Merge pull request #365 from poissonconsulting/dev

JOSS paper draft

.github/workflows/paper.yaml

@@ -0,0 +1,28 @@
+# Workflow derived from https://github.com/marketplace/actions/open-journals-pdf-generator
+
+on:
+  push:
+    branches: [main, dev]
+  pull_request:
+    branches: [main, dev]
+
+name: paper
+
+jobs:
+  paper:
+    runs-on: ubuntu-latest
+    name: Paper Draft
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Build draft PDF
+        uses: openjournals/openjournals-draft-action@master
+        with:
+          journal: joss
+          paper-path: paper/paper.md
+      - name: Upload
+        uses: actions/upload-artifact@v1
+        with:
+          name: paper
+          path: paper/paper.pdf
+

.github/workflows/pkgdown.yaml

@@ -2,9 +2,9 @@
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    branches: [main, master]
+    branches: main
   pull_request:
-    branches: [main, master]
+    branches: main
   release:
     types: [published]
   workflow_dispatch:

.github/workflows/test-coverage.yaml

@@ -2,9 +2,9 @@
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    branches: [main, master]
+    branches: main
   pull_request:
-    branches: [main, master]
+    branches: main
 
 name: test-coverage
 

.gitignore

@@ -14,3 +14,4 @@ docs/
 inst/docs/
 scripts/
 inst/doc
+paper/paper.pdf

DESCRIPTION

@@ -4,37 +4,41 @@ Version: 1.0.6.9015
 Authors@R: c(
     person("Joe", "Thorley", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-7683-4592")),
-    person("Carl", "Schwarz", role = "aut"),
     person("Rebecca", "Fisher", , "[email protected]", role = "aut"),
     person("David", "Fox", , "[email protected]", role = "aut"),
+    person("Carl", "Schwarz", role = "aut"),
     person("Angeline", "Tillmanns", role = "ctb"),
-    person("Ali", "Azizishirazi", role = "ctb"),
+    person("Seb", "Dalgarno", , "[email protected]", role = "ctb",
+           comment = c(ORCID = "0000-0002-3658-4517")),
     person("Kathleen", "McTavish", role = "ctb"),
     person("Heather", "Thompson", role = "ctb"),
     person("Doug", "Spry", role = "ctb"),
     person("Rick", "van Dam", role = "ctb"),
     person("Graham", "Batley", role = "ctb"),
-    person("Heather", "Thompson", role = "ctb"),
-    person("Andy", "Teucher", role = "ctb"),
-    person("Seb", "Dalgarno", , "[email protected]", role = "ctb",
-           comment = c(ORCID = "0000-0002-3658-4517")),
-    person("Emilie", "Doussantousse", role = "ctb"),
-    person("Stephanie", "Hazlitt", role = "ctb"),
+    person("Yulia", "Cuthbertson", role = "ctb"),
+    person("Tony", "Bigwood", role = "ctb"),
+    person("Michael", "Antenucci", role = "ctb"),
+    person("Ali", "Azizishirazi", role = "ctb"),
     person("Nadine", "Hussein", , "[email protected]", role = "ctb",
            comment = c(ORCID = "0000-0003-4470-8361")),
-    person("Nan-Hung", "Hsieh", role = "ctb"),
-    person("Sergio", "Ibarra Espinosa", role = "ctb"),
+    person("Sarah", "Lyons", , "[email protected]", role = "ctb",
+           comment = c(ORCID = "0000-0002-6745-6796")),
+    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("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"))
   )
 Description: Species sensitivity distributions are cumulative probability
     distributions which are fitted to toxicity concentrations for
     different species as described by Posthuma et al.(2001)
-    <isbn:9781566705783>.  The ssdtools package uses Maximum Likelihood to
+    <isbn:9781566705783>. The ssdtools package uses Maximum Likelihood to
     fit distributions such as the gamma, log-logistic, log-normal and
-    Weibull to censored and/or weighted data.  Multiple distributions can
+    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.

