fairical.scripts.evaluate

Evaluation CLI for demographically fair machine learning systems.

This module defines the evaluate command, which loads one or more system solution files in JSON format, validates them against a predefined data model, and computes Pareto-front indicators. It supports tabulated output in various formats (via tabulate) and optional generation of radar plots to visualize trade-offs between metrics.

The CLI provides options to output formatting, and radar plot generation, and is intended to support analysis of fairness-performance trade-offs across systems.