Merge main, resolve uv.lock conflict

Author: baogorek

CHANGELOG.md

@@ -5,6 +5,24 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.54.1] - 2026-01-26 02:49:11
+
+### Fixed
+
+- Derive partnership_se_income from PUF source columns using Yale Budget Lab's gross-up approach instead of looking for non-existent k1bx14 columns.
+
+## [1.54.0] - 2026-01-25 17:43:38
+
+### Added
+
+- partnership_se_income variable from Schedule K-1 Box 14 (k1bx14p + k1bx14s), representing partnership income subject to self-employment tax.
+
+## [1.53.1] - 2026-01-25 15:48:00
+
+### Changed
+
+- Bumped policyengine-core minimum version to 3.23.5 for pandas 3.0 compatibility
+
 ## [1.53.0] - 2026-01-23 20:51:58
 
 ### Changed
@@ -815,6 +833,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 
 
+[1.54.1]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.54.0...1.54.1
+[1.54.0]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.53.1...1.54.0
+[1.53.1]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.53.0...1.53.1
 [1.53.0]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.52.0...1.53.0
 [1.52.0]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.51.1...1.52.0
 [1.51.1]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.51.0...1.51.1

changelog.yaml

@@ -687,3 +687,20 @@
     changed:
     - Added policyengine-claude plugin auto-install configuration.
   date: 2026-01-23 20:51:58
+- bump: patch
+  changes:
+    changed:
+    - Bumped policyengine-core minimum version to 3.23.5 for pandas 3.0 compatibility
+  date: 2026-01-25 15:48:00
+- bump: minor
+  changes:
+    added:
+    - partnership_se_income variable from Schedule K-1 Box 14 (k1bx14p + k1bx14s),
+      representing partnership income subject to self-employment tax.
+  date: 2026-01-25 17:43:38
+- bump: patch
+  changes:
+    fixed:
+    - Derive partnership_se_income from PUF source columns using Yale Budget Lab's
+      gross-up approach instead of looking for non-existent k1bx14 columns.
+  date: 2026-01-26 02:49:11

policyengine_us_data/datasets/cps/extended_cps.py

@@ -50,6 +50,7 @@
     "miscellaneous_income",
     "alimony_expense",
     "farm_income",
+    "partnership_se_income",
     "alimony_income",
     "health_savings_account_ald",
     "non_sch_d_capital_gains",

policyengine_us_data/datasets/puf/puf.py

@@ -381,7 +381,33 @@ def preprocess_puf(puf: pd.DataFrame) -> pd.DataFrame:
     puf["unreported_payroll_tax"] = puf.E09800
     # Ignore f2441 (AMT form attached)
     # Ignore cmbtp (estimate of AMT income not in AGI)
-    # Ignore k1bx14s and k1bx14p (partner self-employment income included in partnership and S-corp income)
+
+    # Partnership self-employment income from Schedule K-1 Box 14
+    # This is the portion of partnership income subject to SE tax (general partners)
+    # Derived from total SE income minus Schedule C and Schedule F income
+    # Based on Yale Budget Lab's Tax-Data process_puf.R approach:
+    #   E30400 = taxpayer's TAXABLE SE income (already * 0.9235)
+    #   E30500 = spouse's TAXABLE SE income (already * 0.9235)
+    #   E00900 = Schedule C net profit/loss (gross)
+    #   E02100 = Schedule F farm income (gross)
+    # Since E30400/E30500 are post-deduction (taxable), we gross them up
+    # by dividing by 0.9235 before subtracting Sch C/F.
+    # PolicyEngine applies the 0.9235 factor itself in taxable_self_employment_income.
+    SE_DEDUCTION_FACTOR = 0.9235  # 1 - 0.5 * 0.153 (half of SE tax rate)
+    taxable_se = puf["E30400"].fillna(0) + puf["E30500"].fillna(0)
+    gross_se = taxable_se / SE_DEDUCTION_FACTOR
+    schedule_c_f_income = puf["E00900"].fillna(0) + puf["E02100"].fillna(0)
+    # Only compute when there's partnership activity (net partnership income != 0)
+    has_partnership = (
+        puf["E25940"].fillna(0)
+        + puf["E25980"].fillna(0)
+        - puf["E25920"].fillna(0)
+        - puf["E25960"].fillna(0)
+    ) != 0
+    partnership_se = np.where(
+        has_partnership, gross_se - schedule_c_f_income, 0
+    )
+    puf["partnership_se_income"] = partnership_se
 
