v0.0.3

.Rbuildignore

@@ -8,3 +8,5 @@
 ^_pkgdown\.yml$
 ^docs$
 ^pkgdown$
+^[.]?air[.]toml$
+^\.vscode$

.gitignore

@@ -7,3 +7,5 @@
 inst/doc
 docs
 pkgdown
+
+/.quarto/

.vscode/extensions.json

@@ -0,0 +1,5 @@
+{
+    "recommendations": [
+        "Posit.air-vscode"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,10 @@
+{
+    "[r]": {
+        "editor.formatOnSave": true,
+        "editor.defaultFormatter": "Posit.air-vscode"
+    },
+    "[quarto]": {
+        "editor.formatOnSave": true,
+        "editor.defaultFormatter": "quarto.quarto"
+    }
+}

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: scimo
 Title: Extra Recipes Steps for Dealing with Omics Data
-Version: 0.0.2
+Version: 0.0.3
 Authors@R: c(
     person("Antoine", "BICHAT", , "antoine.bichat@proton.me", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0001-6599-7081")),
@@ -17,7 +17,7 @@ URL: https://github.com/abichat/scimo
 BugReports: https://github.com/abichat/scimo/issues
 Depends: 
     R (>= 2.10),
-    recipes
+    recipes (>= 1.1)
 Imports: 
     dplyr,
     generics,
@@ -37,4 +37,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: false
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2

NEWS.md

@@ -1,10 +1,15 @@
+# scimo 0.0.3
+
+* Add a dependency on **recipes** >= 1.1 to avoid stack overflow errors with long formulas, as this issue has been resolved in this version (#2).
+
+* Small improvements in documentation (#6, CRAN notes).
+
 # scimo 0.0.2
 
 * New function `step_taxonomy()`.
 
 * Replace superseded `juice()` with `bake(new_data = NULL)` to align with current practices (#1).
 
-
 # scimo 0.0.1
 
 * First release of **scimo**.

R/aggregate.R

@@ -1,12 +1,18 @@
-aggregate_var <- function(data, list_agg, fun_agg,
-                          prefix = "agg_",
-                          keep_original_cols = FALSE) {
-
+aggregate_var <- function(
+  data,
+  list_agg,
+  fun_agg,
+  prefix = "agg_",
+  keep_original_cols = FALSE
+) {
   list_agg <- fill_name(list_agg, prefix)
 
   for (i in seq_along(list_agg)) {
-    data[[names(list_agg[i])]] <- apply(data[, list_agg[[i]]],
-                                        MARGIN = 1, FUN = fun_agg)
+    data[[names(list_agg[i])]] <- apply(
+      data[, list_agg[[i]]],
+      MARGIN = 1,
+      FUN = fun_agg
+    )
   }
 
   if (!keep_original_cols) {

R/aggregate_hclust.R

@@ -5,7 +5,7 @@
 #' @param recipe A recipe object. The step will be added to the sequence of
 #' operations for this recipe.
 #' @param ... One or more selector functions to choose variables
-#'  for this step. See [selections()] for more details.
+#'  for this step. See [recipes::selections()] for more details.
 #' @param role For model terms created by this step, what analysis role should
 #'  they be assigned? By default, the new columns created by this step from
 #'  the original variables will be used as `predictors` in a model.
@@ -23,8 +23,8 @@
 #' @param keep_original_cols A logical to keep the original variables in
 #' the output. Defaults to `FALSE`.
 #' @param skip A logical. Should the step be skipped when the
-#'  recipe is baked by [bake()]? While all operations are baked
-#'  when [prep()] is run, some operations may not be able to be
+#'  recipe is baked by [recipes::bake()]? While all operations are baked
+#'  when [recipes::prep()] is run, some operations may not be able to be
 #'  conducted on new data (e.g. processing the outcome variable(s)).
 #'  Care should be taken when using `skip = TRUE` as it may affect
 #'  the computations for subsequent operations.
@@ -50,18 +50,21 @@
 #' rec
 #' tidy(rec, 1)
 #' bake(rec, new_data = NULL)
-step_aggregate_hclust <- function(recipe, ..., role = "predictor",
-                                  trained = FALSE,
-                                  n_clusters,
-                                  fun_agg,
-                                  dist_metric = "euclidean",
-                                  linkage_method = "complete",
-                                  res = NULL,
-                                  prefix = "cl_",
-                                  keep_original_cols = FALSE,
-                                  skip = FALSE,
-                                  id = rand_id("aggregate_hclust")) {
-
+step_aggregate_hclust <- function(
+  recipe,
+  ...,
+  role = "predictor",
+  trained = FALSE,
+  n_clusters,
+  fun_agg,
+  dist_metric = "euclidean",
+  linkage_method = "complete",
+  res = NULL,
+  prefix = "cl_",
+  keep_original_cols = FALSE,
+  skip = FALSE,
+  id = rand_id("aggregate_hclust")
+) {
   add_step(
     recipe,
     step_aggregate_hclust_new(
@@ -82,25 +85,35 @@ step_aggregate_hclust <- function(recipe, ..., role = "predictor",
 }
 
