Implement block_sizes argument for undirected SBMs

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

@@ -8,9 +8,10 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
 
-name: R-CMD-check
+name: R-CMD-check.yaml
+
+permissions: read-all
 
 jobs:
   R-CMD-check:
@@ -25,22 +26,22 @@ jobs:
           - {os: macos-latest,   r: 'release'}
 
           - {os: windows-latest, r: 'release'}
-          # use 4.1 to check with rtools40's older compiler
-          - {os: windows-latest, r: '4.1'}
+          # use 4.0 or 4.1 to check with rtools40's older compiler
+          - {os: windows-latest, r: 'oldrel-4'}
 
-          - {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-2'}
-          - {os: ubuntu-latest,   r: 'oldrel-3'}
-          - {os: ubuntu-latest,   r: 'oldrel-4'}
+          - {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-2'}
+          - {os: ubuntu-latest,  r: 'oldrel-3'}
+          - {os: ubuntu-latest,  r: 'oldrel-4'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
       R_KEEP_PKG_SOURCE: yes
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-pandoc@v2
 
@@ -58,3 +59,4 @@ jobs:
       - uses: r-lib/actions/check-r-package@v2
         with:
           upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'

.github/workflows/pkgdown.yaml

@@ -4,12 +4,13 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
   release:
     types: [published]
   workflow_dispatch:
 
-name: pkgdown
+name: pkgdown.yaml
+
+permissions: read-all
 
 jobs:
   pkgdown:
@@ -22,7 +23,7 @@ jobs:
     permissions:
       contents: write
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-pandoc@v2
 
@@ -41,7 +42,7 @@ jobs:
 
       - name: Deploy to GitHub pages 🚀
         if: github.event_name != 'pull_request'
-        uses: JamesIves/github-pages-deploy-action@v4.4.1
+        uses: JamesIves/github-pages-deploy-action@v4.5.0
         with:
           clean: false
           branch: gh-pages

.github/workflows/pr-commands.yaml

@@ -4,7 +4,9 @@ on:
   issue_comment:
     types: [created]
 
-name: Commands
+name: pr-commands.yaml
+
+permissions: read-all
 
 jobs:
   document:
@@ -13,8 +15,10 @@ jobs:
     runs-on: ubuntu-latest
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/pr-fetch@v2
         with:
@@ -50,8 +54,10 @@ jobs:
     runs-on: ubuntu-latest
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/pr-fetch@v2
         with:

.github/workflows/test-coverage.yaml

@@ -4,9 +4,10 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
 
-name: test-coverage
+name: test-coverage.yaml
+
+permissions: read-all
 
 jobs:
   test-coverage:
@@ -15,36 +16,47 @@ jobs:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-r@v2
         with:
           use-public-rspm: true
 
       - uses: r-lib/actions/setup-r-dependencies@v2
         with:
-          extra-packages: any::covr
+          extra-packages: any::covr, any::xml2
           needs: coverage
 
       - name: Test coverage
         run: |
-          covr::codecov(
+          cov <- covr::package_coverage(
             quiet = FALSE,
             clean = FALSE,
-            install_path = file.path(Sys.getenv("RUNNER_TEMP"), "package")
+            install_path = file.path(normalizePath(Sys.getenv("RUNNER_TEMP"), winslash = "/"), "package")
           )
+          print(cov)
+          covr::to_cobertura(cov)
         shell: Rscript {0}
 
+      - uses: codecov/codecov-action@v5
+        with:
+          # Fail if error if not on PR, or if on PR and token is given
+          fail_ci_if_error: ${{ github.event_name != 'pull_request' || secrets.CODECOV_TOKEN }}
+          files: ./cobertura.xml
+          plugins: noop
+          disable_search: true
+          token: ${{ secrets.CODECOV_TOKEN }}
+
       - name: Show testthat output
         if: always()
         run: |
           ## --------------------------------------------------------------------
-          find ${{ runner.temp }}/package -name 'testthat.Rout*' -exec cat '{}' \; || true
+          find '${{ runner.temp }}/package' -name 'testthat.Rout*' -exec cat '{}' \; || true
         shell: bash
 
