Jesse_Chen
62afa521f4
Implement offset and softmax relative-support scales and a public holdout calibration script, but leave the default proportional because no scheme passed the coverage-and-width gate. Co-authored-by: Cursor <cursoragent@cursor.com>
66 lines
3.0 KiB
Python
66 lines
3.0 KiB
Python
from __future__ import annotations
|
|
|
|
import unittest
|
|
from decimal import Decimal
|
|
|
|
from scripts.rectification.decision_policy import (
|
|
POLICY_VERSION,
|
|
RELATIVE_SUPPORT_MODE,
|
|
_relative_support,
|
|
build_candidate_decisions,
|
|
)
|
|
from scripts.rectification.scoring_service import ALGORITHM_VERSION
|
|
|
|
|
|
def _row(time: str, score: float) -> dict:
|
|
return {"time": time, "score": score, "evidence": [], "missing_layers": []}
|
|
|
|
|
|
class RelativeSupportScaleTest(unittest.TestCase):
|
|
def test_holdout_gate_keeps_proportional_default(self) -> None:
|
|
self.assertEqual(POLICY_VERSION, "rectification-candidate-policy-v3")
|
|
self.assertEqual(ALGORITHM_VERSION, "rectification-v5-matrix-scoring-7")
|
|
self.assertEqual(RELATIVE_SUPPORT_MODE, "proportional")
|
|
|
|
def test_offset_top_two_lead_is_at_least_proportional(self) -> None:
|
|
scores = [
|
|
Decimal("15.52"), Decimal("15.40"), Decimal("14.10"), Decimal("13.00"),
|
|
Decimal("12.50"), Decimal("12.00"), Decimal("11.80"), Decimal("11.50"),
|
|
Decimal("11.40"), Decimal("11.20"), Decimal("11.10"), Decimal("10.96"),
|
|
]
|
|
floor = min(scores)
|
|
proportional = _relative_support(scores, floor=floor, mode="proportional")
|
|
offset = _relative_support(scores, floor=floor, mode="offset")
|
|
prop_lead = sorted(proportional, reverse=True)
|
|
offset_lead = sorted(offset, reverse=True)
|
|
self.assertGreaterEqual(offset_lead[0] - offset_lead[1], prop_lead[0] - prop_lead[1])
|
|
self.assertEqual(sum(offset), 100)
|
|
self.assertEqual(sum(proportional), 100)
|
|
|
|
def test_equal_scores_split_evenly_for_offset_and_proportional(self) -> None:
|
|
scores = [Decimal("12")] * 12
|
|
expected = _relative_support(scores, floor=Decimal("12"), mode="proportional")
|
|
offset = _relative_support(scores, floor=Decimal("12"), mode="offset")
|
|
self.assertEqual(offset, expected)
|
|
self.assertEqual(sum(offset), 100)
|
|
self.assertTrue(all(value in {8, 9} for value in offset))
|
|
|
|
def test_build_candidate_decisions_offset_lead_beats_proportional_on_spaced_grid(self) -> None:
|
|
scores = [
|
|
15.52, 15.40, 14.10, 13.00, 12.50, 12.00,
|
|
11.80, 11.50, 11.40, 11.20, 11.10, 10.96,
|
|
]
|
|
rows = [_row(f"05:{index * 5:02d}", score) for index, score in enumerate(scores)]
|
|
proportional = build_candidate_decisions(rows, result_id="00000000-0000-4000-8000-000000000001", support_mode="proportional")
|
|
offset = build_candidate_decisions(rows, result_id="00000000-0000-4000-8000-000000000001", support_mode="offset")
|
|
self.assertEqual(len(proportional), 12)
|
|
self.assertEqual(len(offset), 12)
|
|
prop_lead = proportional[0]["relative_support"] - proportional[1]["relative_support"]
|
|
offset_lead = offset[0]["relative_support"] - offset[1]["relative_support"]
|
|
self.assertGreaterEqual(offset_lead, prop_lead)
|
|
self.assertEqual(sum(item["relative_support"] for item in offset), 100)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|