add esa_salmon data sets

Author: eeholmes

R/atsalibrary-package.R

@@ -12,10 +12,10 @@
 #' * [neon_barc]
 #' * [MLCO2]
 #' * [NHTemp]
-#' 
+#' * [esa_salmon]
 #'
 #' @name atsalibrary-package
-#' @aliases atsalibrary
+#' @aliases atsalibrary-package
 #' @docType package
 #' @keywords package
 NULL

R/esa-salmon-data.R

@@ -0,0 +1,45 @@
+#' Annual spawner data from Endangered and Threatened PNW salmonids
+#'
+#' @description The data set has yearly spawner counts for endangered and threatened ESU (Evolutionary Significant Units) and DPS (Distinct Population Segments) in the Washington and Oregon. Data were downloaded from  [Coordinated Assessments API](https://www.streamnet.org/resources/exchange-tools/rest-api-documentation/). Coordinated 
+#' Assessments data eXchange (CAX) is developed by the Coordinated Assessments Partnership (CAP).
+#' 
+#' @details There are two datasets included:  `esa.salmon` and `columbia.river`.  The Columbia River data set is a subset of the `esa.salmon` dataset that has all the ESUs and DPSs.
+#' The dataset has the following columns
+#' * species: Chinook, Coho, Steelhead, Chum, Sockeye
+#' * esu_dps: name of the ESU
+#' * majorpopgroup: biological major group
+#' * commonpopname: common population name, generally a stream or river
+#' * run: run-timing
+#' * spawningyear: the year that the spawners were counted on the spawning grounds
+#' * spawner: total (natural-born and hatchery-born) spawners on the spawning ground. Generally some type of redd-count expansion or some other stream count of spawners. Redd = a gravel nest.
+#' * log.spawners: log of value
+#' 
+#' @docType data
+#' 
+#' @name esa_salmon
+#' 
+#' @aliases esa.salmon columbia.river
+#'
+#' @usage data(esa_salmon)
+#' 
+#' @format Objects of class \code{"data.frame"}.  Columns are species, 
+#' esu_dps, majorpopgroup, commonpopname, run, spawningyear, spawner, log.spawner
+#'
+#' @keywords datasets
+#'
+#' @source 
+#' \href{https://www.streamnet.org/cap/current-hli/}{CAP} StreamNet Coordinated Assessments Partnership (CAP) standardized high-level indicators (HLIs) for Natural Origin Spawner Abundance (NOSA).
+#' 
+#' @references 
+#' rCAX: https://zenodo.org/records/10214433
+#'
+#' @examples
+#' data(esa.salmon)
+#' df <- esa.salmon %>% subset(species == "Steelhead" & run == "Winter")
+#' ggplot(df, aes(x=spawningyear, y=log.spawner, color=majorpopgroup)) + 
+#'   geom_point(size=0.2) + 
+#'   theme(strip.text.x = element_text(size = 2)) +
+#'   theme(axis.text.x = element_text(size = 5, angle = 90)) +
+#'   facet_wrap(~esapopname)
+"esa.salmon"
+"columbia.river"

