Transformer

Deseasonalizer

Remove seasonal components from a time series.

Applies statsmodels.tsa.seasonal.seasonal_compose and removes the seasonal component in transform. Adds seasonal component back again in inverse_transform. Seasonality removal can be additive or multiplicative.

fit computes seasonal components and stores them in seasonal_ attribute.

transform aligns seasonal components stored in seasonal_ with the time index of the passed series and then subtracts them (“additive” model) from the passed series or divides the passed series by them (“multiplicative” model).

Schnellstart

python

from sktime.transformations.detrend import Deseasonalizer

estimator = Deseasonalizer(sp=1, model='additive')

Parameter(2)

spint, default=1: Seasonal periodicity.
model{“additive”, “multiplicative”}, default=”additive”: Model to use for estimating seasonal component.

Beispiele

>>> from sktime.transformations.detrend import Deseasonalizer
>>> from sktime.datasets import load_airline
>>> y = load_airline ()
>>> transformer = Deseasonalizer ()
>>> y_hat = transformer. fit_transform (y)