libre/hsparse
libre/hsparse
4
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

Count unique values per column

Browse source
This commit is contained in:
Jeff Moe 2024-09-19 19:26:23 -06:00
parent 5b02a6198f
commit e08dfc02f7
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
hsparse/parse_csv_contacts.py
View file

@ -78,11 +78,15 @@ def csv_non_empty(CSV):
col: df[col].count() for col in df.columns if not df[col].isnull().all() col: df[col].count() for col in df.columns if not df[col].isnull().all()
} }
sorted_columns = sorted(non_empty_columns.items(), key=lambda x: x[1], reverse=True) unique_counts = {col: df[col].nunique() for col in non_empty_columns.keys()}
sorted_columns = sorted(unique_counts.items(), key=lambda x: x[1], reverse=True)
print("Column\tNon-empty values\tUnique values")
if sorted_columns: if sorted_columns:
for col, count in sorted_columns: for col, unique_count in sorted_columns:
print(f"{col}: {count}") count = non_empty_columns[col]
print(f"{col}\t{count}\t{unique_count}")
else: else:
print("No non-empty values found.") print("No non-empty values found.")