This R Markdown document is designed to transform data that is not in CWP format into CWP format. Initially, it changes the format of the data; subsequently, it maps the data to adhere to CWP standards. This markdown is automatically created from the function: https://raw.githubusercontent.com/firms-gta/geoflow-tunaatlas/refs/heads/master/R/tunaatlas_scripts/pre-harmonization/west_pacific_ocean_effort_5deg_1m_bb_tunaatlaswcpfc_level0.R, the documentation keeps the format of roxygen2 skeleton.
A summary of the mapping process is provided. The path to the dataset is specified. You will find on this same repository on GitHub the first line of each dataset. The datasets are named after the historical name provided by tRFMOs while exporting and may change. The information provided in the Rmd allows understanding correctly which dataset should be used in this markdown.
Additional operations are performed next to verify other aspects of the data, such as the consistency of the geolocation, the values, and the reported catches in numbers and tons.
If you are interested in further details, the results and codes are available for review.
Each .Rmd script requires the user to knit the
dataset at the beginning of the script in order to execute the
harmonization process correctly. It is also possible to run the code
chunk by chunk but be sure to be in the correct working directory (i.e.,
the one of the .Rmd).
path_to_raw_dataset <- here::here('R/tunaatlas_scripts/pre-harmonization', 'wcpfc', 'effort', 'data', 'WCPFC_P_PUBLIC_BY_YY_MM.csv')Harmonize WCPFC Pole-and-line Effort Datasets
This function harmonizes the WCPFC Pole-and-line effort datasets, preparing them for integration into the Tuna Atlas database according to specified format requirements.
@return None; the function outputs files directly, including harmonized datasets, optional metadata, and code lists for integration within the Tuna Atlas database.
@details This function modifies the dataset to ensure compliance with the standardized format, including renaming, reordering, and recalculating specific fields as necessary. Metadata integration is contingent on the intended use within the Tuna Atlas database.
@import dplyr @import tidyr @import reshape @importFrom stringr str_replace @seealso for converting WCPFC Driftnet data structure, @export @keywords data harmonization, fisheries, WCPFC, tuna @author Paul Taconet, IRD @author Bastien Grasset, IRD
# Input data sample:
# YY MM LAT5 LON5 DAYS SKJ_C YFT_C OTH_C
# 1950 1 30N 135E 0 0 0 0
# 1950 1 30N 140E 0 0 0 0
# 1950 1 35N 140E 0 0 0 0
# 1950 1 40N 140E 0 0 0 0
# 1950 1 40N 145E 0 0 0 0
# 1950 2 30N 135E 0 0 0 0
# Effort: pivot data sample:
# YY MM LAT5 LON5 Effort EffortUnits School Gear
# 1950 1 30N 135E 0 DAYS ALL P
# 1950 1 30N 140E 0 DAYS ALL P
# 1950 1 35N 140E 0 DAYS ALL P
# 1950 1 40N 140E 0 DAYS ALL P
# 1950 1 40N 145E 0 DAYS ALL P
# 1950 2 30N 135E 0 DAYS ALL P
# Effort: final data sample:
# Flag Gear time_start time_end AreaName School EffortUnits Effort
# ALL P 1970-03-01 1970-04-01 6200150 ALL DAYS 82
# ALL P 1970-04-01 1970-05-01 6200150 ALL DAYS 74
# ALL P 1970-05-01 1970-06-01 6200150 ALL DAYS 82
# ALL P 1970-06-01 1970-07-01 6200150 ALL DAYS 81
# ALL P 1970-07-01 1970-08-01 6200150 ALL DAYS 75
# ALL P 1970-12-01 1971-01-01 6200150 ALL DAYS 56
#packages
if(!require(foreign)){
install.packages("foreign")
require(foreign)
}
if(!require(reshape)){
install.packages("reshape")
require(reshape)
}
if(!require(tidyr)){
install.packages("tidyr")
require(tidyr)
}
if(!require(dplyr)){
install.packages("dplyr")
require(dplyr)
}
# Historical name for the dataset at source WCPFC_P_PUBLIC_BY_YR_MON.csv
opts <- options()
options(encoding = "UTF-8")
##Efforts
DF <- read.csv(path_to_raw_dataset)
colnames(DF) <- toupper(colnames(DF))
DF$CWP_GRID <- NULL
DF <- DF %>% tidyr::gather(variable, value, -c(colnames(DF[1:5])))
DF <- DF %>% dplyr::filter(!value %in% 0) %>% dplyr::filter(!is.na(value))
DF$variable <- as.character(DF$variable)
colnames(DF)[which(colnames(DF) == "variable")] <- "Species"
