## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

## ----eval = FALSE-------------------------------------------------------------
# library(leakaudit)
# 
# # 1. Hash every image and record which split it currently belongs to
# hashes <- compute_hashes(
#   paths = image_paths,
#   split = split_labels
# )
# 
# # 2. Cluster images into near-duplicate groups
# grouped <- find_duplicate_groups(hashes, threshold = 5)
# 
# # 3. Audit: how much leakage is there?
# report <- dhash_audit(grouped)
# print(report)
# 
# # 4. Clean: reassign leaked groups to a single split
# clean <- clean_splits(grouped, priority = c("train", "val", "test"))

## -----------------------------------------------------------------------------
library(leakaudit)

groups <- data.frame(
  path     = c("a.jpg", "b.jpg", "c.jpg", "d.jpg", "e.jpg"),
  split    = c("train", "test", "train", "val", "test"),
  group_id = c(1, 1, 2, 3, 3),
  stringsAsFactors = FALSE
)

report <- dhash_audit(groups)
report

## -----------------------------------------------------------------------------
clean_splits(groups)