Skip to content

Adaptation to the latest RDBES data format & fixed bug with lower hierarchies #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Kasia-MIR wants to merge 2 commits into
base: dev
Choose a base branch
from
Draft

Adaptation to the latest RDBES data format & fixed bug with lower hierarchies #24

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ffd7272
Update preprocessSamplingDataForCoverage.R
Kasia-MIR Oct 16, 2025
402b327
fixed bug with lower hierarchies
Kasia-MIR Oct 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 20 additions & 16 deletions R/preprocessSamplingDataForCoverage.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,8 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
if (verbose) {
print("Preparing sample data")
}
#check hierarchy

# Check hierarchy
H <- unique(RDBESDataObject[["DE"]]$DEhierarchy)
if (verbose) {
print(paste0("Upper hierarchy: ", H))
Expand Down Expand Up @@ -67,7 +68,7 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
# obtain the key to FO, in order to extract time information from there
SA <- merge(
RDBESDataObject[["SA"]],
RDBEScore::createTableOfRDBESIds(RDBESDataObject) |> dplyr::select(SAid, OSid, BVid, FMid, DEid, SDid) |> dplyr::distinct()
RDBEScore:::createTableOfRDBESIds(RDBESDataObject) |> dplyr::select(SAid, OSid, BVid, FMid, DEid, SDid) |> dplyr::distinct()
)
SA <- merge(SA, RDBESDataObject[["OS"]] |> dplyr::select(OSid, OSsamDate), by = "OSid")
SA$month <- stringr::str_sub(SA$OSsamDate, 6, 7)
Expand All @@ -79,7 +80,7 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
}
SA <- merge(
RDBESDataObject[["SA"]],
RDBEScore::createTableOfRDBESIds(RDBESDataObject) |> dplyr::select(SAid, BVid, FMid, DEid, SDid) |> dplyr::distinct()
RDBEScore:::createTableOfRDBESIds(RDBESDataObject) |> dplyr::select(SAid, BVid, FMid, DEid, SDid) |> dplyr::distinct()
)
}

Expand All @@ -88,34 +89,36 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
RDBESDataObject[["DE"]] |> dplyr::select(DEid, DEsampScheme, DEyear, DEhierarchy),
by = "DEid")

# Add general info (SD)
if (generalVar) {
#add general information
SD <- merge(SA, RDBESDataObject[["SD"]] |> dplyr::select(SDid, SDctry), by = "SDid")
SD <- merge(SA, RDBESDataObject[["SD"]] |> dplyr::select(SDid, SDctry)|>distinct(), by = "SDid")
}
if (bioVar) {
#add biological variables and frequancy measures
#lower hierarchy: A
if (length(RDBESDataObject[["FM"]]) != 0 &&
length(RDBESDataObject[["BV"]]) != 0) {
if (nrow(RDBESDataObject[["FM"]]) != 0 &&
nrow(RDBESDataObject[["BV"]]) != 0) {
FM <- SA |> dplyr::mutate(SAFMid = paste0(SAid, FMid)) |> # I add new variable to don't lose intomation about lower hierarchy D
dplyr::left_join(
RDBESDataObject[["FM"]] |>
dplyr::mutate(SAFMid = paste0(SAid, FMid)) |>
dplyr::select(SAFMid, FMclassMeas, FMnumAtUnit, FMtypeMeas,FMmethod),
by = "SAFMid"
)

BVar <- FM |>
dplyr::left_join(
RDBESDataObject[["BV"]] |> dplyr::select(BVid, BVfishId, BVtypeMeas, BVvalueMeas, BVvalUnitScale,BVmethod),
RDBESDataObject[["BV"]] |> dplyr::select(BVid, BVfishId, BVtypeMeas, BVvalueMeas, BVvalUnitScale,BVspecType),
by = "BVid"
)
#SD information
if (generalVar) {
SA <- merge(SD |> select(BVid, SDctry), BVar, by = "BVid")
SA <- merge(BVar,RDBESDataObject[["SD"]] |> select(SDid, SDctry)|>distinct(), by = "SDid")
}
}
if (length(RDBESDataObject[["FM"]]) != 0 &&
length(RDBESDataObject[["BV"]]) == 0) {
if (nrow(RDBESDataObject[["FM"]]) != 0 &&
nrow(RDBESDataObject[["BV"]]) == 0) {
#lower hierarchy: B
BVar <- SA |> dplyr::mutate(SAFMid = paste0(SAid, FMid)) |> # I add new variable to don't lose intomation about lower hierarchy D
dplyr::left_join(
Expand All @@ -129,8 +132,8 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
SA <- merge(SD |> dplyr::mutate(SAFMid = paste0(SAid, FMid)), BVar, by = "SAFMid")
}
}
if (length(RDBESDataObject[["FM"]]) == 0 &&
length(RDBESDataObject[["BV"]]) != 0) {
if (nrow(RDBESDataObject[["FM"]]) == 0 &&
nrow(RDBESDataObject[["BV"]]) != 0) {
#lower hierarchy: C
BVar <- SA |> dplyr::mutate(SABVid = paste0(SAid, BVid)) |> # I add new variable to don't lose intomation about lower hierarchy
dplyr::left_join(
Expand All @@ -142,7 +145,7 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
BVfishId,
BVtypeMeas,
BVvalueMeas,
BVmethod,
BVspecType,
BVvalUnitScale
),
by = "SABVid"
Expand All @@ -152,8 +155,8 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
SA <- merge(SD |> dplyr::mutate(paste0(SAid, BVid)), BVar, by = "SABVid")
}
}
if (length(RDBESDataObject[["FM"]]) == 0 &&
length(RDBESDataObject[["BV"]]) == 0) {
if (nrow(RDBESDataObject[["FM"]]) == 0 &&
nrow(RDBESDataObject[["BV"]]) == 0) {
#lower hierarchy: D
print(
"No frequency measure and biological variables data.
Expand Down Expand Up @@ -206,5 +209,6 @@ preprocessSamplingDataForCoverage <- function(RDBESDataObject,
month = NA
)
}
SA

return(SA)
}