from typing import List, Dict, Any from collections import Counter from model_data.epc_attributes.FloorAttributes import FloorAttributes from model_data.epc_attributes.HotWaterAttributes import HotWaterAttributes from model_data.epc_attributes.MainFuelAttributes import MainFuelAttributes from model_data.epc_attributes.MainheatAttributes import MainHeatAttributes from model_data.epc_attributes.MainheatControlAttributes import MainheatControlAttributes from model_data.epc_attributes.RoofAttributes import RoofAttributes from model_data.epc_attributes.WallAttributes import WallAttributes from model_data.epc_attributes.WindowAttributes import WindowAttributes class EpcClean: """ Container for methods which we utilise for epc_attributes EPC data """ CLEANING_FIELDS: List[str] = [ "floor-description", "hotwater-description", "main-fuel", "mainheat-description", "mainheatcont-description", "roof-description", "walls-description", "windows-description", ] def __init__(self, data: List[Dict[str, Any]]) -> None: """ EpcClean constructor. :param data: List of dictionaries containing EPC data. """ self.data: List[Dict[str, Any]] = data self.unique_vals: Dict[str, Any] = {} self.cleaned: Dict[str, List[Any]] = {} def clean(self) -> None: """ Cleans the EPC data, mapping text fields to property epc_attributes. """ self._init_empty_cleaned_obj() for field in self.CLEANING_FIELDS: self.unique_vals[field] = Counter([v[field] for v in self.data]) self.clean_wrapper(field="floor-description", cleaning_cls=FloorAttributes) self.clean_wrapper(field="hotwater-description", cleaning_cls=HotWaterAttributes) self.clean_wrapper(field="main-fuel", cleaning_cls=MainFuelAttributes) self.clean_wrapper(field="mainheat-description", cleaning_cls=MainHeatAttributes) self.clean_wrapper(field="mainheatcont-description", cleaning_cls=MainheatControlAttributes) self.clean_wrapper(field="roof-description", cleaning_cls=RoofAttributes) self.clean_wrapper(field="walls-description", cleaning_cls=WallAttributes) self.clean_wrapper(field="windows-description", cleaning_cls=WindowAttributes) def _init_empty_cleaned_obj(self) -> None: """ Initializes an empty object for cleaned data. """ self.cleaned = {field: [] for field in self.CLEANING_FIELDS} def clean_wrapper(self, field, cleaning_cls): for description in self.unique_vals[field].keys(): self.cleaned[field].append( { "original_description": description, **cleaning_cls(description).process() } )