policyengine 3.1.3__tar.gz → 3.1.5__tar.gz

{policyengine-3.1.3 → policyengine-3.1.5}/CHANGELOG.md

@@ -5,6 +5,18 @@ 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).
 
+## [3.1.5] - 2025-11-21 12:59:36
+
+### Fixed
+
+- Minor fixes
+
+## [3.1.4] - 2025-11-20 14:06:49
+
+### Fixed
+
+- Minor fixes
+
 ## [3.1.3] - 2025-11-18 13:46:23
 
 ### Fixed
@@ -215,6 +227,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 
 
+[3.1.5]: https://github.com/PolicyEngine/policyengine.py/compare/3.1.4...3.1.5
+[3.1.4]: https://github.com/PolicyEngine/policyengine.py/compare/3.1.3...3.1.4
 [3.1.3]: https://github.com/PolicyEngine/policyengine.py/compare/3.1.2...3.1.3
 [3.1.2]: https://github.com/PolicyEngine/policyengine.py/compare/3.1.1...3.1.2
 [3.1.1]: https://github.com/PolicyEngine/policyengine.py/compare/3.1.0...3.1.1

{policyengine-3.1.3 → policyengine-3.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: policyengine
-Version: 3.1.3
+Version: 3.1.5
 Summary: A package to conduct policy analysis using PolicyEngine tax-benefit models.
 Author-email: PolicyEngine <hello@policyengine.org>
 License:                     GNU AFFERO GENERAL PUBLIC LICENSE

{policyengine-3.1.3 → policyengine-3.1.5}/changelog.yaml

@@ -175,3 +175,13 @@
     fixed:
     - Entity variables moved out to an editable constant.
   date: 2025-11-18 13:46:23
+- bump: patch
+  changes:
+    fixed:
+    - Minor fixes
+  date: 2025-11-20 14:06:49
+- bump: patch
+  changes:
+    fixed:
+    - Minor fixes
+  date: 2025-11-21 12:59:36

{policyengine-3.1.3 → policyengine-3.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "policyengine"
-version = "3.1.3"
+version = "3.1.5"
 description = "A package to conduct policy analysis using PolicyEngine tax-benefit models."
 readme = "README.md"
 authors = [

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/core/dataset.py

@@ -1,5 +1,6 @@
 from uuid import uuid4
 
+import numpy as np
 import pandas as pd
 from microdf import MicroDataFrame
 from pydantic import BaseModel, ConfigDict, Field
@@ -100,7 +101,7 @@ def map_to_entity(
     target_entity: str,
     person_entity: str = "person",
     columns: list[str] | None = None,
-    values: list | None = None,
+    values: np.ndarray | None = None,
     how: str = "sum",
 ) -> MicroDataFrame:
     """Map data from source entity to target entity using join keys.
@@ -143,6 +144,9 @@ def map_to_entity(
     # Get source data (convert to plain DataFrame to avoid weighted operations during mapping)
     source_df = pd.DataFrame(entity_data[source_entity])
 
+    # Track if we should return a MicroSeries (values is a numpy array, not a list)
+    return_series = values is not None
+
     # Handle values parameter - create a temporary column with the provided values
     if values is not None:
         if len(values) != len(source_df):
@@ -166,7 +170,10 @@ def map_to_entity(
 
     # Same entity - return as is
     if source_entity == target_entity:
-        return MicroDataFrame(source_df, weights=target_weight)
+        result = MicroDataFrame(source_df, weights=target_weight)
+        if return_series:
+            return result["__mapped_value"]
+        return result
 
     # Get target data and key
     target_df = entity_data[target_entity]
@@ -225,7 +232,10 @@ def map_to_entity(
             # Fill NaN with 0 for groups with no members in source entity
             result[agg_cols] = result[agg_cols].fillna(0)
 