DF$CatchUnits <- substr(DF$Species, nchar(DF$Species), nchar(DF$Species))
DF$CatchUnits <- toupper(DF$CatchUnits)
DF$Species <- toupper(DF$Species)
DF$Species <- sub("_C", "", DF$Species)
DF$Species <- sub("_N", "", DF$Species)
DF$School <- "OTH"
DF$EffortUnits <- colnames(DF[5])
colnames(DF)[5] <- "Effort"
efforts_pivot_WCPFC <- DF; rm(DF)
#-------------
#Gear
efforts_pivot_WCPFC$Gear<-"P"
# Catchunits
index.kg <- which( efforts_pivot_WCPFC[,"CatchUnits"] == "C" )
efforts_pivot_WCPFC[index.kg,"CatchUnits"]<- "t"
index.nr <- which( efforts_pivot_WCPFC[,"CatchUnits"] == "N" )
efforts_pivot_WCPFC[index.nr,"CatchUnits"]<- "no"
# School
efforts_pivot_WCPFC$School<-"OTH"
colToKeep_efforts <- c("FishingFleet","Gear","time_start","time_end","AreaName","School","EffortUnits","Effort")
source("https://raw.githubusercontent.com/firms-gta/geoflow-tunaatlas/master/R/sardara_functions/WCPFC_CE_efforts_pivotDSD_to_harmonizedDSD.R")
efforts<-WCPFC_CE_efforts_pivotDSD_to_harmonizedDSD(efforts_pivot_WCPFC,colToKeep_efforts)
colnames(efforts)<-c("fishing_fleet","gear_type","time_start","time_end","geographic_identifier","fishing_mode","measurement_unit","measurement_value")
efforts$source_authority<-"WCPFC"
efforts$measurement <- "effort"
#----------------------------------------------------------------------------------------------------------------------------
efforts$time_start <- as.Date(efforts$time_start)
efforts$time_end <- as.Date(efforts$time_end)
dataset_temporal_extent <- paste(
paste0(format(min(efforts$time_start), "%Y"), "-01-01"),
paste0(format(max(efforts$time_end), "%Y"), "-12-31"),
sep = "/"
)
efforts$measurement_processing_level <- "unknown"
# output in same folder as path_to_raw_dataset
output_name_dataset <- here::here('R/tunaatlas_scripts/pre-harmonization', 'wcpfc', 'effort', 'data', 'WCPFC_P_PUBLIC_BY_YY_MM_harmonized.csv')
write.csv(efforts, output_name_dataset, row.names = FALSE)
georef_dataset <- efforts
#----------------------------------------------------------------------------------------------------------------------------@ Load pre-harmonization scripts and apply mappings
download.file('https://raw.githubusercontent.com/firms-gta/geoflow-tunaatlas/master/R/tunaatlas_scripts/pre-harmonization/map_codelists_no_DB.R', destfile = 'local_map_codelists_no_DB.R')
source('local_map_codelists_no_DB.R')
fact <- "effort"
mapping_codelist <- map_codelists_no_DB(fact, mapping_dataset = "https://raw.githubusercontent.com/fdiwg/fdi-mappings/main/global/firms/gta/codelist_mapping_rfmos_to_global.csv", dataset_to_map = georef_dataset, mapping_keep_src_code = FALSE, summary_mapping = TRUE, source_authority_to_map = c("IATTC", "CCSBT", "WCPFC", "ICCAT", "IOTC"))##
## mapping dimension gear_type with code list mapping##
## mapping dimension fishing_fleet with code list mapping##
## mapping dimension fishing_mode with code list mapping##
## mapping dimension measurement_unit with code list mapping@ Handle unmapped values and save the results
georef_dataset <- mapping_codelist$dataset_mapped %>% dplyr::mutate(fishing_fleet = ifelse(fishing_fleet == 'UNK', 'NEI', fishing_fleet), gear_type = ifelse(gear_type == 'UNK', '99.9', gear_type))
data.table::fwrite(mapping_codelist$recap_mapping, here::here('R/tunaatlas_scripts/pre-harmonization', 'wcpfc', 'effort', 'data', 'WCPFC_P_PUBLIC_BY_YY_MM_recap_mapping.csv'))
data.table::fwrite(mapping_codelist$not_mapped_total, here::here('R/tunaatlas_scripts/pre-harmonization', 'wcpfc', 'effort', 'data', 'WCPFC_P_PUBLIC_BY_YY_MM_not_mapped_total.csv'))
data.table::fwrite(georef_dataset, here::here('R/tunaatlas_scripts/pre-harmonization', 'wcpfc', 'effort', 'data', 'WCPFC_P_PUBLIC_BY_YY_MM_CWP_dataset.csv'))Display the first few rows of the mapping summaries
print(head(mapping_codelist$recap_mapping))## # A tibble: 4 × 5
## src_code trg_code src_codingsystem trg_codingsystem source_authority
## <chr> <chr> <chr> <chr> <chr>
## 1 DAYS FDAYS effortunit_wcpfc effortunit_rfmos WCPFC
## 2 OTH OTH schooltype_wcpfc schooltype_rfmos WCPFC
## 3 ALL NEI flag_wcpfc fishingfleet_firms WCPFC
## 4 P 09.1 gear_wcpfc isscfg_revision_1 WCPFC