Summarise the manual validation

Runs the whole post-validation step: classifies the reviewed clips and writes, to output_dir:

• validation_by_clip.csv: manifest + verdict of each clip (classify_review());

• precision_by_bin.csv: precision by species x confidence bin (precision_by_bin());

• suggested_thresholds.csv: lowest confidence reaching the target precision, by species (suggest_thresholds());

• nightly_presence.csv: confirmed presence by site x species x night (nightly_presence());

• retraining_clips.csv: positive clips for retraining (retraining_clips());

• precision_by_bin.png: precision curves (plot_precision()), when 'ggplot2' is installed.

Usage

post_validation(
  review_dir,
  manifest_path,
  output_dir,
  positive_pattern = "positiv",
  negative_pattern = "negativ",
  bins = seq(0.1, 1, by = 0.1),
  target_precision = 0.9,
  min_n = 15
)

Arguments

review_dir

Folder with the reviewed clips (the clips folder of the validation package, after the review).

manifest_path

Path to the manifest of the same run as the reviewed clips (clip_manifest.csv, or a v1.2.0 manifesto_clipes.csv).

output_dir

Output folder; created if needed.

positive_pattern, negative_pattern

Regular expressions (case-insensitive) that identify the positive and negative folders in the path of each clip.

bins

Breaks of the confidence bins (left-closed).

target_precision

Target precision.

min_n

Minimum of reviewed clips for a bin to be taken seriously; bins with fewer are flagged in low_support.

Value

A list with the tables validation, precision, thresholds, presence and retraining, invisibly.

Details

This is the function form of the v1.2.0 script pos_validacao.R.