Skip to content
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.

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

Fix filtering of QualityCurrentID column #121

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion R/import_bbs_data.R
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ ObsN <- RTENO <- Date <- TotalSpp <- NULL # bind variable to avoid CMD CHK WARN
fns.50stop[stringr::str_detect(tolower(fns.50stop), pattern = ".zip")] # to remove the dir that isnt a .zip

fns.routes <- list.files(path = paste0(bbs_dir),
pattern = "routes.zip",
pattern = "outes.zip",
full.names = TRUE)
fns.vehicle <- list.files(path = paste0(bbs_dir),
pattern = "ehicle",
Expand Down
17 changes: 15 additions & 2 deletions R/import_species_list.R
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,18 @@
#' @export import_species_list
import_species_list <- function(bbs_dir){
fn <- list.files(bbs_dir, full.names=TRUE, pattern="SpeciesList")
species_list <- readr::read_fwf(fn, skip=c(9))## currently the best function for guessing the fixed widths...

# read first 50 lines to determine n linse to skip
species_list <- readr::read_fwf(fn, n_max = 50, show_col_types = FALSE)

# newest version has different n rows of text at the top so use line row to
# find start of table
ln_row <- stringr::str_which(species_list[[1]], "---")

species_list <- readr::read_fwf(fn, skip = ln_row - 2, show_col_types = FALSE)## currently the best function for guessing the fixed widths...
## unfortunately, need to manually assign row 1 as header and remove the "line" row
# names=as.vector(c(species_list[1,]))

temp <- lapply(species_list[1, ], as.character)
species_list <- species_list[-c(1:2),]

Expand All @@ -19,7 +28,11 @@ import_species_list <- function(bbs_dir){
species_list$AOU <- as.integer(as.character(species_list$AOU))

## Join this species list with the package data list
species_list <- dplyr::left_join(species_list, bbsAssistant::species_list)
species_list <- dplyr::left_join(species_list,
bbsAssistant::species_list %>% select(-Seq),
by = dplyr::join_by(AOU, English_Common_Name,
Spanish_Common_Name, ORDER, Family,
Genus, Species))

return(species_list)
}
5 changes: 4 additions & 1 deletion R/munge_bbs_data.R
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,9 @@ munge_bbs_data <-
CountryNum <- RPID <-
iso_a2 <- ObsFirstYearOnRTENO <- ObsFirstYearOnBBS <- NULL

# Change name that matches column to avoid confusion
QualityCurrentIDIn <- QualityCurrentID

# SPATIOTEMPORAL SUBSETTING -----------------------------------------------
## SPATIAL SUBSETTING OBSERVATIONS ---------------------------------------------------
# grab region codes
Expand Down Expand Up @@ -141,7 +144,7 @@ munge_bbs_data <-
## the last code in this chunk (.remove.rtenos) should allow only one filter on either
### weather or vehicle_data to take place, but needs to be tested.
myweather <-
bbs_list$weather %>% dplyr::filter(QualityCurrentID %in% QualityCurrentID &
bbs_list$weather %>% dplyr::filter(QualityCurrentID %in% QualityCurrentIDIn &
RPID %in% rpid)
mycars <- bbs_list$vehicle_data <- bbs_list$vehicle_data %>% dplyr::filter(RPID %in% rpid)

Expand Down
40 changes: 40 additions & 0 deletions R/update_sb_items.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
update_sb_items <- function(bbs_par_id = "52b1dfa8e4b0d9b325230cd9",
res_par_id = "5ea835e082cefae35a1fada7"){
bbs_ch <- sbtools::item_list_children(bbs_par_id)

bbs_ch_hist <- sbtools::item_list_children(bbs_ch[[2]]$id)

res_ch <- sbtools::item_list_children(res_par_id)

make_df <- function(x){
df <- data.frame(sb_parent = x$parentId, sb_item = x$id,
sb_title = x$title, sb_link = x$link$url)

df %>%
dplyr::mutate(
release_year = stringr::str_extract(sb_title, "(\\d\\d\\d\\d.*) Release", group = 1),
year_start = stringr::str_extract(sb_title, "(\\d\\d\\d\\d).?-.?\\d\\d\\d\\d", group = 1),
year_end = stringr::str_extract(sb_title, "\\d\\d\\d\\d.?-.?(\\d\\d\\d\\d)", group = 1),
data_type = ifelse(stringr::str_detect(sb_title, "esults"), "results", "observations"),
legacy_format = ifelse(stringr::str_detect(sb_title, "legacy"), "y", "n")
)
}

lst_items <- c(list(bbs_ch[[1]]), bbs_ch_hist, res_ch)

new_sb_items <- lapply(lst_items, make_df) %>% dplyr::bind_rows()

if(is.null(sb_items)){
sb_items <- data.frame(sb_item = letters[1:10])
}

add_rows <- dplyr::anti_join(new_sb_items, sb_items, by = "sb_item")

if(nrow(add_rows) > 0){
message("returning sb_items with", nrow(add_rows), " new rows")

return(new_sb_items)
} else {
return(sb_items)
}
}