fastSmoothEMD code review suggestions

.Rbuildignore

@@ -3,3 +3,5 @@
 ^data-raw$
 ^.travis.yml
 ^appveyor\.yml$
+^doc$
+^Meta$

.github/workflows/build.yml

@@ -0,0 +1,75 @@
+# 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]
+  schedule:
+    - cron: "5 5 5 * *"  # run at 05:05 on 5th day of each month
+
+name: Build
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'oldrel'}
+          - {os: ubuntu-latest,   r: 'devel'}
+          - {os: macOS-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+    steps:
+      # on PR set branch to be able to push back, see https://github.com/actions/checkout/issues/124
+      - uses: actions/checkout@v2
+        if: github.event_name == 'pull_request'
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+
+      - uses: actions/checkout@v2
+        if: github.event_name != 'pull_request'
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-pandoc@v2
+      - uses: r-lib/actions/setup-tinytex@v2
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: |
+            any::devtools
+            any::covr
+
+      - name: Document
+        run: devtools::document()
+        shell: Rscript {0}
+
+      - name: Commit and push documentation changes
+        if: ${{ (matrix.config.os == 'ubuntu-latest') && (matrix.config.r == 'release') }}
+        run: |
+          git config --local user.name "$GITHUB_ACTOR"
+          git config --local user.email "[email protected]"
+          git add man/\* NAMESPACE
+          git commit -m "Update documentation" || echo "No changes to commit"
+          git pull --ff-only
+          git push origin
+
+      - name: Check package
+        run: devtools::check()
+        shell: Rscript {0}
+
+      - name: Check coverage
+        run: covr::codecov(quiet = FALSE)
+        shell: Rscript {0}

.github/workflows/pkgdown.yml

@@ -0,0 +1,41 @@
+# 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]
+  release:
+    types: [published]
+
+name: Website
+
+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 }}
+    steps:
+      - uses: actions/checkout@v2
+
+      - 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::.
+
+      - name: Build site
+        run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
+        shell: Rscript {0}
+
+      - name: Deploy to GitHub pages 🚀
+        uses: JamesIves/[email protected]
+        with:
+          clean: false
+          branch: gh-pages
+          folder: docs

.gitignore

@@ -6,3 +6,7 @@
 *.so
 *.dll
 vignettes/.build.timestamp
+inst/doc
+doc
+Meta
+docs/

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: netdist
 Title: An implementation of the NetEMD alignment-free network distance measure
-Version: 0.4.9000
+Version: 0.4.9100
 Authors@R: person("Martin", "O'Reilly",email = "[email protected]", 
                   role = c("aut", "cre"))
 Description: An implementation of the NetEMD alignment-free network
@@ -20,13 +20,15 @@ Imports:
     purrr,
     lpSolve,
     plyr,
-    dplyr,
-    Rcpp
+    pheatmap,
+    Rcpp,
 Suggests:
+    dplyr,
+    phangorn,
     testthat,
     knitr,
-    phangorn,
-    rmarkdown
-RoxygenNote: 6.0.1
+    rmarkdown,
+    roxygen2
+RoxygenNote: 7.2.0
 VignetteBuilder: knitr
 Encoding: UTF-8

