pkgdown.yaml and R-CMD-check.yaml scripts are commented out

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

@@ -1,54 +1,54 @@
 # Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
-on:
-  push:
-    branches: [test1-09302024-11.48AM]
-  pull_request:
-    branches: [test1-09302024-11.48AM]
-
-name: R-CMD-check.yaml
-
-permissions: read-all
-
-jobs:
-  R-CMD-check:
-    runs-on: ${{ matrix.config.os }}
-
-    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
-
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - {os: macos-latest,   r: 'release'}
-          - {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'}
-
-    env:
-      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
-      R_KEEP_PKG_SOURCE: yes
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: r-lib/actions/setup-pandoc@v2
-
-      - uses: r-lib/actions/setup-r@v2
-        with:
-          r-version: ${{ matrix.config.r }}
-          http-user-agent: ${{ matrix.config.http-user-agent }}
-          use-public-rspm: true
-
-      - uses: r-lib/actions/setup-r-dependencies@v2
-        with:
-          extra-packages: any::rcmdcheck
-
-      - uses: r-lib/actions/check-r-package@v2
-        with:
-          upload-snapshots: true
-          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'
+# on:
+#   push:
+#     branches: [test1-09302024-11.48AM]
+#   pull_request:
+#     branches: [test1-09302024-11.48AM]
+#
+# name: R-CMD-check.yaml
+#
+# permissions: read-all
+#
+# jobs:
+#   R-CMD-check:
+#     runs-on: ${{ matrix.config.os }}
+#
+#     name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+#
+#     strategy:
+#       fail-fast: false
+#       matrix:
+#         config:
+#           - {os: macos-latest,   r: 'release'}
+#           - {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'}
+#
+#     env:
+#       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+#       R_KEEP_PKG_SOURCE: yes
+#
+#     steps:
+#       - uses: actions/checkout@v4
+#
+#       - uses: r-lib/actions/setup-pandoc@v2
+#
+#       - uses: r-lib/actions/setup-r@v2
+#         with:
+#           r-version: ${{ matrix.config.r }}
+#           http-user-agent: ${{ matrix.config.http-user-agent }}
+#           use-public-rspm: true
+#
+#       - uses: r-lib/actions/setup-r-dependencies@v2
+#         with:
+#           extra-packages: any::rcmdcheck
+#
+#       - uses: r-lib/actions/check-r-package@v2
+#         with:
+#           upload-snapshots: true
+#           build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'
 
       # - uses: ./setup-r-dependencies
       #   with:

.github/workflows/pkgdown.yaml

@@ -1,50 +1,50 @@
 # Workflow derived from https://github.com/r-lib/actions/tree/v2/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]
-  release:
-    types: [published]
-  workflow_dispatch:
-
-name: pkgdown.yaml
-
-permissions: read-all
-
-jobs:
-  pkgdown:
-    runs-on: ubuntu-latest
-    # Only restrict concurrency for non-PR jobs
-    concurrency:
-      group: pkgdown-${{ github.event_name != 'pull_request' || github.run_id }}
-    env:
-      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: r-lib/actions/setup-pandoc@v2
-
-      - uses: r-lib/actions/setup-r@v2
-        with:
-          use-public-rspm: true
-
-      - uses: r-lib/actions/setup-r-dependencies@v2
-        with:
-          extra-packages: any::pkgdown, local::.
-          needs: website
-
-      - name: Build site
-        run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
-        shell: Rscript {0}
-
-      - name: Deploy to GitHub pages 🚀
-        if: github.event_name != 'pull_request'
-        uses: JamesIves/[email protected]
-        with:
-          clean: false
-          branch: gh-pages
-          folder: docs
+# on:
+#   push:
+#     branches: [main, master]
+#   pull_request:
+#     branches: [main, master]
+#   release:
+#     types: [published]
+#   workflow_dispatch:
+#
+# name: pkgdown.yaml
+#
+# permissions: read-all
+#
+# jobs:
+#   pkgdown:
+#     runs-on: ubuntu-latest
+#     # Only restrict concurrency for non-PR jobs
+#     concurrency:
+#       group: pkgdown-${{ github.event_name != 'pull_request' || github.run_id }}
+#     env:
+#       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+#     permissions:
+#       contents: write
+#     steps:
+#       - uses: actions/checkout@v4
+#
+#       - uses: r-lib/actions/setup-pandoc@v2
+#
+#       - uses: r-lib/actions/setup-r@v2
+#         with:
+#           use-public-rspm: true
+#
+#       - uses: r-lib/actions/setup-r-dependencies@v2
+#         with:
+#           extra-packages: any::pkgdown, local::.
+#           needs: website
+#
+#       - name: Build site
+#         run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
+#         shell: Rscript {0}
+#
+#       - name: Deploy to GitHub pages 🚀
+#         if: github.event_name != 'pull_request'
+#         uses: JamesIves/[email protected]
+#         with:
+#           clean: false
+#           branch: gh-pages
+#           folder: docs