R/licensing.R

@@ -8,7 +8,7 @@
 licensing_md <- function() {
 "## Licensing
   
-  Copyright 2023 Province of British Columbia,
+  Copyright 2024 Province of British Columbia,
    Environment and Climate Change Canada, and 
    Australian Government Department of 
    Climate Change, Energy, the Environment and Water

R/ssd-plot.R

@@ -50,7 +50,7 @@ ssd_plot <- function(data, pred, left = "Conc", right = left,
                      label = NULL, shape = NULL, color = NULL, size = 2.5,
                      linetype = NULL, linecolor = NULL,
                      xlab = "Concentration", ylab = "Species Affected",
-                     ci = TRUE, ribbon = FALSE, hc = 0.05, 
+                     ci = TRUE, ribbon = TRUE, hc = 0.05, 
                      shift_x = 3, add_x = 0,
                      bounds = c(left = 1, right = 1),
                      trans = "log10", xbreaks = waiver()) {

README.Rmd

@@ -15,7 +15,7 @@ knitr::opts_chunk$set(
 # ssdtools <img src="man/figures/logo.png" align="right" />
 
 <!-- badges: start -->
-[![Lifecycle:Maturing](https://img.shields.io/badge/Lifecycle-Maturing-007EC6)](https://github.com/bcgov/repomountie/blob/master/doc/lifecycle-badges.md)
+[![Lifecycle:Stable](https://img.shields.io/badge/Lifecycle-Stable-97ca00)](https://github.com/bcgov/repomountie/blob/master/doc/lifecycle-badges.md)
 [![R-CMD-check](https://github.com/bcgov/ssdtools/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/bcgov/ssdtools/actions/workflows/R-CMD-check.yaml)
 [![codecov](https://codecov.io/github/bcgov/ssdtools/graph/badge.svg?token=gVKHQQD1Jp)](https://codecov.io/github/bcgov/ssdtools)
 [![CRAN status](https://www.r-pkg.org/badges/version/ssdtools)](https://cran.r-project.org/package=ssdtools)
@@ -25,9 +25,9 @@ knitr::opts_chunk$set(
 `ssdtools` is an R package to fit and plot Species Sensitivity Distributions (SSD). 
 
 SSDs are cumulative probability distributions which are fitted to toxicity concentrations for different species as described by Posthuma et al. (2001).
-The ssdtools package uses Maximum Likelihood to fit distributions such as the gamma, log-Gumbel (identical to inverse Weibull), log-logistic, log-normal and Weibull to censored and/or weighted data.
+The ssdtools package uses Maximum Likelihood to fit distributions such as the log-normal, log-logistic, log-Gumbel (also known as the inverse Weibull), gamma, Weibull 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.
+Confidence intervals on hazard concentrations and proportions are produced by bootstrapping.
 
 ## Installation
 
@@ -38,49 +38,44 @@ install.packages("ssdtools")
 
 To install the latest development version from [GitHub](https://github.com/bcgov/ssdtools)
 ```{r, eval = FALSE}
-# install.packages("pak", repos = sprintf("https://r-lib.github.io/p/pak/stable/%s/%s/%s", .Platform$pkgType, R.Version()$os, R.Version()$arch))
-pak::pak("bcgov/ssdtools")
+# install.packages("remotes")
+remotes::install_github("bcgov/ssdtools")
 ```
 
 ## Introduction
 
-`ssdtools` provides a data set for several chemicals including Boron.
+The dependency `ssddata` provides a example data sets for several chemicals including Boron.
 ```{r, message=FALSE}
 library(ssdtools)
 ssddata::ccme_boron
 ```
 
-Distributions are fit using `ssd_fit_dists()`
+The six default distributions are fit using `ssd_fit_dists()`
 ```{r}
-fits <- ssd_fit_dists(ssddata::ccme_boron, dists = c("lnorm", "llogis"))
+fits <- ssd_fit_dists(ssddata::ccme_boron)
 ```
 
 and can be quickly plotted using `autoplot`
 ```{r, warning = FALSE, message = FALSE}
-library(ggplot2)
-
-theme_set(theme_bw())
-
-autoplot(fits) +
-  scale_colour_ssd()
+autoplot(fits)
 ```
 
