_AutoARIMAAdapter

class _AutoARIMAAdapter(**kwargs)[source]

Bases: etna.models.sarimax._SARIMAXBaseAdapter

Class for holding auto arima model.

Notes

We use auto ARIMA [1] model from pmdarima package.

Init auto ARIMA model with given params.

Parameters

**kwargs – Training parameters for auto_arima from pmdarima package.

Inherited-members

Methods

fit(df, regressors)

Fits a SARIMAX model.

forecast(df, prediction_interval, quantiles)

Compute autoregressive predictions from a SARIMAX model.

get_model()

Get statsmodels.tsa.statespace.sarimax.SARIMAXResultsWrapper that is used inside etna class.

predict(df, prediction_interval, quantiles)

Compute predictions from a SARIMAX model and use true in-sample data as lags if possible.