diff --git a/backend/Property.py b/backend/Property.py index 618dfd67..19e5cb2e 100644 --- a/backend/Property.py +++ b/backend/Property.py @@ -2,13 +2,13 @@ import os import ast from itertools import groupby import pandas as pd +import numpy as np from datetime import datetime, timedelta from etl.epc.Dataset import TrainingDataset from etl.epc.Record import EPCRecord from etl.epc.settings import LATEST_FIELD, MANDATORY_FIXED_FEATURES from etl.epc_clean.epc_attributes.all_cleaners import all_cleaner_map -from etl.solar.SolarPhotoSupply import SolarPhotoSupply from utils.logger import setup_logger from utils.s3 import read_dataframe_from_s3_parquet from etl.epc.settings import DATA_ANOMALY_MATCHES @@ -17,10 +17,11 @@ from recommendations.recommendation_utils import ( estimate_perimeter, get_wall_type, estimate_external_wall_area, - esimtate_pitched_roof_area, estimate_windows, ) from backend.ml_models.AnnualBillSavings import AnnualBillSavings +from backend.app.utils import sap_to_epc +import backend.app.assumptions as assumptions ENVIRONMENT = os.environ.get("ENVIRONMENT", "dev") DATA_BUCKET = os.environ.get( @@ -91,6 +92,7 @@ class Property: self.data = { k.replace("_", "-"): v for k, v in epc_record.get("prepared_epc").items() } + self.old_data = epc_record.get("old_data") self.property_dimensions = None # This is a list of measures that have already been installed in the property, typically found as a result @@ -171,8 +173,8 @@ class Property: self.windows_area = None self.solar_pv_percentage = None - self.current_adjusted_energy = None - self.expected_adjusted_energy = None + self.current_energy_consumption = None + self.current_energy_consumption_heating_hotwater = None self.current_energy_bill = None self.expected_energy_bill = None @@ -181,6 +183,7 @@ class Property: self.recommendations_scoring_data = [] self.simulation_epcs = {} + self.updated_simulation_epcs = [] # This additional condition data should change how we pass kwargs to this. We should no longer need to pass # kwargs to this class, but instead, we should pass the energy assessment condition data @@ -211,17 +214,32 @@ class Property: if n_bedrooms not in [None, ""]: n_bedrooms = int(round(float(n_bedrooms) + 1e-5)) + number_of_floors = kwargs.get("number_of_floors", None) + if number_of_floors not in [None, ""]: + number_of_floors = int(round(float(number_of_floors) + 1e-5)) + + insulation_floor_area = kwargs.get("insulation_floor_area", None) + if insulation_floor_area not in [None, ""]: + insulation_floor_area = float(insulation_floor_area) + + insulation_wall_area = kwargs.get("insulation_wall_area", None) + if insulation_wall_area not in [None, ""]: + insulation_wall_area = float(insulation_wall_area) + return { "n_bathrooms": n_bathrooms, "n_bedrooms": n_bedrooms, + "number_of_floors": number_of_floors, + "insulation_floor_area": insulation_floor_area, + "insulation_wall_area": insulation_wall_area, "building_id": kwargs.get("building_id", None), } def parse_kwargs(self, kwargs): # We extract the elements from kwargs that we recognise. Anything additional is ignored - self.n_bathrooms = kwargs.get("n_bathrooms", None) - self.n_bedrooms = kwargs.get("n_bedrooms", None) - self.building_id = kwargs.get("building_id", None) + for arg, val in kwargs.items(): + if val is not None: + setattr(self, arg, val) def create_base_difference_epc_record(self, cleaned_lookup: dict): """ @@ -359,68 +377,88 @@ class Property: ) self.recommendations_scoring_data.append(scoring_dict) - # We also use the representative recommendations to produce transformed EPCs - represenative_recs_to_this_phase = [ - r for r in property_representative_recommendations - if r["phase"] <= phase - ] + simulation_epc = self.epc_record.prepared_epc.copy() + # Insert static values + simulation_epc["lodgement_date"] = simulation_lodgment_date + simulation_epc = {k.replace("_", "-"): v for k, v in simulation_epc.items()} - # TODO: This is placeholder, but it's to handle the case of having both internal and external wall - # insulation as options. This will cause the process below to fall over, so we take just - # external wall insulation in epc_transformations, if we have both - types = [ - x["type"] for x in represenative_recs_to_this_phase - ] - if "external_wall_insulation" in types and "internal_wall_insulation" in types: + types = [x["type"] for x in previous_phase_representatives] + if "external_wall_insulation" in types and "internal_wall_insulation" in types: + raise Exception("We shouldn't have this in the representative recommendations") + # We include previous phases + the recommendation itself in the EPC transformations epc_transformations = [ - x["description_simulation"] for x in represenative_recs_to_this_phase if - x["type"] != "internal_wall_insulation" - ] - else: - epc_transformations = [ - x["description_simulation"] for x in represenative_recs_to_this_phase + x["description_simulation"] for x in previous_phase_representatives + [rec] ] - # It is possible that we could have two simulations applied to the same descriptions - # We extract these out - phase_epc_transformation = {} - for config in epc_transformations: - for k, v in config.items(): - if k in phase_epc_transformation: - if "-energy-eff" in k: - # We take the highest value - if phase_epc_transformation[k] == "Very Good": + # It is possible that we could have two simulations applied to the same descriptions + # We extract these out + phase_epc_transformation = {} + for config in epc_transformations: + for k, v in config.items(): + if k in phase_epc_transformation: + if "-energy-eff" in k: + # We take the highest value + if phase_epc_transformation[k] == "Very Good": + continue + elif phase_epc_transformation[k] == "Good": + if v == "Very Good": + phase_epc_transformation[k] = v + elif phase_epc_transformation[k] == "Average": + if v in ["Good", "Very Good"]: + phase_epc_transformation[k] = v + elif phase_epc_transformation[k] == "Poor": + if v in ["Average", "Good", "Very Good"]: + phase_epc_transformation[k] = v + else: + phase_epc_transformation[k] = v + continue - elif phase_epc_transformation[k] == "Good": - if v == "Very Good": - phase_epc_transformation[k] = v - elif phase_epc_transformation[k] == "Average": - if v in ["Good", "Very Good"]: - phase_epc_transformation[k] = v - elif phase_epc_transformation[k] == "Poor": - if v in ["Average", "Good", "Very Good"]: - phase_epc_transformation[k] = v - else: - phase_epc_transformation[k] = v - continue + if phase_epc_transformation[k] == v: + continue - if phase_epc_transformation[k] == v: - continue + raise NotImplementedError( + "Already have this key in the phase_epc_transformation - implement me" + ) + phase_epc_transformation[k] = v + simulation_epc.update(phase_epc_transformation) + self.simulation_epcs[rec["recommendation_id"]] = simulation_epc - raise NotImplementedError( - "Already have this key in the phase_epc_transformation - implement me" - ) - phase_epc_transformation[k] = v + def update_simulation_epcs(self, impact_summary): + """ + This method will insert the high level measures, such as SAP, heat demand, carbon, etc + :return: + """ + if self.simulation_epcs is None: + raise ValueError("Simulation EPCs have not been created") - simulation_epc = self.epc_record.prepared_epc.copy() - # Insert static values - simulation_epc["lodgement_date"] = simulation_lodgment_date + rec_ids = sorted(list(self.simulation_epcs.keys())) + updated_simulation_epcs = [] + for rec_id in rec_ids: + sim_epc = self.simulation_epcs[rec_id].copy() + rec_impact = [x for x in impact_summary if x["recommendation_id"] == rec_id][0] + # We update all of the features that should have an impact on the kwh model - # Replace the understores with hyphens - simulation_epc = {k.replace("_", "-"): v for k, v in simulation_epc.items()} - simulation_epc.update(phase_epc_transformation) - self.simulation_epcs[phase] = simulation_epc + sim_epc.update( + { + # CO₂ emissions per square metre floor area per year in kg/m². Since CO₂ emissions are in tonnes + # per year, we multiply by 1000 to get kg/m² + "co2-emiss-curr-per-floor-area": round( + 1000 * (rec_impact["carbon"] / self.data["total-floor-area"]) + ), + "co2-emissions-current": rec_impact["carbon"], + "current-energy-rating": sap_to_epc(rec_impact["sap"]), + "current-energy-efficiency": int(np.floor(rec_impact["sap"])), + "energy-consumption-current": rec_impact["heat_demand"], + "id": "+".join([str(self.id), rec_id]) + } + ) + updated_simulation_epcs.append(sim_epc) + + # Now we havet this data inthe + self.updated_simulation_epcs = updated_simulation_epcs + + return updated_simulation_epcs @staticmethod def create_recommendation_scoring_data( @@ -455,81 +493,6 @@ class Property: for recommendation in recommendations: # For the list of recommendations we have, we iteratively update the output - # Update description to indicate it's insulate - if recommendation["type"] in [ - "solid_floor_insulation", - "suspended_floor_insulation", - "exposed_floor_insulation", - ]: - if len(recommendation["parts"]) > 1: - raise NotImplementedError( - "Have more than 1 floor insulation part - handle this case" - ) - - # We don't really see above average for this in the training data - output["floor_insulation_thickness_ending"] = "average" - else: - if output["floor_thermal_transmittance_ending"] is None: - raise ValueError("We should not have a None value for the u value") - - if output["floor_insulation_thickness_ending"] is None: - output["floor_insulation_thickness_ending"] = "none" - - if recommendation["type"] in [ - "loft_insulation", - "room_roof_insulation", - "flat_roof_insulation", - ]: - output["roof_thermal_transmittance_ending"] = recommendation[ - "new_u_value" - ] - - parts = recommendation["parts"] - if len(parts) != 1: - raise ValueError( - "More than one part for roof insulation - investiage me" - ) - - # This is based on the values we have in the training data - valid_numeric_values = [ - 12, - 25, - 50, - 75, - 100, - 150, - 200, - 250, - 270, - 300, - 350, - 400, - ] - - proposed_depth = recommendation["new_thickness"] - if proposed_depth not in valid_numeric_values: - # Take the nearest value for scoring - proposed_depth = min( - valid_numeric_values, key=lambda x: abs(x - proposed_depth) - ) - - output["roof_insulation_thickness_ending"] = str(int(proposed_depth)) - if recommendation["type"] == "loft_insulation": - if proposed_depth >= 270: - output["roof_energy_eff_ending"] = "Very Good" - else: - if output["roof_energy_eff_ending"] not in ["Good", "Very Good"]: - output["roof_energy_eff_ending"] = "Good" - else: - output["roof_energy_eff_ending"] = "Very Good" - else: - # Fill missing roof u-values - this fill is not based on recommended upgrades - if output["roof_thermal_transmittance_ending"] is None: - raise ValueError("We should not have a None value for the u value") - - if output["roof_insulation_thickness_ending"] is None: - output["roof_insulation_thickness_ending"] = "none" - if recommendation["type"] == "sealing_open_fireplace": output["number_open_fireplaces_ending"] = 0 @@ -573,12 +536,28 @@ class Property: if recommendation["type"] in [ "heating", "hot_water_tank_insulation", "heating_control", "secondary_heating", "internal_wall_insulation", "external_wall_insulation", "cavity_wall_insulation", - "cylinder_thermostat" + "cylinder_thermostat", "loft_insulation", "room_roof_insulation", "flat_roof_insulation", + "solid_floor_insulation", "suspended_floor_insulation", ]: # We update the data, as defined in the recommendaton if output["walls_insulation_thickness_ending"] is None: output["walls_insulation_thickness_ending"] = "none" + if output["walls_thermal_transmittance_ending"] is None: + raise ValueError("We should not have a None value for the u value") + + if output["roof_insulation_thickness_ending"] is None: + output["roof_insulation_thickness_ending"] = "none" + + if output["roof_thermal_transmittance_ending"] is None: + raise ValueError("We should not have a None value for the u value") + + if output["floor_thermal_transmittance_ending"] is None: + raise ValueError("We should not have a None value for the u value") + + if output["floor_insulation_thickness_ending"] is None: + output["floor_insulation_thickness_ending"] = "none" + simulation_config = recommendation["simulation_config"] # If any entries in simulation_config are None, we will set them to "Unknown" which is the cleaning # value @@ -595,7 +574,7 @@ class Property: "sealing_open_fireplace", "low_energy_lighting", "internal_wall_insulation", "external_wall_insulation", "cavity_wall_insulation", "loft_insulation", "room_roof_insulation", "flat_roof_insulation", - "solid_floor_insulation", "suspended_floor_insulation", "exposed_floor_insulation", + "solid_floor_insulation", "suspended_floor_insulation", "windows_glazing", "solar_pv", "heating", "hot_water_tank_insulation", "heating_control", "secondary_heating", "cylinder_thermostat" ]: @@ -607,17 +586,18 @@ class Property: return output - def get_components( + def set_features( self, cleaned, - energy_consumption_client + kwh_client, + kwh_predictions ): """ Given the cleaning that has been performed, we'll use this to identify the property components, from roof to walls to windows, heating and hot water :param cleaned: This is the dictionary of components found in cleaner.cleaned - :param energy_consumption_client: Contains the heating and hot water kwh models - used to predict current - energy annual consumption in kWh + :param kwh_client: The client that will be used to convert the energy costs to today's costs + :param kwh_predictions: Contains the kwh predictions for heating and hot water :return: """ @@ -682,7 +662,7 @@ class Property: self.set_windows_count() self.set_energy_source() self.find_energy_sources() - self.set_current_energy_bill(energy_consumption_client) + self.set_current_energy_bill(kwh_client, kwh_predictions) def set_solar_panel_configuration( self, solar_panel_configuration, roof_area @@ -695,7 +675,7 @@ class Property: # We also set the roof area self.roof_area = roof_area - def set_current_energy_bill(self, energy_consumption_client): + def set_current_energy_bill(self, kwh_client, kwh_predictions): """ 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 @@ -707,15 +687,7 @@ class Property: # 2) Predicted KwH # Today's costs - todays_heating_cost = energy_consumption_client.convert_cost_to_today( - original_cost=float(self.data["heating-cost-current"]), - lodgement_date=pd.Timestamp(self.epc_record.prepared_epc["lodgement_date"]).tz_localize(None) - ) - todays_hot_water_cost = energy_consumption_client.convert_cost_to_today( - original_cost=float(self.data["hot-water-cost-current"]), - lodgement_date=pd.Timestamp(self.epc_record.prepared_epc["lodgement_date"]).tz_localize(None) - ) - todays_lighting_cost = energy_consumption_client.convert_cost_to_today( + todays_lighting_cost = kwh_client.convert_cost_to_today( original_cost=float(self.data["lighting-cost-current"]), lodgement_date=pd.Timestamp(self.epc_record.prepared_epc["lodgement_date"]).tz_localize(None) ) @@ -723,97 +695,50 @@ class Property: # If we have the kwh figures, we don't need to predict them condition_data = self.energy_assessment_condition_data.copy() - scoring_df = pd.DataFrame([self.epc_record.prepared_epc]) - # Change columns from underscores to hyphens - scoring_df.columns = [ - x.lower().replace("_", "-") for x in scoring_df.columns - ] - for col in ["heating_kwh", "hot_water_kwh"]: - scoring_df[col] = None - - energy_consumption_client.data = None + heating_kwh_predictions = kwh_predictions["heating_kwh_predictions"] + hotwater_kwh_predictions = kwh_predictions["hotwater_kwh_predictions"] heating_prediction = ( - float(condition_data["space_heating_kwh"]) if condition_data.get("space_heating_kwh") is not None - else energy_consumption_client.score_new_data( - new_data=scoring_df, target="heating_kwh" - )[0] + condition_data.get("space_heating_kwh") if condition_data.get("space_heating_kwh") is not None else + heating_kwh_predictions[ + heating_kwh_predictions["id"].astype(int) == self.uprn + ]["predictions"].values[0] ) hot_water_prediction = ( - float(condition_data["water_heating_kwh"]) if condition_data.get("water_heating_kwh") is not None - else energy_consumption_client.score_new_data( - new_data=scoring_df, target="hot_water_kwh" - )[0] + condition_data.get("water_heating_kwh") if condition_data.get("water_heating_kwh") is not None else + hotwater_kwh_predictions[ + hotwater_kwh_predictions["id"].astype(int) == self.uprn + ]["predictions"].values[0] ) # We convert the lighting cost into kwh, just using the price cap - lighting_kwh = float(self.data["lighting-cost-current"]) / AnnualBillSavings.ELECTRICITY_PRICE_CAP + lighting_kwh = todays_lighting_cost / AnnualBillSavings.ELECTRICITY_PRICE_CAP appliances_kwh = AnnualBillSavings.estimate_appliances_energy_use(total_floor_area=self.floor_area) - adjusted_heating_kwh = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=heating_prediction, - current_epc_rating=self.data["current-energy-rating"], - ) + unadjusted_kwh_estimates = { + "heating": float(heating_prediction), + "hot_water": float(hot_water_prediction), + "lighting": float(lighting_kwh), + "appliances": float(appliances_kwh) + } - adjusted_hot_water_kwh = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=hot_water_prediction, - current_epc_rating=self.data["current-energy-rating"], - ) - - adjusted_lighting_kwh = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=lighting_kwh, - current_epc_rating=self.data["current-energy-rating"], - ) - - adjusted_applicances_kwh = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=appliances_kwh, - current_epc_rating=self.data["current-energy-rating"], - ) - - # Adjust today's cost figures with the UCL model - adjusted_heating_cost = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=todays_heating_cost, - current_epc_rating=self.data["current-energy-rating"], - ) - - adjusted_hot_water_cost = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=todays_hot_water_cost, - current_epc_rating=self.data["current-energy-rating"], - ) - - adjusted_lighting_cost = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=todays_lighting_cost, - current_epc_rating=self.data["current-energy-rating"], - ) - - adjusted_appliances_cost = AnnualBillSavings.adjust_energy_to_metered( - epc_energy=appliances_kwh * AnnualBillSavings.ELECTRICITY_PRICE_CAP, - current_epc_rating=self.data["current-energy-rating"], - ) + unadjusted_heating_costs = { + "heating": None, + "hot_water": None, + "lighting": float(todays_lighting_cost), + "appliances": float(appliances_kwh) * AnnualBillSavings.ELECTRICITY_PRICE_CAP + } # Sum up the adjusted kwh figures - self.current_adjusted_energy = ( - adjusted_heating_kwh + adjusted_hot_water_kwh + adjusted_lighting_kwh + adjusted_applicances_kwh - ) - self.current_energy_bill = ( - adjusted_heating_cost + adjusted_hot_water_cost + adjusted_lighting_cost + adjusted_appliances_cost + self.current_energy_consumption = sum(list(unadjusted_kwh_estimates.values())) + self.current_energy_consumption_heating_hotwater = ( + unadjusted_kwh_estimates["heating"] + unadjusted_kwh_estimates["hot_water"] ) self.energy_cost_estimates = { - "adjusted": { - "heating": adjusted_heating_cost, - "hot_water": adjusted_hot_water_cost, - "lighting": adjusted_lighting_cost, - "appliances": adjusted_appliances_cost - }, - "unadjusted": { - "heating": todays_heating_cost, - "hot_water": todays_hot_water_cost, - "lighting": todays_lighting_cost, - "appliances": appliances_kwh * AnnualBillSavings.ELECTRICITY_PRICE_CAP - }, + "unadjusted": unadjusted_heating_costs, "epc": { "heating": float(self.data["heating-cost-current"]), "hot_water": float(self.data["hot-water-cost-current"]), @@ -822,18 +747,7 @@ class Property: } self.energy_consumption_estimates = { - "adjusted": { - "heating": adjusted_heating_kwh, - "hot_water": adjusted_hot_water_kwh, - "lighting": adjusted_lighting_kwh, - "appliances": adjusted_applicances_kwh - }, - "unadjusted": { - "heating": heating_prediction, - "hot_water": hot_water_prediction, - "lighting": lighting_kwh, - "appliances": appliances_kwh - } + "unadjusted": unadjusted_kwh_estimates } def set_spatial(self, spatial: pd.DataFrame): @@ -972,7 +886,8 @@ class Property: "energy_tariff": self.data["energy-tariff"], "primary_energy_consumption": self.energy["primary_energy_consumption"], "co2_emissions": self.energy["co2_emissions"], - "adjusted_energy_consumption": self.current_adjusted_energy, + "current_energy_demand": self.current_energy_consumption, + "current_energy_demand_heating_hotwater": self.current_energy_consumption_heating_hotwater, "estimated": self.data.get("estimated", False), } @@ -1060,18 +975,22 @@ class Property: # We can update the number of floors if we have this information in the condition data self.number_of_floors = int(self.energy_assessment_condition_data["number_of_floors"]) \ - if condition_data.get("number_of_floors") is not None \ + if (condition_data.get("number_of_floors") is not None) and (self.number_of_floors is not None) \ else self.number_of_floors - self.perimeter = float(self.energy_assessment_condition_data["perimeter"]) \ - if condition_data.get("perimeter") is not None \ - else estimate_perimeter( - floor_area=self.floor_area / self.number_of_floors, - num_rooms=self.number_of_rooms / self.number_of_floors - ) + # If we already have this, we re-engineer the perimeter + if self.insulation_floor_area is not None: + self.perimeter = np.sqrt(self.insulation_floor_area) * 4 + else: + self.perimeter = float(self.energy_assessment_condition_data["perimeter"]) \ + if condition_data.get("perimeter") is not None \ + else estimate_perimeter( + floor_area=self.floor_area / self.number_of_floors, + num_rooms=self.number_of_rooms / self.number_of_floors + ) self.insulation_wall_area = float(self.energy_assessment_condition_data["insulation_wall_area"]) \ - if condition_data.get("insulation_wall_area") is not None \ + if (condition_data.get("insulation_wall_area") is not None) and (self.insulation_wall_area is not None) \ else estimate_external_wall_area( num_floors=self.number_of_floors, floor_height=self.floor_height, @@ -1079,9 +998,12 @@ class Property: built_form=self.data["built-form"], ) - self.insulation_floor_area = float(self.energy_assessment_condition_data["main_dwelling_ground_floor_area"]) \ - if condition_data.get("main_dwelling_ground_floor_area") is not None \ - else self.floor_area / self.number_of_floors + if self.insulation_floor_area is None: + self.insulation_floor_area = float( + self.energy_assessment_condition_data["main_dwelling_ground_floor_area"] + ) if (condition_data.get("main_dwelling_ground_floor_area") is not None) else ( + self.floor_area / self.number_of_floors + ) def set_floor_level(self): self.floor_level = ( @@ -1163,16 +1085,6 @@ class Property: return component_data - def set_adjusted_energy( - self, expected_adjusted_energy, expected_energy_bill - ): - """ - Stores these values for usage later - """ - - self.expected_adjusted_energy = expected_adjusted_energy - self.expected_energy_bill = expected_energy_bill - def set_windows_count(self): """ Using the estimate_windows function, this method will set the number of windows in the property @@ -1237,7 +1149,9 @@ class Property: 'has_exhaust_source_heat_pump': 'Electricity', 'has_community_heat_pump': 'Electricity', 'has_wood_pellets': 'Wood Pellets', - 'has_community_scheme': 'Varied (Community Scheme)' + 'has_community_scheme': 'Varied (Community Scheme)', + "has_dual_fuel_mineral_and_wood": 'Wood Logs', + "has_electricaire": 'Electricity', } # Hot water @@ -1263,20 +1177,57 @@ class Property: 'community scheme': 'Community Scheme' } - self.heating_energy_source = [ + self.heating_energy_source = list({ fuel for key, fuel in heating_fuel_mapping.items() if self.main_heating.get(key, False) - ] + }) + + if set(self.heating_energy_source) == {'Electricity', 'Natural Gas'}: + # It means they have mixed heating so we take the primary one, based on main fuel + # This will probably happen in the case of an extension + if self.main_fuel["clean_description"] in ["Mains gas not community", "Mains gas community"]: + self.heating_energy_source = ['Natural Gas'] + else: + self.heating_energy_source = ['Electricity'] + + if set(self.heating_energy_source) == {'Natural Gas', 'Wood Logs'}: + # It means they have mixed heating so we take the primary one, based on main fuel + # This will probably happen in the case of an extension + if self.main_fuel["clean_description"] in ["Mains gas not community", "Mains gas community"]: + self.heating_energy_source = ['Natural Gas'] + else: + self.heating_energy_source = ['Wood Logs'] + if len(self.heating_energy_source) == 0 or len(self.heating_energy_source) > 1: - raise Exception("Investigate em") + raise Exception("Investigate me") self.heating_energy_source = self.heating_energy_source[0] + if self.heating_energy_source == "Varied (Community Scheme)": + if self.main_fuel["fuel_type"] == "mains gas": + self.heating_energy_source = "Natural Gas (Community Scheme)" + else: + raise Exception("Implement me") + if self.hotwater["heater_type"] is not None: self.hot_water_energy_source = heater_type_to_fuel[self.hotwater["heater_type"]] + + if self.hotwater["extra_features"] == "plus solar": + self.hot_water_energy_source = self.heating_energy_source + " + Solar Thermal" + return + else: fuel = system_type_modification[self.hotwater["system_type"]] - if fuel == 'Main System': + + if self.hotwater["extra_features"] == "plus solar": + self.hot_water_energy_source = self.heating_energy_source + " + Solar Thermal" + return + + if fuel in ['Main System', "Community Scheme"]: self.hot_water_energy_source = self.heating_energy_source + elif fuel in ['Secondary System']: + # Check the secondary heating system + secondary_heating = self.data["secondheat-description"] + self.hot_water_energy_source = assumptions.DESCRIPTIONS_TO_FUEL_TYPES[secondary_heating]["fuel"] else: raise Exception("Investiage me") @@ -1329,29 +1280,39 @@ class Property: exclusions = [] if exclusions is None else exclusions - if (self.main_fuel["fuel_type"] == "electricity") or ( - self.main_fuel["fuel_type"] == "mains gas" and not self.is_ashp_valid(exclusions=exclusions) + # If the property currently has an ASHP, we don't gain from any efficiency improvements + if not self.is_ashp_valid(exclusions=exclusions): + return self.current_energy_consumption + + # If the property currently has an electric boiler, it will still benefit from the ASHP efficiency gain + remap_fuel_sources = [ + "Natural Gas", "LPG", "Wood Logs", "Oil", "Electricity", "Coal", "Smokeless Fuel", + "Natural Gas + Solar Thermal", "Anthracite", "Wood Pellets", "LPG + Solar Thermal" + ] + + heating_energy_source = self.heating_energy_source + hot_water_energy_source = self.hot_water_energy_source + heating_consumption = self.energy_consumption_estimates["unadjusted"]["heating"] + hotwater_consumption = self.energy_consumption_estimates["unadjusted"]["hot_water"] + + if (heating_energy_source not in remap_fuel_sources) or ( + hot_water_energy_source not in remap_fuel_sources + ["Electricity + Solar Thermal"] ): - # if the primary fuel is already electricity, we don't need to adjust the consumpion - return self.current_adjusted_energy + raise NotImplementedError("Have not implemented estimating electrical consumption for this fuel type") - if self.main_fuel["fuel_type"] == "mains gas" and self.is_ashp_valid(exclusions=exclusions): - # if the primary fuel is gas, we need to adjust the consumption to reflect the expected - # efficiency of an ASHP. - # We should adjust the energy consumption to reflect the 200-400% efficiency of an ASHP with - # electrified heating, so that the solar panel can cover heating generation. - heating_consumption = self.energy_consumption_estimates["adjusted"]["heating"] - hot_water_consumption = self.energy_consumption_estimates["adjusted"]["hot_water"] + if heating_energy_source in remap_fuel_sources: + # Adjust the heating consumption to reflect the expected efficiency of an ASHP + heating_consumption = heating_consumption / (assumed_ashp_efficiency / 100) - systems_consumptions = heating_consumption + hot_water_consumption + if hot_water_energy_source in remap_fuel_sources: + # Adjust the hot water consumption to reflect the expected efficiency of an ASHP + hotwater_consumption = hotwater_consumption / (assumed_ashp_efficiency / 100) - adjusted_consumption = systems_consumptions / (assumed_ashp_efficiency / 100) - electric_consumption = ( - adjusted_consumption + - self.energy_consumption_estimates["adjusted"]["lighting"] + - self.energy_consumption_estimates["adjusted"]["appliances"] - ) + electric_consumption = ( + heating_consumption + + hotwater_consumption + + self.energy_consumption_estimates["unadjusted"]["lighting"] + + self.energy_consumption_estimates["unadjusted"]["appliances"] + ) - return electric_consumption - - raise NotImplementedError("Have not implemented estimating electrical consumption for this fuel type") + return electric_consumption diff --git a/backend/SearchEpc.py b/backend/SearchEpc.py index 37c2b7f9..5f101d81 100644 --- a/backend/SearchEpc.py +++ b/backend/SearchEpc.py @@ -292,8 +292,7 @@ class SearchEpc: "error": str(e) } - @staticmethod - def filter_rows(rows, property_type=None, address=None): + def filter_rows(self, rows, property_type=None, address=None): """ This method should not be used when property_type and address are both not None :param rows: @@ -321,8 +320,21 @@ class SearchEpc: if address is not None: # We can do a filter on the property type - best_match = process.extractOne(address, [r["address"] for r in rows], score_cutoff=0) - rows_filtered = [r for r in rows if r["address"] == best_match[0]] + # We check if the full address contains the postcode and if it does, remove + if self.postcode in address: + address = address.replace(self.postcode, "").strip().rstrip(",") + + # We check if post town is included in the address + if any([r["posttown"].lower() in address.lower() for r in rows]): + best_match = process.extractOne( + address, [", ".join([r["address"], r["posttown"]]) for r in rows], score_cutoff=0 + ) + # Get all of the scores + rows_filtered = [r for r in rows if ", ".join([r["address"], r["posttown"]]) == best_match[0]] + else: + best_match = process.extractOne(address, [r["address"] for r in rows], score_cutoff=0) + # Get all of the scores + rows_filtered = [r for r in rows if r["address"] == best_match[0]] if rows_filtered: return rows_filtered diff --git a/backend/apis/GoogleSolarApi.py b/backend/apis/GoogleSolarApi.py index 1354bbff..41ec7c11 100644 --- a/backend/apis/GoogleSolarApi.py +++ b/backend/apis/GoogleSolarApi.py @@ -17,10 +17,6 @@ logger = setup_logger() class GoogleSolarApi: NORTH_FACING_AZIMUTH_RANGE = (-30, 30) - # Conservative estimate of the proportion of electricity that will be consumed, whereas the rest will - # 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 @@ -152,7 +148,7 @@ class GoogleSolarApi: # Extract key data from the insights response self.roof_segments = self.insights_data["solarPotential"].get('roofSegmentStats', []) # Automatically exclude north-facing segments - self.exclude_north_facing_segments() + self.exclude_north_facing_segments(property_instance=property_instance) # If a property is semi-detached, it's possible for us to include segments from an attached unit if (property_instance.data["built-form"] == "Semi-Detached") and ( property_instance.data["extension-count"] == 0 @@ -262,7 +258,7 @@ class GoogleSolarApi: # Remove any north facing roof segments panel_performance = [] - for config in self.insights_data["solarPotential"]["solarPanelConfigs"]: + for config in self.insights_data["solarPotential"].get("solarPanelConfigs", []): roof_segment_summaries = config["roofSegmentSummaries"] # Filter on just the segments in self.roof_segment_indexes roof_segment_summaries = [ @@ -295,6 +291,8 @@ class GoogleSolarApi: ) roi_summary = pd.DataFrame(roi_summary) + if roi_summary.empty: + continue weighted_ratio = np.average( roi_summary["ratio"].values, weights=roi_summary["generated_dc_energy"].values @@ -314,13 +312,49 @@ class GoogleSolarApi: ) panel_performance = pd.DataFrame(panel_performance) - # We can have duplicate configurations + + if panel_performance.empty: + self.panel_performance = pd.DataFrame( + columns=[ + "n_panels", + "yearly_dc_energy", + "total_cost", + "panneled_roof_area", + "array_wattage", + "initial_ac_kwh_per_year", + "lifetime_ac_kwh", + "roi", + "expected_payback_years", + "lifetime_dc_kwh" + ] + ) + return + + # We can have duplicate configurations + panel_performance = panel_performance.drop_duplicates() # If we look at the building level, we don't include any projects fewer than 10 panels, otherwise the # minimum is 4 min_panels = 10 if is_building else 4 panel_performance = panel_performance[panel_performance["n_panels"] >= min_panels] + if panel_performance.empty: + self.panel_performance = pd.DataFrame( + columns=[ + "n_panels", + "yearly_dc_energy", + "total_cost", + "panneled_roof_area", + "array_wattage", + "initial_ac_kwh_per_year", + "lifetime_ac_kwh", + "roi", + "expected_payback_years", + "lifetime_dc_kwh" + ] + ) + return + panel_performance["initial_ac_kwh_per_year"] = panel_performance["yearly_dc_energy"] * self.dc_to_ac_rate # Remove anything where the total ac energy is less than half of the array wattage @@ -455,7 +489,7 @@ class GoogleSolarApi: self.panel_performance = panel_performance - def exclude_north_facing_segments(self): + def exclude_north_facing_segments(self, property_instance): """ Filter out any north-facing roof segments from the roof_segments attribute. @@ -466,7 +500,9 @@ class GoogleSolarApi: for segment_index, segment in enumerate(self.roof_segments): segment["segmentIndex"] = segment_index # Check if the segment is north-facing - if self.NORTH_FACING_AZIMUTH_RANGE[0] <= segment['azimuthDegrees'] <= self.NORTH_FACING_AZIMUTH_RANGE[1]: + if ( + self.NORTH_FACING_AZIMUTH_RANGE[0] <= segment['azimuthDegrees'] <= self.NORTH_FACING_AZIMUTH_RANGE[1] + ) and not property_instance.roof["is_flat"]: continue filtered_segments.append(segment) diff --git a/backend/app/assumptions.py b/backend/app/assumptions.py index 13bd913f..5f8cb85c 100644 --- a/backend/app/assumptions.py +++ b/backend/app/assumptions.py @@ -1,3 +1,44 @@ -# Assumes that the average efficiency of an air source heat pump is 300%, taking the median of the 200-400% range, +# Assumes that the average efficiency of an air source heat pump is 250%, taking the median of the 200-400% range, # which is often quoted as a sensible efficiency range for air source heat pumps. +PESSIMISTIC_ASHP_EFFICIENCY = 200 AVERAGE_ASHP_EFFICIENCY = 300 + +# Conservative estimate of the proportion of electricity that will be consumed, whereas the rest will +# be exported +SOLAR_CONSUMPTION_PROPORTION = 0.5 + +DESCRIPTIONS_TO_FUEL_TYPES = { + "Air source heat pump, radiators, electric": { + "fuel": "Electricity", "cop": AVERAGE_ASHP_EFFICIENCY / 100 + }, + "Boiler and radiators, mains gas": {"fuel": 'Natural Gas', "cop": 0.9}, + 'Electric storage heaters': {"fuel": 'Electricity', "cop": 1}, + "Electric immersion, off-peak": {"fuel": 'Electricity', "cop": 1}, + "Electric storage heaters, radiators": {"fuel": 'Electricity', "cop": 1}, + "Room heaters, electric": {"fuel": 'Electricity', "cop": 1}, + "Electric immersion, standard tariff": {"fuel": 'Electricity', "cop": 1}, + "Portable electric heaters assumed for most rooms": {"fuel": 'Electricity', "cop": 1}, + "Boiler and radiators, LPG": {"fuel": 'LPG', "cop": 0.9}, + "Room heaters, dual fuel (mineral and wood)": {"fuel": 'Wood Logs', "cop": 1}, + "Room heaters, mains gas": {"fuel": 'Natural Gas', "cop": 0.9}, + "Warm air, mains gas": {"fuel": 'Natural Gas', "cop": 0.9}, + "Boiler, mains gas": {"fuel": 'Natural Gas', "cop": 0.9}, + "Gas multipoint": {"fuel": "Natural Gas", "cop": 0.9}, + "Warm air, Electricaire": {"fuel": "Electricity", "cop": 1}, + "Gas boiler/circulator": {"fuel": "Natural Gas", "cop": 0.9}, + "Boiler and underfloor heating, mains gas": {"fuel": "Natural Gas", "cop": 0.9}, + "No system present: electric heaters assumed": {"fuel": "Electricity", "cop": 1}, + "Electric instantaneous at point of use": {"fuel": "Electricity", "cop": 1}, + "Boiler and radiators, oil": {"fuel": "Oil", "cop": 0.9}, + "Electric storage heaters, Electric storage heaters": {"fuel": "Electricity", "cop": 1}, + "Boiler and radiators, electric": {"fuel": "Electricity", "cop": 0.9}, + "Gas boiler/circulator, no cylinder thermostat": {"fuel": "Natural Gas", "cop": 0.9}, + "Boiler and radiators, dual fuel (mineral and wood)": {"fuel": "Wood Logs", "cop": 0.9}, + "Electric immersion, standard tariff, plus solar": {"fuel": "Electricity + Solar Thermal", "cop": 1}, + "From main system, flue gas heat recovery": {"fuel": "Natural Gas", "cop": 0.9}, + "Electric underfloor