Issue #552 Merge main into develop

.Rbuildignore

@@ -18,3 +18,4 @@
 ^\.devcontainer$
 ^CODE_OF_CONDUCT\.md$
 ^inst/manuscript/output$
+^CRAN-SUBMISSION$

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,21 @@
+<!-- Thanks for opening this pull request! Below we have provided a suggested template for PRs to this repository and a checklist to complete before opening a PR -->
+
+## Description
+
+This PR closes #<issue-number>.
+
+[Describe the changes that you made in this pull request.]
+
+## Checklist
+
+- [ ] My PR is based on a package issue and I have explicitly linked it.
+- [ ] I have included the target issue or issues in the PR title as follows: *issue-number*: PR title
+- [ ] I have tested my changes locally.
+- [ ] I have added or updated unit tests where necessary.
+- [ ] I have updated the documentation if required.
+- [ ] I have built the package locally and run rebuilt docs using roxygen2.
+- [ ] My code follows the established coding standards and I have run `lintr::lint_package()` to check for style issues introduced by my changes. 
+- [ ] I have added a news item linked to this PR.
+- [ ] I have reviewed CI checks for this PR and addressed them as far as I am able.
+
+<!-- Thanks again for this PR - @scoringutils dev team -->

.gitignore

@@ -18,3 +18,4 @@ docs
 ..bfg-report/
 .DS_Store
 .vscode
+README.html

DESCRIPTION

@@ -41,8 +41,8 @@ Description:
     Scoring metrics can be used either through a convenient data.frame format, 
     or can be applied as individual functions in a vector / matrix format. 
     All functionality has been implemented with a focus on performance and is 
-    robustly tested. Find more information about scoringutils in the 
-    accompanying paper (Bosse et al., 2022) <arXiv:2205.07090v1>. 
+    robustly tested. Find more information about the package in the 
+    accompanying paper (<doi:10.48550/arXiv.2205.07090>).
 License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true

NEWS.md

@@ -39,15 +39,24 @@ The update introduces breaking changes. If you want to keep using the older vers
 - `score()` now calls `na.omit()` on the data, instead of only removing rows with missing values in the columns `observed` and `predicted`. This is because `NA` values in other columns can also mess up e.g. grouping of forecasts according to the unit of a single forecast. 
 - added documentation for the return value of `summarise_scores()`.
 
+# scoringutils 1.2.2
+
+## Package updates
+- `scoringutils` now depends on R 3.6. The change was made since packages `testthat` and `lifecycle`, which are used in `scoringutils` now require R 3.6. We also updated the Github action CI check to work with R 3.6 now. 
+- Added a new PR template with a checklist of things to be included in PRs to facilitate the development and review process
+
+## Bug fixes
+- Fixes a bug with `set_forecast_unit()` where the function only workded with a data.table, but not a data.frame as an input. 
+- The metrics table in the vignette [Details on the metrics implemented in `scoringutils`](https://epiforecasts.io/scoringutils/articles/metric-details.html) had duplicated entries. This was fixed by removing the duplicated rows. 
 
 # scoringutils 1.2.1
 
 ## Package updates
 - This minor update fixes a few issues related to gh actions and the vignettes displayed at epiforecasts.io/scoringutils. It
-  - gets rid of the preferably package in _pkgdown.yml. The theme had a toggle between light and dark theme that didn't work properly
-  - updates the gh pages deploy action to v4 and also cleans up files when triggered
-  - introduces a gh action to automatically render the Readme from Readme.Rmd
-  - removes links to vignettes that have been renamed
+  - Gets rid of the preferably package in _pkgdown.yml. The theme had a toggle between light and dark theme that didn't work properly
+  - Updates the gh pages deploy action to v4 and also cleans up files when triggered
+  - Introduces a gh action to automatically render the Readme from Readme.Rmd
+  - Removes links to vignettes that have been renamed
 
 # scoringutils 1.2.0
 

R/available_forecasts.R

@@ -29,7 +29,9 @@
 #' @export
 #' @keywords check-forecasts
 #' @examples
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #'
 #' get_forecast_counts(example_quantile,
 #'   by = c("model", "target_type")

R/data.R

@@ -20,7 +20,7 @@
 #'   \item{horizon}{forecast horizon in weeks}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_quantile"
 
@@ -47,7 +47,7 @@
 #'   \item{horizon}{forecast horizon in weeks}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_point"
 
@@ -74,7 +74,7 @@
 #'   \item{sample_id}{id for the corresponding sample}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_continuous"
 
