Assign distinct reform IDs to national tax expenditure targets

changelog.d/distinct-tax-expenditure-reform-ids.fixed.md

@@ -0,0 +1 @@
+Assign distinct `reform_id` values to each national JCT tax expenditure target instead of reusing a single generic reform id for all of them.

policyengine_us_data/db/etl_national_targets.py

@@ -14,8 +14,6 @@
     etl_argparser,
 )
 
-TAX_EXPENDITURE_REFORM_ID = 1
-
 
 def extract_national_targets(dataset: str = DEFAULT_DATASET):
     """
@@ -64,43 +62,49 @@ def extract_national_targets(dataset: str = DEFAULT_DATASET):
     # These JCT values are tax expenditures, not baseline deduction totals.
     # They must be matched against repeal-based income tax deltas in the
     # unified calibration path.
-    tax_expenditure_targets = [
+    raw_tax_expenditure_targets = [
         {
+            "reform_id": 1,
             "variable": "salt_deduction",
             "value": 21.247e9,
             "source": "Joint Committee on Taxation",
             "notes": "SALT deduction tax expenditure",
             "year": HARDCODED_YEAR,
         },
         {
+            "reform_id": 2,
             "variable": "medical_expense_deduction",
             "value": 11.4e9,
             "source": "Joint Committee on Taxation",
             "notes": "Medical expense deduction tax expenditure",
             "year": HARDCODED_YEAR,
         },
         {
+            "reform_id": 3,
             "variable": "charitable_deduction",
             "value": 65.301e9,
             "source": "Joint Committee on Taxation",
             "notes": "Charitable deduction tax expenditure",
             "year": HARDCODED_YEAR,
         },
         {
+            "reform_id": 4,
             "variable": "deductible_mortgage_interest",
             "value": 24.8e9,
             "source": "Joint Committee on Taxation",
             "notes": "Mortgage interest deduction tax expenditure",
             "year": HARDCODED_YEAR,
         },
         {
+            "reform_id": 5,
             "variable": "qualified_business_income_deduction",
             "value": 63.1e9,
             "source": "Joint Committee on Taxation",
             "notes": "QBI deduction tax expenditure",
             "year": HARDCODED_YEAR,
         },
     ]
+    tax_expenditure_targets = [{**target} for target in raw_tax_expenditure_targets]
 
     direct_sum_targets = [
         {
@@ -493,7 +497,7 @@ def load_national_targets(
     with Session(engine) as session:
         # Get the national stratum
         us_stratum = (
-            session.query(Stratum).filter(Stratum.parent_stratum_id == None).first()
+            session.query(Stratum).filter(Stratum.parent_stratum_id.is_(None)).first()
         )
 
         if not us_stratum:
@@ -631,6 +635,7 @@ def load_national_targets(
 
             for _, target_data in tax_expenditure_df.iterrows():
                 target_year = target_data["year"]
+                target_reform_id = int(target_data["reform_id"])
 
                 # Clean up incorrectly scoped baseline rows from older DBs.
                 if migrated_stratum_ids:
@@ -641,7 +646,7 @@ def load_national_targets(
                             Target.variable == target_data["variable"],
                             Target.period == target_year,
                             Target.reform_id == 0,
-                            Target.active == True,
+                            Target.active,
                         )
                         .all()
                     )
@@ -654,7 +659,7 @@ def load_national_targets(
                         Target.stratum_id == us_stratum.stratum_id,
                         Target.variable == target_data["variable"],
                         Target.period == target_year,
-                        Target.reform_id == TAX_EXPENDITURE_REFORM_ID,
+                        Target.reform_id == target_reform_id,
                     )
                     .first()
                 )
@@ -679,7 +684,7 @@ def load_national_targets(
                         stratum_id=us_stratum.stratum_id,
                         variable=target_data["variable"],
                         period=target_year,
-                        reform_id=TAX_EXPENDITURE_REFORM_ID,
+                        reform_id=target_reform_id,
                         value=target_data["value"],
                         active=True,
                         source="PolicyEngine",

policyengine_us_data/tests/test_database_build.py

@@ -144,6 +144,29 @@ def test_jct_mortgage_tax_expenditure_uses_mortgage_specific_variable(built_db):
     ]
 
 
+def test_jct_tax_expenditure_targets_have_distinct_reform_ids(built_db):
+    """Each JCT tax expenditure target should have its own reform id."""
+    conn = sqlite3.connect(str(built_db))
+    rows = conn.execute("""
+        SELECT t.variable, t.reform_id
+        FROM targets t
+        WHERE t.notes LIKE '%Modeled as repeal-based income tax expenditure target%'
+          AND t.notes LIKE '%Source: Joint Committee on Taxation%'
+        ORDER BY t.variable
+        """).fetchall()
+    conn.close()
+
+    expected = [
+        ("charitable_deduction", 3),
+        ("deductible_mortgage_interest", 4),
+        ("medical_expense_deduction", 2),
+        ("qualified_business_income_deduction", 5),
+        ("salt_deduction", 1),
+    ]
+
+    assert rows == expected
+
+
 def test_state_income_tax_targets(built_db):
     """State income tax targets should cover all income-tax states."""
     conn = sqlite3.connect(str(built_db))