diff --git a/scripts/test_collection.py b/scripts/test_collection.py
index c32b43a..c8cc58b 100644
--- a/scripts/test_collection.py
+++ b/scripts/test_collection.py
@@ -57,6 +57,8 @@ df = df[["_id", "classificationResult", "calculatedRatio", "deviceId", "deviceRa
 df_count = df.groupby(["classificationResult"]).describe()["calculatedRatio"]["count"]
 print(df.groupby(["classificationResult"]).describe()["calculatedRatio"]["count"])
 
+print("duplicates", len(df['_id']) - len(df['_id'].drop_duplicates()))
+
 # Save the DataFrame to a CSV file
 output_filename = f'tests_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'