R/data.R

In trashbirdecology/dubcorms: Unifying BBS and eBird Data for Integrating Modeling

#' # JDAT CONTENTS -----------------------------------------------------------
#' #' Descriptions of JDAT Contents
#' #'
#' #' A simple lookup table for
#' #' @format A data frame
#' #' \describe{
#' #'   \item{level.1.name}{name of the top level list element}
#' #'   \item{level.2.name}{name of the second-level list element}
#' #'   \item{level.1.description}{description of the top level list element}
#' #'   \item{level.2.description}{description of the second-level list element}
#' #'   \item{class}{expected class of object}
#' #'   \item{notes}{supplementary information}
#' #'   \item{length}{if lowest level object is a vector, length of object}
#' #'   \item{rows}{if object is array, number of rows}
#' #'   \item{c}{if object is array, number of cols}
#' #'   \item{s}{if object is 3-D array, number of slices}
#' #' }
#' jdat.contents <-
#'   structure(
#'     list(
#'       level.1.name = c(
#'         "C",
#'         "Xg",
#'         "Xg",
#'         "Xg",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "Xp",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "indexing",
#'         "gam",
#'         "gam",
#'         "gam",
#'         "gam"
#'       ),
#'       level.1.description = c(
#'         "matrix of observed counts",
#'         "grid-level covariates or descriptors",
#'         "grid-level covariates or descriptors",
#'         "grid-level covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "site-level detection covariates or descriptors",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of indexes and scalars used for indexing within JAGS",
#'         "list of data produced by mgcv::jagam",
#'         "list of data produced by mgcv::jagam",
#'         "list of data produced by mgcv::jagam",
#'         "list of data produced by mgcv::jagam"
#'       ),
#'       level.2.name = c(
#'         "",
#'         "area",
#'         "XY",
#'         "prop",
#'         "nobs",
#'         "nmins",
#'         "doy",
#'         "effort_ha",
#'         "obs_id",
#'         "assistant",
#'         "fyrroute",
#'         "fyrbbs",
#'         "noise",
#'         "car",
#'         "wind",
#'         "nsites",
#'         "ngrids",
#'         "nyears",
#'         "ngridsiteyear",
#'         "gridsiteyear.id",
#'         "nmaxgrids",
#'         "sites.id",
#'         "sites.ind",
#'         "year.id",
#'         "year.ind",
#'         "pregam",
#'         "jags.ini",
#'         "jags.fn",
#'         "jags.data"
#'       ),
#'       level.2.description = c(
#'         "",
#'         "area (m^2) of a given grid cell id",
#'         "XY coordinates associated with grid cell id",
#'         "proportion of the BBS route that falls within a given grid cell id",
#'         "number of observers associated with the checklist_id",
#'         "number of minutes reported by observer",
#'         "day of year (where 1 = January 1 YYYY)",
#'         "area searched (hectare)",
#'         "observer identifier for eBird",
#'         "wind index as provided by BBS (may be scaled)",
#'         "wind index as provided by BBS (may be scaled)",
#'         "wind index as provided by BBS (may be scaled)",
#'         "wind index as provided by BBS (may be scaled)",
#'         "wind index as provided by BBS (may be scaled)",
#'         "wind index as provided by BBS (may be scaled)",
#'         "number of unique sites (rteno, checklists) in a given dataset",
#'         "number of unique grid cells in a given dataset",
#'         "number of unique years in a given dataset",
#'         "number of grids within which a BBS route falls ",
#'         "number of grids within which a BBS route falls ",
#'         "maximum number of grid cells within which a RTENO falls (max taken across all RTENO)",
#'         "site identifier as given in original dataset",
#'         "site identifier given from 1:nsites",
#'         "year",
#'         "site identifier given from 1:nsites",
#'         "standard mgcv GAM setup data, as returned in jagam return list.",
#'         "initialization data for smooth coefficients and smoothing parameters.",
#'         "path of where the unedited JAGS GAM model was saved",
#'         "list of arguments to be supplied to JAGS containing information referenced in model specification."
#'       ),
#'       class = c(
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "flat data",
#'         "integer",
#'         "integer",
#'         "integer",
#'         "flat data",
#'         "array",
#'         "integer",
#'         "vector",
#'         "vector",
#'         "vector",
#'         "vector",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       notes = c(
#'         "bbs and ebird only",
#'         "",
#'         "",
#'         "bbs only",
#'         "eBird only",
#'         "eBird only",
#'         "eBird only",
#'         "eBird only",
#'         "eBird only",
#'         "bbs only",
#'         "bbs only",
#'         "bbs only",
#'         "bbs only",
#'         "bbs only",
#'         "bbs only",
#'         "",
#'         "",
#'         "",
#'         "bbs only",
#'         "bbs only",
#'         "bbs only",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       length = c(
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA,
#'         NA
#'       ),
#'       rows = c(
#'         "",
#'         "number of sites",
#'         "number of grid cells in dataset",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "number of sites",
#'         "",
#'         "",
#'         "",
#'         "number of sites",
#'         "number of sites",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       columns = c(
#'         "",
#'         "number of years",
#'         "2",
#'         "number of grid cells in study area",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "number of years",
#'         "",
#'         "",
#'         "",
#'         "number of years",
#'         "number of years",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       slices = c(
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "nMaxGrid",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       r = c(
#'         "",
#'         "s",
#'         "g",
#'         "",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "s",
#'         "",
#'         "",
#'         "",
#'         "s",
#'         "s",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       c = c(
#'         "",
#'         "t",
#'         "2",
#'         "",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "t",
#'         "",
#'         "",
#'         "",
#'         "t",
#'         "t",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       ),
#'       s = c(
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "nMaxGrid",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         "",
#'         ""
#'       )
#'     ),
#'     class = "data.frame",
#'     row.names = c(NA,-29L)
#'   )
#' usethis::use_data(jdat.contents, internal = FALSE, overwrite=TRUE)
#'
#' #' #' # REGION CODES ------------------------------------------------------------
#' #' #' #' Lookup Table for ISO Codes
#' #' #' #'
#' #' #' #'
#' #'
#' #' # grab ebird region codes
#' #' ebird.codes <- auk::ebird_states |>
#' #'   rename()
#' #'
#' #' # grab bbs region codes
#' #' bbs.codes <- bbsAssistant::region_codes |>
#' #'   dplyr::filter(!stringr::str_detect())
#' #'
#' #' setdiff(tolower(bbs.codes$State),toupper(iso.codes$name))
#' #'
#' #' iso.codes <- rnaturalearth::ne_states() |>
#' #'   as.data.frame() |>
#' #'   # tibble::column_to_rownames(name_en) |>
#' #'   dplyr::select(name_en, iso_3166_2, iso_a2, , name_fr, name_es)
#' #'
#' #' # Add a column for eBird file identification
#' #'
#' #' # Add a column for BBS data subsetting
#' #' region.codes <- iso.codes
#' #'
#' #' usethis::use_data(region.codes, internal = FALSE, overwrite=TRUE)
#' # END DATA ----------------------------------------------------------------
#'
#'
#'