     # --- Qualified Business Income Deduction (QBID) simulation ---
     w2, ubia = simulate_w2_and_ubia_from_puf(puf, seed=42)
@@ -491,6 +517,7 @@ def preprocess_puf(puf: pd.DataFrame) -> pd.DataFrame:
     "business_is_sstb",
     "deductible_mortgage_interest",
     "partnership_s_corp_income",
+    "partnership_se_income",
     "qualified_reit_and_ptp_income",
     "qualified_bdc_income",
 ]
@@ -544,6 +571,13 @@ def generate(self):
             for variable in system.variables
         }
 
+        # Filter FINANCIAL_SUBSET to only include variables defined in
+        # policyengine-us. This allows us-data to be updated before or after
+        # policyengine-us without breaking.
+        self.available_financial_vars = [
+            v for v in FINANCIAL_SUBSET if v in self.variable_to_entity
+        ]
+
         VARIABLES = [
             "person_id",
             "tax_unit_id",
@@ -563,7 +597,7 @@ def generate(self):
             "is_tax_unit_head",
             "is_tax_unit_spouse",
             "is_tax_unit_dependent",
-        ] + FINANCIAL_SUBSET
+        ] + self.available_financial_vars
 
         self.holder = {variable: [] for variable in VARIABLES}
 
@@ -607,7 +641,7 @@ def generate(self):
     def add_tax_unit(self, row, tax_unit_id):
         self.holder["tax_unit_id"].append(tax_unit_id)
 
-        for key in FINANCIAL_SUBSET:
+        for key in self.available_financial_vars:
             if self.variable_to_entity[key] == "tax_unit":
                 self.holder[key].append(row[key])
 
@@ -649,7 +683,7 @@ def add_filer(self, row, tax_unit_id):
             row["interest_deduction"]
         )
 
-        for key in FINANCIAL_SUBSET:
+        for key in self.available_financial_vars:
             if key == "deductible_mortgage_interest":
                 # Skip this one- we are adding it artificially at the filer level.
                 continue
@@ -682,7 +716,7 @@ def add_spouse(self, row, tax_unit_id):
 
         self.holder["deductible_mortgage_interest"].append(0)
 
-        for key in FINANCIAL_SUBSET:
+        for key in self.available_financial_vars:
             if key == "deductible_mortgage_interest":
                 # Skip this one- we are adding it artificially at the filer level.
                 continue
@@ -706,7 +740,7 @@ def add_dependent(self, row, tax_unit_id, dependent_id):
 
         self.holder["deductible_mortgage_interest"].append(0)
 
-        for key in FINANCIAL_SUBSET:
+        for key in self.available_financial_vars:
             if key == "deductible_mortgage_interest":
                 # Skip this one- we are adding it artificially at the filer level.
                 continue

policyengine_us_data/tests/test_pandas3_compatibility.py

@@ -0,0 +1,33 @@
+"""Test pandas 3.0 compatibility.
+
+This test verifies that policyengine-core 3.23.5+ correctly handles
+pandas Series with StringDtype index when encoding enums.
+"""
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from policyengine_core.enums import Enum
+
+
+class SampleEnum(Enum):
+    VALUE_A = "value_a"
+    VALUE_B = "value_b"
+
+
+def test_enum_encode_with_pandas_series():
+    """Test that Enum.encode works with pandas Series containing enum items.
+
+    In pandas 3.0, Series with StringDtype use label-based indexing by default.
+    This test verifies the fix in policyengine-core 3.23.5 that uses .iloc[0]
+    for positional access.
+    """
+    enum_items = [SampleEnum.VALUE_A, SampleEnum.VALUE_B, SampleEnum.VALUE_A]
+    series = pd.Series(enum_items)
+
+    # This would fail with KeyError: 0 before the fix
+    encoded = SampleEnum.encode(series)
+
+    assert len(encoded) == 3
+    assert list(encoded) == [0, 1, 0]

pyproject.toml

@@ -8,7 +8,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "policyengine_us_data"
-version = "1.53.0"
+version = "1.54.1"
 description = "A package to create representative microdata for the US."
 readme = "README.md"
 authors = [
@@ -21,12 +21,12 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-    "policyengine-us>=1.353.0",
-    "policyengine-core>=3.19.0",
+    "policyengine-us>=1.516.0",
+    "policyengine-core>=3.23.6",
     "pandas>=2.3.1",
     "requests>=2.25.0",
     "tqdm>=4.60.0",
-    "microdf_python>=1.0.0",
+    "microdf_python>=1.2.1",
     "setuptools>=60",
     "microimpute>=1.1.4",
     "pip-system-certs>=3.0",