Skip to main content

​
SupportsRefit

Bases: ArrayModel, ABC Adapter can retrain its underlying model on new data.

​
SupportsRefit.refit

Refit the underlying model on history.

​
Parameters

history : Series, shape (n_series, T)

​
SupportsQuantiles

Bases: ArrayModel, ABC Adapter can produce quantile forecasts directly (needed for CQR).

​
SupportsQuantiles.predict_quantiles

Predict requested quantiles.

​
Parameters

history : Series, shape (n_series, T) quantiles : NDArray, shape (n_quantiles,) Values in (0, 1).

​
Returns

Forecast, shape (n_series, n_quantiles, horizon) Quantile forecasts. Note the middle axis indexes quantiles, not samples.

​
SupportsBootstrap

Bases: ArrayModel, ABC Adapter can produce bootstrap ensemble forecasts (needed for EnbPI).

​
SupportsBootstrap.bootstrap_predict

Produce n_bootstraps predictions from bootstrap resamples of training data.

​
Parameters

history : Series, shape (n_series, T) n_bootstraps : int seed : int, default 0 Never None: resampling must be reproducible given the same fitted state and inputs.

​
Returns

Forecast, shape (n_series, n_bootstraps, horizon)

​
SupportsCrossValidation

Bases: ArrayModel, ABC Adapter can run rolling-origin cross-validation natively.

​
SupportsCrossValidation.cross_validate

Run rolling-origin cross-validation on the adapter’s training data.

​
Parameters

n_windows : int Number of evaluation windows. step_size : int Number of time steps between successive windows. refit : bool or int Whether (or how often) to refit the model between windows. aligned : bool, default False False returns dense per-series arrays (window axis = k steps before each series’ own end). True returns calendar-aligned cutoffs with NaN cells for late-starting series.

​
Returns

predictions : Forecast, shape (n_series, n_windows, horizon) truths : Forecast, shape (n_series, n_windows, horizon)

​
SupportsCrossValidationQuantiles

Bases: ArrayModel, ABC Adapter can produce quantile forecasts via cross-validation. This is the fast calibration path for CQR (and any future quantile-based conformal method). Adapters with this capability avoid the per-sample loop of predict_quantiles, instead leveraging the underlying library’s cross-validation API to produce all calibration samples in a single call.

​
SupportsCrossValidationQuantiles.cross_validate_quantiles

Run rolling-origin cross-validation producing quantile forecasts.

​
Parameters

n_windows : int Number of evaluation windows. step_size : int Number of time steps between successive windows. quantiles : NDArray, shape (n_quantiles,) Values in (0, 1). refit : bool or int, default False Same semantics as :meth:SupportsCrossValidation.cross_validate.

​
Returns

quantile_predictions : Forecast, shape (n_series, n_windows, horizon, n_quantiles) Quantiles are on the last axis, matching :class:QuantileScore’s expected input. This differs from :meth:SupportsQuantiles.predict_quantiles, where quantiles are on axis 1 (because predict_quantiles produces a single sample per call). The intentional axis difference avoids an extra transpose in the CQR fast path. truths : Forecast, shape (n_series, n_windows, horizon)