StatsForecastAutoARIMA

class StatsForecastAutoARIMA(start_p: int = 2, d: int | None = None, start_q: int = 2, max_p: int = 5, max_d: int = 2, max_q: int = 5, start_P: int = 1, D: int | None = None, start_Q: int = 1, max_P: int = 2, max_D: int = 1, max_Q: int = 2, max_order: int = 5, sp: int = 1, seasonal: bool = True, stationary: bool = False, information_criterion: str = 'aicc', test: str = 'kpss', seasonal_test: str = 'seas', stepwise: bool = True, n_jobs: int = 2, trend: bool = True, method: str | None = None, offset_test_args: str | None = None, seasonal_test_args: dict | None = None, trace: bool = False, n_fits: int = 94, with_intercept: bool = True, approximation: bool | None = None, truncate: bool | None = None, blambda: float | None = None, biasadj: bool = False, parallel: bool = False)[source]

StatsForecast AutoARIMA estimator.

Direct interface to statsforecast.models.AutoARIMA by Nixtla.

This estimator directly interfaces AutoARIMA, from statsforecast [2] by Nixtla. The statsforecast implementation is inspired by Hyndman’s forecast::auto.arima [1].

Returns best ARIMA model according to either AIC, AICc or BIC value. The function conducts a search over possible model within the order constraints provided.

Parameters:

start_p: int (default 2)

Starting value of p in stepwise procedure.

d: int optional (default None)

Order of first-differencing. If missing, will choose a value based on test.

start_q: int (default 2)

Starting value of q in stepwise procedure.

max_p: int (default 5)

Maximum value of p.

max_d: int (default 2)

Maximum number of non-seasonal differences

max_q: int (default 5)

Maximum value of q.

start_P: int (default 1)

Starting value of P in stepwise procedure.

D: int optional (default None)

Order of seasonal-differencing. If missing, will choose a value based on season_test.

start_Q: int (default 1)

Starting value of Q in stepwise procedure.

max_P: int (default 2)

Maximum value of P.

max_D: int (default 1)

Maximum number of seasonal differences

max_Q: int (default 2)

Maximum value of Q.

max_order: int (default 5)

Maximum value of p+q+P+Q if model selection is not stepwise.

sp: int (default 1)

Number of observations per unit of time. For example 24 for Hourly data.

seasonal: bool (default True)

If False, restricts search to non-seasonal models.

stationary: bool (default False)

If True, restricts search to stationary models.

information_criterion: str (default ‘aicc’)

Information criterion to be used in model selection. It can be chosen from among the following strings: - ‘aicc’ for Akaike’s information criterion corrected. - ‘aic’ for Akaike’s information criterion. - ‘bic’ for bayesian information criterion.

test: str (default ‘kpss’)

Type of unit root test to use. See ndiffs for details. Only ‘kpss’ for the Kwiatkowski-Phillip-Schmidt-Shin test is allowed.

seasonal_test: str (default ‘seas’)

This determines which method is used to select the number of seasonal differences. The default method (‘seas’) is to use a measure of seasonal strength computed from an STL decomposition. Other possibilities involve seasonal unit root tests. Only ‘seas’ is allowed.

stepwise: bool (default True)

If True, will do stepwise selection (faster). Otherwise, it searches over all models. Non-stepwise selection can be very slow, especially for seasonal models.

n_jobs: int (default 2)

Allows the user to specify the amount of parallel processes to be used if parallel = True and stepwise = False. If None, then the number of logical cores is automatically detected and all available cores are used.

trend: bool (default True)

If True, models with drift terms are considered.

method: str optional (default None)

fitting method: maximum likelihood or minimize conditional sum-of-squares. The default (unless there are missing values) is to use conditional-sum-of-squares to find starting values, then maximum likelihood. Can be abbreviated. It can be chosen from among the following strings:

‘CSS-ML’ for conditional sum-of-squares to find starting values and then maximum likelihood.
‘ML’ for maximum likelihood.
‘CSS’ for conditional sum-of-squares.

offset_test_args: dict optional (default None)

Additional arguments to be passed to the unit root test.

seasonal_test_args: dict optional (default None)

Additional arguments to be passed to the seasonal unit root test. See nsdiffs for details.

trace: bool (default False)

If True, the list of ARIMA models considered will be reported.

n_fits: int (default 94)

Maximum number of models considered in the stepwise search.

with_intercept: bool (default True)

If True, models with a non-zero mean are considered.

approximation: bool optional (default None)

If True, estimation is via conditional sums of squares and the information criteria used for model selection are approximated. The final model is still computed using maximum likelihood estimation. Approximation should be used for long time series or a high seasonal period to avoid excessive computation times.

