Merge pull request #114 from Hestia-Homes/main

Implementing database pushes into the lambda - still recommendations to complete

backend/Property.py

@@ -26,6 +26,7 @@ class Property(BaseUtility):
     roof = None
     walls = None
     windows = None
+    lighting = None
 
     coordinates = None
 
@@ -37,6 +38,19 @@ class Property(BaseUtility):
         self.full_sap_epc = None
         self.in_conservation_area = None
         self.year_built = None
+        self.number_of_rooms = None
+
+        self.energy = None
+        self.ventilation = None
+        self.solar_pv = None
+        self.solar_hot_water = None
+        self.wind_turbine = None
+        self.number_of_open_fireplaces = None
+        self.number_of_extensions = None
+        self.number_of_storeys = None
+        self.heat_loss_corridor = None
+        self.mains_gas = None
+        self.floor_height = None
 
         if epc_client:
             self.epc_client = epc_client
@@ -76,6 +90,134 @@ class Property(BaseUtility):
         """
         self.coordinates = {key.lower(): value for key, value in coordinates.items()}
 
+    def set_energy(self):
+        """
+        Extracts and formats data about the home's energy and co2 consumption
+        To being with, this is just formatting epc data
+
+        Data:
+        - primary_energy_consumption
+        This is based on the "energy-consumption-current" field in the EPC data.
+        Current estimated total energy consumption for the property in a 12 month period (kWh/m2). Displayed on EPC
+        as the current primary energy use per square metre of floor area.
+
+        - co2_emissions
+        This is based on the "co2-emissions-current" field in the EPC data.
+        CO₂ emissions per year in tonnes/year.
+        """
+
+        self.energy = {
+            "primary_energy_consumption": float(self.data["energy-consumption-current"]),
+            "co2_emissions": float(self.data["co2-emissions-current"]),
+        }
+
+    def set_ventilation(self):
+        """
+        Extracts and formats data about the home's ventilation
+        To being with, this is just formatting epc data
+
+        Data:
+        - ventilation
+        This is based on the "ventilation-type" field in the EPC data.
+        Ventilation type of the property.
+        """
+
+        ventilation = self.data["mechanical-ventilation"]
+        # perform some simple cleaning - when checking 300k properties, the only unique values were
+        # {'', 'mechanical, supply and extract', 'NO DATA!', 'natural', 'mechanical, extract only'}
+        if ventilation in self.DATA_ANOMALY_MATCHES or ventilation in [""]:
+            ventilation = None
+
+        self.ventilation = {
+            "ventilation": ventilation,
+        }
+
+    def set_solar_pv(self):
+        """
+        Extracts and formats data about the home's solar pv
+        To being with, this is just formatting epc data
+
+        Data:
+        - solar_pv
+        This is based on the "photo-supply" field in the EPC data.
+
+        When checking 100k properties, either the value was "" or a stringified number
+        """
+
+        solar_pv = self.data["photo-supply"]
+        if solar_pv == "":
+            solar_pv = None
+        else:
+            solar_pv = float(solar_pv)
+
+        self.solar_pv = {
+            "solar_pv": solar_pv,
+        }
+
+    def set_solar_hot_water(self):
+        """
+        Extracts and formats data about the home's solar hot water
+        We are just formatting the solar-water-heating-flag in the epc data
+        :return:
+        """
+
+        value_map = {
+            "Y": True,
+            "N": False,
+            "": None,
+        }
+
+        self.solar_hot_water = {
+            "solar_hot_water": value_map[self.data["solar-water-heating-flag"]],
+        }
+
+    def set_wind_turbine(self):
+        """
+        Extracts and formats data about the home's wind turbine
+        We are just formatting the wind-turbine-flag in the epc data
+        :return:
+        """
+
+        wind_turbine_count = self.data["wind-turbine-count"]
+        if wind_turbine_count == "":
+            wind_turbine_count = None
+        else:
+            wind_turbine_count = int(wind_turbine_count)
+
+        self.wind_turbine = {
+            "wind_turbine": wind_turbine_count,
+        }
+
+    def set_count_variables(self):
+
+        """
+        For EPC fields that are just counts, we'll set them here
+        These are fields that are integers but may contain additional values such as "" so we can't do a direct
+        conversion straight to an integer
+        :return:
+        """
+
+        fields = {
+            "number_of_open_fireplaces": "number-open-fireplaces",
+            "number_of_extensions": "extension-count",
+            "number_of_storeys": "flat-storey-count",
+            "number_of_rooms": "number-habitable-rooms",
+        }
+
+        null_attributes = ["number_of_storeys", "number_of_rooms"]
+
+        for attribute, epc_field in fields.items():
+            value = self.data["extension-count"]
+            if value == "" or value in self.DATA_ANOMALY_MATCHES:
+                if attribute in null_attributes:
+                    value = None
+                else:
+                    value = 0
+            else:
+                value = int(value)
+
+            setattr(self, attribute, value)
+
     def get_components(self, cleaned):
         """
         Given the cleaning that has been performed, we'll use this to identify the property
@@ -90,10 +232,24 @@ class Property(BaseUtility):
         if not self.data:
             raise ValueError("Property does not contain data")
 
