first package commit

everything is new!

.Rbuildignore

@@ -0,0 +1,9 @@
+^.*\.Rproj$
+^\.Rproj\.user$
+^LICENSE\.md$
+^README\.Rmd$
+^\.github$
+^cran-comments\.md$
+^\.travis\.yml$
+^CRAN-SUBMISSION$
+^codecov\.yml$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

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

@@ -0,0 +1,49 @@
+# 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]
+
+name: R-CMD-check
+
+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@v3
+
+      - 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
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true

.gitignore

@@ -0,0 +1,7 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
+src/*.o
+src/*.so
+src/*.dll

DESCRIPTION

@@ -0,0 +1,17 @@
+Package: SANple
+Type: Package
+Title: Fitting Common and Shared Atoms Nested Models via MCMC
+Version: 0.0.1
+Date: 2023-09-09
+Author: Laura D'Angelo and Francesco Denti
+Maintainer: Laura D'Angelo <laura.dangelo@live.com>
+Description: An R package for estimating Bayesian nested mixture models via MCMC methods. Specifically, the package implements the common atoms model (Denti et al., 2023), its finite version (D'Angelo et al., 2023), and a hybrid finite-infinite model. All models use Gaussian mixtures with a normal-inverse-gamma prior distribution on the parameters. Additional functions are provided to help analyzing the results of the fitting procedure.
+License: MIT + file LICENSE
+Imports: 
+    Rcpp, RcppArmadillo, salso
+Depends:
+    scales, RColorBrewer
+LinkingTo: 
+    Rcpp, RcppArmadillo, RcppProgress
+RoxygenNote: 7.2.3
+Encoding: UTF-8

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2023
+COPYRIGHT HOLDER: SANple authors

LICENSE.md

@@ -0,0 +1,21 @@
+# MIT License
+
+Copyright (c) 2023 SANple authors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

NAMESPACE

@@ -0,0 +1,33 @@
+# Generated by roxygen2: do not edit by hand
+
+S3method(plot,SANmcmc)
+S3method(print,SANclusters)
+S3method(print,SANmcmc)
+export(estimate_clusters)
+export(sample_CAM)
+export(sample_fSAN)
+export(sample_fSAN_sparsemix)
+export(sample_fiSAN)
+export(sample_fiSAN_sparsemix)
+export(traceplot)
+import(Rcpp)
+import(RcppArmadillo)
+importFrom(RColorBrewer,brewer.pal)
+importFrom(grDevices,colorRampPalette)
+importFrom(grDevices,devAskNewPage)
+importFrom(graphics,abline)
+importFrom(graphics,boxplot)
+importFrom(graphics,lines)
+importFrom(graphics,par)
+importFrom(graphics,points)
+importFrom(salso,salso)
+importFrom(scales,alpha)
+importFrom(stats,cor)
+importFrom(stats,cutree)
+importFrom(stats,density)
+importFrom(stats,dist)
+importFrom(stats,ecdf)
+importFrom(stats,hclust)
+importFrom(stats,rgamma)
+importFrom(stats,var)
+useDynLib(SANple)

R/RcppExports.R

@@ -0,0 +1,23 @@
+# Generated by using Rcpp::compileAttributes() -> do not edit by hand
+# Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
+
+sample_cam_arma <- function(nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta1, hyp_beta2, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, progressbar) {
+    .Call('_SANple_sample_cam_arma', PACKAGE = 'SANple', nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta1, hyp_beta2, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, progressbar)
+}
+
+sample_fcam_arma <- function(nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta1, hyp_beta2, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_alpha, eps_beta, progressbar) {
+    .Call('_SANple_sample_fcam_arma', PACKAGE = 'SANple', nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta1, hyp_beta2, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_alpha, eps_beta, progressbar)
+}
+
+sample_ficam_arma <- function(nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta1, hyp_beta2, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_beta, progressbar) {
+    .Call('_SANple_sample_ficam_arma', PACKAGE = 'SANple', nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta1, hyp_beta2, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_beta, progressbar)
+}
+
+sample_overcam_arma <- function(nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha, hyp_beta, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_alpha, eps_beta, progressbar) {
+    .Call('_SANple_sample_overcam_arma', PACKAGE = 'SANple', nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha, hyp_beta, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_alpha, eps_beta, progressbar)
+}
+
+sample_overficam_arma <- function(nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_beta, progressbar) {
+    .Call('_SANple_sample_overficam_arma', PACKAGE = 'SANple', nrep, y, group, maxK, maxL, m0, tau0, lambda0, gamma0, fixed_alpha, fixed_beta, alpha, beta, hyp_alpha1, hyp_alpha2, hyp_beta, mu_start, sigma2_start, M_start, S_start, alpha_start, beta_start, eps_beta, progressbar)
+}
+

