Added EMP and FRP data through the end of 2024

DESCRIPTION

@@ -49,7 +49,7 @@ Imports:
     rvest
 URL: https://github.com/InteragencyEcologicalProgram/zooper
 BugReports: https://github.com/InteragencyEcologicalProgram/zooper/issues
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 Suggests: 
     spelling,
     testthat (>= 2.1.0),

NEWS.md

@@ -1,6 +1,7 @@
 # zooper (development version)
 
--   Added EMP data released in June 2025 (sampling from 1972–2023), **which no longer includes amphipods in the macro dataset**; see the [amphipods_notes (EDI 522)](https://portal.edirepository.org/nis/mapbrowse?scope=edi&identifier=522) for more information.
+- Added EMP and FRP data released in May 2026  
+- Added EMP data released in June 2025 (sampling from 1972–2023), **which no longer includes amphipods in the macro dataset**; see the [amphipods_notes (EDI 522)](https://portal.edirepository.org/nis/mapbrowse?scope=edi&identifier=522) for more information.
 -   ~~Fixed issue where EMP macro amphipod counts from before 2014 were being converted to unidentified mysids instead of unidentified amphipods, since amphipods were not identified to species before 2014.~~
 -   Fixed issue with biomass conversion for macro and micro zooplankton. Previously it was not taking into account the count and instead providing the BPUE if 1 individual were present. 
 -   Added the biomass for the surveys and size classes with the appropriate conversation factors and length data. This feature is still experimental

R/Download_utilities.R

@@ -82,10 +82,10 @@ zoop_urls<-function(Sources){
     EMP_name_urls <- paste("https://pasta.lternet.edu/package/name/eml/edi/522", EMP_latest_revision, EMP_entities, sep="/")
     names(EMP_entities) <- purrr::map_chr(EMP_name_urls, ~Tryer(n=3, fun=readLines, con=.x, warn = FALSE))
 
-    out$EMP$Meso<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2023_CBMatrix_EDI"])
-    out$EMP$Micro<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2023_PumpMatrix_EDI"])
-    out$EMP$Macro<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2023_MysidMatrix_EDI"])
-    out$EMP$Lengths<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2023_Mysid_Length_Data_EDI"])
+    out$EMP$Meso<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2024_CBMatrix_EDI"])
+    out$EMP$Micro<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2024_PumpMatrix_EDI"])
+    out$EMP$Macro<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2024_MysidMatrix_EDI"])
+    out$EMP$Lengths<-paste0(EMP_pkg_url, "/", EMP_entities["1972-2024_Mysid_Length_Data_EDI"])
 
   }
 
@@ -159,3 +159,6 @@ zoop_urls<-function(Sources){
 
   return(out)
 }
+
+#set options to allow access to EDI without signing in
+#options(HTTPUserAgent="EDI_CodeGen")

