diff --git a/.idea/Model.iml b/.idea/Model.iml
index 0b8ab409..1e51ede4 100644
--- a/.idea/Model.iml
+++ b/.idea/Model.iml
@@ -7,7 +7,7 @@
-
+
diff --git a/.idea/misc.xml b/.idea/misc.xml
index fb10c6b0..50cad4ca 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -3,7 +3,7 @@
-
+
diff --git a/backend/engine/engine.py b/backend/engine/engine.py
index 98db7b88..76a906a9 100644
--- a/backend/engine/engine.py
+++ b/backend/engine/engine.py
@@ -864,6 +864,19 @@ async def model_engine(body: PlanTriggerRequest):
"epc_page_rrn": epc_page_source.get("rrn"),
})
+ # TODO - delete me (finding the entries in epc data that are not in epc record
+ example_property = input_properties[0]
+ example_epc_record = example_property.epc_record
+ example_epc_data = example_property.data
+
+ epc_record_dir = dir(example_epc_record)
+
+ missed_keys = []
+ for k in example_epc_data.keys():
+ k_replaced = k.replace("-", "_")
+ if k_replaced not in epc_record_dir:
+ missed_keys.append(k_replaced)
+
if not input_properties:
return Response(status_code=204)
diff --git a/etl/epc/Record.py b/etl/epc/Record.py
index e1853361..73f09bb9 100644
--- a/etl/epc/Record.py
+++ b/etl/epc/Record.py
@@ -1,3 +1,5 @@
+from typing import Optional, get_origin, get_args, Union
+from dataclasses import fields
from datetime import datetime
from dataclasses import dataclass
from etl.epc.ValidationConfiguration import (
@@ -24,8 +26,11 @@ from etl.epc.settings import (
)
from recommendations.recommendation_utils import estimate_number_of_floors
from utils.s3 import read_dataframe_from_s3_parquet
+from utils.logger import setup_logger
from etl.epc.settings import EARLIEST_EPC_DATE
+logger = setup_logger()
+
# TODO: Change these in the settings file
RDSAP_RESPONSE = RDSAP_RESPONSE.lower()
HEAT_DEMAND_RESPONSE = HEAT_DEMAND_RESPONSE.lower()
@@ -47,60 +52,179 @@ class EPCRecord:
Base class for a EPC record
"""
- uprn: int = None
- walls_description: str = None
- floor_description: str = None
- lighting_description: str = None
- roof_description: str = None
- mainheat_description: str = None
- hotwater_description: str = None
- main_fuel: str = None
- mechanical_ventilation: str = None
- secondheat_description: str = None
- windows_description: str = None
- glazed_type: str = None
- multi_glaze_proportion: float = None
- low_energy_lighting: float = None
- number_open_fireplaces: float = None
- mainheatcont_description: str = None
- solar_water_heating_flag: str = None
- photo_supply: float = None
- transaction_type: str = None
- energy_tariff: str = None
- extension_count: float = None
- total_floor_area: float = None
- floor_height: float = None
- hot_water_energy_eff: str = None
- floor_energy_eff: str = None
- windows_energy_eff: str = None
- walls_energy_eff: str = None
- sheating_energy_eff: str = None
- roof_energy_eff: str = None
- mainheat_energy_eff: str = None
- mainheatc_energy_eff: str = None
- lighting_energy_eff: str = None
- lighting_cost_current: float = None
- heating_cost_current: float = None
- hot_water_cost_current: float = None
- potential_energy_efficiency: float = None
- environment_impact_potential: float = None
- energy_consumption_potential: float = None
- co2_emissions_potential: float = None
- lodgement_date: str = None
- current_energy_efficiency: int = None
- energy_consumption_current: int = None
- co2_emissions_current: float = None
- number_habitable_rooms: float = None
- number_heated_rooms: float = None
- is_post_sap10: bool = None
+ # ------------------------------------------------------------------
+ # IDENTIFIERS / METADATA
+ # ------------------------------------------------------------------
- # u_values_walls = None
- # u_values_roof = None
- # u_values_floor = None
