feat: bbotk async compatibility (#146)

* draft * fix: add start time * refactor: remove rush debug * fix: add callback * fix: transformation * fix: xdomain * refactor: kill workers * feat: cache archive * chore: debug * chore: import rush * feat: add logging * refactor: use optimize_decentralized() * feat: add exponential decay * feat: add min-max imputation * feat: add n_worker parameter * draft * draft * refactor: remove stage * fix: description * feat: add n_worker argument * fix: imports * fix: tests * ci: add redis * drop ADBO for now * do not include partial update changes made to SurrogateLearner * .. --------- Co-authored-by: be-marc <[email protected]>
mlr-org · Jun 21, 2024 · 0cba07b · 0cba07b
1 parent cc45e7b
commit 0cba07b
Show file tree

Hide file tree

Showing 61 changed files with 179 additions and 163 deletions.
diff --git a/.github/workflows/dev-cmd-check.yml b/.github/workflows/dev-cmd-check.yml
@@ -38,6 +38,10 @@ jobs:
         with:
           r-version: ${{ matrix.config.r }}
 
+      - uses: supercharge/[email protected]
+        with:
+          redis-version: 7
+
       - uses: r-lib/actions/setup-r-dependencies@v2
         with:
           extra-packages: any::rcmdcheck
@@ -48,3 +52,6 @@ jobs:
         shell: Rscript {0}
 
       - uses: r-lib/actions/check-r-package@v2
+        with:
+          args: 'c("--no-manual")' # "--as-cran" prevents to start external processes
+
diff --git a/.github/workflows/r-cmd-check.yml b/.github/workflows/r-cmd-check.yml
@@ -36,9 +36,15 @@ jobs:
         with:
           r-version: ${{ matrix.config.r }}
 
+      - uses: supercharge/[email protected]
+        with:
+          redis-version: 7
+
       - uses: r-lib/actions/setup-r-dependencies@v2
         with:
           extra-packages: any::rcmdcheck
           needs: check
 
       - uses: r-lib/actions/check-r-package@v2
+        with:
+          args: 'c("--no-manual")' # "--as-cran" prevents to start external processes
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -41,13 +41,13 @@ BugReports: https://github.com/mlr-org/mlr3mbo/issues
 Depends:
     R (>= 3.1.0)
 Imports:
-    bbotk (>= 0.5.4),
+    bbotk (>= 0.8.0.9000),
     checkmate (>= 2.0.0),
     data.table,
     lgr (>= 0.3.4),
     mlr3 (>= 0.14.0),
     mlr3misc (>= 0.11.0),
-    mlr3tuning (>= 0.14.0),
+    mlr3tuning (>= 0.20.0.9000),
     paradox (>= 0.10.0),
     spacefillr,
     R6 (>= 2.4.1)
@@ -65,7 +65,10 @@ Suggests:
     rmarkdown,
     rpart,
     stringi,
-    testthat (>= 3.0.0),
+    testthat (>= 3.0.0)
+Remotes:
+    mlr-org/bbotk,
+    mlr-org/mlr3tuning,
 ByteCompile: no
 Encoding: UTF-8
 Config/testthat/edition: 3

diff --git a/R/AcqFunction.R b/R/AcqFunction.R
@@ -176,7 +176,7 @@ AcqFunction = R6Class("AcqFunction",
           stopf("Acquisition function '%s' requires the surrogate to have `\"se\"` as `$predict_type`.", format(self))
         }
         private$.surrogate = rhs
-        private$.archive = assert_r6(rhs$archive, classes = "Archive")
+        private$.archive = assert_archive(rhs$archive)
         codomain = generate_acq_codomain(rhs, id = self$id, direction = self$direction)
         self$surrogate_max_to_min = surrogate_mult_max_to_min(rhs)
         domain = generate_acq_domain(rhs)

