Verified example runs successfully and all tests pass

Co-authored-by: osorensen <21175639+osorensen@users.noreply.github.com>

Author: Copilot

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/DESCRIPTION

@@ -0,0 +1,29 @@
+Package: BayesMallowsSMC2
+Type: Package
+Title: Nested Sequential Monte Carlo for the Bayesian Mallows Model
+Version: 0.1.1
+Authors@R: c(person("Oystein", "Sorensen",
+                    email = "oystein.sorensen.1985@gmail.com",
+                    role = c("aut", "cre"),
+                    comment = c(ORCID = "0000-0003-0724-3542")))
+Maintainer: Oystein Sorensen <oystein.sorensen.1985@gmail.com>
+Description: Provides nested sequential Monte Carlo algorithms for performing
+    sequential inference in the Bayesian Mallows model, which is a widely used
+    probability model for rank and preference data. The package implements the
+    SMC² (Sequential Monte Carlo Squared) algorithm for handling sequentially
+    arriving rankings and pairwise preferences, including support for complete
+    rankings, partial rankings, and pairwise comparisons. The methods are based
+    on Sørensen (2025) <doi:10.1214/25-BA1564>.
+License: GPL-3
+Encoding: UTF-8
+LazyData: true
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 7.3.2
+LinkingTo: Rcpp, RcppArmadillo
+Imports: Rcpp
+Depends: R (>= 4.1.0)
+Suggests: testthat (>= 3.0.0), label.switching (>= 1.8)
+Config/testthat/edition: 3
+NeedsCompilation: yes
+Packaged: 2026-01-21 09:58:44 UTC; runner
+Author: Oystein Sorensen [aut, cre] (<https://orcid.org/0000-0003-0724-3542>)

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/NAMESPACE

@@ -0,0 +1,8 @@
+# Generated by roxygen2: do not edit by hand
+
+export(compute_sequentially)
+export(precompute_topological_sorts)
+export(set_hyperparameters)
+export(set_smc_options)
+importFrom(Rcpp,sourceCpp)
+useDynLib(BayesMallowsSMC2, .registration = TRUE)

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/R/BayesMallowsSMC2-package.R

@@ -0,0 +1,9 @@
+## usethis namespace: start
+#' @importFrom Rcpp sourceCpp
+## usethis namespace: end
+NULL
+
+## usethis namespace: start
+#' @useDynLib BayesMallowsSMC2, .registration = TRUE
+## usethis namespace: end
+NULL

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/R/RcppExports.R

@@ -0,0 +1,57 @@
+# Generated by using Rcpp::compileAttributes() -> do not edit by hand
+# Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
+
+#' Precompute All Topological Sorts
+#'
+#' This function precomputes all topological sorts for a given preference matrix and
+#' saves them to a specified output directory. It ensures the output directory exists
+#' and creates it if it does not.
+#'
+#' @param prefs A matrix representing the preference relations. This matrix
+#'   must have two columns, the first of which represents the preferred item
+#'   and the second of which represents the disfavored item.
+#' @param n_items An integer specifying the number of items to sort.
+#' @param save_frac Number between 0 and 1 specifying which fraction of sorts to save.
+#'
+#' @details
+#' The function generates all possible topological sorts for the provided preference matrix
+#' and saves approximately `save_frac` of the sorts in a matrix which is returned.
+#'
+#' @return This function returns the number of topological sorts.
+#'
+#' @export
+#' @examples
+#' # Extract preferences from user 1 in the included example data.
+#' prefs <- pairwise_preferences[
+#'  pairwise_preferences$user == 1, c("top_item", "bottom_item"), drop = FALSE]
+#'
+#' # Generate all topological sorts, but don't save them:
+#' sorts <- precompute_topological_sorts(
+#'   prefs = as.matrix(prefs),
+#'   n_items = 5,
+#'   save_frac = 0
+#' )
+#' # Number of sorts
+#' sorts$sort_count
+#' # Empty matrix
+#' sorts$sort_matrix
+#'
+#' # Generate all topological sorts and save them:
+#' sorts <- precompute_topological_sorts(
+#'   prefs = as.matrix(prefs),
+#'   n_items = 5,
+#'   save_frac = 1
+#' )
+#' # Number of sorts
+#' sorts$sort_count
+#' # Matrix with all of them
+#' sorts$sort_matrix
+#'
+precompute_topological_sorts <- function(prefs, n_items, save_frac) {
+    .Call(`_BayesMallowsSMC2_precompute_topological_sorts`, prefs, n_items, save_frac)
+}
+
+run_smc <- function(input_timeseries, input_prior, input_options, input_sort_matrices, input_sort_counts) {
+    .Call(`_BayesMallowsSMC2_run_smc`, input_timeseries, input_prior, input_options, input_sort_matrices, input_sort_counts)
+}
+

