Merge pull request #396 from bcgov/joss-paper

.Rbuildignore

@@ -21,5 +21,3 @@
 ^CRAN-SUBMISSION$
 ^CODE_OF_CONDUCT\.md$
 ^vignettes/articles$
-^doc$
-^Meta$

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

@@ -5,7 +5,7 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master, dev]
+    branches: [main, master]
 
 name: R-CMD-check
 

.github/workflows/paper.yaml

@@ -2,9 +2,9 @@
 
 on:
   push:
-    branches: [main]
+    branches: [main, joss-paper]
   pull_request:
-    branches: [main, dev]
+    branches: [main, joss-paper]
 
 name: paper
 

.github/workflows/test-coverage.yaml

@@ -4,7 +4,7 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master, dev]
+    branches: [main, master]
 
 name: test-coverage.yaml
 

.gitignore

@@ -10,12 +10,9 @@
 
 *.html
 
-/docs/
-/inst/docs/
-/paper/paper.pdf
-/scripts/boron_samples1
-/scripts/checks.md
+docs
+inst/docs
 inst/doc
-/ignore
-/doc/
-/Meta/
+scripts
+
+/paper/paper.pdf

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: ssdtools
 Title: Species Sensitivity Distributions
-Version: 2.1.0.9001
+Version: 2.2.0
 Authors@R: c(
     person("Joe", "Thorley", , "joe@poissonconsulting.ca", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-7683-4592")),
@@ -11,22 +11,24 @@ Authors@R: c(
     person("Seb", "Dalgarno", , "seb@poissonconsulting.ca", role = "ctb",
            comment = c(ORCID = "0000-0002-3658-4517")),
     person("Kathleen", "McTavish", role = "ctb"),
-    person("Heather", "Thompson", role = "ctb"),
+    person("Heather", "Thompson", role = "ctb"), 
     person("Doug", "Spry", role = "ctb"),
     person("Rick", "van Dam", role = "ctb"),
     person("Graham", "Batley", role = "ctb"),
-    person("Tony", "Bigwood", role = "ctb"),
     person("Ali", "Azizishirazi", role = "ctb"),
     person("Nadine", "Hussein", , "nadine@poissonconsulting.ca", role = "ctb",
            comment = c(ORCID = "0000-0003-4470-8361")),
     person("Sarah", "Lyons", , "sarah@poissonconsulting.ca", role = "ctb",
            comment = c(ORCID = "0000-0002-6745-6796")),
+    person("Duncan", "Kennedy", , "duncan@poissonconsulting.ca", role = "ctb",
+           comment = c(ORCID = "0009-0001-4880-5751")),
     person("Stephanie", "Hazlitt", role = "ctb"),
     person("Hadley", "Wickham", role = "ctb"),
     person("Sergio", "Ibarra Espinosa", role = "ctb"),
     person("Andy", "Teucher", role = "ctb"),
     person("Emilie", "Doussantousse", role = "ctb"),
     person("Nan-Hung", "Hsieh", role = "ctb"),
+    person("Florencia", "D'Andrea", role = "ctb"),
     person("Province of British Columbia", role = c("fnd", "cph")),
     person("Environment and Climate Change Canada", role = c("fnd", "cph")),
     person("Australian Government Department of Climate Change, Energy, the Environment and Water", role = c("fnd", "cph"))
@@ -38,8 +40,7 @@ Description: Species sensitivity distributions are cumulative probability
     fit distributions such as the gamma, log-logistic, log-normal and
     log-normal log-normal mixture. Multiple distributions can be averaged
     using Akaike Information Criteria.  Confidence intervals on hazard
-    concentrations and proportions are produced by parametric
-    bootstrapping.
+    concentrations and proportions are produced by bootstrapping.
 License: Apache License (== 2.0) | file LICENSE
 URL: https://github.com/bcgov/ssdtools, https://bcgov.github.io/ssdtools/
 BugReports: https://github.com/bcgov/ssdtools/issues
@@ -51,6 +52,7 @@ Imports:
     furrr,
     generics,
     ggplot2,
+    ggtext,
     glue,
     goftest,
     graphics,