+ uprn: Optional[int] = None
+ lmk_key: Optional[str] = None
+ building_reference_number: Optional[str] = None
+ report_type: Optional[str] = None
+ transaction_type: Optional[str] = None
+ uprn_source: Optional[str] = None
+
+ lodgement_date: Optional[str] = None
+ lodgement_datetime: Optional[str] = None
+ inspection_date: Optional[str] = None
+
+ # ------------------------------------------------------------------
+ # ADDRESS / LOCATION DATA
+ # ------------------------------------------------------------------
+
+ address: Optional[str] = None
+ address1: Optional[str] = None
+ address2: Optional[str] = None
+ address3: Optional[str] = None
+
+ postcode: Optional[str] = None
+ posttown: Optional[str] = None
+ county: Optional[str] = None
+
+ local_authority: Optional[str] = None
+ local_authority_label: Optional[str] = None
+ constituency: Optional[str] = None
+ constituency_label: Optional[str] = None
+
+ # ------------------------------------------------------------------
+ # PROPERTY CHARACTERISTICS
+ # ------------------------------------------------------------------
+
+ property_type: Optional[str] = None
+ built_form: Optional[str] = None
+ tenure: Optional[str] = None
+ floor_level: Optional[str] = None
+ flat_top_storey: Optional[str] = None
+ flat_storey_count: Optional[int] = None
+
+ glazed_area: Optional[str] = None
+ heat_loss_corridor: Optional[str] = None
+ unheated_corridor_length: Optional[float] = None
+
+ mains_gas_flag: Optional[str] = None
+
+ # ------------------------------------------------------------------
+ # BUILDING FABRIC DESCRIPTIONS
+ # ------------------------------------------------------------------
+
+ walls_description: Optional[str] = None
+ floor_description: Optional[str] = None
+ roof_description: Optional[str] = None
+ windows_description: Optional[str] = None
+
+ walls_env_eff: Optional[str] = None
+ floor_env_eff: Optional[str] = None
+ roof_env_eff: Optional[str] = None
+ windows_env_eff: Optional[str] = None
+ mainheat_env_eff: Optional[str] = None
+ sheating_env_eff: Optional[str] = None
+ hot_water_env_eff: Optional[str] = None
+ mainheatc_env_eff: Optional[str] = None
+
+ walls_energy_eff: Optional[str] = None
+ floor_energy_eff: Optional[str] = None
+ roof_energy_eff: Optional[str] = None
+ windows_energy_eff: Optional[str] = None
+ hot_water_energy_eff: Optional[str] = None
+ sheating_energy_eff: Optional[str] = None
+ mainheat_energy_eff: Optional[str] = None
+ mainheatc_energy_eff: Optional[str] = None
+
+ # ------------------------------------------------------------------
+ # HEATING / HOT WATER / SYSTEMS
+ # ------------------------------------------------------------------
+
+ mainheat_description: Optional[str] = None
+ mainheatcont_description: Optional[str] = None
+ secondheat_description: Optional[str] = None
+ hotwater_description: Optional[str] = None
+ main_fuel: Optional[str] = None
+ main_heating_controls: Optional[str] = None
+
+ mechanical_ventilation: Optional[str] = None
+
+ solar_water_heating_flag: Optional[str] = None
+ wind_turbine_count: Optional[int] = None
+ photo_supply: Optional[float] = None
+
+ # ------------------------------------------------------------------
+ # LIGHTING
+ # ------------------------------------------------------------------
+
+ lighting_description: Optional[str] = None
+ lighting_env_eff: Optional[str] = None
+ lighting_energy_eff: Optional[str] = None
+
+ low_energy_lighting: Optional[float] = None
+ fixed_lighting_outlets_count: Optional[int] = None
+ low_energy_fixed_light_count: Optional[int] = None
+
+ # ------------------------------------------------------------------
+ # ENERGY RATINGS
+ # ------------------------------------------------------------------