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/R/compute_sequentially.R

@@ -0,0 +1,94 @@
+#' Compute the Bayesian Mallows model sequentially
+#'
+#'
+#' @param data A dataframe containing partial rankings or pairwise preferences.
+#'   If `data` contains complete or partial rankings, it must have the following
+#'   columns:
+#'
+#' \itemize{
+#' \item `timepoint`: a numeric vector denoting the timepoint, starting at 1.
+#' \item `user`: a vector identifying the user.
+#' \item `item1`: ranking of item 1.
+#' \item `item2`: ranking of item 2.
+#' \item etc.
+#' }
+#'
+#'   If data contains pairwise preferences, it must have the following
+#'   structure:
+#'
+#' \itemize{
+#' \item `timepoint`: a numeric vector denoting the timepoint, starting at 1.
+#' \item `user`: a vector identifying the user.
+#' \item `top_item`: identifier for the preferred item.
+#' \item `bottom_item`: identifier for the dispreferred item.
+#' }
+#'
+#' @param hyperparameters A list returned from [set_hyperparameters()].
+#' @param smc_options A list returned from [set_smc_options()]
+#' @param topological_sorts A list returned from
+#'   [precompute_topological_sorts()]. Only used with preference data, and
+#'   defaults to `NULL`.
+#'
+#' @return An object of class BayesMallowsSMC2.
+#' @export
+#'
+#' @examples
+#' # Compute the model sequentially with complete rankings
+#' mod <- compute_sequentially(
+#'   complete_rankings,
+#'   hyperparameters = set_hyperparameters(n_items = 5),
+#'   smc_options = set_smc_options(n_particles = 100, n_particle_filters = 1)
+#' )
+#'
+compute_sequentially <- function(
+    data,
+    hyperparameters = set_hyperparameters(),
+    smc_options = set_smc_options(),
+    topological_sorts = NULL
+    ){
+  rank_columns <- grepl("item[0-9]+", colnames(data))
+  preference_columns <- grepl("top\\_item|bottom\\_item", colnames(data))
+
+  if(any(rank_columns)) {
+    input_timeseries <- split(data, f = ~ timepoint) |>
+      lapply(split, f = ~ user) |>
+      lapply(function(x) lapply(x, function(y) as.numeric(y[rank_columns])))
+
+    if(any(is.na(data[rank_columns]))) {
+      attr(input_timeseries, "type") <- "partial rankings"
+    } else {
+      attr(input_timeseries, "type") <- "complete rankings"
+    }
+    sort_matrices <- sort_counts <- list()
+  } else if(sum(preference_columns) == 2) {
+    if(is.null(topological_sorts)) {
+      stop("topological_sorts must be provided with preference data.")
+    }
+    input_timeseries <- split(data, f = ~ timepoint) |>
+      lapply(split, f = ~ user) |>
+      lapply(function(x) lapply(x, function(y) as.matrix(y[preference_columns])))
+    attr(input_timeseries, "type") <- "pairwise preferences"
+
+    sort_matrices <- lapply(topological_sorts, function(x) {
+      lapply(x, function(y) y$sort_matrix)
+    })
+
+    sort_counts <- lapply(topological_sorts, function(x) {
+      lapply(x, function(y) y$sort_count)
+    })
+  } else {
+    stop("Something wrong with data")
+  }
+
+  if(max(table(data$user)) > 1 &&
+     attr(input_timeseries, "type") != "pairwise preferences") {
+    stop("Updated users not supported.")
+  }
+
+  ret <- run_smc(input_timeseries, hyperparameters, smc_options,
+                 sort_matrices, sort_counts)
+
+  class(ret) <- "BayesMallowsSMC2"
+  ret
+}
+

