feature: update readme, add more output to ml-pipeline
This commit is contained in:
@@ -27,6 +27,7 @@ def inspect(df: pd.DataFrame) -> None:
|
||||
|
||||
def e1_remove_observations(df: pd.DataFrame) -> pd.DataFrame:
|
||||
"""E1: Ausreisser und fehlerhafte Beobachtungen entfernen."""
|
||||
df.info()
|
||||
before = len(df)
|
||||
df = df[df.Price < 8000000] # nur Werte bis 8000000 berücksichtigen
|
||||
df = df[
|
||||
@@ -134,6 +135,7 @@ def e41_construct(df: pd.DataFrame) -> pd.DataFrame:
|
||||
def e42_clean_names(df: pd.DataFrame) -> pd.DataFrame:
|
||||
"""E4.2: Unerlaubte Zeichen in Spaltennamen durch _ ersetzen."""
|
||||
df.columns = df.columns.str.replace(r"[^a-zA-Z0-9_]", "_", regex=True)
|
||||
df.info()
|
||||
return df
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user