 The goodness of fit can be assessed using `ssd_gof`
 ```{r}
 ssd_gof(fits)
 ```
 
-and the model-averaged 5% hazard concentration estimated by parametric bootstrapping using `ssd_hc`.
+and the model-averaged 5% hazard concentration estimated by bootstrapping using `ssd_hc`.
 ```{r}
 set.seed(99)
-hc5 <- ssd_hc(fits, ci = TRUE, nboot = 100) # 100 bootstrap samples for speed
+hc5 <- ssd_hc(fits, ci = TRUE)
 print(hc5)
 ```
 
 To bootstrap in parallel set `future::plan()`. For example:
 ```{r, eval=FALSE}
 future::multisession(workers = 2)
-hc5 <- ssd_hc(fits, ci = TRUE, nboot = 100)
+hc5 <- ssd_hc(fits, ci = TRUE)
 ```
 
 Model-averaged predictions complete with confidence intervals can also be estimated by parametric bootstrapping using the `stats` generic `predict`.
@@ -94,8 +89,12 @@ set.seed(99)
 boron_pred <- predict(fits, ci = TRUE)
 ```
 
-and plotted together with the original data using `ssd_plot`.
+The predictions can be plotted together with the original data using `ssd_plot`.
 ```{r}
+library(ggplot2)
+
+theme_set(theme_bw())
+
 ssd_plot(ssddata::ccme_boron, boron_pred,
   shape = "Group", color = "Group", label = "Species",
   xlab = "Concentration (mg/L)", ribbon = TRUE

README.md

@@ -5,7 +5,7 @@
 
 <!-- badges: start -->
 
-[![Lifecycle:Maturing](https://img.shields.io/badge/Lifecycle-Maturing-007EC6)](https://github.com/bcgov/repomountie/blob/master/doc/lifecycle-badges.md)
+[![Lifecycle:Stable](https://img.shields.io/badge/Lifecycle-Stable-97ca00)](https://github.com/bcgov/repomountie/blob/master/doc/lifecycle-badges.md)
 [![R-CMD-check](https://github.com/bcgov/ssdtools/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/bcgov/ssdtools/actions/workflows/R-CMD-check.yaml)
 [![codecov](https://codecov.io/github/bcgov/ssdtools/graph/badge.svg?token=gVKHQQD1Jp)](https://codecov.io/github/bcgov/ssdtools)
 [![CRAN
@@ -19,11 +19,11 @@ Distributions (SSD).
 SSDs are cumulative probability distributions which are fitted to
 toxicity concentrations for different species as described by Posthuma
 et al. (2001). The ssdtools package uses Maximum Likelihood to fit
-distributions such as the gamma, log-Gumbel (identical to inverse
-Weibull), log-logistic, log-normal and Weibull to censored and/or
-weighted data. Multiple distributions can be averaged using Akaike
-Information Criteria. Confidence intervals on hazard concentrations and
-proportions are produced by parametric bootstrapping.
+distributions such as the log-normal, log-logistic, log-Gumbel (also
+known as the inverse Weibull), gamma, Weibull 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 bootstrapping.
 
 ## Installation
 
@@ -38,13 +38,14 @@ To install the latest development version from
 [GitHub](https://github.com/bcgov/ssdtools)
 
 ``` r
-# install.packages("pak", repos = sprintf("https://r-lib.github.io/p/pak/stable/%s/%s/%s", .Platform$pkgType, R.Version()$os, R.Version()$arch))
-pak::pak("bcgov/ssdtools")
+# install.packages("remotes")
+remotes::install_github("bcgov/ssdtools")
 ```
 
 ## Introduction
 
-`ssdtools` provides a data set for several chemicals including Boron.
+The dependency `ssddata` provides a example data sets for several
+chemicals including Boron.
 
 ``` r
 library(ssdtools)
@@ -65,21 +66,16 @@ ssddata::ccme_boron
 #> # ℹ 18 more rows
 ```
 