+
+ current_energy_rating: Optional[str] = None
+ potential_energy_rating: Optional[str] = None
+
+ current_energy_efficiency: Optional[int] = None
+ potential_energy_efficiency: Optional[float] = None
+
+ # ------------------------------------------------------------------
+ # ENERGY / CARBON METRICS
+ # ------------------------------------------------------------------
+
+ energy_consumption_current: Optional[int] = None
+ energy_consumption_potential: Optional[float] = None
+
+ co2_emissions_current: Optional[float] = None
+ co2_emissions_potential: Optional[float] = None
+
+ co2_emiss_curr_per_floor_area: Optional[float] = None
+
+ environment_impact_current: Optional[int] = None
+ environment_impact_potential: Optional[float] = None
+
+ # ------------------------------------------------------------------
+ # COST METRICS
+ # ------------------------------------------------------------------
+
+ heating_cost_current: Optional[float] = None
+ lighting_cost_current: Optional[float] = None
+ hot_water_cost_current: Optional[float] = None
+
+ heating_cost_potential: Optional[float] = None
+ lighting_cost_potential: Optional[float] = None
+ hot_water_cost_potential: Optional[float] = None
+
+ energy_tariff: Optional[str] = None
+
+ # ------------------------------------------------------------------
+ # PROPERTY DIMENSIONS / COUNTS
+ # ------------------------------------------------------------------
+
+ total_floor_area: Optional[float] = None
+ floor_height: Optional[float] = None
+
+ number_habitable_rooms: Optional[float] = None
+ number_heated_rooms: Optional[float] = None
+ number_open_fireplaces: Optional[float] = None
+
+ extension_count: Optional[float] = None
+
+ # ------------------------------------------------------------------
+ # GLAZING
+ # ------------------------------------------------------------------
+
+ glazed_type: Optional[str] = None
+ multi_glaze_proportion: Optional[float] = None
+
+ # ------------------------------------------------------------------
+ # MODEL FLAGS
+ # ------------------------------------------------------------------
+
+ is_post_sap10: Optional[bool] = None
run_mode: str = "training"
- # TODO: Make this a class so thet api_records is structured
epc_records: dict = None
full_sap_epc: dict = None
old_data: list[dict] = None
@@ -146,20 +270,8 @@ class EPCRecord:
self._expand_prepared_epc_to_attributes()
self._identify_delta_between_prepared_and_original_records()
- # Process to create uvalues for the single epc record
- # self.df = self.epc_record_as_dataframe('prepared_epc')
- # self._feature_generation()
- # self._drop_features()
-
return
- # self._expand_description_to_features()
- # self._expand_description_to_uvalues()
- #
- # self._generate_uvalues()
- # self._validate_expanded_description()
- # self._validate_u_values()
-
def _drop_features(self):
"""
Drop features that are not needed for modelling
@@ -200,88 +312,59 @@ class EPCRecord:
self.prepared_epc = epc_data_processor.data.to_dict(orient="records")[0]
+ def _cast_value(self, value, type_hint):
+
+ origin = get_origin(type_hint)
+ args = get_args(type_hint)
+
+ if origin is Union:
+ type_hint = [a for a in args if a is not type(None)][0]
+
+ if type_hint is int:
+ return int(value)
+
+ if type_hint is float:
+ return float(value)
+
+ if type_hint is bool:
+ if isinstance(value, bool):
+ return value
+ return str(value).lower() in ["true", "1", "y", "yes"]
+
+ if type_hint is str:
+ return str(value)
+
+ return value
+
def _expand_prepared_epc_to_attributes(self):
"""
- This method will expand the prepared epc to attributes
+ Expand prepared_epc dictionary into dataclass attributes.
+ Assumes prepared_epc keys are snake_case.