@@ -101,7 +101,7 @@
 #'   \item{sample_id}{id for the corresponding sample}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_integer"
 
@@ -134,7 +134,7 @@
 #'   \item{predicted}{predicted value}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_binary"
 
@@ -159,7 +159,7 @@
 #'   \item{horizon}{forecast horizon in weeks}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_quantile_forecasts_only"
 
@@ -181,7 +181,7 @@
 #'   \item{location_name}{name of the country for which a prediction was made}
 #' }
 # nolint start
-#' @source \url{https://github.com/covid19-forecast-hub-europe/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
+#' @source \url{https://github.com/european-modelling-hubs/covid19-forecast-hub-europe/commit/a42867b1ea152c57e25b04f9faa26cfd4bfd8fa6/}
 # nolint end
 "example_truth_only"
 

R/pairwise-comparisons.R

@@ -51,7 +51,9 @@
 #' @author Johannes Bracher, \email{johannes.bracher@@kit.edu}
 #' @keywords scoring
 #' @examples
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #'
 #' scores <- score(example_quantile)
 #' pairwise <- pairwise_comparison(scores, by = "target_type")

R/pit.R

@@ -62,7 +62,9 @@
 #' @seealso [pit()]
 #' @importFrom stats runif
 #' @examples
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #'
 #' ## continuous predictions
 #' observed <- rnorm(20, mean = 1:20)

R/plot.R

@@ -24,7 +24,9 @@
 #' @examples
 #' library(ggplot2)
 #' library(magrittr) # pipe operator
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #'
 #' scores <- score(example_quantile) %>%
 #'   summarise_scores(by = c("model", "target_type")) %>%
@@ -577,11 +579,12 @@ make_na <- make_NA
 #' @importFrom data.table dcast
 #' @export
 #' @examples
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #' data_coverage <- add_coverage(example_quantile)
 #' summarised <- summarise_scores(data_coverage, by = c("model", "range"))
 #' plot_interval_coverage(summarised)
-
 plot_interval_coverage <- function(scores,
                                    colour = "model") {
   ## overall model calibration - empirical interval coverage
@@ -830,7 +833,9 @@ plot_pairwise_comparison <- function(comparison_result,
 #' @importFrom stats density
 #' @return vector with the scoring values
 #' @examples
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #'
 #' # PIT histogram in vector based format
 #' observed <- rnorm(30, mean = 1:30)

R/score.R

@@ -32,7 +32,9 @@
 #' @importFrom stats na.omit
 #' @examples
 #' library(magrittr) # pipe operator
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #'
 #' validated <- as_forecast(example_quantile)
 #' score(validated) %>%

R/summarise_scores.R

@@ -28,7 +28,9 @@
 #' to the names of the columns of the original data specified in `by` or
 #' `across` using the `fun` passed to `summarise_scores()`.
 #' @examples
-#' data.table::setDTthreads(1) # only needed to avoid issues on CRAN
+#' \dontshow{
+#'   data.table::setDTthreads(2) # restricts number of cores used on CRAN
+#' }
 #' library(magrittr) # pipe operator
 #' \dontrun{
 #' scores <- score(example_continuous)

R/zzz.R

@@ -0,0 +1,9 @@
+.onAttach <- function(libname, pkgname) {
+  packageStartupMessage(
+    "Note: scoringutils is currently undergoing major development changes ",
+    "(with an update planned for the first quarter of 2024). We would very ",
+    "much appreciate your opinions and feedback on what should be included in ",
+    "this major update: ",
+    "https://github.com/epiforecasts/scoringutils/discussions/333"
+  )
+}

README.Rmd

@@ -30,7 +30,7 @@ library(knitr)
 
 The `scoringutils` package provides a collection of metrics and proper scoring rules and aims to make it simple to score probabilistic forecasts against observed values. 
 
-You can find additional information and examples in the papers [Evaluating Forecasts with scoringutils in R](https://arxiv.org/abs/2205.07090) [Scoring epidemiological forecasts on transformed scales](https://www.medrxiv.org/content/10.1101/2023.01.23.23284722v1) as well as the Vignettes ([Getting started](https://epiforecasts.io/scoringutils/articles/scoringutils.html), [Details on the metrics implemented](https://epiforecasts.io/scoringutils/articles/metric-details.html) and [Scoring forecasts directly](https://epiforecasts.io/scoringutils/articles/scoring-forecasts-directly.html)).
+You can find additional information and examples in the papers [Evaluating Forecasts with scoringutils in R](https://arxiv.org/abs/2205.07090) [Scoring epidemiological forecasts on transformed scales](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011393) as well as the Vignettes ([Getting started](https://epiforecasts.io/scoringutils/articles/scoringutils.html), [Details on the metrics implemented](https://epiforecasts.io/scoringutils/articles/metric-details.html) and [Scoring forecasts directly](https://epiforecasts.io/scoringutils/articles/scoring-forecasts-directly.html)).
 
