Align Stage 1 validation contracts (#1003)

Author: MaxGhenis

changelog.d/1003.fixed.md

@@ -0,0 +1 @@
+Align Stage 1 validators with the central dataset export and calibration target contracts.

validation/stage_1/test_no_formula_variables_stored.py

@@ -13,13 +13,15 @@
 import numpy as np
 import pytest
 from policyengine_us_data.datasets.cps.extended_cps import ExtendedCPS_2024
+from policyengine_us_data.utils.dataset_validation import (
+    STRUCTURAL_COMPUTED_EXPORT_VARIABLES,
+)
 
 KNOWN_FORMULA_EXCEPTIONS = {
-    "person_id",
     "interest_deduction",
     "self_employed_health_insurance_ald",
     "self_employed_pension_contribution_ald",
-}
+} | STRUCTURAL_COMPUTED_EXPORT_VARIABLES
 
 
 @pytest.fixture(scope="module")

validation/stage_1/test_policy_data_db.py

@@ -3,6 +3,7 @@
 import sqlite3
 
 import pytest
+from policyengine_us_data.utils.target_variables import target_variable_is_valid
 
 from policyengine_us_data.storage import STORAGE_FOLDER
 
@@ -322,14 +323,16 @@ def test_congressional_district_strata(built_db):
 
 
 def test_all_target_variables_exist_in_policyengine(built_db):
-    """Every target variable must be a valid policyengine-us variable."""
+    """Every target variable/expression must use policyengine-us variables."""
     from policyengine_us.system import system
 
     conn = sqlite3.connect(str(built_db))
     variables = {r[0] for r in conn.execute("SELECT DISTINCT variable FROM targets")}
     conn.close()
 
-    missing = [v for v in variables if v not in system.variables]
+    missing = sorted(
+        v for v in variables if not target_variable_is_valid(v, system.variables)
+    )
     assert not missing, f"Target variables not in policyengine-us: {missing}"