working on cleaning epc data for old records

backend/Property.py

@@ -727,11 +727,12 @@ class Property:
 
         self.energy_cost_estimates = {
             "unadjusted": unadjusted_heating_costs,
-            "epc": {
-                "heating": float(self.data["heating-cost-current"]),
-                "hot_water": float(self.data["hot-water-cost-current"]),
-                "lighting": float(self.data["lighting-cost-current"]),
-            }
+            # Don't think we need the EPC
+            # "epc": {
+            #     "heating": float(self.data["heating-cost-current"]),
+            #     "hot_water": float(self.data["hot-water-cost-current"]),
+            #     "lighting": float(self.data["lighting-cost-current"]),
+            # }
         }
 
         self.energy_consumption_estimates = {

backend/app/assumptions.py

@@ -101,3 +101,12 @@ measures_needing_ventilation = [
 
 # If we have a property beyond this size, we assume it's likely large enough to have an ASHP
 ASHP_FLOOR_AREA_THRESHOLD = 120  # m2
+
+# Is a placeholder, used for cleaning data. Is a flat average based on the estimated
+AVERAGE_LIGHTING_COST = 100
+
+# Average bill, based on british gas is #1,838.71. Subtract 100 for lighting, 228 for hot water. This will include
+# appliances so appliances should be removed when this is used
+AVERAGE_HEATING_AND_APPLIANCE_COST = 1510.71
+# Based on https://energysavingtrust.org.uk/sites/default/files/reports/AtHomewithWater%287%29.pdf
+AVERAGE_HOT_WATER_COST = 228

backend/app/db/models/recommendations.py

@@ -3,6 +3,7 @@ from sqlalchemy.orm import declarative_base
 from sqlalchemy.sql import func
 from backend.app.db.models.portfolio import Portfolio, PropertyModel
 from backend.app.db.models.materials import Material
+from backend.app.db.models.portfolio import Epc
 from datatypes.enums import QuantityUnits
 import enum
 
@@ -78,6 +79,16 @@ class Plan(Base):
         ),
         nullable=True,
     )
+    post_sap_points = Column(Float)
+    post_epc_rating = Column(Enum(Epc))
+    post_co2_emissions = Column(Float)
+    co2_savings = Column(Float)
+    post_energy_bill = Column(Float)
+    energy_bill_savings = Column(Float)
+    post_energy_consumption = Column(Float)  # energy demand in kWh/year
+    energy_consumption_savings = Column(Float)
+    valuation_post_retrofit = Column(Float)
+    valuation_increase = Column(Float)
 
 
 class PlanRecommendations(Base):

backend/engine/engine.py

@@ -1,4 +1,3 @@
-import os
 import time
 import json
 from copy import deepcopy
@@ -16,6 +15,7 @@ from etl.epc.Record import EPCRecord
 from sqlalchemy.exc import IntegrityError, OperationalError
 from sqlalchemy.orm import sessionmaker
 from starlette.responses import Response
+from backend.ml_models.AnnualBillSavings import AnnualBillSavings
 
 from backend.app.config import get_settings, get_prediction_buckets
 from backend.app.db.connection import db_engine
@@ -415,8 +415,17 @@ def averages_cleaning(prepared_epc: EPCRecord, cleaning_data: pd.DataFrame):
     :return:
     """
 
-    if not pd.isnull(prepared_epc.prepared_epc["number_habitable_rooms"]) and not pd.isnull(
-        prepared_epc.prepared_epc["number_heated_rooms"]) and not pd.isnull(prepared_epc.prepared_epc["floor_height"]):
+    variables_to_clean = [
+        "number_habitable_rooms",
+        "number_heated_rooms",
+        "floor_height",
+        "lighting_cost_current",
+        "heating_cost_current",
+        "hot_water_cost_current",
+        "energy_consumption_potential",
+    ]
+
+    if not any([pd.isnull(prepared_epc.prepared_epc[k]) for k in variables_to_clean]):
         # Nothing to do
         return prepared_epc
 
@@ -461,6 +470,30 @@ def averages_cleaning(prepared_epc: EPCRecord, cleaning_data: pd.DataFrame):
         prepared_epc.prepared_epc["floor_height"] = clean_floor_height
         prepared_epc.floor_height = clean_floor_height
 
+    if pd.isnull(prepared_epc.lighting_cost_current):
+        # This is a basic assumption as an average
+        prepared_epc.prepared_epc["lighting_cost_current"] = assumptions.AVERAGE_LIGHTING_COST
+        prepared_epc.lighting_cost_current = assumptions.AVERAGE_LIGHTING_COST
+
+    if pd.isnull(prepared_epc.heating_cost_current):
+        # This is a basic assumption as an average
+        appliance_cost = AnnualBillSavings.estimate_appliances_energy_use(
+            total_floor_area=prepared_epc.total_floor_area
+        ) * AnnualBillSavings.ELECTRICITY_PRICE_CAP
+        heating_cleaned_value = assumptions.AVERAGE_HEATING_AND_APPLIANCE_COST - appliance_cost
+        prepared_epc.prepared_epc["heating_cost_current"] = heating_cleaned_value
+        prepared_epc.heating_cost_current = heating_cleaned_value
+
+    if pd.isnull(prepared_epc.hot_water_cost_current):
+        # This is a basic assumption as an average
+        prepared_epc.prepared_epc["hot_water_cost_current"] = assumptions.AVERAGE_HOT_WATER_COST
+        prepared_epc.hot_water_cost_current = assumptions.AVERAGE_HOT_WATER_COST
+
+    if pd.isnull(prepared_epc.energy_consumption_potential):
+        # Set to current
+        prepared_epc.prepared_epc["energy_consumption_potential"] = prepared_epc.energy_consumption_current
+        prepared_epc.energy_consumption_potential = prepared_epc.energy_consumption_current
+
     return prepared_epc