NAMESPACE

@@ -75,6 +75,7 @@ export(ssd_data)
 export(ssd_dists)
 export(ssd_dists_all)
 export(ssd_dists_bcanz)
+export(ssd_dists_shiny)
 export(ssd_eburrIII3)
 export(ssd_ecd)
 export(ssd_ecd_data)
@@ -100,6 +101,7 @@ export(ssd_hp)
 export(ssd_hp_bcanz)
 export(ssd_is_censored)
 export(ssd_label_comma)
+export(ssd_label_comma_hc)
 export(ssd_licensing_md)
 export(ssd_match_moments)
 export(ssd_min_pmix)

NEWS.md

@@ -1,20 +1,23 @@
 <!-- NEWS.md is maintained by https://fledge.cynkra.com, contributors should not edit this file -->
 
-# ssdtools 2.1.0.9001
-
-- Fixed equation rendering for vignettes on website.
-- Corrected y-axis labels for bimodal plots in distributions vignette from Cumulative Probability to Probability Density.
-
-
-# ssdtools 2.1.0.9000
-
-- Same as previous version.
-
+# ssdtools 2.2.0
+
+- Added `ssd_label_comma_hc()` function to label numbers with significant digits and comma and offset hazard concentration value if present in breaks.
+- Added `ssd_dists_shiny()` to define distributions for use in shiny app.
+- For `plot_coord_scale()` function:
+  - Added `x_limits = NULL` to allow setting of x-axis limits.
+  - Added `hc_value = NULL` to pass hazard concentration value.
+  - Restricted `trans` argument to `"identity"`, `"log10"` or "`log`".
+- For `ssd_plot()` function:
+  - Added `text_size` argument.
+  - Added `theme_classic = FALSE` argument to switch classic theme.
+  - Soft-deprecated `size` argument for `label_size`.
+- Turned off x-axis minor breaks for all plots (for consistency) as HC major break causing multiple minor breaks in `ssd_plot()`.
 
 # ssdtools 2.1.0
 
-- Added `ssd_xxmulti_fitdists()` functions to accept object of class `fitdists`.
-- Set `ssd_xxmulti(..., lnorm.weight = 0)` (instead of 1) to avoid incorrect values with `do.call("ssd_xxmulti", c(..., estimates(fits))` if `fits` does not include the log-normal distribution.
+- Added `ssd_xxmulti_fitdists()` family of functions (`ssd_rmulti_fitdists()`, `ssd_pmulti_fitdists()` and `ssd_qmulti_fitdists()`) to accept object of class `fitdists`.
+- Set `lnorm.weight = 1` instead of `1` in the `ssd_xxmulti()` family of functions (`ssd_rmulti()`, `ssd_pmulti()` and `ssd_qmulti`) to avoid incorrect values with `do.call("ssd_xxmulti", c(..., estimates(fits))` if `fits` does not include the log-normal distribution.
 
 
 # ssdtools 2.0.0
@@ -69,7 +72,7 @@ The following functions and arguments were also added:
 
 - `ssd_hp_bcanz()` and `ssd_hp.fitburrlioz()` to get hazard proportions.
 - `ssd_pmulti()`, `ssd_qmulti()` and `ssd_rmulti()` for combined mixture distributions.
-- `ssd_exx()` functions to get default parameter estimates for distributions.
+- `ssd_exx()` family of functions (i.e. `ssd_elnorm()`, `ssd_egamma()` etc) to get default parameter estimates for distributions.
 - `ssd_censor_data()` to censor data. 
 - `npars = c(2L, 5L)` argument to `ssd_dists_bcanz()` to specify the number of parameters.
 - `dists = ssd_dists_bcanz()` to `ssd_fit_bcanz()` to allow other packages to modify.
@@ -155,7 +158,8 @@ ssdtools version 1.0.0 is the first major release of `ssdtools` with some import
 
 ## Fitting
 
-An important change to the functionality of `ssd_fit_dists()` was to switch from model fitting using [`fitdistrplus`](https://github.com/lbbe-software/fitdistrplus) to [`TMB`](https://github.com/kaskr/adcomp) which has resulted in improved handling of censored data.
+An important change to the functionality of `ssd_fit_dists()` was to switch from model fitting using [`fitdistrplus`](https://github.com/lbbe-software/fitdistrplus) to [`TMB`](https://github.com/kaskr/adcomp) to allow full control over model specification as well as improved handling of censored data.
+The change is internal and does not directly affect the user interface.
 Although it was hoped that model fitting would be faster this is currently not the case.
 