-            return MicroDataFrame(result, weights=target_weight)
+            result_df = MicroDataFrame(result, weights=target_weight)
+            if return_series:
+                return result_df["__mapped_value"]
+            return result_df
 
     # Group entity to person: expand group-level data to person level
     if source_entity != person_entity and target_entity == person_entity:
@@ -284,7 +294,10 @@ def map_to_entity(
                     f"Unsupported aggregation method for group->person: {how}. Use 'project' or 'divide'."
                 )
 
-            return MicroDataFrame(result, weights=target_weight)
+            result_df = MicroDataFrame(result, weights=target_weight)
+            if return_series:
+                return result_df["__mapped_value"]
+            return result_df
 
     # Group to group: go through person table
     if source_entity != person_entity and target_entity != person_entity:
@@ -408,7 +421,10 @@ def map_to_entity(
             # Fill NaN with 0
             result[agg_cols] = result[agg_cols].fillna(0)
 
-            return MicroDataFrame(result, weights=target_weight)
+            result_df = MicroDataFrame(result, weights=target_weight)
+            if return_series:
+                return result_df["__mapped_value"]
+            return result_df
 
     raise ValueError(
         f"Unsupported mapping from {source_entity} to {target_entity}"

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/core/simulation.py

@@ -24,6 +24,13 @@ class Simulation(BaseModel):
     def run(self):
         self.tax_benefit_model_version.run(self)
 
+    def ensure(self):
+        try:
+            self.tax_benefit_model_version.load(self)
+        except Exception:
+            self.run()
+            self.save()
+
     def save(self):
         """Save the simulation's output dataset."""
         self.tax_benefit_model_version.save(self)

policyengine-3.1.5/src/policyengine/tax_benefit_models/uk/__init__.py

@@ -0,0 +1,44 @@
+"""PolicyEngine UK tax-benefit model."""
+
+from importlib.util import find_spec
+
+if find_spec("policyengine_uk") is not None:
+    from policyengine.core import Dataset
+
+    from .analysis import general_policy_reform_analysis
+    from .datasets import (
+        PolicyEngineUKDataset,
+        UKYearData,
+        create_datasets,
+        ensure_datasets,
+        load_datasets,
+    )
+    from .model import (
+        PolicyEngineUK,
+        PolicyEngineUKLatest,
+        uk_latest,
+        uk_model,
+    )
+    from .outputs import ProgrammeStatistics
+
+    # Rebuild Pydantic models to resolve forward references
+    Dataset.model_rebuild()
+    UKYearData.model_rebuild()
+    PolicyEngineUKDataset.model_rebuild()
+    PolicyEngineUKLatest.model_rebuild()
+
+    __all__ = [
+        "UKYearData",
+        "PolicyEngineUKDataset",
+        "create_datasets",
+        "load_datasets",
+        "ensure_datasets",
+        "PolicyEngineUK",
+        "PolicyEngineUKLatest",
+        "uk_model",
+        "uk_latest",
+        "general_policy_reform_analysis",
+        "ProgrammeStatistics",
+    ]
+else:
+    __all__ = []

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/tax_benefit_models/uk/datasets.py

@@ -37,11 +37,7 @@ class PolicyEngineUKDataset(Dataset):
         if self.data is not None:
             self.save()
         elif self.filepath and not self.data:
-            try:
-                self.load()
-            except FileNotFoundError:
-                # File doesn't exist yet, that's OK
-                pass
+            self.load()
 
     def save(self) -> None:
         """Save dataset to HDF5 file."""
@@ -85,7 +81,9 @@ def create_datasets(
         "hf://policyengine/policyengine-uk-data/enhanced_frs_2023_24.h5",
     ],
     years: list[int] = [2026, 2027, 2028, 2029, 2030],
-) -> None:
+    data_folder: str = "./data",
+) -> dict[str, PolicyEngineUKDataset]:
+    result = {}
     for dataset in datasets:
         from policyengine_uk import Microsimulation
 
