From 6f1e4d988df2d935a7626c5a08ff0f3f1ccc7215 Mon Sep 17 00:00:00 2001 From: Praateek Mahajan Date: Thu, 6 Feb 2025 11:38:30 -0800 Subject: [PATCH] Update examples/exact_deduplication.py Co-authored-by: Sarah Yurick <53962159+sarahyurick@users.noreply.github.com> Signed-off-by: Praateek Mahajan --- examples/exact_deduplication.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/exact_deduplication.py b/examples/exact_deduplication.py index a2e01253..37dfefb6 100644 --- a/examples/exact_deduplication.py +++ b/examples/exact_deduplication.py @@ -53,7 +53,7 @@ def main(args): # cache_dir=output_dir # Optionally write the output to disk ) - # When perform_removal=False, it'll only call .identify_duplicates() and return the duplicates. + # When perform_removal=False, it will only call .identify_duplicates() and return the list of duplicate IDs. # When perform_removal=True then exact_dup outputs dataset with the duplicates removed # It'll behave by calling .identify_duplicates() and .removal() in sequence. duplicates = exact_dup(