Merge pull request #87 from jasenfinch/devel

v0.14.10

.github/workflows/R-CMD-check.yaml

@@ -22,7 +22,7 @@ jobs:
           - {os: windows-latest, r: 'release'}
           - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
           - {os: ubuntu-latest,   r: 'release'}
-          - {os: ubuntu-latest,   r: 'oldrel/1'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
@@ -43,26 +43,4 @@ jobs:
         with:
           extra-packages: rcmdcheck
 
-      - name: Check
-        env:
-          _R_CHECK_CRAN_INCOMING_: false
-        run: |
-          options(crayon.enabled = TRUE)
-          rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), error_on = "warning", check_dir = "check")
-        shell: Rscript {0}
-
-      - name: Show testthat output
-        if: always()
-        run: find check -name 'testthat.Rout*' -exec cat '{}' \; || true
-        shell: bash
-
-      - name: Test coverage
-        run: covr::codecov()
-        shell: Rscript {0}
-
-      - name: Upload check results
-        if: failure()
-        uses: actions/upload-artifact@main
-        with:
-          name: ${{ runner.os }}-r${{ matrix.config.r }}-results
-          path: check
+      - uses: r-lib/actions/check-r-package@v1

.github/workflows/pkgdown.yaml

@@ -0,0 +1,35 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/master/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  release:
+    types: [published]
+  workflow_dispatch:
+
+name: pkgdown
+
+jobs:
+  pkgdown:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: r-lib/actions/setup-pandoc@v1
+
+      - uses: r-lib/actions/setup-r@v1
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v1
+        with:
+          extra-packages: pkgdown
+          needs: website
+
+      - name: Deploy package
+        run: |
+          git config --local user.name "$GITHUB_ACTOR"
+          git config --local user.email "$GITHUB_ACTOR@users.noreply.github.com"
+          Rscript -e 'pkgdown::deploy_to_branch(new_process = FALSE)'

.github/workflows/test-coverage.yaml

@@ -0,0 +1,30 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/master/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+name: test-coverage
+
+jobs:
+  test-coverage:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: r-lib/actions/setup-r@v1
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v1
+        with:
+          extra-packages: covr
+
+      - name: Test coverage
+        run: covr::codecov()
+        shell: Rscript {0}

.gitignore

@@ -7,3 +7,4 @@ doc
 Meta
 /doc/
 /Meta/
+docs

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: metabolyseR
 Title: Methods for Pre-Treatment, Data Mining and Correlation Analyses of Metabolomics Data
-Version: 0.14.9
+Version: 0.14.10
 Authors@R: person("Jasen", "Finch", email = "jsf9@aber.ac.uk", role = c("aut", "cre"))
 Description: A tool kit for pre-treatment, modelling, feature selection and correlation analyses of metabolomics data.
 URL: https://jasenfinch.github.io/metabolyseR
@@ -76,6 +76,7 @@ Collate: allClasses.R
     plotting.R
     plotUnsupervisedRF.R
     pre-treatment.R
+    predict.R
     QC.R
     reexports.R
     remove.R
@@ -85,6 +86,7 @@ Collate: allClasses.R
     show-method.R
     split.R
     transform.R
+    tune.R
     univariate.R
     modelling-accessors.R
 VignetteBuilder: knitr

NAMESPACE

@@ -48,6 +48,7 @@ export(metabolyse)
 export(metrics)
 export(modellingMethods)
 export(modellingParameters)
+export(mtry)
 export(nFeatures)
 export(nSamples)
 export(occupancy)
@@ -73,6 +74,7 @@ export(preTreated)
 export(preTreatmentElements)
 export(preTreatmentMethods)
 export(preTreatmentParameters)
+export(predict)
 export(proximity)
 export(randomForest)
 export(raw)
@@ -97,6 +99,7 @@ export(transformSQRT)
 export(transformTICnorm)
 export(transformVast)
 export(ttest)
+export(tune)
 export(type)
 exportClasses(Analysis)
 exportClasses(AnalysisData)
@@ -137,6 +140,7 @@ importFrom(dplyr,mutate_if)
 importFrom(dplyr,n)
 importFrom(dplyr,relocate)
 importFrom(dplyr,rename)
+importFrom(dplyr,rename_with)
 importFrom(dplyr,rowwise)
 importFrom(dplyr,select)
 importFrom(dplyr,select_if)
@@ -147,6 +151,7 @@ importFrom(e1071,naiveBayes)
 importFrom(forestControl,fpr_fs)
 importFrom(furrr,furrr_options)
 importFrom(furrr,future_map)
+importFrom(furrr,future_map2)
 importFrom(future,plan)
 importFrom(ggdendro,dendro_data)
 importFrom(ggplot2,aes)
@@ -210,6 +215,7 @@ importFrom(patchwork,wrap_plots)
 importFrom(purrr,map)
 importFrom(purrr,map_chr)
 importFrom(purrr,map_dbl)
+importFrom(purrr,map_depth)
 importFrom(purrr,map_df)
 importFrom(purrr,map_lgl)
 importFrom(purrr,walk)
@@ -231,6 +237,7 @@ importFrom(stats,runif)
 importFrom(stats,sd)
 importFrom(stringr,str_c)
 importFrom(stringr,str_extract)
+importFrom(stringr,str_remove)
 importFrom(stringr,str_remove_all)
 importFrom(stringr,str_replace_all)
 importFrom(stringr,str_split)
@@ -241,6 +248,7 @@ importFrom(tibble,deframe)
 importFrom(tibble,rowid_to_column)
 importFrom(tibble,tibble)
 importFrom(tidyr,drop_na)
+importFrom(tidyr,expand_grid)
 importFrom(tidyr,gather)
 importFrom(tidyr,spread)
 importFrom(tidyselect,all_of)