R/estimate_clusters.R

@@ -0,0 +1,65 @@
+
+#' Estimate observational and distributional clusters
+#' @description Given the MCMC output, estimate the observational and distributional partitions using \code{\link[salso:salso]{salso::salso()}}.
+#'
+#' @param object object of class \code{SANmcmc} (the result of a call to \code{\link{sample_fiSAN}}, \code{\link{sample_fiSAN_sparsemix}}, 
+#' \code{\link{sample_fSAN}}, \code{\link{sample_fSAN_sparsemix}}, or \code{\link{sample_CAM}}).
+#' @param burnin the length of the burn-in to be discarded before estimating the clusters (default is 2/3 of the iterations).
+#' @param ncores the number of CPU cores to use, i.e., the number of simultaneous runs at any given time. A value of zero indicates to use all cores on the system.
+#'
+#' @return Object of class \code{SANclusters}. The object contains:
+#' @returns \code{est_oc} estimated partition at the observational level. It is an object of class \code{salso.estimate}.
+#' @returns \code{est_dc} estimated partition at the distributional level. It is an object of class \code{salso.estimate}.
+#' @returns \code{clus_means} cluster-specific sample means of the estimated partition.
+#' @returns \code{clus_vars} cluster-specific sample variances of the estimated partition.
+#' 
+#' @seealso \code{\link[salso:salso]{salso::salso()}}, \code{\link{print.SANmcmc}}, \code{\link{plot.SANmcmc}}, \code{\link{print.SANclusters}}
+#'
+#' @examples 
+#' set.seed(123)
+#' y <- c(rnorm(170),rnorm(70,5))
+#' g <- c(rep(1,100), rep(2, 140))
+#' out <- sample_fiSAN(nrep = 3000, y = y, group = g, beta = 1)
+#' estcl <- estimate_clusters(out)
+#' estcl
+#'
+#'
+#' @export
+#' @importFrom salso salso
+#' @useDynLib SANple
+estimate_clusters = function(object, burnin = NULL, ncores = 0)
+{
+
+  if(is.null(burnin)) { burnin = 1:round(object$params$nrep/3*2) }
+  estimated_oc =  suppressWarnings(salso::salso(object$sim$obs_cluster[-burnin,], nCores = ncores)) 
+  estimated_dc =  suppressWarnings(salso::salso(object$sim$distr_cluster[-burnin,], nCores = ncores))
+
+  n_oc = length(unique(estimated_oc))
+  n_dc = length(unique(estimated_dc))
+
+  means = matrix(NA, n_oc, n_dc)
+  vars = matrix(NA, n_oc, n_dc)
+
+  dc_long = estimated_dc[object$params$group]
+
+  for(j in 1:n_dc) {
+
+    suby = object$params$y[dc_long == j]
+    subcl = estimated_oc[dc_long == j]
+
+    for(k in unique(subcl)) {
+      means[k,j] = mean(suby[(subcl == k)]) 
+      if(length(suby[subcl == k])>1) {
+        vars[k,j] = var(suby[subcl == k]) }
+    }
+  }
+
+
+
+  out = (list("est_oc" = estimated_oc,
+              "est_dc" = estimated_dc,
+              "clus_means" = means,
+              "clus_vars" = vars))
+
+  structure(out, class = c("SANclusters", class(out)))
+}