 The `scoringutils` package offers convenient automated forecast evaluation through the function `score()`. The function operates on data.frames (it uses `data.table` internally for speed and efficiency) and can easily be integrated in a workflow based on `dplyr` or `data.table`. It also provides experienced users with a set of reliable lower-level scoring metrics operating on vectors/matrices they can build upon in other applications. In addition it implements a wide range of flexible plots designed to cover many use cases.
 

README.md

@@ -20,7 +20,7 @@ You can find additional information and examples in the papers
 [Evaluating Forecasts with scoringutils in
 R](https://arxiv.org/abs/2205.07090) [Scoring epidemiological forecasts
 on transformed
-scales](https://www.medrxiv.org/content/10.1101/2023.01.23.23284722v1)
+scales](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011393)
 as well as the Vignettes ([Getting
 started](https://epiforecasts.io/scoringutils/articles/scoringutils.html),
 [Details on the metrics
@@ -143,17 +143,20 @@ example_quantile %>%
     digits = 2
   ) %>%
   kable()
+#> Some rows containing NA values may be removed. This is fine if not unexpected.
+#> Some rows containing NA values may be removed. This is fine if not unexpected.
+#> Some rows containing NA values may be removed. This is fine if not unexpected.
 ```
 
-| model                 | target_type |   wis | overprediction | underprediction | dispersion |    bias | coverage_50 | coverage_90 | coverage_deviation | ae_median | relative_skill | scaled_rel_skill |
-|:----------------------|:------------|------:|---------------:|----------------:|-----------:|--------:|------------:|------------:|-------------------:|----------:|---------------:|-----------------:|
-| EuroCOVIDhub-baseline | Cases       | 28000 |        14000.0 |         10000.0 |       4100 |  0.0980 |        0.33 |        0.82 |             -0.120 |     38000 |           1.30 |              1.6 |
-| EuroCOVIDhub-baseline | Deaths      |   160 |           66.0 |             2.1 |         91 |  0.3400 |        0.66 |        1.00 |              0.120 |       230 |           2.30 |              3.8 |
-| EuroCOVIDhub-ensemble | Cases       | 18000 |        10000.0 |          4200.0 |       3700 | -0.0560 |        0.39 |        0.80 |             -0.100 |     24000 |           0.82 |              1.0 |
-| EuroCOVIDhub-ensemble | Deaths      |    41 |            7.1 |             4.1 |         30 |  0.0730 |        0.88 |        1.00 |              0.200 |        53 |           0.60 |              1.0 |
-| UMass-MechBayes       | Deaths      |    53 |            9.0 |            17.0 |         27 | -0.0220 |        0.46 |        0.88 |             -0.025 |        78 |           0.75 |              1.3 |
-| epiforecasts-EpiNow2  | Cases       | 21000 |        12000.0 |          3300.0 |       5700 | -0.0790 |        0.47 |        0.79 |             -0.070 |     28000 |           0.95 |              1.2 |
-| epiforecasts-EpiNow2  | Deaths      |    67 |           19.0 |            16.0 |         32 | -0.0051 |        0.42 |        0.91 |             -0.045 |       100 |           0.98 |              1.6 |
+| model                 | target_type |   wis | overprediction | underprediction | dispersion |    bias | interval_coverage_50 | interval_coverage_90 | interval_coverage_deviation | ae_median | relative_skill | scaled_rel_skill |
+|:----------------------|:------------|------:|---------------:|----------------:|-----------:|--------:|---------------------:|---------------------:|----------------------------:|----------:|---------------:|-----------------:|
+| EuroCOVIDhub-baseline | Cases       | 28000 |        14000.0 |         10000.0 |       4100 |  0.0980 |                 0.33 |                 0.82 |                      -0.120 |     38000 |           1.30 |              1.6 |
+| EuroCOVIDhub-baseline | Deaths      |   160 |           66.0 |             2.1 |         91 |  0.3400 |                 0.66 |                 1.00 |                       0.120 |       230 |           2.30 |              3.8 |