diff --git a/R/AcqFunctionAEI.R b/R/AcqFunctionAEI.R
@@ -40,7 +40,7 @@
 #'     codomain = codomain,
 #'     properties = "noisy")
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionCB.R b/R/AcqFunctionCB.R
@@ -35,7 +35,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionEHVI.R b/R/AcqFunctionEHVI.R
@@ -30,7 +30,7 @@
 #'   codomain = ps(y1 = p_dbl(tags = "minimize"), y2 = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceMultiCrit$new(
+#'   instance = OptimInstanceBatchMultiCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'
@@ -117,7 +117,7 @@ AcqFunctionEHVI = R6Class("AcqFunctionEHVI",
       }
 
       columns = colnames(self$ys_front_augmented)
-      
+
       ps = self$surrogate$predict(xdt)
       means = map_dtc(ps, "mean")
 

diff --git a/R/AcqFunctionEHVIGH.R b/R/AcqFunctionEHVIGH.R
@@ -41,7 +41,7 @@
 #'   codomain = ps(y1 = p_dbl(tags = "minimize"), y2 = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceMultiCrit$new(
+#'   instance = OptimInstanceBatchMultiCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'
@@ -175,20 +175,20 @@ adjust_gh_data = function(gh_data, mu, sigma, r) {
   idx = as.matrix(expand.grid(rep(list(1:n), n_obj)))
   nodes = matrix(gh_data[idx, 1L], nrow = nrow(idx), ncol = n_obj)
   weights = apply(matrix(gh_data[idx, 2L], nrow = nrow(idx), ncol = n_obj), MARGIN = 1L, FUN = prod)
- 
-  # pruning with pruning rate r 
+
+  # pruning with pruning rate r
   if (r > 0) {
     weights_quantile = quantile(weights, probs = r)
     nodes = nodes[weights > weights_quantile, ]
     weights = weights[weights > weights_quantile]
   }
-  
+
   # rotate, scale, translate nodes with error catching
   # rotation will not have an effect unless we support surrogate models modelling correlated objectives
   # for now we still support this more general case and scaling is useful anyways
   nodes = tryCatch(
     {
-      eigen_decomp = eigen(sigma) 
+      eigen_decomp = eigen(sigma)
       rotation = eigen_decomp$vectors %*% diag(sqrt(eigen_decomp$values))
       nodes = t(rotation %*% t(nodes) + mu)
     }, error = function(ec) nodes

diff --git a/R/AcqFunctionEI.R b/R/AcqFunctionEI.R
@@ -30,7 +30,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionEIPS.R b/R/AcqFunctionEIPS.R
@@ -9,9 +9,9 @@
 #' @description
 #' Expected Improvement per Second.
 #'
-#' It is assumed that calculations are performed on an [bbotk::OptimInstanceSingleCrit].
+#' It is assumed that calculations are performed on an [bbotk::OptimInstanceBatchSingleCrit].
 #' Additionally to target values of the codomain that should be minimized or maximized, the
-#' [bbotk::Objective] of the [bbotk::OptimInstanceSingleCrit] should return time values.
+#' [bbotk::Objective] of the [bbotk::OptimInstanceBatchSingleCrit] should return time values.
 #' The column names of the target variable and time variable must be passed as `cols_y` in the
 #' order `(target, time)` when constructing the [SurrogateLearnerCollection] that is being used as a
 #' surrogate.
@@ -37,7 +37,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"), time = p_dbl(tags = "time"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionMean.R b/R/AcqFunctionMean.R
@@ -27,7 +27,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionPI.R b/R/AcqFunctionPI.R
@@ -30,7 +30,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionSD.R b/R/AcqFunctionSD.R
@@ -27,7 +27,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqFunctionSmsEgo.R b/R/AcqFunctionSmsEgo.R
@@ -40,7 +40,7 @@
 #'   codomain = ps(y1 = p_dbl(tags = "minimize"), y2 = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceMultiCrit$new(
+#'   instance = OptimInstanceBatchMultiCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/AcqOptimizer.R b/R/AcqOptimizer.R
@@ -59,7 +59,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'
@@ -146,7 +146,7 @@ AcqOptimizer = R6Class("AcqOptimizer",
       logger$set_threshold(self$param_set$values$logging_level)
       on.exit(logger$set_threshold(old_threshold))
 
