All checks were successful
CI / lint (push) Successful in 46s
CI / notebooks-smoke (push) Successful in 2m11s
Deploy / changes (push) Successful in 20s
Deploy / notebooks (push) Has been skipped
Deploy / zotero (push) Has been skipped
Deploy / docs (push) Has been skipped
Deploy / api (push) Has been skipped
Deploy / bcda (push) Has been skipped
Deploy / llm (push) Has been skipped
Deploy / mc (push) Has been skipped
Deploy / report (push) Successful in 16s
CI / test (push) Successful in 4m33s
Typer forces a color terminal when GITHUB_ACTIONS is set. Rich then inserts an ANSI code between the dashes of --option, so assertions that look for the option name fail on the runner and pass locally.
845 lines
27 KiB
Python
845 lines
27 KiB
Python
"""Shared pytest fixtures for the stack test suite.
|
|
|
|
Fixtures are organized by domain:
|
|
- polars DataFrames for every major input_layer schema shape
|
|
- PFS computation DataFrames (RVU, GPCI, labor, supply, equipment)
|
|
- rex primitives (Sieve, FieldMap, sample raw text)
|
|
- bib.tag helpers
|
|
- temporary file paths
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import re
|
|
import shutil
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
# Gitea Actions sets GITHUB_ACTIONS. Typer then forces a color terminal, and
|
|
# Rich's option highlighter puts an ANSI code between the two dashes of
|
|
# ``--option``. A dumb TERM keeps CliRunner output colorless on every worker.
|
|
os.environ["TERM"] = "dumb"
|
|
|
|
import polars as pl
|
|
import pytest
|
|
|
|
# ── pfs.families registry fixture (shared: pfs + llm tests) ──────────────────
|
|
# Any test that calls ``refresh_from``/mutates the live ``pfs.families.FAMILIES``
|
|
# registry (directly, or indirectly by opening a real replica — I5) must not
|
|
# leave it clobbered for the rest of the session.
|
|
|
|
|
|
@pytest.fixture
|
|
def restore_families():
|
|
"""Snapshot ``pfs.families.FAMILIES`` and restore it (and the compiled
|
|
phrase/code index built off it) in teardown, even if the test body
|
|
raises."""
|
|
from pfs import families as mod
|
|
|
|
before = dict(mod.FAMILIES)
|
|
try:
|
|
yield mod
|
|
finally:
|
|
mod.FAMILIES.clear()
|
|
mod.FAMILIES.update(before)
|
|
mod.rebuild_index()
|
|
|
|
|
|
# ── Perf hooks — auto-file Gitea issues on test failure/skip in CI ───────────
|
|
# Only active when STACK_FILE_TEST_ISSUES=true (set in CI workflows).
|
|
|
|
try:
|
|
from perf.hooks import pytest_runtest_logreport # noqa: F401
|
|
except ImportError:
|
|
pass
|
|
|
|
# ── Zotero DB fixture (session-scoped for speed) ─────────────────────────────
|
|
# create_db() takes ~10s. By creating once and copying per-test, we cut
|
|
# cumulative DB creation from ~30min to ~10s across 200+ Zotero tests.
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def _zotero_template_db():
|
|
"""Session-scoped: create one Zotero schema DB, reuse everywhere."""
|
|
from zot.schema import create_db
|
|
|
|
with tempfile.TemporaryDirectory() as td:
|
|
path = str(Path(td) / "template.sqlite")
|
|
con = create_db(path)
|
|
con.close()
|
|
yield path
|
|
|
|
|
|
@pytest.fixture
|
|
def zotero_db(_zotero_template_db, tmp_path):
|
|
"""Per-test Zotero DB: fast copy of the session template."""
