Build the validation clip set

Runs the whole first stage: reads the selection tables, selects the clips, cuts them, writes clip_manifest.csv and zips one package per species. This is the function form of the v1.2.0 script extrair_clipes_validacao.R.

Usage

extract_validation_clips(
  data_dir,
  output_dir,
  ...,
  table_pattern = "^BirdNET_SelectionTable\\.txt$",
  make_zip = TRUE,
  simulate = FALSE,
  classifier = NULL
)

Arguments

data_dir

Root folder, searched recursively.

output_dir

Output folder; created if needed.

...

Sampling design, passed to select_clips() (e.g. sampling_mode, n_top, threshold, target_total, remap_from, remap_to).

table_pattern

Regular expression for the table file names.

make_zip

Zip one package per species (skipped when simulate is TRUE).

simulate

If TRUE, no audio is cut (the empty species folders are still created), but status tells what would be done. Useful to check a selection before cutting.

classifier

Label of the classifier that produced the selection tables (e.g. "FrogNet v2, BirdNET-Analyzer 2.4.0"), recorded in extraction_info.csv. NULL records NA.

Value

The manifest written to clip_manifest.csv, invisibly.

Details

Output structure:

<output_dir>/clips/<species_folder>/*.wav
<output_dir>/packages/<species_folder>.zip
<output_dir>/clip_manifest.csv
<output_dir>/extraction_info.csv

extraction_info.csv records the provenance of the run (one key, value row per item): the date, the versions of sheepdog and R, the folder of the selection tables, the classifier label and every argument passed to select_clips(). Keep it with the manifest: it tells later rounds which classifier produced the clips (for instance, to leave out of a validation round the clips used to retrain that classifier).

Examples

if (FALSE) { # \dontrun{
# Check the selection first, then cut
extract_validation_clips("N:/Arara", "N:/Arara/validation",
                         remap_from = "N:/", remap_to = "/Volumes/Arara/",
                         simulate = TRUE)
} # }