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

add duplicate counts

Browse Source
This commit is contained in:
Pritimay Sarkar
2023-09-23 17:20:12 +05:30
parent 4e486bf8ed
commit b8e9592f21
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/user_collection.py
View File

@@ -52,6 +52,8 @@ df = pd.DataFrame(data)
print(df) print(df)
print(df.size) print(df.size)
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 = "data.csv" output_filename = "data.csv"
df.to_csv(output_filename, index=False) df.to_csv(output_filename, index=False)