|
|
dest = str(tmp_path / "z.sqlite")
|
|
shutil.copy2(_zotero_template_db, dest)
|
|
return dest
|
|
|
|
|
|
# ── input_layer fixtures ──────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.fixture
|
|
def medical_claim_df() -> pl.DataFrame:
|
|
"""One-row medical claim matching input_layer.medical_claim schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"claim_id": ["CLM001"],
|
|
"claim_line_number": [1],
|
|
"claim_type": ["professional"],
|
|
"person_id": ["P001"],
|
|
"member_id": ["M001"],
|
|
"patient_id": ["PT001"],
|
|
"payer": ["Medicare"],
|
|
"plan": [None],
|
|
"encounter_id": [None],
|
|
"claim_start_date": [None],
|
|
"claim_end_date": [None],
|
|
"service_unit": [1],
|
|
"hcpcs_code": ["99213"],
|
|
"hcpcs_modifier_1": [None],
|
|
"hcpcs_modifier_2": [None],
|
|
"hcpcs_modifier_3": [None],
|
|
"hcpcs_modifier_4": [None],
|
|
"rendering_npi": ["1234567890"],
|
|
"billing_npi": [None],
|
|
"facility_npi": [None],
|
|
"paid_date": [None],
|
|
"paid_amount": [75.00],
|
|
"allowed_amount": [95.00],
|
|
"charge_amount": [150.00],
|
|
"diagnosis_code_type": ["icd-10-cm"],
|
|
"diagnosis_code_1": ["E11.9"],
|
|
"diagnosis_code_2": [None],
|
|
"diagnosis_poa_1": [None],
|
|
"procedure_code_type": [None],
|
|
"procedure_code_1": [None],
|
|
"procedure_date_1": [None],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def eligibility_df() -> pl.DataFrame:
|
|
"""One-row eligibility matching input_layer.eligibility schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"person_id": ["P001"],
|
|
"member_id": ["M001"],
|
|
"subscriber_id": [None],
|
|
"gender": ["M"],
|
|
"race": [None],
|
|
"birth_date": [None],
|
|
"death_date": [None],
|
|
"death_flag": [0],
|
|
"enrollment_start_date": [None],
|
|
"enrollment_end_date": [None],
|
|
"payer": ["Medicare"],
|
|
"payer_type": ["government"],
|
|
"plan": [None],
|
|
"dual_status_code": [None],
|
|
"medicare_status_code": [None],
|
|
"first_name": [None],
|
|
"last_name": [None],
|
|
"state": ["TX"],
|
|
"zip_code": ["78701"],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def pharmacy_claim_df() -> pl.DataFrame:
|
|
"""One-row pharmacy claim matching input_layer.pharmacy_claim schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"claim_id": ["RX001"],
|
|
"claim_line_number": [1],
|
|
"person_id": ["P001"],
|
|
"member_id": ["M001"],
|
|
"patient_id": ["PT001"],
|
|
"payer": ["Medicare Part D"],
|
|
"plan": [None],
|
|
"dispensing_provider_id": [None],
|
|
"dispensing_date": [None],
|
|
"ndc_code": ["00071015523"],
|
|
"quantity": [30.0],
|
|
"days_supply": [30],
|
|
"refills": [0],
|
|
"paid_date": [None],
|
|
"paid_amount": [12.50],
|
|
"allowed_amount": [15.00],
|
|
"charge_amount": [25.00],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def encounter_df() -> pl.DataFrame:
|
|
"""One-row encounter matching input_layer.encounter schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"encounter_id": ["ENC001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_type": ["acute inpatient"],
|
|
"encounter_start_date": [None],
|
|
"encounter_end_date": [None],
|
|
"length_of_stay": [3],
|
|
"admit_source_code": [None],
|
|
"admit_source_description": [None],
|
|
"admit_type_code": [None],
|
|
"admit_type_description": [None],
|
|
"discharge_disposition_code": ["01"],
|
|
"discharge_disposition_description": ["home"],
|
|
"attending_provider_id": [None],
|
|
"attending_provider_name": [None],
|
|
"facility_id": [None],
|
|
"facility_name": [None],
|
|
"primary_diagnosis_code_type": ["icd-10-cm"],
|
|
"primary_diagnosis_code": ["E11.9"],
|
|
"primary_diagnosis_description": [None],
|
|
"drg_code_type": [None],
|
|
"drg_code": [None],
|
|
"drg_description": [None],
|
|
"paid_amount": [5000.00],
|
|
"allowed_amount": [6000.00],
|
|
"charge_amount": [12000.00],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def condition_df() -> pl.DataFrame:
