TiRex2Forecaster

class TiRex2Forecaster(model_path: str = 'NX-AI/TiRex-2', device: str = 'auto', revision: str = None, tta_sign_flip: bool = None, tta_diff: bool = None, hf_kwargs: dict = None, ignore_deps: bool = False)[source]

Interface to the TiRex-2 zero-shot forecaster by NX-AI.

TiRex-2 is a pretrained xLSTM-based time series foundation model for zero-shot forecasting. It natively supports multivariate targets, past covariates, and known-future covariates, and outputs nine quantile levels (0.1 to 0.9) per prediction step.

The model is run in eager mode, via torch.compiler.set_stance, because the underlying package applies torch.compile unconditionally, which requires a working C++ toolchain and fails on machines without one.

Parameters:

model_pathstr, default=”NX-AI/TiRex-2”

Hugging Face repo id or local checkpoint directory.

The decontaminated variants NX-AI/TiRex-2-gifteval-zs, NX-AI/TiRex-2-gifteval-pretrain and NX-AI/TiRex-2-fevbench are gated on Hugging Face and require authentication to download.

device{“auto”, “cpu”, “cuda”, “mps”}, default=”auto”

Device used for inference. "auto" resolves to cuda, then mps, then cpu, depending on availability.

revisionstr, optional, default=None

Model repository revision, branch, tag, or commit.

tta_sign_flipbool, optional, default=None

Sign-flip test-time augmentation. None uses the checkpoint default. Roughly doubles inference cost when enabled.

tta_diffbool, optional, default=None

Postprocessor differencing. None uses the checkpoint default.

hf_kwargsdict, optional, default=None

Additional keyword arguments passed to huggingface_hub.snapshot_download.

ignore_depsbool, default=False

If True, soft dependency checks are skipped. Intended for tests and controlled environments.

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/NX-AI/tirex-2

[2]

TiRex-2: Generalizing TiRex to Multivariate Data and Streaming, arXiv:2607.01204

Examples

>>> from sktime.datasets import load_airline
>>> from sktime.forecasting.tirex2 import TiRex2Forecaster
>>> y = load_airline()
>>> forecaster = TiRex2Forecaster()
>>> forecaster.fit(y)
>>> 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.