+        self.set_energy()
+        self.set_ventilation()
+        self.set_solar_pv()
+        self.set_solar_hot_water()
+        self.set_wind_turbine()
+        self.set_count_variables()
+        self.set_heat_loss_corridor()
+        self.set_mains_gas()
+        self.set_floor_height()
+
         for description, attribute in cleaned.items():
 
             if self.data[description] in self.DATA_ANOMALY_MATCHES:
-                setattr(self, self.ATTRIBUTE_MAP[description], {"original_description": self.data[description]})
+                setattr(
+                    self,
+                    self.ATTRIBUTE_MAP[description],
+                    {"original_description": self.data[description], "clean_description": self.data[description]}
+                )
                 continue
 
             attributes = [
@@ -131,3 +287,140 @@ class Property(BaseUtility):
 
         # We don't know when the property was built
         self.year_built = None
+
+    def set_heat_loss_corridor(self):
+        """
+        cleans the heat-loss-corridor
+        :return:
+        """
+        map = {
+            "no corridor": False,
+            "unheated corridor": True,
+            "heated corridor": False
+        }
+
+        if self.data["heat-loss-corridor"] in self.DATA_ANOMALY_MATCHES:
+            has_heat_loss_corridor = False
+        else:
+            has_heat_loss_corridor = map[self.data["heat-loss-corridor"]]
+
+        length = self.data["unheated-corridor-length"]
+        if length == "":
+            length = None
+        else:
+            length = float(length)
+
+        self.heat_loss_corridor = {
+            "heat_loss_corridor": has_heat_loss_corridor,
+            "length": length
+        }
+
+    def set_mains_gas(self):
+        """
+        Sets whether the property has mains gas
+        :return:
+        """
+
+        map = {
+            "Y": True,
+            "N": False,
+        }
+
+        if self.data["mains-gas-flag"] == "" or self.data["mains-gas-flag"] in self.DATA_ANOMALY_MATCHES:
+            self.mains_gas = None
+        else:
+            self.mains_gas = map[self.data["mains-gas-flag"]]
+
+    def set_floor_height(self):
+        """
+        Sets the floor height of the property
+        :return:
+        """
+
+        if self.data["floor-height"] == "" or self.data["floor-height"] in self.DATA_ANOMALY_MATCHES:
+            self.floor_height = None
+        else:
+            self.floor_height = float(self.data["floor-height"])
+
+    def _clean_upload_data(self, to_update):
+        for k, v in to_update.items():
+            if v in self.DATA_ANOMALY_MATCHES:
+                to_update[k] = None
+        return to_update
+
+    def get_full_property_data(self):
+        """
+        This method extracts the data which is pushed to the database, containing core information, from the EPC
+        about a property
+        :return:
+        """
+
+        property_data = {
+            "creation_status": "READY",
+            "uprn": int(self.data["uprn"]),
+            "building_reference_number": int(self.data["building-reference-number"]),
+            "has_pre_condition_report": True,
+            "has_recommendations": True,
+            "property_type": self.data["property-type"],
+            "built_form": self.data["built-form"],
+            "local_authority": self.data["local-authority-label"],
+            "constituency": self.data["constituency-label"],
+            "number_of_rooms": self.number_of_rooms,
+            "year_built": self.year_built,
+            "tenure": self.data["tenure"],
+            "current_epc_rating": self.data["current-energy-rating"],
+            "current_sap_points": self.data["current-energy-efficiency"]
+        }
+
+        property_data = self._clean_upload_data(property_data)
+
+        return property_data
+
+    @classmethod
+    def _prepare_rating_field(cls, field, rating_lookup):
+        """
+        Utility function for usage in the lambda, for preparing the _rating fields