|
|
"""One-row condition matching input_layer.condition schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"condition_id": ["COND001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": ["ENC001"],
|
|
"claim_id": [None],
|
|
"recorded_date": [None],
|
|
"onset_date": [None],
|
|
"resolved_date": [None],
|
|
"status": ["active"],
|
|
"condition_type": ["problem"],
|
|
"source_code_type": ["icd-10-cm"],
|
|
"source_code": ["E119"],
|
|
"source_description": ["Type 2 diabetes mellitus without complications"],
|
|
"normalized_code_type": ["icd-10-cm"],
|
|
"normalized_code": ["E11.9"],
|
|
"normalized_description": [
|
|
"Type 2 diabetes mellitus without complications"
|
|
],
|
|
"condition_rank": [1],
|
|
"present_on_admit_code": [None],
|
|
"present_on_admit_description": [None],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
"payer": ["Medicare"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def procedure_df() -> pl.DataFrame:
|
|
"""One-row procedure matching input_layer.procedure schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"procedure_id": ["PROC001"],
|
|
"person_id": ["P001"],
|
|
"member_id": [None],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": ["ENC001"],
|
|
"claim_id": ["CLM001"],
|
|
"procedure_date": [None],
|
|
"source_code_type": ["hcpcs"],
|
|
"source_code": ["99213"],
|
|
"source_description": ["Office visit, established patient"],
|
|
"normalized_code_type": ["hcpcs"],
|
|
"normalized_code": ["99213"],
|
|
"normalized_description": ["Office visit, established patient"],
|
|
"modifier_1": [None],
|
|
"modifier_2": [None],
|
|
"modifier_3": [None],
|
|
"modifier_4": [None],
|
|
"modifier_5": [None],
|
|
"practitioner_id": [None],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def patient_df() -> pl.DataFrame:
|
|
"""One-row patient matching input_layer.patient schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"name_suffix": [None],
|
|
"first_name": ["Jane"],
|
|
"middle_name": [None],
|
|
"last_name": ["Smith"],
|
|
"sex": ["F"],
|
|
"race": [None],
|
|
"birth_date": [None],
|
|
"death_date": [None],
|
|
"death_flag": [0],
|
|
"social_security_number": [None],
|
|
"address": ["123 Main St"],
|
|
"city": ["Austin"],
|
|
"state": ["TX"],
|
|
"zip_code": ["78701"],
|
|
"county": [None],
|
|
"latitude": [None],
|
|
"longitude": [None],
|
|
"phone": [None],
|
|
"email": [None],
|
|
"ethnicity": [None],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def practitioner_df() -> pl.DataFrame:
|
|
"""One-row practitioner matching input_layer.practitioner schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"practitioner_id": ["DR001"],
|
|
"npi": ["1234567890"],
|
|
"first_name": ["Alice"],
|
|
"last_name": ["Johnson"],
|
|
"practice_affiliation": [None],
|
|
"specialty": ["Internal Medicine"],
|
|
"sub_specialty": [None],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def location_df() -> pl.DataFrame:
|
|
"""One-row location matching input_layer.location schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"location_id": ["LOC001"],
|
|
"npi": ["9876543210"],
|
|
"name": ["General Hospital"],
|
|
"facility_type": ["hospital"],
|
|
"parent_organization": [None],
|
|
"address": ["456 Oak Ave"],
|
|
"city": ["Austin"],
|
|
"state": ["TX"],
|
|
"zip_code": ["78702"],
|
|
"latitude": [30.2672],
|
|
"longitude": [-97.7431],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def medication_df() -> pl.DataFrame:
|
|
"""One-row medication matching input_layer.medication schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"medication_id": ["MED001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": [None],
|
|
"dispensing_date": [None],
|
|
"prescribing_date": [None],
|
|
"source_code_type": ["ndc"],
|
|
"source_code": ["00071015523"],
|
|