 #' @importFrom recipes step
-step_aggregate_hclust_new <- function(terms, role, trained,
-                                      n_clusters, fun_agg,
-                                      dist_metric, linkage_method,
-                                      res, prefix, keep_original_cols,
-                                      skip, id) {
-
-  step(subclass = "aggregate_hclust",
-       terms = terms,
-       role = role,
-       trained = trained,
-       n_clusters = n_clusters,
-       fun_agg = fun_agg,
-       dist_metric = dist_metric,
-       linkage_method = linkage_method,
-       res = res,
-       prefix = prefix,
-       keep_original_cols = keep_original_cols,
-       skip = skip,
-       id = id)
+step_aggregate_hclust_new <- function(
+  terms,
+  role,
+  trained,
+  n_clusters,
+  fun_agg,
+  dist_metric,
+  linkage_method,
+  res,
+  prefix,
+  keep_original_cols,
+  skip,
+  id
+) {
+  step(
+    subclass = "aggregate_hclust",
+    terms = terms,
+    role = role,
+    trained = trained,
+    n_clusters = n_clusters,
+    fun_agg = fun_agg,
+    dist_metric = dist_metric,
+    linkage_method = linkage_method,
+    res = res,
+    prefix = prefix,
+    keep_original_cols = keep_original_cols,
+    skip = skip,
+    id = id
+  )
 }
 
 #' @export
@@ -112,12 +125,32 @@ step_aggregate_hclust_new <- function(terms, role, trained,
 prep.step_aggregate_hclust <- function(x, training, info = NULL, ...) {
   col_names <- recipes_eval_select(x$terms, training, info)
   check_type(training[, col_names], quant = TRUE)
-  check_in(x$dist_metric, name_x = "dist_metric",
-           values = c("euclidean", "maximum", "manhattan",
-                      "canberra", "binary", "minkowski"))
-  check_in(x$linkage_method, name_x = "linkage_method",
-           values = c("ward.D", "ward.D2", "single", "complete",
-                      "average", "mcquitty", "median", "centroid"))
+  check_in(
+    x$dist_metric,
+    name_x = "dist_metric",
+    values = c(
+      "euclidean",
+      "maximum",
+      "manhattan",
+      "canberra",
+      "binary",
+      "minkowski"
+    )
+  )
+  check_in(
+    x$linkage_method,
+    name_x = "linkage_method",
+    values = c(
+      "ward.D",
+      "ward.D2",
+      "single",
+      "complete",
+      "average",
+      "mcquitty",
+      "median",
+      "centroid"
+    )
+  )
 
   ct <-
     training[, col_names] %>%
@@ -132,7 +165,6 @@ prep.step_aggregate_hclust <- function(x, training, info = NULL, ...) {
     enframe(name = "terms", value = "aggregate") %>%
     mutate(aggregate = paste0(x$prefix, .data$aggregate))
 
-
   step_aggregate_hclust_new(
     terms = x$terms,
     role = x$role,
@@ -158,9 +190,13 @@ bake.step_aggregate_hclust <- function(object, new_data, ...) {
 
   list_agg_hc <- split(object$res$terms, object$res$aggregate)
 
-  aggregate_var(new_data, list_agg = list_agg_hc, fun_agg = object$fun_agg,
-                prefix = object$prefix,
-                keep_original_cols = object$keep_original_cols)
+  aggregate_var(
+    new_data,
+    list_agg = list_agg_hc,
+    fun_agg = object$fun_agg,
+    prefix = object$prefix,
+    keep_original_cols = object$keep_original_cols
+  )
 }
 
 #' @export