version 0.6.2

cran · Aug 10, 2023 · 9f08abf · 9f08abf
1 parent e3a8ca3
commit 9f08abf
Show file tree

Hide file tree

Showing 11 changed files with 1,094 additions and 551 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: swfscDAS
 Title: Southwest Fisheries Science Center Shipboard DAS Data Processing
-Version: 0.6.1
+Version: 0.6.2
 Authors@R: 
     person("Sam", "Woodman", email = "sam.woodman@noaa.gov", role = c("aut", "cre"), comment = c(ORCID = "0000-0001-6071-8186"))
 Description: Process and summarize shipboard 
@@ -13,16 +13,16 @@ URL: https://smwoodman.github.io/swfscDAS/,
         https://github.com/smwoodman/swfscDAS/
 BugReports: https://github.com/smwoodman/swfscDAS/issues/
 Depends: R (>= 4.0.0)
-Imports: dplyr, lubridate, magrittr, methods, parallel, purrr, readr,
-        rlang, sf, swfscMisc, tidyr
+Imports: dplyr (>= 1.1.0), lubridate, magrittr, methods, parallel,
+        purrr, readr, rlang, sf, swfscMisc, tidyr
 Suggests: knitr, rmarkdown, stringr, testthat (>= 2.1.0)
 License: CC0
 Encoding: UTF-8
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.3
 VignetteBuilder: knitr
 NeedsCompilation: no
-Packaged: 2022-01-31 19:23:23 UTC; sam.woodman
+Packaged: 2023-08-08 23:34:27 UTC; sam.woodman
 Author: Sam Woodman [aut, cre] (<https://orcid.org/0000-0001-6071-8186>)
 Maintainer: Sam Woodman <sam.woodman@noaa.gov>
 Repository: CRAN
-Date/Publication: 2022-01-31 19:50:02 UTC
+Date/Publication: 2023-08-10 07:00:02 UTC
diff --git a/MD5 b/MD5
@@ -1,6 +1,6 @@
-6c62aa665e827c2dbfbacfc51e644035 *DESCRIPTION
-2dba93c5f274f2ce6a36fa11ae741852 *NAMESPACE
-65e67d6e38b443fcf8661fb8471508f9 *NEWS.md
+102bbc6779e4f8d156a59063b07e4d4a *DESCRIPTION
+10e42513eee3c462e23b4e4640234e56 *NAMESPACE
+2bca52b91acfa31da9b853a55b8e09ed *NEWS.md
 102266fa9dd1be4dfcddcf7a603b4d62 *R/as_das_df.R
 1e4cba8a7d8da74119d7012247866623 *R/as_das_dfr.R
 41efa05eba27e51ef7d4117b7745693d *R/das_check.R
@@ -17,14 +17,14 @@ c418ed6b1524e453015f178111ee8a16 *R/das_effort_strata.R
 c0648eb11398f305921cf697009adedb *R/das_process.R
 ea4549aa913deb4902f1ad0833fee956 *R/das_read.R
 37f5ff79244213e016b624e04090564a *R/das_segdata.R
