Read the validation tables for calibration — read

Stacks the validation_by_clip.csv tables of several sites (output of post_validation()) and keeps the clips with a positive or negative verdict and a confidence score. Tables written by v1.2.0 (validacao_por_clipe.csv) are also read. Whole-recording clips of "random_recordings" have no confidence and are left out.

Usage

read_validations(files, site_map = NULL, keep = NULL)

Arguments

files: Paths to the validation_by_clip.csv files. Missing files are skipped with a warning.
site_map: Optional named character vector to fix diverging site names, as c(old = "new"), e.g. c(BEP2 = "BEP").
keep: Optional character vector of input columns to retain, e.g. c("source_audio", "night") for grouped cross-validation. Missing columns raise an error rather than silently falling back to clip folds.

Value

A tibble with site and species (factors; species is the species folder code), confidence, logit_conf (logit of the confidence, bounded at 1e-4 and 1 - 1e-4) and tp (1 = true positive, 0 = false positive), plus the columns requested in keep.