Added unit tests for annual bill savings appliance consumption

.idea/Model.iml

@@ -7,7 +7,7 @@
       <sourceFolder url="file://$MODULE_DIR$/open_uprn" isTestSource="false" />
       <sourceFolder url="file://$MODULE_DIR$/recommendations" isTestSource="false" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.10 (backend)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.10 (model_data)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyNamespacePackagesService">

.idea/misc.xml

@@ -3,7 +3,7 @@
   <component name="Black">
     <option name="sdkName" value="Python 3.10 (backend)" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (backend)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (model_data)" project-jdk-type="Python SDK" />
   <component name="PythonCompatibilityInspectionAdvertiser">
     <option name="version" value="3" />
   </component>

backend/Property.py

@@ -18,6 +18,7 @@ from recommendations.recommendation_utils import (
     esimtate_pitched_roof_area,
     estimate_windows,
 )
+from backend.ml_models.AnnualBillSavings import AnnualBillSavings
 
 ENVIRONMENT = os.environ.get("ENVIRONMENT", "dev")
 DATA_BUCKET = os.environ.get(
@@ -590,6 +591,23 @@ class Property:
         self.set_energy_source()
         self.find_energy_sources()
 
+    def set_current_energy_bill(self):
+        """
+        Given what we know about the property now, estimates the current energy consumption using the UCL paper
+        https://www.sciencedirect.com/science/article/pii/S0378778823002542
+        :return:
+        """
+        starting_heat_demand = (
+            float(self.data["energy-consumption-current"]) * self.floor_area
+        )
+
+        self.current_adjusted_energy = AnnualBillSavings.adjust_energy_to_metered(
+            epc_energy_consumption=starting_heat_demand,
+            current_epc_rating=self.data["current-energy-rating"],
+        )
+
+        self.current_energy_bill = AnnualBillSavings.calculate_annual_bill(self.current_adjusted_energy)
+
     def set_spatial(self, spatial: pd.DataFrame):
         """
         Sets whether the property is in a conservation area given the output of the ConservationAreaClient
@@ -909,14 +927,13 @@ class Property:
         return component_data
 
     def set_adjusted_energy(
-        self, current_adjusted_energy, expected_adjusted_energy, current_energy_bill, expected_energy_bill
+        self, expected_adjusted_energy, expected_energy_bill
     ):
         """
         Stores these values for usage later
         """
-        self.current_adjusted_energy = current_adjusted_energy
+
         self.expected_adjusted_energy = expected_adjusted_energy
-        self.current_energy_bill = current_energy_bill
         self.expected_energy_bill = expected_energy_bill
 
     def set_windows_count(self):

backend/apis/GoogleSolarApi.py

@@ -14,6 +14,31 @@ class GoogleSolarApi:
     # be exported
     SOLAR_CONSUMPTION_PROPORTION = 0.5
 
+    # These are variables, described in the documentation for cost analysis for non-us locations, seen here
+    # https://developers.google.com/maps/documentation/solar/calculate-costs-non-us
+    # We use the default figures that the API uses for US locations
+
+    # The factor by which the cost of electricity increases annually. The Solar API uses 1.022 (2.2% annual increase)
+    # for US locations.
+    cost_increase_factor = 1.022
+
+    # The efficiency at which an inverter converts the DC electricity that is produced by the solar panels to the AC
+    # electricity that is used in a household. The Solar API uses 85% for US locations. We use 0.95.5 which is the
+    # middle value of the 93-98% range, cited by Sunsave:
+    # https://www.sunsave.energy/solar-panels-advice/system-size/inverters
+    dc_to_ac_rate = 0.955
+
+    # The Solar API uses 1.04 (4% annual increase) for US locations
+    discount_rate = 1.04
+
+    # How much the efficiency of the solar panels declines each year. The Solar API uses 0.995 (0.5% annual decrease)
+    # for US locations
+    efficiency_depreciation_factor = 0.995
+
+    # The expected lifespan of the solar installation. The Solar API uses 20 years. Adjust this value as needed for
+    # your area
+    installation_life_span = 20
+
     def __init__(self, api_key, max_retries=5):
         """
         Initialize the GoogleSolarApi class with the provided API key and maximum retries.
@@ -94,6 +119,13 @@ class GoogleSolarApi:
             self.insights_data["solarPotential"]["panelWidthMeters"]
         )
         self.panel_wattage = self.insights_data["solarPotential"]["panelCapacityWatts"]
+        if self.panel_wattage != 400:
+            # In the API documentation, it claims that the default output is 250W, however we've only seen 400W, so if
+            # we get anything other than 400W, we'll need to adjust the calculations in the output. For this, we should
+            # refer to https://developers.google.com/maps/documentation/solar/calculate-costs-non-us
+            # Where the documentation explains how to adjust the yearlyEnergyDcKwh figures.
+            # It should be straightforward, but I'd rather see an actual instance of this happening
+            raise NotImplementedError("Panel wattage is not 400W - implement me")
 
