_ARIMAAdapter

class _ARIMAAdapter(order: Tuple[int, int, int] = (0, 0, 0), season_length: int = 1, seasonal_order: Tuple[int, int, int] = (0, 0, 0), **kwargs)[source]

Bases: etna.models.statsforecast._StatsForecastBaseAdapter

Adapter for statsforecast.models.ARIMA.

Init model with given params.

Parameters

  • order (Tuple[int, int, int]) – A specification of the non-seasonal part of the ARIMA model: the three components (p, d, q) are the AR order, the degree of differencing, and the MA order.

  • season_length (int) – Number of observations per unit of time. Ex: 24 Hourly data.

  • seasonal_order (Tuple[int, int, int]) – A specification of the seasonal part of the ARIMA model. (P, D, Q) for the AR order, the degree of differencing, the MA order.

  • **kwargs – Additional parameters for statsforecast.models.ARIMA.

Inherited-members

Methods

fit(df, regressors)

Fit statsforecast adapter.

forecast(df[, prediction_interval, quantiles])

Compute predictions on future data from a statsforecast model.

forecast_components(df)

Estimate forecast components.

get_model()

Get statsforecast model that is used inside etna class.

predict(df[, prediction_interval, quantiles])

Compute in-sample predictions from a statsforecast model.

predict_components(df)

Estimate prediction components.
fit(df: pandas.core.frame.DataFrame, regressors: List[str]) → etna.models.statsforecast._StatsForecastBaseAdapter

Fit statsforecast adapter.

Parameters

  • df (pandas.core.frame.DataFrame) – Features dataframe

  • regressors (List[str]) – List of the columns with regressors

Returns

Fitted adapter

Return type

etna.models.statsforecast._StatsForecastBaseAdapter

forecast(df: pandas.core.frame.DataFrame, prediction_interval: bool = False, quantiles: Sequence[float] = ()) → pandas.core.frame.DataFrame

Compute predictions on future data from a statsforecast model.

This method only works on data that goes right after the train.

Parameters

  • df (pandas.core.frame.DataFrame) – Features dataframe

  • prediction_interval (bool) – If True returns prediction interval for forecast

  • quantiles (Sequence[float]) – Levels of prediction distribution

Returns

DataFrame with predictions

Return type

pandas.core.frame.DataFrame

forecast_components(df: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame

Estimate forecast components.

Parameters

df (pandas.core.frame.DataFrame) – features dataframe

Returns

dataframe with forecast components

Return type

pandas.core.frame.DataFrame

get_model() → Union[statsforecast.models.AutoCES, statsforecast.models.AutoARIMA, statsforecast.models.AutoTheta, statsforecast.models.AutoETS, etna.libs.statsforecast.arima.ARIMA]

Get statsforecast model that is used inside etna class.

Returns

Internal model

Return type

Union[statsforecast.models.AutoCES, statsforecast.models.AutoARIMA, statsforecast.models.AutoTheta, statsforecast.models.AutoETS, etna.libs.statsforecast.arima.ARIMA]

predict(df: pandas.core.frame.DataFrame, prediction_interval: bool = False, quantiles: Sequence[float] = ()) → pandas.core.frame.DataFrame

Compute in-sample predictions from a statsforecast model.

This method only works on train data.

Parameters

  • df (pandas.core.frame.DataFrame) – Features dataframe

  • prediction_interval (bool) – If True returns prediction interval for forecast

  • quantiles (Sequence[float]) – Levels of prediction distribution

Returns

DataFrame with predictions

Return type

pandas.core.frame.DataFrame

predict_components(df: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame

Estimate prediction components.

Parameters

df (pandas.core.frame.DataFrame) – features dataframe

Returns

dataframe with prediction components

Return type

pandas.core.frame.DataFrame