Optimize threshold for clean data extraction.

Usage

optimal_threshold(
  refdata,
  outliers,
  var_col = NULL,
  warn = FALSE,
  verbose = FALSE,
  plot = FALSE
)

Arguments

refdata: dataframe. Species data frame from precleaned analysis.
outliers: datacleaner. Datacleaner output with outliers flagged in multidetect function.
var_col: string. A column with species names if dataset for species is a dataframe not a list. See pred_extract for extracting environmental data.
warn: logical. If TRUE, warning on whether absolute outliers obtained at a low threshold is indicated. Default TRUE.
verbose: logical. If true, then messages about the outlier flagging will be displayed.
plot: logical. to show plot of loess fitted function with minima and maxima (optimal threshold and clean data).

Value

Either a list or dataframe of cleaned records for multiple species.

Examples


if (FALSE) { # \dontrun{

data(jdsdata)
data(efidata)
matchdata <- match_datasets(datasets = list(jds = jdsdata, efi = efidata),
                            lats = 'lat',
                            lons = 'lon',
                            species = c('speciesname','scientificName'),
                            country= c('JDS4_site_ID'),
                            date=c('sampling_date', 'Date'))

datacheck <- check_names(matchdata, colsp= 'species', pct = 90, merge =TRUE)


db <- sf::st_read(system.file('extdata/danube/basinfinal.shp', package='specleanr'), quiet=TRUE)


worldclim <- terra::rast(system.file('extdata/worldclim.tiff', package='specleanr'))

rdata <- pred_extract(data = datacheck,
                      raster= worldclim ,
                      lat = 'decimalLatitude',
                      lon= 'decimalLongitude',
                      colsp = 'speciescheck',
                      bbox = db,
                      multiple = TRUE,
                      minpts = 10,
                      list=TRUE,
                      merge=F)


out_df <- multidetect(data = rdata, multiple = TRUE,
                      var = 'bio6',
                      output = 'outlier',
                      exclude = c('x','y'),
                      methods = c('zscore', 'adjbox','iqr', 'semiqr','hampel'))

#extracting optimal threshold for each species

threshopt <- optimal_threshold(refdata = rdata, outliers = out_df)
} # }