"source_description": ["Lipitor 10mg"],
|
|
"ndc_code": ["00071015523"],
|
|
"ndc_description": ["Atorvastatin 10mg"],
|
|
"rxnorm_code": ["617312"],
|
|
"rxnorm_description": [None],
|
|
"atc_code": [None],
|
|
"atc_description": [None],
|
|
"route": ["oral"],
|
|
"strength": ["10mg"],
|
|
"quantity": [30.0],
|
|
"quantity_unit": ["tablets"],
|
|
"days_supply": [30],
|
|
"practitioner_id": [None],
|
|
"data_source": ["test"],
|
|
"file_name": ["test.csv"],
|
|
"ingest_datetime": [None],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def observation_df() -> pl.DataFrame:
|
|
"""One-row observation matching input_layer.observation schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"observation_id": ["OBS001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": ["ENC001"],
|
|
"panel_id": [None],
|
|
"observation_date": [None],
|
|
"observation_type": ["vital-sign"],
|
|
"source_code_type": ["loinc"],
|
|
"source_code": ["8480-6"],
|
|
"source_description": ["Systolic blood pressure"],
|
|
"normalized_code_type": ["loinc"],
|
|
"normalized_code": ["8480-6"],
|
|
"normalized_description": ["Systolic blood pressure"],
|
|
"result": ["120"],
|
|
"source_units": ["mm[Hg]"],
|
|
"normalized_units": ["mmHg"],
|
|
"source_reference_range_low": ["90"],
|
|
"source_reference_range_high": ["140"],
|
|
"normalized_reference_range_low": ["90"],
|
|
"normalized_reference_range_high": ["140"],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def appointment_df() -> pl.DataFrame:
|
|
"""One-row appointment matching input_layer.appointment schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"appointment_id": ["APT001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": ["ENC001"],
|
|
"source_appointment_type_code": ["office"],
|
|
"source_appointment_type_description": ["Office Visit"],
|
|
"normalized_appointment_type_code": ["office"],
|
|
"normalized_appointment_type_description": ["Office Visit"],
|
|
"start_datetime": [None],
|
|
"end_datetime": [None],
|
|
"duration": [30],
|
|
"location_id": ["LOC001"],
|
|
"practitioner_id": ["DR001"],
|
|
"source_status": ["completed"],
|
|
"normalized_status": ["completed"],
|
|
"appointment_specialty": ["Internal Medicine"],
|
|
"reason": ["Follow-up"],
|
|
"source_reason_code_type": [None],
|
|
"source_reason_code": [None],
|
|
"source_reason_description": [None],
|
|
"normalized_reason_code_type": [None],
|
|
"normalized_reason_code": [None],
|
|
"normalized_reason_description": [None],
|
|
"cancellation_reason": [None],
|
|
"source_cancellation_reason_code_type": [None],
|
|
"source_cancellation_reason_code": [None],
|
|
"source_cancellation_reason_description": [None],
|
|
"normalized_cancellation_reason_code_type": [None],
|
|
"normalized_cancellation_reason_code": [None],
|
|
"normalized_cancellation_reason_description": [None],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def immunization_df() -> pl.DataFrame:
|
|
"""One-row immunization matching input_layer.immunization schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"immunization_id": ["IMM001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": ["ENC001"],
|
|
"source_code_type": ["cvx"],
|
|
"source_code": ["208"],
|
|
"source_description": ["COVID-19 Pfizer"],
|
|
"normalized_code_type": ["cvx"],
|
|
"normalized_code": ["208"],
|
|
"normalized_description": ["COVID-19 Pfizer-BioNTech"],
|
|
"status": ["completed"],
|
|
"status_reason": [None],
|
|
"occurrence_date": [None],
|
|
"source_dose": ["0.3 mL"],
|
|
"normalized_dose": ["0.3 mL"],
|
|
"lot_number": ["EL9269"],
|
|
"body_site": ["left arm"],
|
|
"route": ["intramuscular"],
|
|
"location_id": ["LOC001"],
|
|
"practitioner_id": ["DR001"],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def lab_result_df() -> pl.DataFrame:
|
|
"""One-row lab result matching input_layer.lab_result schema."""
