feat(pfs): valuation rows by vintage from the DuckDB replica with pfs.rules conversion factors (refs P48)

This commit is contained in:
kert
2026-09-08 22:31:10 -04:00
parent 36eea3a013
commit a743540046
2 changed files with 381 additions and 0 deletions

166
src/pfs/valuation.py Normal file
View File

@@ -0,0 +1,166 @@
"""RVUs, conversion factor and national unadjusted payment per code and
vintage, read from the DuckDB replica (``pfs.rvu`` final years,
``pfs.rvu_proposed`` for the newest NPRM). Conversion factors come from
``pfs.rules`` — never from ``pfs.rvu.conv_factor``. Pure DuckDB SQL; no
narwhals (this module runs inside the ``llm`` container).
"""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Sequence
from pfs.nprm import NPRM_SOURCES
from pfs.rules import RULES, proposed_for
@dataclass(frozen=True)
class ValuationRow:
code: str
description: str
vintage: str # "CY2026 final" | "CY2027 proposed"
year: int
proposed: bool
status: str
work: float | None
pe_nf: float | None
pe_f: float | None
mp: float | None
total_nf: float | None
total_f: float | None
cf: float
pay_nf: float | None
pay_f: float | None
label: str # "[PFS CY2026 Addendum B]"
citation: str # "90 FR 49266"
url: str
def vintage_label(year: int, proposed: bool) -> str:
return f"[CY{year} NPRM Addendum B]" if proposed else f"[PFS CY{year} Addendum B]"
def fr_citation_url(cite: str) -> str:
parts = cite.split()
if len(parts) != 3 or parts[1].upper() != "FR":
return ""
return f"https://www.federalregister.gov/citation/{parts[0]}-FR-{parts[2]}"
def _pay(total: float | None, cf: float) -> float | None:
return None if total is None else round(total * cf, 2)
_FINAL_SQL = """
WITH base AS (
SELECT hcpcs, year, description, status_code, work_rvu, non_fac_pe_rvu,
fac_pe_rvu, mp_rvu, non_fac_total, fac_total
FROM pfs.rvu
WHERE hcpcs IN (SELECT UNNEST(?::VARCHAR[]))
QUALIFY row_number() OVER (
PARTITION BY hcpcs, year ORDER BY (mod IS NULL OR mod = '') DESC, mod
) = 1
)
SELECT * FROM base
QUALIFY dense_rank() OVER (PARTITION BY hcpcs ORDER BY year DESC) <= ?
ORDER BY hcpcs, year
"""
_PROPOSED_SQL = """
SELECT hcpcs, description, status_code, work_rvu, non_fac_pe_rvu, fac_pe_rvu, mp_rvu
FROM pfs.rvu_proposed
WHERE cms_rule_id = ? AND hcpcs IN (SELECT UNNEST(?::VARCHAR[]))
QUALIFY row_number() OVER (
PARTITION BY hcpcs ORDER BY (mod IS NULL OR mod = '') DESC, mod
) = 1
ORDER BY hcpcs
"""
def _sum(*vals: float | None) -> float | None:
if any(v is None for v in vals):
return None
return round(sum(vals), 4) # type: ignore[arg-type]
def valuation(
con: Any, codes: Sequence[str], *, years: int = 4
) -> tuple[list[ValuationRow], list[str]]:
"""Rows for *codes* (last *years* final vintages + the newest NPRM),
ordered by code then year with the proposed row last per code, and the
codes that produced no rows at all."""
wanted = sorted({c.upper() for c in codes})
if not wanted:
return [], []
by_code: dict[str, list[ValuationRow]] = {c: [] for c in wanted}
for hcpcs, year, desc, status, work, pe_nf, pe_f, mp, tot_nf, tot_f in con.execute(
_FINAL_SQL, [wanted, years]
).fetchall():
rule = RULES.get(int(year))
if rule is None:
continue
cf = rule.conversion_factor
cite = rule.federal_register_citation
by_code[hcpcs].append(
ValuationRow(
code=hcpcs,
description=desc or "",
vintage=f"CY{year} final",
year=int(year),
proposed=False,
status=status or "",
work=work,
pe_nf=pe_nf,
pe_f=pe_f,
mp=mp,
total_nf=tot_nf,
total_f=tot_f,
cf=cf,
pay_nf=_pay(tot_nf, cf),
pay_f=_pay(tot_f, cf),
label=vintage_label(int(year), False),
citation=cite,
url=fr_citation_url(cite),
)
)
nprm_year, _tag, rule_id, _pin = max(NPRM_SOURCES, key=lambda s: s[0])
prop = proposed_for(nprm_year)
if prop is not None:
cf = prop.conversion_factor
cite = prop.federal_register_citation
for hcpcs, desc, status, work, pe_nf, pe_f, mp in con.execute(
_PROPOSED_SQL, [rule_id, wanted]
).fetchall():
tot_nf, tot_f = _sum(work, pe_nf, mp), _sum(work, pe_f, mp)
by_code[hcpcs].append(
ValuationRow(
code=hcpcs,
description=desc or "",
vintage=f"CY{nprm_year} proposed",
year=nprm_year,
proposed=True,
status=status or "",
work=work,
pe_nf=pe_nf,
pe_f=pe_f,
mp=mp,
total_nf=tot_nf,
total_f=tot_f,
cf=cf,
pay_nf=_pay(tot_nf, cf),
pay_f=_pay(tot_f, cf),
label=vintage_label(nprm_year, True),
citation=cite,
url=fr_citation_url(cite),
)
)
rows = [
r
for c in wanted
for r in sorted(by_code[c], key=lambda r: (r.year, r.proposed))
]
unpriced = [c for c in wanted if not by_code[c]]
return rows, unpriced

