TheilSenTrendTransform

class TheilSenTrendTransform(in_column: str, poly_degree: int = 1, **regression_params)

Bases: etna.transforms.base.PerSegmentWrapper

Transform that uses sklearn.linear_model.TheilSenRegressor to find linear or polynomial trend in data.

Warning

This transform can suffer from look-ahead bias. For transforming data at some timestamp it uses information from the whole train part.

Notes

Setting parameter n_subsamples manually might cause the error. It should be at least the number of features (plus 1 if fit_intercept=True) and the number of samples in the shortest segment as a maximum.

Create instance of TheilSenTrendTransform.

Parameters

• in_column (str) – name of processed column

• poly_degree (int) – degree of polynomial to fit trend on

• regression_params – params that should be used to init sklearn.linear_model.TheilSenRegressor

Inherited-members

Methods

fit(df)	Fit transform on each segment.
fit_transform(df)	May be reimplemented.
inverse_transform(df)	Apply inverse_transform to each segment.
transform(df)	Apply transform to each segment separately.