mixins¶

Classes

`ModelForecastingMixin`()	Base class for model mixins.
`MultiSegmentModelMixin`(base_model)	Mixin for holding methods for multi-segment prediction.
`NonPredictionIntervalContextIgnorantModelMixin`()	Mixin for models that don't support prediction intervals and don't need context for prediction.
`NonPredictionIntervalContextRequiredModelMixin`()	Mixin for models that don't support prediction intervals and need context for prediction.
`PerSegmentModelMixin`(base_model)	Mixin for holding methods for per-segment prediction.
`PredictionIntervalContextIgnorantModelMixin`()	Mixin for models that support prediction intervals and don't need context for prediction.
`PredictionIntervalContextRequiredModelMixin`()	Mixin for models that support prediction intervals and need context for prediction.
`SaveNNMixin`()	Implementation of `AbstractSaveable` torch related classes.

class ModelForecastingMixin[source]¶: Base class for model mixins.

class MultiSegmentModelMixin(base_model: Any)[source]¶

Mixin for holding methods for multi-segment prediction.

It currently isn’t working with prediction intervals and context.

Init MultiSegmentModel.

Parameters: base_model (Any) – Internal model which will be used to forecast segments, expected to have fit/predict interface

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.models.mixins.MultiSegmentModelMixin[source]¶

Fit model.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
Returns: Model after fit
Return type: etna.models.mixins.MultiSegmentModelMixin

get_model() → Any[source]¶

Get internal model that is used inside etna class.

Internal model is a model that is used inside etna to forecast segments, e.g. catboost.CatBoostRegressor or sklearn.linear_model.Ridge.

Returns: Internal model
Return type: Any

class NonPredictionIntervalContextIgnorantModelMixin[source]¶

Mixin for models that don’t support prediction intervals and don’t need context for prediction.

forecast(ts: etna.datasets.tsdataset.TSDataset, return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions.

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
return_components (bool) – If True additionally returns forecast components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

predict(ts: etna.datasets.tsdataset.TSDataset, return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions with using true values as autoregression context if possible (teacher forcing).

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
return_components (bool) – If True additionally returns prediction components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

class NonPredictionIntervalContextRequiredModelMixin[source]¶

Mixin for models that don’t support prediction intervals and need context for prediction.

forecast(ts: etna.datasets.tsdataset.TSDataset, prediction_size: int, return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions.

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context for models that require it.
return_components (bool) – If True additionally returns forecast components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

predict(ts: etna.datasets.tsdataset.TSDataset, prediction_size: int, return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions with using true values as autoregression context if possible (teacher forcing).

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context for models that require it.
return_components (bool) – If True additionally returns prediction components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

class PerSegmentModelMixin(base_model: Any)[source]¶

Mixin for holding methods for per-segment prediction.

Init PerSegmentModelMixin.

Parameters: base_model (Any) – Internal model which will be used to forecast segments, expected to have fit/predict interface

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.models.mixins.PerSegmentModelMixin[source]¶

Fit model.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
Returns: Model after fit
Return type: etna.models.mixins.PerSegmentModelMixin

get_model() → Dict[str, Any][source]¶

Get internal models that are used inside etna class.

Internal model is a model that is used inside etna to forecast segments, e.g. catboost.CatBoostRegressor or sklearn.linear_model.Ridge.

Returns: dictionary where key is segment and value is internal model
Return type: Dict[str, Any]

class PredictionIntervalContextIgnorantModelMixin[source]¶

Mixin for models that support prediction intervals and don’t need context for prediction.

forecast(ts: etna.datasets.tsdataset.TSDataset, prediction_interval: bool = False, quantiles: Sequence[float] = (0.025, 0.975), return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions.

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
prediction_interval (bool) – If True returns prediction interval for forecast
quantiles (Sequence[float]) – Levels of prediction distribution. By default 2.5% and 97.5% are taken to form a 95% prediction interval
return_components (bool) – If True additionally returns forecast components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

predict(ts: etna.datasets.tsdataset.TSDataset, prediction_interval: bool = False, quantiles: Sequence[float] = (0.025, 0.975), return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions with using true values as autoregression context if possible (teacher forcing).

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
prediction_interval (bool) – If True returns prediction interval for forecast
quantiles (Sequence[float]) – Levels of prediction distribution. By default 2.5% and 97.5% are taken to form a 95% prediction interval
return_components (bool) – If True additionally returns prediction components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

class PredictionIntervalContextRequiredModelMixin[source]¶

Mixin for models that support prediction intervals and need context for prediction.

forecast(ts: etna.datasets.tsdataset.TSDataset, prediction_size: int, prediction_interval: bool = False, quantiles: Sequence[float] = (0.025, 0.975), return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions.

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context for models that require it.
prediction_interval (bool) – If True returns prediction interval for forecast
quantiles (Sequence[float]) – Levels of prediction distribution. By default 2.5% and 97.5% are taken to form a 95% prediction interval
return_components (bool) – If True additionally returns forecast components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

predict(ts: etna.datasets.tsdataset.TSDataset, prediction_size: int, prediction_interval: bool = False, quantiles: Sequence[float] = (0.025, 0.975), return_components: bool = False) → etna.datasets.tsdataset.TSDataset[source]¶

Make predictions with using true values as autoregression context if possible (teacher forcing).

Parameters

ts (etna.datasets.tsdataset.TSDataset) – Dataset with features
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context for models that require it.
prediction_interval (bool) – If True returns prediction interval for forecast
quantiles (Sequence[float]) – Levels of prediction distribution. By default 2.5% and 97.5% are taken to form a 95% prediction interval
return_components (bool) – If True additionally returns prediction components

Returns

Dataset with predictions

Return type

etna.datasets.tsdataset.TSDataset

class SaveNNMixin[source]¶

Implementation of AbstractSaveable torch related classes.

It saves object to the zip archive with 2 files:

metadata.json: contains library version and class name.
object.pt: object saved by torch.save.

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.