215
tests/pfs/test_valuation.py Normal file
View File

@@ -0,0 +1,215 @@
"""pfs.valuation — RVUs + national payment by vintage from a DuckDB replica."""
from __future__ import annotations
import duckdb
import pytest
from pfs.rules import RULES, proposed_for
from pfs.valuation import ValuationRow, fr_citation_url, valuation, vintage_label
RVU_COLS = (
"hcpcs VARCHAR, mod VARCHAR, description VARCHAR, status_code VARCHAR, "
"work_rvu DOUBLE, non_fac_pe_rvu DOUBLE, fac_pe_rvu DOUBLE, mp_rvu DOUBLE, "
"non_fac_total DOUBLE, fac_total DOUBLE, conv_factor DOUBLE, year INTEGER"
)
PROPOSED_COLS = (
"hcpcs VARCHAR, mod VARCHAR, description VARCHAR, status_code VARCHAR, "
"work_rvu DOUBLE, non_fac_pe_rvu DOUBLE, fac_pe_rvu DOUBLE, mp_rvu DOUBLE, cms_rule_id VARCHAR"
)
@pytest.fixture
def con():
c = duckdb.connect(":memory:")
c.execute("CREATE SCHEMA pfs")
c.execute(f"CREATE TABLE pfs.rvu ({RVU_COLS})")
c.execute(f"CREATE TABLE pfs.rvu_proposed ({PROPOSED_COLS})")
rows = [
# G0556: 2025 + 2026 final, with a modifier row that must be ignored
(
"G0556",
None,
"Adv prim care mgmt lvl 1",
"A",
0.25,
0.20,
0.10,
0.02,
0.47,
0.37,
32.3465,
2025,
),
(
"G0556",
None,
"Adv prim care mgmt lvl 1",
"A",
0.25,
0.22,
0.06,
0.02,
0.49,
0.33,
33.4009,
2026,
),
(
"G0556",
"26",
"Adv prim care mgmt lvl 1",
"A",
9.0,
9.0,
9.0,
9.0,
27.0,
27.0,
33.4009,
2026,
),
# 99490: six years so the last-N cut applies (2021..2026)
*[
(
"99490",
"",
"Chrnc care mgmt srvc 20 min",
"A",
1.0,
1.0,
0.5,
0.05,
2.05,
1.55,
30.0,
y,
)
for y in range(2021, 2027)
],
# I-status code with NULL components
(
"G9999",
None,
"Not priced",
"I",
None,
None,
None,
None,
None,
None,
33.4009,
2026,
),
]
c.executemany("INSERT INTO pfs.rvu VALUES (?,?,?,?,?,?,?,?,?,?,?,?)", rows)
c.executemany(
"INSERT INTO pfs.rvu_proposed VALUES (?,?,?,?,?,?,?,?,?)",
[
(
"G0556",
None,
"Adv prim care mgmt lvl 1",
"A",
0.25,
0.23,
0.07,
0.02,
"CMS-1848-P",
),
(
"G0556",
"26",
"Adv prim care mgmt lvl 1",
"A",
9.0,
9.0,
9.0,
9.0,
"CMS-1848-P",
),
("G0556", None, "older nprm", "A", 0.1, 0.1, 0.1, 0.1, "CMS-1832-P"),
],
)
yield c
c.close()
class TestHelpers:
def test_vintage_label(self):
assert vintage_label(2026, False) == "[PFS CY2026 Addendum B]"
assert vintage_label(2027, True) == "[CY2027 NPRM Addendum B]"
