add duplicate counts

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)