smiuser/hpos-data
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add duplicates count

Browse Source
This commit is contained in:
Pritimay Sarkar
2023-10-05 23:04:45 +05:30
parent e0ef061317
commit 8816fd537e
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/test_collection.py
View File

@@ -57,6 +57,8 @@ df = df[["_id", "classificationResult", "calculatedRatio", "deviceId", "deviceRa
df_count = df.groupby(["classificationResult"]).describe()["calculatedRatio"]["count"] df_count = df.groupby(["classificationResult"]).describe()["calculatedRatio"]["count"]
print(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 # Save the DataFrame to a CSV file
output_filename = f'tests_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx' output_filename = f'tests_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'