policyengine-uk 2.42.0__py3-none-any.whl → 2.43.1__py3-none-any.whl

policyengine_uk/data/dataset_schema.py

@@ -14,11 +14,17 @@ class UKSingleYearDataset:
     household: pd.DataFrame
 
     @staticmethod
-    def validate_file_path(file_path: str):
+    def validate_file_path(file_path: str, raise_exception: bool = True):
         if not file_path.endswith(".h5"):
-            raise ValueError("File path must end with '.h5' for UKDataset.")
+            if raise_exception:
+                raise ValueError(
+                    "File path must end with '.h5' for UKDataset."
+                )
+            return False
         if not Path(file_path).exists():
-            raise FileNotFoundError(f"File not found: {file_path}")
+            if raise_exception:
+                raise FileNotFoundError(f"File not found: {file_path}")
+            return False
 
         # Check if the file contains time_period, person, benunit, and household datasets
         with h5py.File(file_path, "r") as f:
@@ -30,9 +36,14 @@ class UKSingleYearDataset:
             ]
             for dataset in required_datasets:
                 if dataset not in f:
-                    raise ValueError(
-                        f"Dataset '{dataset}' not found in the file: {file_path}"
-                    )
+                    if raise_exception:
+                        raise ValueError(
+                            f"Dataset '{dataset}' not found in the file: {file_path}"
+                        )
+                    else:
+                        return False
+
+        return True
 
     def __init__(
         self,
@@ -137,7 +148,7 @@ class UKMultiYearDataset:
                 self.datasets[year] = dataset
 
         if file_path is not None:
-            UKSingleYearDataset.validate_file_path(file_path)
+            UKMultiYearDataset.validate_file_path(file_path)
             with pd.HDFStore(file_path) as f:
                 self.datasets = {}
                 for year in f.keys():
@@ -162,6 +173,10 @@ class UKMultiYearDataset:
         else:
             raise ValueError(f"No dataset found for year {fiscal_year}.")
 
+    @property
+    def years(self):
+        return list(self.datasets.keys())
+
     def __getitem__(self, fiscal_year: int):
         return self.get_year(fiscal_year)
 
@@ -203,21 +218,49 @@ class UKMultiYearDataset:
         return UKMultiYearDataset(datasets=list(new_datasets.values()))
 
     @staticmethod
-    def validate_file_path(file_path: str):
+    def validate_file_path(file_path: str, raise_exception: bool = False):
         if not file_path.endswith(".h5"):
-            raise ValueError(
-                "File path must end with '.h5' for UKMultiYearDataset."
-            )
+            if raise_exception:
+                raise ValueError(
+                    "File path must end with '.h5' for UKMultiYearDataset."
+                )
+            else:
+                return False
         if not Path(file_path).exists():
-            raise FileNotFoundError(f"File not found: {file_path}")
+            if raise_exception:
+                raise FileNotFoundError(f"File not found: {file_path}")
+            else:
+                return False
 
         # Check if the file contains datasets for multiple years
         with h5py.File(file_path, "r") as f:
             for required_dataset in ["person", "benunit", "household"]:
                 if not any(f"{required_dataset}" in key for key in f.keys()):
-                    raise ValueError(
-                        f"Dataset '{required_dataset}' not found in the file: {file_path}"
-                    )
+                    if raise_exception:
+                        raise ValueError(
+                            f"Dataset '{required_dataset}' not found in the file: {file_path}"
+                        )
+                    else:
+                        return False
+
+                # Check that there is at least one dataset year in the folder (keys include e.g. person/2025)
+
+                # Check that there is at least one dataset year in the folder
+                years_found = False
+                for key in f.keys():
+                    parts = key.split("/")
+                    if len(parts) >= 2 and required_dataset == parts[0]:
+                        years_found = True
+                        break
+
+                if not years_found:
+                    if raise_exception:
+                        raise ValueError(
+                            f"No yearly data found for '{required_dataset}' in file: {file_path}"
+                        )
+                    else:
+                        return False
+        return True
 
     def load(self):
         data = {}
@@ -228,3 +271,8 @@ class UKMultiYearDataset:
                         data[col] = {}
                     data[col][year] = df[col].values
         return data
+
+    def reset_uprating(self):
+        from policyengine_uk.data.economic_assumptions import reset_uprating
+
+        reset_uprating(self)

policyengine_uk/data/economic_assumptions.py

@@ -1,14 +1,31 @@
 from policyengine_uk.data import UKMultiYearDataset, UKSingleYearDataset
-from policyengine_uk.system import system
+
 import yaml
 from policyengine_core.parameters import ParameterNode
 from pathlib import Path
 import numpy as np
 