def test_fr_citation_url(self):
assert (
fr_citation_url("90 FR 49266")
== "https://www.federalregister.gov/citation/90-FR-49266"
)
assert fr_citation_url("") == ""
class TestValuation:
def test_final_and_proposed_rows_with_cf_and_payment(self, con):
rows, unpriced = valuation(con, ["G0556"], years=4)
assert unpriced == []
assert [(r.year, r.proposed) for r in rows] == [
(2025, False),
(2026, False),
(2027, True),
]
r26 = rows[1]
assert isinstance(r26, ValuationRow)
assert (r26.code, r26.status, r26.work, r26.pe_nf, r26.pe_f, r26.mp) == (
"G0556",
"A",
0.25,
0.22,
0.06,
0.02,
)
assert (r26.total_nf, r26.total_f) == (0.49, 0.33)
assert r26.cf == RULES[2026].conversion_factor
assert r26.pay_nf == round(0.49 * RULES[2026].conversion_factor, 2)
assert r26.pay_f == round(0.33 * RULES[2026].conversion_factor, 2)
assert r26.label == "[PFS CY2026 Addendum B]"
assert r26.citation == RULES[2026].federal_register_citation
assert r26.url == fr_citation_url(RULES[2026].federal_register_citation)
assert r26.vintage == "CY2026 final"
p = rows[2]
assert p.label == "[CY2027 NPRM Addendum B]" and p.vintage == "CY2027 proposed"
assert p.cf == proposed_for(2027).conversion_factor
assert p.total_nf == round(0.25 + 0.23 + 0.02, 4) and p.total_f == round(
0.25 + 0.07 + 0.02, 4
)
assert p.pay_nf == round(p.total_nf * p.cf, 2)
assert p.citation == proposed_for(2027).federal_register_citation
def test_modifier_rows_are_ignored(self, con):
rows, _ = valuation(con, ["G0556"])
assert all(r.work == 0.25 for r in rows)
def test_last_n_years_only(self, con):
rows, _ = valuation(con, ["99490"], years=4)
assert [r.year for r in rows if not r.proposed] == [2023, 2024, 2025, 2026]
def test_unpriced_codes_reported(self, con):
rows, unpriced = valuation(con, ["G0556", "Z9999"])
assert unpriced == ["Z9999"]
assert {r.code for r in rows} == {"G0556"}
def test_null_components_pass_through(self, con):
rows, unpriced = valuation(con, ["G9999"])
assert unpriced == []
(r,) = rows
assert r.status == "I" and r.work is None and r.pay_nf is None
def test_order_is_code_then_year(self, con):
rows, _ = valuation(con, ["G0556", "99490"], years=2)
assert [(r.code, r.year) for r in rows] == [
("99490", 2025),
("99490", 2026),
("G0556", 2025),
("G0556", 2026),
("G0556", 2027),
]