Fix bug in loading multi-year datasets (#1257)

* Rename dataset

* Add multi-year dataset (working in sim load)

* Add core uprating functionality

* Adjust tests

* Add rent uprating

* Downgrade microdf

* 0.4.5

* 0.4.4?

* Add versioning

* UKMultiYearDataset fails when downloading from HuggingFace
Fixes #1256

* Update tests

Author: nikhilwoodruff

changelog_entry.yaml

@@ -0,0 +1,4 @@
+- bump: patch
+  changes:
+    fixed:
+    - Bug in handling downloads of UKMultiYearDataset from HuggingFace.

policyengine_uk/data/dataset_schema.py

@@ -213,12 +213,11 @@ def validate_file_path(file_path: str):
 
         # Check if the file contains datasets for multiple years
         with h5py.File(file_path, "r") as f:
-            if not any(key.startswith("/person/") for key in f.keys()):
-                raise ValueError("No person dataset found in the file.")
-            if not any(key.startswith("/benunit/") for key in f.keys()):
-                raise ValueError("No benunit dataset found in the file.")
-            if not any(key.startswith("/household/") for key in f.keys()):
-                raise ValueError("No household dataset found in the file.")
+            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}"
+                    )
 
     def load(self):
         data = {}

policyengine_uk/system.py

@@ -202,9 +202,13 @@ def __init__(self, *args, dataset=ENHANCED_FRS, **kwargs):
                             dataset = UKMultiYearDataset(
                                 file_path=dataset_file_path
                             )
-                        except:
+                        except Exception as e:
                             pass
-                        dataset = Dataset.from_file(dataset_file_path)
+
+                        if not isinstance(
+                            dataset, (UKSingleYearDataset, UKMultiYearDataset)
+                        ):
+                            dataset = Dataset.from_file(dataset_file_path)
 
         super().__init__(*args, dataset=dataset, **kwargs)
 

policyengine_uk/tests/microsimulation/reforms_config.yaml

@@ -1,10 +1,10 @@
 reforms:
 - name: Raise basic rate by 1pp
-  expected_impact: 7.6
+  expected_impact: 7.5
   parameters:
     gov.hmrc.income_tax.rates.uk[0].rate: 0.21
 - name: Raise higher rate by 1pp
-  expected_impact: 4.8
+  expected_impact: 4.7
   parameters:
     gov.hmrc.income_tax.rates.uk[1].rate: 0.42
 - name: Raise personal allowance by ~800GBP/year
@@ -16,18 +16,18 @@ reforms:
   parameters:
     gov.hmrc.child_benefit.amount.additional: 25
 - name: Reduce Universal Credit taper rate to 20%
-  expected_impact: -36.5
+  expected_impact: -36.4
   parameters:
     gov.dwp.universal_credit.means_test.reduction_rate: 0.2
 - name: Raise Class 1 main employee NICs rate to 10%
   expected_impact: 12.3
   parameters:
     gov.hmrc.national_insurance.class_1.rates.employee.main: 0.1
 - name: Raise VAT standard rate by 2pp
-  expected_impact: 18.8
+  expected_impact: 18.9
   parameters:
     gov.hmrc.vat.standard_rate: 0.22
 - name: Raise additional rate by 3pp
-  expected_impact: 5.5
+  expected_impact: 5.3
   parameters:
     gov.hmrc.income_tax.rates.uk[2].rate: 0.48