         # Automatically exclude north-facing segments
         self.exclude_north_facing_segments()

backend/app/plan/router.py

@@ -426,9 +426,7 @@ async def trigger_plan(body: PlanTriggerRequest):
 
             (
                 recommendations_with_impact,
-                current_adjusted_energy,
                 expected_adjusted_energy,
-                current_energy_bill,
                 expected_energy_bill
             ) = (
                 Recommendations.calculate_recommendation_impact(
@@ -440,9 +438,7 @@ async def trigger_plan(body: PlanTriggerRequest):
 
             # Store the resulting adjusted energy in the property instance
             property_instance.set_adjusted_energy(
-                current_adjusted_energy=current_adjusted_energy,
                 expected_adjusted_energy=expected_adjusted_energy,
-                current_energy_bill=current_energy_bill,
                 expected_energy_bill=expected_energy_bill
             )
 

backend/ml_models/AnnualBillSavings.py

@@ -1,3 +1,6 @@
+import numpy as np
+
+
 class AnnualBillSavings:
     """
     This is a simple class which will estimate the annual bill savings, based on the kwh savings.
@@ -60,8 +63,58 @@ class AnnualBillSavings:
 
         return cls.ELECTRICITY_PRICE_CAP * kwh + (cls.DAILY_STANDARD_CHARGE_ELECTRICITY * 365)
 
+    @staticmethod
+    def calculate_occupants(total_floor_area):
+        """
+        From Table 1b of the SAP 2012 documentation https://bregroup.com/documents/d/bre-group/sap-2012_9-92
+        Provides a methodology to estimate occupancy, based on floor area. This is used to calculate the amount of
+        electricity used be appliances and during cooking.
+        :param total_floor_area:
+        :return:
+        """
+
+        if total_floor_area <= 13.9:
+            return 1
+
+        return 1 + (1.76 * (1 - np.exp(-0.000349 * (total_floor_area - 13.9) * (total_floor_area - 13.9))) + 0.0013 * (
+            total_floor_area - 13.9))
+
+    @staticmethod
+    def estimate_electrical_appliances(occupants, total_floor_area):
+        """
+        From secion L2 of SAP2012 Electrical appliances
+        https://bregroup.com/documents/d/bre-group/sap-2012_9-92
+        Used to estimate the amount of energy used by electrical appliances
+        :param occupants:
+        :param total_floor_area:
+        :return:
+        """
+        e_a = 207.8 * np.power(total_floor_area * occupants, 0.4717)
+
+        days_in_month = {
+            1: 31,
+            2: 28,
+            3: 31,
+            4: 30,
+            5: 31,
+            6: 30,
+            7: 31,
+            8: 31,
+            9: 30,
+            10: 31,
+            11: 30,
+            12: 31
+        }
+
+        eam = 0
+        for m in range(1, 13):
+            nm = days_in_month[m]
+            eam += e_a * (1 + 0.157 * np.cos(2 * np.pi * (m - 1.78) / 12)) * nm / 365
+
+        return eam
+
     @classmethod
-    def adjust_energy_to_metered(cls, epc_energy_consumption, current_epc_rating):
+    def adjust_energy_to_metered(cls, epc_energy_consumption, current_epc_rating, total_floor_area):
         """
         The over-prediction of energy use by EPCs in Great Britain: A comparison
         of EPC-modelled and metered primary energy use intensity
@@ -72,6 +125,13 @@ class AnnualBillSavings:
         :return:
         """
 
