MMMCVPlotSuite.predictions

MMMCVPlotSuite.predictions(cv_data=None, dims=None, hdi_prob=0.94, figsize=None, backend=None, return_as_pc=False, hdi_kwargs=None, **pc_kwargs)

Posterior predictive HDI bands per CV fold.

For each fold: blue HDI band over train dates, orange HDI band over test dates, black observed line, and a green dashed vertical boundary at the train/test split.

Parameters:

cv_dataaz.InferenceData or None

Override the stored self.cv_data for this call only. _validate_cv_results is re-run on the override.

dimsdict or None

Filter coordinate values before rendering (e.g. {"geo": ["North"]}).

hdi_probfloat

HDI probability mass (default 0.94).

figsizetuple or None

Figure size in inches; injected into figure_kwargs.

backendstr or None

PlotCollection backend ("matplotlib" / "plotly" / "bokeh"). Non-matplotlib requires return_as_pc=True.

return_as_pcbool

Return the raw PlotCollection instead of (Figure, NDArray[Axes]).

hdi_kwargsdict or None

Extra kwargs forwarded to azp.visuals.fill_between_y.

**pc_kwargs

Forwarded to PlotCollection.grid().

Returns:

tuple[Figure, NDArray[Axes]] or PlotCollection