DESCRIPTION

@@ -38,7 +38,9 @@ Imports:
     tidyr,
     ggplot2,
     matrixStats,
-    haven
+    haven,
+    tree,
+    plotrix
 Suggests: 
     knitr,
     rmarkdown,

R/ReprTree.R

@@ -0,0 +1,70 @@
+#' Representative trees from ensembles
+#' 
+#' This package implements the concept of representative trees from ensemble
+#' tree-based learners introduced by Banerjee, et al, (2012). Representative trees
+#' are, in some sense, trees in the ensemble which are on average the "closest" to 
+#' all the other trees in the ensemble. Several trees can be representative of the 
+#' ensemble in general. This package currently implements the d2 metric of tree closeness
+#' (close in prediction) from Banerjee, et al.
+#' 
+#' @name reprtree-package
+#' @references M. Banerjee, Y. Ding and A-M Noone (2012) "Identifying representative
+#'     trees from ensembles". Statistics in Medicine, 31(15):1601-1616.
+#' @import randomForest tree
+#' @docType package
+#' @name reprtree
+#' @examples
+#' library(reprtree)
+#' rforest <- randomForest(Species~., data=iris)
+#' reptree <- ReprTree(rforest, iris, metric='d2')
+#' plot(reptree, index=1)
+NULL
+
+
+#' Identifying and extracting representative trees from a random forest 
+#' 
+#' This function takes a random forest object and data to run predictions on
+#' and identifies representative trees based on the d0, d1 or d2 metric defined
+#' in Banerjee, et al (2012). Currently only the d2 metric is implemented, using
+#' either a euclidean distance (for numeric predictions) or a mismatch distance 
+#' (for categorical predictions). The average distance D(T) of each tree in the 
+#' set of trees in computed, and trees with the lowest D(T) value are extracted
+#' and formatted to be compatible with the \code{\link{tree}} class. Trees can then
+#' be visualized using \code{plot.tree} and \code{text.tree}, or using a custom
+#' plot function (to be defined)
+#' 
+#' @param rforest A randomForest object
+#' @param newdata The data on which predictions will be computed
+#' @param metric The metric to be used to evaluate distance between trees. Currently
+#'    only the d2 metric is implemented
+#' @return A list object containing representations of the representative trees
+#'    conformable with the \code{tree} class. Names of the list give the indices
+#'    of the representative trees in the set of trees. 
+#' @import randomForest tree
+#' @export
+#' @references M. Banerjee, Y. Ding and A-M Noone (2012) "Identifying representative
+#'     trees from ensembles". Statistics in Medicine, 31(15):1601-1616.
+#' @examples
+#' library(randomForest)
+#' library(tree)
+#' rforest <- randomForest(Species~., data=iris)
+#' reptree <- ReprTree(rforest, iris, metric='d2')
+ReprTree <- function(rforest, newdata, metric='d2'){
+  if(metric!='d2') stop('invalid metric!')
+  require(randomForest)
+  print('Constructing distance matrix...')
+  preds <- predict2(rforest, newdata=newdata, predict.all=T)
+  preds.indiv <- preds$individual
+  d <- dist.fn(t(preds.indiv), method=ifelse(rforest$type=='classification',
+                                             'mismatch',
+                                             'euclidean'))
+  print('Finding representative trees...')
+  D <- colMeans(d)
+  index <- which(D==min(D))
+  trees <- lapply(as.list(index), function(i) getTree(rforest, i, labelVar=TRUE))
+  names(trees) <- as.character(index)
+  trees <- lapply(trees, as.tree, rforest)
+  out <- list(trees=trees,D = D)
+  class(out) <- c('reprtree','list')
+  return(out)
+}