+| EuroCOVIDhub-ensemble | Cases       | 18000 |        10000.0 |          4200.0 |       3700 | -0.0560 |                 0.39 |                 0.80 |                      -0.100 |     24000 |           0.82 |              1.0 |
+| EuroCOVIDhub-ensemble | Deaths      |    41 |            7.1 |             4.1 |         30 |  0.0730 |                 0.88 |                 1.00 |                       0.200 |        53 |           0.60 |              1.0 |
+| UMass-MechBayes       | Deaths      |    53 |            9.0 |            17.0 |         27 | -0.0220 |                 0.46 |                 0.88 |                      -0.025 |        78 |           0.75 |              1.3 |
+| epiforecasts-EpiNow2  | Cases       | 21000 |        12000.0 |          3300.0 |       5700 | -0.0790 |                 0.47 |                 0.79 |                      -0.070 |     28000 |           0.95 |              1.2 |
+| epiforecasts-EpiNow2  | Deaths      |    67 |           19.0 |            16.0 |         32 | -0.0051 |                 0.42 |                 0.91 |                      -0.045 |       100 |           0.98 |              1.6 |
 
 `scoringutils` contains additional functionality to transform forecasts,
 to summarise scores at different levels, to visualise them, and to
@@ -175,27 +178,28 @@ example_quantile %>%
   score %>%
   summarise_scores(by = c("model", "target_type", "scale")) %>%
   head()
+#> Some rows containing NA values may be removed. This is fine if not unexpected.
 #>                    model target_type   scale         wis overprediction
 #> 1: EuroCOVIDhub-ensemble       Cases natural 11550.70664    3650.004755
 #> 2: EuroCOVIDhub-baseline       Cases natural 22090.45747    7702.983696
 #> 3:  epiforecasts-EpiNow2       Cases natural 14438.43943    5513.705842
 #> 4: EuroCOVIDhub-ensemble      Deaths natural    41.42249       7.138247
 #> 5: EuroCOVIDhub-baseline      Deaths natural   159.40387      65.899117
 #> 6:       UMass-MechBayes      Deaths natural    52.65195       8.978601
-#>    underprediction dispersion        bias coverage_50 coverage_90
-#> 1:     4237.177310 3663.52458 -0.05640625   0.3906250   0.8046875
-#> 2:    10284.972826 4102.50094  0.09726562   0.3281250   0.8203125
-#> 3:     3260.355639 5664.37795 -0.07890625   0.4687500   0.7890625
-#> 4:        4.103261   30.18099  0.07265625   0.8750000   1.0000000
-#> 5:        2.098505   91.40625  0.33906250   0.6640625   1.0000000
-#> 6:       16.800951   26.87239 -0.02234375   0.4609375   0.8750000
-#>    coverage_deviation   ae_median
-#> 1:        -0.10230114 17707.95312
-#> 2:        -0.11437500 32080.48438
-#> 3:        -0.06963068 21530.69531
-#> 4:         0.20380682    53.13281
-#> 5:         0.12142045   233.25781
-#> 6:        -0.02488636    78.47656
+#>    underprediction dispersion        bias interval_coverage_50
+#> 1:     4237.177310 3663.52458 -0.05640625            0.3906250
+#> 2:    10284.972826 4102.50094  0.09726562            0.3281250
+#> 3:     3260.355639 5664.37795 -0.07890625            0.4687500
+#> 4:        4.103261   30.18099  0.07265625            0.8750000
+#> 5:        2.098505   91.40625  0.33906250            0.6640625
+#> 6:       16.800951   26.87239 -0.02234375            0.4609375
+#>    interval_coverage_90 interval_coverage_deviation   ae_median
+#> 1:            0.8046875                 -0.10230114 17707.95312
+#> 2:            0.8203125                 -0.11437500 32080.48438
+#> 3:            0.7890625                 -0.06963068 21530.69531
+#> 4:            1.0000000                  0.20380682    53.13281
+#> 5:            1.0000000                  0.12142045   233.25781
+#> 6:            0.8750000                 -0.02488636    78.47656
 ```
 
 ## Citation

inst/WORDLIST

@@ -1,16 +1,18 @@
 AJ
+al
+Bosse
 Bracher
 CMD
 COVID
 CRPS
 Camacho
-Comput
 Cori
 DSS
 Dawid
 ECDC
 Eggo
 EpiNow
+et
 EuroCOVIDhub
 Gneiting
 Höhle
@@ -44,9 +46,7 @@ facetted
 facetting
 frac
 ggplot
-implict
 jss
-matriced
 medRxiv
 metacran
 miscalibrated
@@ -58,6 +58,7 @@ pval
 pvalues
 rel
 scoringRules
+scoringutils
 standalone
 u
 underprediction