"""
- # for key, value in self.prepared_epc.items():
- # setattr(self, key, value)
+ field_map = {f.name: f for f in fields(self)}
- self.uprn: int = int(self.prepared_epc["uprn"])
- self.walls_description: str = self.prepared_epc["walls_description"]
- self.floor_description: str = self.prepared_epc["floor_description"]
- self.lighting_description: str = self.prepared_epc["lighting_description"]
- self.roof_description: str = self.prepared_epc["roof_description"]
- self.mainheat_description: str = self.prepared_epc["mainheat_description"]
- self.hotwater_description: str = self.prepared_epc["hotwater_description"]
- self.main_fuel: str = self.prepared_epc["main_fuel"]
- self.mechanical_ventilation: str = self.prepared_epc["mechanical_ventilation"]
- self.secondheat_description: str = self.prepared_epc["secondheat_description"]
- self.windows_description: str = self.prepared_epc["windows_description"]
- self.glazed_type: str = self.prepared_epc["glazed_type"]
- self.multi_glaze_proportion: float = float(
- self.prepared_epc["multi_glaze_proportion"]
- )
- self.low_energy_lighting: float = float(
- self.prepared_epc["low_energy_lighting"]
- )
- self.number_open_fireplaces: float = float(
- self.prepared_epc["number_open_fireplaces"]
- )
- self.mainheatcont_description: str = self.prepared_epc[
- "mainheatcont_description"
- ]
- self.solar_water_heating_flag: str = self.prepared_epc[
- "solar_water_heating_flag"
- ]
- self.photo_supply: float = float(self.prepared_epc["photo_supply"])
- self.transaction_type: str = self.prepared_epc["transaction_type"]
- self.energy_tariff: str = self.prepared_epc["energy_tariff"]
- self.extension_count: float = float(self.prepared_epc["extension_count"])
- self.total_floor_area: float = float(self.prepared_epc["total_floor_area"])
- self.floor_height: float = float(self.prepared_epc["floor_height"])
- self.hot_water_energy_eff: str = self.prepared_epc["hot_water_energy_eff"]
- self.floor_energy_eff: str = self.prepared_epc["floor_energy_eff"]
- self.windows_energy_eff: str = self.prepared_epc["windows_energy_eff"]
- self.walls_energy_eff: str = self.prepared_epc["walls_energy_eff"]
- self.sheating_energy_eff: str = self.prepared_epc["sheating_energy_eff"]
- self.roof_energy_eff: str = self.prepared_epc["roof_energy_eff"]
- self.mainheat_energy_eff: str = self.prepared_epc["mainheat_energy_eff"]
- self.mainheatc_energy_eff: str = self.prepared_epc["mainheatc_energy_eff"]
- self.lighting_energy_eff: str = self.prepared_epc["lighting_energy_eff"]
- self.lighting_cost_current: float = self.prepared_epc["lighting_cost_current"]
- self.heating_cost_current: float = self.prepared_epc["heating_cost_current"]
- self.hot_water_cost_current: float = self.prepared_epc["hot_water_cost_current"]
- self.potential_energy_efficiency: float = float(
- self.prepared_epc["potential_energy_efficiency"]
- )
- self.environment_impact_potential: float = float(
- self.prepared_epc["environment_impact_potential"]
- )
- self.energy_consumption_potential: float = float(
- self.prepared_epc["energy_consumption_potential"]
- )
- self.co2_emissions_potential: float = float(
- self.prepared_epc["co2_emissions_potential"]
- )
- self.lodgement_date: str = self.prepared_epc["lodgement_date"]
- self.current_energy_efficiency: int = int(
- self.prepared_epc["current_energy_efficiency"]
- )