data/esa_salmon.RData

@@ -0,0 +1,97 @@
+# Create data files
+# remotes:::install_github("nwfsc-cb/rCAX@*release")
+library(rCAX)
+library(tidyr)
+library(stringr)
+library(dplyr)
+x <-  rCAX:::caxesu
+valid_esu <- which(!str_detect(x, "XN") & !str_detect(x,"N/A"))
+esa.salmon <- NULL
+for(i in valid_esu){
+  esuname <- rCAX:::caxesu[i]
+  print(esuname)
+  a <- rcax_hli("NOSA", type="colnames")
+  tab <- rcax_hli("NOSA", flist = list(esu_dps = esuname))
+  # error no data
+  if (!is.data.frame(tab)) next
+  # find the pops with no data and remove
+  tab <- tab %>% 
+    subset((datastatus == "Final" | datastatus == "Reviewed") & bestvalue=="Yes")
+  if(tab$tsaej[1]=="") tab$value <- tab$tsaij else tab$value <- tab$tsaej
+  aa <- tab %>% 
+    group_by(esapopname, run) %>% 
+    summarize(n = sum(value!= "" & value!="0" & majorpopgroup != ""))
+  bad <- aa[which(aa$n==0),]
+  aa <- tab %>% 
+    group_by(esapopname, run) %>% 
+    summarize(n = any(duplicated(spawningyear)))
+  df <- tab %>% 
+    subset(!(esapopname %in% bad$esapopname & run %in% bad$run)) %>%
+    mutate(value = as.numeric(value))
+  
+  # get the min and max years in data
+  years <- min(df$spawningyear[!is.na(df$value)]):max(df$spawningyear[!is.na(df$value)])
+  # fill out the missing years with NAs
+  df <- df %>%
+    select(species, esu_dps, majorpopgroup, esapopname, commonpopname, spawningyear, value, run) %>% 
+    group_by(species, esu_dps, majorpopgroup, esapopname, commonpopname, run) %>% 
+    complete(spawningyear=years, fill=list(value=NA))
+  
+  # Deal with pops with multiple data
+  if(any(aa$n)){
+    cat(aa$esapopname[aa$n], "has duplicated years\n")
+    df <- df %>% ungroup() %>%
+      group_by(species, esu_dps, majorpopgroup, esapopname, run, spawningyear) %>%
+      summarize(value = mean(value, na.rm = TRUE,
+                             commonpopname = commonpopname[1]))
+  }
+  esa.salmon <- bind_rows(esa.salmon, df)
+}
+esa.salmon <- esa.salmon %>% subset(species != "") %>% ungroup()
+esa.salmon$log.spawner <- log(esa.salmon$value)
+esa.salmon <- rename(esa.salmon, spawner = value)
+
+columbia.river <- NULL
+for(i in c(17, 20, 15, 11, 2)){
+  esuname <- rCAX:::caxesu[i]
+  a <- rcax_hli("NOSA", type="colnames")
+  tab <- rcax_hli("NOSA", flist = list(esu_dps = esuname))
+  # find the pops with no data and remove
+  tab <- tab %>% 
+    subset((datastatus == "Final" | datastatus == "Reviewed") & bestvalue=="Yes")
+  if(i == 17 | i == 20) tab$value <- tab$tsaij else tab$value <- tab$tsaej
+  aa <- tab %>% 
+    group_by(esapopname, run) %>% 
+    summarize(n = sum(value!= "" & value!="0" & majorpopgroup != ""))
+  bad <- aa[which(aa$n==0),]
+  aa <- tab %>% 
+    group_by(esapopname, run) %>% 
+    summarize(n = any(duplicated(spawningyear)))
+  df <- tab %>% 
+    subset(!(esapopname %in% bad$esapopname & run %in% bad$run)) %>%
+    mutate(value = as.numeric(value))
+  
+  # get the min and max years in data
+  years <- min(df$spawningyear[!is.na(df$value)]):max(df$spawningyear[!is.na(df$value)])
+  # fill out the missing years with NAs
+  df <- df %>%
+    select(species, esu_dps, majorpopgroup, esapopname, commonpopname, spawningyear, value, run) %>% 
+    group_by(species, esu_dps, majorpopgroup, esapopname, commonpopname, run) %>% 
+    complete(spawningyear=years, fill=list(value=NA))
+  
+  # Deal with pops with multiple data
+  if(any(aa$n)){
+    cat(aa$esapopname[aa$n], "has duplicated years\n")
+    df <- df %>% ungroup() %>%
+      group_by(species, esu_dps, majorpopgroup, esapopname, run, spawningyear) %>%
+      summarize(value = mean(value, na.rm = TRUE,
+                             commonpopname = commonpopname[1]))
+  }
+  if(i == 17 | i == 20) df$value_type <- "tsaij" else df$value_type <- "tsaej"
+  columbia.river <- bind_rows(columbia.river, df)
+}
+columbia.river <- columbia.river %>% subset(species != "") %>% ungroup()
+columbia.river$log.spawner <- log(columbia.river$value)
+columbia.river <- rename(columbia.river, spawner = value)
+save(esa.salmon, columbia.river, file=here::here("data", "esa_salmon.RData"))
+