reno.viz.plot_trace_refs

reno.viz.plot_trace_refs(reference_model, traces, ref_list, cols=None, rows=None, smoothing=0.1, **figargs)

Create a set of plots for each of the specified references, automatically plotting timeseries sequences or distribution densities where relevant.

Parameters:

• reference_model – The model from which the datasets are being plotted, this is used to help axes titles and determine which references are random variables etc.

• traces (list[az.InferenceData | xr.Dataset] | dict[str, az.InferenceData | xr.Dataset) – A list or dictionary of traces or dataset to plot the references from. Passed traces will plot from the posterior, pass the specific dataset if you need the priors (pymc_trace.prior). If a dictionary is used, the legends will use the specified keys.

• ref_list (list[str | reno.components.Reference]) – Either the string names or actual reference objects to plot the data of. (A separate plot will be created for each reference.)

• cols (int) – The number of columns to split the plots into.

• rows (int) – The number of rows to split the plots into.

• smoothing (float) – Degree of smoothing to apply to density plots, lower = more bumpy.

• **figargs – Arguments to pass to the figure creation plt.subplots(..., **figargs) call.