From 3cd3d3c89dc63979378368f1ac88d27f328672d0 Mon Sep 17 00:00:00 2001
From: Max Ghenis <mghenis@gmail.com>
Date: Sat, 25 Apr 2026 17:18:34 -0400
Subject: [PATCH] Map CPS farm income to farm operations

---
 changelog.d/cps-farm-operations-income.fixed  |  1 +
 policyengine_us_data/datasets/cps/cps.py      |  2 +-
 .../datasets/test_cps_income_variables.py     | 68 +++++++++++++++++++
 3 files changed, 70 insertions(+), 1 deletion(-)
 create mode 100644 changelog.d/cps-farm-operations-income.fixed
 create mode 100644 tests/unit/datasets/test_cps_income_variables.py

diff --git a/changelog.d/cps-farm-operations-income.fixed b/changelog.d/cps-farm-operations-income.fixed
new file mode 100644
index 000000000..b54206125
--- /dev/null
+++ b/changelog.d/cps-farm-operations-income.fixed
@@ -0,0 +1 @@
+Map CPS farm self-employment income to farm operations income.
diff --git a/policyengine_us_data/datasets/cps/cps.py b/policyengine_us_data/datasets/cps/cps.py
index d12ba7eef..877eed849 100644
--- a/policyengine_us_data/datasets/cps/cps.py
+++ b/policyengine_us_data/datasets/cps/cps.py
@@ -798,7 +798,7 @@ def add_personal_income_variables(cps: h5py.File, person: DataFrame, year: int):
         1 - p["taxable_interest_fraction"]
     )
     cps["self_employment_income"] = person.SEMP_VAL
-    cps["farm_income"] = person.FRSE_VAL
+    cps["farm_operations_income"] = person.FRSE_VAL
     cps["qualified_dividend_income"] = (
         person.DIV_VAL * (p["qualified_dividend_fraction"])
     )
diff --git a/tests/unit/datasets/test_cps_income_variables.py b/tests/unit/datasets/test_cps_income_variables.py
new file mode 100644
index 000000000..b85639858
--- /dev/null
+++ b/tests/unit/datasets/test_cps_income_variables.py
@@ -0,0 +1,68 @@
+import numpy as np
+import pandas as pd
+
+from policyengine_us_data.datasets.cps.cps import add_personal_income_variables
+
+
+def _minimal_person_income_frame() -> pd.DataFrame:
+    columns = [
+        "WSAL_VAL",
+        "HRSWK",
+        "A_HRS1",
+        "INT_VAL",
+        "SEMP_VAL",
+        "FRSE_VAL",
+        "DIV_VAL",
+        "RNT_VAL",
+        "RESNSS1",
+        "RESNSS2",
+        "SS_VAL",
+        "A_AGE",
+        "UC_VAL",
+        "LKWEEKS",
+        "PNSN_VAL",
+        "ANN_VAL",
+        "DST_SC1",
+        "DST_VAL1",
+        "DST_SC2",
+        "DST_VAL2",
+        "DST_SC1_YNG",
+        "DST_VAL1_YNG",
+        "DST_SC2_YNG",
+        "DST_VAL2_YNG",
+        "OI_OFF",
+        "OI_VAL",
+        "CSP_VAL",
+        "PAW_VAL",
+        "SSI_VAL",
+        "RETCB_VAL",
+        "CAP_VAL",
+        "WICYN",
+        "VET_VAL",
+        "WC_VAL",
+        "DIS_VAL1",
+        "DIS_SC1",
+        "DIS_VAL2",
+        "DIS_SC2",
+        "CHSP_VAL",
+        "PHIP_VAL",
+        "POTC_VAL",
+        "PMED_VAL",
+        "MCARE",
+        "PEMCPREM",
+    ]
+    person = pd.DataFrame({column: [0.0, 0.0] for column in columns})
+    person["A_AGE"] = [30, 45]
+    person["LKWEEKS"] = [0, 0]
+    return person
+
+
+def test_add_personal_income_variables_maps_farm_self_employment_to_operations():
+    person = _minimal_person_income_frame()
+    person["FRSE_VAL"] = [1_000.0, -500.0]
+    cps = {}
+
+    add_personal_income_variables(cps, person, 2024)
+
+    np.testing.assert_array_equal(cps["farm_operations_income"], [1_000.0, -500.0])
+    assert "farm_income" not in cps