Skip to content

Commit

Permalink
Printing PID of duplicate entries
Browse files Browse the repository at this point in the history
Signed-off-by: George Araújo <george.gcac@gmail.com>
  • Loading branch information
george-gca committed Jan 16, 2025
1 parent 871d159 commit 4657d9b
Showing 1 changed file with 8 additions and 2 deletions.
10 changes: 8 additions & 2 deletions asreviewcontrib/datatools/dedup.py
Original file line number Diff line number Diff line change
Expand Up @@ -125,8 +125,14 @@ def deduplicate_data(asdata: ASReviewData, args: Namespace) -> None:

if len(duplicate_entries) > 0:
print("Duplicate entries:")
for i, row in duplicate_entries.iterrows():
print(f"\tLine {i} - {row['title']}")

if args.pid in duplicate_entries.columns:
for i, row in duplicate_entries.iterrows():
print(f"\tLine {i} - {args.pid} "
f"{row[args.pid]} - {row['title']}")
else:
for i, row in duplicate_entries.iterrows():
print(f"\tLine {i} - {row['title']}")

asdata.df.reset_index(drop=True, inplace=True)

Expand Down

0 comments on commit 4657d9b

Please sign in to comment.