heating": {"fuel": "Electricity", "cop": 1}, + "No system present: electric immersion assumed": {"fuel": "Electricity", "cop": 1}, + "Air source heat pump, underfloor, electric": { + "fuel": "Electricity", "cop": AVERAGE_ASHP_EFFICIENCY / 100 + }, +} diff --git a/backend/app/config.py b/backend/app/config.py index f80da387..b5ea72fe 100644 --- a/backend/app/config.py +++ b/backend/app/config.py @@ -30,6 +30,8 @@ class Settings(BaseSettings): LIGHTING_COST_PREDICTIONS_BUCKET: str HEATING_COST_PREDICTIONS_BUCKET: str HOT_WATER_COST_PREDICTIONS_BUCKET: str + HEATING_KWH_PREDICTIONS_BUCKET: str + HOTWATER_KWH_PREDICTIONS_BUCKET: str class Config: env_file = "backend/.env" @@ -48,5 +50,7 @@ def get_prediction_buckets(): "carbon_change_predictions": get_settings().CARBON_PREDICTIONS_BUCKET, "lighting_cost_predictions": get_settings().LIGHTING_COST_PREDICTIONS_BUCKET, "heating_cost_predictions": get_settings().HEATING_COST_PREDICTIONS_BUCKET, - "hot_water_cost_predictions": get_settings().HOT_WATER_COST_PREDICTIONS_BUCKET + "hot_water_cost_predictions": get_settings().HOT_WATER_COST_PREDICTIONS_BUCKET, + "heating_kwh_predictions": get_settings().HEATING_KWH_PREDICTIONS_BUCKET, + "hotwater_kwh_predictions": get_settings().HOTWATER_KWH_PREDICTIONS_BUCKET, } diff --git a/backend/app/db/models/portfolio.py b/backend/app/db/models/portfolio.py index aa0146c0..7580a27d 100644 --- a/backend/app/db/models/portfolio.py +++ b/backend/app/db/models/portfolio.py @@ -3,6 +3,7 @@ import pytz import datetime from sqlalchemy import Column, Integer, Text, Boolean, Float, DateTime, Enum, ForeignKey, CheckConstraint from sqlalchemy.ext.declarative import declarative_base +from backend.app.db.models.users import UserModel # noqa Base = declarative_base() @@ -168,7 +169,8 @@ class PropertyDetailsEpcModel(Base): energy_tariff = Column(Text) primary_energy_consumption = Column(Float) co2_emissions = Column(Float) - adjusted_energy_consumption = Column(Float) + current_energy_demand = Column(Float) + current_energy_demand_heating_hotwater = Column(Float) estimated = Column(Boolean, default=False) @@ -204,3 +206,13 @@ class PropertyTargetsModel(Base): created_at = Column(DateTime, nullable=False, default=datetime.datetime.now(pytz.utc)) epc = Column(Enum(Epc)) heat_demand = Column(Text) + + +class PortfolioUsers(Base): + __tablename__ = "portfolioUsers" + id = Column(Integer, primary_key=True, autoincrement=True) + user_id = Column(Integer, ForeignKey('user.id'), nullable=False) + portfolioId = Column(Integer, ForeignKey('portfolio.id'), nullable=False) + role = Column(Text, 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)) diff --git a/backend/app/plan/router.py b/backend/app/plan/router.py index 7e14b61f..e773e303 100644 --- a/backend/app/plan/router.py +++ b/backend/app/plan/router.py @@ -20,7 +20,7 @@ from backend.app.db.functions.property_functions import ( update_or_create_property_spatial_details ) from backend.app.db.functions.recommendations_functions import ( - create_plan, create_plan_recommendations, upload_recommendations, create_scenario + create_plan, upload_recommendations, create_scenario ) from backend.app.db.functions.energy_assessment_functions import get_latest_assessment_by_uprn from backend.app.db.models.portfolio import rating_lookup @@ -30,9 +30,9 @@ from backend.app.plan.utils import get_cleaned from backend.app.utils import epc_to_sap_lower_bound, sap_to_epc from backend.ml_models.api import ModelApi +from backend.ml_models.AnnualBillSavings import AnnualBillSavings from backend.Property import Property from backend.apis.GoogleSolarApi import GoogleSolarApi -from etl.solar.SolarPhotoSupply import SolarPhotoSupply from recommendations.optimiser.CostOptimiser import CostOptimiser from recommendations.optimiser.GainOptimiser import GainOptimiser @@ -42,7 +42,11 @@ from recommendations.Mds import Mds from utils.logger import setup_logger from utils.s3 import read_dataframe_from_s3_parquet, read_csv_from_s3 from backend.ml_models.Valuation import PropertyValuation + from etl.bill_savings.EnergyConsumptionModel import EnergyConsumptionModel +from etl.bill_savings.KwhData import KwhData +from etl.spatial.OpenUprnClient import OpenUprnClient +from etl.solar.SolarPhotoSupply import SolarPhotoSupply logger = setup_logger() @@ -129,8 +133,8 @@ def extract_portfolio_aggregation_data( [r["energy_cost_savings"] for r in default_recommendations] ) - pre_retrofit_energy_consumption = p.current_adjusted_energy - post_retrofit_energy_consumption = p.current_adjusted_energy - sum( + pre_retrofit_energy_consumption = p.current_energy_consumption + post_retrofit_energy_consumption = p.current_energy_consumption - sum( [r["kwh_savings"] for r in default_recommendations] ) @@ -244,8 +248,8 @@ def create_epc_records(epc_searcher: SearchEpc, energy_assessment: dict): # We insert county into the epc, since right now this isn't something that we pull out from the energy # assessment - epc["county"] = epc_searcher.newest_epc["county"] - epc["constituency"] = epc_searcher.newest_epc["constituency"] + for col in ["county", "constituency", "constituency-label", "local-authority", "local-authority-label"]: + epc[col] = epc_searcher.newest_epc[col] # We check if the energy assessment is newer than the newest EPC if pd.to_datetime(energy_assessment_date) > pd.to_datetime(epc_searcher.newest_epc["inspection-date"]): @@ -283,6 +287,80 @@ def create_epc_records(epc_searcher: SearchEpc, energy_assessment: dict): }, energy_assessment_is_newer +def get_on_site_data(body: PlanTriggerRequest): + """ + This function will read in the on-site data from the S3 bucket + :param body: The request body + :return: + """ + patches = [] + if body.patches_file_path: + patches = read_csv_from_s3(bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.patches_file_path) + + already_installed = [] + if body.already_installed_file_path: + already_installed = read_csv_from_s3( + bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.already_installed_file_path + ) + + non_invasive_recommendations = [] + if body.non_invasive_recommendations_file_path: + non_invasive_recommendations = read_csv_from_s3( + bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.non_invasive_recommendations_file_path + ) + + return patches, already_installed, non_invasive_recommendations + + +def extract_property_on_site_recommendations(config, patches, already_installed, non_invasive_recommendations, uprn): + patch_has_uprn = "uprn" in patches[0] if patches else True + if patch_has_uprn: + patch = next(( + x for x in patches if str(x["uprn"]) == str(config["uprn"]) + ), {}) + else: + patch = next(( + x for x in patches if (x["address"] == config["address"]) and (x["postcode"] == config["postcode"]) + ), {}) + + property_already_installed = next(( + x for x in already_installed if + (x["address"] == config["address"]) and (x["postcode"] == config["postcode"]) + ), {}) + + # Because we have some non-invasive recommendations that match on address and postcode, but not UPRN + # we need to check existence of uprn + has_uprn = "uprn" in non_invasive_recommendations[0] if non_invasive_recommendations else True + if has_uprn: + property_non_invasive_recommendations = next(( + x for x in non_invasive_recommendations if + (str(x["uprn"]) == str(uprn)) + ), {}) + + # We patch the non-invasive recs that are ['cavity_extract_and_refill'] + else: + property_non_invasive_recommendations = next(( + x for x in non_invasive_recommendations if + (x["address"] == config["address"]) and (x["postcode"] == config["postcode"]) + ), {}) + + if isinstance(property_non_invasive_recommendations.get("recommendations"), str): + import ast + property_non_invasive_recommendations["recommendations"] = ast.literal_eval( + property_non_invasive_recommendations["recommendations"] + ) + transformed = [] + for rec in property_non_invasive_recommendations["recommendations"]: + if isinstance(rec, str): + transformed.append({"type": rec, }) + else: + transformed.append(rec) + + property_non_invasive_recommendations["recommendations"] = str(transformed) + + return patch, property_already_installed, property_non_invasive_recommendations + + router = APIRouter( prefix="/plan", tags=["plan"], @@ -304,21 +382,7 @@ async def trigger_plan(body: PlanTriggerRequest): logger.info("Getting the inputs") plan_input = read_csv_from_s3(bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.trigger_file_path) # If we have patches or overrides, we should read them in here - patches = [] - if body.patches_file_path: - patches = read_csv_from_s3(bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.patches_file_path) - - already_installed = [] - if body.already_installed_file_path: - already_installed = read_csv_from_s3( - bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.already_installed_file_path - ) - - non_invasive_recommendations = [] - if body.non_invasive_recommendations_file_path: - non_invasive_recommendations = read_csv_from_s3( - bucket_name=get_settings().PLAN_TRIGGER_BUCKET, filepath=body.non_invasive_recommendations_file_path - ) + patches, already_installed, non_invasive_recommendations = get_on_site_data(body) cleaning_data = read_dataframe_from_s3_parquet( bucket_name=get_settings().DATA_BUCKET, file_key="sap_change_model/cleaning_dataset.parquet", @@ -326,7 +390,6 @@ async def trigger_plan(body: PlanTriggerRequest): input_properties = [] for config in tqdm(plan_input): - # We validate each record in the file. If the record is NOT valid, we need to handle this accordingly uprn = config.get("uprn", None) if uprn: @@ -370,9 +433,13 @@ async def trigger_plan(body: PlanTriggerRequest): epc_records, energy_assessment["energy_assessment_is_newer"] = create_epc_records( epc_searcher, energy_assessment ) - patch = next(( - x for x in patches if (x["address"] == config["address"]) and (x["postcode"] == config["postcode"]) - ), {}) + + patch, property_already_installed, property_non_invasive_recommendations = ( + extract_property_on_site_recommendations( + config, patches, already_installed, non_invasive_recommendations, uprn + ) + ) + epc_records = patch_epc(patch, epc_records) prepared_epc = EPCRecord( @@ -381,16 +448,6 @@ async def trigger_plan(body: PlanTriggerRequest): cleaning_data=cleaning_data ) - property_already_installed = next(( - x for x in already_installed if - (x["address"] == config["address"]) and (x["postcode"] == config["postcode"]) - ), {}) - - property_non_invasive_recommendations = next(( - x for x in non_invasive_recommendations if - (x["address"] == config["address"]) and (x["postcode"] == config["postcode"]) - ), {}) - input_properties.append( Property( id=property_id, @@ -415,11 +472,6 @@ async def trigger_plan(body: PlanTriggerRequest): materials = get_materials(session) cleaned = get_cleaned() - uprn_filenames = read_dataframe_from_s3_parquet( - bucket_name=get_settings().DATA_BUCKET, file_key="spatial/filename_meta.parquet" - ) - solar_api_client = GoogleSolarApi(api_key=get_settings().GOOGLE_SOLAR_API_KEY) - dataset_version = "2024-07-08" energy_consumption_client = EnergyConsumptionModel( model_paths={ @@ -432,18 +484,38 @@ async def trigger_plan(body: PlanTriggerRequest): environment=get_settings().ENVIRONMENT ) - logger.info("Getting spatial data") - for p in input_properties: - p.get_components(cleaned=cleaned, energy_consumption_client=energy_consumption_client) - p.get_spatial_data(uprn_filenames) + kwh_client = KwhData(bucket=get_settings().DATA_BUCKET, read_consumption_data=True) + model_api = ModelApi( + portfolio_id=body.portfolio_id, + timestamp=created_at, + prediction_buckets=get_prediction_buckets() + ) + + epcs_for_scoring = kwh_client.transform(data=kwh_client.prepare_epc(input_properties), cleaned=cleaned) + + kwh_preds = model_api.paginated_predictions( + data=epcs_for_scoring, + bucket=get_settings().DATA_BUCKET, + model_prefixes=["heating_kwh_predictions", "hotwater_kwh_predictions"], + extract_ids=False, + batch_size=SCORING_BATCH_SIZE + ) + + # Insert the spatial data + logger.info("Getting spatial data") + input_properties = OpenUprnClient.set_spatial_data(input_properties, bucket_name=get_settings().DATA_BUCKET) + + [p.set_features(cleaned=cleaned, kwh_client=kwh_client, kwh_predictions=kwh_preds) for p in input_properties] logger.info("Performing solar analysis") + # TODO: Tidy this up # TODO: If a property is semi-detached, we might get roof surfaces for the main building + the neighbour # TODO: If we can't get high image quality, should we use the solar API? Maybe just for semi-detached units with # extensions, since it doesn't seem to do a great job # TODO: For simple properties, we should do a comparison/check between the solar API's roof area and the # basic estimate of roof area + building_ids = [ { "building_id": p.building_id, @@ -514,6 +586,7 @@ async def trigger_plan(body: PlanTriggerRequest): energy_consumption = sum( [entry['energy_consumption'] for entry in building_ids if entry['building_id'] == building_id] ) + solar_api_client = GoogleSolarApi(api_key=get_settings().GOOGLE_SOLAR_API_KEY) solar_api_client.get( longitude=coordinates["longitude"], latitude=coordinates["latitude"], @@ -528,7 +601,8 @@ async def trigger_plan(body: PlanTriggerRequest): } # Store the data in the database - # TODO: Rather than just doing a straight insert, we should overwrite what's already there if it exists + # TODO: Rather than just doing a straight insert, we should overwrite what's already there if it + # exists solar_api_client.save_to_db( session=session, uprns_to_location=building_uprns[building_id], scenario_type="building" ) @@ -543,15 +617,18 @@ async def trigger_plan(body: PlanTriggerRequest): energy_consumption ) p.set_solar_panel_configuration(unit_solar_panel_configuration) - if individual_units: # Model the solar potential at the property level - for unit in individual_units: + for unit in tqdm(individual_units): property_instance = [p for p in input_properties if p.id == unit["property_id"]][0] # At this level, we check if the property is suitable for solar and if now, skip if not property_instance.is_solar_pv_valid(): continue + # We check if we have a solar non-invasive recommendation + if [r for r in property_instance.non_invasive_recommendations if r["type"] == "solar_pv"]: + continue + solar_api_client = GoogleSolarApi(api_key=get_settings().GOOGLE_SOLAR_API_KEY) solar_api_client.get( longitude=unit["longitude"], latitude=unit["latitude"], @@ -563,7 +640,8 @@ async def trigger_plan(body: PlanTriggerRequest): ) # Store the data in the database - # TODO: Rather than just doing a straight insert, we should overwrite what's already there if it exists + # TODO: Rather than just doing a straight insert, we should overwrite what's already there if it + # exists solar_api_client.save_to_db( session=session, uprns_to_location=[ @@ -585,12 +663,11 @@ async def trigger_plan(body: PlanTriggerRequest): roof_area=solar_api_client.roof_area ) - logger.info("Getting components and epc recommendations") + logger.info("Identifying property recommendations") recommendations = {} recommendations_scoring_data = [] representative_recommendations = {} for p in tqdm(input_properties): - recommender = Recommendations(property_instance=p, materials=materials, exclusions=body.exclusions) property_recommendations, property_representative_recommendations = recommender.recommend() @@ -608,7 +685,6 @@ async def trigger_plan(body: PlanTriggerRequest): recommendations_scoring_data.extend(p.recommendations_scoring_data) # TODO: Make sure that number_habitable_rooms has been dropped - logger.info("Preparing data for scoring in sap change api") recommendations_scoring_data = pd.DataFrame(recommendations_scoring_data) @@ -617,54 +693,69 @@ async def trigger_plan(body: PlanTriggerRequest): "carbon_ending"] ) - model_api = ModelApi(portfolio_id=body.portfolio_id, timestamp=created_at) + all_predictions = model_api.paginated_predictions( + data=recommendations_scoring_data, + bucket=get_settings().DATA_BUCKET, + batch_size=SCORING_BATCH_SIZE + ) - all_predictions = model_api.predictions_template() - to_loop_over = range(0, recommendations_scoring_data.shape[0], SCORING_BATCH_SIZE) - for chunk in tqdm(to_loop_over, total=len(to_loop_over)): - predictions_dict = model_api.predict_all( - df=recommendations_scoring_data.iloc[chunk:chunk + SCORING_BATCH_SIZE], - bucket=get_settings().DATA_BUCKET, - prediction_buckets=get_prediction_buckets() + # Insert the predictions into the recommendations, and get the impact summary + scoring_epcs = [] # For scoring the kwh models + for property_id in recommendations.keys(): + property_instance = [p for p in input_properties if p.id == property_id][0] + + recommendations_with_impact, impact_summary = ( + Recommendations.calculate_recommendation_impact( + property_instance=property_instance, + all_predictions=all_predictions, + recommendations=recommendations, + ) ) - # Append the predictions to the predictions dictionary - for key, scored in predictions_dict.items(): - all_predictions[key] = pd.concat([all_predictions[key], scored]) + # We use the impact_summary to update the simulation_epcs with the new SAP, heat demand, carbon, cost etc + # at each phase + property_instance.update_simulation_epcs(impact_summary) + scoring_epcs.extend(property_instance.updated_simulation_epcs) + recommendations[property_id] = recommendations_with_impact + + # We call the API with the scoring epcs + scoring_epcs = pd.DataFrame(scoring_epcs) + scoring_epcs = kwh_client.transform(data=scoring_epcs, cleaned=cleaned) + + kwh_simulation_predictions = model_api.paginated_predictions( + data=scoring_epcs, + bucket=get_settings().DATA_BUCKET, + model_prefixes=["heating_kwh_predictions", "hotwater_kwh_predictions"], + batch_size=SCORING_BATCH_SIZE + ) + + # We now insert kwh estimates and costs into the recommendations + # TODO: We should join the methodology which maps the heating and hot water descriptions to the fuel types in + # Recommendations, but also the Property class + logger.info("Calculating tenant savings - kwh and bills") + for property_id in tqdm([p.id for p in input_properties]): + property_recommendations = recommendations.get(property_id, []) + property_instance = [p for p in input_properties if p.id == property_id][0] + + property_current_energy_bill = Recommendations.calculate_recommendation_tenant_savings( + property_instance=property_instance, + kwh_simulation_predictions=kwh_simulation_predictions, + property_recommendations=property_recommendations + ) + property_instance.current_energy_bill = property_current_energy_bill # Insert the predictions into the recommendations and run the optimiser # TODO: If a recommendation has a negative impact on SAP, we should remove it - this seems to have become a # possibility with heating system # TODO: After optimising, if there are any cheap, quick win measures (e.g. insulate water tank with hot water # cylinder jacket), we should add these to the recommendations as default - logger.info("Optimising recommendations") - for property_id in recommendations.keys(): - property_instance = [p for p in input_properties if p.id == property_id][0] + for p in input_properties: + if not recommendations.get(p.id): + continue + input_measures = prepare_input_measures(recommendations[p.id], body.goal) - ( - recommendations_with_impact, - expected_adjusted_energy, - expected_energy_bill - ) = ( - Recommendations.calculate_recommendation_impact( - property_instance=property_instance, - all_predictions=all_predictions, - recommendations=recommendations, - representative_recommendations=representative_recommendations, - energy_consumption_client=energy_consumption_client - ) - ) - - # Store the resulting adjusted energy in the property instance - property_instance.set_adjusted_energy( - expected_adjusted_energy=expected_adjusted_energy, - expected_energy_bill=expected_energy_bill - ) - - input_measures = prepare_input_measures(recommendations_with_impact, body.goal) - - current_sap_points = int(property_instance.data["current-energy-efficiency"]) + current_sap_points = int(p.data["current-energy-efficiency"]) target_sap_points = epc_to_sap_lower_bound(body.goal_value) sap_gain = CostOptimiser.calculate_sap_gain_with_slack(target_sap_points - current_sap_points) @@ -691,7 +782,7 @@ async def trigger_plan(body: PlanTriggerRequest): "internal_wall_insulation", "external_wall_insulation", "cavity_wall_insulation" ]): ventilation_rec = next( - (r[0] for r in recommendations_with_impact if r[0]["type"] == "mechanical_ventilation"), + (r[0] for r in recommendations[p.id] if r[0]["type"] == "mechanical_ventilation"), None ) @@ -705,29 +796,14 @@ async def trigger_plan(body: PlanTriggerRequest): {**rec, "default": True if rec["recommendation_id"] in selected_recommendations else False} for rec in recommendations_by_type ] - for recommendations_by_type in recommendations_with_impact + for recommendations_by_type in recommendations[p.id] ] # We'll also unlist the recommendations so they're a bit easier to handle from here onwards final_recommendations = [ rec for recommendations_by_type in final_recommendations for rec in recommendations_by_type ] - recommendations[property_id] = final_recommendations - - # df = [] - # for rec in recommendations[list(recommendations.keys())[0]]: - # df.append( - # { - # "id": rec["recommendation_id"], - # "description": rec["description"], - # "sap": rec["sap_points"], - # } - # ) - # df = pd.DataFrame(df) - - # 1) the property data - # 2) the property details (epc) - # 3) the recommendations + recommendations[p.id] = final_recommendations logger.info("Uploading recommendations to the database") # If we have any work to do, we create a new scenario @@ -1001,7 +1077,7 @@ async def build_mds(body: MdsRequest): recommendations = {} for p in tqdm(input_properties): - p.get_components(cleaned, photo_supply_lookup, floor_area_decile_thresholds) + p.set_features(cleaned, photo_supply_lookup, floor_area_decile_thresholds) mds = Mds(property_instance=p, materials=materials, optimise_measures=optimise_measures) mds_recommendations, property_representative_recommendations, errors = mds.build() @@ -1050,7 +1126,9 @@ async def build_mds(body: MdsRequest): "carbon_ending"] ) - model_api = ModelApi(portfolio_id=body.portfolio_id, timestamp=created_at) + model_api = ModelApi( + portfolio_id=body.portfolio_id, timestamp=created_at, prediction_buckets=get_prediction_buckets() + ) all_predictions = { "sap_change_predictions": pd.DataFrame(), @@ -1061,12 +1139,6 @@ async def build_mds(body: MdsRequest): for chunk in tqdm(to_loop_over, total=len(to_loop_over)): predictions_dict = model_api.predict_all( df=recommendations_scoring_data.iloc[chunk:chunk + SCORING_BATCH_SIZE], - bucket=get_settings().DATA_BUCKET, - prediction_buckets={ - "sap_change_predictions": get_settings().SAP_PREDICTIONS_BUCKET, - "heat_demand_predictions": get_settings().HEAT_PREDICTIONS_BUCKET, - "carbon_change_predictions": get_settings().CARBON_PREDICTIONS_BUCKET - } ) # Append the predictions to the predictions dictionary diff --git a/backend/app/plan/schemas.py b/backend/app/plan/schemas.py index 108eb1ae..04a1eb89 100644 --- a/backend/app/plan/schemas.py +++ b/backend/app/plan/schemas.py @@ -33,6 +33,11 @@ class PlanTriggerRequest(BaseModel): "solar_pv", # Specific measures "air_source_heat_pump", + "internal_wall_insulation", + "external_wall_insulation", + "secondary_heating", + "boiler_upgrade", + "high_heat_retention_storage_heater", } _allowed_goals = {"Increasing EPC"} diff --git a/backend/ml_models/AnnualBillSavings.py b/backend/ml_models/AnnualBillSavings.py index e4d9d143..211e5ea6 100644 --- a/backend/ml_models/AnnualBillSavings.py +++ b/backend/ml_models/AnnualBillSavings.py @@ -1,4 +1,6 @@ import numpy as np +import pandas as pd +import backend.app.assumptions as assumptions QUARTERLY_ENERGY_PRICES = [ # 2024 Q1 @@ -40,6 +42,53 @@ class AnnualBillSavings: DAILY_STANDARD_CHARGE_GAS = 0.3143 DAILY_STANDARD_CHARGE_ELECTRICITY = 0.601 + # Based on https://www.nottenergy.com/advice-and-tools/project-energy-cost-comparison + # For July 2024. These quotes are based on the east midlands region, so we + FUEL_DATA = pd.DataFrame([ + {"Fuel": "Electricity Standard", "Price (p)": 28.58, "Unit": "kWh", "Boiler Efficiency (%)": 100, + "Energy Content, Net Calorific value (kWh/unit)": 1.00, "Price per kWh (p) (inc boiler efficiency)": 28.58, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.275}, + {"Fuel": "Mains Gas Standard", "Price (p)": 6.31, "Unit": "kWh", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 1.00, "Price per kWh (p) (inc boiler efficiency)": 7.01, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.213}, + {"Fuel": "Kerosene", "Price (p)": 62.49, "Unit": "Litre", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 9.79, "Price per kWh (p) (inc boiler efficiency)": 7.09, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.298}, + {"Fuel": "Gas oil", "Price (p)": 94.50, "Unit": "Litre", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 9.96, "Price per kWh (p) (inc boiler efficiency)": 10.54, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.316}, + {"Fuel": "LPG", "Price (p)": 55.00, "Unit": "Litre", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 6.78, "Price per kWh (p) (inc boiler efficiency)": 9.01, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.240}, + {"Fuel": "Butane", "Price (p)": 216.58, "Unit": "Litre", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 6.64, "Price per kWh (p) (inc boiler efficiency)": 36.24, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.248}, + {"Fuel": "Propane", "Price (p)": 157.67, "Unit": "Litre", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 7.22, "Price per kWh (p) (inc boiler efficiency)": 24.25, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.239}, + {"Fuel": "Kiln Dried (logs)", "Price (p)": 36.52, "Unit": "kg", "Boiler Efficiency (%)": 85, + "Energy Content, Net Calorific value (kWh/unit)": 4.09, "Price per kWh (p) (inc boiler efficiency)": 10.51, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.024}, + {"Fuel": "Pellets (Bagged)", "Price (p)": 39.62, "Unit": "kg", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 4.80, "Price per kWh (p) (inc boiler efficiency)": 9.17, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.049}, + {"Fuel": "Pellets (Blown bulk)", "Price (p)": 33.92, "Unit": "kg", "Boiler Efficiency (%)": 90, + "Energy Content, Net Calorific value (kWh/unit)": 4.80, "Price per kWh (p) (inc boiler efficiency)": 7.85, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.049}, + {"Fuel": "Smokeless fuel", "Price (p)": 67.26, "Unit": "kg", "Boiler Efficiency (%)": 75, + "Energy Content, Net Calorific value (kWh/unit)": 6.70, "Price per kWh (p) (inc boiler efficiency)": 13.38, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.404}, + {"Fuel": "Coal", "Price (p)": 48.50, "Unit": "kg", "Boiler Efficiency (%)": 75, + "Energy Content, Net Calorific value (kWh/unit)": 7.95, "Price per kWh (p) (inc boiler efficiency)": 8.13, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.404}, + {"Fuel": "GSHP", "Price (p)": 28.58, "Unit": "kWh", "Boiler Efficiency (%)": 350, + "Energy Content, Net Calorific value (kWh/unit)": 1.00, "Price per kWh (p) (inc boiler efficiency)": 8.17, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.079}, + {"Fuel": "ASHP", "Price (p)": 28.58, "Unit": "kWh", "Boiler Efficiency (%)": 294, + "Energy Content, Net Calorific value (kWh/unit)": 1.00, "Price per kWh (p) (inc boiler efficiency)": 9.72, + "CO2eq emission factor kgCO2eq/kWh (Gross CV)": 0.094} + ]) + EPC_BANDS = ["G", "F", "E", "D", "C", "B", "A"] @classmethod @@ -199,3 +248,75 @@ class AnnualBillSavings: return current_epc_rating return cls.EPC_BANDS[expected_index - 1] + + @staticmethod + def cost_per_kwh(price_per_unit, energy_content_per_unit): + """ + Calculate the cost of fuel per kWh given the price per unit in GBP and the energy content per unit in kWh. + """ + cost_per_kwh = price_per_unit / energy_content_per_unit + # Tgis data is returned in pennies so we convert to pounds + return cost_per_kwh / 100 + + @classmethod + def calculate_recommendation_fuel_cost(cls, kwh, fuel, cop): + if fuel == "Electricity": + return (kwh / cop) * cls.ELECTRICITY_PRICE_CAP + + if fuel in ["Natural Gas", "Natural Gas (Community Scheme)"]: + return (kwh / cop) * cls.GAS_PRICE_CAP + + if fuel == "LPG": + # Get the cost per kwh + price_data = cls.FUEL_DATA[cls.FUEL_DATA["Fuel"] == "LPG"].squeeze() + cost_per_kwh = cls.cost_per_kwh( + price_data["Price (p)"], price_data["Energy Content, Net Calorific value (kWh/unit)"] + ) + return (kwh / cop) * cost_per_kwh + + if fuel in ["Wood Logs", "Wood Pellets"]: + price_data = cls.FUEL_DATA[cls.FUEL_DATA["Fuel"] == "Pellets (Bagged)"].squeeze() + cost_per_kwh = cls.cost_per_kwh( + price_data["Price (p)"], price_data["Energy Content, Net Calorific value (kWh/unit)"] + ) + return (kwh / cop) * cost_per_kwh + + if fuel == "Natural Gas + Solar Thermal": + # The solar thermal covers a % of the heating kwh, so we need to adjust the cost + return (kwh / cop) * assumptions.SOLAR_CONSUMPTION_PROPORTION * cls.GAS_PRICE_CAP + + if fuel == "Electricity + Solar Thermal": + # The solar thermal covers a % of the heating kwh, so we need to adjust the cost + return (kwh / cop) * assumptions.SOLAR_CONSUMPTION_PROPORTION * cls.ELECTRICITY_PRICE_CAP + + if fuel == "LPG + Solar Thermal": + # The solar thermal covers a % of the heating kwh, so we need to adjust the cost + price_data = cls.FUEL_DATA[cls.FUEL_DATA["Fuel"] == "LPG"].squeeze() + cost_per_kwh = cls.cost_per_kwh( + price_data["Price (p)"], price_data["Energy Content, Net Calorific value (kWh/unit)"] + ) + return (kwh / cop) * cost_per_kwh * assumptions.SOLAR_CONSUMPTION_PROPORTION + + if fuel == "Oil": + price_data = cls.FUEL_DATA[cls.FUEL_DATA["Fuel"] == "Kerosene"].squeeze() + cost_per_kwh = cls.cost_per_kwh( + price_data["Price (p)"], price_data["Energy Content, Net Calorific value (kWh/unit)"] + ) + return (kwh / cop) * cost_per_kwh + + if fuel in ["Smokeless Fuel", "Anthracite"]: + price_data = cls.FUEL_DATA[cls.FUEL_DATA["Fuel"] == "Smokeless fuel"].squeeze() + cost_per_kwh = cls.cost_per_kwh( + price_data["Price (p)"], price_data["Energy Content, Net Calorific value (kWh/unit)"] + ) + return (kwh / cop) * cost_per_kwh + + # We use coal's values for + if fuel == "Coal": + price_data = cls.FUEL_DATA[cls.FUEL_DATA["Fuel"] == "Coal"].squeeze() + cost_per_kwh = cls.cost_per_kwh( + price_data["Price (p)"], price_data["Energy Content, Net Calorific value (kWh/unit)"] + ) + return (kwh / cop) * cost_per_kwh + + raise Exception("Fuel not recognised") diff --git a/backend/ml_models/api.py b/backend/ml_models/api.py index 4844d7fd..e922d7fc 100644 --- a/backend/ml_models/api.py +++ b/backend/ml_models/api.py @@ -1,4 +1,5 @@ import pandas as pd +from tqdm import tqdm import requests from requests.exceptions import RequestException from utils.logger import setup_logger @@ -12,24 +13,27 @@ class ModelApi: "sap_change_predictions", "heat_demand_predictions", "carbon_change_predictions", - "lighting_cost_predictions", - "heating_cost_predictions", - "hot_water_cost_predictions", + # "lighting_cost_predictions", + # "heating_cost_predictions", + # "hot_water_cost_predictions", ] MODEL_URLS = { "sap_change_predictions": "sapmodel", "heat_demand_predictions": "heatmodel", "carbon_change_predictions": "carbonmodel", - "lighting_cost_predictions": "lightingmodel", - "heating_cost_predictions": "heatingmodel", - "hot_water_cost_predictions": "hotwatermodel", + "hotwater_kwh_predictions": "hotwaterkwhmodel", + "heating_kwh_predictions": "heatingkwhmodel", + # "lighting_cost_predictions": "lightingmodel", + # "heating_cost_predictions": "heatingmodel", + # "hot_water_cost_predictions": "hotwatermodel", } def __init__( self, portfolio_id, timestamp, + prediction_buckets, base_url="https://api.dev.hestia.homes", ): """ @@ -44,6 +48,7 @@ class ModelApi: self.base_url = base_url self.portfolio_id = portfolio_id self.timestamp = timestamp + self.prediction_buckets = prediction_buckets @staticmethod def predictions_template(): @@ -51,9 +56,8 @@ class ModelApi: "sap_change_predictions": pd.DataFrame(), "heat_demand_predictions": pd.DataFrame(), "carbon_change_predictions": pd.DataFrame(), - "lighting_cost_predictions": pd.DataFrame(), - "heating_cost_predictions": pd.DataFrame(), - "hot_water_cost_predictions": pd.DataFrame(), + "hotwater_kwh_predictions": pd.DataFrame(), + "heating_kwh_predictions": pd.DataFrame(), } def upload_scoring_data(self, df: pd.DataFrame, bucket: str, model_prefix: str) -> str: @@ -68,8 +72,8 @@ class ModelApi: :return: """ - if model_prefix not in self.MODEL_PREFIXES: - raise ValueError(f"Model prefix specified is not in {self.MODEL_PREFIXES}") + # if model_prefix not in self.MODEL_PREFIXES: + # raise ValueError(f"Model prefix specified is not in {self.MODEL_PREFIXES}") # Store parquet file in s3 for scoring file_location = f"{model_prefix}/{self.portfolio_id}/{self.timestamp}.parquet" @@ -123,7 +127,7 @@ class ModelApi: else: return None - def predict_all(self, df, bucket, prediction_buckets) -> dict: + def predict_all(self, df, bucket, model_prefixes=None, extract_ids=True) -> dict: """ For each model prefix, this method will upload the scoring data to s3 and then make a request to the @@ -132,19 +136,24 @@ class ModelApi: a dictionary of panaas dataframes :param df: Pandas dataframe with scoring data to be uploaded to s3 :param bucket: Name of the bucket in s3 to upload to - :param prediction_buckets: Dictionary containing the prediction buckets for each model prefix + :param model_prefixes: List of model prefixes to generate predictions for. If None, all model prefixes will be + used + :param extract_ids: Boolean to determine if the property_id and recommendation_id should be extracted from the + id column :return: """ + model_prefixes = self.MODEL_PREFIXES if model_prefixes is None else model_prefixes + predictions = {} - for model_prefix in self.MODEL_PREFIXES: + for model_prefix in model_prefixes: logger.info(f"Scoring for model prefix: {model_prefix}") file_location = self.upload_scoring_data(df, bucket, model_prefix) response = self.predict( "s3://{DATA_BUCKET}/".format(DATA_BUCKET=bucket) + file_location, model_prefix ) - predictions_bucket = prediction_buckets[model_prefix] + predictions_bucket = self.prediction_buckets[model_prefix] # Retrieve the predictions predictions_df = pd.DataFrame( @@ -155,16 +164,35 @@ class ModelApi: ) predictions_df['predictions'] = predictions_df["predictions"].astype(float).round(1) - predictions_df[['property_id', 'recommendation_id']] = predictions_df['id'].str.split('+', expand=True) - # To grab the phase, we pull the integer after "phase=" in the recommendation_id. We can do this with a - # string split on phase= and then grab the second element of the resulting list. We could also use a - # regular expression to do this but we use the string split method here, for safety. - # We may not always have a phase to split on, so we need to handle this case. We can do this by using the - # str[1] method to grab the second element of the resulting list. We then grab the first character of this - # string to get the phase. We then convert this to an integer. - # Convert back to int - predictions_df['phase'] = predictions_df['recommendation_id'].apply(self.extract_phase) + if extract_ids: + predictions_df[['property_id', 'recommendation_id']] = predictions_df['id'].str.split('+', expand=True) + # To grab the phase, we pull the integer after "phase=" in the recommendation_id. We can do this with a + # string split on phase= and then grab the second element of the resulting list. We could also use a + # regular expression to do this but we use the string split method here, for safety. + # We may not always have a phase to split on, so we need to handle this case. We can do this by using + # the str[1] method to grab the second element of the resulting list. We then grab the first + # character of this + # string to get the phase. We then convert this to an integer. + # Convert back to int + predictions_df['phase'] = predictions_df['recommendation_id'].apply(self.extract_phase) predictions[model_prefix] = predictions_df return predictions + + def paginated_predictions(self, data, bucket, batch_size, model_prefixes=None, extract_ids=True): + all_predictions = self.predictions_template() + to_loop_over = range(0, data.shape[0], batch_size) + for chunk in tqdm(to_loop_over, total=len(to_loop_over)): + predictions_dict = self.predict_all( + df=data.iloc[chunk:chunk + batch_size], + bucket=bucket, + model_prefixes=model_prefixes, + extract_ids=extract_ids + ) + + # Append the predictions to the predictions dictionary + for key, scored in predictions_dict.items(): + all_predictions[key] = pd.concat([all_predictions[key], scored]) + + return all_predictions diff --git a/etl/bill_savings/EnergyConsumptionModel.py b/etl/bill_savings/EnergyConsumptionModel.py index