Working preflight

2025-08-29 16:54:31 -04:00
parent b025daaa2a
commit 7ef5a83ff2
2 changed files with 1 additions and 1 deletions
@@ -76,6 +76,7 @@ def export_groups_for_review(df, col, group_col, min_number_in_group, path_lengt
    """
    Compute longest common paths, group filepaths, write CSV for review.
    """
+    df = df.drop_duplicates(subset=[col], keep='first')
    df = add_longest_common_two_local(df, col=col, new_col=group_col)
    grouped = df.groupby(group_col)[col].apply(list).reset_index()
    grouped = grouped.sort_values(by=col)