NAMESPACE

@@ -1,7 +1,6 @@
 # Generated by roxygen2: do not edit by hand
 
 export(NetEmdSmoothV2)
-export(NetEmdSmooth)
 export(adaptive_breaks)
 export(area_between_dhist_ecmfs)
 export(as_smoothed_dhist)
@@ -10,13 +9,15 @@ export(binned_densities_adaptive)
 export(count_graphlet_tuples)
 export(count_graphlet_tuples_ego)
 export(count_graphlets_ego)
-export(count_graphlets_ego_scaled)
 export(count_graphlets_for_graph)
 export(count_graphlets_per_node)
 export(count_orbits_per_node)
 export(counts_from_observations)
 export(cross_comp_to_matrix)
 export(cross_comparison_spec)
+export(density_binned_counts)
+export(density_binned_counts_gp)
+export(density_from_counts)
 export(dhist)
 export(dhist_ecmf)
 export(dhist_from_obs)
@@ -25,6 +26,8 @@ export(dhist_mean_location)
 export(dhist_std)
 export(dhist_variance)
 export(ecmf_knots)
+export(ego_network_density)
+export(ego_to_graphlet_counts)
 export(emd)
 export(emd_cs)
 export(emd_fast_no_smoothing)
@@ -46,29 +49,31 @@ export(min_emd)
 export(min_emd_exhaustive)
 export(min_emd_optimise)
 export(min_emd_optimise_fast)
-export(netEMDSpeedTest)
 export(netEMDSpeedTestSmooth)
-export(net_emd)
-export(net_emds_for_all_graphs)
 export(netdis)
+export(netdis.plot)
 export(netdis_centred_graphlet_counts)
-export(netdis_centred_graphlet_counts_ego)
-export(netdis_expected_graphlet_counts)
-export(netdis_expected_graphlet_counts_ego)
-export(netdis_expected_graphlet_counts_ego_fn)
-export(netdis_for_all_graphs)
+export(netdis_expected_counts)
+export(netdis_many_to_many)
+export(netdis_one_to_many)
+export(netdis_one_to_one)
+export(netdis_subtract_exp_counts)
+export(netdis_uptok)
+export(netemd.plot)
+export(netemd_many_to_many)
+export(netemd_one_to_one)
+export(netemd_single_pair)
 export(normalise_dhist_mass)
 export(normalise_dhist_variance)
 export(orbit_key)
 export(orbit_to_graphlet_counts)
 export(read_simple_graph)
 export(read_simple_graphs)
 export(scale_graphlet_count)
+export(scale_graphlet_counts_ego)
 export(shift_dhist)
 export(simplify_graph)
+export(single_density_bin)
 export(sort_dhist)
-export(zeros_to_ones)
-import(Rcpp)
-importFrom(Rcpp,evalCpp)
 importFrom(Rcpp,sourceCpp)
 useDynLib(netdist, .registration=TRUE)

R/PlottingFunctions.R

@@ -0,0 +1,56 @@
+
+#' Heatmap of Netdis many-to-many comparisons
+#'
+#' Provides a heatmap and dendrogram for the network comparisons via \code{pheatmap}.
+#' 
+#' @param netdislist Default output of \code{netdis_many_to_many}.
+#'
+#' @param whatrow Selection of the row in \code{netdis_many_to_many$comp_spec} to be used for plotting.
+#'
+#' @param clustering_method Clustering method as allowed in the \code{pheatmap} function from the \code{pheatmap} package. The dendrogram will appear if \code{docluster} is TRUE (default).
+#'
+#' @param main Title of the plot.
+#' 
+#' @param docluster controls the order of the rows and columns. If TRUE (default) the rows and columns will be reordered to create the dendrogram. If FALSE, then only the heatmap is drawn.
+#' 
+#' @return Provides a heatmap and dendrogram for the network comparisons via \code{pheatmap}.
+#' @export
+
+netdis.plot <- function(netdislist,whatrow=c(1,2)[2],clustering_method="ward.D",main="Nedis",docluster=TRUE){
+  adjmat <- cross_comp_to_matrix(measure = netdislist$netdis[whatrow,], cross_comparison_spec = netdislist$comp_spec)
+  vnames <- rownames(adjmat)
+
+  legend1 <- seq(min(adjmat),max(adjmat),length.out = 5)
+  levels1 <- round(legend1,digits = 2)
+  pheatmap::pheatmap(mat = as.dist(adjmat),cluster_rows = docluster,cluster_cols = docluster,clustering_method = clustering_method,angle_col=45,main = main,treeheight_row = 80,labels_row = vnames,labels_col = vnames,display_numbers = TRUE,legend_breaks = legend1,legend_labels = levels1)
+}
+
+
+
+
+#' Heatmap of NetEmd many-to-many comparisons
+#'
+#' Provides a heatmap and dendrogram for the network comparisons via \code{pheatmap}.
+#' 
+#' @param netdislist Default output of \code{netdis_many_to_many}.
+#'
+#' @param whatrow Selection of the row in \code{netdis_many_to_many$comp_spec} to be used for plotting.
+#'
+#' @param clustering_method Clustering method as allowed in the \code{pheatmap} function from the \code{pheatmap} package. The dendrogram will appear if \code{docluster} is TRUE (default).
+#'
+#' @param main Title of the plot.
+#' 
+#' @param docluster controls the order of the rows and columns. If TRUE (default) the rows and columns will be reordered to create the dendrogram. If FALSE, then only the heatmap is drawn.
+#' 
+#' @return Provides a heat map and dendrogram for the network comparisons via \code{pheatmap}.
+#' @export
+
+netemd.plot <- function(netemdlist,clustering_method="ward.D",main="NetEmd",docluster=TRUE){
+  adjmat <- cross_comp_to_matrix(measure = netemdlist$netemds, cross_comparison_spec = netemdlist$comp_spec)
+  vnames <- rownames(adjmat)
+
+  legend1 <- seq(min(adjmat),max(adjmat),length.out = 5)
+  levels1 <- round(legend1,digits = 2)
+  pheatmap::pheatmap(mat = as.dist(adjmat),cluster_rows = docluster,cluster_cols = docluster,clustering_method = clustering_method,angle_col=45,main = main,treeheight_row = 80,labels_row = vnames,labels_col = vnames,display_numbers = TRUE,legend_breaks = legend1,legend_labels = levels1)
+
+}

