Update lps_sharks with new data, rewrite get_lps_sharks for new dataset

data-raw/get_lps_sharks.R

@@ -1,49 +1,58 @@
-## HMS sharks occurence on the shelf
-# Data from MRIP - https://www.fisheries.noaa.gov/recreational-fishing-data/recreational-fishing-data-downloads
-# Seleted species from categories from Duartes lists from observer data
+## HMS sharks from Large Pelagics Survey (LPS)
+## Provided by HMS Cliff Hutt
+## Last updated 2/6/2025
 library(tidyverse)
+library(readxl)
 
-raw.hms.dir <- here::here("data-raw/hms-mrip")
+# Establish directory and define input file name
 raw.dir <- here::here("data-raw")
+lps_xlsx <- "LPS Pelagic Shark Harvest Estimates 2002-2024.xlsx"
 
 get_lps_sharks <- function(save_clean = F){
-  ## Bring in data
-  lps_csv <- "LPS_shark_catch.csv"
-  species_list <- "species_list.csv"
-  hms_cat<- "hms_sp_category.csv"
+  # Load and format data for SOE
+  lps_sharks <- readxl::read_excel(file.path(raw.dir,lps_xlsx), sheet = "Sheet3") |>
+    janitor::row_to_names(1) |>
+    dplyr::select(-"(blank)")
 
-  d <- read.csv(file.path(raw.dir,lps_csv))
-  sp <- read.csv(file.path(raw.hms.dir,species_list)) %>%
-    dplyr::rename(SP_CODE = sp_code) %>%
-    dplyr::select(SP_CODE, COMMON_NAME)
-  sp_cat <- read.csv(file.path(raw.hms.dir,hms_cat))
+  # Split dataset into MAB and NE subsets
+  # MAB
+  lps_sharks_mab <- lps_sharks[2:24,] |>
+    dplyr::mutate(Units = "N of Fish",
+                  EPU = "MAB") |>
+    dplyr::rename("Total" = "Grand Total",
+                  "Year" = "Row Labels",
+                  "Blue_Shark" = "BLUE SHARK",
+                  "Common_Thresher" = "COMMON THRESHER",
+                  "Shortfin_Mako" = "SHORTFIN MAKO") |>
+    tidyr::pivot_longer(cols = c("Blue_Shark",
+                                 "Common_Thresher",
+                                 "Shortfin_Mako",
+                                 "Total"),
+                        names_to = "Var", values_to = "Value") |>
+    dplyr::select(Year, Var, Value, EPU, Units)
 
- region<- data.frame(State.Area = c("VIRGINIA" ,"MARYLAND/DELAWARE","SOUTH NEW JERSEY", "NORTH NEW JERSEY","NEW YORK",
-            "CONNECTICUT/RHODE ISLAND", "MASSACHUSETTS","NEW HAMPSHIRE/MAINE"),
-                    EPU = c("MAB","MAB","MAB","MAB","MAB","MAB","NE", "NE"))
+  # NE
+  lps_sharks_ne <- lps_sharks[26:48,] |>
+    dplyr::mutate(Units = "N of Fish",
+                  EPU = "NE") |>
+    dplyr::rename("Total" = "Grand Total",
+                  "Year" = "Row Labels",
+                  "Blue_Shark" = "BLUE SHARK",
+                  "Common_Thresher" = "COMMON THRESHER",
+                  "Shortfin_Mako" = "SHORTFIN MAKO") |>
+    tidyr::pivot_longer(cols = c("Blue_Shark",
+                                 "Common_Thresher",
+                                 "Shortfin_Mako",
+                                 "Total"),
+                        names_to = "Var", values_to = "Value") |>
+    dplyr::select(Year, Var, Value, EPU, Units)
 
-  ## select those in NEUS Shelf
-  lps_sharks<- d %>%
-    dplyr::rename("COMMON_NAME" = Species,
-                  "Total_Catch" = "Total.Catch..Kept.Alive.Dead.") %>%
-    dplyr::mutate(COMMON_NAME=recode(COMMON_NAME, 'PORBEAGLE SHARK'='PORBEAGLE',
-                                     'COMMON THRESHER'='THRESHER SHARK')) %>%
-    dplyr::filter(!Total_Catch == ".") %>%
-    left_join(sp_cat, by= "COMMON_NAME") %>%
-    left_join(region, by = "State.Area") %>%
-    dplyr::group_by(Year, SP_CATEGORY, EPU) %>%
-    dplyr::mutate(Total_Catch = as.numeric(Total_Catch)) %>%
-    dplyr::summarise(Value = sum(Total_Catch)) %>%
-    dplyr::rename( Time = Year,
-                   Var = SP_CATEGORY) %>%
-    dplyr::mutate(Units = "N of Fish")%>%
-    dplyr::select(Time, Var, Value, EPU, Units)
+  lps_sharks <- rbind(lps_sharks_mab, lps_sharks_ne)
 
   # metadata ----
   attr(lps_sharks, "tech-doc_url") <- "https://noaa-edab.github.io/tech-doc/recreational-shark-fishing-indicators.html"
   attr(lps_sharks, "data_files")   <- list(
-    lps_csv = lps_csv,
-    hms_cat = hms_cat)
+    lps_xlsx = lps_xlsx)
   attr(lps_sharks, "data_steward") <- c(
     "Kimberly Bastille <[email protected]>")