ReliabilityModelPlot

class ReliabilityModelPlot

Bases: object

Visualize ReliabilityModel outputs — calibration and the two trust axes.

Turns the tables from ReliabilityModel into a per-sample view — each prediction’s score with its uncertainty interval, colored by trust status (ranking()) — and three batch diagnostics: a calibration curve (reliability_diagram(), from ReliabilityModel.eval()), the out-of-distribution score distribution (ood_hist()), and a score-vs-OOD map colored by the reliable flag (trust_map(); the last three from ReliabilityModel.predict()).

Added in version 1.1.0.

See also

• ReliabilityModel for the measures these methods visualize.

Methods

ood_hist(df_rel[, figsize, bins, color, ...])	Histogram of the out-of-distribution score, with the in-domain boundary at 1.0.
ranking(df_rel[, names, figsize, top_n, ...])	Per-sample view — each prediction's score with its uncertainty, colored by trust status.
reliability_diagram(df_eval[, figsize, ...])	Calibration curve — mean predicted score vs.
trust_map(df_rel[, figsize, title, ax])	Score vs.