-      instance = OptimInstanceSingleCrit$new(objective = self$acq_function, search_space = self$acq_function$domain, terminator = self$terminator, check_values = FALSE, keep_evals = "all")
+      instance = OptimInstanceBatchSingleCrit$new(objective = self$acq_function, search_space = self$acq_function$domain, terminator = self$terminator, check_values = FALSE)
 
       # warmstart
       if (self$param_set$values$warmstart) {

diff --git a/R/OptimizerMbo.R b/R/OptimizerMbo.R
@@ -47,7 +47,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'
@@ -75,7 +75,7 @@
 #'   codomain = ps(y1 = p_dbl(tags = "minimize"), y2 = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceMultiCrit$new(
+#'   instance = OptimInstanceBatchMultiCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'
@@ -89,7 +89,7 @@
 #' }
 #' }
 OptimizerMbo = R6Class("OptimizerMbo",
-  inherit = bbotk::Optimizer,
+  inherit = bbotk::OptimizerBatch,
 
   public = list(
     #' @description

diff --git a/R/ResultAssigner.R b/R/ResultAssigner.R
@@ -28,7 +28,7 @@ ResultAssigner = R6Class("ResultAssigner",
     #' @description
     #' Assigns the result, i.e., the final point(s) to the instance.
     #'
-    #' @param instance ([bbotk::OptimInstanceSingleCrit] | [bbotk::OptimInstanceMultiCrit])\cr
+    #' @param instance ([bbotk::OptimInstanceBatchSingleCrit] | [bbotk::OptimInstanceBatchMultiCrit])\cr
     #'   The [bbotk::OptimInstance] the final result should be assigned to.
     assign_result = function(instance) {
       stop("Abstract.")

diff --git a/R/ResultAssignerArchive.R b/R/ResultAssignerArchive.R
@@ -26,12 +26,12 @@ ResultAssignerArchive = R6Class("ResultAssignerArchive",
     #' @description
     #' Assigns the result, i.e., the final point(s) to the instance.
     #'
-    #' @param instance ([bbotk::OptimInstanceSingleCrit] | [bbotk::OptimInstanceMultiCrit])\cr
+    #' @param instance ([bbotk::OptimInstanceBatchSingleCrit] | [bbotk::OptimInstanceBatchMultiCrit])\cr
     #'   The [bbotk::OptimInstance] the final result should be assigned to.
     assign_result = function(instance) {
       res = instance$archive$best()
       xdt = res[, instance$search_space$ids(), with = FALSE]
-      if (inherits(instance, "OptimInstanceMultiCrit")) {
+      if (inherits(instance, "OptimInstanceBatchMultiCrit")) {
         ydt = res[, instance$archive$cols_y, with = FALSE]
         instance$assign_result(xdt, ydt)
       }

diff --git a/R/ResultAssignerSurrogate.R b/R/ResultAssignerSurrogate.R
@@ -7,7 +7,7 @@
 #' Result assigner that chooses the final point(s) based on a surrogate mean prediction of all evaluated points in the [bbotk::Archive].
 #' This is especially useful in the case of noisy objective functions.
 #'
-#' In the case of operating on an [bbotk::OptimInstanceMultiCrit] the [SurrogateLearnerCollection] must use as many learners as there are objective functions.
+#' In the case of operating on an [bbotk::OptimInstanceBatchMultiCrit] the [SurrogateLearnerCollection] must use as many learners as there are objective functions.
 #'
 #' @family Result Assigner
 #' @export
@@ -32,15 +32,15 @@ ResultAssignerSurrogate = R6Class("ResultAssignerSurrogate",
     #' Assigns the result, i.e., the final point(s) to the instance.
     #' If `$surrogate` is `NULL`, `default_surrogate(instance)` is used and also assigned to `$surrogate`.
     #'
-    #' @param instance ([bbotk::OptimInstanceSingleCrit] | [bbotk::OptimInstanceMultiCrit])\cr
+    #' @param instance ([bbotk::OptimInstanceBatchSingleCrit] | [bbotk::OptimInstanceBatchMultiCrit])\cr
     #'   The [bbotk::OptimInstance] the final result should be assigned to.
     assign_result = function(instance) {
       if (is.null(self$surrogate)) {
         self$surrogate = default_surrogate(instance)
       }
-      if (inherits(instance, "OptimInstanceSingleCrit")) {
+      if (inherits(instance, "OptimInstanceBatchSingleCrit")) {
         assert_r6(self$surrogate, classes = "SurrogateLearner")
-      } else if (inherits(instance, "OptimInstanceMultiCrit")) {
+      } else if (inherits(instance, "OptimInstanceBatchMultiCrit")) {
         assert_r6(self$surrogate, classes = "SurrogateLearnerCollection")
         if (self$surrogate$n_learner != instance$objective$ydim) {
           stopf("Surrogate used within the result assigner uses %i learners but the optimization instance has %i objective functions", self$surrogate$n_learner, instance$objective$ydim)
@@ -62,9 +62,9 @@ ResultAssignerSurrogate = R6Class("ResultAssignerSurrogate",
       best = archive_tmp$best()[, archive_tmp$cols_x, with = FALSE]
 