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/R/data.R

@@ -0,0 +1,44 @@
+#' Simulated Data
+#'
+#' @format ## `complete_rankings`
+#' A data frame with 100 rows and 7 columns:
+#' \describe{
+#'   \item{timepoint}{Timepoint}
+#'   \item{user}{User id}
+#'   \item{item1, item2, item3, item4, item5}{Ranking given to the item.}
+#' }
+"complete_rankings"
+
+#' Simulated Data with Missing Values
+#'
+#' @format ## `partial_rankings`
+#' A data frame with 100 rows and 7 columns:
+#' \describe{
+#'   \item{timepoint}{Timepoint}
+#'   \item{user}{User id}
+#'   \item{item1, item2, item3, item4, item5}{Ranking given to the item.}
+#' }
+"partial_rankings"
+
+#' Simulated Data with Pairwise Preferences
+#'
+#' @format ## `pairwise_preferences`
+#' A data frame with 400 rows and 4 columns:
+#' \describe{
+#'   \item{timepoint}{Timepoint}
+#'   \item{user}{User id}
+#'   \item{top_item}{Item preferred in the comparison.}
+#'   \item{bottom_item}{Item disfavored in the comparison.}
+#' }
+"pairwise_preferences"
+
+#' Simulated Two-Component Mixtures Data
+#'
+#' @format ## `mixtures`
+#' A data frame with 400 rows and 7 columns:
+#' \describe{
+#'   \item{timepoint}{Timepoint}
+#'   \item{user}{User id}
+#'   \item{item1, item2, item3, item4, item5}{Ranking given to the item.}
+#' }
+"mixtures"

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/R/set_hyperparameters.R

@@ -0,0 +1,17 @@
+#' Set hyperparameters
+#'
+#' @param n_items Integer defining the number of items.
+#' @param alpha_shape Shape of gamma prior for alpha.
+#' @param alpha_rate Rate of gamma prior for alpha.
+#' @param cluster_concentration Concentration parameter of Dirichlet distribution for cluster probabilities.
+#' @param n_clusters Integer defining the number of clusters.
+#'
+#' @return A list
+#' @export
+#'
+set_hyperparameters <- function(
+    n_items, alpha_shape = 1, alpha_rate = .5, cluster_concentration = 10,
+    n_clusters = 1) {
+  if(missing(n_items)) stop("n_items must be provided")
+  as.list(environment())
+}

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/R/set_smc_options.R

@@ -0,0 +1,34 @@
+#' Set SMC options
+#'
+#' @param n_particles Number of particles
+#' @param n_particle_filters Initial number of particle filters for each
+#'   particle
+#' @param max_particle_filters Maximum number of particle filters.
+#' @param resampling_threshold Effective sample size threshold for resampling
+#' @param doubling_threshold Threshold for particle filter doubling. If the
+#'   acceptance rate of the rejuvenation step falls below this threshold, the
+#'   number of particle filters is doubled. Defaults to 0.2.
+#' @param max_rejuvenation_steps Maximum number of rejuvenation steps. If the
+#'   number of unique particles has not exceeded half the number of particles
+#'   after this many steps, the rejuvenation is still stopped.
+#' @param metric Metric
+#' @param resampler resampler
+#' @param latent_rank_proposal latent rank proposal
+#' @param verbose Boolean
+#' @param trace Logical specifying whether to save static parameters at each
+#'   timestep.
+#' @param trace_latent Logical specifying whether to sample and save one
+#'   complete set of latent rankings for each particle and each timepoint.
+#'
+#' @return A list
+#' @export
+#'
+set_smc_options <- function(
+    n_particles = 1000, n_particle_filters = 50, max_particle_filters = 10000,
+    resampling_threshold = n_particles / 2, doubling_threshold = .2,
+    max_rejuvenation_steps = 20,
+    metric = "footrule", resampler = "multinomial",
+    latent_rank_proposal = "uniform", verbose = FALSE,
+    trace = FALSE, trace_latent = FALSE) {
+  as.list(environment())
+}

BayesMallowsSMC2.Rcheck/00_pkg_src/BayesMallowsSMC2/README.md

@@ -0,0 +1,28 @@
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+# BayesMallowsSMC2
+
+<!-- badges: start -->
+
+[![R-CMD-check](https://github.com/osorensen/BayesMallowsSMC2/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/osorensen/BayesMallowsSMC2/actions/workflows/R-CMD-check.yaml)
+<!-- badges: end -->
+
+BayesMallowsSMC2 provides functions for performing sequential inference
+in the Bayesian Mallows model using the SMC$^{2}$ algorithm.
+
+## Installation
+
+You can install the development version of BayesMallowsSMC2 from
+[GitHub](https://github.com/) with:
+
+``` r
+# install.packages("devtools")
+devtools::install_github("osorensen/BayesMallowsSMC2")
+```
+
+## Usage
+
+This package is under development, and is not yet well documented. For
+examples on how to use it, see the code in the OSF repository
+<https://osf.io/pquk4/>.