+        """
+        return rating_lookup[field].value if field not in cls.DATA_ANOMALY_MATCHES else None
+
+    def get_property_details_epc(self, portfolio_id: int, rating_lookup):
+
+        property_details_epc = {
+            "property_id": self.id,
+            "portfolio_id": portfolio_id,
+            "full_address": self.data["address"],
+            "total_floor_area": float(self.data["total-floor-area"]),
+            "walls": self.walls["clean_description"],
+            "walls_rating": self._prepare_rating_field(self.data["walls-energy-eff"], rating_lookup),
+            "roof": self.roof["clean_description"],
+            "roof_rating": self._prepare_rating_field(self.data["roof-energy-eff"], rating_lookup),
+            "floor": self.floor["clean_description"],
+            "floor_rating": self._prepare_rating_field(self.data["floor-energy-eff"], rating_lookup),
+            "windows": self.windows["clean_description"],
+            "windows_rating": self._prepare_rating_field(self.data["windows-energy-eff"], rating_lookup),
+            "heating": self.main_heating["clean_description"],
+            "heating_rating": self._prepare_rating_field(self.data["mainheat-energy-eff"], rating_lookup),
+            "heating_controls": self.main_heating_controls["clean_description"],
+            "heating_controls_rating": self._prepare_rating_field(self.data["mainheatc-energy-eff"], rating_lookup),
+            "hot_water": self.hotwater["clean_description"],
+            "hot_water_rating": self._prepare_rating_field(self.data["hot-water-energy-eff"], rating_lookup),
+            "lighting": self.lighting["clean_description"],
+            "lighting_rating": self._prepare_rating_field(self.data["lighting-energy-eff"], rating_lookup),
+            "mainfuel": self.main_fuel["clean_description"],
+            "ventilation": self.ventilation["ventilation"],
+            "solar_pv": self.solar_pv["solar_pv"],
+            "solar_hot_water": self.solar_hot_water["solar_hot_water"],
+            "wind_turbine": self.wind_turbine["wind_turbine"],
+            "floor_height": self.floor_height,
+            "heat_loss_corridor": self.heat_loss_corridor["heat_loss_corridor"],
+            "unheated_corridor_length": self.heat_loss_corridor["length"],
+            "number_of_open_fireplaces": self.number_of_open_fireplaces,
+            "number_of_extensions": self.number_of_extensions,
+            "number_of_storeys": self.number_of_storeys,
+            "mains_gas": self.mains_gas,
+            "energy_tariff": self.data["energy-tariff"],
+            "primary_energy_consumption": self.energy["primary_energy_consumption"],
+            "co2_emissions": self.energy["co2_emissions"],
+        }
+
+        return property_details_epc

backend/app/db/functions/property_functions.py

@@ -2,8 +2,11 @@
 # This script contains methods for interacting with the property table in the database
 ###
 import datetime
+import pytz
 from sqlalchemy.orm import sessionmaker
-from backend.app.db.models.portfolio import PropertyModel, PropertyCreationStatus, PortfolioStatus
+from backend.app.db.models.portfolio import (
+    PropertyModel, PropertyCreationStatus, PortfolioStatus, PropertyTargetsModel, PropertyDetailsEpcModel
+)
 from backend.app.db.connection import db_engine
 from sqlalchemy.orm.exc import NoResultFound
 
@@ -20,8 +23,6 @@ def create_property(portfolio_id: int, address: str, postcode: str) -> (int, boo
     Session = sessionmaker(bind=db_engine)
     with Session() as session:
 
-        now = datetime.datetime.now()
-
         try:
             # Attempt to fetch the existing property
             existing_property = session.query(PropertyModel).filter_by(
@@ -29,7 +30,7 @@ def create_property(portfolio_id: int, address: str, postcode: str) -> (int, boo
             ).one()
 
             # Update the 'updated_at' field
-            existing_property.updated_at = now
+            existing_property.updated_at = datetime.datetime.now(pytz.utc)
 