@@ -139,9 +137,10 @@ def create_datasets(
             )
 
             uk_dataset = PolicyEngineUKDataset(
+                id=f"{Path(dataset).stem}_year_{year}",
                 name=f"{dataset}-year-{year}",
                 description=f"UK Dataset for year {year} based on {dataset}",
-                filepath=f"./data/{Path(dataset).stem}_year_{year}.h5",
+                filepath=f"{data_folder}/{Path(dataset).stem}_year_{year}.h5",
                 year=year,
                 data=UKYearData(
                     person=MicroDataFrame(person_df, weights="person_weight"),
@@ -154,3 +153,75 @@ def create_datasets(
                 ),
             )
             uk_dataset.save()
+
+            dataset_key = f"{Path(dataset).stem}_{year}"
+            result[dataset_key] = uk_dataset
+
+    return result
+
+
+def load_datasets(
+    datasets: list[str] = [
+        "hf://policyengine/policyengine-uk-data/frs_2023_24.h5",
+        "hf://policyengine/policyengine-uk-data/enhanced_frs_2023_24.h5",
+    ],
+    years: list[int] = [2026, 2027, 2028, 2029, 2030],
+    data_folder: str = "./data",
+) -> dict[str, PolicyEngineUKDataset]:
+    result = {}
+    for dataset in datasets:
+        for year in years:
+            filepath = f"{data_folder}/{Path(dataset).stem}_year_{year}.h5"
+            uk_dataset = PolicyEngineUKDataset(
+                name=f"{dataset}-year-{year}",
+                description=f"UK Dataset for year {year} based on {dataset}",
+                filepath=filepath,
+                year=year,
+            )
+            uk_dataset.load()
+
+            dataset_key = f"{Path(dataset).stem}_{year}"
+            result[dataset_key] = uk_dataset
+
+    return result
+
+
+def ensure_datasets(
+    datasets: list[str] = [
+        "hf://policyengine/policyengine-uk-data/frs_2023_24.h5",
+        "hf://policyengine/policyengine-uk-data/enhanced_frs_2023_24.h5",
+    ],
+    years: list[int] = [2026, 2027, 2028, 2029, 2030],
+    data_folder: str = "./data",
+) -> dict[str, PolicyEngineUKDataset]:
+    """Ensure datasets exist, loading if available or creating if not.
+
+    Args:
+        datasets: List of HuggingFace dataset paths
+        years: List of years to load/create data for
+        data_folder: Directory containing or to save the dataset files
+
+    Returns:
+        Dictionary mapping dataset keys to PolicyEngineUKDataset objects
+    """
+    # Check if all dataset files exist
+    all_exist = True
+    for dataset in datasets:
+        for year in years:
+            filepath = Path(
+                f"{data_folder}/{Path(dataset).stem}_year_{year}.h5"
+            )
+            if not filepath.exists():
+                all_exist = False
+                break
+        if not all_exist:
+            break
+
+    if all_exist:
+        return load_datasets(
+            datasets=datasets, years=years, data_folder=data_folder
+        )
+    else:
+        return create_datasets(
+            datasets=datasets, years=years, data_folder=data_folder
+        )

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/tax_benefit_models/uk/model.py

@@ -265,17 +265,29 @@ class PolicyEngineUKLatest(TaxBenefitModelVersion):
 
     def load(self, simulation: "Simulation"):
         """Load the simulation's output dataset."""
+        import os
+
+        filepath = str(
+            Path(simulation.dataset.filepath).parent / (simulation.id + ".h5")
+        )
+
         simulation.output_dataset = PolicyEngineUKDataset(
             id=simulation.id,
             name=simulation.dataset.name,
             description=simulation.dataset.description,
-            filepath=str(
-                Path(simulation.dataset.filepath).parent
-                / (simulation.id + ".h5")
-            ),
+            filepath=filepath,
             year=simulation.dataset.year,
             is_output_dataset=True,
         )
 