- self.energy_consumption_current: int = int(
- self.prepared_epc["energy_consumption_current"]
- )
- self.co2_emissions_current: float = float(
- self.prepared_epc["co2_emissions_current"]
- )
- self.number_habitable_rooms: float = float(
- self.prepared_epc["number_habitable_rooms"]
- )
- self.number_heated_rooms: float = float(
- self.prepared_epc["number_heated_rooms"]
- )
- self.is_post_sap10: bool = bool(self.prepared_epc["is_post_sap10"])
+ for key, value in self.prepared_epc.items():
+
+ # Enforce schema consistency
+ if "-" in key:
+ raise ValueError(f"Invalid EPC key format (expected snake_case): {key}")
+
+ if key not in field_map:
+ # Ignore keys that are not part of the dataclass schema
+ continue
+
+ if value in ("", None):
+ setattr(self, key, None)
+ continue
+
+ try:
+ cast_value = self._cast_value(value, field_map[key].type)
+ setattr(self, key, cast_value)
+
+ except Exception as e:
+ logger.error(f"Failed casting field '{key}' with value '{value}': {e}")
+ setattr(self, key, value)
def _identify_delta_between_prepared_and_original_records(self):
"""
diff --git a/etl/epc/tests/test_epcrecord.py b/etl/epc/tests/test_epcrecord.py
index feb39c8e..0d862acc 100644
--- a/etl/epc/tests/test_epcrecord.py
+++ b/etl/epc/tests/test_epcrecord.py
@@ -416,3 +416,162 @@ class TestEpcRecord:
)
assert prepared_epc.get("year_built") == 1900
+
+ def test_casting(self, cleaning_data):
+ # Tests expected type casting, against previously hard-coded expectations to ensure that the
+ # expected types are correct and that we don't accidentally change them in future
+
+ test_epc_records = {
+ 'original_epc': {
+ 'uprn': '100023417525', 'county': 'Greater London Authority', 'tenure': 'rental (social)',
+ 'address': '31 Mimosa House, Larch Crescent',
+ 'lmk-key': '201660309922019061719223615438661', 'address1': '31 Mimosa House',
+ 'address2': 'Larch Crescent', 'address3': '', 'postcode': 'UB4 9DH', 'posttown': 'HAYES',
+ 'main-fuel': 'mains gas (not community)', 'built-form': 'Mid-Terrace', 'floor-level': 2,
+ 'glazed-area': 'Normal', 'glazed-type': 'double glazing, unknown install date',
+ 'report-type': '100', 'uprn-source': 'Address Matched', 'constituency': 'E14000737',
+ 'floor-height': 2.39, 'photo-supply': None, 'roof-env-eff': 'Average',
+ 'energy-tariff': 'Single', 'floor-env-eff': 'N/A', 'property-type': 'Maisonette',
+ 'walls-env-eff': 'Average', 'lodgement-date': '2019-06-17', 'mains-gas-flag': True,
+ 'extension-count': 0, 'flat-top-storey': 'Y', 'inspection-date': '2019-06-17',
+ 'local-authority': 'E09000017', 'roof-energy-eff': 'Average', 'windows-env-eff': 'Average',
+ 'floor-energy-eff': 'NO DATA!', 'lighting-env-eff': 'Good', 'mainheat-env-eff': 'Good',
+ 'roof-description': 'Pitched, 100 mm loft insulation', 'sheating-env-eff': 'N/A',
+ 'total-floor-area': 67.0, 'transaction-type': 'rental (social)',
+ 'walls-energy-eff': 'Average', 'flat-storey-count': None,
+ 'floor-description': '(another dwelling below)', 'hot-water-env-eff': 'Good',
+ 'mainheatc-env-eff': 'Average', 'walls-description': 'Cavity wall, filled cavity',
+ 'constituency-label': 'Hayes and Harlington', 'heat-loss-corridor': 'no corridor',
+ 'lodgement-datetime': '2019-06-17 19:22:36', 'wind-turbine-count': 0,
+ 'windows-energy-eff': 'Average', 'lighting-energy-eff': 'Good',
+ 'low-energy-lighting': '67', 'mainheat-energy-eff': 'Good', 'number-heated-rooms': 3.0,
