Draft implementation of HMI

.Rbuildignore

@@ -9,6 +9,7 @@
 CONTRIBUTING
 README.md
 ^\.github
+^\.lintr
 cran-comments.md
 man-roxygen
 data-raw

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

@@ -50,7 +50,7 @@ jobs:
           - {os: macOS-latest, r: 'release'}
           - {os: ubuntu-22.04, r: '4.1',
           rspm: "https://packagemanager.rstudio.com/cran/__linux__/jammy/latest"}
-          - {os: ubuntu-latest, r: 'release',
+          - {os: ubuntu-24.04, r: 'release',
           rspm: "https://packagemanager.rstudio.com/cran/__linux__/noble/latest"}
           - {os: ubuntu-latest, r: 'devel',
           rspm: "https://packagemanager.rstudio.com/cran/__linux__/noble/latest"}
@@ -76,12 +76,6 @@ jobs:
           r-version: ${{ matrix.config.r }}
           extra-repositories: https://ms609.github.io/packages/
 
-      - name: Install apt packages (Linux)
-        if: runner.os == 'Linux'
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y texlive-latex-base libglpk-dev texlive-fonts-recommended
-
       - name: Set up R dependencies (Windows)
         if: runner.os == 'Windows'
         uses: r-lib/actions/setup-r-dependencies@v2
@@ -126,3 +120,23 @@ jobs:
         if: runner.os == 'Windows'
         run: covr::codecov()
         shell: Rscript {0}
+
+      - name: Notify on failure
+        if: failure() && github.event_name == 'schedule'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: 164,
+              body: 'Scheduled workflow has failed: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}'
+            });
+
+            await github.rest.issues.update({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: 164,
+              state: 'open'
+            });

.github/workflows/benchmark.yml

@@ -3,10 +3,28 @@ name: Benchmark
 on:
   workflow_dispatch:
   pull_request:
+    paths:
+      - "src/**"
+      - "R/**" 
+      - "**.R"
+      - "**.cpp"
+      - "**.c"
+      - "**.h"
+      - "**.hpp"
+      - "configure*"
+      - "Makevars*"
     paths-ignore:
+      - "DESCRIPTION"
+      - ".**"
       - "Meta**"
       - "memcheck**"
       - "docs**"
+      - "inst**"
+      - "man**"
+      - "man-roxygen**"
+      - "memcheck**"
+      - "tests**"
+      - "vignettes**"
       - "**.git"
       - "**.json"
       - "**.md"

.github/workflows/memcheck.yml

@@ -34,12 +34,8 @@ on:
 name: mem-check
 
 jobs:
-  mem-check:
-    runs-on: ubuntu-20.04
-    # stringi requires libicui18n - apt get libicu-dev too recent,
-    # libicu66 deprecated in ubuntu 22.04
-    # Reinstalling stringi seems not to help
-
+  mem-check-templated:
+    runs-on: ubuntu-24.04
     name: valgrind ${{ matrix.config.test }}, ubuntu, R release
 
     strategy:
@@ -53,10 +49,32 @@ jobs:
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       _R_CHECK_FORCE_SUGGESTS_: false
-      RSPM: https://packagemanager.rstudio.com/cran/__linux__/focal/latest
+      RSPM: https://packagemanager.rstudio.com/cran/__linux__/noble/latest
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
 
     steps:
+      - uses: ms609/actions/memcheck@main
+        with:
+          test: ${{ matrix.config.test}}
+
+  mem-check-legacy:
+    runs-on: ubuntu-24.04
+    name: valgrind ${{ matrix.config.test }}, ubuntu, R release
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {test: 'tests'}
+          - {test: 'examples'}
+          - {test: 'vignettes'}
+
+    env:
+      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
+      _R_CHECK_FORCE_SUGGESTS_: false
+      RSPM: https://packagemanager.rstudio.com/cran/__linux__/noble/latest
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
       - uses: actions/checkout@v5
 
       - uses: r-lib/actions/setup-r@v2

.github/workflows/rhub.yaml

@@ -1,8 +1,8 @@
-# R-hub's generic GitHub Actions workflow file. Its canonical location is at
-# https://github.com/r-hub/rhub2/blob/v1/inst/workflow/rhub.yaml
+# R-hub's generic GitHub Actions workflow file. It's canonical location is at
+# https://github.com/r-hub/actions/blob/v1/workflows/rhub.yaml
 # You can update this file to a newer version using the rhub2 package:
 #
-# rhub2::rhub_setup()
+# rhub::rhub_setup()
 #
 # It is unlikely that you need to modify this file manually.
 