NEWS.md

@@ -1,3 +1,11 @@
+# metabolyseR 0.14.10
+
+* Added the method [`predict()`](https://jasenfinch.github.io/metabolyseR/reference/predict.html) for the [`RandomForest`](https://jasenfinch.github.io/metabolyseR/reference/RandomForest-class.html) S4 class to predict model response values.
+
+* Added the method [`mtry()`](https://jasenfinch.github.io/metabolyseR/reference/modelling-accessors.html) for the [`AnalysisData`](https://jasenfinch.github.io/metabolyseR/reference/AnalysisData-class.html) S4 class to return the default `mtry` random forest parameter for a given response variable.
+
+* Added the method [`tune()`]() for the [`AnalysisData`](https://jasenfinch.github.io/metabolyseR/reference/tune.html) S4 class to tune the random forest parameters `mtry` and `ntree` for a given response variable.
+
 # metabolyseR 0.14.9
 
 * Suppressed name repair console message encountered during random forest permutation testing.

R/modelling-accessors.R

@@ -9,6 +9,7 @@
 #' @param ... arguments to parse to method for specific class
 #' @section Methods:
 #' * `binaryComparisons`: Return a vector of all possible binary comparisons for a given sample information column.
+#' * `mtry`: Return the default `mtry` random forest parameter value for a given sample information column.
 #' * `type`: Return the type of random forest analysis.
 #' * `response`: Return the response variable name used for a random forest analysis.
 #' * `metrics`: Retrieve the model performance metrics for a random forest analysis
@@ -21,9 +22,12 @@
 #' 
 #' d <- analysisData(abr1$neg[,200:300],abr1$fact)
 #' 
-#' ## Return possible binary comparisons for the 'day' column
+#' ## Return possible binary comparisons for the `day` response column
 #' binaryComparisons(d,cls = 'day')
 #' 
+#' ## Return the default random forest `mtry` parameter for the `day` response column
+#' mtry(d,cls = 'day')
+#' 
 #' ## Perform random forest analysis
 #' rf_analysis <- randomForest(d,cls = 'day')
 #' 
@@ -70,6 +74,40 @@ setMethod('binaryComparisons',signature = 'AnalysisData',
 #' @rdname modelling-accessors
 #' @export
 
+setGeneric("mtry", function(x,cls = 'class')
+  standardGeneric("mtry"))
+
+#' @rdname modelling-accessors
+
+setMethod('mtry',signature = 'AnalysisData',
+          function(x,cls = 'class'){
+
+            if (is.null(cls)){
+              rf_type <- 'classification'
+            } else {
+              response <- x %>% 
+                clsExtract(cls = cls)
+
+              rf_type <- ifelse(is.numeric(response),
+                                'regression',
+                                'classification')
+            }
+
+            n_features <- nFeatures(x)
+
+            mtry <- switch(rf_type,
+                           regression = n_features/3,
+                           classification = sqrt(n_features)) %>% 
+              floor() %>% 
+              c(.,1) %>% 
+              max()
+
+            return(mtry)
+          })
+
+#' @rdname modelling-accessors
+#' @export
+
 setGeneric("type", function(x)
   standardGeneric("type"))
 

R/nlda.R

@@ -3,7 +3,7 @@
 setGeneric('nlda',function(x,cls = 'class',prior = NULL,scale = FALSE,comprank = FALSE,...)
   standardGeneric('nlda'))
 
-#' @importFrom e1071 naiveBayes
+#' @importFrom e1071 naiveBayes 
 #' @importFrom stats cov predict 
 #' @importFrom methods as
 
@@ -135,7 +135,7 @@ setMethod('nlda',signature = 'AnalysisData',
             dimnames(xmeans)[[2]] <- colnames(x)
 
             nbmod <- naiveBayes(data.frame(x),cl)
-            prob <- predict(nbmod,data.frame(x),type="raw")
+            prob <- stats::predict(nbmod,data.frame(x),type="raw")
             pred <- apply(prob,1,which.max)
             pred <- factor(levels(cl)[pred], levels = levels(cl))