truncate: bool optional (default None)

An integer value indicating how many observations to use in model selection. The last truncate values of the series are used to select a model when truncate is not None and approximation=True. All observations are used if either truncate=None or approximation=False.

blambda: float optional (default None)

Box-Cox transformation parameter. If lambda=”auto”, then a transformation is automatically selected using BoxCox.lambda. The transformation is ignored if None. Otherwise, data transformed before model is estimated.

biasadj: bool (default False)

Use adjusted back-transformed mean for Box-Cox transformations. If transformed data is used to produce forecasts and fitted values, a regular back transformation will result in median forecasts. If biasadj is True, an adjustment will be made to produce mean forecasts and fitted values.

parallel: bool (default False)

If True and stepwise = False, then the specification search is done in parallel. This can give a significant speedup on multicore machines.

Attributes:

cutoff: Cut-off = “present time” state of forecaster.
fh: Forecasting horizon that was passed.
is_fitted: Whether fit has been called.
state: State of the estimator.

References

[1]

https://github.com/robjhyndman/forecast

[2]

https://github.com/Nixtla/statsforecast

Examples

>>> from sktime.datasets import load_airline
>>> from sktime.forecasting.statsforecast import StatsForecastAutoARIMA
>>> y = load_airline()
>>> forecaster = StatsForecastAutoARIMA(
...     sp=12, d=0, max_p=2, max_q=2
... )
>>> forecaster.fit(y)
StatsForecastAutoARIMA(...)
>>> y_pred = forecaster.predict(fh=[1,2,3])

Methods

`check_is_fitted`([method_name])	Check if the estimator has been fitted.
`clone`()	Obtain a clone of the object with same hyper-parameters and config.
`clone_tags`(estimator[, tag_names])	Clone tags from another object as dynamic override.
`create_test_instance`([parameter_set])	Construct an instance of the class, using first test parameter set.
`create_test_instances_and_names`([parameter_set])	Create list of all test instances and a list of names for them.
`fit`(y[, X, fh])	Fit forecaster to training data.
`fit_predict`(y[, X, fh, X_pred])	Fit and forecast time series at future horizon.
`get_class_tag`(tag_name[, tag_value_default])	Get class tag value from class, with tag level inheritance from parents.
`get_class_tags`()	Get class tags from class, with tag level inheritance from parent classes.
`get_config`()	Get config flags for self.
`get_fitted_params`([deep])	Get fitted parameters.
`get_param_defaults`()	Get object's parameter defaults.
`get_param_names`([sort])	Get object's parameter names.
`get_params`([deep])	Get a dict of parameters values for this object.
`get_pretrained_params`([deep])	Get pretrained parameters of this estimator.
`get_tag`(tag_name[, tag_value_default, ...])	Get tag value from instance, with tag level inheritance and overrides.
`get_tags`()	Get tags from instance, with tag level inheritance and overrides.
`get_test_params`([parameter_set])	Return testing parameter settings for the estimator.
`is_composite`()	Check if the object is composed of other BaseObjects.
`load_from_path`(serial)	Load object from file location.
`load_from_serial`(serial)	Load object from serialized memory container.
`predict`([fh, X])	Forecast time series at future horizon.
`predict_interval`([fh, X, coverage])	Compute/return prediction interval forecasts.
`predict_proba`([fh, X, marginal])	Compute/return fully probabilistic forecasts.
`predict_quantiles`([fh, X, alpha])	Compute/return quantile forecasts.
`predict_residuals`([y, X])	Return residuals of time series forecasts.
`predict_var`([fh, X, cov])	Compute/return variance forecasts.
`pretrain`(y[, X, fh])	Pre-train forecaster on panel (global) data.
`reset`()	Reset the object to a clean post-init state.
`save`([path, serialization_format])	Save serialized self to bytes-like object or to (.zip) file.
`score`(y[, X, fh])	Scores forecast against ground truth, using MAPE (non-symmetric).
`set_config`(**config_dict)	Set config flags to given values.
`set_params`(**params)	Set the parameters of this object.
`set_random_state`([random_state, deep, ...])	Set random_state pseudo-random seed parameters for self.
`set_tags`(**tag_dict)	Set instance level tag overrides to given values.
`update`(y[, X, update_params])	Update cutoff value and, optionally, fitted parameters.
`update_predict`(y[, cv, X, update_params, ...])	Make predictions and update model iteratively over the test set.
`update_predict_single`([y, fh, X, update_params])	Update model with new data and make forecasts.