|
|
return pl.DataFrame(
|
|
{
|
|
"lab_result_id": ["LAB001"],
|
|
"person_id": ["P001"],
|
|
"patient_id": ["PT001"],
|
|
"encounter_id": ["ENC001"],
|
|
"accession_number": ["ACC001"],
|
|
"source_order_type": ["loinc"],
|
|
"source_order_code": ["2345-7"],
|
|
"source_order_description": ["Glucose"],
|
|
"source_component_type": ["loinc"],
|
|
"source_component_code": ["2345-7"],
|
|
"source_component_description": ["Glucose [Mass/volume] in Serum"],
|
|
"normalized_order_type": ["loinc"],
|
|
"normalized_order_code": ["2345-7"],
|
|
"normalized_order_description": ["Glucose"],
|
|
"normalized_component_type": ["loinc"],
|
|
"normalized_component_code": ["2345-7"],
|
|
"normalized_component_description": ["Glucose [Mass/volume] in Serum"],
|
|
"status": ["final"],
|
|
"result": ["105"],
|
|
"result_datetime": [None],
|
|
"collection_datetime": [None],
|
|
"source_units": ["mg/dL"],
|
|
"normalized_units": ["mg/dL"],
|
|
"source_reference_range_low": ["70"],
|
|
"source_reference_range_high": ["100"],
|
|
"normalized_reference_range_low": ["70"],
|
|
"normalized_reference_range_high": ["100"],
|
|
"source_abnormal_flag": ["H"],
|
|
"normalized_abnormal_flag": ["high"],
|
|
"specimen": ["serum"],
|
|
"ordering_practitioner_id": ["DR001"],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def provider_attribution_df() -> pl.DataFrame:
|
|
"""One-row provider attribution matching input_layer.provider_attribution."""
|
|
return pl.DataFrame(
|
|
{
|
|
"person_id": ["P001"],
|
|
"member_id": ["M001"],
|
|
"practitioner_id": ["DR001"],
|
|
"practitioner_npi": ["1234567890"],
|
|
"attribution_type": ["primary"],
|
|
"attribution_start_date": [None],
|
|
"attribution_end_date": [None],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def member_months_df() -> pl.DataFrame:
|
|
"""Simple member-months DataFrame used by claims_preprocessing pipeline."""
|
|
return pl.DataFrame(
|
|
{
|
|
"person_id": ["P001"],
|
|
"member_id": ["M001"],
|
|
"year": [2024],
|
|
"month": [1],
|
|
"payer": ["Medicare"],
|
|
"plan": [None],
|
|
"data_source": ["test"],
|
|
}
|
|
)
|
|
|
|
|
|
# ── PFS computation fixtures ──────────────────────────────────────────────────
|
|
|
|
TEST_CF: float = 32.7442
|
|
"""Conversion factor used by PFS payment() tests (historical CY2023)."""
|
|
|
|
|
|
@pytest.fixture
|
|
def rvu_df() -> pl.DataFrame:
|
|
"""RVU data for PFS payment calculation tests.
|
|
|
|
Note: ``conv_factor`` is no longer a column on pfs.rvu — it's
|
|
passed as the ``cf=`` keyword to ``pfs.calcs.payment.payment()``.
|
|
Use ``tests.conftest.TEST_CF`` when calling.
|
|
"""
|
|
return pl.DataFrame(
|
|
{
|
|
"hcpcs": ["99213", "99214", "99215"],
|
|
"work_rvu": [0.97, 1.50, 2.11],
|
|
"non_fac_pe_rvu": [1.04, 1.56, 2.22],
|
|
"fac_pe_rvu": [0.41, 0.63, 0.95],
|
|
"mp_rvu": [0.07, 0.11, 0.16],
|
|
"mac": ["10212", "10212", "10212"],
|
|
"locality": ["0201", "0201", "0201"],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def gpci_df() -> pl.DataFrame:
|
|
"""GPCI data for PFS payment calculation tests."""