-bbbc8546e49f9a377e099592bca691ed *R/das_sight.R
+d02b5b2390d050adda047aa70e49e7d5 *R/das_sight.R
 ce7d7c6cb53836f6b4b9b891b24747e4 *R/distance_greatcircle.R
 d1632370a5a33bd5f35db26a0ce42da9 *R/randpicks_convert.R
 6c3088d16042b73f6c2a2ea1ea2f534d *R/subsetting.R
 a13f59f7aab865b75d633d6969103c54 *R/swfscDAS-internal.R
-5076a5e29db8a50290844c47e878bbf7 *R/swfscDAS-package.R
-35abc67baf9094dd0da3defc2d5a6072 *README.md
-72642f8b1d5f15a2e03248acbfc9bd05 *build/vignette.rds
+a80867b1be9c12bb070c9daf03778070 *R/swfscDAS-package.R
+2908c42189b954e8a886ed088cb59d1a *README.md
+241d2b461d173c2f167578080d0e9f3e *build/vignette.rds
 dd00f8695b1893fbd071e5dfdda1fd21 *inst/DAS_Format.pdf
 019d2c4a47e87035cddc8ec511bffee7 *inst/DAS_chop_equallength_figures.pdf
 ad585d78881d3eb2512fadfd80370e11 *inst/Ship_sample.dat
@@ -34,10 +34,10 @@ ad585d78881d3eb2512fadfd80370e11 *inst/Ship_sample.dat
 18a11c4354a278365ad9e9861a9751e5 *inst/das_sample_stratum.csv
 b5c224f276415b32bb94148851164805 *inst/doc/DAS_data_join.R
 682b2d5c6fd4bed582338b2d254f0614 *inst/doc/DAS_data_join.Rmd
-b51f4ca95c7a17da9e10e3ced70c5bee *inst/doc/DAS_data_join.html
+84db6baae0e84012310efaf166f4f0c1 *inst/doc/DAS_data_join.html
 8f7244d93b3101114c1555b29dc53b78 *inst/doc/swfscDAS.R
 e4ee86caaf4778899b2b06a07d1a3935 *inst/doc/swfscDAS.Rmd
-ceb8d824e307a5b5c098ea75e0852817 *inst/doc/swfscDAS.html
+1a672926522a1d2c963b5a5b43b7eacf *inst/doc/swfscDAS.html
 acb9dda27e69da9f5fda5956ed84638b *man/as_das_df.Rd
 bca1a04e09d1b5d5ba65e26dcc90a68b *man/as_das_dfr.Rd
 a368461ed7c8e921c970d1f54b7e836f *man/das_check.Rd
@@ -55,7 +55,7 @@ b24e29c860a2ef260d0c1fd34cbcb9d8 *man/das_dfr-class.Rd
 eecec7a83534b0f53cda76b318c9e8d5 *man/das_process.Rd
 5dae722319d5c57a7b46a6eb0a304a3a *man/das_read.Rd
 8a17926f90a088e283340cc4a188d15d *man/das_segdata.Rd
-45db8c0c00b147bbe302434aba1d13ea *man/das_sight.Rd
+7caab785545223e560f1ed8d0bd5a8aa *man/das_sight.Rd
 02fe9ad730065f37020f8d5b6e13ee5c *man/distance_greatcircle.Rd
 1a14ec3976ce02b3ccad4c7ae7299c9b *man/randpicks_convert.Rd
 c774a3c1d6219d824e8a1e078080c5b2 *man/subsetting.Rd