             # Merge the updated property back into the session
             session.merge(existing_property)
@@ -43,8 +44,6 @@ def create_property(portfolio_id: int, address: str, postcode: str) -> (int, boo
                 address=address,
                 postcode=postcode,
                 portfolio_id=portfolio_id,
-                created_at=now,
-                updated_at=now,
                 creation_status=PropertyCreationStatus.LOADING,
                 status=PortfolioStatus.ASSESSMENT.value,
                 has_pre_condition_report=False,
@@ -57,3 +56,67 @@ def create_property(portfolio_id: int, address: str, postcode: str) -> (int, boo
             session.commit()
 
             return new_property.id, True
+
+
+def create_property_targets(property_id: int, portfolio_id: int, epc_target=None, heat_demand_target=None):
+    """
+    This function will create a record for the property targets in the database if it does not exist.
+    :param property_id: The ID of the property the targets belong to
+    :param portfolio_id: The ID of the portfolio the property belongs to
+    :param epc_target: Goal EPC value for the property
+    :param heat_demand_target: Heat demand target for the property in kwh/m^2/year
+    :return:
+    """
+    Session = sessionmaker(bind=db_engine)
+    with Session() as session:
+        new_target = PropertyTargetsModel(
+            property_id=property_id,
+            portfolio_id=portfolio_id,
+            epc=epc_target,
+            heat_demand=heat_demand_target
+        )
+        session.add(new_target)
+        session.commit()
+
+    return True
+
+
+def update_property_data(property_id: int, portfolio_id: int, property_data: dict):
+    Session = sessionmaker(bind=db_engine)
+    now = datetime.datetime.now(pytz.utc)
+    with Session() as session:
+        try:
+            # Attempt to fetch the existing property
+            existing_property = session.query(PropertyModel).filter_by(
+                id=property_id, portfolio_id=portfolio_id
+            ).one()
+
+            # Update the fields with the data in property_data
+            for key, value in property_data.items():
+                setattr(existing_property, key, value)
+
+            existing_property.updated_at = now
+
+            # Merge the updated property back into the session and commit
+            session.merge(existing_property)
+            session.commit()
+
+        except NoResultFound:
+            raise Exception(f"Property with property_id {property_id} and portfolio_id {portfolio_id} not found")
+
+    return True
+
+
+def create_property_details_epc(property_details_epc: dict):
+    """
+    This function will create a record for the property details EPC in the database.
+    :param property_details_epc: A dictionary containing details about the property EPC.
+    :return: True if successful, False otherwise.
+    """
+    Session = sessionmaker(bind=db_engine)
+    with Session() as session:
+        new_property_details_epc = PropertyDetailsEpcModel(**property_details_epc)
+        session.add(new_property_details_epc)
+        session.commit()
+
+    return True

backend/app/db/models/portfolio.py

@@ -1,5 +1,7 @@
 import enum
-from sqlalchemy import Column, Integer, Text, Boolean, Float, DateTime, Enum, ForeignKey
+import pytz
+import datetime
+from sqlalchemy import Column, Integer, Text, Boolean, Float, DateTime, Enum, ForeignKey, CheckConstraint
 from sqlalchemy.ext.declarative import declarative_base
 
 Base = declarative_base()
@@ -40,8 +42,8 @@ class Portfolio(Base):
     property_valuation_increase = Column(Float)  # Unit is always £ so we don't need to store the unit for the moment
     rental_yield_increase = Column(Float)  # Unit is always £ so we don't need to store the unit for the moment
     total_work_hours = Column(Float)
-    created_at = Column(DateTime, nullable=False)
-    updated_at = Column(DateTime, nullable=False)
+    created_at = Column(DateTime, nullable=False, default=datetime.datetime.now(pytz.utc))
+    updated_at = Column(DateTime, nullable=False, default=datetime.datetime.now(pytz.utc))
 