+        # Load timestamps from file system metadata
+        if os.path.exists(filepath):
+            simulation.created_at = datetime.datetime.fromtimestamp(
+                os.path.getctime(filepath)
+            )
+            simulation.updated_at = datetime.datetime.fromtimestamp(
+                os.path.getmtime(filepath)
+            )
+
 
 uk_latest = PolicyEngineUKLatest()

policyengine-3.1.5/src/policyengine/tax_benefit_models/uk.py

@@ -0,0 +1,38 @@
+"""PolicyEngine UK tax-benefit model - imports from uk/ module."""
+
+from importlib.util import find_spec
+
+if find_spec("policyengine_uk") is not None:
+    from .uk import (
+        PolicyEngineUK,
+        PolicyEngineUKDataset,
+        PolicyEngineUKLatest,
+        ProgrammeStatistics,
+        UKYearData,
+        create_datasets,
+        ensure_datasets,
+        general_policy_reform_analysis,
+        load_datasets,
+        uk_latest,
+        uk_model,
+    )
+
+    __all__ = [
+        "UKYearData",
+        "PolicyEngineUKDataset",
+        "create_datasets",
+        "load_datasets",
+        "ensure_datasets",
+        "PolicyEngineUK",
+        "PolicyEngineUKLatest",
+        "uk_model",
+        "uk_latest",
+        "general_policy_reform_analysis",
+        "ProgrammeStatistics",
+    ]
+
+    # Rebuild models to resolve forward references
+    PolicyEngineUKDataset.model_rebuild()
+    PolicyEngineUKLatest.model_rebuild()
+else:
+    __all__ = []

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/tax_benefit_models/us/__init__.py

@@ -6,7 +6,13 @@ if find_spec("policyengine_us") is not None:
     from policyengine.core import Dataset
 
     from .analysis import general_policy_reform_analysis
-    from .datasets import PolicyEngineUSDataset, USYearData, create_datasets
+    from .datasets import (
+        PolicyEngineUSDataset,
+        USYearData,
+        create_datasets,
+        ensure_datasets,
+        load_datasets,
+    )
     from .model import (
         PolicyEngineUS,
         PolicyEngineUSLatest,
@@ -25,6 +31,8 @@ if find_spec("policyengine_us") is not None:
         "USYearData",
         "PolicyEngineUSDataset",
         "create_datasets",
+        "load_datasets",
+        "ensure_datasets",
         "PolicyEngineUS",
         "PolicyEngineUSLatest",
         "us_model",

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/tax_benefit_models/us/datasets.py

@@ -44,11 +44,7 @@ class PolicyEngineUSDataset(Dataset):
         if self.data is not None:
             self.save()
         elif self.filepath and not self.data:
-            try:
-                self.load()
-            except FileNotFoundError:
-                # File doesn't exist yet, that's OK
-                pass
+            self.load()
 
     def save(self) -> None:
         """Save dataset to HDF5 file."""
@@ -112,15 +108,21 @@ def create_datasets(
         "hf://policyengine/policyengine-us-data/enhanced_cps_2024.h5",
     ],
     years: list[int] = [2024, 2025, 2026, 2027, 2028],
-) -> None:
+    data_folder: str = "./data",
+) -> dict[str, PolicyEngineUSDataset]:
     """Create PolicyEngineUSDataset instances from HuggingFace dataset paths.
 