|
|
return pl.DataFrame(
|
|
{
|
|
"mac": ["10212"],
|
|
"locality": ["0201"],
|
|
"work_gpci": [1.0],
|
|
"pe_gpci": [0.998],
|
|
"mp_gpci": [0.633],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def labor_df() -> pl.DataFrame:
|
|
"""Clinical labor inputs for direct PE cost tests."""
|
|
return pl.DataFrame(
|
|
{
|
|
"hcpcs": ["99213", "99213", "99214"],
|
|
"nf_minutes": [14.0, 5.0, 18.0],
|
|
"f_minutes": [9.0, 3.0, 12.0],
|
|
"rate_per_minute": [0.63, 0.49, 0.63],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def supply_df() -> pl.DataFrame:
|
|
"""Medical supply inputs for direct PE cost tests."""
|
|
return pl.DataFrame(
|
|
{
|
|
"hcpcs": ["99213", "99214"],
|
|
"nf_quantity": [2.0, 3.0],
|
|
"f_quantity": [1.0, 2.0],
|
|
"unit_price": [0.12, 0.12],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def equipment_df() -> pl.DataFrame:
|
|
"""Medical equipment inputs for direct PE cost tests."""
|
|
return pl.DataFrame(
|
|
{
|
|
"hcpcs": ["99213", "99214"],
|
|
"nf_minutes": [10.0, 15.0],
|
|
"f_minutes": [6.0, 10.0],
|
|
"unit_price": [1200.0, 1200.0],
|
|
"useful_life": [7.0, 7.0],
|
|
"minutes_per_year": [525600.0, 525600.0],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def equipment_with_maintenance_df() -> pl.DataFrame:
|
|
"""Equipment DataFrame that includes a maintenance_factor column."""
|
|
return pl.DataFrame(
|
|
{
|
|
"hcpcs": ["99213"],
|
|
"nf_minutes": [10.0],
|
|
"f_minutes": [6.0],
|
|
"unit_price": [1200.0],
|
|
"useful_life": [7.0],
|
|
"minutes_per_year": [525600.0],
|
|
"maintenance_factor": [0.05],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def work_time_df() -> pl.DataFrame:
|
|
"""Physician work time for time-intensity ratio tests."""
|
|
return pl.DataFrame(
|
|
{
|
|
"hcpcs": ["99213", "99214", "99215"],
|
|
"work_rvu": [0.97, 1.50, 2.11],
|
|
"total_time": [21.0, 31.0, 46.0],
|
|
"intra_service_time": [15.0, 22.0, 33.0],
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def mppr_claims_df() -> pl.DataFrame:
|
|
"""Two procedures in the same session for MPPR reduction tests."""
|
|
return pl.DataFrame(
|
|
{
|
|
"claim_id": ["CLM001", "CLM001"],
|
|
"hcpcs": ["99214", "99213"],
|
|
"session_id": ["SES001", "SES001"],
|
|
"non_fac_pe_rvu": [1.56, 1.04],
|
|
}
|
|
)
|
|
|
|
|
|
# ── rex fixtures ──────────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.fixture
|
|
def sas_listing_text() -> str:
|
|
"""Multiline SAS listing file content for sieve classification tests."""
|
|
return (
|
|
" The SAS System 10:30 AM\n"
|
|
"\n"
|
|
" Obs claim_id paid_amount diag_code\n"
|
|
" 1 CLM001 75.00 E119\n"
|
|
" 2 CLM002 150.00 I10\n"
|
|
" 3 CLM003 225.00 J449\n"
|
|
" Total: 450.00\n"
|
|
"\n"
|
|
"NOTE: The data set WORK.CLAIMS has 3 observations.\n"
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def fixed_width_text() -> str:
|
|
"""Fixed-width records for FieldMap positional extraction tests."""
|
|
return (
|
|
"CLM001 P001 20240115000007500\n"
|
|
"CLM002 P002 20240116000015000\n"
|
|
"CLM003 P003 20240117000022500\n"
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def pipe_delimited_text() -> str:
|
|
"""Pipe-delimited file for FieldMap delimiter-mode tests."""