ff225073..4daf2b31 100644 --- a/etl/bill_savings/EnergyConsumptionModel.py +++ b/etl/bill_savings/EnergyConsumptionModel.py @@ -6,6 +6,7 @@ from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_percenta from sklearn.feature_selection import RFECV from utils.s3 import save_pickle_to_s3, read_pickle_from_s3, read_dataframe_from_s3_parquet, read_csv_from_s3 from utils.logger import setup_logger +from backend.Property import Property logger = setup_logger() @@ -125,37 +126,6 @@ class EnergyConsumptionModel: self.retail_price_comparison = pd.DataFrame(data_rows, columns=header) self.retail_price_comparison['Date'] = pd.to_datetime(self.retail_price_comparison['Date'], errors='coerce') - def convert_cost_to_today(self, original_cost, lodgement_date): - """ - Given energy costs in an EPC, this function converts that energy cost to a figure based on today's energy costs - (or as close to today as possible) - :param original_cost: The original energy cost - :param lodgement_date: The date the EPC was lodged - :return: - """ - closest_date = self.retail_price_comparison.iloc[ - (self.retail_price_comparison['Date'] - lodgement_date).abs().argsort()[:1] - ]['Date'].values[0] - closest_date = pd.Timestamp(closest_date) - - # Extract the tariff price on the closest date - tariff_2024 = self.retail_price_comparison[ - self.retail_price_comparison['Date'] == closest_date - ]['Average standard variable tariff (Large legacy suppliers)'].values[0] - - # Extract the latest available tariff price - latest_tariff = self.retail_price_comparison[ - 'Average standard variable tariff (Large legacy suppliers)' - ].iloc[-1] - - # Calculate the ratio - ratio = float(latest_tariff) / float(tariff_2024) - - # Calculate the updated heating cost - updated_cost = original_cost * ratio - - return updated_cost - def read_dataset(self, file_path): """Reads the dataset from the specified file path.""" logger.info(f"Reading dataset from {file_path}") @@ -525,7 +495,7 @@ class EnergyConsumptionModel: def estimate_new_consumption(self, current_energy_efficiency, target_efficiency, current_consumption): """ - Given then consumption_averages dataset, which is produced as a result of the data_combining.py script, + Given then consumption_averages dataset, which is produced as a result of the training_data.py script, for the energy kwh models, this function will estimate the new consumption based on the current consumption, based on the expected reduction in consumption from the current rating to the target rating. :param current_energy_efficiency: diff --git a/etl/bill_savings/KwhData.py b/etl/bill_savings/KwhData.py new file mode 100644 index 00000000..6b5f594a --- /dev/null +++ b/etl/bill_savings/KwhData.py @@ -0,0 +1,363 @@ +import re +import pandas as pd +import numpy as np +from datetime import datetime +from tqdm import tqdm +from utils.logger import setup_logger +from utils.s3 import ( + list_files_in_s3_folder, read_pickle_from_s3, save_dataframe_to_s3_parquet, read_dataframe_from_s3_parquet, + read_csv_from_s3 +) +from backend.Property import Property + +logger = setup_logger() + + +class KwhData: + COLS_TO_STRINGIFY = ["main-heating-controls", "floor-level"] + + CATEGORICAL_COLUMNS = [ + "lodgement-year", "lodgement-month", "main-fuel", "mainheat-description", "number-heated-rooms", + "number-habitable-rooms", "mainheat-energy-eff", "mainheatcont-description", "property-type", + "built-form", + "construction-age-band", "secondheat-description", "hotwater-description", "hot-water-energy-eff", + "walls-description", "walls-energy-eff", "roof-description", "roof-energy-eff", "floor-description", + "county", + "windows-description", "windows-energy-eff", "flat-top-storey", + "flat-storey-count", "unheated-corridor-length", "solar-water-heating-flag", "mechanical-ventilation", + "low-energy-lighting", "environment-impact-current", "energy-tariff", "current-energy-rating", + "floor-level" + ] + + NUMERICAL_COLUMNS = [ + 'heating-cost-current', 'total-floor-area', 'co2-emissions-current', 'energy-consumption-current', + 'heating-cost-potential', 'hot-water-cost-current', 'current-energy-efficiency' + ] + + def __init__(self, bucket=None, read_consumption_data=False): + self.run_date = datetime.now().strftime("%Y-%m-%d") + self.bucket = bucket + self.data = None + + self.consumption_data_filepath = None + self.consumption_averages_filepath = None + self.model_training_data_filepath = None + + self.consumption_averages = None + self.retail_price_comparison = None + if read_consumption_data: + self.get_consumption_data() + self.read_retail_price_comparison() + + def get_consumption_data(self): + + # Look for the latest version of this file + s3_contents = list_files_in_s3_folder(bucket_name=self.bucket, folder_name="energy_consumption/") + consumption_averages = [ + {"run_date": pd.to_datetime(x.split("/")[1]), "filepath": x} + for x in s3_contents if "consumption_averages.parquet" in x + ] + # Get the file with the soonest run date + consumption_averages = sorted(consumption_averages, key=lambda x: x["run_date"]) + if not consumption_averages: + raise ValueError("No consumption averages data found, something went wrong") + + self.consumption_averages = read_dataframe_from_s3_parquet( + bucket_name=self.bucket, + file_key=consumption_averages[-1]["filepath"] + ) + + def read_retail_price_comparison(self): + data = read_csv_from_s3( + bucket_name=self.bucket, + filepath="energy_consumption/retail-price-comparison.csv" + ) + header = ['Date', 'Average standard variable tariff (Large legacy suppliers)', + 'Average standard variable tariff (Other suppliers)', 'Average fixed tariff', + 'Cheapest tariff (Large legacy suppliers)', 'Cheapest tariff (All suppliers)', + 'Cheapest tariff (Basket)', 'Default tariff cap level'] + + # Extract data rows + data_rows = [] + for row in data[1:]: + date = row['\ufeff"'] + values = row[None] + data_rows.append([date] + values) + + self.retail_price_comparison = pd.DataFrame(data_rows, columns=header) + self.retail_price_comparison['Date'] = pd.to_datetime(self.retail_price_comparison['Date'], errors='coerce') + + @staticmethod + def extract_kwh_value(text: str): + """ + Extract the numerical kWh value from a given string. + + :param text: The input string containing the kWh value. + :return: The extracted numerical kWh value as an integer. + """ + # Use regular expression to find the numerical value followed by "kWh per year" + match = re.search(r'([\d,]+) kWh per year', text) + + if match: + # Remove commas from the extracted value and convert to integer + kwh_value = int(match.group(1).replace(',', '')) + return kwh_value + else: + # If no match is found, return None or raise an exception + return None + + def combine(self): + """ + Given the data that is collected containing the kwh values for heating and hot water, this method will combine + and save the data + :return: + """ + + # Firstly, list all of the saved files in s3 + data_files = list_files_in_s3_folder(bucket_name="retrofit-datalake-dev", folder_name="energy_consumption_data") + + complete_data = [] + for files in tqdm(data_files): + dataset_run_date = files.split("/")[-1].split(".")[0] + # Extract the date from the file name + dataset_run_date = pd.Timestamp(dataset_run_date) + + # Load the data from the file + data = read_pickle_from_s3(bucket_name="retrofit-datalake-dev", s3_file_name=files) + + # We check that the retrieved energy consumption sufficiently matches the EPC data + internal_dataset = [] + for x in data: + epc_data = x["epc"] + epc_sap = epc_data["current-energy-efficiency"] + epc_potential_sap = epc_data["potential-energy-efficiency"] + # Make sure this matches the extracted sap + if int(epc_sap) != int(x["current_epc_efficiency"]) or int(epc_potential_sap) != int( + x["potential_epc_efficiency"] + ): + continue + + heating_kwh = self.extract_kwh_value(x["heating_text"]) + hot_water_kwh = self.extract_kwh_value(x["hot_water_text"]) + internal_dataset.append( + { + **epc_data, + "heating_kwh": heating_kwh, + "hot_water_kwh": hot_water_kwh, + "dataset_run_date": dataset_run_date + } + ) + + complete_data.extend(internal_dataset) + + df = pd.DataFrame(complete_data) + # Because we collate multiple runs into a single data source, it's possible that we have duplicated data at + # the uprn level, so we dedupe based on the newest dataset_run_date + + df = df.sort_values("dataset_run_date", ascending=False).drop_duplicates(subset="uprn", keep="first") + df = df.drop(columns=["dataset_run_date"]) + + for col in self.COLS_TO_STRINGIFY: + df[col] = df[col].astype(str) + + # Save the data back to s3, but this time as a parquet file + self.consumption_data_filepath = f"energy_consumption/{self.run_date}/energy_consumption_dataset.parquet" + logger.info(f"Storing energy consumption dataset in s3 at {self.consumption_data_filepath}") + save_dataframe_to_s3_parquet( + bucket_name=self.bucket, + file_key=self.consumption_data_filepath, + df=df + ) + + # We also estimate the energy consumption reduction from this data, by band + df["total_consumption"] = df["heating_kwh"] + df["hot_water_kwh"] + consumption_averages = df.groupby("current-energy-efficiency")["total_consumption"].mean().reset_index() + df = df.drop(columns=["total_consumption"]) + + self.consumption_averages_filepath = f"energy_consumption/{self.run_date}/consumption_averages.parquet" + logger.info(f"Storing consumption averages in s3 at {self.consumption_averages_filepath}") + # Save the consumption averages back to s3 + save_dataframe_to_s3_parquet( + bucket_name="retrofit-data-dev", + file_key=self.consumption_averages_filepath, + df=consumption_averages + ) + + self.data = df + + def transform( + self, data: pd.DataFrame, cleaned, new=False, save=False + ): + """ + Given the input EPCs, this method will transform the data into a format that can be used by the model + This method can be used to transform the training data, or new epcs within the backend engine + :return: + """ + if save and self.bucket is None: + raise Exception("bucket not set, cannot save data") + + # TODO: New is a temporary parameter, which will transform the epc descriptions to their transformed features + # in anticipation of the new model + + data["lodgement-date"] = pd.to_datetime(data["lodgement-date"]) + data["lodgement-year"] = data["lodgement-date"].dt.year + data["lodgement-month"] = data["lodgement-date"].dt.month + + # For walls, roof, floor description where we have average thermal transmittance, to avoid too many + # categories + # we group them + ranges = { + "lessthan 0.1": (0, 0.1), + "0.1 - 0.3": (0.1, 0.3), + "0.3 - 0.5": (0.3, 0.5), + "morethan 0.5": (0.5, 2.5), + } + + # Generate the lookup table + thermal_transmittance_lookup_table = [] + for i in range(1, 251): + value = i / 100 + for label, (low, high) in ranges.items(): + if low < value <= high: + thermal_transmittance_lookup_table.append({"from": value, "to": label}) + break + + # Convert to DataFrame for display + thermal_transmittance_lookup_table = pd.DataFrame(thermal_transmittance_lookup_table) + thermal_transmittance_lookup_table["from"] = thermal_transmittance_lookup_table["from"].astype(str) + + # Apply the lookup table to the data + for feature in ["walls-description", "roof-description", "floor-description"]: + cleaned_df = pd.DataFrame(cleaned[feature])[["original_description", "thermal_transmittance"]] + # Round to 2 decimal places and convert to string + cleaned_df["thermal_transmittance"] = cleaned_df["thermal_transmittance"].round(2).astype(str) + + data = data.merge( + cleaned_df, + how="left", + left_on=feature, + right_on="original_description", + ) + # We now have the thermal transmittance in the data, which we can use to group with the lookup table + data = data.merge( + thermal_transmittance_lookup_table, + how="left", + left_on="thermal_transmittance", + right_on="from", + ) + # Where "to" is populated, replace feature with to + data[feature] = np.where( + ~pd.isnull(data["to"]), + data["to"], + data[feature] + ) + data = data.drop(columns=["original_description", "thermal_transmittance", "from", "to"]) + + data[self.NUMERICAL_COLUMNS] = data[self.NUMERICAL_COLUMNS].apply(pd.to_numeric) + data[self.CATEGORICAL_COLUMNS] = data[self.CATEGORICAL_COLUMNS].astype(str) + + # Create new features: + data['estimate_annual_kwh'] = data['energy-consumption-current'] * data['total-floor-area'] + + if save: + self.model_training_data_filepath = f"energy_consumption/{self.run_date}/training_data.parquet" + logger.info(f"Storing energy consumption dataset in s3 at {self.consumption_data_filepath}") + save_dataframe_to_s3_parquet( + bucket_name=self.bucket, + file_key=self.model_training_data_filepath, + df=data + ) + return + + return data + + @staticmethod + def _prepare_epc(p: Property): + """ + Given an instance of the property class, this method will ensure that the EPC is ready for scoring with the + kwh models. In the backend, we perform some cleaning and transformation on an EPC so we just ensure that the + data is in the format required by the model + :return: + """ + + epc = p.data.copy() + numeric_cols = [ + 'current-energy-efficiency', + 'potential-energy-efficiency', 'environment-impact-current', + 'environment-impact-potential', 'energy-consumption-current', + 'energy-consumption-potential', 'co2-emissions-current', + 'co2-emiss-curr-per-floor-area', 'co2-emissions-potential', + 'lighting-cost-current', 'lighting-cost-potential', + 'heating-cost-current', 'heating-cost-potential', + 'hot-water-cost-current', 'hot-water-cost-potential', + 'total-floor-area', 'multi-glaze-proportion', + 'extension-count', 'number-habitable-rooms', 'number-heated-rooms', + 'low-energy-lighting', 'number-open-fireplaces', + 'wind-turbine-count', 'unheated-corridor-length', + 'floor-height', 'photo-supply', 'fixed-lighting-outlets-count', + 'low-energy-fixed-light-count', + ] + for v in numeric_cols: + if epc[v] is not None: + epc[v] = float(epc[v]) + + bools_to_remap = ['mains-gas-flag', 'flat-top-storey'] + bool_map = { + True: "Y", + False: "N", + None: "N", + "Y": "Y", + "N": "N" + } + for v in bools_to_remap: + epc[v] = bool_map[epc[v]] + + no_data = { + "floor-level": "NODATA!", + "floor-energy-eff": "NO DATA!" + } + for v, fill_val in no_data.items(): + if pd.isnull(epc[v]): + epc[v] = fill_val + + return epc + + def prepare_epc(self, input_properties: list[Property]): + scoring_data = pd.DataFrame([self._prepare_epc(p) for p in input_properties]) + scoring_data["lodgement-year"] = pd.to_datetime(scoring_data["lodgement-date"]).dt.year + scoring_data["lodgement-month"] = pd.to_datetime(scoring_data["lodgement-date"]).dt.month + + scoring_data["id"] = scoring_data["uprn"].copy() + + return scoring_data + + def convert_cost_to_today(self, original_cost, lodgement_date): + """ + Given energy costs in an EPC, this function converts that energy cost to a figure based on today's energy costs + (or as close to today as possible) + :param original_cost: The original energy cost + :param lodgement_date: The date the EPC was lodged + :return: + """ + closest_date = self.retail_price_comparison.iloc[ + (self.retail_price_comparison['Date'] - lodgement_date).abs().argsort()[:1] + ]['Date'].values[0] + closest_date = pd.Timestamp(closest_date) + + # Extract the tariff price on the closest date + tariff_2024 = self.retail_price_comparison[ + self.retail_price_comparison['Date'] == closest_date + ]['Average standard variable tariff (Large legacy suppliers)'].values[0] + + # Extract the latest available tariff price + latest_tariff = self.retail_price_comparison[ + 'Average standard variable tariff (Large legacy suppliers)' + ].iloc[-1] + + # Calculate the ratio + ratio = float(latest_tariff) / float(tariff_2024) + + # Calculate the updated heating cost + updated_cost = original_cost * ratio + + return updated_cost diff --git a/etl/bill_savings/data_collection.py b/etl/bill_savings/data_collection.py index 15a52663..49bcff82 100644 --- a/etl/bill_savings/data_collection.py +++ b/etl/bill_savings/data_collection.py @@ -131,53 +131,57 @@ def app(): sample_size = 500 energy_consumption_data = [] - cavity_walls_data = [] for i, directory in tqdm(enumerate(epc_directories), total=len(epc_directories)): - - # Skip the first 50 - # if i < 57: - # continue - - data = pd.read_csv(directory / "certificates.csv", low_memory=False) - # Rename the columns to the same format as the api returns - data.columns = [c.replace("_", "-").lower() for c in data.columns] - - # Take just date before the date threshold - data = data[data["lodgement-date"] >= EARLIEST_EPC_DATE] - - data = data[~pd.isnull(data["uprn"])] - # Take just the newest EPC per uprn, based on lodgement-date - data = data.sort_values("lodgement-date", ascending=False).drop_duplicates("uprn") - - data = data.sample(sample_size, replace=False) - # We use the addreess data to find the related information - - collected_data = [] - for _, property_data in data.iterrows(): - time.sleep(np.random.uniform(0.2, 1.5)) - - uprn = int(property_data["uprn"]) - address = property_data["address1"] - postcode = property_data["postcode"] - expected_expiry_date = calculate_expiry_date(property_data["lodgement-date"]) - - response = retrieve_find_my_epc_data( - uprn=uprn, - postcode=postcode, - address=address, - expected_expiry_date=expected_expiry_date - ) - if response is None: + try: + # Skip the first 50 + if i < 256: continue - collected_data.append( - { - **response, - "epc": property_data.to_dict(), - "epc_directory": str(directory) - } - ) - energy_consumption_data.extend(collected_data) + data = pd.read_csv(directory / "certificates.csv", low_memory=False) + # Rename the columns to the same format as the api returns + data.columns = [c.replace("_", "-").lower() for c in data.columns] + + # Take just date before the date threshold + data = data[data["lodgement-date"] >= EARLIEST_EPC_DATE] + + data = data[~pd.isnull(data["uprn"])] + # Take just the newest EPC per uprn, based on lodgement-date + data = data.sort_values("lodgement-date", ascending=False).drop_duplicates("uprn") + + data = data.sample(sample_size, replace=False) + # We use the addreess data to find the related information + + collected_data = [] + for _, property_data in data.iterrows(): + time.sleep(np.random.uniform(0.2, 1.5)) + + uprn = int(property_data["uprn"]) + address = property_data["address1"] + postcode = property_data["postcode"] + expected_expiry_date = calculate_expiry_date(property_data["lodgement-date"]) + + response = retrieve_find_my_epc_data( + uprn=uprn, + postcode=postcode, + address=address, + expected_expiry_date=expected_expiry_date + ) + if response is None: + continue + collected_data.append( + { + **response, + "epc": property_data.to_dict(), + "epc_directory": str(directory) + } + ) + + energy_consumption_data.extend(collected_data) + except Exception as e: + print(f"Error for directory {directory}: {e}") + # If we have an error, then we wait for a bit since it's likely due to timeout + time.sleep(300) + continue # Store the pickle in s3 save_time = datetime.now() diff --git a/etl/bill_savings/data_combining.py b/etl/bill_savings/data_combining.py deleted file mode 100644 index dece3834..00000000 --- a/etl/bill_savings/data_combining.py +++ /dev/null @@ -1,104 +0,0 @@ -import re -from datetime import datetime -from tqdm import tqdm - -import pandas as pd - -from utils.s3 import list_files_in_s3_folder, read_pickle_from_s3, save_dataframe_to_s3_parquet - -# These columns we co-erce to strings before saving -PROBLEMATIC_COLUMNS = ["main-heating-controls", "floor-level"] - - -def extract_kwh_value(text): - """ - Extract the numerical kWh value from a given string. - - :param text: The input string containing the kWh value. - :return: The extracted numerical kWh value as an integer. - """ - # Use regular expression to find the numerical value followed by "kWh per year" - match = re.search(r'([\d,]+) kWh per year', text) - - if match: - # Remove commas from the extracted value and convert to integer - kwh_value = int(match.group(1).replace(',', '')) - return kwh_value - else: - # If no match is found, return None or raise an exception - return None - - -def app(): - """ - Given the files written in our datalake in s3, this application will collate the data into a single file - and store it back in s3 for analysis - :return: - """ - - # Firstly, list all of the saved files in s3 - data_files = list_files_in_s3_folder(bucket_name="retrofit-datalake-dev", folder_name="energy_consumption_data") - - run_date = datetime.now().strftime("%Y-%m-%d") - - complete_data = [] - for files in tqdm(data_files): - dataset_run_date = files.split("/")[-1].split(".")[0] - # Extract the date from the file name - dataset_run_date = pd.Timestamp(dataset_run_date) - - # Load the data from the file - data = read_pickle_from_s3(bucket_name="retrofit-datalake-dev", s3_file_name=files) - - # We check that the retrieved energy consumption sufficiently matches the EPC data - internal_dataset = [] - for x in data: - epc_data = x["epc"] - epc_sap = epc_data["current-energy-efficiency"] - epc_potential_sap = epc_data["potential-energy-efficiency"] - # Make sure this matches the extracted sap - if int(epc_sap) != int(x["current_epc_efficiency"]) or int(epc_potential_sap) != int( - x["potential_epc_efficiency"] - ): - continue - - heating_kwh = extract_kwh_value(x["heating_text"]) - hot_water_kwh = extract_kwh_value(x["hot_water_text"]) - internal_dataset.append( - { - **epc_data, - "heating_kwh": heating_kwh, - "hot_water_kwh": hot_water_kwh, - "dataset_run_date": dataset_run_date - } - ) - - complete_data.extend(internal_dataset) - - df = pd.DataFrame(complete_data) - # Because we collate multiple runs into a single data source, it's possible that we have duplicated data at - # the uprn level, so we dedupe based on the newest dataset_run_date - - df = df.sort_values("dataset_run_date", ascending=False).drop_duplicates(subset="uprn", keep="first") - df = df.drop(columns=["dataset_run_date"]) - - for col in PROBLEMATIC_COLUMNS: - df[col] = df[col].astype(str) - - # Save the data back to s3, but this time as a parquet file - save_dataframe_to_s3_parquet( - bucket_name="retrofit-data-dev", - file_key=f"energy_consumption/{run_date}/energy_consumption_dataset.parquet", - df=df - ) - - # We also estimate the energy consumption reduction from this data, by band - df["total_consumption"] = df["heating_kwh"] + df["hot_water_kwh"] - consumption_averages = df.groupby("current-energy-efficiency")["total_consumption"].mean().reset_index() - - # Save the consumption averages back to s3 - save_dataframe_to_s3_parquet( - bucket_name="retrofit-data-dev", - file_key=f"energy_consumption/{run_date}/consumption_averages.parquet", - df=consumption_averages - ) diff --git a/etl/bill_savings/training.py b/etl/bill_savings/training.py deleted file mode 100644 index df60298b..00000000 --- a/etl/bill_savings/training.py +++ /dev/null @@ -1,57 +0,0 @@ -from pprint import pprint -import msgpack -from utils.s3 import read_from_s3 -from etl.bill_savings.EnergyConsumptionModel import EnergyConsumptionModel - - -def handler(): - """ - This function is used to train the model and store the final models in s3 as pickles - :return: - """ - - dataset_version = "2024-07-08" - - # Usage: - cleaned = read_from_s3( - s3_file_name="cleaned_epc_data/cleaned.bson", - bucket_name="retrofit-data-dev" - ) - - cleaned = msgpack.unpackb(cleaned, raw=False) - - model = EnergyConsumptionModel(cleaned=cleaned, n_jobs=2) - model.read_dataset(f'energy_consumption/{dataset_version}/energy_consumption_dataset.parquet') - model.feature_engineering() - model.save_dummy_schema(dataset_version=dataset_version) - - # For heating_kwh - model.split_dataset(target='heating_kwh') - model.fit_model(target='heating_kwh') - model.re_train_final_model(target='heating_kwh') - evaluation_results = model.evaluate_model(target='heating_kwh') - - pprint(evaluation_results["train"]) - pprint(evaluation_results["test"]) - - model.save_model(target='heating_kwh', dataset_version=dataset_version) - - # importance_df = evaluation_results["train"]["Feature Importance"] - # testing_predictions = model.testing_predictions["heating_kwh"] - # testing_predictions = testing_predictions.sort_values("residual", ascending=False) - # training_predictions = model.training_predictions["heating_kwh"] - # training_predictions = training_predictions.sort_values("residual", ascending=False) - # # Merge on model.input_data, by the index - # merged_data = testing_predictions.merge(model.input_data, left_index=True, right_index=True) - # merged_data_train = training_predictions.merge(model.input_data, left_index=True, right_index=True) - - # For hot_water_kwh - model.split_dataset(target='hot_water_kwh') - model.fit_model(target='hot_water_kwh') - model.re_train_final_model(target='hot_water_kwh') - evaluation_results = model.evaluate_model(target='hot_water_kwh') - - pprint(evaluation_results["train"]) - pprint(evaluation_results["test"]) - - model.save_model(target='hot_water_kwh', dataset_version=dataset_version) diff --git a/etl/bill_savings/training_data.py b/etl/bill_savings/training_data.py new file mode 100644 index 00000000..a3d58af3 --- /dev/null +++ b/etl/bill_savings/training_data.py @@ -0,0 +1,24 @@ +import msgpack +from etl.bill_savings.KwhData import KwhData +from utils.s3 import read_from_s3 + + +def app(): + """ + Given the files written in our datalake in s3, this application will collate the data into a single file + and store it back in s3 for analysis + :return: + """ + + cleaned = read_from_s3( + s3_file_name="cleaned_epc_data/cleaned.bson", + bucket_name="retrofit-data-dev" + ) + + cleaned = msgpack.unpackb(cleaned, raw=False) + + # If there is any problematic data, it could be: + # s3://retrofit-datalake-dev/energy_consumption_data/2024-08-10 18:48:06.866647.pkl + kwh_data_client = KwhData(bucket="retrofit-datalake-dev") + kwh_data_client.combine() + kwh_data_client.transform(data=kwh_data_client.data, cleaned=cleaned, save=True) diff --git a/etl/customers/bcc_tender/app.py b/etl/customers/bcc_tender/app.py new file mode 100644 index 00000000..281cf864 --- /dev/null +++ b/etl/customers/bcc_tender/app.py @@ -0,0 +1,186 @@ +""" +This script prepares some data for the Birmingham City Council tender +""" +import pandas as pd +import numpy as np + +epc_data = pd.read_csv("local_data/all-domestic-certificates/domestic-E08000025-Birmingham/certificates.csv") + +# Broad assumptions +# Around 67% of homes in the Uk have an EPC, to be conservative with our estimates, we round up to 70%: +# https://www.ons.gov.uk/peoplepopulationandcommunity/housing/articles/energyefficiencyofhousinginenglandandwales/2023 +# However, we have 322128 homes in Birmingham with an EPC, which is 76% of the total number of homes in Birmingham +# based on the 2021 census, which put this figure at 423,500 homes +PROPORTION_OF_HOMES_WITH_AN_EPC = 0.761 +N_HOUSEHOLDS_IN_BIRMINGHAM = 423_500 +N_HOMES_WITHOUT_AN_EPC = 423_500 - 322128 + +# 55% of households are recipients of benefits in the West Midlands +# (2021/2022 - https://www.statista.com/statistics/382858/uk-state-benefits-by-region/) +PROPORTION_OF_HOMES_ON_BENEFITS = 0.55 + +# https://www.justgroupplc.co.uk/~/media/Files/J/Just-Retirement-Corp/news-doc/2023/six-in-10-homeowners-eligible-for +# -benefits-failing-to-claim-just-group-annual-insight-report.pdf +PROPORTION_OF_HOMEOWNERS_CLAIMING_FOR_BENEFITS = 0.106 + +# Breakdown of properties in council tax bands in the UK, to give us an estimate of the number of properties in A-D +band_a_proportion = 0.239 +band_b_proportion = 0.195 +band_c_proportion = 0.219 +band_d_proportion = 0.156 +COUNCIL_TAX_BAND_A_TO_D_PROPORTION = band_a_proportion + band_b_proportion + band_c_proportion + band_d_proportion + +# Get the newest record, based on lodgment datetime, by uprn +epc_data["LODGEMENT_DATETIME"] = pd.to_datetime(epc_data["LODGEMENT_DATETIME"], errors="coerce") +epc_data = epc_data.sort_values(["LODGEMENT_DATETIME"], ascending=False).drop_duplicates("UPRN") + +# We want to figure out the number of properties that are eligible for ECO/GBIS funding + +social_tenures = ["Rented (social)", "rental (social)"] +owner_occupied_tenures = ["Owner-occupied", "owner-occupied"] +prs_tenures = ["Rented (private)", "rental (private)"] + +# If social tenure, then as long as the property is EPC D-G, it's eligible +epc_data["eligibility_type"] = None + +# Eligibiltiy 1: ECO4 help to heat group OO - tenure is owner occupied and EPC rating D-G +epc_data["eligibility_type"] = np.where( + ( + epc_data["TENURE"].isin(owner_occupied_tenures) & + epc_data["CURRENT_ENERGY_RATING"].isin(["D", "E", "F", "G"]) & + pd.isnull(epc_data["eligibility_type"]) + ), + "eco4_oo_hthg_needs_scaling_on_benefits", + epc_data["eligibility_type"] +) + +# Eligibility 2: ECO4 help to heat group PRS - tenure is private rental and EPC rating E-G +epc_data["eligibility_type"] = np.where( + ( + epc_data["TENURE"].isin(prs_tenures) & + epc_data["CURRENT_ENERGY_RATING"].isin(["E", "F", "G"]) & + pd.isnull(epc_data["eligibility_type"]) + ), + "eco4_prs_hthg_needs_scaling_on_benefits", + epc_data["eligibility_type"] +) + +# Eligibiltiy 3: ECO4 Social housing - tenure is social rented and EPC rating D-G +epc_data["eligibility_type"] = np.where( + ( + epc_data["TENURE"].isin(social_tenures) & + epc_data["CURRENT_ENERGY_RATING"].isin(["D", "E", "F", "G"]) & + pd.isnull(epc_data["eligibility_type"]) + ), + "eco4_social_housing", + epc_data["eligibility_type"] +) + +# Eligibility 4: GBIS General Eligibility, OO - tenure is owner occupied and EPC rating D-G +# This is a subset of Eligiblity 1. We scale eco4_oo_hthg_needs_scaling based on thhe % of properties on benefits +# For any properties left over that are deemed as not eligibile, a % of these will be eligible for GBIS via Eligibility +# 4, and therefore any properties that fall out of Eligibility 1, a % will fall into eligibility 4 based a % of units +# being in council tax bands A-D + +# Eligibility 5: GBIS General Eligibility, PRS - tenure is private rental and EPC rating D-G +# Additionally, some units that fall our of Eligibility 2 will be eligible for GBIS via Eligibility 5, via the same +# mechanism as Eligibility 4. We handle this later +epc_data["eligibility_type"] = np.where( + ( + epc_data["TENURE"].isin(prs_tenures) & + epc_data["CURRENT_ENERGY_RATING"].isin(["D", "E", "F", "G"]) & + pd.isnull(epc_data["eligibility_type"]) + ), + "gbis_prs_ge_needs_scaling_on_council_tax_band", + epc_data["eligibility_type"] +) + +# Eligibiilty 6: GBIS General Eligibility, Social - tenure is social rented and EPC rating D-G, but also the property +# should be rented out below market rate +# This is a subset of Eligibility 3 - we likely don't need to do any scaling + +n_eco4_oo_hthg_needs_scaling_on_benefits = epc_data[ + epc_data["eligibility_type"] == "eco4_oo_hthg_needs_scaling_on_benefits" + ].shape[0] + +n_eco4_prs_hthg_needs_scaling_on_benefits = epc_data[ + epc_data["eligibility_type"] == "eco4_prs_hthg_needs_scaling_on_benefits" + ].shape[0] + +n_eco4_social = epc_data[ + epc_data["eligibility_type"] == "eco4_social_housing" + ].shape[0] + +n_gbis_prs_ge_needs_scaling_on_council_tax_band = epc_data[ + epc_data["eligibility_type"] == "gbis_prs_ge_needs_scaling_on_council_tax_band" + ].shape[0] + +# We're going to make the broad assumption that all homeowners claiming for benefits, live in homes in council tax +# bands A-D. There there are no additionals in eligibility 4 and 5 + +# n_eligibility_1 = np.floor(n_eco4_oo_hthg_needs_scaling_on_benefits * PROPORTION_OF_HOMEOWNERS_CLAIMING_FOR_BENEFITS) +n_eligibility_1 = np.floor(n_eco4_oo_hthg_needs_scaling_on_benefits * COUNCIL_TAX_BAND_A_TO_D_PROPORTION) + +# n_eligibility_2 = np.floor(n_eco4_prs_hthg_needs_scaling_on_benefits * PROPORTION_OF_HOMES_ON_BENEFITS) +n_eligibility_2 = np.floor(n_eco4_prs_hthg_needs_scaling_on_benefits * COUNCIL_TAX_BAND_A_TO_D_PROPORTION) + +n_eligiblity_3 = n_eco4_social + +# We subtract the number of homes in eligiblity 1, from the number of homes under ECO4 OO, HTHG, before scaling on +# benefits. This gives us the number of homes that were not on benefits. We then scale this number based on the % of +# homes in council tax bands A-D +# n_eligiblity_4 = np.floor( +# (n_eco4_oo_hthg_needs_scaling_on_benefits - n_eligibility_1) * COUNCIL_TAX_BAND_A_TO_D_PROPORTION +# ) + +# We also need to add on homes that fall out of eligibility 2 +n_eligibiltiy_5 = np.floor( + np.floor(n_gbis_prs_ge_needs_scaling_on_council_tax_band * COUNCIL_TAX_BAND_A_TO_D_PROPORTION) + # np.floor((n_eco4_prs_hthg_needs_scaling_on_benefits - n_eligibility_2) * COUNCIL_TAX_BAND_A_TO_D_PROPORTION) +) + +# We don't scale up the # of homes based on % of homes with an EPC, because +n_owner_occupied = epc_data[epc_data["TENURE"].isin(owner_occupied_tenures)].shape[0] +oo_eligibility = n_eligibility_1 + +# 68% of owner occupied are eligibiltiy +proportion_of_oo_eligible = oo_eligibility / n_owner_occupied +# We then use this % on the rest of the homes in Birmingham that do not have an EPC +oo_eligible_without_an_epc = np.floor(N_HOMES_WITHOUT_AN_EPC * proportion_of_oo_eligible) +oo_eligibility = oo_eligibility + oo_eligible_without_an_epc + +# All private rentals require an EPC +prs_eligibility = (n_eligibility_2 + n_eligibiltiy_5) +# Most social housing properties will have an EPC so we don't scale this up +social_eligibility = n_eligiblity_3 + +# We scale this up since this number is based on the number of homes in Birmingham with an EPC, and we want to +# estimate the total number of homes in Birmingham +total_eligible = oo_eligibility + prs_eligibility + social_eligibility + +proportion_of_homes_eligibile = total_eligible / N_HOUSEHOLDS_IN_BIRMINGHAM +# Approx 53% of homes in Birmingham are eligible for ECO/GBIS funding + +# Approximately 53% of Homes are eligible for some form of ECO4 or GBIS funding, 227k homes +# This is broken down as follows: +# - 155k owner occupiers +# - 33k private rentals +# - 39k social housing + +# We can't seem to identify the properties owned by the council in the company ownership data, because what is the +# entity that owns the property? Is it the council, or is it a company that is owned by the council? We can't be sure +# and so since BCC owns 54,000 social housing properties (5k) supported housing +# [https://www.birmingham.gov.uk/info/50094/housing_options/2686/apply_for_social_housing#:~:text=We%20manage +# %20around%2054%2C000%20social,a%20member%20of%20your%20household.] +# and there are 78,410 social housing properties in Birmingham, we can assume that the council owns 54,000 of these +# and so 69% of the social housing is owned by the Council + +# Since we saw that 38,779 of 78,410 social housing looked to be able to benefit from ECO/GBIS funding, we can assume +# that 69% of these are owned by the council, which is 26,757 properties + +# So, with these assumptions in mind: +# We can commit to [x] per annum based on your 54k council-owned, of which approximately 27k are likely to be eligible +# for some form of ECO/GBIS funding. We will work directly with Housing associations to address the remaining 12k +# social properties that may be eligible for funding through ECO/GBIS. +# We will market directly to the 33k private rentals and 155k owner occupiers that are eligible for funding, +# and assuming a 5% conversion, will aim to complete work on diff --git a/etl/customers/newhaven/__init__.py b/etl/customers/newhaven/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/etl/customers/newhaven/newhaven_study.py b/etl/customers/newhaven/newhaven_study.py new file mode 100644 index 00000000..67471813 --- /dev/null +++ b/etl/customers/newhaven/newhaven_study.py @@ -0,0 +1,378 @@ +import inspect +import pandas as pd +from etl.epc.settings import EARLIEST_EPC_DATE +from pathlib import Path +import numpy as np +from utils.s3 import save_csv_to_s3 + +src_file_path = inspect.getfile(lambda: None) + +EPC_DIRECTORY = Path(src_file_path).parent / "local_data" / "all-domestic-certificates" +CUSTOMER_DATA_DIRECTORY = "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Newhaven/Data" + +USER_ID = 8 +PORTFOLIO_ID = 90 + + +def make_asset_list(): + """ + Set up a small asset list for the study + """ + + # Read in EPC data for Lewes + lewes_directory = EPC_DIRECTORY / "domestic-E07000063-Lewes/certificates.csv" + epc_data = pd.read_csv(lewes_directory, low_memory=False) + # Rename the columns to the same format as the api returns + epc_data.columns = [c.replace("_", "-").lower() for c in epc_data.columns] + + # Take just date before the date threshold + epc_data = epc_data[epc_data["lodgement-date"] >= EARLIEST_EPC_DATE] + + epc_data = epc_data[~pd.isnull(epc_data["uprn"])] + epc_data["uprn"] = epc_data["uprn"].astype(int).astype(str) + # Take the newest EPC per uprn + epc_data = epc_data.sort_values("lodgement-date").groupby("uprn").last().reset_index() + # /Users/khalimconn-kowlessar/Documents/hestia/Customers/Newhaven/Data/ + # We read in the multiple data sources + address_base = pd.read_csv( + f"{CUSTOMER_DATA_DIRECTORY}/OS AddressBase Premium/OS AddressBase Premium.csv", + low_memory=False, + ) + # Filter on resi + address_base = address_base[address_base["Primary Code Description"] == "Residential"] + address_base["UPRN"] = address_base["UPRN"].astype(int).astype(str) + + pv_potential = pd.read_csv( + f"{CUSTOMER_DATA_DIRECTORY}/Domestic Rooftop PV Potential/Domestic Rooftop PV Potential.csv", + low_memory=False, + ) + pv_potential["UPRN"] = pv_potential["UPRN"].astype(int).astype(str) + + ashp_potential = pd.read_csv( + f"{CUSTOMER_DATA_DIRECTORY}/Air Source Heat Pump Potential/Air Source Heat Pump Potential.csv", + low_memory=False, + ) + ashp_potential["UPRN"] = ashp_potential["UPRN"].astype(int).astype(str) + + ashp_potential[ashp_potential["UPRN"] == "100060067063"].squeeze() + + insulation_potential = pd.read_csv( + f"{CUSTOMER_DATA_DIRECTORY}/Insulation Potential/Insulation Potential.csv", + low_memory=False, + ) + insulation_potential["UPRN"] = insulation_potential["UPRN"].astype(int).astype(str) + + renewables_cost = pd.read_csv( + f"{CUSTOMER_DATA_DIRECTORY}/Low Carbon Technology Costs/Low Carbon Technology Costs.csv", + low_memory=False, + ) + renewables_cost["UPRN"] = renewables_cost["UPRN"].astype(int).astype(str) + + # Merge the EPC data onto address base + asset_list = address_base[ + [ + "UPRN", "Class Description", "Relative Height - Eaves", + ] + ].merge( + epc_data[ + ["uprn", "current-energy-efficiency", "current-energy-rating", "address1", "postcode", "floor-height", + "property-type", "built-form", "co2-emissions-current"]], + how="left", + left_on="UPRN", + right_on="uprn" + ).drop( + columns=["uprn"] + ).merge( + insulation_potential[["UPRN", "EPC Rating", "Wall Area [m^2]", "Building Area [m^2]"]], + how="left", + on="UPRN" + ).rename( + columns={"Wall Area [m^2]": "insulation_wall_area", "Building Area [m^2]": "floor_area"} + ) + + had_an_epc = asset_list[~pd.isnull(asset_list["current-energy-efficiency"])] + below_b = asset_list[asset_list["current-energy-efficiency"].astype(float) <= 80].shape + below_c = asset_list[asset_list["current-energy-efficiency"].astype(float) <= 69].shape + had_an_epc["energy-efficiency-rating"].value_counts() + asset_list["current-energy-rating"].value_counts() + asset_list["co2-emissions-current"].mean() + # # Get the underlying data of a histograme + import matplotlib.pyplot as plt + n, bins, patches = plt.hist(asset_list["co2-emissions-current"], bins=100, color="blue", alpha=0.7) + # + bins = np.arange(0, asset_list["co2-emissions-current"].max(), 1) # Bins from 50 to 150 with a step of 10 + # + # # Step 3: Calculate the frequency of data in each bin + hist, bin_edges = np.histogram(asset_list["co2-emissions-current"], bins=bins) + + # Take properties below a B - there are 2844 units + asset_list = asset_list[asset_list["current-energy-efficiency"].astype(float) <= 80] + # Drop caravans + asset_list = asset_list[asset_list["Class Description"] != "Caravan"] + asset_list = asset_list[~pd.isnull(asset_list["current-energy-efficiency"])] + + # Take a sample, for properties that have an EPC, with a seed + # asset_list = asset_list.sample(frac=0.5, random_state=42) + + AVG_FLOOR_HEIGHT = asset_list["floor-height"].median() + + def estimate_n_floors( + building_height, floor_height, address_base_property_description, epc_property_type, + ): + + if address_base_property_description == "Self Contained Flat (Includes Maisonette / Apartment)": + if epc_property_type in ["Flat"]: + return 1 + if epc_property_type == "Maisonette": + return 2 + return None + + if pd.isnull(floor_height): + return np.round(building_height / AVG_FLOOR_HEIGHT) + + return np.round(building_height / floor_height) + + # Estimate the number of floors + asset_list["number_of_floors"] = asset_list.apply( + lambda x: estimate_n_floors( + building_height=x["Relative Height - Eaves"], + floor_height=x["floor-height"], + address_base_property_description=x["Class Description"], + epc_property_type=x["property-type"], + ), + axis=1 + ) + # Drop any entires with null floors because that means the ordnance survey data doesn't align with the epc data + asset_list = asset_list[~pd.isnull(asset_list["number_of_floors"])] + # Drop any entries with null insulation wall area + asset_list = asset_list[~pd.isnull(asset_list["insulation_wall_area"])] + + # D 0.419929 + # C 0.391459 + # E 0.160142 + # F 0.017794 + # G 0.010676 + + # Total asset list: + # D 0.450409 + # C 0.412016 + # E 0.110203 + # F 0.020263 + # G 0.007110 + + # We do the followings: + # 1) Create final asset list + # 2) Create Non-intrusive recommendations + # 3) Create a third party costing object + + cost_testing = renewables_cost.merge( + insulation_potential, how="inner", on="UPRN" + ) + + cost_testing["cwi_cost_per_m2"] = cost_testing["Insulation - Cavity Wall - Total"] / cost_testing["Wall Area [m^2]"] + # Their cavity wall insulation is £8 per m^2 + + cost_testing["ewi_cost_per_m2"] = cost_testing["Insulation - External Wall - Total"] / cost_testing[ + "Wall Area [m^2]"] + + cost_testing["li_cost_per_m2"] = cost_testing["Insulation - Loft - Total"] / cost_testing["Building Area [m^2]"] + + cost_testing["underfloor_cost_per_m2"] = cost_testing["Insulation - Under Floor- Total"] / cost_testing[ + "Building Area [m^2]"] + + final_asset_list = asset_list.rename( + columns={"UPRN": "uprn", "address1": "address", "floor_area": "insulation_floor_area"} + )[["uprn", "address", "postcode", "insulation_wall_area", "insulation_floor_area", "number_of_floors"]] + + # Create non-invasive recommendations, which come from the solar potential and ASHP potential data sources + non_invasive_recommendations = [] + for _, row in final_asset_list.iterrows(): + property_ashp_potential = ashp_potential[ + (ashp_potential["UPRN"] == row["uprn"]) & ashp_potential["Overall Suitability Rating"] + ] + property_pv_potential = pv_potential[ + (pv_potential["UPRN"] == row["uprn"]) & pv_potential["Overall Suitability"] + ] + property_costs = renewables_cost[renewables_cost["UPRN"] == row["uprn"]] + + property_non_invasive_recs = [] + if not property_ashp_potential.empty: + + if property_costs.empty: + similar_properties = ashp_potential[ + ashp_potential["Overall Suitability Rating"] & + (ashp_potential["Recommended Heat Pump Size [kW]"] == + property_ashp_potential["Recommended Heat Pump Size [kW]"].values[0]) + ].merge( + renewables_cost, how="inner", on="UPRN" + ) + property_costs = similar_properties[["Air Source Heat Pump - Total"]].mean().to_frame().T + + property_non_invasive_recs.append( + { + "type": "air_source_heat_pump", + "suitable": True, + "size": property_ashp_potential["Recommended Heat Pump Size [kW]"].values[0], + "cost": property_costs["Air Source Heat Pump - Total"].values[0], + "ashp_only_heating_recommendation": True + } + ) + else: + property_non_invasive_recs.append( + { + "type": "air_source_heat_pump", + "suitable": False + } + ) + + if not property_pv_potential.empty: + property_non_invasive_recs.append( + { + "type": "solar_pv", + "suitable": True, + "array_wattage": property_pv_potential["Recommended Array Size [kW]"].values[0] * 1000, + "initial_ac_kwh_per_year": property_pv_potential["Annual Generation [kWh]"].values[0], + "panneled_roof_area": property_pv_potential["Roof area suitable for PV [m^2]"].values[0], + "cost": property_costs["Rooftop PV - Total"].values[0], + } + ) + else: + property_non_invasive_recs.append( + { + "type": "solar_pv", + "suitable": False + } + ) + + non_invasive_recommendations.append( + { + "uprn": row["uprn"], + "recommendations": property_non_invasive_recs, + } + ) + + # Save the asset list + + # Store the asset list in s3 + filename = f"{USER_ID}/{PORTFOLIO_ID}/pilot.csv" + save_csv_to_s3( + dataframe=final_asset_list, + bucket_name="retrofit-plan-inputs-dev", + file_name=filename + ) + + # Store non-invasive recommendations in S3 + non_invasive_recommendations_filename = f"{USER_ID}/{PORTFOLIO_ID}/non_invasive_recommendations.csv" + save_csv_to_s3( + dataframe=pd.DataFrame(non_invasive_recommendations), + bucket_name="retrofit-plan-inputs-dev", + file_name=non_invasive_recommendations_filename + ) + + # We add a patch to one of the units because there's no data for the built form + # We would be able to handle this automatically in the future, when using OS API + patches = [ + { + "uprn": "10033266220", + "built-form": "Semi-Detached", + }, + {'uprn': '10033266219', 'built-form': 'Semi-Detached'} + ] + + # Store patches in s3 + patches_filename = f"{USER_ID}/{PORTFOLIO_ID}/patches.json" + save_csv_to_s3( + dataframe=pd.DataFrame(patches), + bucket_name="retrofit-plan-inputs-dev", + file_name=patches_filename + ) + + # Create three scenarios + body1 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": patches_filename, + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "Demand Reduction - no solid wall, windows, LEDs", + "multi_plan": True, + "exclusions": [ + "internal_wall_insulation", "external_wall_insulation", "floor_insulation", "heating", "solar_pv", + "lighting", "windows", "secondary_heating" + ], + "budget": None, + } + print(body1) + + body2 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": patches_filename, + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "Demand Reduction - no solid wall, floors or heating", + "multi_plan": True, + "exclusions": [ + "internal_wall_insulation", "external_wall_insulation", "floor_insulation", "heating", "solar_pv", + ], + "budget": None, + } + print(body2) + + # 2.5 - full fabric, no decant + body2_5 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": patches_filename, + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "Demand Reduction - no solid wall, floors or heating", + "multi_plan": True, + "exclusions": [ + "internal_wall_insulation", "floor_insulation", "heating", "solar_pv", + ], + "budget": None, + } + print(body2_5) + + # Scenario B + body3 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": patches_filename, + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "Demand Reduction, Heating Systems, Solar PV - no solid wall or floors", + "multi_plan": True, + "exclusions": ["internal_wall_insulation", "external_wall_insulation", "floor_insulation"], + "budget": None, + } + print(body3) + + # Scenario 4 - deep fabric, no IWI, floor + body4 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": patches_filename, + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "Whole House", + "multi_plan": True, + "budget": None, + } + print(body4) diff --git a/etl/customers/newhaven/slides.py b/etl/customers/newhaven/slides.py new file mode 100644 index 00000000..2fe914e2 --- /dev/null +++ b/etl/customers/newhaven/slides.py @@ -0,0 +1,417 @@ +from tqdm import tqdm +import pandas as pd +import numpy as np +from sqlalchemy.orm import sessionmaker +from backend.app.db.connection import db_engine +from backend.app.db.models.recommendations import Recommendation, Plan, PlanRecommendations, Scenario +from backend.app.db.models.portfolio import PropertyModel, PropertyDetailsEpcModel + + +def get_data(portfolio_id, scenario_ids): + session = sessionmaker(bind=db_engine)() + session.begin() + + # Get properties and their details for a specific portfolio + properties_query = session.query( + PropertyModel, + PropertyDetailsEpcModel + ).join( + PropertyDetailsEpcModel, PropertyModel.id == PropertyDetailsEpcModel.property_id + ).filter( + PropertyModel.portfolio_id == portfolio_id # Filter by portfolio ID + ).all() + + # Transform properties data to include all fields dynamically + properties_data = [ + {**{col.name: getattr(prop.PropertyModel, col.name) for col in PropertyModel.__table__.columns}, + **{col.name: getattr(prop.PropertyDetailsEpcModel, col.name) for col in + PropertyDetailsEpcModel.__table__.columns}} + for prop in properties_query + ] + + # Get property IDs from fetched properties + + # Get plans linked to the fetched properties + plans_query = session.query(Plan).filter(Plan.scenario_id.in_(scenario_ids)).all() + + # Transform plans data to include all fields dynamically + plans_data = [ + {col.name: getattr(plan, col.name) for col in Plan.__table__.columns} + for plan in plans_query + ] + + # Extract plan IDs for filtering recommendations through PlanRecommendations + plan_ids = [plan['id'] for plan in plans_data] + + # Get recommendations through PlanRecommendations for those plans and that are default + recommendations_query = session.query( + Recommendation, + Plan.scenario_id + ).join( + PlanRecommendations, Recommendation.id == PlanRecommendations.recommendation_id + ).join( + Plan, Plan.id == PlanRecommendations.plan_id # Join with Plan to access scenario_id + ).filter( + PlanRecommendations.plan_id.in_(plan_ids), + Recommendation.default == True # Filtering for default recommendations + ).all() + + # Transform recommendations data to include all fields dynamically and include scenario_id + recommendations_data = [ + {**{col.name: getattr(rec.Recommendation, col.name) if hasattr(rec, 'Recommendation') else getattr(rec, + col.name) for + col in Recommendation.__table__.columns}, + "Scenario ID": rec.scenario_id} + for rec in recommendations_query + ] + + session.close() + + return properties_data, plans_data, recommendations_data + + +def estimate_post_retrofit_heating_hotwater_kwh(properties_df, recommendations_df, scenario_ids): + # properties_starting_with_electric_heating = properties_df[ + # properties_df["mainfuel"].isin( + # ["Electricity not community", "Electricity electricity unspecified tariff"] + # ) + # ]["id"].tolist() + + # Get the recommendations for the scenario, default + scenario_comparison_df = [] + scenario_comparison_df_2 = [] + cost_per_kwh_saved_table = [] + for scenario_id in scenario_ids: + # Get the recommendations for the scenario, default + scenario_recommendations = recommendations_df[ + (recommendations_df["Scenario ID"] == scenario_id) & + (recommendations_df["default"] == True) + ].copy() + + scenario_recommendations['ligting_kwh'] = scenario_recommendations.apply( + lambda x: x['kwh_savings'] if x['type'] == 'low_energy_lighting' else 0, + axis=1) + scenario_recommendations['solar_kwh'] = scenario_recommendations.apply( + lambda x: x['kwh_savings'] if x['type'] == 'solar_pv' else 0, axis=1) + + # Set 'Estimated Kwh Savings' to zero where specific kwh columns are used + scenario_recommendations['Estimated Kwh Savings'] = scenario_recommendations.apply( + lambda x: 0 if x['type'] in ['low_energy_lighting', 'solar_pv'] else x[ + 'kwh_savings'], axis=1) + + # We need to determine if any of the properties start with electric heating or end with it + # property_electric_heating = [] + # for pid, recs in scenario_recommendations.groupby("property_id"): + # has_ashp = recs[recs["description"].str.contains("air source heat pump")] + # if not has_ashp.empty: + # property_electric_heating.append(pid) + # continue + # has_heating_rec = recs[recs["description"].str.contains("high heat retention electric")] + # if not has_heating_rec.empty: + # property_electric_heating.append(pid) + # continue + + grouped_data = scenario_recommendations.groupby(['property_id']).agg({ + 'Estimated Kwh Savings': 'sum', + 'ligting_kwh': 'sum', + 'solar_kwh': 'sum', + "estimated_cost": "sum" + }).reset_index() + + comparison = properties_df.drop_duplicates().merge( + grouped_data, on=["property_id"], how="left" + ) + + comparison["Post Retrofit Heating & Hotwater kwh"] = ( + comparison["current_energy_demand_heating_hotwater"] - \ + comparison["Estimated Kwh Savings"] + ) + + avgs = comparison[['current_energy_demand_heating_hotwater', 'Post Retrofit Heating & Hotwater kwh']].mean() + + # We now, for properties that have a plan, do a before and after + with_savings = comparison[~pd.isnull(comparison["Estimated Kwh Savings"])] + + avgs2 = with_savings[ + ['current_energy_demand_heating_hotwater', 'Post Retrofit Heating & Hotwater kwh']].mean() + avgs2["difference"] = avgs2["current_energy_demand_heating_hotwater"] - avgs2[ + "Post Retrofit Heating & Hotwater kwh"] + avgs2["percentage_reduction"] = 100 * avgs2["difference"] / avgs2["current_energy_demand_heating_hotwater"] + + # We also calculate the cost per kwh saves + total_kwh_saved = ( + with_savings["Estimated Kwh Savings"].sum() + + with_savings["ligting_kwh"].sum() + + with_savings["solar_kwh"].sum() + ) + total_cost = with_savings["estimated_cost"].sum() + cost_per_kwh_saved = total_cost / total_kwh_saved + + scenario_comparison_df.append({"scenario_id": scenario_id, **avgs}) + scenario_comparison_df_2.append({"scenario_id": scenario_id, **avgs2}) + cost_per_kwh_saved_table.append({"scenario_id": scenario_id, "cost_per_kwh_saved": cost_per_kwh_saved}) + + scenario_comparison_population = pd.DataFrame(scenario_comparison_df) + scenario_comparison_retrofitted_units = pd.DataFrame(scenario_comparison_df_2) + cost_per_kwh_saved_table = pd.DataFrame(cost_per_kwh_saved_table) + + return scenario_comparison_population, scenario_comparison_retrofitted_units, cost_per_kwh_saved_table + + +def slides(): + # Prepares the information required for the slides + + # Right now this is the second version of the nehaven portfolio + portfolio_id = 90 + # Look at one scenario at a time, otherwise this is agony + scenario_ids = [47, 48, 49, 50, 51] + + properties_data, plans_data, recommendations_data = get_data(portfolio_id, scenario_ids) + + properties_df = pd.DataFrame(properties_data) + plans_df = pd.DataFrame(plans_data) + recommendations_df = pd.DataFrame(recommendations_data) + + if properties_df.shape[0] != 2553: + raise ValueError("The number of unique properties is not 2553") + + # Q1: What is the baseline heating and energy demand for the properties in the portfolio - baseline? + heating_hotwater_kwh = ( + properties_df[['current_energy_demand', 'current_energy_demand_heating_hotwater']] + .mean() + ) + + # Q2: For each scenario, what is for what is the heating and hot water kwh after retrofit, on the entire + # popoulation (incl those without retrofit) and for just those being retrofit + # We also calculat the cost per kwh saved + scenario_comparison_population, scenario_comparison_retrofitted_units, cost_per_kwh_saved_table = ( + estimate_post_retrofit_heating_hotwater_kwh(properties_df, recommendations_df, scenario_ids) + ) + + # Q3: For each scenario, we want to answer what the heating and hot water kwh looks like after retrofit + # We need to take recommndations that affect just the heating and hot water + + # By property + + recommendations_df["type_mapped"] = recommendations_df["type"].copy().replace( + { + "loft_insulation": "roof_insulation", + "room_roof_insulation": "roof_insulation", + "flat_roof_insulation": "roof_insulation", + "hot_water_tank_insulation": "other", + "cylinder_thermostat": "other", + "sealing_open_fireplace": "other", + "suspended_floor_insulation": "floor_insulation", + "solid_floor_insulation": "floor_insulation", + } + ) + + recommendations_df["type_mapped"] = np.where( + recommendations_df["description"].str.contains("air source heat pump"), + "air_source_heat_pump", + recommendations_df["type_mapped"] + ) + + # Group by 'Plan Name' and 'Recommendation Type' and count unique 'Property ID' + recommendation_summary = recommendations_df[recommendations_df["default"] == True].groupby( + ['Scenario ID', 'type_mapped'] + ).agg({ + 'property_id': 'nunique' + }).reset_index() + + recommendation_summary.columns = ['Scenario ID', 'Type Mapped', 'Number of Properties'] + recommendation_summary["Percentage of Properties"] = 100 * ( + recommendation_summary["Number of Properties"] / properties_df["id"].nunique() + ) + + recommendation_summary_final_scenario = recommendation_summary[recommendation_summary["Scenario ID"].isin([51])] + + # MVP implementation of funding estimation for the most basic scenario, using GBIS + + project_scores_matrix = pd.read_csv("/Users/khalimconn-kowlessar/Downloads/ECO4 Full Project Scores Matrix.csv") + + def find_abs(sap_movement, starting_sap, floor_area): + starting_band = find_band(starting_sap) + finishing_band = find_band(starting_sap + sap_movement) + if starting_band == finishing_band: + return 0 + + if floor_area <= 72: + floor_area_segment = '0-72' + elif (floor_area > 72) and (floor_area <= 97): + floor_area_segment = "73-97" + elif (floor_area > 97) and (floor_area <= 199): + floor_area_segment = "98-199" + else: + floor_area_segment = "200+" + + return project_scores_matrix[ + (project_scores_matrix["Floor Area Segment"] == floor_area_segment) & + (project_scores_matrix["Starting Band"] == starting_band) & + (project_scores_matrix["Finishing Band"] == finishing_band) + ].squeeze()["Cost Savings"] + + eco4_scores_sap_table = [ + {'Band': 'High_A', 'From': 96.0, 'Up to': 100.0, 'Mid-point': 98.0}, + {'Band': 'Low_A', 'From': 92.0, 'Up to': 96.0, 'Mid-point': 94.0}, + {'Band': 'High_B', 'From': 86.0, 'Up to': 91.0, 'Mid-point': 88.5}, + {'Band': 'Low_B', 'From': 81.0, 'Up to': 86.0, 'Mid-point': 83.5}, + {'Band': 'High_C', 'From': 74.5, 'Up to': 80.0, 'Mid-point': 77.25}, + {'Band': 'Low_C', 'From': 69.0, 'Up to': 74.5, 'Mid-point': 71.75}, + {'Band': 'High_D', 'From': 61.5, 'Up to': 68.0, 'Mid-point': 64.75}, + {'Band': 'Low_D', 'From': 55.0, 'Up to': 61.5, 'Mid-point': 58.25}, + {'Band': 'High_E', 'From': 46.5, 'Up to': 54.0, 'Mid-point': 50.25}, + {'Band': 'Low_E', 'From': 39.0, 'Up to': 46.5, 'Mid-point': 42.75}, + {'Band': 'High_F', 'From': 29.5, 'Up to': 38.0, 'Mid-point': 33.75}, + {'Band': 'Low_F', 'From': 21.0, 'Up to': 29.5, 'Mid-point': 25.25}, + {'Band': 'High_G', 'From': 10.5, 'Up to': 20.0, 'Mid-point': 15.25}, + {'Band': 'Low_G', 'From': 1.0, 'Up to': 10.5, 'Mid-point': 5.75} + ] + eco4_scores_sap_table = pd.DataFrame(eco4_scores_sap_table) + + def find_band(value): + # Iterate through each row in the DataFrame to find the correct band + value_floored = np.floor(value) + return eco4_scores_sap_table[ + (eco4_scores_sap_table["From"] <= value_floored) & (eco4_scores_sap_table["Up to"] >= value_floored) + ].squeeze()["Band"] + + def identify_funding_measure(p, p_recs, is_social): + measures = ["cavity_wall_insulation", "loft_insulation"] + property_abs = [] + for m in measures: + funding_measure = p_recs[p_recs["type"] == m] + if not funding_measure.empty: + funding_measure = funding_measure.squeeze() + project_abs = find_abs( + sap_movement=funding_measure["sap_points"], + starting_sap=p["current_sap_points"], + floor_area=p["total_floor_area"] + ) + property_abs.append({ + "property_id": p["property_id"], + "measure": funding_measure["type"], + "cost": funding_measure["estimated_cost"], + "abs": project_abs, + "is_social": is_social + }) + + if not property_abs: + return None + + property_abs = pd.DataFrame(property_abs).sort_values("cost", ascending=False) + property_abs = property_abs.head(1).to_dict(orient="records")[0] + return property_abs + + social_tenure = ["rental (social)", "Rented (social)"] + scenario_recs = recommendations_df[recommendations_df["Scenario ID"].isin([47])] + + funding = [] + for _, p in tqdm(properties_df.iterrows(), total=len(properties_df)): + p_recs = scenario_recs[scenario_recs["property_id"] == p["property_id"]] + if p_recs.empty: + continue + + if (p["tenure"] in social_tenure) and (p["current_sap_points"] < 69): + f = identify_funding_measure(p, p_recs, True) + if f: + funding.append(f) + continue + + if p["current_sap_points"] < 69: + f = identify_funding_measure(p, p_recs, False) + if f: + funding.append(f) + continue + + funding = pd.DataFrame(funding) + conservative_abs = 20 + funding["expected_funding"] = funding["abs"] * conservative_abs + # We take rows where the expected funding is higher than the cost of the works + 10% + funding = funding[funding["expected_funding"] >= (funding["cost"] * 1.15)] + + # From the owner of the properties, the funding that they see is just the cost of the works. The actual funding + # recieved will go to the installer + # We now look at the social funding + social_funding = funding[funding["is_social"]]["cost"].sum() + # For the private funding, we need to scale this to consider the fact that only a proportion of the properties + # will qualify due to needing the property to fall into council tax bands A - D, and that only some of the tenants + # will meet the benefits criteria + private_funding = funding[~funding["is_social"]]["cost"].sum() + + # 51% of households are recipients of benefits in the South East, in the UK + # (2021/2022 - https://www.statista.com/statistics/382858/uk-state-benefits-by-region/) + + # We also need to deduce the % of properties in council tax bands A - D + # 2023 council tax bands: + # https://www.gov.uk/government/statistics/council-tax-stock-of-properties-2023/council-tax-stock-of-properties + # -statistical-commentary + band_a_proportion = 0.239 + band_b_proportion = 0.195 + band_c_proportion = 0.219 + band_d_proportion = 0.156 + a_to_d_proportion = band_a_proportion + band_b_proportion + band_c_proportion + band_d_proportion + + benefits_proportion = 0.51 + + # Note: It's probable that an occupant of a property in council tax bands A-D is more likely to be on benefits, + # however we retain the regional average to be conservative + # We scale the private funding based on these two factors + private_funding_scaled = private_funding * benefits_proportion * a_to_d_proportion + + n_private_projects = np.round((~funding["is_social"]).sum() * benefits_proportion * a_to_d_proportion) + + # Look at the impact of EWI for scenario + + ewi_jobs = recommendations_df[ + (recommendations_df["Scenario ID"] == 49) & (recommendations_df["type"] == "external_wall_insulation") + ] + ewi_jobs["estimated_cost"].sum() + + has_cavity = recommendations_df[ + (recommendations_df["type"] == "cavity_wall_insulation") & (recommendations_df["Scenario ID"] == 47) + ] + # Take the some properties in this + cavity_units = properties_df[properties_df["property_id"].isin(has_cavity["property_id"].values)] + + cavity_units[cavity_units.index == 3][["uprn", "property_id"]] + + z = recommendations_df[recommendations_df["property_id"] == 24525] + + # Recommenation type by kwh savings per unit + recommendations_final_scenario = recommendations_df[ + recommendations_df["Scenario ID"].isin([51]) & + (recommendations_df["default"] == True) + ].copy() + # Merge on floor area + recommendations_final_scenario = recommendations_final_scenario.merge( + properties_df[["property_id", "total_floor_area"]], on="property_id", how="left" + ) + recommendations_final_scenario = recommendations_final_scenario[ + ~pd.isnull(recommendations_final_scenario["total_floor_area"])] + recommendations_final_scenario["kwh_savings_per_unit"] = recommendations_final_scenario["kwh_savings"] / \ + recommendations_final_scenario["total_floor_area"] + + recommendations_final_scenario["type_mapped2"] = recommendations_df["type"].copy().replace( + { + "room_roof_insulation": "roof_insulation", + "flat_roof_insulation": "roof_insulation", + "hot_water_tank_insulation": "other", + "cylinder_thermostat": "other", + "sealing_open_fireplace": "other", + "suspended_floor_insulation": "floor_insulation", + "solid_floor_insulation": "floor_insulation", + } + ) + + aggs = recommendations_final_scenario.groupby("type_mapped")[ + ["kwh_savings_per_unit", "estimated_cost"]].mean().reset_index().sort_values( + "kwh_savings_per_unit", ascending=False + ) + aggs["cost_per_kwh_saved"] = aggs["estimated_cost"] / aggs["kwh_savings_per_unit"] + # Show more columns with pandas + pd.set_option('display.max_columns', None) + # Show more rows with pandas + pd.set_option('display.max_rows', None) + # Show more characters in a column + pd.set_option('display.max_colwidth', None) diff --git a/etl/customers/orbit/archetypes.py b/etl/customers/orbit/archetypes.py new file mode 100644 index 00000000..cee18267 --- /dev/null +++ b/etl/customers/orbit/archetypes.py @@ -0,0 +1,420 @@ +import pandas as pd +import numpy as np +from backend.SearchEpc import SearchEpc +from dotenv import load_dotenv +from tqdm import tqdm +import os + +load_dotenv(dotenv_path="backend/.env") +EPC_AUTH_TOKEN = os.getenv("EPC_AUTH_TOKEN") + + +def clean_colnames(df): + secondary_cols = ["" if pd.isnull(x) else x for x in df.iloc[0, :].values] + new_colnames = [ + "+".join([df.columns[i], secondary_cols[i]]) if secondary_cols[i] else df.columns[i] + for i, c in enumerate(df.columns) + ] + # Drop row 0 + df = df.drop(0) + df.columns = new_colnames + return df + + +def lesney_farms(): + """ + Some rough and ready analysis to get a view of what the achetypes could be, ahead of a meeting with Wates + on the 28th Aug 2024 + :return: + """ + + all_locations = [ + "Forest Road Erith", + "Lesney Farms", + "Brook Street 155 - 243", + "Hazel Drive", + "Page Crescent", + "Brook Salmon Roberts and Chapma", + "Beacon Road" + ] + + all_assets = pd.read_excel( + "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Orbit - Wates/Bexley Wave 3 Project - external - " + "reduced.xlsx", + sheet_name="Full Property List", + header=1 + ) + all_assets = clean_colnames(all_assets) + all_assets["Location"] = None + + locations = { + location_name: clean_colnames(pd.read_excel( + "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Orbit - Wates/Bexley Wave 3 Project - external - " + "reduced.xlsx", + sheet_name=location_name, + header=1 + )) for location_name in all_locations + } + + for loc in all_locations: + all_assets["Location"] = np.where( + all_assets["Asset Reference"].isin(locations[loc]["Asset Reference"]), + loc, + all_assets["Location"] + ) + + if pd.isnull(all_assets["Location"]).sum(): + raise Exception("something went wrong") + + # 234 properties below EPC C + below_epc_c = all_assets[all_assets["PRE CALCULATED EPC"].isin(["D", "E", "F", "G"])].copy() + + # We simplify wall type + below_epc_c["wall_type_simplified"] = below_epc_c["Wall Type"].str.split(" ").str[0] + + known_no_epc = [ + 28679, # These is no EPC for 11 Page Crescent, Erith, Kent, DA8 2HJ, just 11A + 29291, # No EPC for 225 Slade Green Road, Erith, Kent, DA8 2JW + ] + # Get the EPC data + # epc_data = [] + # for _, home in tqdm(all_assets.iterrows(), total=len(all_assets)): + # if home["Asset Reference"] in known_no_epc: + # continue + # + # address = home["Address"] + # # Spelling error + # if "Frinstead" in address: + # address = address.replace("Frinstead", "Frinsted") + # + # address1 = address.split(",")[0] + # + # asset_type_map = { + # "HOUSE": "House", + # "BUNGALOWS": "Bungalow", + # "FLATS": "Flat", + # "MAISONETTES": "Maisonette", + # } + # + # searcher = SearchEpc( + # address1=address1, + # postcode=home["Address - Postcode"], + # auth_token=EPC_AUTH_TOKEN, + # os_api_key="", + # full_address=address, + # ) + # searcher.ordnance_survey_client.property_type = asset_type_map[home["Asset Type"]] + # searcher.ordnance_survey_client.built_form = None + # + # searcher.find_property(skip_os=True) + # if searcher.newest_epc is None: + # raise Exception("Couldn't find") + # + # epc_data.append( + # { + # "Asset Reference": home["Asset Reference"], + # **searcher.newest_epc.copy() + # } + # ) + # + # epc_data = pd.DataFrame(epc_data) + epc_data = pd.read_csv("/Users/khalimconn-kowlessar/Documents/hestia/Customers/Orbit - Wates/Bexley EPC data.csv", ) + # epc_data.to_csv( + # "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Orbit - Wates/Bexley EPC data.csv", index=False + # ) + + epc_comparison = all_assets[ + ['Asset Reference', 'Address', 'PRE CALCULATED EPC'] + ].merge( + epc_data[["Asset Reference", "current-energy-rating", "lodgement-date"]], + on='Asset Reference', + how="left" + ) + + # There are a large # of properties (147) that have different pre calcualted EPC rating, to what's on the registry + # These may be internally held EPRs but this may inform which properties we might want to prioritise for survey + different_epcs = epc_comparison[ + epc_comparison["PRE CALCULATED EPC"] != epc_comparison["current-energy-rating"] + ] + + not_c = different_epcs[ + (different_epcs["PRE CALCULATED EPC"] == "C") & + (different_epcs["current-energy-rating"] != "C") + ] + + system_builds = below_epc_c[ + below_epc_c["Wall Type"].str.contains("SystemBuilt") + ].copy() + + combinations = system_builds[ + ['Asset Type', 'Property Type', 'Location', 'PRE CALCULATED EPC', 'Wall Type', ] + ].drop_duplicates() + + system_build_data_comparison = system_builds.merge( + epc_data[ + ["Asset Reference", "walls-description", "roof-description", "current-energy-rating", "lodgement-date", + "current-energy-efficiency"]], + left_on='Asset Reference', + right_on='Asset Reference', + how="left" + ) + + # Apply patches + patches = { + 25847: {"Property Type": "Semi Detached House"}, + } + + for asset_ref, patch in patches.items(): + for k, v in patch.items(): + system_build_data_comparison.loc[ + system_build_data_comparison["Asset Reference"] == asset_ref, + k + ] = v + + archetype_columns = [ + ["Asset Type", "Property Type", "Wall Type", "Location"], + ["Asset Type", "Property Type", "Location"], + ["Asset Type", "Property Type", "Wall Type", "Location", "PRE CALCULATED EPC", "roof-description"], + ["Asset Type", "Property Type", "Location", "PRE CALCULATED EPC"] + ] + + summary = [] + for cols in archetype_columns: + combinations = system_build_data_comparison[cols].drop_duplicates() + summary.append( + { + "cols": cols, + "number_archetypes": len(combinations), + } + ) + + summary = pd.DataFrame(summary) + + # Let's use this column combination + chosen_combination = [ + "Asset Type", "Property Type", "Wall Type", "Location", "PRE CALCULATED EPC", "roof-description" + ] + + # For this combination, let's find the properties + archetype_combinations = system_build_data_comparison[chosen_combination].drop_duplicates().reset_index(drop=True) + archetype_combinations["archetype ID"] = archetype_combinations.index + + archetyped_data = system_build_data_comparison.merge( + archetype_combinations, how="left", on=chosen_combination + ) + + counts = archetyped_data["archetype ID"].value_counts() + # Archetype 0: Semi D, As built system built, Pre calculated EPC D, flat insulated roof, (Lesney-0) + # Archetype 1: Semi D, Externally insulated system built, Pre calculated EPC D, flat insulated roof (Lesney-1) + # Archetype 4: Semi D, System built with unknown insulation, Pre calculated EPC D, flat roof insulated (Lesney-2) + # Archetype 3: Semi D, Externally insulated system built, Pre calculated EPC D, flat roof uninsulated (assumed) ( + # Lesney-3) + # 0 21 + # 1 11 + # 4 11 + # 3 3 + # 2 1 + # 5 1 + # 6 1 + # 7 1 + # 8 1 + # 9 1 + + # This archetype is the same as 0, apart from the pre calculate EPC being an E. The registry says this is a D + # This has been added to additonal units + eg1 = archetyped_data[archetyped_data["archetype ID"] == 2] + + # Semi D, System built with unknown insulation, Pre calculated EPC D, flat roof insulated + # This looks like it would fit either in archetype + eg2 = archetyped_data[archetyped_data["archetype ID"] == 5] + + eg3 = archetyped_data[archetyped_data["archetype ID"] == 6] + + # Archetypes 7, 8, 9 are all similar, Semi D, Uninsulated system built, with pitched lofts with up to 200mm + # insulation in the lofts + + # It's just the three units + # They're all labelled as + pitched_system_built_properties = archetyped_data[archetyped_data["archetype ID"].isin([9, 10, 11])] + pitched_system_built_properties["Address"] + + notes = [ + { + "Asset Reference": 27445, + "note": "Confirmed this has a pitched roof on Maps" + }, + { + "Asset Reference": 27443, + "note": "Confirmed this has a pitched roof on Maps" + }, + { + "Asset Reference": 27442, + "note": "Confirmed this has a pitched roof on Maps" + }, + { + "Asset Reference": 25847, + "note": "This is labelled as a mid-terrace but the EPC data + Maps suggest it's a semi-detached" + } + ] + + # These are As Built, System Built + system_built_streets = ( + archetyped_data["Address"].str.split(",").str[0].str.split(" ").str[1].unique() + ) + + all_assets_w_epcs = all_assets.merge(epc_data, on="Asset Reference", how="left") + + # Grab all of the properties on this street that aren't system built + streets_not_system_builds = all_assets_w_epcs[ + all_assets_w_epcs["Address"].str.split(",").str[0].str.split(" ").str[1].isin(system_built_streets) & + ~all_assets_w_epcs["Wall Type"].str.contains("SystemBuilt") + ] + + system_builds = archetyped_data[ + archetyped_data["Wall Type"].str.contains("SystemBuilt") + ][["Asset Reference", "Address", "Wall Type", "walls-description"]].sort_values("Address") + + birling_street_system_builds = system_builds[system_builds["Address"].str.contains("Birling")] + halstead_street_system_builds = system_builds[system_builds["Address"].str.contains("Halstead")] + brasted_street_system_builds = system_builds[system_builds["Address"].str.contains("Brasted")] + frinstead_street_system_builds = system_builds[ + system_builds["Address"].str.contains("Frinstead") | system_builds["Address"].str.contains("Frinsted") + ] + + pd.set_option('display.max_rows', 500) + pd.set_option('display.max_columns', 500) + pd.set_option('display.width', 1000) + streets_not_system_builds[["Asset Reference", "Address", "Wall Type", "walls-description"]] + + system_builds[system_builds["Address"].str.contains("Birling")] + + # Possible System Builds + + # Create the proposed sample + # lesney-0 + archetyped_data["lodgement-date"] = pd.to_datetime(archetyped_data["lodgement-date"]) + + lesney_0 = archetyped_data[archetyped_data["archetype ID"] == 0].copy() + # Get the oldest EPC per postcode + lesney_0 = lesney_0.sort_values(["Address - Postcode", "lodgement-date"]) + lesney_0[["Address", "Address - Postcode", "lodgement-date"]] + + lesney_1 = archetyped_data[archetyped_data["archetype ID"] == 1].copy() + lesney_1 = lesney_1.sort_values(["Address - Postcode", "lodgement-date"]) + lesney_1[["Address", "Address - Postcode", "lodgement-date"]] + + lesney_2 = archetyped_data[archetyped_data["archetype ID"] == 4].copy() + lesney_2 = lesney_2.sort_values(["Address - Postcode", "lodgement-date"]) + lesney_2[["Address", "Address - Postcode", "lodgement-date"]] + + lesney_3 = archetyped_data[archetyped_data["archetype ID"] == 3].copy() + lesney_3 = lesney_3.sort_values(["Address - Postcode", "lodgement-date"]) + lesney_3[["Address", "Address - Postcode", "lodgement-date", "roof-description"]] + + # Get the pitched roof properties, which are lesney-4 + lesney_4 = archetyped_data[archetyped_data["archetype ID"].isin([7, 8, 9])].copy() + lesney_4 = lesney_4.sort_values(["Address - Postcode", "lodgement-date"]) + lesney_4[["Address", "Address - Postcode", "lodgement-date", "roof-description"]] + + assigned_archetypes = archetyped_data[ + ["Asset Reference", "archetype ID", "Address", "Address - Postcode"] + chosen_combination + + ["lodgement-date", "current-energy-rating", "current-energy-efficiency", "walls-description"] + ].copy() + # Map the archetype ID to their string representation + assigned_archetypes["archetype ID"] = assigned_archetypes["archetype ID"].replace( + { + 0: "Lesney-0", + 1: "Lesney-1", + 4: "Lesney-2", + 3: "Lesney-3", + 7: "Lesney-4", + 8: "Lesney-4", + 9: "Lesney-4", + 2: "Lesney-0", + 5: "Lesney-2", + 6: "Lesney-0", + } + ) + + assigned_archetypes["Asset Reference"] = assigned_archetypes["Asset Reference"].astype(int) + + assigned_archetypes.to_csv( + "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Orbit - Wates/assigned_archetypes.csv", index=False + ) + + +def culworth_court(): + """ + Some rough works on Cuthwork Court + + They're looking at an ASHP/GSHP + + :return: + """ + + asset_list = pd.read_excel( + "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Orbit - Wates/001 - EPC CULWORTH COURT.xlsx", + sheet_name="EPC C", + header=1 + ) + asset_list = clean_colnames(asset_list) + + # Let's get the EPC data + # Get the EPC data + epc_data = [] + for _, home in tqdm(asset_list.iterrows(), total=len(asset_list)): + + address = home["Address"] + # Spelling error + if "Frinstead" in address: + address = address.replace("Frinstead", "Frinsted") + + address1 = address.split(",")[0] + + asset_type_map = { + "HOUSE": "House", + "BUNGALOWS": "Bungalow", + "FLATS": "Flat", + "MAISONETTES": "Maisonette", + } + + searcher = SearchEpc( + address1=address1, + postcode=home["Address - Postcode"], + auth_token=EPC_AUTH_TOKEN, + os_api_key="", + full_address=address, + ) + searcher.ordnance_survey_client.property_type = asset_type_map[home["Asset Type"]] + searcher.ordnance_survey_client.built_form = None + + searcher.find_property(skip_os=True) + if searcher.newest_epc is None: + raise Exception("Couldn't find") + + epc_data.append( + { + "Asset Reference": home["Asset Reference"], + **searcher.newest_epc.copy() + } + ) + epc_data = pd.DataFrame(epc_data) + + asset_list = asset_list.merge(epc_data, on="Asset Reference", how="left") + asset_list["floor-level"] = np.where( + asset_list["floor-level"] == "NODATA!", + "", + asset_list["floor-level"] + ) + + asset_list["built-form"] = np.where( + asset_list["built-form"] == "Enclosed End-Terrace", + "End-Terrace", + asset_list["built-form"] + ) + + archetype_combinations = asset_list[ + ["Asset Type", "Property Type", "built-form", "floor-level"] + ].drop_duplicates() + + z = asset_list[asset_list["built-form"] == "Enclosed End-Terrace"] diff --git a/etl/customers/orbit/funding_example_portfolio.py b/etl/customers/orbit/funding_example_portfolio.py new file mode 100644 index 00000000..cf0e151f --- /dev/null +++ b/etl/customers/orbit/funding_example_portfolio.py @@ -0,0 +1,141 @@ +import pandas as pd + +from utils.s3 import save_csv_to_s3 + +USER_ID = 8 +PORTFOLIO_ID = 100 + + +def app(): + """ + This function sets up an asset list with just a few properties to model the impact of the following scenarios: + 1) EWI + 2) EWI + Solar + 3) EWI + Solar + ASHP + :return: + """ + + asset_list = [ + # This is an example of a low D - SAP score is 60 + { + "address": "37, Birling Road", + "postcode": "DA8 3JQ", + "uprn": 100020225444 + }, + { + "address": "16, Brasted Road", + "postcode": "DA8 3HU", + "uprn": 100020225805 + }, + { + "address": "25, Birling Road", + "postcode": "DA8 3JQ", + "uprn": 100020225432, + }, + { + "address": "4, Halstead Road", + "postcode": "DA8 3HX", + "uprn": 100020229555 + } + ] + asset_list = pd.DataFrame(asset_list) + + filename = f"{USER_ID}/{PORTFOLIO_ID}/pilot.csv" + save_csv_to_s3( + dataframe=asset_list, + bucket_name="retrofit-plan-inputs-dev", + file_name=filename + ) + + non_invasive_recs = [] + for _, al in asset_list.iterrows(): + solar_rec = { + "type": "solar_pv", + "suitable": True, + "array_wattage": 4000, + "initial_ac_kwh_per_year": 3800, + "cost": 4009, + "panneled_roof_area": 20 # Rough estimate for 10 panels, around 1m x 1.8m (accomodate gaps and 30cm edge) + } + + non_invasive_recs.append({ + "uprn": al["uprn"], + "recommendations": [solar_rec], + }) + + # Store non-invasive recommendations in S3 + non_invasive_recommendations_filename = f"{USER_ID}/{PORTFOLIO_ID}/non_invasive_recommendations.csv" + save_csv_to_s3( + dataframe=pd.DataFrame(non_invasive_recs), + bucket_name="retrofit-plan-inputs-dev", + file_name=non_invasive_recommendations_filename + ) + + body1 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": "", + "non_invasive_recommendations_file_path": "", + "scenario_name": "ECO4 funding - EWI", + "multi_plan": True, + "exclusions": [ + "internal_wall_insulation", + "roof_insulation", "ventilation", "floor_insulation", "windows", "fireplace", "heating", "hot_water", + "lighting", "secondary_heating", "solar_pv" + ], + "budget": None, + } + print(body1) + + body2 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": "", + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "ECO4 funding - EWI + Solar", + "multi_plan": True, + "exclusions": [ + "internal_wall_insulation", + "roof_insulation", + "ventilation", + "floor_insulation", + "windows", + "fireplace", + "heating", + "hot_water", + "lighting", + "secondary_heating", + "boiler_upgrade", + "high_heat_retention_storage_heater", + ], + "budget": None, + } + print(body2) + + body3 = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "A", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": "", + "non_invasive_recommendations_file_path": non_invasive_recommendations_filename, + "scenario_name": "ECO4 funding - EWI + Solar + ASHP", + "multi_plan": True, + "exclusions": [ + "internal_wall_insulation", + "roof_insulation", "ventilation", "floor_insulation", "windows", "fireplace", "hot_water", + "lighting", "secondary_heating", + ], + "budget": None, + } + print(body3) diff --git a/etl/ownership/Ownership.py b/etl/ownership/Ownership.py new file mode 100644 index 00000000..3bc4b60d --- /dev/null +++ b/etl/ownership/Ownership.py @@ -0,0 +1,1126 @@ +from datetime import datetime +from typing import List +from tqdm import tqdm +import pandas as pd +import Levenshtein +import re +from utils.s3 import save_excel_to_s3, read_excel_from_s3 +from utils.logger import setup_logger +from backend.SearchEpc import SearchEpc +from etl.spatial.OpenUprnClient import OpenUprnClient + +logger = setup_logger() + + +class Ownership: + # These are a number of prefix phrases, found in the ownership data. If an address begins with a any of these + # terms, we remove them + OWNERSHIP_STARTING_TERMS = [ + "land adjoining", "land on the", "land to the rear of", "land and buildings on the", + "garage adjoining", "car park adjoining", "the land adjoining", "land and buildings adjoining", + "all royal mines" + ] + + # anything that is sold within this many months is flagged to have sold recently and is then + # considered to be dropped from matching + SOLD_RECENTLY_MONTHS = 12 + + # Anything that has been lodged for a marketed or unmarketed sale within this many months is + # flagged as potentially in the process of being sold + LODGED_RECENTLY_MONTHS = 12 + + # These are the columns in the land registry data + LAND_REGISTRY_COLUMNS = [ + "transaction_id", + "price", + "date_of_transfer", + "postcode", + "property_type", + "old_new", + "duration", + "paon", + "saon", + "street", + "locality", + "town_city", + "district", + "county", + "ppd_category_type", + "record_status", + ] + + def __init__( + self, + epc_paths: List[str], + domestic_ownership_path: str, + overseas_ownership_path: str, + land_registry_path: str, + project_name: str, + bucket: str, + average_property_value: float, + portfolio_value: float, + excluded_owners: List[str] = None, + excluded_uprns: List[int] = None, + ): + """ + + :param epc_paths: A list of strings, which points to the location of the EPC data to be used. TO date, this + data has been held locally, and so will require extension to read from remote locaations like + s3 + :param domestic_ownership_path: A string which points to the location of the CCOD ownership data, that details + corporate ownership of properties in the UK, where the companies are UK based + :param overseas_ownership_path: A string which points to the location of the OCOD ownership data, that details + corporate ownership of properties in the UK, where the companies are overseas + :param land_registry_path: A string that points to the location of the land registry data + :param project_name: A string that is used to identify the project + :param bucket: The name of the s3 bucket where the data will be stored + :param average_property_value: The average property value in the area + """ + + # All epc paths should end with certificates.csv + if not any(path for path in epc_paths if path.endswith("certificates.csv")): + raise ValueError("epc_paths contains a path that does not end with certificates.csv") + self.epc_paths = epc_paths + self.domestic_ownership_path = domestic_ownership_path + self.overseas_ownership_path = overseas_ownership_path + self.land_registry_path = land_registry_path + + self.excluded_owners = [] if excluded_owners is None else excluded_owners + self.excluded_uprns = [] if excluded_uprns is None else excluded_uprns + + self.run_timestamp = str(datetime.now()) + self.project_name = project_name + self.bucket = bucket + + self.average_property_value = average_property_value + self.portfolio_value = portfolio_value + + # Data storage paths + self.epc_data_filepath = f"ownership/{self.project_name}/{self.run_timestamp}/epc_data.xlsx" + self.filtered_land_registry_filepath = ( + f"ownership/{self.project_name}/{self.run_timestamp}/filtered_land_registry.xlsx" + ) + self.matched_addresses_pre_filter_filepath = ( + f"ownership/{self.project_name}/{self.run_timestamp}/matched_addresses_pre_filter.xlsx" + ) + self.combined_matching_lookup_pre_filter_filepath = ( + f"ownership/{self.project_name}/{self.run_timestamp}/combined_matching_lookup_pre_filter.xlsx" + ) + # Final output paths + self.portfolio_owners_filepath = f"ownership/{self.project_name}/{self.run_timestamp}/portfolio_owners.xlsx" + self.portfolio_properties_filepath = ( + f"ownership/{self.project_name}/{self.run_timestamp}/portfolio_properties.xlsx" + ) + self.portfolio_epc_data_filepath = ( + f"ownership/{self.project_name}/{self.run_timestamp}/portfolio_epc_data.xlsx" + ) + + # Data + self.epc_data = None + self.ownership_data = None + self.freehold_matching_lookup = None + self.leasehold_matching_lookup = None + self.shared_freehold_match = None + self.shared_leasehold_match = None + self.land_registry = None + + # Match tables + self.combined_matching_lookup = None + self.matched_addresses = None + self.land_registry_matches = None + + # Final outputs data + self.portfolio_owners = None + self.portfolio_properties = None + self.portfolio_epc_data = None + + def pipeline(self, column_filters=None): + """ + Runs the full ownership process + :param column_filters: Dictionary with column names as keys and list of acceptable values as values. This + dictionary is is used to filter the EPC data and should look like this: + {"column_name": ["value1", "value2", ...]}, where column_name is the name of the column + in the EPC data and ["value1", "value2", ...] is a list of acceptable values for that + column. If a column is not found in the EPC data, an exception is raised. + """ + # Step 1: Get EPC data + self.source_epc_properties(column_filters=column_filters) + + # Step 2: Get company ownership data + self.load_company_ownership() + + # Step 3: Prepare data for matching + self.prepare_for_matching() + + # Step 4: Match EPC data to ownership data + self.match() + + # Step 5: Match land registry data to existing matches + self.match_with_land_registry() + # We store this data in s3 before we perform any filtering + save_excel_to_s3( + df=self.matched_addresses, + bucket_name=self.bucket, + file_key=self.matched_addresses_pre_filter_filepath + ) + save_excel_to_s3( + df=self.combined_matching_lookup, + bucket_name=self.bucket, + file_key=self.combined_matching_lookup_pre_filter_filepath + ) + + # Prepare the final outputs: + self.create_final_matches() + + def source_epc_properties(self, column_filters=None): + """ + This function will filter the epc data as specified by column filters, searching across all of the EPC tables + :param column_filters: Dictionary with column names as keys and list of acceptable values as values. This + dictionary is is used to filter the EPC data and should look like this: + {"column_name": ["value1", "value2", ...]}, where column_name is the name of the column + in the EPC data and ["value1", "value2", ...] is a list of acceptable values for that + column. If a column is not found in the EPC data, an exception is raised. + """ + + column_filters = {} if column_filters is None else column_filters + + data = [] + for path in tqdm(self.epc_paths): + epc_data = pd.read_csv(path, low_memory=False) + epc_data = epc_data[~pd.isnull(epc_data["UPRN"])] + epc_data["UPRN"] = epc_data["UPRN"].astype(int).astype(str) + + if pd.isnull(pd.to_datetime(epc_data["LODGEMENT_DATETIME"], errors="coerce")).sum(): + raise Exception("Lodgement datetime contains invalid data") + + epc_data["LODGEMENT_DATETIME"] = pd.to_datetime(epc_data["LODGEMENT_DATETIME"], errors="coerce") + epc_data = epc_data.sort_values(["LODGEMENT_DATETIME"], ascending=False).drop_duplicates("UPRN") + + # Apply column filters + for column, values in column_filters.items(): + if column in epc_data.columns: + epc_data = epc_data[epc_data[column].isin(values)] + else: + raise Exception(f"Column {column} not found in data. column_filters is malformed") + + data.append(epc_data) + + self.epc_data = pd.concat(data, ignore_index=True) + + if self.excluded_uprns: + self.epc_data = self.epc_data[~self.epc_data["UPRN"].astype(float).isin(self.excluded_uprns)] + + # We now store the data in s3 + save_excel_to_s3( + df=self.epc_data, + bucket_name=self.bucket, + file_key=self.epc_data_filepath + ) + + def load_company_ownership(self): + """ + This function reads in the company ownership data and + :return: + """ + logger.info("Reading in company ownership data") + self.ownership_data = pd.read_csv(self.domestic_ownership_path) + self.ownership_data["is_overseas"] = False + overseas_company_ownership = pd.read_csv(self.overseas_ownership_path) + overseas_company_ownership["is_overseas"] = True + + self.ownership_data = pd.concat([self.ownership_data, overseas_company_ownership]) + + # FIlter on relevant postcodes - this is done to reduce the large size of the ownership dataset + logger.info("Filtering ownership data on EPC postcodes") + self.ownership_data = self.ownership_data[ + self.ownership_data["Postcode"].str.lower().isin(self.epc_data["POSTCODE"].str.lower().unique()) + ] + + logger.info("Removing excluded owners") + # Use the company registration number to filter out excluded owners + self.ownership_data = self.ownership_data[ + ~self.ownership_data["Company Registration No. (1)"].astype(str).isin(self.excluded_owners) + ] + + def prepare_for_matching(self): + """ + Given the epc properties and the ownership data, this function performs a number of operations on both datasets + to prepare them for matching + """ + + logger.info("Preparing data for matching") + # Now we filter properties the other way around, since the ownership data might not have all of the + # postcodes that appear in the EPC data + self.epc_data = self.epc_data[ + self.epc_data["POSTCODE"].str.lower().isin(self.ownership_data["Postcode"].str.lower().unique()) + ] + # We have some duplicated on UPRN + # Take the newest UPRN + self.epc_data = self.epc_data.sort_values("LODGEMENT_DATE", ascending=False).drop_duplicates("UPRN") + + # Remove entries where the address begins with the term "land adjoining", or other records that don't + # reference the + # the property itself + + for starting_term in self.OWNERSHIP_STARTING_TERMS: + self.ownership_data = self.ownership_data[ + ~self.ownership_data["Property Address"].str.lower().str.startswith(starting_term) + ] + + @staticmethod + def extract_numeric_part(house_number: str) -> str: + """ + Extracts only the numeric part from a house number that may contain letters. + + Parameters: + - house_number (str): The house number string possibly containing letters. + + Returns: + - str: The numeric part of the house number. + """ + # Use regular expression to replace all non-digit characters with nothing + numeric_part = re.sub(r'\D', '', house_number) + return numeric_part + + @staticmethod + def remove_text_in_brackets(address: str) -> str: + """ + Removes any text within parentheses, including the parentheses themselves. + + Parameters: + - address (str): The address string to clean. + + Returns: + - str: The cleaned address with text in parentheses removed. + """ + # Regex to find and remove content in parentheses + cleaned_address = re.sub(r'\s*\([^)]*\)', '', address) + return cleaned_address + + @staticmethod + def extract_range_from_house_number(house_number_range: str): + """ + Detects if the house number includes a numeric range (formatted as 'x-y') and extracts all values within this + range. + Non-numeric strings containing hyphens are ignored. + + Parameters: + - house_number_range (str): The house number string that might contain a range. + + Returns: + - list of str: A list of all numbers within the range if it is a range; otherwise, returns None. + """ + + if not house_number_range: + return None + + if '-' in house_number_range: + parts = house_number_range.split('-') + if len(parts) == 2 and parts[0].isdigit() and parts[1].isdigit(): + # Both parts are numeric, so it's a valid range + start, end = map(int, parts) # Convert parts to integers + return [str(x) for x in range(start, end + 1)] + else: + # Not a valid numeric range + return None + else: + # No hyphen present or not a range + return None + + @staticmethod + def is_in_range(row, house_no): + """ Check if the house number is within the range provided in the row. """ + if row and any(house_no == num for num in row): + return True + return False + + @staticmethod + def levenstein_match(matching_string, df, address_col): + match_to = df[address_col].tolist() + # Strip out punctuation and spaces + match_to = [re.sub(r'[^\w\s]', '', x) for x in match_to] + match_to = [x.replace(" ", "") for x in match_to] + + # Perform matching between full key and match_to + distances = [Levenshtein.distance(matching_string, s) for s in match_to] + best_match_index = distances.index(min(distances)) + # We might want to consider a threshold for the distance, however for the momeny, + # we don't consider this for the moment + df = df.iloc[best_match_index:best_match_index + 1] + + return df + + @classmethod + def remove_duplicate_matches(cls, matching_lookup, properties, company_ownership): + duplicated_titles = matching_lookup[matching_lookup["Title Number"].duplicated()]["Title Number"].unique() + + to_drop = [] + for dupe_title in duplicated_titles: + dupe_data = matching_lookup[matching_lookup["Title Number"] == dupe_title].copy() + matched_addresses = dupe_data.merge( + properties[["UPRN", "ADDRESS"]].rename(columns={"ADDRESS": "epc_address"}), + how="left", on="UPRN" + ).merge( + company_ownership[["Title Number", "Property Address"]], + how="left", on="Title Number" + ) + # We perform levenstein to get the best match + best_match = cls.levenstein_match( + matching_string=matched_addresses["Property Address"].values[0], + df=matched_addresses, + address_col="epc_address" + ) + matches_to_drop = matched_addresses[ + ~matched_addresses["UPRN"].isin(best_match["UPRN"].values) + ] + + to_drop.append( + matches_to_drop[["UPRN", "Title Number"]].copy() + ) + + to_drop = pd.concat(to_drop) if to_drop else pd.DataFrame() + + if not to_drop.empty: + merged = pd.merge(matching_lookup, to_drop, on=['UPRN', 'Title Number'], how='left', indicator=True) + merged = merged[merged['_merge'] == 'left_only'].drop(columns=['_merge']) + + return merged + + return matching_lookup + + @classmethod + def remove_duplicate_uprn_matches(cls, matching_lookup, properties, company_ownership): + dupe_uprns = matching_lookup[matching_lookup["UPRN"].duplicated()]["UPRN"].unique().tolist() + + to_drop = [] + for dupe_uprn in dupe_uprns: + dupe_data = matching_lookup[matching_lookup["UPRN"] == dupe_uprn].copy() + matched_addresses = dupe_data.merge( + properties[["UPRN", "ADDRESS"]].rename(columns={"ADDRESS": "epc_address"}), + how="left", on="UPRN" + ).merge( + company_ownership[["Title Number", "Property Address"]], + how="left", on="Title Number" + ) + # We perform levenstein to get the best match + best_match = cls.levenstein_match( + matching_string=matched_addresses["Property Address"].values[0], + df=matched_addresses, + address_col="epc_address" + ) + matches_to_drop = matched_addresses[ + ~matched_addresses["Title Number"].isin(best_match["Title Number"].values) + ] + + to_drop.append( + matches_to_drop[["UPRN", "Title Number"]].copy() + ) + + to_drop = pd.concat(to_drop) + + if not to_drop.empty: + merged = pd.merge(matching_lookup, to_drop, on=['UPRN', 'Title Number'], how='left', indicator=True) + merged = merged[merged['_merge'] == 'left_only'].drop(columns=['_merge']) + + return merged + + return matching_lookup + + @staticmethod + def is_substring(x, match_string): + if pd.isnull(x): + return False + return x in match_string.lower() + + @staticmethod + def house_number_match(paon, house_number): + # Firstly try and convert to numberic + try: + paon_numeric = int(paon) + house_number_numeric = int(house_number) + return paon_numeric == house_number_numeric + except Exception as e: # noqa + # If we can't convert both to numeric, we do an equality + + return paon == house_number + + @staticmethod + def check_equalities(lr_filtered): + all_paon_equal = all(lr_filtered["paon"] == lr_filtered["paon"].values[0]) + if pd.isnull(lr_filtered["saon"].values[0]): + all_saon_equal = all(pd.isnull(lr_filtered["saon"])) + else: + all_saon_equal = all(lr_filtered["saon"] == lr_filtered["saon"].values[0]) + + all_street_equal = all(lr_filtered["street"] == lr_filtered["street"].values[0]) + + return all_paon_equal, all_saon_equal, all_street_equal + + def match(self): + if (self.epc_data is None) or (self.ownership_data is None): + raise ValueError("epc_data and ownership_data should not be null") + + logger.info("Matching EPC data to ownership data") + freehold_matching_lookup = [] + leasehold_matching_lookup = [] + shared_leasehold_match = [] + shared_freehold_match = [] + for _, address in tqdm(self.epc_data.iterrows(), total=len(self.epc_data)): + match_type = "exact" + filtered = self.ownership_data[ + self.ownership_data["Postcode"].str.lower() == address["POSTCODE"].lower() + ].copy() + + # Remove postcode and remove trailing commas + filtered["house_number"] = ( + filtered["Property Address"] + .apply(self.remove_text_in_brackets) + .apply(SearchEpc.get_house_number) + .str.lower() + .str.replace(",", "") + ) + house_no = SearchEpc.get_house_number(address["ADDRESS1"]) + if house_no is not None: + house_no = house_no.replace(",", "") + + if house_no is None: + # It's hard for us to get a reliable match + # filtered = filtered[filtered["Property Address"].str.contains(address["ADDRESS1"])] + # if filtered.shape[0] > 1: + # raise Exception("No valid - maybe we should do levenstein?") + continue + + else: + + if house_no not in filtered["house_number"].values: + # If this happens, we check house_number for a x-y range of addresses + filtered["house_number_range"] = filtered["house_number"].apply( + self.extract_range_from_house_number + ) + # If we have found a house number range, we check if the house number is in the range and if not, + # we drop the row + filtered['is_in_range'] = filtered['house_number_range'].apply( + lambda x: self.is_in_range(x, house_no) + ) + + if filtered['is_in_range'].any(): + # If house_no is found in any range, keep only rows where it is in range + filtered = filtered[filtered['is_in_range']] + else: + # If house_no is not found in any range, filter out rows where 'house_number_range' is not None + filtered = filtered[filtered['house_number_range'].isnull()] + + # Strip out letters from house_no and house_number + house_no = self.extract_numeric_part(house_no) + filtered["house_number"] = filtered["house_number"].astype(str).apply(self.extract_numeric_part) + match_type = "approximate" + + filtered = filtered[filtered["house_number"] == house_no] + + if filtered.empty: + continue + + filtered_freehold = filtered[filtered["Tenure"] == "Freehold"] + filtered_leasehold = filtered[filtered["Tenure"] == "Leasehold"] + + if filtered_freehold.shape[0] > 1: + matched = filtered_leasehold[["Title Number"]].copy() + matched.insert(0, "UPRN", address["UPRN"]) + shared_freehold_match.append(matched) + elif not filtered_freehold.empty: + freehold_matching_lookup.append( + { + "UPRN": address["UPRN"], + "Title Number": filtered_freehold["Title Number"].values[0], + "match_type": match_type, + } + ) + + if filtered_leasehold.shape[0] > 1: + matched = filtered_leasehold[["Title Number"]].copy() + matched.insert(0, "UPRN", address["UPRN"]) + shared_leasehold_match.append(matched) + elif not filtered_leasehold.empty: + leasehold_matching_lookup.append( + { + "UPRN": address["UPRN"], + "Title Number": filtered_leasehold["Title Number"].values[0], + "match_type": match_type, + } + ) + + logger.info("Matching complete - creating lookup tables") + + self.freehold_matching_lookup = pd.DataFrame(freehold_matching_lookup) + self.leasehold_matching_lookup = pd.DataFrame(leasehold_matching_lookup) + + self.freehold_matching_lookup = self.freehold_matching_lookup[ + self.freehold_matching_lookup["match_type"] == "exact" + ] + self.leasehold_matching_lookup = self.leasehold_matching_lookup[ + self.leasehold_matching_lookup["match_type"] == "exact" + ] + + self.shared_leasehold_match = shared_leasehold_match + self.shared_freehold_match = shared_freehold_match + + # finally, we create matched addresses + self.combined_matching_lookup = pd.concat([self.freehold_matching_lookup, self.leasehold_matching_lookup]) + + # Remove duplicates + self.combined_matching_lookup = self.remove_duplicate_matches( + matching_lookup=self.combined_matching_lookup, + properties=self.epc_data, + company_ownership=self.ownership_data + ) + # We also have duplicates at a UPRN level + self.combined_matching_lookup = self.remove_duplicate_uprn_matches( + matching_lookup=self.combined_matching_lookup, + properties=self.epc_data, + company_ownership=self.ownership_data + ) + + self.matched_addresses = self.combined_matching_lookup.merge( + self.epc_data[ + [ + "UPRN", + "ADDRESS", + "ADDRESS1", + "CURRENT_ENERGY_EFFICIENCY", + "CURRENT_ENERGY_RATING", + "POSTCODE", + "LODGEMENT_DATE", + "TRANSACTION_TYPE" + ] + ].rename( + columns={ + "ADDRESS": "epc_address", + "ADDRESS1": "epc_address1", + "POSTCODE": "epc_postcode" + } + ), + how="left", on="UPRN" + ).merge( + self.ownership_data[ + [ + "Title Number", + "Property Address", + "Postcode", + "Company Registration No. (1)", + "Proprietor Name (1)", + "Date Proprietor Added", + ] + ], + how="left", on="Title Number" + ) + + # Let's try and get the house number + self.matched_addresses["house_number"] = ( + self.matched_addresses["epc_address"] + .apply(self.remove_text_in_brackets) + .apply(SearchEpc.get_house_number) + .str.lower() + .str.replace(",", "") + ) + + logger.info("Successfully completed matching") + + def get_land_registry(self): + """ + This function reads in the land registry data and filters it on the postcodes found in the EPC data + """ + land_registry = pd.read_csv(self.land_registry_path, header=None) + land_registry.columns = self.LAND_REGISTRY_COLUMNS + land_registry = land_registry[ + land_registry["postcode"].str.lower().isin(self.epc_data["POSTCODE"].str.lower().unique()) + ] + land_registry["date_of_transfer"] = pd.to_datetime( + land_registry["date_of_transfer"], format="%Y-%m-%d", errors="coerce" + ) + # Take data from the last 5 years + land_registry = land_registry[ + (land_registry["date_of_transfer"] >= datetime.now() - pd.DateOffset(years=5)) + ] + + return land_registry + + def match_with_land_registry(self): + """ + This function matches the land registry data to the existing matches + :return: + """ + # TODO: Refactor this entire function + if self.matched_addresses is None: + raise ValueError("Run match() first!") + + logger.info("Reading land registry data") + self.land_registry = self.get_land_registry() + # Store this fitereed version in s3 + save_excel_to_s3( + df=self.land_registry, + bucket_name=self.bucket, + file_key=self.filtered_land_registry_filepath, + ) + + for col in ["postcode", "street", "paon", "saon"]: + self.land_registry[col] = self.land_registry[col].str.lower().str.strip() + + self.land_registry["date_of_transfer"] = pd.to_datetime(self.land_registry["date_of_transfer"]) + + logger.info("Performing land registry matching") + land_registry_matches = [] + for _, match in tqdm(self.matched_addresses.iterrows(), total=len(self.matched_addresses)): + # Filter land registry on the postcode + lr_filtered = self.land_registry[ + (self.land_registry["postcode"] == match["epc_postcode"].lower().strip()) + ].copy() + + # Filter further, when the street is in in the address + # street should be contained in epc_address + lr_filtered = lr_filtered[ + lr_filtered["street"].apply(lambda x: self.is_substring(x, match["epc_address"].lower())) | + lr_filtered["street"].apply(lambda x: self.is_substring(x, match["Property Address"].lower())) + ] + + if lr_filtered.empty: + continue + + # We now check if paon is in address 1 + lr_filtered["paon_match"] = lr_filtered["paon"].apply( + lambda x: self.house_number_match(x, match["house_number"]) + ) + # We also try the secondary match + lr_filtered["saon_match"] = ( + lr_filtered["saon"].apply( + lambda x: False if pd.isnull(x) else self.is_substring(x, match["epc_address1"]) + ) + ) + # We fileter where we have a primary or secondary match + lr_filtered = lr_filtered[ + lr_filtered["paon_match"] | lr_filtered["saon_match"] + ] + + if lr_filtered.empty: + continue + elif lr_filtered.shape[0] == 1: + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + elif lr_filtered.shape[0] > 1: + # We make sure all records are the same and take the newest + all_paon_equal, all_saon_equal, all_street_equal = self.check_equalities(lr_filtered) + has_paon_match = any(lr_filtered["paon_match"]) + + if all_paon_equal and all_street_equal and all_saon_equal: + # Take the newest record, append and continue + lr_filtered = lr_filtered.sort_values("date_of_transfer", ascending=False) + lr_filtered = lr_filtered.head(1) + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + elif has_paon_match and all_street_equal: + # Peform filter on paon + lr_filtered = lr_filtered[lr_filtered["paon_match"]] + # Do an addtiioanl equality check + all_paon_equal, all_saon_equal, all_street_equal = self.check_equalities(lr_filtered) + if all_paon_equal and all_street_equal and all_saon_equal: + lr_filtered = lr_filtered.sort_values("date_of_transfer", ascending=False) + lr_filtered = lr_filtered.head(1) + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + else: + # We do a match on saon + lr_filtered["saon_match2"] = lr_filtered["saon"].apply( + lambda x: False if pd.isnull(x) else self.is_substring(x, match["epc_address"]) + ) + + lr_filtered = lr_filtered[lr_filtered["saon_match2"]] + + if lr_filtered.empty: + continue + elif lr_filtered.shape[0] == 1: + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + else: + raise NotImplementedError("wtf") + else: + # We have a final check, based on an observed case + lr_address_1 = " ".join([x.lower().strip() for x in match["Property Address"].split(",")[0:2]]) + + lr_filtered["paon_match2"] = lr_filtered["paon"].apply( + lambda x: False if pd.isnull(x) else self.is_substring(x, lr_address_1) + ) + + lr_filtered = lr_filtered[lr_filtered["paon_match2"]] + + if lr_filtered.empty: + continue + elif lr_filtered.shape[0] == 1: + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + else: + # Check all the same + all_paon_equal, all_saon_equal, all_street_equal = self.check_equalities(lr_filtered) + + # Check saon is house number with exact match + lr_filtered["saon_match2"] = lr_filtered["saon"].apply( + lambda x: False if pd.isnull(x) else self.house_number_match(x, match["house_number"]) + ) + # We check if we have a flat + match_flat_number = re.match("flat (\d+)", match["epc_address1"].lower()) + match_apartment_number = re.match("apartment (\d+)", match["epc_address1"].lower()) + lr_filtered["saon_match3"] = False + if match_flat_number is not None: + # Get out the match + match_flat_number = "flat " + match_flat_number.group(1) + lr_filtered["saon_match3"] = lr_filtered["saon"].apply( + lambda x: False if pd.isnull(x) else x == match_flat_number + ) + + if match_apartment_number is not None: + # Get out the match + match_apartment_number = "apartment " + match_apartment_number.group(1) + lr_filtered["saon_match3"] = lr_filtered["saon"].apply( + lambda x: False if pd.isnull(x) else x == match_apartment_number + ) + + if all_paon_equal and all_saon_equal and all_street_equal: + # Take the newest record + lr_filtered = lr_filtered.sort_values("date_of_transfer", ascending=False) + lr_filtered = lr_filtered.head(1) + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + elif any(lr_filtered["saon_match2"]): + lr_filtered = lr_filtered[lr_filtered["saon_match2"]] + all_saon_equal, all_paon_equal, all_street_equal = self.check_equalities(lr_filtered) + if all_paon_equal and all_saon_equal and all_street_equal: + # Filter on the newest record + lr_filtered = lr_filtered.sort_values("date_of_transfer", ascending=False) + lr_filtered = lr_filtered.head(1) + if lr_filtered.shape[0] == 1: + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + elif any(lr_filtered["saon_match3"]): + lr_filtered = lr_filtered[lr_filtered["saon_match3"]] + if lr_filtered.shape[0] == 1: + land_registry_matches.append( + { + "uprn": match["UPRN"], + "transaction_id": lr_filtered['transaction_id'].values[0], + "price": lr_filtered["price"].values[0], + "date_of_transfer": lr_filtered["date_of_transfer"].values[0], + } + ) + continue + + raise NotImplementedError("wtf") + else: + raise NotImplementedError("What happened here?") + + self.land_registry_matches = pd.DataFrame(land_registry_matches) + + logger.info("Sucessfully completed land registry matching - merging onto matched_addresses") + # Merge onto the EPC - ownership matches + self.matched_addresses = self.matched_addresses.merge( + self.land_registry_matches, + how="left", + left_on="UPRN", + right_on="uprn" + ).drop(columns=["uprn"]) + + # Flag anything that sold in the last year + self.matched_addresses["sold_recently"] = ( + self.matched_addresses["date_of_transfer"] >= pd.Timestamp.now() - + pd.DateOffset(month=self.SOLD_RECENTLY_MONTHS) + ) + + self.matched_addresses["sale_lodged_recently"] = ( + ( + pd.to_datetime( + self.matched_addresses["LODGEMENT_DATE"] + ) >= pd.Timestamp.now() - pd.DateOffset(months=self.LODGED_RECENTLY_MONTHS) + ) & + (self.matched_addresses["TRANSACTION_TYPE"].isin(["marketed