diff --git a/NAMESPACE b/NAMESPACE
@@ -74,6 +74,7 @@ importFrom(dplyr,left_join)
 importFrom(dplyr,mutate)
 importFrom(dplyr,n)
 importFrom(dplyr,n_distinct)
+importFrom(dplyr,reframe)
 importFrom(dplyr,right_join)
 importFrom(dplyr,select)
 importFrom(dplyr,slice)

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,10 @@
+# swfscDAS 0.6.2
+
+* Use `reframe` in grouping summaries in `das_sight` for when none of a certain event are in the data (#8)
+
+* Ensure that `sum(GsSpx)` equals `GsSchoolx`, for all of Best, High and Low (#9)
+
+
 # swfscDAS 0.6.1
 
 * Fix bug in `das_sight` and `das_effort` when the DAS file contains no sightings

diff --git a/R/das_sight.R b/R/das_sight.R
@@ -21,7 +21,7 @@
 #'   marine mammal subgroup sightings (code "G"),
 #'   marine mammal subgroup resights (code "g"),
 #'   turtle sightings (code "t"),
-#'   pinniped sightings (code "p")
+#'   pinniped sightings (code "p"),
 #'   and fishing vessel sightings (code "F").
 #'   Warnings are printed if all S, K, M, and G events (and only these events) are not
 #'   followed by an A event and at least one numeric event.
@@ -99,11 +99,13 @@
 #'
 #'   SightNoDaily is a running count of the number of S/K/M/G sightings that occurred on each day.
 #'   It is formatted as 'YYYYMMDD'_'running count', e.g. "20050101_1".
+#'
 #'   The GsSchoolBest, GsSchoolHigh, and GsSchoolLow columns are either:
-#'   1) the arithmetic mean across observer estimates for the "default" and "wide" formats, or
-#'   2) the individual observer estimates for the "complete" format.
+#'   1) the arithmetic mean across observer estimates, for the "default" and "wide" formats, or
+#'   2) the individual observer estimates, for the "complete" format.
 #'   Note that for non-"complete" formats, \code{na.rm = TRUE} is used when calculating the mean,
 #'   and thus blank elements of estimates (but not the whole incomplete estimate) are ignored.
+#'
 #'   To convert the perpendicular distance back to nautical miles,
 #'   one would divide PerpDistKm by 1.852
 #'
@@ -120,13 +122,19 @@
 #'     Species code          \tab SpCode \tab Boat type or mammal, turtle, or pinniped species codes\cr
 #'     Probable species code \tab SpCodeProb \tab Probable mammal species codes; \code{NA} if none or not applicable\cr
 #'     Group size of species - best estimate \tab GsSpBest \tab
-#'       Arithmetic mean, across observer estimates, of the product(s) of GsSchoolBest and the corresponding species percentage\cr
+#'       The product of the arithmetic means of GsSchoolBest and the corresponding species percentage\cr
 #'     Group size of species - high estimate \tab GsSpHigh \tab
-#'       Arithmetic mean, across observer estimates, of the product(s) of GsSchoolHigh and the corresponding species percentage\cr
+#'       The product of the arithmetic means of GsSchoolHigh and the corresponding species percentage\cr
 #'     Group size of species - low estimate \tab GsSpLow \tab
-#'       Arithmetic mean, across observer estimates, of the product(s) of GsSchoolLow and the corresponding species percentage\cr
+#'       The product of the arithmetic means of GsSchoolLow and the corresponding species percentage\cr
 #'   }
 #'
+#'   Note that for the above calculations,
+#'   the GsSchoolX value and corresponding species percentages were each
+#'   averaged across observers, using \code{na.rm = TRUE},
+#'   before being multiplied to calculate GsSpX. For example, in the workflow:
+#'   \code{GsSpBest1 = mean(.data$Data2, na.rm = TRUE) * mean(.data$Data5, na.rm = TRUE)}
+#'
 #' @section The "wide" and "complete" format outputs:
 #'   The "wide" and "complete" options have very similar columns in their output date frames.
 #'   There are two main differences: 1) the "wide" format has one row for each sighting event,
@@ -171,7 +179,8 @@
 #'   For the "wide" format, ObsEstimate is a list-column of all of the observer codes
 #'   that provided an estimate.
 #'   Also in the "wide" format, the GsSpBest# columns are the product of
-#'   GsSchoolBest and the corresponding species percentage.
+#'   the means of GsSchoolBest and the corresponding species percentage
+#'   (see the Default section for calculation details).
 #'   These numbers, 1 to 4, correspond to the order of the data as it appears in the DAS file
 #'
 #' @examples
@@ -197,6 +206,8 @@ das_sight.data.frame <- function(x, ...) {
 das_sight.das_df <- function(x, return.format = c("default", "wide", "complete"),
                              return.events = c("S", "K", "M", "G", "s", "k", "m", "g", "t", "p", "F"),
                              ...) {
+  mean_narm <- function(i) mean(i, na.rm = TRUE)
+
   #----------------------------------------------------------------------------
   return.format <- match.arg(return.format)
   return.events <- match.arg(return.events, several.ok = TRUE)
@@ -322,9 +333,9 @@ das_sight.das_df <- function(x, return.format = c("default", "wide", "complete")
   sight.info.skmg3 <- sight.df %>%
     filter(.data$Event %in% c("?")) %>%
     group_by(.data$sight_cumsum) %>%
-    summarise(Prob = TRUE,
-              SpCodeProb1 = .data$Data5, SpCodeProb2 = .data$Data6,
-              SpCodeProb3 = .data$Data7, SpCodeProb4 = .data$Data8)
+    reframe(Prob = TRUE,
+            SpCodeProb1 = .data$Data5, SpCodeProb2 = .data$Data6,
+            SpCodeProb3 = .data$Data7, SpCodeProb4 = .data$Data8)
 