 As a result of the change the `fitdists` objects returned by `ssd_fit_dists()` from previous versions of `ssdtools` are not compatible with the major release and should be regenerated.
@@ -251,7 +255,7 @@ The function `ssd_fit_burrlioz()` was added to approximate the behaviour of [Bur
 Hazard concentration estimation is performed by `ssd_hc()` (which is wrapped by `predict()`) and hazard protection estimation by `ssd_hp()`.
 By default confidence intervals are estimated by parametric bootstrapping.
 
-To reduce the time required for bootstrapping, parallelization was implemented using the [future](https://github.com/HenrikBengtsson/future) package.
+To reduce the time required for bootstrapping, parallelization was implemented using the [future](https://github.com/futureverse/future) package.
 
 The following arguments were added to `ssd_hc()` and `ssd_hp()`
 

R/RcppExports.R

@@ -1,11 +1,7 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
-dgompertz_ssd <- function(x, location, shape) {
-    .Call(`_ssdtools_dgompertz_ssd`, x, location, shape)
-}
-
-dgumbel_ssd <- function(x, location, scale) {
-    .Call(`_ssdtools_dgumbel_ssd`, x, location, scale)
+fun_ssd <- function(x) {
+    .Call(`_ssdtools_fun_ssd`, x)
 }
 

R/censor.R

@@ -16,6 +16,9 @@
 #    limitations under the License.
 
 #' Censor Data
+#' 
+#' Censors data to a specified range based on the `censoring` argument.
+#' The function is useful for creating test data sets.
 #'
 #' @inheritParams params
 #'
@@ -27,6 +30,10 @@
 ssd_censor_data <- function(data, left = "Conc", ..., right = left, censoring = c(0, Inf)) {
   .chk_data(data, left, right)
   chk_unused(...)
+  chk_numeric(censoring)
+  chk_vector(censoring)
+  chk_length(censoring, 2L)
+  chk_not_any_na(censoring)
 
   if (left == right) {
     right <- "right"
@@ -63,11 +70,10 @@ censor_data <- function(data, censoring) {
   if (!.is_censored(censoring)) {
     return(data)
   }
-  chk_not_any_na(censoring)
-
-  data$right[data$left < censoring[1]] <- censoring[1]
+
+  data$right[data$left < censoring[1]] <- min(censoring)
   data$left[data$left < censoring[1]] <- 0
-  data$left[data$right > censoring[2]] <- censoring[2]
+  data$left[data$right > censoring[2]] <- max(censoring)
   data$right[data$right > censoring[2]] <- Inf
   data
 }

R/censored.R

@@ -70,6 +70,4 @@ ssd_is_censored.fitdists <- function(x, ...) {
 #' @seealso [`ssd_is_censored()`]
 is_censored <- function(x) {
   lifecycle::deprecate_stop("0.3.7", "is_censored()", "ssd_is_censored()")
-  chk_s3_class(x, "fitdists")
-  ssd_is_censored(x)
 }

R/d.R

@@ -19,33 +19,3 @@ any_missing <- function(...) {
   x <- unlist(list(...))
   any(is.na(x) & !is.nan(x))
 }
-
-.ddist <- function(dist, x, ..., log) {
-  inf <- !is.na(x) & is.infinite(x)
-  x[inf] <- NA_real_
-  fun <- paste0("d", dist, "_ssd")
-  d <- mapply(fun, x, ...)
-  d[mapply(any_missing, x, ...)] <- NA_real_
-  d[inf] <- -Inf
-  if (!log) d <- exp(d)
-  d
-}
-
-ddist <- function(dist, x, ..., log = FALSE, .lgt = FALSE) {
-  if (!length(x)) {
-    return(numeric(0))
-  }
-
-  if (!.lgt) {
-    return(.ddist(dist, x = x, ..., log = log))
-  }
-
-  lte <- !is.na(x) & x <= 0
-  x[lte] <- NA_real_
-  d <- .ddist(dist, x = log(x), ..., log = FALSE) / x
-  d[lte] <- 0
-  if (log) {
-    return(log(d))
-  }
-  d
-}

R/devtools-helpers.R

@@ -19,7 +19,7 @@ release_questions <- function() {
   c(
     "Have you run `data-raw/data-raw.R`?",
     "Have you tested using `ssdtests` package?",
-    "Have you updated `small-sample-bias.pdf`?",
+    "Have you run `vignettestatic/small-sample-bias.Rmd`?",
     "Have you confirmed all images in .Rmd files have alternative text defined using the `fig.alt` argument?",
     "Have you confirmed updated Apache 2.0 license at the top of all code files?",
     "Have you confirmed update Creative Commons license for all non-code files?"