 
 class PropertyCreationStatus(enum.Enum):
@@ -66,13 +68,14 @@ class PropertyModel(Base):
     portfolio_id = Column(Integer, ForeignKey('portfolio.id'), nullable=False)
     creation_status = Column(Enum(PropertyCreationStatus), nullable=False)
     uprn = Column(Integer)
+    building_reference_number = Column(Integer)
     status = Column(Enum(PortfolioStatus, values_callable=lambda x: [e.value for e in x]), nullable=False)
     address = Column(Text)
     postcode = Column(Text)
     has_pre_condition_report = Column(Boolean)
     has_recommendations = Column(Boolean)
-    created_at = Column(DateTime, nullable=False)
-    updated_at = Column(DateTime, nullable=False)
+    created_at = Column(DateTime, nullable=False, default=datetime.datetime.now(pytz.utc))
+    updated_at = Column(DateTime, nullable=False, default=datetime.datetime.now(pytz.utc))
     property_type = Column(Text)
     built_form = Column(Text)
     local_authority = Column(Text)
@@ -85,14 +88,29 @@ class PropertyModel(Base):
 
 
 class FeatureRating(enum.Enum):
-    VERY_GOOD = "Very good"
-    GOOD = "Good"
-    POOR = "Poor"
-    VERY_POOR = "Very poor"
-    NA = "N/A"
+    VERY_GOOD = 5
+    GOOD = 4
+    AVERAGE = 3
+    POOR = 2
+    VERY_POOR = 1
+    NA = None
 
 
-class PropertyDetailsEpc(Base):
+rating_lookup = {
+    "Very Good": FeatureRating.VERY_GOOD,
+    "Good": FeatureRating.GOOD,
+    "Average": FeatureRating.AVERAGE,
+    "Poor": FeatureRating.POOR,
+    "Very Poor": FeatureRating.VERY_POOR,
+    "N/A": FeatureRating.NA
+}
+
+
+def get_feature_rating_from_string(rating_str: str):
+    return rating_lookup.get(rating_str, FeatureRating.NA)
+
+
+class PropertyDetailsEpcModel(Base):
     __tablename__ = 'property_details_epc'
     id = Column(Integer, primary_key=True, autoincrement=True)
     property_id = Column(Integer, ForeignKey('property.id'), nullable=False)
@@ -100,21 +118,24 @@ class PropertyDetailsEpc(Base):
     full_address = Column(Text)
     total_floor_area = Column(Float)
     walls = Column(Text)
-    walls_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    walls_rating = Column(Integer, CheckConstraint('walls_rating>=1 AND walls_rating<=5'))
     roof = Column(Text)
-    roof_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    roof_rating = Column(Integer, CheckConstraint('roof_rating>=1 AND roof_rating<=5'))
     floor = Column(Text)
-    floor_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    floor_rating = Column(Integer, CheckConstraint('floor_rating>=1 AND floor_rating<=5'))
     windows = Column(Text)
-    windows_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    windows_rating = Column(Integer, CheckConstraint('windows_rating>=1 AND windows_rating<=5'))
     heating = Column(Text)
-    heating_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
-    heating_contols = Column(Text)
-    heating_contols_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    heating_rating = Column(Integer, CheckConstraint('heating_rating>=1 AND heating_rating<=5'))
+    heating_controls = Column(Text)
+    heating_controls_rating = Column(
+        Integer, CheckConstraint('heating_controls_rating>=1 AND heating_controls_rating<=5')
+    )
     hot_water = Column(Text)
-    hot_water_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    hot_water_rating = Column(Integer, CheckConstraint('hot_water_rating>=1 AND hot_water_rating<=5'))
     lighting = Column(Text)
-    lighting_rating = Column(Enum(FeatureRating, values_callable=lambda x: [e.value for e in x]))
+    lighting_rating = Column(Integer, CheckConstraint('lighting_rating>=1 AND lighting_rating<=5'))
+    mainfuel = Column(Text)
     ventilation = Column(Text)
     solar_pv = Column(Text)
     solar_hot_water = Column(Text)
@@ -143,11 +164,11 @@ class PropertyDetailsMeter(Base):
     meter_reading_gas = Column(Float)
 