R/data.R

@@ -2,7 +2,7 @@
 #'
 #' A crosswalk table relating the taxonomic code used by each dataset to current scientific names, life stages, and taxonomic hierarchies.
 #'
-#' @format a tibble with 404 rows and 34 variables
+#' @format a tibble with 471 rows and 37 variables
 #' \describe{
 #'   \item{EMP_Micro}{Taxonomic codes used in the Environmental Monitoring Program microzooplankton (43 \eqn{\mu}m) mesh dataset}
 #'   \item{EMP_Meso}{Taxonomic codes used in the Environmental Monitoring Program mesozooplankton (160 \eqn{\mu}m) mesh dataset}
@@ -36,6 +36,8 @@
 #'   \item{twentymmstart2}{First year the 20mm Survey restarted counting this taxa}
 #'   \item{DOPstart}{First year DOP starting counting this taxa}
 #'   \item{DOPend}{Last year DOP counted this taxa}
+#'   \item{FRPstart}{First year FRP starting counting this taxa}
+#'   \item{FRPend}{Last year FRP counted this taxa}
 #'   }
 #' @seealso \code{\link{Zoopdownloader}}, \code{\link{Zoopsynther}}, \code{\link{zooper}}
 "crosswalk"
@@ -57,7 +59,7 @@
 #'
 #' Latitudes and longitudes for each zooplankton station.
 #'
-#' @format a tibble with 387 rows and 4 columns
+#' @format a tibble with 399 rows and 4 columns
 #' \describe{
 #'   \item{Source}{Abbreviated name of the source dataset}
 #'   \item{Station}{Sampling station name}
@@ -71,7 +73,7 @@
 #'
 #' Latitudes and longitudes for EMP EZ stations on each sampling date from 2004 to present.
 #'
-#' @format a tibble with 491 rows and 4 columns
+#' @format a tibble with 575 rows and 4 columns
 #' \describe{
 #'   \item{Date}{Date sample was collected}
 #'   \item{Station}{Sampling station name}
@@ -85,7 +87,7 @@
 #'
 #' All source zooplankton datasets combined into one tibble.
 #'
-#' @format a tibble with 3,615,105 rows and 14 columns.
+#' @format a tibble with 3,833,994 rows and 14 columns.
 #' \describe{
 #'   \item{Source}{Abbreviated name of the source dataset. "EMP"=Environmental Monitoring Program, "FRP"=Fish Restoration Program, "FMWT"= Fall Midwater Trawl, "STN"= Townet Survey, "20mm" =20mm survey, "DOP" = Directed Outflow Project Lower Trophic Study, and "YBFMP"= Yolo Bypass Fish Monitoring Program.}
 #'   \item{SizeClass}{Net size class. Micro corresponds to 43-50 \eqn{\mu}m mesh, Meso corresponds to 150-160 \eqn{\mu}m mesh, and Macro corresponds to 500-505 \eqn{\mu}m mesh. However, prior to 1974 EMP macrozooplankton were sampled with a 930 \eqn{\mu}m mesh net.}
@@ -112,7 +114,7 @@
 #' Accessory environmental data from the combined zooplankton dataset. Not all datasets report all environmental parameters.
 #'
 #' @encoding UTF-8
-#' @format a tibble with 44,690 rows and 20 columns
+#' @format a tibble with 48,933 rows and 20 columns
 #' \describe{
 #'   \item{Source}{Abbreviated name of the source dataset.  "EMP"=Environmental Monitoring Program, "FRP"=Fish Restoration Program, "FMWT"= Fall Midwater Trawl, "STN"= Townet Survey, "20mm" =20mm survey, "DOP" = Directed Outflow Project Lower Trophic Study, and "YBFMP"= Yolo Bypass Fish Monitoring Program.}
 #'   \item{Year}{Year sample was collected}