R/dists.R

@@ -62,3 +62,18 @@ ssd_dists <- function(bcanz = NULL, tails = NULL, npars = 2:5) {
 ssd_dists_all <- function() {
   ssd_dists(bcanz = NULL, tails = NULL, npars = 2:5)
 }
+
+#' All Shiny Species Sensitivity Distributions
+#'
+#' Gets a character vector of the names of all the available distributions
+#' in the shinyssdtools.
+#'
+#' @return A unique, sorted character vector of the distributions.
+#' @family dists
+#' @export
+#'
+#' @examples
+#' ssd_dists_shiny()
+ssd_dists_shiny <- function() {
+  ssd_dists(bcanz = NULL, tails = TRUE, npars = 2:5)
+}

R/ggplot.R

@@ -33,11 +33,14 @@ ssd_pal <- function() {
 }
 
 #' Discrete color-blind scale for SSD Plots
+#' 
+#' The functions were designed for coloring different groups in a plot of SSD data.
 #'
 #' @param ... Arguments passed to [ggplot2::discrete_scale()].
 #' @family ggplot
 #' @export
 #' @examples
+#' # Use the color-blind palette for a SSD plot
 #' ssd_plot(ssddata::ccme_boron, boron_pred, shape = "Group", color = "Group") +
 #'   scale_colour_ssd()
 scale_colour_ssd <- function(...) {
@@ -52,6 +55,12 @@ scale_color_ssd <- function(...) {
 
 #' @describeIn scale_colour_ssd Discrete color-blind scale for SSD Plots
 #' @export
+#' @examples
+#' # Use the color-blind palette for a histogram of concentrations
+#' ggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Species, y = Conc, fill = Group)) +
+#'   ggplot2::geom_col() +
+#'   scale_fill_ssd() +
+#'   ggplot2::theme(axis.text.x = ggplot2::element_text(angle = 90, vjust = 0.5, hjust = 1))
 scale_fill_ssd <- function(...) {
   discrete_scale("fill", palette = ssd_pal(), ...)
 }
@@ -192,16 +201,11 @@ geom_xribbon <- function(mapping = NULL,
 #' Species Sensitivity Data Points
 #' `r lifecycle::badge('deprecated')`
 #'
-#' `geom_ssd()` has been deprecated for `geom_ssdpoint()`.
+#' Deprecated for `geom_ssdpoint()`.
 #'
 #' @inheritParams ggplot2::layer
 #' @inheritParams ggplot2::geom_point
 #' @export
-#' @examples
-#' \dontrun{
-#' ggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Conc)) +
-#'   geom_ssd()
-#' }
 geom_ssd <- function(mapping = NULL,
                      data = NULL,
                      stat = "ssdpoint",
@@ -211,12 +215,6 @@ geom_ssd <- function(mapping = NULL,
                      show.legend = NA,
                      inherit.aes = TRUE) {
   lifecycle::deprecate_stop("0.3.5", "geom_ssd()", "geom_ssdpoint()")
-
-  geom_ssdpoint(
-    mapping = mapping, data = data, stat = stat,
-    position = position, na.rm = na.rm, show.legend = show.legend,
-    inherit.aes = inherit.aes, ...
-  )
 }
 
 #' Plot Species Sensitivity Data
@@ -229,11 +227,6 @@ geom_ssd <- function(mapping = NULL,
 #' @seealso [`geom_ssdpoint()`]
 #' @family ggplot2
 #' @export
-#' @examples
-#' \dontrun{
-#' ggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Conc)) +
-#'   stat_ssd()
-#' }
 stat_ssd <- function(mapping = NULL,
                      data = NULL,
                      geom = "point",
@@ -243,10 +236,4 @@ stat_ssd <- function(mapping = NULL,
                      show.legend = NA,
                      inherit.aes = TRUE) {
   lifecycle::deprecate_stop("0.3.5", "stat_ssd()")
-
-  layer(
-    stat = StatSsdpoint, data = data, mapping = mapping, geom = geom,
-    position = position, show.legend = show.legend, inherit.aes = inherit.aes,
-    params = list(na.rm = na.rm, ...)
-  )
 }