+        # The EPC energy consumption does not factor in cooking and applicance use, so this is estimated using the
+        # methodology outlined in SAP, and is discussed in the UCL paper in section 3.1.1
+        estimated_occupants = cls.calculate_occupants(total_floor_area=total_floor_area)
+        appliances_energy_use = cls.estimate_electrical_appliances(estimated_occupants, total_floor_area)
+
+        epc_energy_consumption += appliances_energy_use
+
         gradients = {
             "A": -0.1,
             "B": -0.1,

etl/customers/stonewater/shdf_3_clustering.py

@@ -6,6 +6,7 @@ from backend.SearchEpc import SearchEpc
 import urllib.parse
 import requests
 from datetime import datetime
+from scipy import stats
 
 from fuzzywuzzy import fuzz
 import numpy as np
@@ -1598,7 +1599,6 @@ def compile_data_final():
         property_attributes[c] = property_attributes[c].fillna(0)
         property_attributes[c] = property_attributes[c].astype(float)
 
-    from scipy import stats
     for col in fill_with_mode:
         property_attributes[col] = property_attributes[col].replace('', None)
         mode_val = stats.mode([float(x) for x in property_attributes[col].values if x not in [None, "", np.nan]])[0]
@@ -1632,6 +1632,12 @@ def compile_data_final():
     #     s3_file_name="customers/Stonewater/clustering/clustering_dataframe.pkl"
     # )
 
+    # from utils.s3 import read_pickle_from_s3
+    # data = read_pickle_from_s3(
+    #     bucket_name="retrofit-data-dev",
+    #     s3_file_name="customers/Stonewater/clustering/clustering_dataframe.pkl"
+    # )
+
     # CLUSTERING!!
 
     # from sklearn.cluster import KMeans

recommendations/Recommendations.py

@@ -311,14 +311,6 @@ class Recommendations:
         # This is the unadjusted resulting heat demand
         predicted_heat_demand_change = starting_heat_demand - expected_heat_demand
 
-        # We don't want to adjust the heat demand for mechanical ventilation so we add it back on
-
-        # We adjust the heat demand figures to align to the UCL paper
-        current_adjusted_energy = AnnualBillSavings.adjust_energy_to_metered(
-            epc_energy_consumption=starting_heat_demand,
-            current_epc_rating=property_instance.data["current-energy-rating"],
-        )
-
         # TODO: This isn't quite right as this is based on EVERY possible measure, not just the ones that are
         #       actually implemented
         expected_adjusted_energy = AnnualBillSavings.adjust_energy_to_metered(
@@ -327,11 +319,10 @@ class Recommendations:
         )
 
         adjusted_heat_demand_change = (
-            current_adjusted_energy - expected_adjusted_energy
+            property_instance.current_adjusted_energy - expected_adjusted_energy
         )
 
         # TODO: We should determine if the home is gas & electricity or just electricity
-        current_energy_bill = AnnualBillSavings.calculate_annual_bill(current_adjusted_energy)
         expected_energy_bill = AnnualBillSavings.calculate_annual_bill(expected_adjusted_energy)
 
         for recommendations_by_type in property_recommendations:
@@ -410,8 +401,6 @@ class Recommendations:
 
         return (
             property_recommendations,
-            current_adjusted_energy,
             expected_adjusted_energy,
-            current_energy_bill,
             expected_energy_bill
         )