Update package version

Author: MaxGhenis

CHANGELOG.md

@@ -1,3 +1,10 @@
+## [1.113.1] - 2026-05-13
+
+### Fixed
+
+- Remove temporary CPS take-up source anchors from persisted H5 outputs and add an enhanced-CPS-only data build path.
+
+
 ## [1.113.0] - 2026-05-12
 
 ### Added

changelog.d/964.fixed

@@ -761,7 +761,7 @@ Worker function that builds a subset of H5 files.
 ### `modal_app.data_build.build_datasets`
 
 ```python
-def build_datasets(upload: bool = False, branch: str = 'main', sequential: bool = False, clear_checkpoints: bool = False, skip_tests: bool = False, skip_enhanced_cps: bool = False, stage_only: bool = False, run_id: str = '')
+def build_datasets(upload: bool = False, branch: str = 'main', sequential: bool = False, clear_checkpoints: bool = False, skip_tests: bool = False, skip_enhanced_cps: bool = False, skip_stage_5: bool = False, stage_only: bool = False, run_id: str = '')
 ```
 
 Build all datasets with preemption-resilient checkpointing.

docs/engineering/pipeline-map.md

@@ -61,7 +61,7 @@
     "docstring": "\"Add auto loan balance, interest and net_worth variable.",
     "id": "add_auto_loan",
     "kind": "function",
-    "line": 2778,
+    "line": 2792,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_auto_loan_interest_and_net_worth"
@@ -88,7 +88,7 @@
     "docstring": "Populate household-level geography variables used by PolicyEngine US.\n\nArgs:\n    cps: Output CPS H5 group receiving derived household variables.\n    household: Raw CPS household table.",
     "id": "add_household_variables",
     "kind": "function",
-    "line": 1440,
+    "line": 1454,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_household_variables"
@@ -115,7 +115,7 @@
     "docstring": "Add basic ID and weight variables.\n\nArgs:\n    cps (h5py.File): The CPS dataset file.\n    person (DataFrame): The person table of the ASEC.\n    tax_unit (DataFrame): The tax unit table created from the person table\n        of the ASEC.\n    family (DataFrame): The family table of the ASEC.\n    spm_unit (DataFrame): The SPM unit table created from the person table\n        of the ASEC.\n    household (DataFrame): The household table of the ASEC.",
     "id": "add_id_variables",
     "kind": "function",
-    "line": 919,
+    "line": 933,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_id_variables"
@@ -142,7 +142,7 @@
     "docstring": "Impute ORG-derived wage and union inputs onto CPS persons.",
     "id": "add_org_inputs",
     "kind": "function",
-    "line": 2662,
+    "line": 2676,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_org_labor_market_inputs"
@@ -169,7 +169,7 @@
     "docstring": "Add income variables.\n\nArgs:\n    cps (h5py.File): The CPS dataset file.\n    person (DataFrame): The CPS person table.\n    year (int): The CPS year",
     "id": "add_personal_income_variables",
     "kind": "function",
-    "line": 1125,
+    "line": 1139,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_personal_income_variables"
@@ -196,7 +196,7 @@
     "docstring": "Add personal demographic variables.\n\nArgs:\n    cps (h5py.File): The CPS dataset file.\n    person (DataFrame): The CPS person table.",
     "id": "add_personal_variables",
     "kind": "function",
-    "line": 981,
+    "line": 995,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_personal_variables"
@@ -223,7 +223,7 @@
     "docstring": "",
     "id": "add_previous_year_income",
     "kind": "function",
-    "line": 1482,
+    "line": 1496,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_previous_year_income"
@@ -277,7 +277,7 @@
     "docstring": "",
     "id": "add_spm_variables",
     "kind": "function",
-    "line": 1401,
+    "line": 1415,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_spm_variables"
@@ -304,7 +304,7 @@
