nexus/data-pipeline
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix typo in log message

Browse source
This commit is contained in:
Ingrid Werner 2026-02-06 09:05:00 +00:00
parent ee3a056449
commit cf5e45713c
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/transform/clean.py
View file

@ -18,7 +18,7 @@ def normalise_timestamps(df: pd.DataFrame, col: str) -> pd.DataFrame:
def deduplicate(df: pd.DataFrame, key_cols: list[str]) -> pd.DataFrame: def deduplicate(df: pd.DataFrame, key_cols: list[str]) -> pd.DataFrame:
before = len(df) before = len(df)
df = df.drop_duplicates(subset=key_cols, keep="last") df = df.drop_duplicates(subset=key_cols, keep="last")
print(f"[clean] Dedup removed {before - len(df)} rows") print(f"[clean] Deduplicated, removed {before - len(df)} rows")
return df return df