       # ys are still the ones originally evaluated
-      best_y = if (inherits(instance, "OptimInstanceSingleCrit")) {
+      best_y = if (inherits(instance, "OptimInstanceBatchSingleCrit")) {
         unlist(archive$data[best, on = archive$cols_x][, archive$cols_y, with = FALSE])
-      } else if (inherits(instance, "OptimInstanceMultiCrit")) {
+      } else if (inherits(instance, "OptimInstanceBatchMultiCrit")) {
         archive$data[best, on = archive$cols_x][, archive$cols_y, with = FALSE]
       }
       instance$assign_result(xdt = best, best_y)

diff --git a/R/Surrogate.R b/R/Surrogate.R
@@ -99,7 +99,7 @@ Surrogate = R6Class("Surrogate",
       if (missing(rhs)) {
         private$.archive
       } else {
-        private$.archive = assert_r6(rhs, classes = "Archive")
+        private$.archive = assert_archive(rhs, null_ok = TRUE)
         invisible(private$.archive)
       }
     },

diff --git a/R/SurrogateLearner.R b/R/SurrogateLearner.R
@@ -44,7 +44,7 @@
 #'   codomain = ps(y = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceSingleCrit$new(
+#'   instance = OptimInstanceBatchSingleCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'

diff --git a/R/SurrogateLearnerCollection.R b/R/SurrogateLearnerCollection.R
@@ -47,7 +47,7 @@
 #'   codomain = ps(y1 = p_dbl(tags = "minimize"), y2 = p_dbl(tags = "minimize"))
 #'   objective = ObjectiveRFun$new(fun = fun, domain = domain, codomain = codomain)
 #'
-#'   instance = OptimInstanceMultiCrit$new(
+#'   instance = OptimInstanceBatchMultiCrit$new(
 #'     objective = objective,
 #'     terminator = trm("evals", n_evals = 5))
 #'   xdt = generate_design_random(instance$search_space, n = 4)$data

diff --git a/R/TunerMbo.R b/R/TunerMbo.R
@@ -1,4 +1,4 @@
-#' @title Tuner using Model Based Optimization
+#' @title TunerBatch using Model Based Optimization
 #'
 #' @name mlr_tuners_mbo
 #'
@@ -23,7 +23,7 @@
 #'   resampling = rsmp("cv", folds = 3)
 #'   measure = msr("classif.acc")
 #'
-#'   instance = TuningInstanceSingleCrit$new(
+#'   instance = TuningInstanceBatchSingleCrit$new(
 #'     task = task,
 #'     learner = learner,
 #'     resampling = resampling,
@@ -38,7 +38,7 @@
 #'   resampling = rsmp("cv", folds = 3)
 #'   measures = msrs(c("classif.acc", "selected_features"))
 #'
-#'   instance = TuningInstanceMultiCrit$new(
+#'   instance = TuningInstanceBatchMultiCrit$new(
 #'     task = task,
 #'     learner = learner,
 #'     resampling = resampling,
@@ -50,7 +50,7 @@
 #' }
 #' }
 TunerMbo = R6Class("TunerMbo",
-  inherit = mlr3tuning::TunerFromOptimizer,
+  inherit = mlr3tuning::TunerBatchFromOptimizerBatch,
 
   public = list(
     #' @description