-Distributions are fit using `ssd_fit_dists()`
+The six default distributions are fit using `ssd_fit_dists()`
 
 ``` r
-fits <- ssd_fit_dists(ssddata::ccme_boron, dists = c("lnorm", "llogis"))
+fits <- ssd_fit_dists(ssddata::ccme_boron)
 ```
 
 and can be quickly plotted using `autoplot`
 
 ``` r
-library(ggplot2)
-
-theme_set(theme_bw())
-
-autoplot(fits) +
-  scale_colour_ssd()
+autoplot(fits)
 ```
 
 ![](man/figures/README-unnamed-chunk-5-1.png)<!-- -->
@@ -88,31 +84,35 @@ The goodness of fit can be assessed using `ssd_gof`
 
 ``` r
 ssd_gof(fits)
-#> # A tibble: 2 × 9
-#>   dist      ad     ks    cvm   aic  aicc   bic delta weight
-#>   <chr>  <dbl>  <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>
-#> 1 lnorm  0.507 0.107  0.0703  239.  240.  242.  0      0.73
-#> 2 llogis 0.487 0.0994 0.0595  241.  241.  244.  1.99   0.27
+#> # A tibble: 6 × 9
+#>   dist           ad     ks    cvm   aic  aicc   bic delta weight
+#>   <chr>       <dbl>  <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>
+#> 1 gamma       0.440 0.117  0.0554  238.  238.  240. 0.005  0.357
+#> 2 lgumbel     0.829 0.158  0.134   244.  245.  247. 6.56   0.013
+#> 3 llogis      0.487 0.0994 0.0595  241.  241.  244. 3.39   0.066
+#> 4 lnorm       0.507 0.107  0.0703  239.  240.  242. 1.40   0.177
+#> 5 lnorm_lnorm 0.320 0.116  0.0414  240.  243.  247. 4.98   0.03 
+#> 6 weibull     0.434 0.117  0.0542  238.  238.  240. 0      0.357
 ```
 
-and the model-averaged 5% hazard concentration estimated by parametric
+and the model-averaged 5% hazard concentration estimated by
 bootstrapping using `ssd_hc`.
 
 ``` r
 set.seed(99)
-hc5 <- ssd_hc(fits, ci = TRUE, nboot = 100) # 100 bootstrap samples for speed
+hc5 <- ssd_hc(fits, ci = TRUE)
 print(hc5)
-#> # A tibble: 1 × 10
-#>   dist    percent   est    se   lcl   ucl    wt method     nboot pboot
-#>   <chr>     <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>      <dbl> <dbl>
-#> 1 average       5  1.65 0.599 0.923  3.34     1 parametric   100     1
+#> # A tibble: 1 × 11
+#>   dist    proportion   est    se   lcl   ucl    wt method    nboot pboot samples
+#>   <chr>        <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>     <dbl> <dbl> <I<lis>
+#> 1 average       0.05  1.26 0.781 0.407  3.29     1 parametr…  1000 0.999 <dbl>
 ```
 
 To bootstrap in parallel set `future::plan()`. For example:
 
 ``` r
 future::multisession(workers = 2)
-hc5 <- ssd_hc(fits, ci = TRUE, nboot = 100)
+hc5 <- ssd_hc(fits, ci = TRUE)
 ```
 
 Model-averaged predictions complete with confidence intervals can also
@@ -128,9 +128,14 @@ set.seed(99)
 boron_pred <- predict(fits, ci = TRUE)
 ```
 
-and plotted together with the original data using `ssd_plot`.
+The predictions can be plotted together with the original data using
+`ssd_plot`.
 
 ``` r
+library(ggplot2)
+
+theme_set(theme_bw())
+
 ssd_plot(ssddata::ccme_boron, boron_pred,
   shape = "Group", color = "Group", label = "Species",
   xlab = "Concentration (mg/L)", ribbon = TRUE
@@ -202,7 +207,7 @@ By contributing to this project, you agree to abide by its terms.
 
 ## Licensing
 
-Copyright 2023 Province of British Columbia, Environment and Climate
+Copyright 2024 Province of British Columbia, Environment and Climate
 Change Canada, and Australian Government Department of Climate Change,
 Energy, the Environment and Water