Back to models
Transformer

ThetaLinesTransformer

API referenceSource
Unequal length

Decompose the original data into two or more Theta-lines.

Implementation of decomposition for Theta-method [1] as described in [2].

Overview: Input univariate series of length “n” and ThetaLinesTransformer modifies the local curvature of the time series using Theta-coefficient values passed through the parameter theta.

Each Theta-coefficient is applied directly to the second differences of the input series. The resulting transformed series (Theta-lines) are returned as a pd.DataFrame of shape len(input series) * len(theta).

Quickstart

python
from sktime.transformations.theta import ThetaLinesTransformer

estimator = ThetaLinesTransformer(theta=(0, 2))

Parameters(1)

thetasequence of float, default=(0,2)
Theta-coefficients to use in transformation.

Examples

>>> from sktime.transformations.theta import ThetaLinesTransformer
>>> from sktime.datasets import load_airline
>>> y = load_airline ()
>>> transformer = ThetaLinesTransformer ([0, 0.25, 0.5, 0.75 ])
>>> y_thetas = transformer. fit_transform (y)

References

[1]

V.Assimakopoulos et al., “The theta model: a decomposition approach to forecasting”, International Journal of Forecasting, vol. 16, pp. 521-530, 2000.

[2]

E.Spiliotis et al., “Generalizing the Theta method for automatic forecasting “, European Journal of Operational Research, vol. 284, pp. 550-558, 2020.