ChangePointsTrendTransform

class ChangePointsTrendTransform(in_column: str, change_point_model: ruptures.base.BaseEstimator, detrend_model: Type[sklearn.base.RegressorMixin], **change_point_model_predict_params)[source]

Bases: etna.transforms.base.PerSegmentWrapper

ChangePointsTrendTransform subtracts multiple linear trend from series.

Warning

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

Init ChangePointsTrendTransform.

Parameters

  • in_column (str) – name of column to apply transform to

  • change_point_model (ruptures.base.BaseEstimator) – model to get trend change points TODO: replace this parameters with the instance of BaseChangePointsModelAdapter in ETNA 2.0

  • detrend_model (Type[sklearn.base.RegressorMixin]) – model to get trend in data

  • change_point_model_predict_params – params for change_point_model.predict method

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.

load(path)

Load an object.

save(path)

Save the object.

to_dict()

Collect all information about etna object in dict.

transform(df)

Apply transform to each segment separately.