 
   # Data from numeric events (groupsize and composition estimates)
@@ -350,26 +361,38 @@ das_sight.das_df <- function(x, return.format = c("default", "wide", "complete")
              Data6 = as.numeric(.data$Data6), Data7 = as.numeric(.data$Data7),
              Data8 = as.numeric(.data$Data8)) %>%
       group_by(.data$sight_cumsum) %>%
-      summarise(ObsEstimate = list(.data$Data1),
-                SpPerc1 = mean(.data$Data5, na.rm = TRUE),
-                SpPerc2 = mean(.data$Data6, na.rm = TRUE),
-                SpPerc3 = mean(.data$Data7, na.rm = TRUE),
-                SpPerc4 = mean(.data$Data8, na.rm = TRUE),
-                GsSchoolBest = mean(.data$Data2, na.rm = TRUE),
-                GsSchoolHigh = mean(.data$Data3, na.rm = TRUE),
-                GsSchoolLow = mean(.data$Data4, na.rm = TRUE),
-                GsSpBest1 = mean(.data$Data2 * .data$Data5 / 100, na.rm = TRUE),
-                GsSpBest2 = mean(.data$Data2 * .data$Data6 / 100, na.rm = TRUE),
-                GsSpBest3 = mean(.data$Data2 * .data$Data7 / 100, na.rm = TRUE),
-                GsSpBest4 = mean(.data$Data2 * .data$Data8 / 100, na.rm = TRUE),
-                GsSpHigh1 = mean(.data$Data3 * .data$Data5 / 100, na.rm = TRUE),
-                GsSpHigh2 = mean(.data$Data3 * .data$Data6 / 100, na.rm = TRUE),
-                GsSpHigh3 = mean(.data$Data3 * .data$Data7 / 100, na.rm = TRUE),
-                GsSpHigh4 = mean(.data$Data3 * .data$Data8 / 100, na.rm = TRUE),
-                GsSpLow1 = mean(.data$Data4 * .data$Data5 / 100, na.rm = TRUE),
-                GsSpLow2 = mean(.data$Data4 * .data$Data6 / 100, na.rm = TRUE),
-                GsSpLow3 = mean(.data$Data4 * .data$Data7 / 100, na.rm = TRUE),
-                GsSpLow4 = mean(.data$Data4 * .data$Data8 / 100, na.rm = TRUE))
+      reframe(ObsEstimate = list(.data$Data1),
+              SpPerc1 = mean_narm(.data$Data5),
+              SpPerc2 = mean_narm(.data$Data6),
+              SpPerc3 = mean_narm(.data$Data7),
+              SpPerc4 = mean_narm(.data$Data8),
+              GsSchoolBest = mean_narm(.data$Data2),
+              GsSchoolHigh = mean_narm(.data$Data3),
+              GsSchoolLow = mean_narm(.data$Data4),
+              GsSpBest1 = mean_narm(.data$Data2) * mean_narm(.data$Data5) / 100,
+              GsSpBest2 = mean_narm(.data$Data2) * mean_narm(.data$Data6) / 100,
+              GsSpBest3 = mean_narm(.data$Data2) * mean_narm(.data$Data7) / 100,
+              GsSpBest4 = mean_narm(.data$Data2) * mean_narm(.data$Data8) / 100,
+              GsSpHigh1 = mean_narm(.data$Data3) * mean_narm(.data$Data5) / 100,
+              GsSpHigh2 = mean_narm(.data$Data3) * mean_narm(.data$Data6) / 100,
+              GsSpHigh3 = mean_narm(.data$Data3) * mean_narm(.data$Data7) / 100,
+              GsSpHigh4 = mean_narm(.data$Data3) * mean_narm(.data$Data8) / 100,
+              GsSpLow1  = mean_narm(.data$Data4) * mean_narm(.data$Data5) / 100,
+              GsSpLow2  = mean_narm(.data$Data4) * mean_narm(.data$Data6) / 100,
+              GsSpLow3  = mean_narm(.data$Data4) * mean_narm(.data$Data7) / 100,
+              GsSpLow4  = mean_narm(.data$Data4) * mean_narm(.data$Data8) / 100)
+              # GsSpBest1 = mean(.data$Data2 * .data$Data5 / 100, na.rm = TRUE),
+              # GsSpBest2 = mean(.data$Data2 * .data$Data6 / 100, na.rm = TRUE),
+              # GsSpBest3 = mean(.data$Data2 * .data$Data7 / 100, na.rm = TRUE),
+              # GsSpBest4 = mean(.data$Data2 * .data$Data8 / 100, na.rm = TRUE),
+              # GsSpHigh1 = mean(.data$Data3 * .data$Data5 / 100, na.rm = TRUE),
+              # GsSpHigh2 = mean(.data$Data3 * .data$Data6 / 100, na.rm = TRUE),
+              # GsSpHigh3 = mean(.data$Data3 * .data$Data7 / 100, na.rm = TRUE),
+              # GsSpHigh4 = mean(.data$Data3 * .data$Data8 / 100, na.rm = TRUE),
+              # GsSpLow1 = mean(.data$Data4 * .data$Data5 / 100, na.rm = TRUE),
+              # GsSpLow2 = mean(.data$Data4 * .data$Data6 / 100, na.rm = TRUE),
+              # GsSpLow3 = mean(.data$Data4 * .data$Data7 / 100, na.rm = TRUE),
+              # GsSpLow4 = mean(.data$Data4 * .data$Data8 / 100, na.rm = TRUE))
   }
 
