From b8e9592f21cf2c0d3f8bb822a79c8abc5b35adfc Mon Sep 17 00:00:00 2001 From: Pritimay Sarkar Date: Sat, 23 Sep 2023 17:20:12 +0530 Subject: [PATCH] add duplicate counts --- scripts/user_collection.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/user_collection.py b/scripts/user_collection.py index 3c12e1b..c2b5f6d 100644 --- a/scripts/user_collection.py +++ b/scripts/user_collection.py @@ -52,6 +52,8 @@ df = pd.DataFrame(data) print(df) print(df.size) +print("duplicates", len(df['_id']) - len(df['_id'].drop_duplicates())) + # Save the DataFrame to a CSV file output_filename = "data.csv" df.to_csv(output_filename, index=False)