     Args:
         datasets: List of HuggingFace dataset paths (e.g., "hf://policyengine/policyengine-us-data/cps_2024.h5")
         years: List of years to extract data for
+        data_folder: Directory to save the dataset files
+
+    Returns:
+        Dictionary mapping dataset keys (e.g., "enhanced_cps_2024") to PolicyEngineUSDataset objects
     """
     from policyengine_us import Microsimulation
 
+    result = {}
     for dataset in datasets:
         sim = Microsimulation(dataset=dataset)
 
@@ -263,9 +265,10 @@ def create_datasets(
                         tax_unit_df = entity_df
 
             us_dataset = PolicyEngineUSDataset(
+                id=f"{Path(dataset).stem}_year_{year}",
                 name=f"{dataset}-year-{year}",
                 description=f"US Dataset for year {year} based on {dataset}",
-                filepath=f"./data/{Path(dataset).stem}_year_{year}.h5",
+                filepath=f"{data_folder}/{Path(dataset).stem}_year_{year}.h5",
                 year=year,
                 data=USYearData(
                     person=MicroDataFrame(person_df, weights="person_weight"),
@@ -285,3 +288,83 @@ def create_datasets(
                 ),
             )
             us_dataset.save()
+
+            dataset_key = f"{Path(dataset).stem}_{year}"
+            result[dataset_key] = us_dataset
+
+    return result
+
+
+def load_datasets(
+    datasets: list[str] = [
+        "hf://policyengine/policyengine-us-data/enhanced_cps_2024.h5",
+    ],
+    years: list[int] = [2024, 2025, 2026, 2027, 2028],
+    data_folder: str = "./data",
+) -> dict[str, PolicyEngineUSDataset]:
+    """Load PolicyEngineUSDataset instances from saved HDF5 files.
+
+    Args:
+        datasets: List of HuggingFace dataset paths (used to derive file names)
+        years: List of years to load data for
+        data_folder: Directory containing the dataset files
+
+    Returns:
+        Dictionary mapping dataset keys (e.g., "enhanced_cps_2024") to PolicyEngineUSDataset objects
+    """
+    result = {}
+    for dataset in datasets:
+        for year in years:
+            filepath = f"{data_folder}/{Path(dataset).stem}_year_{year}.h5"
+            us_dataset = PolicyEngineUSDataset(
+                name=f"{dataset}-year-{year}",
+                description=f"US Dataset for year {year} based on {dataset}",
+                filepath=filepath,
+                year=year,
+            )
+            us_dataset.load()
+
+            dataset_key = f"{Path(dataset).stem}_{year}"
+            result[dataset_key] = us_dataset
+
+    return result
+
+
+def ensure_datasets(
+    datasets: list[str] = [
+        "hf://policyengine/policyengine-us-data/enhanced_cps_2024.h5",
+    ],
+    years: list[int] = [2024, 2025, 2026, 2027, 2028],
+    data_folder: str = "./data",
+) -> dict[str, PolicyEngineUSDataset]:
+    """Ensure datasets exist, loading if available or creating if not.
+
+    Args:
+        datasets: List of HuggingFace dataset paths
+        years: List of years to load/create data for
+        data_folder: Directory containing or to save the dataset files
+
+    Returns:
+        Dictionary mapping dataset keys to PolicyEngineUSDataset objects
+    """
+    # Check if all dataset files exist
+    all_exist = True
+    for dataset in datasets:
+        for year in years:
+            filepath = Path(
+                f"{data_folder}/{Path(dataset).stem}_year_{year}.h5"
+            )
+            if not filepath.exists():
+                all_exist = False
+                break
+        if not all_exist:
+            break
+
+    if all_exist:
+        return load_datasets(
+            datasets=datasets, years=years, data_folder=data_folder
+        )
+    else:
+        return create_datasets(
+            datasets=datasets, years=years, data_folder=data_folder
+        )

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/tax_benefit_models/us/model.py

@@ -311,18 +311,30 @@ class PolicyEngineUSLatest(TaxBenefitModelVersion):
 
     def load(self, simulation: "Simulation"):
         """Load the simulation's output dataset."""
+        import os
+
+        filepath = str(
+            Path(simulation.dataset.filepath).parent / (simulation.id + ".h5")
+        )
+
         simulation.output_dataset = PolicyEngineUSDataset(
             id=simulation.id,
             name=simulation.dataset.name,
             description=simulation.dataset.description,
-            filepath=str(
-                Path(simulation.dataset.filepath).parent
-                / (simulation.id + ".h5")
-            ),
+            filepath=filepath,
             year=simulation.dataset.year,
             is_output_dataset=True,
         )
 