       - name: Upload test results
         if: failure()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: coverage-test-failures
           path: ${{ runner.temp }}/package

NEWS.md

@@ -1,5 +1,9 @@
 # fastRG (development version)
 
+- Added option to specify precise number of nodes in each block of a `dcsbm()` or `sbm()` via the `block_sizes` argument. This makes it easier to construct blockmodels with exactly repeated eigenvalues.
+- The default behavior of `dcsbm()`, `sbm()` and `planted_partition()` has changed: when `block_sizes` or `pi` is unspecified, the new default is to balance block sizes as evenly as possible. Previously, `pi` was set to a constant vector, balancing block sizes in expectation only.
+- Specifying both `k` and `B` in `dcsbm()` and `sbm()` now results in an error; only specify one of these arguments.
+
 # fastRG 0.3.3
 
 - Improve cross-linking to documentation of other packages for CRAN

R/expected-degrees.R

@@ -25,7 +25,7 @@
 #'
 #' B <- matrix(c(a, b, b, a), nrow = 2)
 #'
-#' b_model <- sbm(n = n, k = 2, B = B, poisson_edges = FALSE)
+#' b_model <- sbm(n = n, B = B, poisson_edges = FALSE)
 #'
 #' b_model
 #'

R/undirected_dcsbm.R

@@ -110,11 +110,19 @@ validate_undirected_dcsbm <- function(x) {
 #'   symmetrized via the update `B := B + t(B)`. Defaults to `NULL`.
 #'   You must specify either `k` or `B`, but not both.
 #'
-#' @param pi (relative block probabilities) Relative block
+#' @param block_sizes (block sizes) Number of nodes in each block,
+#'   as a vector of integers. Must match the dimensions of `B`, or `k` and
+#'   must sum to `n`. Defaults to `NULL`, in which case blocks are made
+#'   to be as balanced as possible. You can specify either `pi` or
+#'   `block_sizes`, but not both.
+#'
+#' @param pi (block sizes) Relative block
 #'   probabilities. Must be positive, but do not need to sum
 #'   to one, as they will be normalized internally.
-#'   Must match the dimensions of `B` or `k`. Defaults to
-#'   `rep(1 / k, k)`, or a balanced blocks.
+#'   Must match the dimensions of `B` or `k`. Defaults to `NULL`, in which
+#'   case the `block_sizes` argument will take precedence. Note that
+#'   you can specify either `pi` or `block_sizes`, but should not
+#'   specify both.
 #'
 #' @param sort_nodes Logical indicating whether or not to sort the nodes
 #'   so that they are grouped by block and by `theta`. Useful for plotting.
@@ -239,18 +247,31 @@ validate_undirected_dcsbm <- function(x) {
 #' edgelist <- sample_edgelist(custom_dcsbm)
 #' edgelist
 #'
+#'
+#' dcsbm_explicit_block_sizes <- dcsbm(
+#'   theta = rexp(100, 1 / 3) + 1,
+#'   B = B,
+#'   block_sizes = c(13, 17, 40, 14, 16),
+#'   expected_degree = 5
+#' )
+#'
+#' # respects block sizes
+#' summary(dcsbm_explicit_block_sizes$z)
+#'
 #' # efficient eigendecompostion that leverages low-rank structure in
 #' # E(A) so that you don't have to form E(A) to find eigenvectors,
 #' # as E(A) is typically dense. computation is
 #' # handled via RSpectra
 #'
 #' population_eigs <- eigs_sym(custom_dcsbm)
 #'
+#'
 dcsbm <- function(
     n = NULL, theta = NULL,
     k = NULL, B = NULL,
     ...,
-    pi = rep(1 / k, k),
+    block_sizes = NULL,
+    pi = NULL,
     sort_nodes = TRUE,
     force_identifiability = FALSE,
     poisson_edges = TRUE,
@@ -273,6 +294,8 @@ dcsbm <- function(
     theta <- stats::rlnorm(n, meanlog = 2, sdlog = 1)
   } else if (is.null(n)) {
     n <- length(theta)
+  } else {
+    stop("Must specify only one of `n` and `theta`, not both.", call. = FALSE)
   }
 