 
-class PropertyTargets(Base):
+class PropertyTargetsModel(Base):
     __tablename__ = 'property_targets'
     id = Column(Integer, primary_key=True, autoincrement=True)
     property_id = Column(Integer, ForeignKey('property.id'), nullable=False)
     portfolio_id = Column(Integer, ForeignKey('portfolio.id'), nullable=False)
-    created_at = Column(DateTime, nullable=False)
+    created_at = Column(DateTime, nullable=False, default=datetime.datetime.now(pytz.utc))
     epc = Column(Enum(Epc))
     heat_demand = Column(Text)

backend/app/plan/router.py

@@ -1,4 +1,5 @@
 from fastapi import APIRouter, Depends
+from backend.app.db.models.portfolio import rating_lookup
 from backend.app.dependencies import validate_token
 from backend.app.plan.schemas import PlanTriggerRequest
 from backend.app.utils import read_csv_from_s3
@@ -9,12 +10,14 @@ from utils.logger import setup_logger
 from recommendations.FloorRecommendations import FloorRecommendations
 from recommendations.WallRecommendations import WallRecommendations
 from utils.uvalue_estimates import classify_decile_newvalues
+from model_data.EpcClean import EpcClean
 
 # database interaction functions
-from backend.app.db.functions.property_functions import create_property
+from backend.app.db.functions.property_functions import (
+    create_property, create_property_targets, update_property_data, create_property_details_epc
+)
 
 # TODO: This is placeholder until data is stored in DB
-from backend.app.plan.temp_cleaned_data import cleaned
 from backend.app.plan.uvalue_estimates_walls import uvalue_estimates_walls
 from backend.app.plan.uvalue_estimates_floors import uvalue_estimates_floors
 
@@ -69,6 +72,12 @@ walls_decile_data = {
                       'Decile 9', 'Decile 10'], 'decile_boundaries': [6., 49., 51., 55., 64., 71., 76., 83., 96.,
                                                                       120., 2279.]}
 
+lighting_averages = [
+    {'lighting-description': 'good lighting efficiency', 'low-energy-lighting': 99.26666666666667},
+    {'lighting-description': 'excellent lighting efficiency', 'low-energy-lighting': 100.0},
+    {'lighting-description': 'below average lighting efficiency', 'low-energy-lighting': 0.0}
+]
+
 
 @router.post("/trigger")
 async def trigger_plan(body: PlanTriggerRequest):
@@ -93,6 +102,14 @@ async def trigger_plan(body: PlanTriggerRequest):
         if not is_new:
             continue
 
+        # TODO: Need to add heat demand target
+        create_property_targets(
+            property_id=property_id,
+            portfolio_id=body.portfolio_id,
+            epc_target=body.goal_value,
+            heat_demand_target=None
+        )
+
         input_properties.append(
             Property(
                 postcode=config['postcode'],
@@ -120,6 +137,10 @@ async def trigger_plan(body: PlanTriggerRequest):
         )
         p.set_is_in_conservation_area(in_conservation_area)
 
+    # TODO: This won't work perfectly as we need the table of lighting averages by constituency
+    cleaner = EpcClean(data=[x.data for x in input_properties])
+    cleaner.clean()
+
     logger.info("Getting components and properties recommendations")
     recommendations = []
     for property_id, p in enumerate(input_properties):
@@ -131,7 +152,7 @@ async def trigger_plan(body: PlanTriggerRequest):
         )[0]
 
         # Property recommendations
-        p.get_components(cleaned)
+        p.get_components(cleaner.cleaned)
 
         # This is placeholder, until the full dataset is loaded into the database and we just make a read to the
         # database
@@ -187,4 +208,17 @@ async def trigger_plan(body: PlanTriggerRequest):
 
         recommendations.extend(wall_recomendations.recommendations)
 
+    # Once we're done, we'll store:
+    # 1) the property data
+    # 2) the property details (epc)
+    # 3) the recommendations
+
+    # Upload property data
+    for p in input_properties:
+        property_details_epc = p.get_property_details_epc(portfolio_id=body.portfolio_id, rating_lookup=rating_lookup)
+        create_property_details_epc(property_details_epc)
+
+        property_data = p.get_full_property_data()
+        update_property_data(property_id=p.id, portfolio_id=body.portfolio_id, property_data=property_data)
+
     return {"recommendations": recommendations}

model_data/EpcClean.py

@@ -1,7 +1,6 @@
 from typing import List, Dict, Any
 from collections import Counter
-
-import pandas as pd
+from collections import defaultdict
 
 from model_data.utils import correct_spelling
 from model_data.epc_attributes.FloorAttributes import FloorAttributes
@@ -32,7 +31,8 @@ class EpcClean:
         "lighting-description"
     ]
 
-    def __init__(self, data: List[Dict[str, Any]]) -> None:
+    def __init__(self, data: List[Dict[str, Any]],
+                 lighting_averages: List[Dict[str, str | float]] | None = None) -> None:
         """
         EpcClean constructor.
 