+ 'sheating-energy-eff': 'N/A', 'windows-description': 'Fully double glazed',
+ 'heating-cost-current': '310', 'hot-water-energy-eff': 'Good',
+ 'hotwater-description': 'From main system',
+ 'lighting-description': 'Low energy lighting in 67% of fixed outlets',
+ 'mainheat-description': 'Boiler and radiators, mains gas',
+ 'mainheatc-energy-eff': 'Average', 'co2-emissions-current': 2.1,
+ 'construction-age-band': 'England and Wales: 1950-1966', 'current-energy-rating': 'C',
+ 'lighting-cost-current': '70', 'local-authority-label': 'Hillingdon',
+ 'main-heating-controls': '2104', 'heating-cost-potential': '265',
+ 'hot-water-cost-current': '136', 'mechanical-ventilation': 'natural',
+ 'multi-glaze-proportion': '100', 'number-habitable-rooms': 3.0,
+ 'number-open-fireplaces': 0, 'secondheat-description': 'None',
+ 'co2-emissions-potential': 1.7, 'lighting-cost-potential': '53',
+ 'potential-energy-rating': 'C', 'hot-water-cost-potential': '106',
+ 'mainheatcont-description': 'Programmer and room thermostat',
+ 'solar-water-heating-flag': 'N', 'unheated-corridor-length': None,
+ 'building-reference-number': '6110075568', 'current-energy-efficiency': 73,
+ 'energy-consumption-current': 180.0, 'environment-impact-current': '72',
+ 'potential-energy-efficiency': 77, 'energy-consumption-potential': '141',
+ 'environment-impact-potential': '78', 'fixed-lighting-outlets-count': 9,
+ 'low-energy-fixed-light-count': '', 'co2-emiss-curr-per-floor-area': '32'
+ },
+ 'full_sap_epc': {},
+ 'old_data': [
+ {'uprn': '100023417525', 'county': 'Greater London Authority', 'tenure': 'rental (social)',
+ 'address': '31 Mimosa House, Larch Crescent', 'lmk-key': '201660300922008121514105815828768',
+ 'address1': '31 Mimosa House', 'address2': 'Larch Crescent', 'address3': '', 'postcode': 'UB4 9DH',
+ 'posttown': 'HAYES',
+ 'main-fuel': 'mains gas - this is for backwards compatibility only and should not be used',
+ 'built-form': 'Mid-Terrace', 'floor-level': '2nd', 'glazed-area': 'Normal',
+ 'glazed-type': 'double glazing, unknown install date', 'report-type': '100',
+ 'uprn-source': 'Address Matched', 'constituency': 'E14000737', 'floor-height': '2.36',
+ 'photo-supply': '0.0', 'roof-env-eff': 'Good', 'energy-tariff': 'Single', 'floor-env-eff': 'N/A',
+ 'property-type': 'Flat', 'walls-env-eff': 'Poor', 'lodgement-date': '2008-12-15',
+ 'mains-gas-flag': 'Y', 'extension-count': '0', 'flat-top-storey': 'Y', 'inspection-date': '2008-12-12',
+ 'local-authority': 'E09000017', 'roof-energy-eff': 'Good', 'windows-env-eff': 'Average',
+ 'floor-energy-eff': 'N/A', 'lighting-env-eff': 'Good', 'mainheat-env-eff': 'Good',
+ 'roof-description': 'Pitched, 150 mm loft insulation', 'sheating-env-eff': 'N/A',
+ 'total-floor-area': '69.8', 'transaction-type': 'rental (social)', 'walls-energy-eff': 'Poor',
+ 'flat-storey-count': '4.0', 'floor-description': '(other premises below)', 'hot-water-env-eff': 'Good',
+ 'mainheatc-env-eff': 'Poor', 'walls-description': 'Cavity wall, as built, no insulation (assumed)',
+ 'constituency-label': 'Hayes and Harlington', 'heat-loss-corridor': 'no corridor',
+ 'lodgement-datetime': '2008-12-15 14:10:58', 'wind-turbine-count': '0',
+ 'windows-energy-eff': 'Average', 'lighting-energy-eff': 'Good', 'low-energy-lighting': '56',
+ 'mainheat-energy-eff': 'Good', 'number-heated-rooms': '3', 'sheating-energy-eff': 'N/A',