+        # Load timestamps from file system metadata
+        if os.path.exists(filepath):
+            simulation.created_at = datetime.datetime.fromtimestamp(
+                os.path.getctime(filepath)
+            )
+            simulation.updated_at = datetime.datetime.fromtimestamp(
+                os.path.getmtime(filepath)
+            )
+
     def _build_simulation_from_dataset(self, microsim, dataset, system):
         """Build a PolicyEngine Core simulation from dataset entity IDs.
 

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine/tax_benefit_models/us.py

@@ -9,7 +9,10 @@ if find_spec("policyengine_us") is not None:
         PolicyEngineUSLatest,
         ProgramStatistics,
         USYearData,
+        create_datasets,
+        ensure_datasets,
         general_policy_reform_analysis,
+        load_datasets,
         us_latest,
         us_model,
     )
@@ -17,6 +20,9 @@ if find_spec("policyengine_us") is not None:
     __all__ = [
         "USYearData",
         "PolicyEngineUSDataset",
+        "create_datasets",
+        "load_datasets",
+        "ensure_datasets",
         "PolicyEngineUS",
         "PolicyEngineUSLatest",
         "us_model",

{policyengine-3.1.3 → policyengine-3.1.5}/src/policyengine.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: policyengine
-Version: 3.1.3
+Version: 3.1.5
 Summary: A package to conduct policy analysis using PolicyEngine tax-benefit models.
 Author-email: PolicyEngine <hello@policyengine.org>
 License:                     GNU AFFERO GENERAL PUBLIC LICENSE

policyengine-3.1.3/src/policyengine/tax_benefit_models/uk/__init__.py

@@ -1,26 +0,0 @@
-"""PolicyEngine UK tax-benefit model."""
-
-from .analysis import general_policy_reform_analysis
-from .datasets import PolicyEngineUKDataset, UKYearData, create_datasets
-from .model import PolicyEngineUK, PolicyEngineUKLatest, uk_latest, uk_model
-from .outputs import ProgrammeStatistics
-
-__all__ = [
-    "UKYearData",
-    "PolicyEngineUKDataset",
-    "create_datasets",
-    "PolicyEngineUK",
-    "PolicyEngineUKLatest",
-    "uk_model",
-    "uk_latest",
-    "general_policy_reform_analysis",
-    "ProgrammeStatistics",
-]
-
-# Rebuild models to resolve forward references
-from policyengine.core import Dataset
-
-Dataset.model_rebuild()
-UKYearData.model_rebuild()
-PolicyEngineUKDataset.model_rebuild()
-PolicyEngineUKLatest.model_rebuild()

policyengine-3.1.3/src/policyengine/tax_benefit_models/uk.py

@@ -1,33 +0,0 @@
-"""PolicyEngine UK tax-benefit model - imports from uk/ module."""
-
-from .uk import (
-    PolicyEngineUK,
-    PolicyEngineUKDataset,
-    PolicyEngineUKLatest,
-    ProgrammeStatistics,
-    UKYearData,
-    create_datasets,
-    general_policy_reform_analysis,
-    uk_latest,
-    uk_model,
-)
-
-__all__ = [
-    "UKYearData",
-    "PolicyEngineUKDataset",
-    "create_datasets",
-    "PolicyEngineUK",
-    "PolicyEngineUKLatest",
-    "uk_model",
-    "uk_latest",
-    "general_policy_reform_analysis",
-    "ProgrammeStatistics",
-]
-
-# Rebuild models to resolve forward references
-from policyengine.core import Dataset
-
-Dataset.model_rebuild()
-UKYearData.model_rebuild()
-PolicyEngineUKDataset.model_rebuild()
-PolicyEngineUKLatest.model_rebuild()