Próbuję wykonać poniższy kod ale dostaję błąd:
df_clean = (
df
.rename(columns=lambda x: x.lower().replace(' ', '_')) # Normalize column names
.loc[lambda x: x['supplemental_video_type'].isnull()] # Remove supplementals (trailers, teasers, etc)
.assign(
start_time = lambda x: pd.to_datetime(x['start_time']),
start_time_kz = lambda x: x['start_time'] + pd.DateOffset(hours=1), # Convert to UTC +1 (Poland, Warsaw)
duration = lambda x: pd.to_datetime(x['duration'], format='%H:%M:%S'),
duration_hours = lambda x: x['duration'].dt.hour + x['duration'].dt.minute / 60,
title_clean = lambda x: x['title'].str.replace(': (?i)(part|season|volume|limited series|series|chapter)(.*)', '').str.strip(),
start_date = lambda x: x['start_time_kz'].dt.date,
start_hour = lambda x: x['start_time_kz'].dt.hour,
is_holiday = lambda x: x['start_time_kz'].dt.weekday >= 5,
)
[['profile_name', 'start_time_kz', 'is_holiday', 'start_date', 'start_hour', 'duration_hours', 'title', 'title_clean']]
)
df_clean.sample(5)
FutureWarning: The default value of regex will change from True to False in a future version.
title_clean = lambda x: x['title'].str.replace(': (?i)(part|season|volume|limited series|series|chapter)(.*)', '').str.strip(),
ma ktoś pomysł jak mogę to naprawić?