+ 'windows-description': 'Fully double glazed', 'heating-cost-current': '315',
+ 'hot-water-energy-eff': 'Good', 'hotwater-description': 'From main system',
+ 'lighting-description': 'Low energy lighting in 56% of fixed outlets',
+ 'mainheat-description': 'Boiler and radiators, mains gas', 'mainheatc-energy-eff': 'Poor',
+ 'co2-emissions-current': '2.8', 'construction-age-band': 'England and Wales: 1967-1975',
+ 'current-energy-rating': 'C', 'lighting-cost-current': '46', 'local-authority-label': 'Hillingdon',
+ 'main-heating-controls': '2104', 'heating-cost-potential': '207', 'hot-water-cost-current': '119',
+ 'mechanical-ventilation': 'natural', 'multi-glaze-proportion': '100', 'number-habitable-rooms': '3',
+ 'number-open-fireplaces': '0', 'secondheat-description': 'None', 'co2-emissions-potential': '1.7',
+ 'lighting-cost-potential': '32', 'potential-energy-rating': 'B', 'hot-water-cost-potential': '96',
+ 'mainheatcont-description': 'Programmer and room thermostat', 'solar-water-heating-flag': 'N',
+ 'unheated-corridor-length': '', 'building-reference-number': '6110075568',
+ 'current-energy-efficiency': '71', 'energy-consumption-current': '239',
+ 'environment-impact-current': '67', 'potential-energy-efficiency': '82',
+ 'energy-consumption-potential': '148', 'environment-impact-potential': '80',
+ 'fixed-lighting-outlets-count': '', 'low-energy-fixed-light-count': '',
+ 'co2-emiss-curr-per-floor-area': '40'}
+ ]
+ }
+
+ record = EPCRecord(
+ epc_records=test_epc_records,
+ run_mode="newdata",
+ cleaning_data=cleaning_data
+ )
+
+ expected_types = {
+ "uprn": int,
+ "walls_description": str,
+ "floor_description": str,
+ "lighting_description": str,
+ "roof_description": str,
+ "mainheat_description": str,
+ "hotwater_description": str,
+ "main_fuel": str,
+ "mechanical_ventilation": str,
+ "secondheat_description": str,
+ "windows_description": str,
+ "glazed_type": str,
+ "multi_glaze_proportion": float,
+ "low_energy_lighting": float,
+ "number_open_fireplaces": float,
+ "mainheatcont_description": str,
+ "solar_water_heating_flag": str,
+ "photo_supply": float,
+ "transaction_type": str,
+ "energy_tariff": str,
+ "extension_count": float,
+ "total_floor_area": float,
+ "floor_height": float,
+ "hot_water_energy_eff": str,
+ "floor_energy_eff": None, # THe input is NO DATA so we map to None
+ "windows_energy_eff": str,
+ "walls_energy_eff": str,
+ "sheating_energy_eff": None,
+ "roof_energy_eff": str,
+ "mainheat_energy_eff": str,
+ "mainheatc_energy_eff": str,
+ "lighting_energy_eff": str,
+ "lighting_cost_current": float,
+ "heating_cost_current": float,
+ "hot_water_cost_current": float,
+ "potential_energy_efficiency": float,
+ "environment_impact_potential": float,
+ "energy_consumption_potential": float,
+ "co2_emissions_potential": float,
+ "lodgement_date": str,
+ "current_energy_efficiency": int,
+ "energy_consumption_current": int,
+ "co2_emissions_current": float,
+ "number_habitable_rooms": float,
+ "number_heated_rooms": float,
+ "is_post_sap10": bool,
+ }
+
+ for field, expected_type in expected_types.items():
+ value = getattr(record, field)
+
+ if expected_type is None:
+ assert value is None, f"{field} expected to be None, got {value}"
+ continue
+
+ assert isinstance(
+ value, expected_type
+ ), f"{field} expected {expected_type}, got {type(value)}"