Add new datasets namibia_data and regional_allele_frequencies. Update…

… vignette with code to use the new datasets. (#27)

Add new datasets namibia_data and regional_allele_frequencies. Update vignette with code to use the new datasets.

- Added new datasets namibia_data and regional_allele_frequencies.
- Updated vignette with code to use the new datasets.

.lintr

@@ -1,5 +1,4 @@
 linters: linters_with_defaults(
     line_length_linter(120),
-    indentation_linter(2)
-) 
+    indentation_linter(2)) 
 encoding: "UTF-8"

DESCRIPTION

@@ -33,7 +33,7 @@ Imports:
     stats,
     purrr,
     rlang,
-    ggplot2,
+    ggplot2
 URL: https://github.com/EPPIcenter/moire, https://eppicenter.github.io/moire/, https://eppicenter.ucsf.edu/resources
 BugReports: https://github.com/EPPIcenter/moire/issues
 Roxygen: list(markdown = TRUE)
@@ -43,7 +43,8 @@ Suggests:
     rmarkdown,
     markdown,
     forcats,
-    testthat (>= 3.0.0)
+    testthat (>= 3.0.0),
+    parallelly
 VignetteBuilder: knitr
 Depends: 
     R (>= 4.0.0)

R/data.R

@@ -7,3 +7,28 @@
 #' MCMC results from using the packaged simulated data and calling `run_mcmc()`
 #'
 "mcmc_results"
+
+#' Genetic and epidemiological data from Namibia
+#'
+#' A dataset containing the genetic and epidemiological data from Namibia
+#'
+#' @format A data frame with 8 columns and 2585 rows:
+#' \describe{
+#'   \item{sample_id}{Sample ID}
+#'   \item{HealthFacility}{Health facility}
+#'   \item{HealthDistrict}{Health district}
+#'   \item{Region}{Region}
+#'   \item{Country}{Country}
+#'   \item{locus}{Locus}
+#'   \item{allele}{Allele}
+#' }
+#' @source \url{https://doi.org/10.7554/eLife.43510.018}
+"namibia_data"
+
+#' Allele frequencies for different regions
+#'
+#' A list of allele frequencies for different regions, estimated from the pf7k dataset.
+#'
+#' @format A list of lists, where each list element is a list of allele frequencies
+#' for a specific region.
+"regional_allele_frequencies"

_pkgdown.yml

@@ -39,5 +39,7 @@ reference:
 - contents:
   - simulated_data
   - mcmc_results
+  - namibia_data
+  - regional_allele_frequencies
 
 

data-raw/namibia_data.R

@@ -0,0 +1,7 @@
+namibia_data <- readxl::read_excel("data-raw/xls/elife-43510-supp1-v2.xlsx", skip = 1) |>
+  dplyr::rename(sample_id = ID) |>
+  tidyr::pivot_longer(cols = 6:31, names_to = "locus", values_to = "allele") |>
+  tidyr::separate_rows(allele, sep = ";") |>
+  tidyr::drop_na()
+
+usethis::use_data(namibia_data, overwrite = TRUE, compress = "xz")

src/Makevars

@@ -1,7 +1,12 @@
+ifdef ENABLE_GLIBCXX_DEBUG
+    PKG_CXXFLAGS+=-D_GLIBCXX_DEBUG
+endif
+
 ifdef ENABLE_PROFILER
-    PKG_LIBS +=-lprofiler
-    PKG_CXXFLAGS +=-DENABLE_PROFILER
+    PKG_LIBS+=-lprofiler
+    PKG_CXXFLAGS+=-DENABLE_PROFILER
 endif
-PKG_CXXFLAGS +=$(SHLIB_OPENMP_CXXFLAGS)
-PKG_LIBS +=$(SHLIB_OPENMP_CXXFLAGS)
-PKG_LIBS +=$(shell ${R_HOME}/bin/Rscript -e "RcppParallel::RcppParallelLibs()")
+
+PKG_CXXFLAGS+=$(SHLIB_OPENMP_CXXFLAGS)
+PKG_LIBS+=$(SHLIB_OPENMP_CXXFLAGS)
+PKG_LIBS+=$(shell ${R_HOME}/bin/Rscript -e "RcppParallel::RcppParallelLibs()")

vignettes/namibia.Rmd

@@ -5,6 +5,7 @@ vignette: >
   %\VignetteIndexEntry{Application to Namibia}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
+  %\VignetteDepends{parallelly, dplyr}
 ---
 
 ```{r setup, include=FALSE}
@@ -19,18 +20,10 @@ knitr::opts_chunk$set(
 The following code reproduces our analysis of data from Namibia as described in our paper. 
 
 ```{r namibia, eval=FALSE, include=TRUE}
-library(moire)
-library(readr)
-library(dplyr)
-
 # Download Nambia data from here https://doi.org/10.7554/eLife.43510.018
 # and save it as namibia_data.xlsx in the working directory
 
-full_dat <- readxl::read_excel("namibia_data.xlsx", skip = 1) |>
-  dplyr::rename(sample_id = ID) |>
-  tidyr::pivot_longer(cols = 6:31, names_to = "locus", values_to = "allele") |>
-  tidyr::separate_rows(allele, sep = ";") |>
-  tidyr::drop_na()
+full_dat <- moire::namibia_data
 
 epi_dat <- full_dat |>
   dplyr::select(sample_id, HealthFacility, HealthDistrict, Region, Country) |>
@@ -42,15 +35,15 @@ all_hfs <- epi_dat |>
 
 verbose <- F
 allow_relatedness <- TRUE
-burnin <- 5e3
-num_samples <- 1e4
+burnin <- 5e2
+num_samples <- 1e2
 r_alpha <- 1
 r_beta <- 1
 eps_pos_alpha <- 1
 eps_pos_beta <- 1
 eps_neg_alpha <- 1
 eps_neg_beta <- 1
-num_threads <- parallely::availableCores() - 1
+num_threads <- parallelly::availableCores() - 1
 
 for (hf in all_hfs) {
   hf_dat <- full_dat |>