@@ -33,7 +33,7 @@ jobs:
 
     steps:
     # NO NEED TO CHECKOUT HERE
-    - uses: r-hub/rhub2/actions/rhub-setup@v1
+    - uses: r-hub/actions/setup@v1
       with:
         config: ${{ github.event.inputs.config }}
       id: rhub-setup
@@ -51,27 +51,17 @@ jobs:
       image: ${{ matrix.config.container }}
 
     steps:
-      - name: Check distribution
-        run: |
-          echo "distribution=$(awk -F= '/^ID=/{print $2}' /etc/os-release)" \
-            >> $GITHUB_OUTPUT;
-        id: check_distribution
-      - name: apt-get install sudo (Ubuntu, for clang-asan)
-        run: apt-get install sudo
-        if: ${{ steps.check_distribution.outputs.distribution == 'ubuntu' }}
-      - uses: r-lib/actions/setup-pandoc@v2
-        if: ${{ steps.check_distribution.outputs.distribution != 'fedora' }}
-      - uses: r-hub/rhub2/actions/rhub-checkout@v1
-      - uses: r-hub/rhub2/actions/rhub-platform-info@v1
+      - uses: r-hub/actions/checkout@v1
+      - uses: r-hub/actions/platform-info@v1
         with:
           token: ${{ secrets.RHUB_TOKEN }}
           job-config: ${{ matrix.config.job-config }}
-      - uses: r-hub/rhub2/actions/rhub-setup-deps@v1
+      - uses: r-hub/actions/setup-deps@v1
         with:
           token: ${{ secrets.RHUB_TOKEN }}
           job-config: ${{ matrix.config.job-config }}
           extra-packages: TreeDistData=?ignore-before-r=99.0.0
-      - uses: r-hub/rhub2/actions/rhub-run-check@v1
+      - uses: r-hub/actions/run-check@v1
         with:
           token: ${{ secrets.RHUB_TOKEN }}
           job-config: ${{ matrix.config.job-config }}
@@ -87,25 +77,21 @@ jobs:
         config: ${{ fromJson(needs.setup.outputs.platforms) }}
 
     steps:
-      - uses: teatimeguest/setup-texlive-action@v3
-        with:
-          packages: scheme-basic
-      - uses: r-lib/actions/setup-pandoc@v2
-      - uses: r-hub/rhub2/actions/rhub-checkout@v1
-      - uses: r-hub/rhub2/actions/rhub-setup-r@v1
+      - uses: r-hub/actions/checkout@v1
+      - uses: r-hub/actions/setup-r@v1
         with:
           job-config: ${{ matrix.config.job-config }}
           token: ${{ secrets.RHUB_TOKEN }}
-      - uses: r-hub/rhub2/actions/rhub-platform-info@v1
+      - uses: r-hub/actions/platform-info@v1
         with:
           token: ${{ secrets.RHUB_TOKEN }}
           job-config: ${{ matrix.config.job-config }}
-      - uses: r-hub/rhub2/actions/rhub-setup-deps@v1
+      - uses: r-hub/actions/setup-deps@v1
         with:
           job-config: ${{ matrix.config.job-config }}
           token: ${{ secrets.RHUB_TOKEN }}
           extra-packages: TreeDistData=?ignore-before-r=99.0.0
-      - uses: r-hub/rhub2/actions/rhub-run-check@v1
+      - uses: r-hub/actions/run-check@v1
         with:
           job-config: ${{ matrix.config.job-config }}
           token: ${{ secrets.RHUB_TOKEN }}

.gitignore

@@ -18,6 +18,7 @@ src/*.dll
 *.utf8.md
 /* *.Rd */
 revdep/
+inst/__pycache__*
 vignettes/*.html
 vignettes/*.pdf
 vignettes/*_files

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: TreeDist
 Type: Package
 Title: Calculate and Map Distances Between Phylogenetic Trees
-Version: 2.10.1.9001
+Version: 2.10.1.9002
 Authors@R: c(person("Martin R.", "Smith",
                     email = "martin.smith@durham.ac.uk", 
                     role = c("aut", "cre", "cph", "prg"), 
@@ -23,6 +23,8 @@ Description: Implements measures of tree similarity, including
   including the Nye et al. (2006) metric <doi:10.1093/bioinformatics/bti720>;
   the Matching Split Distance (Bogdanowicz & Giaro 2012)
   <doi:10.1109/TCBB.2011.48>;
+  the Hierarchical Mutual Information (Perotti et al. 2015)
+  <doi:10.1103/PhysRevE.92.062825>;
   Maximum Agreement Subtree distances;
   the Kendall-Colijn (2016) distance <doi:10.1093/molbev/msw124>, and the
   Nearest Neighbour Interchange (NNI) distance, approximated per Li et al. 

