FlowStateForecaster

class FlowStateForecaster(model_path: str = 'ibm-research/flowstate', revision: str = 'r1.1', scale_factor: float = 1.0, config: dict | None = None, batch_first: bool = True, prediction_type: str = 'mean')[source]

Zero-shot forecaster wrapping IBM FlowState via granite-tsfm.

FlowState, developed by IBM Research, is an encoder-decoder architecture, employing an S5-based encoder and a functional basis decoder.

Univariate only. Implementation adapted from [1].

Parameters:

model_pathstr, default=”ibm-research/flowstate”: Hugging Face model id or local path.
revisionstr, default=”r1.1”: Model revision on the Hugging Face Hub. Always forwarded to from_pretrained; do not duplicate in config.
scale_factorfloat, default=1.0: Temporal scaling passed to the model at predict time.
configdict, optional, default=None: Extra kwargs for FlowStateForPrediction.from_pretrained.
batch_firstbool, default=True: past_values layout for the model.
prediction_type{“mean”, “median”}, default=”mean”: Point forecast type passed to the model.

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.

Notes

predict_proba returns a skpro HistogramQPD built from FlowState’s native quantile grid. Quantiles between grid points are linearly interpolated, while levels outside the grid are clamped to the nearest native quantile.

References

[1]

https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/flowstate_getting_started_pipeline.ipynb

[2]

Graf et al., FlowState: Sampling Rate Invariant Time Series Forecasting, arXiv:2508.05287

Examples

>>> from sktime.datasets import load_airline
>>> from sktime.forecasting.flowstate import FlowStateForecaster
>>> from sktime.split import temporal_train_test_split
>>> y = load_airline()
>>> y_train, _ = temporal_train_test_split(y)
>>> f = FlowStateForecaster()
>>> f.fit(y_train)
>>> y_pred = f.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.