   if (!all(sight.info.skmg1$sight_cumsum %in% sight.info.skmg4$sight_cumsum))

diff --git a/R/swfscDAS-package.R b/R/swfscDAS-package.R
@@ -13,7 +13,7 @@
 #'
 #' @importFrom dplyr add_row arrange between bind_cols bind_rows case_when desc
 #'   distinct everything filter full_join group_by if_else
-#'   lag left_join mutate n n_distinct
+#'   lag left_join mutate n n_distinct reframe
 #'   right_join select slice starts_with summarise ungroup
 #' @importFrom lubridate year month day tz
 #' @importFrom magrittr %>%

diff --git a/README.md b/README.md
@@ -7,9 +7,7 @@
 
 [![CRAN
 version](http://www.r-pkg.org/badges/version/swfscDAS)](https://cran.r-project.org/package=swfscDAS)
-[![R-CMD-check](https://github.com/smwoodman/swfscDAS/workflows/R-CMD-check/badge.svg)](https://github.com/smwoodman/swfscDAS/actions)
-<!-- [![Travis build status](https://travis-ci.com/smwoodman/swfscDAS.svg?branch=master)](https://travis-ci.com/smwoodman/swfscDAS)
-[![AppVeyor build status](https://ci.appveyor.com/api/projects/status/github/smwoodman/swfscDAS?branch=master&svg=true)](https://ci.appveyor.com/project/smwoodman/swfscDAS) -->
+[![R-CMD-check](https://github.com/smwoodman/swfscDAS/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/smwoodman/swfscDAS/actions/workflows/R-CMD-check.yaml)
 <!-- badges: end -->
 
 This package contains functions designed for processing and analyzing
@@ -38,16 +36,6 @@ You can install the developmental version of swfscDAS from
 remotes::install_github("smwoodman/swfscDAS")
 ```
 
-Before installing swfscDAS, you must have
-[R](https://www.r-project.org/),
-[RStudio](https://www.rstudio.com/products/rstudio/download/), and the
-appropriate version of
-[Rtools](https://cran.r-project.org/bin/windows/Rtools/) installed. When
-installing the developmental version, it is best practice to install
-after closing all instances of R and RStudio, and then running the
-install code from the R GUI rather than RStudio. Please contact the
-developer if you have any issues.
-
 ## DAS data format
 
 swfscDAS expects data to follow the conventions and format used by the

diff --git a/build/vignette.rds b/build/vignette.rds