NAMESPACE

@@ -27,6 +27,8 @@ S3method(NNIDiameter,list)
 S3method(NNIDiameter,multiPhylo)
 S3method(NNIDiameter,numeric)
 S3method(NNIDiameter,phylo)
+S3method(NTip,HPart)
+S3method(RenumberTips,HPart)
 S3method(SPRDist,list)
 S3method(SPRDist,multiPhylo)
 S3method(SPRDist,phylo)
@@ -35,8 +37,17 @@ S3method(SplitwiseInfo,Splits)
 S3method(SplitwiseInfo,list)
 S3method(SplitwiseInfo,multiPhylo)
 S3method(SplitwiseInfo,phylo)
+S3method(as.HPart,HPart)
+S3method(as.HPart,default)
+S3method(as.HPart,list)
+S3method(as.HPart,phylo)
+S3method(as.phylo,HPart)
+S3method(clone,HPart)
 S3method(median,multiPhylo)
+S3method(plot,HPart)
+S3method(print,HPart)
 export(.TreeDistance)
+export(AHMI)
 export(AllSplitPairings)
 export(CalculateTreeDistance)
 export(ClusteringEntropy)
@@ -49,10 +60,15 @@ export(DifferentPhylogeneticInfo)
 export(DisplayMatching)
 export(DistFromMed)
 export(DistanceFromMedian)
+export(EHMI)
 export(Entropy)
 export(ExpectedVariation)
 export(GeneralizedRF)
 export(GetParallel)
+export(HH)
+export(HMI)
+export(HierarchicalMutualInfo)
+export(HierarchicalMutualInformation)
 export(InfoRobinsonFoulds)
 export(InfoRobinsonFouldsSplits)
 export(Islands)
@@ -105,6 +121,7 @@ export(RobinsonFouldsInfo)
 export(RobinsonFouldsMatching)
 export(RobinsonFouldsSplits)
 export(SPRDist)
+export(SelfHMI)
 export(SetParallel)
 export(SharedPhylogeneticInfo)
 export(SharedPhylogeneticInfoSplits)
@@ -127,7 +144,10 @@ export(TreeDistance)
 export(TreesConsistentWithTwoSplits)
 export(VisualiseMatching)
 export(VisualizeMatching)
+export(as.HPart)
+export(clone)
 export(entropy_int)
+export(is.HPart)
 importFrom(Rdpack,reprompt)
 importFrom(TreeTools,AllAncestors)
 importFrom(TreeTools,DropTip)
@@ -141,6 +161,7 @@ importFrom(TreeTools,Log2Unrooted)
 importFrom(TreeTools,Log2Unrooted.int)
 importFrom(TreeTools,MSTEdges)
 importFrom(TreeTools,MSTLength)
+importFrom(TreeTools,MatchStrings)
 importFrom(TreeTools,NRooted)
 importFrom(TreeTools,NSplits)
 importFrom(TreeTools,NTip)
@@ -162,6 +183,7 @@ importFrom(TreeTools,as.ClusterTable)
 importFrom(TreeTools,as.Splits)
 importFrom(TreeTools,edge_to_splits)
 importFrom(ape,Nnode.phylo)
+importFrom(ape,as.phylo)
 importFrom(ape,drop.tip)
 importFrom(ape,edgelabels)
 importFrom(ape,nodelabels)

NEWS.md

@@ -1,5 +1,7 @@
-# TreeDist 2.10.1.9001 (development)
+# TreeDist 2.10.1.9002 (development)
 
+- `HierarchicalMutualInformation()` calculates the information shared between
+  pairs of hierarchical partition structures <doi:10.1103/PhysRevE.92.062825>.
 - Fix crash in `robinson_foulds_all_pairs()` and `RobinsonFoulds(list)`.
 - Fix bug in calculation of `MutualClusteringInfo()`: greedy optimization
   was not guaranteed to find globally optimal matching, causing distances to be