@@ -42,34 +42,51 @@ class EpcClean:
         self.unique_vals: Dict[str, Any] = {}
         self.cleaned: Dict[str, List[Any]] = {}
 
-        self.lighting_averages = self._calculate_lighting_averages()
+        if not lighting_averages:
+            self.lighting_averages = self._calculate_lighting_averages()
+        else:
+            self.lighting_averages = lighting_averages
 
     def _calculate_lighting_averages(self):
 
         """
-        This is a simple utility function that for few textual lighting descritpions, will calculate the average
+        This is a simple utility function that for few textual lighting descriptions, will calculate the average
         low energy lighting proportion. This is only valid for a very tiny number of cases and so a very simple
         methodology is applied
-        :return: Dataframe of avergages for the corresponding descriptions
+
+        This is done without pandas so we can utilise this inside of our lambdas
+
+        :return: list of avergages for the corresponding descriptions
         """
 
-        df = pd.DataFrame(self.data)
-        aggs = df[
-            df["lighting-description"].isin(
-                [
-                    'Below average lighting efficiency',
-                    'Good lighting efficiency',
-                    'Excelent lighting efficiency'
-                ]
-            )
-        ].copy()
-        aggs["low-energy-lighting"] = aggs["low-energy-lighting"].astype(float)
+        data = self.data
 
-        averages = aggs.groupby("lighting-description")["low-energy-lighting"].mean().reset_index()
-        averages["lighting-description"] = averages["lighting-description"].str.lower()
+        # Filter rows with the specified lighting descriptions
+        filtered_data = [
+            row for row in data if row["lighting-description"] in [
+                'Below average lighting efficiency',
+                'Good lighting efficiency',
+                'Excelent lighting efficiency'
+            ]
+        ]
 
-        # Correct spelling mistakes in averages
-        averages["lighting-description"] = averages["lighting-description"].apply(correct_spelling)
+        # Convert low-energy-lighting to float
+        for row in filtered_data:
+            row["low-energy-lighting"] = float(row["low-energy-lighting"])
+
+        # Calculate averages
+        sums = defaultdict(float)
+        counts = defaultdict(int)
+
+        for row in filtered_data:
+            description = row["lighting-description"]
+            sums[description] += row["low-energy-lighting"]
+            counts[description] += 1
+
+        averages = [{
+            "lighting-description": correct_spelling(description.lower()),
+            "low-energy-lighting": total / counts[description]
+        } for description, total in sums.items()]
 
         return averages
 
@@ -103,9 +120,12 @@ class EpcClean:
 
     def clean_wrapper(self, field, cleaning_cls, **kwargs):
         for description in self.unique_vals[field].keys():
+            cln = cleaning_cls(description, **kwargs)
+
             self.cleaned[field].append(
                 {
                     "original_description": description,
-                    **cleaning_cls(description, **kwargs).process()
+                    "clean_description": cln.description.capitalize(),
+                    **cln.process()
                 }
             )

model_data/app.py

@@ -74,6 +74,10 @@ def app():
 
     # Incorporate input data into cleaning
     cleaner = EpcClean(data)
+    lighting_averages = cleaner.lighting_averages
+    # TODO: WE need to store lighting_averages to a db
+    #       We should also extend these averages so they're by more variables (property type, age band, constituency,
+    #       etc)
     cleaner.clean()
     # TODO: cleaner.cleaned datasets to a db
 

model_data/epc_attributes/LightingAttributes.py

@@ -22,10 +22,12 @@ class LightingAttributes:
 
         if ('good lighting efficiency' in description) or ('excellent lighting efficiency' in description) or \
             ('below average lighting efficiency' in description):
+            average = [
+                x for x in self.averages if x["lighting-description"] == description
+            ][0]["low-energy-lighting"]
+
             return {
-                "low_energy_proportion": self.averages[
-                    self.averages["lighting-description"] == description
-                    ]["low-energy-lighting"].values[0]
+                "low_energy_proportion": average
             }
 
         match = re.search(r'\d+', description)