 
+def extend_single_year_dataset(
+    dataset: UKSingleYearDataset,
+    end_year: int = 2029,
+) -> UKMultiYearDataset:
+    # Extend years and uprate
+    start_year = int(dataset.time_period)
+    datasets = [dataset]
+    for year in range(start_year, end_year + 1):
+        next_year = dataset.copy()
+        next_year.time_period = str(year)
+        datasets.append(next_year)
+    multi_year_dataset = UKMultiYearDataset(datasets=datasets)
+    return apply_uprating(multi_year_dataset)
+
+
 def apply_uprating(
     dataset: UKMultiYearDataset,
 ):
+    from policyengine_uk.system import system
+
     # Apply uprating to the dataset.
     dataset = dataset.copy()
 

policyengine_uk/model_api.py

@@ -2,5 +2,6 @@ from policyengine_core.model_api import *
 from policyengine_uk.entities import *
 from policyengine_core import periods
 from microdf import MicroSeries, MicroDataFrame
+from policyengine_uk.utils.scenario import Scenario
 
 GBP = "currency-GBP"

policyengine_uk/parameters/gov/economic_assumptions/yoy_growth.yaml

@@ -108,12 +108,10 @@ obr:
       reference:
         - title: OBR EFO March 2025
           href: https://obr.uk/efo/economic-and-fiscal-outlook-march-2025/
-      reference:
         - title: ONS CPI weights
           href: https://www.ons.gov.uk/economy/inflationandpriceindices/datasets/consumerpriceinflationupdatingweightsannexatablesw1tow3
-      reference: 
         - title: ONS CPI series excluding housing costs
-        - href: https://www.ons.gov.uk/economy/inflationandpriceindices/adhocs/2863consumerpriceindicesseriesexcludingrentsmaintenancerepairsandwaterchargesfortheperiodjanuary1996toapril2025
+          href: https://www.ons.gov.uk/economy/inflationandpriceindices/adhocs/2863consumerpriceindicesseriesexcludingrentsmaintenancerepairsandwaterchargesfortheperiodjanuary1996toapril2025
 
   non_labour_income:
     description: Non-labour income year-on-year growth.

policyengine_uk/scenarios/__init__.py

@@ -0,0 +1,3 @@
+from .pip_reform import reform_pip_phase_in
+from .reindex_benefit_cap import reindex_benefit_cap
+from .repeal_two_child_limit import repeal_two_child_limit

policyengine_uk/scenarios/pip_reform.py

@@ -0,0 +1,23 @@
+from policyengine_uk.model_api import Scenario
+from policyengine_uk import Simulation
+import numpy as np
+
+
+def modify_simulation(sim: Simulation):
+    np.random.seed(42)  # For reproducibility
+    pip_seed = np.random.random(len(sim.calculate("person_id")))
+
+    start_year = 2025
+    end_year = 2029
+
+    for year in range(start_year, end_year + 1):
+        current_pip = sim.calculate("pip", year)
+        percent_along_phase_in = (year - start_year) / (end_year - start_year)
+        current_pip[pip_seed < 0.25 * percent_along_phase_in] = 0
+        sim.set_input("pip", year, current_pip)
+    return sim
+
+
+reform_pip_phase_in = Scenario(
+    simulation_modifier=modify_simulation,
+)

policyengine_uk/scenarios/reindex_benefit_cap.py

@@ -0,0 +1,32 @@
+from policyengine_uk.model_api import Scenario
+from policyengine_uk import Simulation
+from policyengine_core.parameters import Parameter
+
+
+def index_benefit_cap(simulation: Simulation):
+    # Identify benefit cap parameters
+    simulation.tax_benefit_system.reset_parameters()
+
+    params = (
+        simulation.tax_benefit_system.parameters.gov.dwp.benefit_cap.get_descendants()
+    )
+    # We just want the leaf nodes of the parameter tree
+    # TODO: add a get-descendants-leaf-nodes-only function
+
+    params = [param for param in params if isinstance(param, Parameter)]
+
+    for parameter in params:
+        parameter: Parameter  # Type annotation
+        # Delete all values after 2025
+        parameter.values_list = [
+            entry
+            for entry in parameter.values_list
+            if entry.instant_str < "2026-01-01"
+        ]
+        parameter.metadata.update(
+            uprating="gov.benefit_uprating_cpi",
+        )
+    simulation.tax_benefit_system.process_parameters()
+
+
+reindex_benefit_cap = Scenario(simulation_modifier=index_benefit_cap)

policyengine_uk/scenarios/repeal_two_child_limit.py

@@ -0,0 +1,10 @@
+from policyengine_uk.model_api import Scenario
+import numpy as np
+
+repeal_two_child_limit = Scenario(
+    parameter_changes={
+        "gov.dwp.universal_credit.elements.child.limit.child_count": {
+            "year:2026:10": np.inf
+        }
+    }
+)