"""R4(a) shared-cell-speed graph and descriptive grouped statistics.""" from itertools import combinations import numpy as np from scipy.sparse import csr_matrix from scipy.sparse.csgraph import dijkstra from s2_custody_statistics import contrast def graph_field(g, speed, sources): speed = np.asarray(speed, dtype=np.float64) if speed.shape != (len(g['t']),) or not np.isfinite(speed).all() or np.any(speed <= 0): raise ValueError('Invalid shared cell speed') edges = np.sort(g['t'][:, list(combinations(range(4), 2))].reshape(-1, 2), axis=1) incident_speed = np.repeat(speed, 6) unique, inverse = np.unique(edges, axis=0, return_inverse=True) fastest = np.zeros(len(unique), dtype=np.float64) np.maximum.at(fastest, inverse, incident_speed) weights = np.linalg.norm(g['x'][unique[:, 0]]-g['x'][unique[:, 1]], axis=1)/fastest if not np.isfinite(weights).all() or np.any(weights <= 0): raise ValueError('Nonpositive edge length/cost; no repair') graph = csr_matrix((np.r_[weights, weights], (np.r_[unique[:, 0], unique[:, 1]], np.r_[unique[:, 1], unique[:, 0]])), shape=(len(g['x']), len(g['x']))) field = dijkstra(graph, directed=False, indices=np.asarray(sources), min_only=True) if not np.isfinite(field).all() or np.any(field < 0) or np.any(field[sources] != 0): raise ValueError('Invalid/unreachable graph field') return field, dict(edges=len(unique), minimum_cost=float(weights.min()), maximum_cost=float(weights.max())) def paired_summary(rows, roster, metric): by = {r['case']: r for r in rows} groups = {} for r in roster: groups.setdefault(r['component_id'], []).append(r['case']) values = {'F': {}, 'G': {}} excluded = {} for component, cases in sorted(groups.items()): reasons = [] for case in cases: for arm in values: value = by.get(case, {}).get('metrics', {}).get(arm, {}).get(metric, {}).get('value') if value is None or not np.isfinite(value): reasons.append(dict(case=case, arm=arm, reason='missing or undefined metric')) if reasons: excluded[component] = reasons continue for arm in values: values[arm][component] = float(np.mean([by[case]['metrics'][arm][metric]['value'] for case in cases])) result = dict(component_values=values, excluded_components=excluded, paired_components=len(values['F']), requested_components=len(groups), paired_parts=sum(len(groups[k]) for k in values['F'])) if metric == 'relative_l2': delta = contrast(values['G'], values['F'], replicates=2000, seed=2026111408) delta.pop('region', None) delta['interpretation'] = 'descriptive only; no CI gate or effect-size margin' result['delta'] = delta else: result['means'] = {a: float(np.mean(list(v.values()))) if v else None for a, v in values.items()} return result def may_dispatch(spent, active, cap=28800., per_part=1800.): return spent+(active+1)*(per_part+2.) <= cap def scoring_allowed(records, requested, stop_reason): return stop_reason is None and len(records) == requested and all(r['worker']['status'] == 'PASS' for r in records)