     "docstring": "Assign SSN card type using PRCITSHP, employment status, and ASEC-UA conditions.\nCodes:\n- 0: \"NONE\" - Likely undocumented immigrants\n- 1: \"CITIZEN\" - US citizens (born or naturalized)\n- 2: \"NON_CITIZEN_VALID_EAD\" - Non-citizens with work/study authorization\n- 3: \"OTHER_NON_CITIZEN\" - Non-citizens with indicators of legal status",
     "id": "add_ssn_card_type",
     "kind": "function",
-    "line": 1588,
+    "line": 1602,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_ssn_card_type"
@@ -331,7 +331,7 @@
     "docstring": "",
     "id": "add_takeup",
     "kind": "function",
-    "line": 466,
+    "line": 476,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_takeup"
@@ -358,7 +358,7 @@
     "docstring": "",
     "id": "add_tips",
     "kind": "function",
-    "line": 2487,
+    "line": 2501,
     "metadata": {
       "api_refs": [
         "policyengine_us_data.datasets.cps.cps.add_tips"
@@ -471,10 +471,10 @@
     "source_file": "policyengine_us_data/calibration/publish_local_area.py"
   },
   "build_datasets": {
-    "docstring": "Build all datasets with preemption-resilient checkpointing.\n\nArgs:\n    upload: Whether to upload completed datasets.\n    branch: Git branch to build from.\n    sequential: Use sequential (non-parallel) execution.\n    clear_checkpoints: Clear existing checkpoints before starting.\n    skip_tests: Skip running the test suite (useful for calibration runs).\n    skip_enhanced_cps: Skip enhanced_cps.py and small_enhanced_cps.py\n        (useful for calibration runs that only need source_imputed H5).\n    stage_only: Upload to HF staging only, without promoting a release.",
+    "docstring": "Build all datasets with preemption-resilient checkpointing.\n\nArgs:\n    upload: Whether to upload completed datasets.\n    branch: Git branch to build from.\n    sequential: Use sequential (non-parallel) execution.\n    clear_checkpoints: Clear existing checkpoints before starting.\n    skip_tests: Skip running the test suite (useful for calibration runs).\n    skip_enhanced_cps: Skip enhanced_cps.py and small_enhanced_cps.py\n        (useful for calibration runs that only need source_imputed H5).\n    skip_stage_5: Skip source-imputed CPS and small enhanced CPS after\n        enhanced_cps_2024.h5 is built.\n    stage_only: Upload to HF staging only, without promoting a release.",
     "id": "build_datasets",
     "kind": "function",
-    "line": 555,
+    "line": 563,
     "metadata": {
       "api_refs": [
         "modal_app.data_build.build_datasets"
@@ -499,7 +499,7 @@
       ]
     },
     "object_path": "modal_app.data_build.build_datasets",
-    "signature": "def build_datasets(upload: bool = False, branch: str = 'main', sequential: bool = False, clear_checkpoints: bool = False, skip_tests: bool = False, skip_enhanced_cps: bool = False, stage_only: bool = False, run_id: str = '')",
+    "signature": "def build_datasets(upload: bool = False, branch: str = 'main', sequential: bool = False, clear_checkpoints: bool = False, skip_tests: bool = False, skip_enhanced_cps: bool = False, skip_stage_5: bool = False, stage_only: bool = False, run_id: str = '')",
     "source_file": "modal_app/data_build.py"
   },
   "build_districts": {
@@ -968,7 +968,7 @@
     "docstring": "Build CPS before PUF because PUF pension imputation loads CPS_2024.",
     "id": "cps_puf_build_phase",
     "kind": "function",
-    "line": 426,
+    "line": 432,
     "metadata": {
       "api_refs": [
         "modal_app.data_build.run_cps_then_puf_phase"

docs/generated/pipeline_api.json

@@ -8,7 +8,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "policyengine_us_data"
-version = "1.113.0"
+version = "1.113.1"
 description = "A package to create representative microdata for the US."
 readme = "README.md"
 authors = [