coreforecast.lag_transforms
Lag
lag
(int): Number of periods to offset__init__
stack
take
transform
update
RollingMean
lag
(int): Number of periods to offset by before applying the transformation.window_size
(int): Length of the rolling window.min_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
RollingStd
lag
(int): Number of periods to offset by before applying the transformation.window_size
(int): Length of the rolling window.min_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
RollingMin
lag
(int): Number of periods to offset by before applying the transformation.window_size
(int): Length of the rolling window.min_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
RollingMax
lag
(int): Number of periods to offset by before applying the transformation.window_size
(int): Length of the rolling window.min_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
RollingQuantile
lag
(int): Number of periods to offset by before applying the transformationp
(float): Quantile to computewindow_size
(int): Length of the rolling windowmin_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
SeasonalRollingMean
lag
(int): Number of periods to offset by before applying the transformationseason_length
(int): Length of the seasonal period, e.g. 7 for weekly datawindow_size
(int): Length of the rolling windowmin_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
SeasonalRollingStd
lag
(int): Number of periods to offset by before applying the transformationseason_length
(int): Length of the seasonal period, e.g. 7 for weekly datawindow_size
(int): Length of the rolling windowmin_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
SeasonalRollingMin
lag
(int): Number of periods to offset by before applying the transformationseason_length
(int): Length of the seasonal period, e.g. 7 for weekly datawindow_size
(int): Length of the rolling windowmin_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
SeasonalRollingMax
lag
(int): Number of periods to offset by before applying the transformationseason_length
(int): Length of the seasonal period, e.g. 7 for weekly datawindow_size
(int): Length of the rolling windowmin_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
SeasonalRollingQuantile
lag
(int): Number of periods to offset by before applying the transformationp
(float): Quantile to computeseason_length
(int): Length of the seasonal period, e.g. 7 for weekly datawindow_size
(int): Length of the rolling windowmin_samples
(int, optional): Minimum number of samples required to compute the statistic. If None, defaults to window_size.__init__
stack
take
transform
update
ExpandingMean
lag
(int): Number of periods to offset by before applying the transformation__init__
stack
take
transform
update
ExpandingStd
lag
(int): Number of periods to offset by before applying the transformation__init__
stack
take
transform
update
ExpandingMin
lag
(int): Number of periods to offset by before applying the transformation__init__
stack
take
transform
update
ExpandingMax
lag
(int): Number of periods to offset by before applying the transformation__init__
stack
take
transform
update
ExpandingQuantile
__init__
stack
take
transform
update
ExponentiallyWeightedMean
lag
(int): Number of periods to offset by before applying the transformationalpha
(float): Smoothing factor__init__
stack
take
transform
update