R/RcppExports.R

@@ -29,16 +29,6 @@ emd_fast_no_smoothing <- function(locations1, values1, locations2, values2) {
 #' Compute EMD
 NULL
 
-#'
-#' @export
-NetEmdSmooth <- function(loc1, val1, binWidth1, loc2, val2, binWidth2) {
-    .Call(`_netdist_NetEmdSmooth`, loc1, val1, binWidth1, loc2, val2, binWidth2)
-}
-
-#' @title
-#' Compute EMD
-NULL
-
 #'
 #' @export
 NetEmdSmoothV2 <- function(loc1, val1, binWidth1, loc2, val2, binWidth2) {

R/data.R

@@ -1,8 +1,8 @@
 #' Protein-protein interaction (PPI) networks for 5 microorganisms
 #'
-#' A dataset containing the protein-protein interaction networks for the 
+#' A dataset containing the protein-protein interaction networks for the
 #' following 5 microorganisms
-#'\itemize{
+#' \itemize{
 #'  \item EBV
 #'    \itemize{
 #'      \item Common name: Epstein Barr virus
@@ -33,11 +33,32 @@
 #'      \item Scientific name: Human alphaherpesvirus 3
 #'      \item TaxonomyID: 10335
 #'    }
-#'}
+#' }
 #'
 #' @format A list of \code{igraph} objects.
 #' @source \strong{PPI data (EBV, HSV-1, KSHV, VZV):} Fossum E, Friedel CC, Rajagopala SV, Titz B, Baiker A, Schmidt T, et al. (2009) Evolutionarily Conserved Herpesviral Protein Interaction Networks. PLoS Pathog 5(9): e1000570. \url{https://doi.org/10.1371/journal.ppat.1000570}. Data from Table S2 in the supporting information.
 #' @source \strong{PPI data (ECL):} Peregrín-Alvarez JM, Xiong X, Su C, Parkinson J (2009) The Modular Organization of Protein Interactions in Escherichia coli. PLoS Comput Biol 5(10): e1000523. \url{https://doi.org/10.1371/journal.pcbi.1000523}
 #' @source \strong{Taxonomy ground truth:} NCBI taxonomy database. \url{https://www.ncbi.nlm.nih.gov/taxonomy}
 #' @encoding UTF-8
-"virusppi"
+"virusppi"
+
+
+
+
+
+#' World trade networks from 1985–2014
+#' 
+#' The world trade data set consists of a small sample of world trade networks for the years 2001-2014, and pre-computed subgraph counts of a larger set of world trade networks (1985–2014). The world trade networks are based on the data set from [Feenstra et al., 2005] for the years 1962- 2000 and on the United Nations division COMTRADE [Division, 2015] for the years 2001-2014.
+#'
+#' \itemize{
+#'  \item wtnets:  List of \code{igraph} objects providing the world trade networks from 2001–2014.
+#'  \item Counts:  Pre-computed graphlet counts for the world trade networks in the years 1985-2014.
+#'  }
+#'  
+#' @format A list of two elements. The first element, 'wtnets', is a list of \code{igraph} objects providing a small sample of world trade networks from 2001–2014. The second element, 'Counts', is a list of pre-computed subgraph counts of world trade networks in the years 1985-2014.
+#' @source \strong{World trade networks:}. United nations commodity trade statistics database (UN comtrade). http://comtrade.un.org/, 2015.
+#' @source \strong{Subgraph Counts:} Feenstra RC,Lipsey RE, Deng H, Ma AC, and Mo H. (2005) World trade flows: 1962-2000. Technical report, National Bureau of Economic Research. (See also https://cid.econ.ucdavis.edu/wix.html).
+#' 
+#' @encoding UTF-8
+"worldtradesub"
+