|
|
return (
|
|
"claim_id|person_id|service_date|paid_amount\n"
|
|
"CLM001|P001|20240115|75.00\n"
|
|
"CLM002|P002|20240116|150.00\n"
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def copybook_text() -> str:
|
|
"""Simple COBOL copybook definition for copybook parser tests."""
|
|
return """
|
|
01 CLAIM-RECORD.
|
|
05 CLAIM-ID PIC X(10).
|
|
05 PERSON-ID PIC X(10).
|
|
05 SERVICE-DATE PIC 9(8).
|
|
05 PAID-AMOUNT PIC S9(7)V99 COMP-3.
|
|
05 FILLER PIC X(5).
|
|
05 DX-CODE PIC X(7).
|
|
"""
|
|
|
|
|
|
@pytest.fixture
|
|
def basic_sieve():
|
|
"""Minimal Sieve with only a data pattern for simple unit tests."""
|
|
from rex.sieve import Sieve
|
|
|
|
return Sieve(
|
|
name="test_basic",
|
|
data=re.compile(r"^\s+\d+\s+\w"),
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def sas_sieve():
|
|
"""Full four-pattern SAS listing Sieve matching the module docstring."""
|
|
from rex.sieve import Sieve
|
|
|
|
return Sieve(
|
|
name="sas_listing",
|
|
head=re.compile(r"^\s*(The SAS System|\x0c)|^\s+\d{2}:\d{2}"),
|
|
rule=re.compile(r"^\s*(Obs\s+\w|---+[\s-]*---+)"),
|
|
data=re.compile(r"^\s+\d+\s+\w"),
|
|
skip=re.compile(r"^\s*(Total|NOTE:|WARNING:|$)"),
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def fixed_width_field_map():
|
|
"""FieldMap in fixed-width positional mode for claim record extraction."""
|
|
from rex.sieve import FieldMap
|
|
|
|
return FieldMap(
|
|
positions={
|
|
"claim_id": (0, 10),
|
|
"person_id": (10, 20),
|
|
"service_date": (20, 28),
|
|
"paid_amount": (28, 37),
|
|
}
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def delimited_field_map():
|
|
"""FieldMap in pipe-delimited mode with index mapping."""
|
|
from rex.sieve import FieldMap
|
|
|
|
return FieldMap(
|
|
delimiter="|",
|
|
indices={
|
|
"claim_id": 0,
|
|
"person_id": 1,
|
|
"service_date": 2,
|
|
"paid_amount": 3,
|
|
},
|
|
)
|
|
|
|
|
|
# ── bib.tag fixtures ──────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.fixture
|
|
def tag_labels() -> list[str]:
|
|
"""Mixed tag label strings for filter_tags tests."""
|
|
return [
|
|
"module:pfs",
|
|
"module:aco",
|
|
"table:pfs.rvu",
|
|
"source:cms-website",
|
|
"year:2026",
|
|
"rule:cms-1807-f",
|
|
"file:rvu",
|
|
]
|
|
|
|
|
|
# ── temp file fixtures ────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.fixture
|
|
def tmp_text_file(tmp_path: Path) -> Path:
|
|
"""Write the SAS listing sample to a temporary .lst file."""
|
|
content = (
|
|
" The SAS System 10:30 AM\n"
|
|
"\n"
|
|
" Obs claim_id paid_amount\n"
|
|
" 1 CLM001 75.00\n"
|
|
" 2 CLM002 150.00\n"
|
|
)
|
|
f = tmp_path / "report.lst"
|
|
f.write_text(content, encoding="utf-8")
|
|
return f
|
|
|
|
|
|
@pytest.fixture
|
|
def tmp_csv_file(tmp_path: Path) -> Path:
|
|
"""Write a simple CSV to a temporary file."""
|
|
content = "claim_id,person_id,paid_amount\nCLM001,P001,75.00\nCLM002,P002,150.00\n"
|
|
f = tmp_path / "claims.csv"
|
|
f.write_text(content, encoding="utf-8")
|
|
return f
|