53 lines
2.5 KiB
Python
53 lines
2.5 KiB
Python
"""Tests for descriptive EasyCom AI pre-label aggregation."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import tempfile
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
from summarize_easycom_event_prelabels import summarize
|
|
|
|
|
|
class EventPrelabelSummaryTests(unittest.TestCase):
|
|
def test_summary_separates_ai_prelabels_and_two_pass_agreement(self) -> None:
|
|
base = {
|
|
"protocol_version": "p1", "schema_version": 6,
|
|
"candidate_source": "WEARER_ONSET", "task": "wearer_entry",
|
|
"human_status": "UNREVIEWED", "ai_confidence": 0.8,
|
|
"llm_adjudication": {"prompt_version": "v1", "model": "m", "passes": 2},
|
|
}
|
|
rows = [
|
|
{**base, "uid": "u1", "session": "Session_1", "ai_verdict": "POSITIVE",
|
|
"ai_event_type": "WEARER_ENTRY", "ai_subtype": None,
|
|
"llm_adjudication": {**base["llm_adjudication"], "decisions": [
|
|
{"verdict": "POSITIVE", "event_type": "WEARER_ENTRY"},
|
|
{"verdict": "POSITIVE", "event_type": "WEARER_ENTRY"},
|
|
]}},
|
|
{**base, "uid": "u2", "session": "Session_4", "task": "int_yield",
|
|
"candidate_source": "WEARER_OFFSET", "ai_verdict": "EXCLUDE",
|
|
"ai_event_type": None, "ai_subtype": None,
|
|
"ai_exclude_reason": "OUT_OF_SCOPE_NORMAL_COMPLETION",
|
|
"ai_exclude_reason_group": "OUT_OF_SCOPE",
|
|
"llm_adjudication": {**base["llm_adjudication"], "decisions": [
|
|
{"verdict": "EXCLUDE", "exclude_reason": "OUT_OF_SCOPE_NORMAL_COMPLETION"},
|
|
{"verdict": "EXCLUDE", "exclude_reason": "INSUFFICIENT_EVIDENCE"},
|
|
]}},
|
|
]
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
source = root / "input.jsonl"
|
|
source.write_text("".join(json.dumps(row) + "\n" for row in rows))
|
|
summary = summarize([source], root / "out")
|
|
cohorts = {item["cohort"]: item for item in summary["cohorts"]}
|
|
self.assertEqual(cohorts["Test pooled (Sessions 1-3)"]["num_positive"], 1)
|
|
self.assertEqual(cohorts["Session 4 audit (train split)"]["num_exclude"], 1)
|
|
self.assertEqual(cohorts["All supplied (descriptive only)"]["num_two_pass_semantic_agreement"], 1)
|
|
self.assertEqual(cohorts["All supplied (descriptive only)"]["num_two_pass_full_decision_agreement"], 1)
|
|
self.assertIn("AI pre-label audit only", (root / "out/manuscript_ai_prelabel_table.tex").read_text())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|