TimeFlagsTransform¶
- class TimeFlagsTransform(minute_in_hour_number: bool = True, fifteen_minutes_in_hour_number: bool = False, hour_number: bool = True, half_hour_number: bool = False, half_day_number: bool = False, one_third_day_number: bool = False, out_column: Optional[str] = None)[source]¶
Bases:
etna.transforms.base.Transform,etna.transforms.base.FutureMixinTimeFlagsTransform is a class that implements extraction of the main time-based features from datetime column.
Initialise class attributes.
- Parameters
minute_in_hour_number (bool) – if True: add column with minute number to feature dataframe in transform
fifteen_minutes_in_hour_number (bool) – if True: add column with number of fifteen-minute interval within hour with numeration from 0 to feature dataframe in transform
hour_number (bool) – if True: add column with hour number to feature dataframe in transform
half_hour_number (bool) – if True: add column with 0 for the first half of the hour and 1 for the second to feature dataframe in transform
half_day_number (bool) – if True: add column with 0 for the first half of the day and 1 for the second to feature dataframe in transform
one_third_day_number (bool) – if True: add column with number of 8-hour interval within day with numeration from 0 to feature dataframe in transform
out_column (Optional[str]) –
base for the name of created columns;
if set the final name is ‘{out_column}_{feature_name}’;
if don’t set, name will be
transform.__repr__(), repr will be made for transform that creates exactly this column
- Raises
ValueError – if feature has invalid initial params:
- Inherited-members
Methods
fit(*args, **kwargs)Fit datetime model.
fit_transform(df)May be reimplemented.
inverse_transform(df)Inverse transforms dataframe.
transform(df)Transform method for features based on time.
- fit(*args, **kwargs) etna.transforms.timestamp.time_flags.TimeFlagsTransform[source]¶
Fit datetime model.