   ### mixing matrix
@@ -297,18 +320,59 @@ dcsbm <- function(
     }
 
     k <- nrow(B)
+  } else {
+    stop("Must specify only one of `B` and `k`, not both.", call. = FALSE)
   }
 
   ### block membership
 
-  if (length(pi) != nrow(B) || length(pi) != ncol(B)) {
-    stop("Length of `pi` must match dimensions of `B`.", call. = FALSE)
-  }
+  if (is.null(block_sizes) && is.null(pi)) {
+
+    base_value <- floor(n / k)
+    remainder <- n %% k
+    num_base_values <- k - remainder
+
+    upper_values <- rep(base_value + 1, remainder)
+    base_values <- rep(base_value, num_base_values)
+
+    block_sizes <- c(upper_values, base_values)
+
+    z <- sample(rep(1:k, times = block_sizes))
+
+    # for sorting by block size later
+    pi <- block_sizes / n
+  } else if (!is.null(block_sizes)) {
+
+    if(sum(block_sizes) != n) {
+      stop("Sum of `block_sizes` must equal `n` or `length(theta)`.", call. = FALSE)
+    }
+
+    z <- sample(rep(1:k, times = block_sizes))
+
+    # for sorting by block size later
+    pi <- block_sizes / n
+
+  } else if (!is.null(pi)) {
+    if (!is.null(pi) && !is.null(block_sizes)) {
+      stop("Length of `pi` must match dimensions of `B`.", call. = FALSE)
+    }
+
+    if (length(pi) != nrow(B) || length(pi) != ncol(B)) {
+      stop("Length of `pi` must match dimensions of `B`.", call. = FALSE)
+    }
+
+    if (any(pi < 0)) {
+      stop("All elements of `pi` must be >= 0.", call. = FALSE)
+    }
+
 
-  if (any(pi < 0)) {
-    stop("All elements of `pi` must be >= 0.", call. = FALSE)
+    z <- sample(k, n, replace = TRUE, prob = pi)
+  } else {
+    stop("Must at most one of `block_sizes` and `pi`.", call. = FALSE)
   }
 
+  z <- factor(z, levels = 1:k, labels = paste0("block", 1:k))
+
   # order mixing matrix by expected group size
 
   if (k > 1 && sort_nodes) {
@@ -319,11 +383,6 @@ dcsbm <- function(
 
   pi <- pi / sum(pi)
 
-  # sample block memberships
-
-  z <- sample(k, n, replace = TRUE, prob = pi)
-  z <- factor(z, levels = 1:k, labels = paste0("block", 1:k))
-
   if (sort_nodes) {
     z <- sort(z)
   }

R/undirected_planted_partition.R

@@ -127,7 +127,8 @@ planted_partition <- function(
     between_block = NULL,
     a = NULL,
     b = NULL,
-    pi = rep(1 / k, k),
+    block_sizes = NULL,
+    pi = NULL,
     sort_nodes = TRUE,
     poisson_edges = TRUE,
     allow_self_loops = TRUE) {
@@ -144,9 +145,10 @@ planted_partition <- function(
 
   pp <- sbm(
     n = n,
-    k = k,
+    k = NULL, # implicit in dimensions of B
     B = B,
     ...,
+    block_sizes = block_sizes,
     pi = pi,
     sort_nodes = sort_nodes,
     poisson_edges = poisson_edges,