   n.iter = 2
   res = makeResampleDesc("Holdout")

tests/testthat/test_tune_tuneParamsMultiCrit.R

@@ -1,5 +1,7 @@
 
 test_that("tuneParamsMultiCrit", {
+  requirePackagesOrSkip("emoa", default.method = "load")
+
   lrn = makeLearner("classif.rpart")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(
@@ -75,6 +77,9 @@ test_that("tuneParamsMultiCrit", {
 
 
 test_that("tuneParamsMultiCrit works with low number of evals and dependencies", {
+
+  requirePackagesOrSkip("emoa", default.method = "load")
+
   # we had a bug here triggered thru code in PH
   ps = makeParamSet(
     makeNumericParam("C", lower = -12, upper = 12, trafo = function(x) 2^x),
@@ -92,6 +97,8 @@ test_that("tuneParamsMultiCrit works with low number of evals and dependencies",
 
 # FIXME: I am not sure how we can check wich value is imputed for the optimizer?
 test_that("y imputing works", {
+  requirePackagesOrSkip("emoa", default.method = "load")
+
   configureMlr(on.learner.error = "quiet")
   lrn = makeLearner("classif.__mlrmocklearners__2")
   rdesc = makeResampleDesc("Holdout")
@@ -110,6 +117,8 @@ test_that("y imputing works", {
 })
 
 test_that("tuneParamsMultiCrit with budget", {
+  requirePackagesOrSkip("emoa", default.method = "load")
+
   lrn = makeLearner("classif.rpart")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(
@@ -162,6 +171,7 @@ test_that("tuneParamsMultiCrit with budget", {
 })
 
 test_that("plotTuneMultiCritResult works with pretty.names", {
+  requirePackagesOrSkip("emoa", default.method = "load")
   lrn = makeLearner("classif.rpart")
   ps = makeParamSet(
     makeDiscreteParam("minsplit", values = c(5, 10))
@@ -174,6 +184,7 @@ test_that("plotTuneMultiCritResult works with pretty.names", {
 })
 
 test_that("tuneParamsMultiCrit with resample.fun", {
+  requirePackagesOrSkip("emoa", default.method = "load")
   lrn = makeLearner("classif.rpart")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(
@@ -210,6 +221,8 @@ test_that("tuneParamsMultiCrit with resample.fun", {
 })
 
 test_that("check n.objectives for MBO multi crit", {
+  requirePackagesOrSkip("emoa", default.method = "load")
+
   lrn = makeLearner("classif.rpart")
   rdesc = makeResampleDesc("Holdout")
   ps = makeParamSet(

tests/testthat/test_tune_tuneThreshold.R

@@ -1,5 +1,6 @@
 
 test_that("tuneThreshold", {
+  requirePackagesOrSkip("lhs", default.method = "load")
 
   # binary classes, 1 th
   lrn = makeLearner("classif.lda", predict.type = "prob")