R/zoop_downloader.R

@@ -134,7 +134,7 @@ Zoopdownloader <- function(
       dplyr::filter(!is.na(.data$SampleDate))%>%
       dplyr::mutate(SampleDate=lubridate::parse_date_time(.data$SampleDate, "%m/%d/%Y", tz="America/Los_Angeles"),
                     Datetime=lubridate::parse_date_time(dplyr::if_else(is.na(.data$Time), NA_character_, paste(.data$SampleDate, .data$Time)),
-                                                        c("%Y-%m-%d %I:%M %p"), tz="Etc/GMT+8"), #create a variable for datetime
+                                                        c("%Y-%m-%d %H:%M"), tz="Etc/GMT+8"), #create a variable for datetime
                     Datetime=lubridate::with_tz(.data$Datetime, "America/Los_Angeles"))%>% # Ensure everything ends up in local time
       tidyr::pivot_longer(cols=c(-"SampleDate", -"StationNZ", -"Time", -"Secchi", -"Chl_a", -"Temperature",
                                  -"ECSurfacePreTow", -"ECBottomPreTow", -"Volume", -"Datetime", -"Depth"),
@@ -823,7 +823,6 @@ Zoopdownloader <- function(
                                                   CommonName == "Palaemonetes" ~ "Palaemon",
                                                   CommonName == "Hymenoptera UNID" ~ "Hymenoptera Other",
                                                   CommonName == "Asellidae UNID" ~ "Asellidae",
-                                                  CommonName == "Diptera adult" ~ "Diptera Adult",
                                                   CommonName == "Coleoptera other" ~ "Coleoptera Other",
                                                   CommonName == "Tricoptera larvae UNID"~"Trichoptera larvae Other",
                                                   TRUE ~ CommonName))
@@ -903,7 +902,7 @@ Zoopdownloader <- function(
     data.list[["EMP_Macro"]] <- zoo_EMP_Macro%>%
       dplyr::mutate(SampleDate=lubridate::parse_date_time(.data$SampleDate, "%m/%d/%Y", tz="America/Los_Angeles"),
                     Datetime=lubridate::parse_date_time(dplyr::if_else(is.na(.data$Time), NA_character_, paste(.data$SampleDate, .data$Time)),
-                                                        c("%Y-%m-%d %I:%M %p"), tz="Etc/GMT+8"), #create a variable for datetime
+                                                        c("%Y-%m-%d %H:%M"), tz="Etc/GMT+8"), #create a variable for datetime
                     Datetime=lubridate::with_tz(.data$Datetime, "America/Los_Angeles"))%>% # Ensure everything ends up in local time
       tidyr::pivot_longer(cols=c(-"SampleDate", -"Time", -"Datetime", -"StationNZ", -"Secchi", -"Chl_a", -"Temperature",
                                  -"ECSurfacePreTow", -"ECBottomPreTow", -"Volume", -"Depth"),

data-raw/EZ_stations.csv

@@ -557,3 +557,23 @@ NZEZ6SJR,12/4/2023,38.02171,-121.8073
 NZEZ2SJR,12/4/2023,38.04548,-121.6952
 NZEZ2,12/6/2023,38.12078,-121.7008
 NZEZ6,12/6/2023,38.07955,-121.7616
+NZEZ2SJR,2024-01-03,38.03355,-121.7176
+NZEZ6,2024-01-05,38.06473,-121.8441
+NZEZ2,2024-01-05,38.06417,-121.7917
+NZEZ2,2024-02-06,38.04848,-121.9154
+NZEZ6,2024-02-06,38.05835,-121.9602
+NZEZ6,2024-04-19,38.0598,-122.0023
+NZEZ2,2024-04-19,38.05653,-121.9664
+NZEZ6,2024-05-17,38.06454,-122.0364
+NZEZ2,2024-06-17,38.0596,-121.9812
+NZEZ6,2024-06-17,38.0596,-121.9812
+NZEZ6,2024-07-16,38.04959,-121.9249
+NZEZ2,2024-07-16,38.06318,-121.8238
+NZEZ6,2024-08-16,38.04704,-121.8993
+NZEZ2,2024-08-16,38.06195,-121.8165
+NZEZ2,2024-09-13,38.0625,-121.8186
+NZEZ6,2024-09-13,38.05059,-121.8825
+NZEZ6,2024-10-10,38.06509,-121.8346
+NZEZ2,2024-10-10,38.07302,-121.775
+NZEZ6,2024-12-11,38.06281,-121.8228
+NZEZ2,2024-12-11,38.07899,-121.7615

data-raw/crosswalk-zoopComb-zoopEnvComb-startDates.R

@@ -35,6 +35,8 @@ zoopComb <- zoop$Zooplankton
 
 zoopEnvComb <- zoop$Environment
 
+
+
 startDates<-zoopComb%>%
   dplyr::left_join(zoopEnvComb%>%
                      dplyr::select(Date, SampleID),
@@ -46,3 +48,4 @@ startDates<-zoopComb%>%
 
 usethis::use_data(zoopComb, zoopEnvComb, startDates, crosswalk, overwrite = TRUE)
 
+