sale", "non marketed sale"])) + ) + + def aggregate_matches(self, matching_lookup, company_ownership, properties): + df = matching_lookup.merge( + company_ownership, how="left", on="Title Number" + ).merge( + properties[["UPRN", "LOCAL_AUTHORITY_LABEL"]], how="left", on="UPRN" + ) + counts = ( + df.groupby(["Company Registration No. (1)", "LOCAL_AUTHORITY_LABEL"])["UPRN"] + .count() + .reset_index(name="number_of_properties") + ) + counts = counts.sort_values("number_of_properties", ascending=False) + + pivot_counts = counts.pivot_table( + index=["Company Registration No. (1)"], # Rows: companies and proprietors + columns="LOCAL_AUTHORITY_LABEL", # Columns: each local authority + values="number_of_properties", # The counts of properties + fill_value=0 # Fill missing values with 0 (where there are no properties owned) + ).reset_index() + + total_counts = ( + df.groupby(["Company Registration No. (1)"])["UPRN"] + .count() + .reset_index(name="total_number_of_properties") + ) + + # We have cases where the same company registration number results in the same company name, so we produce a + # best + # name per company registration number + best_names = ( + df.groupby(["Company Registration No. (1)"])["Proprietor Name (1)"] + .first() + .reset_index() + ) + + total_counts = best_names.merge( + total_counts, how="left", on=["Company Registration No. (1)"] + ) + + pivot_counts = pivot_counts.merge( + total_counts, how="left", on=["Company Registration No. (1)"] + ) + + pivot_counts = pivot_counts.sort_values("total_number_of_properties", ascending=False) + pivot_counts = pivot_counts[pivot_counts["total_number_of_properties"] > 1] + + pivot_counts["approx_value"] = self.average_property_value * pivot_counts["total_number_of_properties"] + pivot_counts["cumulative_value"] = pivot_counts["approx_value"].cumsum() + + return pivot_counts + + def create_final_matches(self): + """ + Given the matching to this point, this method creates the final matching tables + :return: + """ + logger.info("Creating final matches") + matched_addresses_final = self.matched_addresses[ + ~self.matched_addresses["sold_recently"] & + ~self.matched_addresses["sale_lodged_recently"] + ].copy() + + logger.info("Performing conservation area and listed/herigage building filtering") + + portfolio_spatial_data = OpenUprnClient.get_spatial_data( + matched_addresses_final["UPRN"].unique().tolist(), bucket_name="retrofit-data-dev" + ) + + portfolio_spatial_data = portfolio_spatial_data[ + ["UPRN", "conservation_status", "is_listed_building", "is_heritage_building"] + ].copy() + portfolio_spatial_data["UPRN"] = portfolio_spatial_data["UPRN"].astype(str) + + # Filter matched_addresses_final and filter combined_matching_lookup_final + matched_addresses_final = matched_addresses_final.merge( + portfolio_spatial_data, how="left", on="UPRN" + ) + matched_addresses_final = matched_addresses_final[ + matched_addresses_final["conservation_status"].isin([None, False]) & + matched_addresses_final["is_listed_building"].isin([None, False]) & + matched_addresses_final["is_heritage_building"].isin([None, False]) + ] + + # Filter combined_matching_lookup accordingly + combined_matching_lookup_final = self.combined_matching_lookup[ + self.combined_matching_lookup["UPRN"].isin(matched_addresses_final["UPRN"]) + ] + + # Roll up portfolio + combined_aggregate = self.aggregate_matches( + matching_lookup=combined_matching_lookup_final, + company_ownership=self.ownership_data, + properties=self.epc_data + ) + + self.portfolio_owners = combined_aggregate[combined_aggregate["cumulative_value"] <= self.portfolio_value] + + self.portfolio_properties = matched_addresses_final[ + matched_addresses_final["Company Registration No. (1)"].isin( + self.portfolio_owners["Company Registration No. (1)"] + ) + ] + + # We perform some checks + if self.portfolio_owners["total_number_of_properties"].sum() != self.portfolio_properties["UPRN"].nunique(): + raise ValueError("Portfolio owners and properties don't match") + + self.portfolio_epc_data = self.epc_data[self.epc_data["UPRN"].isin(self.portfolio_properties["UPRN"])] + + # Additional checks + if self.portfolio_properties["UPRN"].nunique() != self.portfolio_epc_data["UPRN"].nunique(): + raise ValueError("Portfolio properties and epc data don't match") + + logger.info("Storing final outpus") + # Store data + save_excel_to_s3( + df=self.portfolio_owners, + bucket_name=self.bucket, + file_key=self.portfolio_owners_filepath, + ) + + save_excel_to_s3( + df=self.portfolio_properties, + bucket_name=self.bucket, + file_key=self.portfolio_properties_filepath, + ) + + save_excel_to_s3( + df=self.portfolio_epc_data, + bucket_name=self.bucket, + file_key=self.portfolio_epc_data_filepath, + ) + + def get_asset_list(self): + """ + From the EPC data, creates the asset list + :return: + """ + + asset_list = self.portfolio_epc_data[["UPRN", "ADDRESS1", "POSTCODE"]].copy().rename( + columns={ + "UPRN": "uprn", + "ADDRESS1": "address", + "POSTCODE": "postcode" + } + ) + + return asset_list + + def create_final_outputs(self, portfolio_timestamp, storage_date, exclusion_uprns=None): + """ + Given the completed outputs of the matching process, this function creates the final outputs, after matching + valuation data, and creates a "working" directory, which is our current view of the sfr portfolio. This means + that we can iterate on the portfolio without affecting the final outputs, and then once we're happy with the + new version, we can commit those files to the "working" directory. This inforamtion shouldn't update very + often and so we're ok to store this at a daily level + :return: + """ + + exclusion_uprns = [] if exclusion_uprns is None else exclusion_uprns + + # Step 1: Read in the valuations data + valuations = read_excel_from_s3( + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/sfr property valuations.xlsx", + header_row=0 + ) + + # Load in the portfolio data + # 1) owners + portfolio_owners = read_excel_from_s3( + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/{portfolio_timestamp}/portfolio_owners.xlsx", + header_row=0 + ) + # 2) EPC + portfolio_epc_data = read_excel_from_s3( + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/{portfolio_timestamp}/portfolio_epc_data.xlsx", + header_row=0 + ) + + # 3) properties + portfolio_properties = read_excel_from_s3( + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/{portfolio_timestamp}/portfolio_properties.xlsx", + header_row=0 + ) + + # Check they're the right size + if portfolio_owners["total_number_of_properties"].sum() != portfolio_properties["UPRN"].nunique(): + raise ValueError("Portfolio owners and properties don't match") + + if portfolio_properties["UPRN"].nunique() != portfolio_epc_data["UPRN"].nunique(): + raise ValueError("Portfolio properties and epc data don't match") + + # We make some final cuts based on UPRNs that at a later stage are found to be odd + if portfolio_properties["UPRN"].isin(exclusion_uprns).sum(): + raise Exception("Implement me!") + # Identify who the owners are for thes uprns + # owners = portfolio_properties[portfolio_properties["UPRN"].isin(exclusion_uprns)].groupby( + # "Company Registration No. (1)" + # )["UPRN"].nunique().reset_index().rename( + # columns={"UPRN": "number_of_properties_to_exclude"} + # ) + # + # min_owners_threshold = portfolio_owners["total_number_of_properties"].min() + # + # portfolio_owners = portfolio_owners.merge( + # owners, how="left", on="Company Registration No. (1)", suffixes=("", "_excluded") + # ) + + # Step 2: Merge in the valuations data + portfolio_properties = portfolio_properties.merge( + valuations.rename(columns={"uprn": "UPRN"}).drop(columns=['address', 'postcode']), how="left", on="UPRN" + ) + + # Step 3: Store the final outputs + save_excel_to_s3( + df=portfolio_owners, + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/current/{storage_date}/portfolio_owners.xlsx", + ) + + save_excel_to_s3( + df=portfolio_properties, + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/current/{storage_date}/portfolio_properties.xlsx", + ) + + save_excel_to_s3( + df=portfolio_epc_data, + bucket_name=self.bucket, + file_key=f"ownership/{self.project_name}/current/{storage_date}/portfolio_epc_data.xlsx", + ) diff --git a/etl/ownership/README.md b/etl/ownership/README.md new file mode 100644 index 00000000..38b71474 --- /dev/null +++ b/etl/ownership/README.md @@ -0,0 +1,10 @@ +# Ownership Application + +This application contains methods that allows us to attempt to discover +corporate ownership of properties, where possible. + +Practically, it's likely that the code within this application will be +exported into other areas of this repository, and used to assemble +pipelines that solve specific property ownership questions, and so this +codebase is set up with the goal of providing farily easy to use, plug +and play tools. \ No newline at end of file diff --git a/etl/ownership/config.py b/etl/ownership/config.py new file mode 100644 index 00000000..ac92693a --- /dev/null +++ b/etl/ownership/config.py @@ -0,0 +1,35 @@ +# These are the registration numbers for companies we've heard a reponse from, and cannot sell +OWNERS_WHO_CANT_SELL = [ + # Al Rayan - they're the senior lender, not able to sell + "4483430", + # Ultrabarn - they're unwilling to sell and will sort any retrofits themselves + "2794851", + # Mountview - Anna spoke with someone from Mounview - they acquire tenancies and sell them as soon as they become + # vacant. They have no immediate opportunities but we may come back and remove this + "328090", +] + +EXCLUDED_UPRNS = [ + # This property no longer exists + 200003827624, + # This property doesn't seem to exist + 90070698, + # Can't really find a solid record on Zoopla/Rightmove + 10090437990, + # This property doesn't seem to exist + 100070902790, + # This property doesn't seem to exist + 100070902791, + # This property doesn't seem to exist + 100031997775, + # Can't find reliable information to this property on zoopla/rightmove + 200001372608, + # Can't find reliable information to this property on zoopla/rightmove + 100031592801, + # Can't find reliable information to this property on zoopla/rightmove + 100031579087, + # Can't find reliable information to this property on zoopla/rightmove + 200000877273, + # Can't find reliable information to this property on zoopla/rightmove - seems like a post office! + 100071391639 +] diff --git a/etl/ownership/projects/midlands_portfolio/app.py b/etl/ownership/projects/midlands_portfolio/app.py new file mode 100644 index 00000000..d004965f --- /dev/null +++ b/etl/ownership/projects/midlands_portfolio/app.py @@ -0,0 +1,181 @@ +import datetime + +from sqlalchemy.orm import sessionmaker +from backend.app.db.connection import db_engine +from backend.app.db.models.portfolio import Portfolio, PortfolioUsers +from etl.ownership.Ownership import Ownership +from etl.ownership.config import OWNERS_WHO_CANT_SELL as EXCLUDED_OWNERS, EXCLUDED_UPRNS +from utils.s3 import save_csv_to_s3 + +# Set up the project configuration +USER_IDS = [ + 2, # Khalim + 3, # Chenai + 5, # Anna + 30, # Patricia +] + +EPC_PATHS = [ + "local_data/all-domestic-certificates/domestic-E08000025-Birmingham/certificates.csv", + "local_data/all-domestic-certificates/domestic-E08000031-Wolverhampton/certificates.csv", + "local_data/all-domestic-certificates/domestic-E08000026-Coventry/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000016-Leicester/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000015-Derby/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000021-Stoke-on-Trent/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000018-Nottingham/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000154-Northampton/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000061-North-Northamptonshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000062-West-Northamptonshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000152-East-Northamptonshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000155-South-Northamptonshire/certificates.csv", + # + "local_data/all-domestic-certificates/domestic-E08000027-Dudley/certificates.csv", + "local_data/all-domestic-certificates/domestic-E08000029-Solihull/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000234-Bromsgrove/certificates.csv", + "local_data/all-domestic-certificates/domestic-E08000030-Walsall/certificates.csv", + "local_data/all-domestic-certificates/domestic-E08000028-Sandwell/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000019-Herefordshire-County-of/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000020-Telford-and-Wrekin/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000218-North-Warwickshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000222-Warwick/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000237-Worcester/certificates.csv", + # East midlands + "local_data/all-domestic-certificates/domestic-E07000035-Derbyshire-Dales/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000038-North-East-Derbyshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000039-South-Derbyshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000012-North-East-Lincolnshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000013-North-Lincolnshire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000138-Lincoln/certificates.csv", + "local_data/all-domestic-certificates/domestic-E07000134-North-West-Leicestershire/certificates.csv", + "local_data/all-domestic-certificates/domestic-E06000017-Rutland/certificates.csv", +] + +DOMESTIC_OWNERSHIP_PATH = "/Users/khalimconn-kowlessar/Downloads/CCOD_FULL_2024_07.csv" +OVERSEAS_OWNERSHIP_PATH = "/Users/khalimconn-kowlessar/Downloads/OCOD_FULL_2024_07.csv" +LAND_REGISTRY_PATH = "/Users/khalimconn-kowlessar/Downloads/pp-complete.csv" + +PROJECT_NAME = "Midlands Portfolio" +DATA_BUCKET = "retrofit-data-dev" + +# We use this as a rough figure, which helps us shape the portfolio +PROPERTY_VALUE_ESTIMATE = 200_000 +# We want a 50m portfolio, but we create a bigger portfolio that needed, since properties will be filtered out +PORTFOLIO_VALUE = 75_000_000 + + +def create_sfr_portfolio(project_name, user_ids, status, goal): + session = sessionmaker(bind=db_engine)() + try: + session.begin() + + # Check for an existing portfolio by name + portfolio = session.query(Portfolio).filter_by(name=project_name).one_or_none() + + if portfolio: + # Fetch the associated users + existing_user_ids = { + pu.user_id for pu in session.query(PortfolioUsers.user_id).filter_by(portfolioId=portfolio.id) + } + + # Check if the specified user_ids match any existing associations + if existing_user_ids.intersection(set(user_ids)): + print("Portfolio already exists under this name, for specified users.") + else: + print("Portfolio already exists under this name, for different users.") + session.rollback() # No changes to be committed + return None # Optional: You could also update the user associations here if needed + + return portfolio # Return the existing portfolio data + + # If portfolio does not exist, create a new one with the provided status and goal + new_portfolio = Portfolio(name=project_name, status=status, goal=goal) + session.add(new_portfolio) + session.flush() # Ensures that 'id' is available before committing if needed + + # Create new user associations in PortfolioUsers + for user_id in user_ids: + new_association = PortfolioUsers(user_id=user_id, portfolioId=new_portfolio.id) # corrected attribute name + session.add(new_association) + + session.commit() + print(f"New portfolio created with ID: {new_portfolio.id}") + return new_portfolio + + except Exception as e: + session.rollback() # Ensure no partial changes are committed + print(f"An error occurred: {e}") + raise + + finally: + session.close() + + +def app(): + epc_column_filters = { + "CURRENT_ENERGY_RATING": ["F", "G"] + } + + ownership_instance = Ownership( + epc_paths=EPC_PATHS, + domestic_ownership_path=DOMESTIC_OWNERSHIP_PATH, + overseas_ownership_path=OVERSEAS_OWNERSHIP_PATH, + land_registry_path=LAND_REGISTRY_PATH, + project_name=PROJECT_NAME, + bucket=DATA_BUCKET, + average_property_value=PROPERTY_VALUE_ESTIMATE, + portfolio_value=PORTFOLIO_VALUE, + excluded_owners=EXCLUDED_OWNERS, + excluded_uprns=EXCLUDED_UPRNS + ) + ownership_instance.pipeline(column_filters=epc_column_filters) + + # Create the project, if a portfolio doesn't exist for the project name + + # Create the asset list and the body of the portfolio + asset_list = ownership_instance.get_asset_list() + + # Create the portfolio + # TODO: Wasn't working + # create_sfr_portfolio(project_name=PROJECT_NAME, user_ids=USER_IDS, status="scoping", goal="Increasing EPC") + + portfolio_id = 99 + user_id = 8 + + filename = f"{user_id}/{portfolio_id}/asset_list.csv" + save_csv_to_s3( + dataframe=asset_list, + bucket_name="retrofit-plan-inputs-dev", + file_name=filename + ) + + body = { + "portfolio_id": str(portfolio_id), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "C", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": "", + "non_invasive_recommendations_file_path": "", + "scenario_name": "Hit EPC C", + "multi_plan": True, + "exclusions": ["fireplace", "floor_insulation"], + "budget": None, + } + print(body) + + # # We read in the current valuation data and identify if there are any uprns that need to be added + # previous_valuations = pd.read_excel( + # "/Users/khalimconn-kowlessar/Documents/hestia/Customers/sfr/sfr property valuations.xlsx") + # missed = asset_list[~asset_list["uprn"].astype(str).isin(previous_valuations["uprn"].astype(str))] + # missed.to_csv("missed_valuations.csv") + + # We now need a distinct step to prepare final outputs + portfolio_timestamp = "2024-08-20 19:51:33.884145" + + # Create a date in the yyyy-mm-dd format to store the data against + storage_date = datetime.datetime.now().strftime("%Y-%m-%d") + + ownership_instance.create_final_outputs( + portfolio_timestamp=portfolio_timestamp, storage_date=storage_date, exclusion_uprns=EXCLUDED_UPRNS + ) diff --git a/etl/spatial/OpenUprnClient.py b/etl/spatial/OpenUprnClient.py index 7392c4ac..11827f8d 100644 --- a/etl/spatial/OpenUprnClient.py +++ b/etl/spatial/OpenUprnClient.py @@ -3,7 +3,8 @@ from tqdm import tqdm import pandas as pd import geopandas as gpd from utils.logger import setup_logger -from utils.s3 import read_io_from_s3, save_dataframe_to_s3_parquet +from utils.s3 import read_io_from_s3, save_dataframe_to_s3_parquet, read_dataframe_from_s3_parquet +from backend.Property import Property logger = setup_logger() @@ -116,3 +117,81 @@ class OpenUprnClient: file_key=file_key, bucket_name=bucket_name ) + + @staticmethod + def make_uprn_map(uprns, uprn_filenames): + """ + Given a list of UPRNs, this method will return a map of the UPRN to the filename that the UPRN is contained in + :param uprns: List of UPRNs + :param uprn_filenames: Lookup from UPRN range to filename + :return: + """ + uprn_map = {} + for uprn in uprns: + filtered_df = uprn_filenames[ + (uprn_filenames["lower"] <= int(uprn)) + & (uprn_filenames["upper"] >= int(uprn)) + ] + if filtered_df["filenames"].values[0] in uprn_map: + uprn_map[filtered_df["filenames"].values[0]].append(int(uprn)) + else: + uprn_map[filtered_df["filenames"].values[0]] = [int(uprn)] + + return uprn_map + + @classmethod + def set_spatial_data(cls, input_properties: list[Property], bucket_name): + """ + Given a list of properties, this method will set the spatial data for each property + The method will look for the minimal set of uprn datasets that it needs to read in to get all of the spatial + data for the properties + """ + + uprn_filenames = read_dataframe_from_s3_parquet( + bucket_name=bucket_name, file_key="spatial/filename_meta.parquet" + ) + + uprns = [p.uprn for p in input_properties] + uprn_map = cls.make_uprn_map(uprns, uprn_filenames) + + for filename, associated_uprn in tqdm(uprn_map.items(), total=len(uprn_map)): + # Read in the file + spatial_data = read_dataframe_from_s3_parquet( + bucket_name="retrofit-data-dev", file_key=f"spatial/{filename}" + ) + + spatial_df = spatial_data[spatial_data["UPRN"].isin(associated_uprn)] + for p in input_properties: + if p.uprn in associated_uprn: + p.set_spatial(spatial_df[spatial_df["UPRN"] == p.uprn]) + + # Perform a final check to ensure that all properties have spatial data + for p in input_properties: + if p.spatial is None: + raise Exception(f"Property with UPRN {p.uprn} does not have spatial data") + + return input_properties + + @classmethod + def get_spatial_data(cls, uprns: list[int], bucket_name): + """ + Similar method to set_spatial_data, but designed to work more generally on a list of uprns + :return: + """ + uprn_filenames = read_dataframe_from_s3_parquet( + bucket_name=bucket_name, file_key="spatial/filename_meta.parquet" + ) + + uprn_map = cls.make_uprn_map(uprns, uprn_filenames) + + uprn_spatial_table = [] + for filename, associated_uprn in tqdm(uprn_map.items(), total=len(uprn_map)): + # Read in the file + spatial_data = read_dataframe_from_s3_parquet( + bucket_name="retrofit-data-dev", file_key=f"spatial/{filename}" + ) + + spatial_df = spatial_data[spatial_data["UPRN"].isin(associated_uprn)] + uprn_spatial_table.append(spatial_df) + + return pd.concat(uprn_spatial_table) diff --git a/etl/testing_data/bills_model_testing.py b/etl/testing_data/bills_model_testing.py new file mode 100644 index 00000000..ea13f796 --- /dev/null +++ b/etl/testing_data/bills_model_testing.py @@ -0,0 +1,287 @@ +# We use some sample properties from Newhaven to use as a testing dataset for implementing the model fixes + + +import inspect +import pandas as pd +from etl.epc.settings import EARLIEST_EPC_DATE +from pathlib import Path +from utils.s3 import save_csv_to_s3 + +src_file_path = inspect.getfile(lambda: None) + +EPC_DIRECTORY = Path(src_file_path).parent / "local_data" / "all-domestic-certificates" + +USER_ID = 8 +PORTFOLIO_ID = -1 + + +def app(): + """ + This application is tasked with pulling a large quantity of data from the find my epc website, containing the + estimated energy consumption for properties + :return: + """ + + lewes_directory = EPC_DIRECTORY / "domestic-E07000063-Lewes/certificates.csv" + + data = pd.read_csv(lewes_directory, low_memory=False) + # Rename the columns to the same format as the api returns + data.columns = [c.replace("_", "-").lower() for c in data.columns] + + # Take just date before the date threshold + data = data[data["lodgement-date"] >= EARLIEST_EPC_DATE] + + data = data[~pd.isnull(data["uprn"])] + data = data[data["current-energy-efficiency"].astype(float) < 52] + data = data.sample(10) + + # Create an asset list + asset_list = data[["uprn", "address1", "postcode"]].copy().rename(columns={"address1": "address"}) + asset_list["uprn"] = asset_list["uprn"].astype(str) + + filename = f"{USER_ID}/{PORTFOLIO_ID}/pilot.csv" + save_csv_to_s3( + dataframe=asset_list, + bucket_name="retrofit-plan-inputs-dev", + file_name=filename + ) + + body = { + "portfolio_id": str(PORTFOLIO_ID), + "housing_type": "Private", + "goal": "Increasing EPC", + "goal_value": "B", + "trigger_file_path": filename, + "already_installed_file_path": "", + "patches_file_path": "", + "non_invasive_recommendations_file_path": "", + "budget": None, + } + print(body) + + +# This is some temp code, which is for diagnosing the issues with the bills models +heating_training_data_filepath = "sap_change_model/2024-08-06-11-19-49/dataset_rooms.parquet" + +# For the heating model: +heating_drop_columns = [ + "sap_ending", "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", + "lighting_cost_ending", "hot_water_cost_ending", + # "days_to_ending", "days_to_starting", # TODO This is in the live version + 'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', + 'number_heated_rooms_ending', + 'number_habitable_rooms', 'number_heated_rooms' +] + +heating_response = "heating_cost_ending" + +# for the hot water model (older dataset) +hot_water_training_data_filepath = "sap_change_model/2024-07-10-20-28-54/dataset_rooms.parquet" + +hot_water_drop_columns = [ + "sap_ending", "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", + "lighting_cost_ending", "heating_cost_ending", + "days_to_starting", "days_to_ending", + 'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', + 'number_heated_rooms_ending', + 'number_habitable_rooms', 'number_heated_rooms' +] + +# Diagnose heating +from utils.s3 import read_dataframe_from_s3_parquet + +train = read_dataframe_from_s3_parquet( + bucket_name="retrofit-data-dev", + file_key=heating_training_data_filepath +) + +# Drop the columns that aren't used +train = train.drop(columns=heating_drop_columns) + +# if the value is postive, it means the ending cost is bigger than the starting (which means it got more expensive) +train["cost_diference"] = (train["heating_cost_ending"] - train["heating_cost_starting"]) +change_direction = train["cost_diference"] > 0 +change_direction.value_counts(normalize=True) + +average_costs_by_time_starting = train.groupby( + ["lodgement_year_starting", "lodgement_month_starting"] +)["heating_cost_starting"].mean().reset_index().sort_values(["lodgement_year_starting", "lodgement_month_starting"]) + +average_costs_by_time_ending = train.groupby( + ["lodgement_year_ending", "lodgement_month_ending"] +)["heating_cost_ending"].mean().reset_index().sort_values(["lodgement_year_ending", "lodgement_month_ending"]) + +# Check by photo supply values - if the property is gas, solar panels won't have an affect on the heating or hot +# water so let's look for electric homes +# Across the entire dataset, there is no correlation +# Even for electric properties, there is no correlation +photo_supply_averages = train[ + train["fuel_type_ending"] == "electricity" + ].groupby(["photo_supply_ending"])["heating_cost_ending"].mean().reset_index() + +photo_supply_to_size = train.groupby("photo_supply_ending")["total_floor_area_ending"].mean().reset_index() +photo_supply_to_size[["photo_supply_ending", "total_floor_area_ending"]].corr() +train[["total_floor_area_ending", "heating_cost_ending"]].corr() +# Bigger properties end up with smaller photo_supply values. This will be because the array size likely remains fairly +# consistent but takes up a smaller proportion of the roof. Typically, the bigger the floor area, the higher the heating +# costs, but bigger units also have smaller photo_supply +adding_solar = train[ + (train["photo_supply_ending"] > 0) & (train["photo_supply_starting"] == 0) + ] +is_positive = (adding_solar["cost_diference"] > 0) +is_positive.value_counts(normalize=True) + +photo_supply_by_time = ( + train[ + train["fuel_type_ending"] == "electricity" + ].groupby( + ["lodgement_year_ending", "photo_supply_ending"] + )["heating_cost_ending"].mean().reset_index().sort_values( + ["lodgement_year_ending", "photo_supply_ending"], ascending=True) +) +# Plot +photo_supply_by_time[["photo_supply_ending", "heating_cost_ending"]].corr() +photo_supply_by_time.plot() + +# Observations +# 1) We retain all of the potential columns, however they are just based on the starting EPC +# 2) 21% of the the time, the ending heating cost is more than the starting but this is clearly a minority +# 3) Let's get ride of estimated perimeter starting and ending + +# Things I should check +# 1) Do we updated the lodgment_year_ending and lodgement_month_ending +# 2) Should we adjust costs to now, as well as lodgement_dates to today? Since 2023, costs have increased a lot so +# any savings should be benchmarked against what a customer is paying now +# 3) It might make sense to create a feature between floor area and photo supply, to give a more consistent estimate +# of a panel size for the property + +# Get an example and score with the models +example = train[ + (train["photo_supply_starting"] == 0) & + (train["photo_supply_ending"] > 0) & + (train["heating_cost_starting"] > train["heating_cost_ending"]) + ].sample(1) + +# example["lodgement_month_starting"] +# example["lodgement_year_starting"] +# example["lodgement_month_ending"] +# example["lodgement_year_ending"].values[0] +# +# example["lodgement_year_ending"] = 2023 +# example["days_to_ending"] = 3500 +# example["days_to_starting"] + +# {'heating_cost_predictions': predictions +# 0 378.5} +resp = model_api.predict_all( + df=example, + bucket="retrofit-data-dev", + prediction_buckets=get_prediction_buckets(), + model_prefixes=["heating_cost_predictions"], + extract_ids=False +) + +# Step 1: get a cost for today +p.create_base_difference_epc_record(cleaned) +cwi_impact = p.base_difference_record.df.copy() +for k in property_recommendations[0][0]["simulation_config"]: + cwi_impact[k] = property_recommendations[0][0]["simulation_config"][k] + +# 2212.4 - Baseline +today = model_api.predict_all( + df=p.base_difference_record.df.copy(), + bucket="retrofit-data-dev", + prediction_buckets=get_prediction_buckets(), + model_prefixes=["heating_cost_predictions"], + extract_ids=False +) + +# impact of CWI - 1908 +cwi_response = model_api.predict_all( + df=cwi_impact, + bucket="retrofit-data-dev", + prediction_buckets=get_prediction_buckets(), + model_prefixes=["heating_cost_predictions"], + extract_ids=False +) + +pv_impact = cwi_impact.copy() +pv_impact["photo_supply_ending"] = 50 +pv_impact["heating_cost_starting"] = 2212.4 + +pv_response = model_api.predict_all( + df=pv_impact, + bucket="retrofit-data-dev", + prediction_buckets=get_prediction_buckets(), + model_prefixes=["heating_cost_predictions"], + extract_ids=False +) + +# Testing kwh for vde +base_prediction = model_api.predict_all( + df=epcs_for_scoring, + bucket=get_settings().DATA_BUCKET, + prediction_buckets=get_prediction_buckets(), + model_prefixes=["heating_kwh_predictions"], + extract_ids=False +) + +cwi_epc = pd.DataFrame([property_scoring_epcs[1].copy()]) +cwi_epc = add_features_from_code(cwi_epc) +cwi_epc = add_estimate_annual_kwh(cwi_epc) +# cwi_epc["walls-description"] = "Cavity wall, filled cavity" +# cwi_epc["walls-energy-eff"] = "Good" +# cwi_epc["heating-cost-current"] = 1650 +# cwi_epc["current-energy-efficiency"] = 72 +# cwi_epc["current-energy-rating"] = "C" +# cwi_epc["co2-emissions-current"] = 3.7 +# cwi_epc["energy-consumption-current"] = 121 +# cwi_epc["co2-emiss-curr-per-floor-area"] = 19 +# cwi_epc["photo-supply"] = 0 +# cwi_epc["energy-consumption-current"] = +# cwi_epc["roof-description"] = "Pitched, 300 mm loft insulation" +# cwi_epc["roof-energy-eff"] = "Very Good" +# cwi_epc["heating-cost-current"] = 1264 + +# "heating-cost-current": rec_impact["epc_heating_cost"], +# "hot-water-cost-current": rec_impact["epc_hot_water_cost"], +# # CO₂ emissions per square metre floor area per year in kg/m². Since CO₂ emissions are in tonnes +# # per year, we multiply by 1000 to get kg/m² +# "co2-emiss-curr-per-floor-area": round( +# 1000 * (rec_impact["carbon"] / self.data["total-floor-area"]) +# ), +# "co2-emissions-current": rec_impact["carbon"], +# "current-energy-rating": sap_to_epc(rec_impact["sap"]), +# "current-energy-efficiency": int(np.floor(rec_impact["sap"])), +# "energy-consumption-current": rec_impact["heat_demand"], +# "lighting-cost-current": rec_impact["epc_lighting_cost"], +# "id": "+".join([str(self.id), rec_id]) + +cwi_prediction = model_api.predict_all( + df=cwi_epc, + bucket=get_settings().DATA_BUCKET, + prediction_buckets=get_prediction_buckets(), + model_prefixes=["heating_kwh_predictions", "hotwater_kwh_predictions"], + extract_ids=False +) + +# 77 perryn +starting_heating = 19837.2 +starting_hot_water = 2974.1 + +ending_heating = 17041.1 +ending_hot_water = 2735.3 + +# 44 lindlings +starting_heating = 13327.1 +starting_hot_water = 2349.5 + +ending_heating = 9672.3 +ending_hot_water = 2030.2 + +ending_heating = 8695.1 +ending_hot_water = 2437.0 + +heating_impact = starting_heating - ending_heating +hot_water_impact = starting_hot_water - ending_hot_water +total_impact = heating_impact + hot_water_impact diff --git a/etl/xml_survey_extraction/app.py b/etl/xml_survey_extraction/app.py index 92451d76..f5394abf 100644 --- a/etl/xml_survey_extraction/app.py +++ b/etl/xml_survey_extraction/app.py @@ -166,6 +166,7 @@ def main(): # For each property, we download the xmls and extract the data database_data = [] for uprn, xmls in assessments_map.items(): + extracted_data = {} for xml in xmls: xml_data = read_from_s3(bucket_name=BUCKET, s3_file_name=xml) diff --git a/recommendations/Costs.py b/recommendations/Costs.py index 738e9b07..8deed75a 100644 --- a/recommendations/Costs.py +++ b/recommendations/Costs.py @@ -100,8 +100,8 @@ CONDENSING_BOILER_COSTS = { # The unit is a 15kw boiler, capable of outputting between 3kw and 15kw. Costs seem to be around £1800 ELECTRIC_BOILER_COSTS = 1800 -# Assumes 3 hours to remove each heater (including re-decorating) -ROOM_HEATER_REMOVAL_COST = 120 +# Assumes 1 hours to remove each heater (including re-decorating) +ROOM_HEATER_REMOVAL_COST = 50 ROOM_HEATER_REMOVAL_LABOUR_HOURS = 3 # This is a cost quoted by Jim for a system flush - existig system will run more efficiently @@ -1014,7 +1014,7 @@ class Costs: "labour_days": labour_days } - def solar_pv(self, wattage: float, has_battery: bool = False): + def solar_pv(self, wattage: float, has_battery: bool = False, array_cost=None): """ Calculates the total cost for solar PV based data provided by the MCS dashboard, which contains @@ -1028,13 +1028,17 @@ class Costs: https://www.checkatrade.com/blog/cost-guides/cost-of-solar-panel-installation/ :param wattage: Peak wattage of the solar PV system] :param has_battery: Bool, whether the system includes a battery + :param array_cost: float, containing the cost of the solar PV array """ # Get the cost data relevant to the region regional_cost = MCS_SOLAR_PV_COST_DATA["-".join(["average_cost_per_kwh", self.region])] - kw = wattage / 1000 - total_cost = kw * regional_cost + if array_cost is not None: + total_cost = array_cost + else: + kw = wattage / 1000 + total_cost = kw * regional_cost if has_battery: # The battery cost is based on the £3500 quote, recieved from installers diff --git a/recommendations/FloorRecommendations.py b/recommendations/FloorRecommendations.py index 9faedb89..c63d45c2 100644 --- a/recommendations/FloorRecommendations.py +++ b/recommendations/FloorRecommendations.py @@ -8,9 +8,10 @@ from datatypes.enums import QuantityUnits from backend.Property import Property from recommendations.recommendation_utils import ( r_value_per_mm_to_u_value, calculate_u_value_uplift, is_diminishing_returns, update_lowest_selected_u_value, - get_recommended_part, get_floor_u_value, override_costs + get_recommended_part, get_floor_u_value, override_costs, check_simulation_difference ) from recommendations.Costs import Costs +from etl.epc_clean.epc_attributes.FloorAttributes import FloorAttributes class FloorRecommendations(Definitions): @@ -73,7 +74,6 @@ class FloorRecommendations(Definitions): u_value = self.property.floor["thermal_transmittance"] property_type = self.property.data["property-type"] floor_area = self.property.insulation_floor_area - year_built = self.property.year_built if self.property.floor["another_property_below"] | (self.property.floor["insulation_thickness"] in [ "average", "above average" @@ -94,14 +94,16 @@ class FloorRecommendations(Definitions): if u_value: - # By being built more recently than this, it means that the property was likely build with soild - # concrete floors with insulation already - if year_built < self.PART_L_YEAR_CUTOFF: - raise NotImplementedError("Not investigated this use case") - - if u_value <= self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE: - # The floor is already compliant - return + # In this case where we have the u-value of a floor, we likely don't have any other information about it + # so there is no recommendation that we can practically make + if ( + self.property.floor["is_suspended"] or + self.property.floor["is_to_unheated_space"] or + self.property.floor["is_to_external_air"] or + self.property.floor["is_solid"] + ): + raise ValueError("This should not be possible") + return if u_value is None: u_value = get_floor_u_value( @@ -118,7 +120,11 @@ class FloorRecommendations(Definitions): if u_value < self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE: return - if self.property.floor["is_suspended"]: + if ( + self.property.floor["is_suspended"] or + self.property.floor["is_to_unheated_space"] or + self.property.floor["is_to_external_air"] + ): # Given the U-value, we recommend underfloor insulation self.recommend_floor_insulation( phase=phase, @@ -138,10 +144,6 @@ class FloorRecommendations(Definitions): ) return - if self.property.floor["is_to_unheated_space"] or self.property.floor["is_to_external_air"]: - self.recommend_floor_insulation(u_value=u_value, parts=self.exposed_floor_insulation_parts) - return - raise NotImplementedError("Implement me!") @staticmethod @@ -197,6 +199,8 @@ class FloorRecommendations(Definitions): if already_installed: cost_result = override_costs(cost_result) + new_description = "Suspended, insulated" + elif material["type"] == "solid_floor_insulation": cost_result = self.costs.solid_floor_insulation( insulation_floor_area=self.property.insulation_floor_area, @@ -207,9 +211,21 @@ class FloorRecommendations(Definitions): already_installed = "solid_floor_insulation" in self.property.already_installed if already_installed: cost_result = override_costs(cost_result) + + new_description = "Solid, insulated" else: raise NotImplementedError("Implement me!") + floor_ending_config = FloorAttributes(new_description).process() + floor_simulation_config = check_simulation_difference( + new_config=floor_ending_config, old_config=self.property.floor, prefix="floor_" + ) + + simulation_config = { + **floor_simulation_config, + "floor_thermal_transmittance_ending": new_u_value, + } + self.recommendations.append( { "phase": phase, @@ -227,6 +243,7 @@ class FloorRecommendations(Definitions): "new_u_value": new_u_value, "sap_points": None, "already_installed": already_installed, + "simulation_config": simulation_config, "description_simulation": { "floor-description": "Solid, insulated" if material["type"] == "solid_floor_insulation" diff --git a/recommendations/HeatingControlRecommender.py b/recommendations/HeatingControlRecommender.py index 6e827084..3e47c355 100644 --- a/recommendations/HeatingControlRecommender.py +++ b/recommendations/HeatingControlRecommender.py @@ -43,7 +43,7 @@ class HeatingControlRecommender: # For an ASHP, we can recommend time and temperature zone controls, as well as programmer, trvs and a bypass # which are common configurations for ASHPs self.recommend_time_temperature_zone_controls() - self.recommend_programmer_trvs_bypass() + # self.recommend_programmer_trvs_bypass() def recommend_room_heaters_electric_controls(self): """ diff --git a/recommendations/HeatingRecommender.py b/recommendations/HeatingRecommender.py index 4d91f21b..78dce329 100644 --- a/recommendations/HeatingRecommender.py +++ b/recommendations/HeatingRecommender.py @@ -28,7 +28,7 @@ class HeatingRecommender: self.property.main_heating["clean_description"] in self.ELECTRIC_HEATING_DESCRIPTIONS ) - def is_high_heat_retention_valid(self): + def is_high_heat_retention_valid(self, ashp_only_heating_recommendation, exclusions): """ Check conditions if high heat retention storage is valid :return: @@ -40,45 +40,29 @@ class HeatingRecommender: self.property.main_heating["clean_description"] in ["No system present, electric heaters assumed"] ) - return self.has_electric_heating_description or electric_heating_assumed + has_electric = self.has_electric_heating_description or electric_heating_assumed - def recommend(self, has_cavity_or_loft_recommendations, phase=0, exclusions=None): + return ( + has_electric and (not ashp_only_heating_recommendation) and ("boiler_upgrade" not in exclusions) + ) + + def is_boiler_upgrade_suitable(self, exclusions, ashp_only_heating_recommendation): """ - Produces heating recommendations - :param has_cavity_or_loft_recommendations: boolean indicating if we have produced a cavity or loft insulation - recommendation. If there are cavity or loft recommendations, the property would need to complete those measures - before being able to get the boiler upgrade scheme benefits. The messaging in the front end would be to - :param phase: indicates the phase of the retrofit programme - :param exclusions: A list of exclusions for the recommendations + These are the conditions we apply to recommend a boiler installation + :return: """ - # TODO: We could have a system flush recommendation for an existing boiler, where there is no need to replace - # the boiler, but instead flushing the system will make it run more efficiently. There is a cost for this - # in the Costs class, stored as SYSTEM_FLUSH_COST - - exclusions = [] if exclusions is None else exclusions - - self.heating_recommendations = [] - self.heating_control_recommendations = [] - # This first iteration of the recommender will provide very basic recommendation - # We recommend heating controls based on the main heating system - - if self.is_high_heat_retention_valid(): - # Recommend high heat retention storage heaters - # TODO: We need to allow for the possibility that the property aleady has storage heaters, but just - # needs the controls - self.recommend_hhr_storage_heaters(phase=phase, system_change=True, heating_controls_only=False) - - # if the property has mains heating with boiler and radiators, we recommend optimal heating controls + # 1) if the property has mains heating with boiler and radiators, we recommend optimal heating controls has_boiler = self.property.main_heating["clean_description"] in ["Boiler and radiators, mains gas"] - # We also check that the property doesn't have a heating system, but it has access to the mains gas + # 2) If the property doesn't have a heating system, but it has access to the mains gas no_heating_has_mains = self.property.main_heating["clean_description"] in [ 'No system present, electric heaters assumed' ] and self.property.data["mains-gas-flag"] - has_gas_heaters = ( - self.property.main_heating["clean_description"] in ["Room heaters, mains gas"] and + # The property is using portable heaters and has access to gas mains + has_room_heaters = ( + self.property.main_heating["clean_description"] in ["Room heaters, mains gas", "Room heaters, electric"] and self.property.data["mains-gas-flag"] ) @@ -91,13 +75,66 @@ class HeatingRecommender: self.property.data["mains-gas-flag"] ) - if ( - has_boiler or - no_heating_has_mains or - electic_heating_has_mains or - has_gas_heaters or - portable_heaters_has_mains - ): + is_valid = ( + ( + has_boiler or + no_heating_has_mains or + electic_heating_has_mains or + has_room_heaters or + portable_heaters_has_mains + ) and + (not ashp_only_heating_recommendation) and + ("boiler_upgrade" not in exclusions) + ) + + return is_valid, has_boiler + + def recommend(self, has_cavity_or_loft_recommendations, phase=0, exclusions=None): + """ + Produces heating recommendations + + :param has_cavity_or_loft_recommendations: boolean indicating if we have produced a cavity or loft insulation + recommendation. If there are cavity or loft recommendations, the property would need to complete those measures + before being able to get the boiler upgrade scheme benefits. The messaging in the front end would be to + :param phase: indicates the phase of the retrofit programme + :param exclusions: A list of exclusions for the recommendations + """ + + # TODO: We could have a system flush recommendation for an existing boiler, where there is no need to replace + # the boiler, but instead flushing the system will make it run more efficiently. There is a cost for this + # in the Costs class, stored as SYSTEM_FLUSH_COST + + # TODO: Right now, we don't have recommendations for electric boilers - we should probably have one + + exclusions = [] if exclusions is None else exclusions + non_invasive_ashp_recommendation = next( + (r for r in self.property.non_invasive_recommendations if r["type"] == "air_source_heat_pump"), + {"suitable": True} + ) + # We allow for the non-invasive recommendation to be that ASHP is not suitable + + # This option will prevent other heating recommendations from being specified, other than an ASHP + ashp_only_heating_recommendation = non_invasive_ashp_recommendation.get( + "ashp_only_heating_recommendation", False + ) + self.heating_recommendations = [] + self.heating_control_recommendations = [] + # This first iteration of the recommender will provide very basic recommendation + # We recommend heating controls based on the main heating system + + hhr_valid = self.is_high_heat_retention_valid(ashp_only_heating_recommendation, exclusions) + + if hhr_valid: + # Recommend high heat retention storage heaters + # TODO: We need to allow for the possibility that the property aleady has storage heaters, but just + # needs the controls + self.recommend_hhr_storage_heaters(phase=phase, system_change=True, heating_controls_only=False) + + gas_boiler_suitable, has_boiler = self.is_boiler_upgrade_suitable( + exclusions=exclusions, ashp_only_heating_recommendation=ashp_only_heating_recommendation + ) + + if gas_boiler_suitable: # This indicates that the home previously did not have a boiler in place and so would require # an overhaul to the system - right now, this is all reasons, apart from if there is an existing boiler system_change = not has_boiler @@ -116,9 +153,11 @@ class HeatingRecommender: # In the future, we'll allow overrides, so that non-intrusive surveys can contradict these conditions # and either allow or prevent the recommendation of an air source heat pump - if self.property.is_ashp_valid(exclusions=exclusions): + if self.property.is_ashp_valid(exclusions=exclusions) and non_invasive_ashp_recommendation["suitable"]: self.recommend_air_source_heat_pump( - phase=phase, has_cavity_or_loft_recommendations=has_cavity_or_loft_recommendations + phase=phase, + has_cavity_or_loft_recommendations=has_cavity_or_loft_recommendations, + ) return @@ -194,14 +233,21 @@ class HeatingRecommender: :return: """ + # Look for a non-intrusive recommendation + non_intrusive_recommendation = next(( + r for r in self.property.non_invasive_recommendations if r["type"] == "air_source_heat_pump" + ), {}) + controls_recommender = HeatingControlRecommender(self.property) controls_recommender.recommend(heating_description="Air source heat pump, radiators, electric") ashp_costs = self.costs.air_source_heat_pump() - # We add the costs of the heating controls, onto each key in the costs dictionary - if controls_recommender.recommendation: - for key in ashp_costs: - ashp_costs[key] += controls_recommender.recommendation[0][key] + if non_intrusive_recommendation: + # Update with non-intrusive recommendation + if non_intrusive_recommendation.get("cost"): + ashp_costs.update( + {"total": non_intrusive_recommendation["cost"], "subtotal": None, "vat": None} + ) already_installed = "air_source_heat_pump" in self.property.already_installed @@ -213,6 +259,14 @@ class HeatingRecommender: if already_installed: ashp_costs = override_costs(ashp_costs) + if non_intrusive_recommendation and not all([x is None for x in controls_recommendations]): + # We just use the ttzc control + controls_recommendations = [ + x for x in controls_recommendations if ( + x["description_simulation"]["mainheatcont-description"] == "Time and temperature zone control" + ) + ] + # This is a map from the heating controls description to the description of the air source heat pump set up ashp_descriptions = { "Time and temperature zone control": ( @@ -233,7 +287,8 @@ class HeatingRecommender: if controls_rec: for key in ashp_costs_with_controls: - ashp_costs_with_controls[key] += controls_rec[key] + if ashp_costs_with_controls[key] is not None: + ashp_costs_with_controls[key] += controls_rec[key] if controls_rec is None: description = "Install an air source heat pump." @@ -245,19 +300,19 @@ class HeatingRecommender: # If the property does not have existing cavity and loft insulation, we include a note that the cost # includes the boiler upgrade scheme and that the cavity and loft need to be treated, to ensure access # to the funding - if has_cavity_or_loft_recommendations: - description = description + ( - f" The cost includes the £" - f"{BOILER_UPGRADE_SCHEME_ASHP_VALUE} boiler upgrade scheme grant. " - f"You must ensure that the property has an insulated cavity and " - f"270mm+ loft insulation to qualify for the grant" - ) - else: - description = description + ( - f" The cost includes the £{BOILER_UPGRADE_SCHEME_ASHP_VALUE} boiler upgrade scheme grant" - ) + if not non_intrusive_recommendation: + if has_cavity_or_loft_recommendations: + description = description + ( + f" The cost includes the £" + f"{BOILER_UPGRADE_SCHEME_ASHP_VALUE} boiler upgrade scheme grant. " + f"You must ensure that the property has an insulated cavity and " + f"270mm+ loft insulation to qualify for the grant" + ) + else: + description = description + ( + f" The cost includes the £{BOILER_UPGRADE_SCHEME_ASHP_VALUE} boiler upgrade scheme grant" + ) - print("TEMP UPDATED FOR 77 Perryn!!!!!") simulation_config = { "mainheat_energy_eff_ending": "Good", "hot_water_energy_eff_ending": "Good" diff --git a/recommendations/Recommendations.py b/recommendations/Recommendations.py index 81c26e15..4f75b30b 100644 --- a/recommendations/Recommendations.py +++ b/recommendations/Recommendations.py @@ -1,4 +1,5 @@ import pandas as pd +import numpy as np from backend.Property import Property from typing import List from itertools import groupby @@ -15,6 +16,10 @@ from recommendations.HotwaterRecommendations import HotwaterRecommendations from recommendations.SecondaryHeating import SecondaryHeating from backend.ml_models.AnnualBillSavings import AnnualBillSavings from backend.apis.GoogleSolarApi import GoogleSolarApi +import backend.app.assumptions as assumptions + +ASHP_COP = 3 +STARTING_DUMMY_ID_VALUE = -9999 class Recommendations: @@ -66,7 +71,7 @@ class Recommendations: # Building Fabric if "wall_insulation" not in self.exclusions: - self.wall_recomender.recommend(phase=phase) + self.wall_recomender.recommend(phase=phase, exclusions=self.exclusions) if self.wall_recomender.recommendations: property_recommendations.append(self.wall_recomender.recommendations) phase += 1 @@ -359,475 +364,381 @@ class Recommendations: property_instance, all_predictions, recommendations, - representative_recommendations, - energy_consumption_client ): """ Given predictions from the model apis, with method will update the recommendations with the predicted impact of the recommendation on the property + This function will return two objects: + 1) Updated recommendations with the predicted impact of the recommendation + 2) A list of impacts by phase, which will be used for the kwh model scoring + :param property_instance: Instance of the Property class, for the home associated to property_id :param all_predictions: dictionary of predictions from the model apis :param recommendations: dictionary of recommendations for the property - :param representative_recommendations: dictionary of representative recommendations for the property - :param energy_consumption_client: Instance of the EnergyConsumptionClient class :return: """ - property_sap_predictions = all_predictions["sap_change_predictions"][ - all_predictions["sap_change_predictions"]["property_id"] == str(property_instance.id) - ].copy() - property_heat_predictions = all_predictions["heat_demand_predictions"][ - all_predictions["heat_demand_predictions"]["property_id"] == str(property_instance.id) - ].copy() - property_carbon_predictions = all_predictions["carbon_change_predictions"][ - all_predictions["carbon_change_predictions"]["property_id"] == str(property_instance.id) - ].copy() - property_lighting_cost_predictions = all_predictions["lighting_cost_predictions"][ - all_predictions["lighting_cost_predictions"]["property_id"] == str(property_instance.id) - ].copy() - property_heating_cost_predictions = all_predictions["heating_cost_predictions"][ - all_predictions["heating_cost_predictions"]["property_id"] == str(property_instance.id) - ].copy() - property_hot_water_cost_predictions = all_predictions["hot_water_cost_predictions"][ - all_predictions["hot_water_cost_predictions"]["property_id"] == str(property_instance.id) - ].copy() - - # We apply adjustments to each of the heating costs - property_lighting_cost_predictions["adjusted_cost"] = property_lighting_cost_predictions["predictions"].apply( - lambda x: AnnualBillSavings.adjust_energy_to_metered( - x, current_epc_rating=property_instance.data["current-energy-rating"] - ) - ) - - property_heating_cost_predictions["adjusted_cost"] = property_heating_cost_predictions["predictions"].apply( - lambda x: AnnualBillSavings.adjust_energy_to_metered( - x, current_epc_rating=property_instance.data["current-energy-rating"] - ) - ) - - property_hot_water_cost_predictions["adjusted_cost"] = property_hot_water_cost_predictions["predictions"].apply( - lambda x: AnnualBillSavings.adjust_energy_to_metered( - x, current_epc_rating=property_instance.data["current-energy-rating"] - ) - ) + property_predictions = { + prefix + "_predictions": all_predictions[prefix + "_predictions"][ + all_predictions[prefix + "_predictions"]["property_id"] == str(property_instance.id) + ].copy() for prefix in ["sap_change", "heat_demand", "carbon_change"] + } property_recommendations = recommendations[property_instance.id].copy() - # We calculate the impact by phase - sap_phase_impact = property_sap_predictions.groupby("phase")["predictions"].median().reset_index() - heat_phase_impact = property_heat_predictions.groupby("phase")["predictions"].median().reset_index() - carbon_phase_impact = property_carbon_predictions.groupby("phase")["predictions"].median().reset_index() - # lighting_cost_phase_impact = ( - # property_lighting_cost_predictions.groupby("phase")[["adjusted_cost", "predictions"]].median( - # ).reset_index() - # ) - heating_cost_phase_impact = ( - property_heating_cost_predictions.groupby("phase")[["adjusted_cost", "predictions"]].median().reset_index() - ) - hot_water_cost_phase_impact = ( - property_hot_water_cost_predictions.groupby("phase")[ - ["adjusted_cost", "predictions"] - ].median().reset_index() - ) + increasing_variables = ["sap"] + decreasing_variables = ["carbon", "heat_demand"] - representative_rec_ids = [ - rec["recommendation_id"] for rec in representative_recommendations[property_instance.id] - ] - - phase_lighting_costs = {} - phase_kwh_figures = {} - bill_savings_list = [] - kwh_savings_list = [] + impact_summary = [] for recommendations_by_type in property_recommendations: for rec in recommendations_by_type: - if rec["type"] == "mechanical_ventilation": # We don't have a percieved sap impact of mechanical ventilation continue - new_heat_demand = property_heat_predictions[property_heat_predictions["recommendation_id"] == str( - rec["recommendation_id"] - )]["predictions"].values[0] - - new_carbon = property_carbon_predictions[property_carbon_predictions["recommendation_id"] == str( - rec["recommendation_id"] - )]["predictions"].values[0] - - new_sap = property_sap_predictions[property_sap_predictions["recommendation_id"] == str( - rec["recommendation_id"] - )]["predictions"].values[0] - - # Lighting costs won't change unless we have a lighting recommendation - new_lighting_cost_data = property_lighting_cost_predictions[ - property_lighting_cost_predictions["recommendation_id"] == str(rec["recommendation_id"]) - ] - - new_lighting_cost = new_lighting_cost_data["adjusted_cost"].values[0] - new_lighting_cost_unadjusted = new_lighting_cost_data["predictions"].values[0] - - new_heating_cost_data = property_heating_cost_predictions[ - property_heating_cost_predictions["recommendation_id"] == str(rec["recommendation_id"]) - ] - - new_heating_cost = new_heating_cost_data["adjusted_cost"].values[0] - new_heating_cost_unadjusted = new_heating_cost_data["predictions"].values[0] - - new_hot_water_cost_data = property_hot_water_cost_predictions[ - property_hot_water_cost_predictions["recommendation_id"] == str(rec["recommendation_id"]) - ] - - new_hot_water_cost = new_hot_water_cost_data["adjusted_cost"].values[0] - new_hot_water_cost_unadjusted = new_hot_water_cost_data["predictions"].values[0] + phase_energy_efficiency_metrics = { + prefix: property_predictions[prefix + "_predictions"][ + property_predictions[prefix + "_predictions"]["recommendation_id"] == str( + rec["recommendation_id"] + )]["predictions"].values[0] for prefix in ["sap_change", "heat_demand", "carbon_change"] + } + # We structure this so that depending on the phase, we capture the previous phase impacts and + # then just have one piece of code to calculate the difference if rec["phase"] == 0: - predicted_sap_points = new_sap - float(property_instance.data["current-energy-efficiency"]) - predicted_co2_savings = float(property_instance.data["co2-emissions-current"]) - new_carbon - predicted_heat_demand = property_instance.floor_area * ( - float(property_instance.data["energy-consumption-current"]) - new_heat_demand - ) - - if rec["type"] == "lighting": - new_heating_cost = property_instance.energy_cost_estimates["adjusted"]["heating"] - new_hot_water_cost = property_instance.energy_cost_estimates["adjusted"]["hot_water"] - new_lighting_cost = min( - new_lighting_cost, property_instance.energy_cost_estimates["adjusted"]["lighting"] - ) - scoring_heating_cost = property_instance.energy_cost_estimates["unadjusted"]["heating"] - scoring_hot_water_cost = property_instance.energy_cost_estimates["unadjusted"]["hot_water"] - scoring_lighting_cost = min( - property_instance.energy_cost_estimates["unadjusted"]["lighting"], - new_lighting_cost_unadjusted - ) - else: - new_heating_cost = min( - new_heating_cost, property_instance.energy_cost_estimates["adjusted"]["heating"] - ) - new_hot_water_cost = min( - new_hot_water_cost, property_instance.energy_cost_estimates["adjusted"]["hot_water"] - ) - new_lighting_cost = property_instance.energy_cost_estimates["adjusted"]["lighting"] - - scoring_heating_cost = min( - property_instance.energy_cost_estimates["unadjusted"]["heating"], - new_heating_cost_unadjusted - ) - scoring_hot_water_cost = min( - property_instance.energy_cost_estimates["unadjusted"]["hot_water"], - new_hot_water_cost_unadjusted - ) - scoring_lighting_cost = property_instance.energy_cost_estimates["unadjusted"]["lighting"] - - predicted_heating_cost_reduction = ( - property_instance.energy_cost_estimates["adjusted"]["heating"] - new_heating_cost - ) - predicted_hot_water_cost_reduction = ( - property_instance.energy_cost_estimates["adjusted"]["hot_water"] - new_hot_water_cost - ) - - predicted_lighting_cost_reduction = 0 if rec["type"] != "lighting" else ( - property_instance.energy_cost_estimates["adjusted"]["lighting"] - new_lighting_cost - ) - # We store this value for later - phase_lighting_costs[rec["phase"]] = { - "adjusted": new_lighting_cost, - "unadjusted": scoring_lighting_cost - } - - # We now predict the kwh savings using the xgb model - - simulation_epc = property_instance.simulation_epcs[rec["phase"]].copy() - # The current heating, hot water and energy kwh should be based on the new, unadjusted - # costs for lighting, heating, hot water - simulation_epc["heating-cost-current"] = int(scoring_heating_cost) - simulation_epc["hot-water-cost-current"] = int(scoring_hot_water_cost) - simulation_epc["lighting-cost-current"] = int(scoring_lighting_cost) - # We predict with the energy consumption model - scoring_df = pd.DataFrame([simulation_epc]) - # Change columns from underscores to hyphens - scoring_df.columns = [ - x.lower().replace("_", "-") for x in scoring_df.columns - ] - for col in ["heating_kwh", "hot_water_kwh"]: - scoring_df[col] = None - - energy_consumption_client.data = None - new_heating_kwh = energy_consumption_client.score_new_data( - new_data=scoring_df, target="heating_kwh" - )[0] - - new_hot_water_kwh = energy_consumption_client.score_new_data( - new_data=scoring_df, target="hot_water_kwh" - )[0] - - # Adjust these figures - new_heating_kwh_adjusted = AnnualBillSavings.adjust_energy_to_metered( - new_heating_kwh, current_epc_rating=property_instance.data["current-energy-rating"] - ) - new_hot_water_kwh_adjusted = AnnualBillSavings.adjust_energy_to_metered( - new_hot_water_kwh, current_epc_rating=property_instance.data["current-energy-rating"] - ) - - heating_kwh_reduction = 0 if predicted_heating_cost_reduction == 0 else ( - property_instance.energy_consumption_estimates["adjusted"]["heating"] - new_heating_kwh_adjusted - ) - - hot_water_kwh_reduction = 0 if predicted_hot_water_cost_reduction == 0 else ( - property_instance.energy_consumption_estimates["adjusted"]["hot_water"] - - new_hot_water_kwh_adjusted - ) - - lighting_kwh_reduction = predicted_lighting_cost_reduction / AnnualBillSavings.ELECTRICITY_PRICE_CAP - - ( - predicted_appliances_cost_reduction, - predicted_appliances_kwh_reduction - ) = cls._calculate_appliance_solar_savings( - rec=rec, - property_instance=property_instance, - heating_kwh_reduction=heating_kwh_reduction, - hot_water_kwh_reduction=hot_water_kwh_reduction, - lighting_kwh_reduction=lighting_kwh_reduction - ) - - kwh_reduction = ( - heating_kwh_reduction + - hot_water_kwh_reduction + - lighting_kwh_reduction + - predicted_appliances_kwh_reduction - ) - - predicted_bill_savings = ( - predicted_heating_cost_reduction + - predicted_hot_water_cost_reduction + - predicted_lighting_cost_reduction + - predicted_appliances_cost_reduction - ) - - phase_kwh_figures[rec["phase"]] = { - "adjusted": { - "heating": new_heating_kwh_adjusted, - "hot_water": new_hot_water_kwh_adjusted - }, - "unadjusted": { - "heating": new_heating_kwh, - "hot_water": new_hot_water_kwh - } + # These are just the starting values, from the EPC. When we score the ML models, + # heating_cost_starting and heating_cost_ending are just the values in the EPC. However, with + # heating_cost_ending, we expect that the EPC will predict a heating cost based on what would happen + # if we implemented the recommendation today, so our starting value is the EPC + previous_phase_values = { + "sap": float(property_instance.data["current-energy-efficiency"]), + "carbon": float(property_instance.data["co2-emissions-current"]), + "heat_demand": float(property_instance.data["energy-consumption-current"]), } else: - previous_phase = rec["phase"] - 1 - predicted_sap_points = ( - new_sap - sap_phase_impact[sap_phase_impact["phase"] == previous_phase]["predictions"].values[0] - ) - predicted_co2_savings = ( - carbon_phase_impact[carbon_phase_impact["phase"] == previous_phase]["predictions"].values[0] - - new_carbon - ) - predicted_heat_demand = property_instance.floor_area * ( - heat_phase_impact[heat_phase_impact["phase"] == previous_phase]["predictions"].values[0] - - new_heat_demand - ) - if rec["type"] == "lighting": - # If we have a lighting recommendation, the heating, hot water and lighting costs will - # be from the previous phase - nothing will change - new_heating_cost = heating_cost_phase_impact[ - heating_cost_phase_impact["phase"] == previous_phase - ]["adjusted_cost"].values[0] - new_hot_water_cost = hot_water_cost_phase_impact[ - hot_water_cost_phase_impact["phase"] == previous_phase - ]["adjusted_cost"].values[0] + previous_phase_values_multiple = [x for x in impact_summary if x["phase"] == (rec["phase"] - 1)] + if len(previous_phase_values_multiple) != 1: + # Take an average of each of the previous phases + keys_to_median = ["sap", "carbon", "heat_demand"] + + previous_phase_values = {} + for key in keys_to_median: + values = [item[key] for item in previous_phase_values_multiple] + previous_phase_values[key] = np.median(values) - new_lighting_cost = min( - new_lighting_cost, phase_lighting_costs[previous_phase]["adjusted"] - ) - # We also use the unadjusted costs for the scoring from the previous phase - scoring_heating_cost = heating_cost_phase_impact[ - heating_cost_phase_impact["phase"] == previous_phase - ]["predictions"].values[0] - scoring_hot_water_cost = hot_water_cost_phase_impact[ - hot_water_cost_phase_impact["phase"] == previous_phase - ]["predictions"].values[0] - scoring_lighting_cost = min( - new_lighting_cost_unadjusted, - phase_lighting_costs[previous_phase]["unadjusted"] - ) else: - # Whereas for other recommendations, we use the new costs - new_heating_cost = min( - new_heating_cost, - heating_cost_phase_impact[ - heating_cost_phase_impact["phase"] == previous_phase - ]["adjusted_cost"].values[0] + previous_phase_values = previous_phase_values_multiple[0] + + # We extract the values for the current phase + current_phase_values = { + "sap": phase_energy_efficiency_metrics["sap_change"], + "carbon": phase_energy_efficiency_metrics["carbon_change"], + "heat_demand": phase_energy_efficiency_metrics["heat_demand"], + } + + # For increasing variables, the new value needs to be higher than the previous, otherwise we set it to + # the previous + # For decreasing variables, the new value should be lower than the previous, otherwise we set it to + # the previous + # In either case, we adjudge the recommendation to have had no/negligible impact + for v in increasing_variables: + current_phase_values[v] = ( + current_phase_values[v] if current_phase_values[v] > previous_phase_values[v] else + previous_phase_values[v] + ) + for v in previous_phase_values: + if v in decreasing_variables: + current_phase_values[v] = ( + current_phase_values[v] if current_phase_values[v] < previous_phase_values[v] else + previous_phase_values[v] ) - new_hot_water_cost = min( - new_hot_water_cost, - hot_water_cost_phase_impact[ - hot_water_cost_phase_impact["phase"] == previous_phase - ]["adjusted_cost"].values[0] - ) - new_lighting_cost = phase_lighting_costs[previous_phase]["adjusted"] - scoring_heating_cost = min( - new_heating_cost_unadjusted, - heating_cost_phase_impact[ - heating_cost_phase_impact["phase"] == previous_phase - ]["predictions"].values[0] - ) - scoring_hot_water_cost = min( - new_hot_water_cost_unadjusted, - hot_water_cost_phase_impact[ - hot_water_cost_phase_impact["phase"] == previous_phase - ]["predictions"].values[0] - ) - scoring_lighting_cost = phase_lighting_costs[previous_phase]["unadjusted"] - - # We now estimate the adjusted cost savings for the recommendation - predicted_heating_cost_reduction = ( - heating_cost_phase_impact[heating_cost_phase_impact["phase"] == previous_phase][ - "adjusted_cost" - ].values[0] - new_heating_cost - ) - - predicted_hot_water_cost_reduction = ( - hot_water_cost_phase_impact[hot_water_cost_phase_impact["phase"] == previous_phase][ - "adjusted_cost" - ].values[0] - new_hot_water_cost - ) - - # Only lighting recommendations can have an impact here - predicted_lighting_cost_reduction = ( - phase_lighting_costs[previous_phase]["adjusted"] - new_lighting_cost - ) - - # We now predict the kwh savings using the xgb model - this is based on - # the new costs at this phase - - simulation_epc = property_instance.simulation_epcs[rec["phase"]].copy() - # The current heating, hot water and energy kwh should be based on the new, unadjusted - # costs for lighting, heating, hot water - simulation_epc["heating-cost-current"] = int(scoring_heating_cost) - simulation_epc["hot-water-cost-current"] = int(scoring_hot_water_cost) - simulation_epc["lighting-cost-current"] = int(scoring_lighting_cost) - # We predict with the energy consumption model - scoring_df = pd.DataFrame([simulation_epc]) - # Change columns from underscores to hyphens - scoring_df.columns = [ - x.lower().replace("_", "-") for x in scoring_df.columns - ] - for col in ["heating_kwh", "hot_water_kwh"]: - scoring_df[col] = None - - energy_consumption_client.data = None - new_heating_kwh = energy_consumption_client.score_new_data( - new_data=scoring_df, target="heating_kwh" - )[0] - - new_hot_water_kwh = energy_consumption_client.score_new_data( - new_data=scoring_df, target="hot_water_kwh" - )[0] - - # Adjust these figures - new_heating_kwh_adjusted = AnnualBillSavings.adjust_energy_to_metered( - new_heating_kwh, current_epc_rating=property_instance.data["current-energy-rating"] - ) - new_hot_water_kwh_adjusted = AnnualBillSavings.adjust_energy_to_metered( - new_hot_water_kwh, current_epc_rating=property_instance.data["current-energy-rating"] - ) - - heating_kwh_reduction = 0 if predicted_heating_cost_reduction == 0 else ( - phase_kwh_figures[previous_phase]["adjusted"]["heating"] - new_heating_kwh_adjusted - ) - if heating_kwh_reduction < 0: - heating_kwh_reduction = 0 - - hot_water_kwh_reduction = 0 if predicted_hot_water_cost_reduction == 0 else ( - phase_kwh_figures[previous_phase]["adjusted"]["hot_water"] - new_hot_water_kwh_adjusted - ) - if hot_water_kwh_reduction < 0: - hot_water_kwh_reduction = 0 - - lighting_kwh_reduction = predicted_lighting_cost_reduction / AnnualBillSavings.ELECTRICITY_PRICE_CAP - - ( - predicted_appliances_cost_reduction, - predicted_appliances_kwh_reduction - ) = cls._calculate_appliance_solar_savings( - rec=rec, - property_instance=property_instance, - heating_kwh_reduction=heating_kwh_reduction, - hot_water_kwh_reduction=hot_water_kwh_reduction, - lighting_kwh_reduction=lighting_kwh_reduction - ) - - # We now calculate the predicted_bill_savings - predicted_bill_savings = ( - predicted_heating_cost_reduction + predicted_hot_water_cost_reduction + - predicted_lighting_cost_reduction + predicted_appliances_cost_reduction - ) - - kwh_reduction = ( - heating_kwh_reduction + - hot_water_kwh_reduction + - lighting_kwh_reduction + - predicted_appliances_kwh_reduction - ) - - # We store this value for later - phase_lighting_costs[rec["phase"]] = { - "adjusted": new_lighting_cost, - "unadjusted": scoring_lighting_cost - } - - phase_kwh_figures[rec["phase"]] = { - "adjusted": { - "heating": new_heating_kwh_adjusted, - "hot_water": new_hot_water_kwh_adjusted - }, - "unadjusted": { - "heating": new_heating_kwh, - "hot_water": new_hot_water_kwh - } - } + property_phase_impact = { + # Increasing + "sap": current_phase_values["sap"] - previous_phase_values["sap"], + # Decreasing + "carbon": previous_phase_values["carbon"] - current_phase_values["carbon"], + # Decreasing + "heat_demand": previous_phase_values["heat_demand"] - current_phase_values["heat_demand"], + } # Prevent from being negative - predicted_sap_points = 0 if predicted_sap_points < 0 else predicted_sap_points - predicted_co2_savings = 0 if predicted_co2_savings < 0 else predicted_co2_savings - predicted_heat_demand = 0 if predicted_heat_demand < 0 else predicted_heat_demand + for metric in ["sap", "carbon", "heat_demand"]: + property_phase_impact[metric] = ( + 0 if property_phase_impact[metric] < 0 else property_phase_impact[metric] + ) + if metric == "sap": + property_phase_impact[metric] = round(property_phase_impact[metric], 2) + # For the moment, we cap the number of SAP points that can be achieved by LEDs at 2 if rec["type"] == "low_energy_lighting": - # For the moment, we cap the number of SAP points that can be achieved by ventilation at 2 - rec["sap_points"] = min(predicted_sap_points, LightingRecommendations.SAP_LIMIT) - rec["co2_equivalent_savings"] = min(predicted_co2_savings, rec["co2_equivalent_savings"]) - rec["heat_demand"] = predicted_heat_demand - else: - rec["sap_points"] = predicted_sap_points - rec["co2_equivalent_savings"] = predicted_co2_savings - rec["heat_demand"] = predicted_heat_demand + property_phase_impact["sap"] = min(property_phase_impact["sap"], LightingRecommendations.SAP_LIMIT) + property_phase_impact["carbon"] = min( + property_phase_impact["carbon"], rec["co2_equivalent_savings"] + ) - # Round to 2 decimal places - rec["sap_points"] = round(rec["sap_points"], 2) + # Insert this information into the recommendation + rec["sap_points"] = property_phase_impact["sap"] + rec["co2_equivalent_savings"] = property_phase_impact["carbon"] + rec["heat_demand"] = property_phase_impact["heat_demand"] - rec["kwh_savings"] = kwh_reduction - rec["energy_cost_savings"] = predicted_bill_savings - - if rec["recommendation_id"] in representative_rec_ids: - bill_savings_list.append(predicted_bill_savings) - kwh_savings_list.append(kwh_reduction) - - if (rec["sap_points"] is None) and (rec["co2_equivalent_savings"] is None) or ( - rec["heat_demand"] is None) or (rec["energy_cost_savings"] is None): + if ( + (rec["sap_points"] is None) and (rec["co2_equivalent_savings"] is None) or + (rec["heat_demand"] is None) + ): raise ValueError("sap points, co2 or heat demand is missing") - # We sum up the total savings for the property and that is our expected energy bill + impact_summary.append( + { + "phase": rec["phase"], + "recommendation_id": rec["recommendation_id"], + **current_phase_values + } + ) - expected_energy_bill = property_instance.current_energy_bill - sum(bill_savings_list) - expected_adjusted_energy = property_instance.current_adjusted_energy - sum(kwh_savings_list) + return property_recommendations, impact_summary - return ( - property_recommendations, - expected_adjusted_energy, - expected_energy_bill + @staticmethod + def map_descriptions_to_fuel(heating_description, hotwater_description, main_fuel_description): + + # Handle the case of community schemes + if (heating_description == "Community scheme") or (hotwater_description == "Community scheme"): + if main_fuel_description == "mains gas (community)": + return { + "heating_fuel_type": "Natural Gas (Community Scheme)", + "hotwater_fuel_type": "Natural Gas (Community Scheme)", + "heating_cop": 1, + "hotwater_cop": 1 + } + raise NotImplementedError("Handle this case") + + mapped = assumptions.DESCRIPTIONS_TO_FUEL_TYPES[heating_description] + heating_fuel = mapped["fuel"] + + if hotwater_description in [ + "From main system", "From main system, no cylinder thermostat", + ]: + return { + "heating_fuel_type": heating_fuel, "hotwater_fuel_type": heating_fuel, + "heating_cop": mapped["cop"], "hotwater_cop": mapped["cop"] + } + + if hotwater_description in [ + "From main system, plus solar", "From main system, plus solar, no cylinder thermostat" + ]: + # The fuel is + return { + "heating_fuel_type": heating_fuel, "hotwater_fuel_type": heating_fuel + " + Solar Thermal", + "heating_cop": mapped["cop"], "hotwater_cop": 1 + } + + mapped_hotwater = DESCRIPTIONS_TO_FUEL_TYPES[hotwater_description] + + return { + "heating_fuel_type": heating_fuel, "hotwater_fuel_type": mapped_hotwater["fuel"], + "heating_cop": mapped["cop"], "hotwater_cop": mapped_hotwater["cop"] + } + + @classmethod + def calculate_recommendation_tenant_savings( + cls, property_instance, kwh_simulation_predictions, property_recommendations + ): + """ + This method inserts the kwh savings and the bill savings that the customer will make from the recommendations + based on the predictions from the ML model + :param property_instance: Instance of the Property class, for the home associated to property_id + :param kwh_simulation_predictions: dictionary of predictions from the model apis + :param property_recommendations: dictionary of recommendations for the property + :return: + """ + + kwh_impact_table = kwh_simulation_predictions["heating_kwh_predictions"][ + kwh_simulation_predictions["heating_kwh_predictions"]["property_id"] == str(property_instance.id) + ].merge( + kwh_simulation_predictions["hotwater_kwh_predictions"].drop( + columns=["property_id", "recommendation_id", "phase"] + ), + how="inner", + on="id", + suffixes=("_heating", "_hotwater") + ).reset_index(drop=True) + + # We adjust this table with the kwh estimates for low energy lighting kwh values, and solar kwh estimates + led_recommendation = pd.DataFrame([ + { + "phase": r["phase"], + "recommendation_id": r["recommendation_id"], + "lighting_kwh_savings": r["kwh_savings"] + } for recs in property_recommendations for r in recs if r["type"] == "low_energy_lighting" + ], columns=["phase", "recommendation_id", "lighting_kwh_savings"]) + + solar_recommendations = pd.DataFrame([ + { + "phase": r["phase"], + "recommendation_id": r["recommendation_id"], + "solar_kwh_savings": r["initial_ac_kwh_per_year"] * assumptions.SOLAR_CONSUMPTION_PROPORTION, + } for recs in property_recommendations for r in recs if r["type"] == "solar_pv" + ], columns=["phase", "recommendation_id", "solar_kwh_savings"]) + + # merge them on + kwh_impact_table = kwh_impact_table.merge( + led_recommendation, how="left", on=["phase", "recommendation_id"] + ).merge( + solar_recommendations, how="left", on=["phase", "recommendation_id"] ) + + property_kwh = property_instance.energy_consumption_estimates["unadjusted"] + + kwh_impact_table = pd.concat( + [ + pd.DataFrame( + [ + { + "id": STARTING_DUMMY_ID_VALUE, + "phase": STARTING_DUMMY_ID_VALUE, + "recommendation_id": STARTING_DUMMY_ID_VALUE, + "predictions_heating": property_kwh["heating"], + "predictions_hotwater": property_kwh["hot_water"], + } + ] + ), + kwh_impact_table + ] + ).sort_values(["phase", "recommendation_id"], ascending=True).reset_index(drop=True) + + for i in range(0, len(kwh_impact_table)): + current_phase = kwh_impact_table.loc[i, 'phase'] + previous_phase_id = (current_phase - 1) if (current_phase > 0) else -9999 + previous_phase = kwh_impact_table[kwh_impact_table['phase'] == previous_phase_id] + + if not previous_phase.empty: + for col in ["predictions_heating", "predictions_hotwater"]: + if kwh_impact_table.loc[i, col] > previous_phase[col].max(): + kwh_impact_table.loc[i, col] = previous_phase[col].max() + + # For heating system recommendations, this could result in a fuel type change so we reflect that + fuel_mapping = pd.DataFrame([ + { + "id": epc["id"], + **cls.map_descriptions_to_fuel( + epc["mainheat-description"], epc["hotwater-description"], epc["main-fuel"] + ) + } for epc in property_instance.updated_simulation_epcs + ]) + + fuel_mapping = pd.concat( + [ + pd.DataFrame( + [ + { + "id": STARTING_DUMMY_ID_VALUE, + **cls.map_descriptions_to_fuel( + property_instance.data["mainheat-description"], + property_instance.data["hotwater-description"], + property_instance.data["main-fuel"] + ) + } + ] + ), + fuel_mapping + ] + ) + + kwh_impact_table = kwh_impact_table.merge( + fuel_mapping, how="left", on="id" + ).sort_values(["phase", "recommendation_id"], ascending=True).reset_index(drop=True) + + if (pd.isnull(kwh_impact_table["heating_fuel_type"]).sum() or + pd.isnull(kwh_impact_table["hotwater_fuel_type"]).sum()): + raise Exception("Fuel type is missing") + + # kwh_impact_table["heating_fuel_type"] = np.where( + # kwh_impact_table["id"] == STARTING_DUMMY_ID_VALUE, + # property_instance.heating_energy_source, + # kwh_impact_table["heating_fuel_type"] + # ) + # + # kwh_impact_table["hotwater_fuel_type"] = np.where( + # kwh_impact_table["id"] == STARTING_DUMMY_ID_VALUE, + # property_instance.hot_water_energy_source, + # kwh_impact_table["hotwater_fuel_type"] + # ) + + # We now calculate the fuel cost + for k in ["heating", "hotwater"]: + kwh_impact_table[f"{k}_cost"] = kwh_impact_table.apply( + lambda x: AnnualBillSavings.calculate_recommendation_fuel_cost( + x[f"predictions_{k}"], x[f"{k}_fuel_type"], x[f"{k}_cop"] + ), axis=1 + ) + + # We now deduce if any of the recommendations result in a change of fuel type + for recs in property_recommendations: + for rec in recs: + if rec["type"] == "mechanical_ventilation": + continue + + rec_impact = kwh_impact_table[kwh_impact_table["recommendation_id"] == rec["recommendation_id"]] + prevous_phase_id = (rec["phase"] - 1) if (rec["phase"] > 0) else STARTING_DUMMY_ID_VALUE + previous_phase_impact = kwh_impact_table[kwh_impact_table["phase"] == prevous_phase_id] + + if rec["type"] == "solar_pv": + rec["kwh_savings"] = rec_impact["solar_kwh_savings"].values[0] + rec["energy_cost_savings"] = ( + rec_impact["solar_kwh_savings"].values[0] * AnnualBillSavings.ELECTRICITY_PRICE_CAP + ) + continue + + heating_kwh_savings = ( + previous_phase_impact["predictions_heating"].mean() - rec_impact["predictions_heating"].values[0] + ) + heating_cost_savings = ( + previous_phase_impact["heating_cost"].mean() - rec_impact["heating_cost"].values[0] + ) + + hotwater_kwh_savings = ( + previous_phase_impact["predictions_hotwater"].mean() - rec_impact["predictions_hotwater"].values[0] + ) + hotwater_host = ( + previous_phase_impact["hotwater_cost"].mean() - rec_impact["hotwater_cost"].values[0] + ) + + total_kwh_savings = heating_kwh_savings + hotwater_kwh_savings + energy_cost_savings = heating_cost_savings + hotwater_host + + if rec["type"] == "lighting": + # In this case, we should probably just SKIP but check when we have one! + raise Exception("Implement me 3") + + rec["kwh_savings"] = total_kwh_savings + rec["energy_cost_savings"] = energy_cost_savings + + # Finally, we set the current energy bill + # For a community scheme, there is a standing charge but it's based on the operational cost of the network + # and therefore is likely different to the typical standing charge. This will be a cost typically defined + # by the network operator and often a building, whose residents are on a heat network, where the building + # operator will purchase energy from the network and re-sell it to the residents + starting_figures = kwh_impact_table[kwh_impact_table["id"] == STARTING_DUMMY_ID_VALUE].squeeze() + gas_standing_charge = 0 + if ( + (starting_figures["heating_fuel_type"] in ["Natural Gas", "Natural Gas (Community Scheme)"]) or + (starting_figures["hotwater_fuel_type"] == ["Natural Gas", "Natural Gas (Community Scheme)"]) + ): + gas_standing_charge = AnnualBillSavings.DAILY_STANDARD_CHARGE_GAS * 365 + + electricity_standing_charge = AnnualBillSavings.DAILY_STANDARD_CHARGE_ELECTRICITY * 365 + + current_energy_bill = ( + starting_figures["heating_cost"] + + starting_figures["hotwater_cost"] + + property_instance.energy_cost_estimates["unadjusted"]["lighting"] + + property_instance.energy_cost_estimates["unadjusted"]["appliances"] + + gas_standing_charge + + electricity_standing_charge + ) + + return current_energy_bill diff --git a/recommendations/RoofRecommendations.py b/recommendations/RoofRecommendations.py index 56f3721a..5075928e 100644 --- a/recommendations/RoofRecommendations.py +++ b/recommendations/RoofRecommendations.py @@ -5,9 +5,11 @@ from typing import List from datatypes.enums import QuantityUnits from recommendations.recommendation_utils import ( get_roof_u_value, r_value_per_mm_to_u_value, calculate_u_value_uplift, is_diminishing_returns, - update_lowest_selected_u_value, get_recommended_part, convert_thickness_to_numeric, override_costs + update_lowest_selected_u_value, get_recommended_part, convert_thickness_to_numeric, override_costs, + check_simulation_difference ) from recommendations.Costs import Costs +from etl.epc_clean.epc_attributes.RoofAttributes import RoofAttributes class RoofRecommendations: @@ -274,6 +276,40 @@ class RoofRecommendations: if already_installed: cost_result = override_costs(cost_result) new_thickness = insulation_thickness + material["depth"] + + # This is based on the values we have in the training data + valid_numeric_values = [ + 12, + 25, + 50, + 75, + 100, + 150, + 200, + 250, + 270, + 300, + 350, + 400, + ] + + proposed_depth = new_thickness + if (new_thickness not in valid_numeric_values) and material["type"] == "loft_insulation": + # Take the nearest value for scoring + proposed_depth = min( + valid_numeric_values, key=lambda x: abs(x - proposed_depth) + ) + + if proposed_depth >= 270: + new_efficiency = "Very Good" + else: + if self.property.data["walls-energy-eff"] not in ["Good", "Very Good"]: + new_efficiency = "Good" + else: + new_efficiency = "Very Good" + + new_description = f"Pitched, {int(proposed_depth)}mm loft insulation" + elif material["type"] == "flat_roof_insulation": cost_result = self.costs.flat_roof_insulation( floor_area=self.property.insulation_floor_area, @@ -283,38 +319,21 @@ class RoofRecommendations: already_installed = "flat_roof_insulation" in self.property.already_installed if already_installed: cost_result = override_costs(cost_result) - new_thickness = None + new_description = "Flat, insulated" + new_efficiency = "Good" else: raise ValueError("Invalid material type") - # This is based on the values we have in the training data - valid_numeric_values = [ - 12, - 25, - 50, - 75, - 100, - 150, - 200, - 250, - 270, - 300, - 350, - 400, - ] + roof_ending_config = RoofAttributes(new_description).process() + roof_simulation_config = check_simulation_difference( + new_config=roof_ending_config, old_config=self.property.roof, prefix="roof_" + ) - proposed_depth = new_thickness - if new_thickness not in valid_numeric_values: - # Take the nearest value for scoring - proposed_depth = min( - valid_numeric_values, key=lambda x: abs(x - proposed_depth) - ) - - if proposed_depth >= 270: - new_efficiency = "Very Good" - else: - if self.property.data["walls-energy-eff"] not in ["Good", "Very Good"]: - new_efficiency = "Good" + simulation_config = { + **roof_simulation_config, + "roof_thermal_transmittance_ending": new_u_value, + "roof_energy_eff_ending": new_efficiency + } recommendations.append( { @@ -333,9 +352,9 @@ class RoofRecommendations: "new_u_value": new_u_value, "sap_points": None, "already_installed": already_installed, - "new_thickness": new_thickness, + "simulation_config": simulation_config, "description_simulation": { - "roof-description": f"Pitched, {int(proposed_depth)}mm loft insulation", + "roof-description": new_description, "roof-energy-eff": new_efficiency }, **cost_result @@ -386,18 +405,23 @@ class RoofRecommendations: :return: """ - roof_roof_insulation_materials = [m for m in self.materials if m["type"] == "room_roof_insulation"] - if not roof_roof_insulation_materials: - raise ValueError("No room in roof insulation materials found") + # TODO: We temporarilty use costs from SCIS for RIR insulation. The costing was £180/m2 floor + roof_roof_insulation_materials = [ + { + "type": "room_roof_insulation", + "description": "Insulating the ceiling of the roof roof and re-decorate", + "depths": [100], + "depth_unit": "mm", + "r_value_per_mm": 0.038, + "thermal_conductivity": 0.022, + "cost": [180], + } + ] - if self.property.pitched_roof_area is None: - raise ValueError("pitched_roof_area not included as property attribute") - - lowest_selected_u_value = None + # lowest_selected_u_value = None recommendations = [] for material in roof_roof_insulation_materials: for depth, cost_per_unit in zip(material["depths"], material["cost"]): - part_u_value = r_value_per_mm_to_u_value(depth, material["r_value_per_mm"]) _, new_u_value = calculate_u_value_uplift(u_value, part_u_value) @@ -409,36 +433,62 @@ class RoofRecommendations: # If I have a lowest U value and my new u value is lower than the lowest value, it's # further into the diminishing returns threshold and can shouldn't be - if is_diminishing_returns( - recommendations, new_u_value, lowest_selected_u_value, self.DIMINISHING_RETURNS_U_VALUE - ): - continue + # if is_diminishing_returns( + # recommendations, new_u_value, lowest_selected_u_value, self.DIMINISHING_RETURNS_U_VALUE + # ): + # continue # We allow a small tolerance for error so we don't discount the recommendation entirely - if new_u_value <= self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE: - lowest_selected_u_value = update_lowest_selected_u_value(lowest_selected_u_value, new_u_value) + # if new_u_value <= self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE: + # lowest_selected_u_value = update_lowest_selected_u_value(lowest_selected_u_value, new_u_value) - estimated_cost = cost_per_unit * self.property.pitched_roof_area + estimated_cost = cost_per_unit * self.property.insulation_floor_area - recommendations.append( - { - "phase": phase, - "parts": [ - get_recommended_part( - part=material, - selected_depth=depth, - quantity=self.property.pitched_roof_area, - quantity_unit=QuantityUnits.m2.value, - selected_total_cost=estimated_cost - ) - ], - "type": "room_roof_insulation", - "description": self.make_room_roof_insulation_description(material, depth), - "starting_u_value": u_value, - "new_u_value": new_u_value, - "sap_points": None, - "cost": estimated_cost, - } - ) + # Could also be Roof room(s), ceiling insulated + new_descriptin = "Pitched, insulated at rafters" + roof_ending_config = RoofAttributes(new_descriptin).process() + roof_simulation_config = check_simulation_difference( + new_config=roof_ending_config, old_config=self.property.roof, prefix="roof_" + ) + if self.property.data["roof-energy-eff"] in ["Very Poor", "Poor"]: + new_efficiency = "Average" + else: + new_efficiency = self.property.data["roof-energy-eff"] + + simulation_config = { + **roof_simulation_config, + "roof_thermal_transmittance_ending": new_u_value, + "roof_energy_eff_ending": new_efficiency + } + + already_installed = "flat_roof_insulation" in self.property.already_installed + cost_result = { + "total": estimated_cost, + "labour_hours": 80, + "labour_days": 5, + } + if already_installed: + cost_result = override_costs(cost_result) + + recommendations.append( + { + "phase": phase, + "parts": [ + # TODO + ], + "type": "room_roof_insulation", + "description": "Insulate room in roof at rafters and re-decorate", + "starting_u_value": u_value, + "new_u_value": None, + "sap_points": None, + "simulation_config": simulation_config, + "description_simulation": { + "roof-description": new_descriptin, + "roof-energy-eff": new_efficiency + }, + **cost_result, + "already_installed": already_installed + } + ) self.recommendations = recommendations diff --git a/recommendations/SecondaryHeating.py b/recommendations/SecondaryHeating.py index 5d763510..aed48da2 100644 --- a/recommendations/SecondaryHeating.py +++ b/recommendations/SecondaryHeating.py @@ -60,6 +60,9 @@ class SecondaryHeating: **costs, "simulation_config": { "secondheat_description_ending": "None" + }, + "description_simulation": { + "secondheat-description": "None" } } ) diff --git a/recommendations/SolarPvRecommendations.py b/recommendations/SolarPvRecommendations.py index 63519d02..d0d555c9 100644 --- a/recommendations/SolarPvRecommendations.py +++ b/recommendations/SolarPvRecommendations.py @@ -1,6 +1,8 @@ import numpy as np +import pandas as pd + from recommendations.Costs import Costs -from recommendations.recommendation_utils import override_costs +from recommendations.recommendation_utils import override_costs, esimtate_pitched_roof_area class SolarPvRecommendations: @@ -97,7 +99,11 @@ class SolarPvRecommendations: best_configurations = panel_performance.head(1).reset_index(drop=True) for rank, recommendation_config in best_configurations.iterrows(): - roof_coverage_percent = round(recommendation_config["panneled_roof_area"] / total_roof_area * 100) + # If we dont have the panneled_roof_area in the recommendation_config we calculate it + if recommendation_config.get("panneled_roof_area", None): + roof_coverage_percent = round(recommendation_config["panneled_roof_area"] / total_roof_area * 100) + else: + raise Exception("IMPLEMENT ME") # Spread the cost to the individual units - adding a 20% contingency total_cost = recommendation_config["total_cost"] / n_units kw = np.floor(recommendation_config["array_wattage"] / 100) / 10 @@ -150,17 +156,47 @@ class SolarPvRecommendations: self.recommend_building_analysis(phase) return - panel_performance = self.property.solar_panel_configuration["panel_performance"] - roof_area = self.property.roof_area + non_invasive_recommendation = next( + (r for r in self.property.non_invasive_recommendations if r["type"] == "solar_pv"), {"suitable": True} + ) - solar_configurations = panel_performance.head(3).reset_index(drop=True) + # We allow for the non-invasive recommendation to be that solar PV is not suitable + if not non_invasive_recommendation["suitable"]: + return + + if non_invasive_recommendation.get("array_wattage") is not None: + + if self.property.roof["is_flat"]: + roof_area = self.property.insulation_floor_area + else: + roof_area = esimtate_pitched_roof_area( + floor_area=self.property.insulation_floor_area, floor_height=self.property.data["floor-height"] + ) + solar_configurations = pd.DataFrame( + [ + { + "array_wattage": non_invasive_recommendation["array_wattage"], + "initial_ac_kwh_per_year": non_invasive_recommendation["initial_ac_kwh_per_year"], + "panneled_roof_area": non_invasive_recommendation["panneled_roof_area"] + } + ] + ) + else: + # TODO: There may be some instances where we don't want to use the solar API so we should cover for them + panel_performance = self.property.solar_panel_configuration["panel_performance"] + roof_area = self.property.roof_area + solar_configurations = panel_performance.head(3).reset_index(drop=True) # We combine each of these configurations with estimates with and without a battery for rank, recommendation_config in solar_configurations.iterrows(): roof_coverage_percent = round(recommendation_config["panneled_roof_area"] / roof_area * 100) + # We round up to the nearest 10 + roof_coverage_percent = np.ceil(roof_coverage_percent / 10) * 10 for has_battery in [False, True]: cost_result = self.costs.solar_pv( - wattage=recommendation_config["array_wattage"], has_battery=has_battery + wattage=recommendation_config["array_wattage"], + has_battery=has_battery, + array_cost=non_invasive_recommendation.get("cost", None) ) kw = np.floor(recommendation_config["array_wattage"] / 100) / 10 if has_battery: diff --git a/recommendations/WallRecommendations.py b/recommendations/WallRecommendations.py index 4ef747f7..b73f187c 100644 --- a/recommendations/WallRecommendations.py +++ b/recommendations/WallRecommendations.py @@ -61,10 +61,13 @@ class WallRecommendations(Definitions): "Cavity wall, as built, insulated": "Cavity wall, filled cavity and external insulation", "Solid brick, as built, no insulation": "Solid brick, with external insulation", "Solid brick, as built, insulated": "Solid brick, with external insulation", + "Solid brick, as built, partial insulation": "Solid brick, with external insulation", "Cob, as built": "Cob, with external insulation", "System built, as built, no insulation": "System built, with external insulation", "Granite or whinstone, as built, no insulation": 'Granite or whinstone, with external insulation', "Timber frame, as built, no insulation": "Timber frame, with external insulation", + 'Timber frame, as built, partial insulation': 'Timber frame, with external insulation', + "Sandstone or limestone, as built, no insulation": "Sandstone or limestone, with external insulation", } # These are the ending descriptions we consider for walls with internal insulation @@ -72,10 +75,13 @@ class WallRecommendations(Definitions): "Cavity wall, as built, insulated": "Cavity wall, filled cavity and internal insulation", "Solid brick, as built, no insulation": "Solid brick, with internal insulation", "Solid brick, as built, insulated": "Solid brick, with internal insulation", + "Solid brick, as built, partial insulation": "Solid brick, with internal insulation", "Cob, as built": "Cob, with internal insulation", "System built, as built, no insulation": "System built, with internal insulation", "Granite or whinstone, as built, no insulation": 'Granite or whinstone, with internal insulation', "Timber frame, as built, no insulation": "Timber frame, with internal insulation", + 'Timber frame, as built, partial insulation': 'Timber frame, with internal insulation', + "Sandstone or limestone, as built, no insulation": "Sandstone or limestone, with internal insulation", } def __init__( @@ -184,7 +190,7 @@ class WallRecommendations(Definitions): return ewi_recommendations - def recommend(self, phase=0): + def recommend(self, phase=0, exclusions=None): # if building built after 1990 + we're able to identify U-value + # U-value less than 0.18 and if in or close to a conversation area, # recommend internal wall insulation as a possible measure @@ -236,8 +242,8 @@ class WallRecommendations(Definitions): # + it already has a U-value better than the building regulations, so we don't need to recommend anything if ( (not is_cavity_wall) - and (self.property.year_built >= self.YEAR_WALLS_BUILT_WITH_INSULATION) - and (u_value <= self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE) + and ((self.property.year_built >= self.YEAR_WALLS_BUILT_WITH_INSULATION) + or (u_value <= self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE)) ): # Recommend nothing return @@ -262,7 +268,7 @@ class WallRecommendations(Definitions): # Remaining wall types are treated with IWI or EWI if (u_value >= self.BUILDING_REGULATIONS_PART_L_MAX_U_VALUE) and self.is_suitable_for_solid_insulation(): - self.find_insulation(u_value, phase) + self.find_insulation(u_value, phase, exclusions=exclusions) return # If the u-value is within regulations, we don't do anything @@ -552,7 +558,7 @@ class WallRecommendations(Definitions): return recommendations - def find_insulation(self, u_value, phase): + def find_insulation(self, u_value, phase, exclusions=None): """ This function contains the logic for finding potential insulation measures for a property, depending on the parts available and whether the property can have external wall insulation installed @@ -564,8 +570,10 @@ class WallRecommendations(Definitions): # we separate the logic for for recommending them, therefore we don't # consider diminishing returns between the two as they are considered to be separate measures + exclusions = [] if exclusions is None else exclusions + ewi_recommendations = [] - if self.ewi_valid(): + if self.ewi_valid() and "external_wall_insulation" not in exclusions: ewi_recommendations = self._find_insulation( u_value=u_value, insulation_materials=pd.DataFrame( @@ -575,12 +583,14 @@ class WallRecommendations(Definitions): phase=phase, ) - iwi_recommendations = self._find_insulation( - u_value=u_value, - insulation_materials=pd.DataFrame(self.internal_wall_insulation_materials), - non_insulation_materials=self.internal_wall_non_insulation_materials, - phase=phase, - ) + iwi_recommendations = [] + if "internal_wall_insulation" not in exclusions: + iwi_recommendations = self._find_insulation( + u_value=u_value, + insulation_materials=pd.DataFrame(self.internal_wall_insulation_materials), + non_insulation_materials=self.internal_wall_non_insulation_materials, + phase=phase, + ) self.recommendations += ewi_recommendations + iwi_recommendations diff --git a/recommendations/county_to_region.py b/recommendations/county_to_region.py index 7ca86715..f7d5193f 100644 --- a/recommendations/county_to_region.py +++ b/recommendations/county_to_region.py @@ -161,6 +161,9 @@ county_to_region_map = { # Additional mappings requried, based on what we find in the EPC database 'Greater London Authority': 'Inner London', + 'Herefordshire, County of': 'West Midlands', + "North Northamptonshire": 'East Midlands', + "West Northamptonshire": 'East Midlands', # We have a bunch of inner London local authority mappings, which can be used if the county is not found 'Barking and Dagenham': 'Inner London', 'Barnet': 'Inner London', 'Bexley': 'Inner London', 'Brent': 'Inner London', 'Bromley': 'Inner London', 'Camden': 'Inner London', 'City of London': 'Inner London', diff --git a/recommendations/rdsap_tables.py b/recommendations/rdsap_tables.py index 98cda9ab..5110764b 100644 --- a/recommendations/rdsap_tables.py +++ b/recommendations/rdsap_tables.py @@ -514,8 +514,8 @@ FLOOR_LEVEL_MAP = { "top floor": 5, "20+": 20, "21st or above": 21, - **{str(i).zfill(2): i for i in range(0, 21)}, - **{ordinal(i): i for i in range(-1, 21)}, - **{str(i): i for i in range(-1, 21)}, - **{i: i for i in range(-1, 21)}, + **{str(i).zfill(2): i for i in range(0, 51)}, + **{ordinal(i): i for i in range(-1, 51)}, + **{str(i): i for i in range(-1, 51)}, + **{i: i for i in range(-1, 51)}, } diff --git a/recommendations/tests/test_data/heating_recommendations_data.py b/recommendations/tests/test_data/heating_recommendations_data.py new file mode 100644 index 00000000..f283050b --- /dev/null +++ b/recommendations/tests/test_data/heating_recommendations_data.py @@ -0,0 +1,391 @@ +testing_examples = [ + { + "epc": { + 'lmk-key': '948324269042014090409224502942098', 'address1': '15, Ringwood Crescent', 'address2': None, + 'address3': None, 'postcode': 'TS19 9DN', 'building-reference-number': 1016769078, + 'current-energy-rating': 'C', 'potential-energy-rating': 'B', 'current-energy-efficiency': 79, + 'potential-energy-efficiency': 85, 'property-type': 'House', 'built-form': 'Semi-Detached', + 'inspection-date': '2014-08-21', 'local-authority': 'E06000004', 'constituency': 'E14000970', + 'county': None, + 'lodgement-date': '2014-09-04', 'transaction-type': 'none of the above', 'environment-impact-current': 77, + 'environment-impact-potential': 85, 'energy-consumption-current': 152, + 'energy-consumption-potential': 103.0, 'co2-emissions-current': 2.2, 'co2-emiss-curr-per-floor-area': 30, + 'co2-emissions-potential': 1.5, 'lighting-cost-current': 61.0, 'lighting-cost-potential': 47.0, + 'heating-cost-current': 625.0, 'heating-cost-potential': 522.0, 'hot-water-cost-current': 100.0, + 'hot-water-cost-potential': 71.0, 'total-floor-area': 74.0, 'energy-tariff': 'Single', + 'mains-gas-flag': 'Y', 'floor-level': 'NODATA!', 'flat-top-storey': None, 'flat-storey-count': None, + 'main-heating-controls': 2106.0, 'multi-glaze-proportion': 100.0, + 'glazed-type': 'double glazing installed before 2002', 'glazed-area': 'Normal', 'extension-count': 0.0, + 'number-habitable-rooms': 3.0, 'number-heated-rooms': 3.0, 'low-energy-lighting': 70.0, + 'number-open-fireplaces': 0.0, 'hotwater-description': 'From main system', 'hot-water-energy-eff': 'Good', + 'hot-water-env-eff': 'Good', 'floor-description': 'Solid, no insulation (assumed)', + 'floor-energy-eff': None, + 'floor-env-eff': None, 'windows-description': 'Fully double glazed', 'windows-energy-eff': 'Average', + 'windows-env-eff': 'Average', 'walls-description': 'Cavity wall, filled cavity', 'walls-energy-eff': 'Good', + 'walls-env-eff': 'Good', 'secondheat-description': 'Room heaters, mains gas', 'sheating-energy-eff': None, + 'sheating-env-eff': None, 'roof-description': 'Pitched, 50 mm loft insulation', 'roof-energy-eff': 'Poor', + 'roof-env-eff': 'Poor', 'mainheat-description': 'Boiler and radiators, mains gas', + 'mainheat-energy-eff': 'Good', 'mainheat-env-eff': 'Good', + 'mainheatcont-description': 'Programmer, room thermostat and TRVs', 'mainheatc-energy-eff': 'Good', + 'mainheatc-env-eff': 'Good', 'lighting-description': 'Low energy lighting in 70% of fixed outlets', + 'lighting-energy-eff': 'Very Good', 'lighting-env-eff': 'Very Good', + 'main-fuel': 'mains gas (not community)', 'wind-turbine-count': 0.0, 'heat-loss-corridor': 'NO DATA!', + 'unheated-corridor-length': None, 'floor-height': 2.5, 'photo-supply': 50.0, + 'solar-water-heating-flag': None, + 'mechanical-ventilation': 'natural', 'address': '15, Ringwood Crescent', + 'local-authority-label': 'Stockton-on-Tees', 'constituency-label': 'Stockton North', + 'posttown': 'STOCKTON-ON-TEES', 'construction-age-band': 'England and Wales: 1950-1966', + 'lodgement-datetime': '2014-09-04 09:22:45', 'tenure': 'owner-occupied', + 'fixed-lighting-outlets-count': 10.0, 'low-energy-fixed-light-count': 7.0, 'uprn': 100110195416.0, + 'uprn-source': 'Address Matched' + }, + "heating_recommendation_descriptions": [ + "Install an air source heat pump, and upgrade heating controls to Smart Thermostats, room sensors and " + "smart radiator valves (time & temperature zone control). The cost includes the £7500 boiler upgrade " + "scheme grant", + ], + "heating_controls_recommendation_descriptions": [ + "Upgrade heating controls to Smart Thermostats, room sensors and smart radiator valves (time & " + "temperature zone control)" + ], + "notes": "This property has a boiler, radiators & mains gas with good efficiency so the only recommendation" + "we expect here is for an air source heat pump. The heating controls are a programmer, room thermostat" + "and TRVs and so we should expect a TTZC recommendation" + }, + { + "epc": { + 'lmk-key': '153995620832008100717310934068296', 'address1': 'Apartment 13 The Quays', + 'address2': 'Burscough', 'address3': None, 'postcode': 'L40 5TW', + 'building-reference-number': 2604281568, 'current-energy-rating': 'C', 'potential-energy-rating': 'B', + 'current-energy-efficiency': 69, 'potential-energy-efficiency': 84, 'property-type': 'Flat', + 'built-form': 'Detached', 'inspection-date': '2008-10-06', 'local-authority': 'E07000127', + 'constituency': 'E14001033', 'county': 'Lancashire', 'lodgement-date': '2008-10-07', + 'transaction-type': 'marketed sale', 'environment-impact-current': 78, + 'environment-impact-potential': 78, 'energy-consumption-current': 195, + 'energy-consumption-potential': 192.0, 'co2-emissions-current': 1.7, + 'co2-emiss-curr-per-floor-area': 29, 'co2-emissions-potential': 1.7, 'lighting-cost-current': 35, + 'lighting-cost-potential': 38, 'heating-cost-current': 108, 'heating-cost-potential': 89, + 'hot-water-cost-current': 256, 'hot-water-cost-potential': 104, 'total-floor-area': 57.2, + 'energy-tariff': 'Single', 'mains-gas-flag': 'N', 'floor-level': '1st', 'flat-top-storey': 'Y', + 'flat-storey-count': 2.0, 'main-heating-controls': 2603.0, 'multi-glaze-proportion': 100.0, + 'glazed-type': 'double glazing installed during or after 2002', 'glazed-area': 'Normal', + 'extension-count': 0.0, 'number-habitable-rooms': 3.0, 'number-heated-rooms': 3.0, + 'low-energy-lighting': 77.0, 'number-open-fireplaces': 0.0, + 'hotwater-description': 'Electric immersion, standard tariff', 'hot-water-energy-eff': 'Very Poor', + 'hot-water-env-eff': 'Poor', 'floor-description': '(other premises below)', 'floor-energy-eff': None, + 'floor-env-eff': None, 'windows-description': 'Fully double glazed', 'windows-energy-eff': 'Good', + 'windows-env-eff': 'Good', 'walls-description': 'Cavity wall, as built, insulated (assumed)', + 'walls-energy-eff': 'Good', 'walls-env-eff': 'Good', + 'secondheat-description': 'Portable electric heaters', 'sheating-energy-eff': None, + 'sheating-env-eff': None, 'roof-description': '(another dwelling above)', 'roof-energy-eff': None, + 'roof-env-eff': None, 'mainheat-description': 'Room heaters, electric', + 'mainheat-energy-eff': 'Very Poor', 'mainheat-env-eff': 'Poor', + 'mainheatcont-description': 'Programmer and appliance thermostats', 'mainheatc-energy-eff': 'Good', + 'mainheatc-env-eff': 'Good', 'lighting-description': 'Low energy lighting in 77% of fixed outlets', + 'lighting-energy-eff': 'Very Good', 'lighting-env-eff': 'Very Good', + 'main-fuel': 'electricity - this is for backwards compatibility only and should not be used', + 'wind-turbine-count': 0.0, 'heat-loss-corridor': 'heated corridor', 'unheated-corridor-length': None, + 'floor-height': 2.3, 'photo-supply': 0.0, 'solar-water-heating-flag': 'N', + 'mechanical-ventilation': 'natural', 'address': 'Apartment 13 The Quays, Burscough', + 'local-authority-label': 'West Lancashire', 'constituency-label': 'West Lancashire', + 'posttown': 'ORMSKIRK', 'construction-age-band': 'England and Wales: 2003-2006', + 'lodgement-datetime': '2008-10-07 17:31:09', 'tenure': 'owner-occupied', + 'fixed-lighting-outlets-count': None, 'low-energy-fixed-light-count': None, 'uprn': 10012342725.0, + 'uprn-source': 'Address Matched', + }, + "heating_recommendation_descriptions": [ + "Install high heat retention electric storage heaters and upgrade heating controls to High Heat Retention " + "Storage Heater Controls" + ], + "heating_controls_recommendation_descriptions": [], + "notes": "This property has electric room heaters and is off gas so a boiler recommendation is not appropriate." + "We would expect a high heat retention storage recommendation. The property is a flat and therefore" + "we don't expect an air source heat pump recommendation. We also wouldn't expect a specific heating" + "control recommendation here" + }, + { + "epc": { + 'lmk-key': '751851300152012022010205497220090', 'address1': '21, Fullers Close', 'address2': 'Kelvedon', + 'address3': None, 'postcode': 'CO5 9JX', 'building-reference-number': 8075968, 'current-energy-rating': 'D', + 'potential-energy-rating': 'D', 'current-energy-efficiency': 55, 'potential-energy-efficiency': 56, + 'property-type': 'Bungalow', 'built-form': 'Detached', 'inspection-date': '2012-02-20', + 'local-authority': 'E07000067', 'constituency': 'E14001045', 'county': 'Essex', + 'lodgement-date': '2012-02-20', + 'transaction-type': 'non marketed sale', 'environment-impact-current': 39, + 'environment-impact-potential': 39, + 'energy-consumption-current': 475, 'energy-consumption-potential': 472.0, 'co2-emissions-current': 5.4, + 'co2-emiss-curr-per-floor-area': 84, 'co2-emissions-potential': 5.4, 'lighting-cost-current': 53.0, + 'lighting-cost-potential': 40.0, 'heating-cost-current': 674.0, 'heating-cost-potential': 678.0, + 'hot-water-cost-current': 110.0, 'hot-water-cost-potential': 110.0, 'total-floor-area': 64.45, + 'energy-tariff': 'dual', 'mains-gas-flag': 'N', 'floor-level': 'NODATA!', 'flat-top-storey': None, + 'flat-storey-count': None, 'main-heating-controls': '2402', 'multi-glaze-proportion': 100.0, + 'glazed-type': 'double glazing installed before 2002', 'glazed-area': 'Normal', 'extension-count': 0.0, + 'number-habitable-rooms': 3.0, 'number-heated-rooms': 3.0, 'low-energy-lighting': 67.0, + 'number-open-fireplaces': 0.0, 'hotwater-description': 'Electric immersion, off-peak', + 'hot-water-energy-eff': 'Average', 'hot-water-env-eff': 'Very Poor', + 'floor-description': 'Suspended, no insulation (assumed)', 'floor-energy-eff': None, 'floor-env-eff': None, + 'windows-description': 'Fully double glazed', 'windows-energy-eff': 'Average', 'windows-env-eff': 'Average', + 'walls-description': 'Cavity wall, as built, insulated (assumed)', 'walls-energy-eff': 'Good', + 'walls-env-eff': 'Good', 'secondheat-description': 'Room heaters, electric', 'sheating-energy-eff': None, + 'sheating-env-eff': None, 'roof-description': 'Pitched, 300+ mm loft insulation', + 'roof-energy-eff': 'Very Good', + 'roof-env-eff': 'Very Good', 'mainheat-description': 'Electric storage heaters', + 'mainheat-energy-eff': 'Poor', + 'mainheat-env-eff': 'Very Poor', 'mainheatcont-description': 'Automatic charge control', + 'mainheatc-energy-eff': 'Average', 'mainheatc-env-eff': 'Average', + 'lighting-description': 'Low energy lighting in 67% of fixed outlets', 'lighting-energy-eff': 'Good', + 'lighting-env-eff': 'Good', 'main-fuel': 'electricity (not community)', 'wind-turbine-count': 0.0, + 'heat-loss-corridor': 'NO DATA!', 'unheated-corridor-length': None, 'floor-height': 2.38, + 'photo-supply': 0.0, + 'solar-water-heating-flag': None, 'mechanical-ventilation': 'natural', + 'address': '21, Fullers Close, Kelvedon', + 'local-authority-label': 'Braintree', 'constituency-label': 'Witham', 'posttown': 'COLCHESTER', + 'construction-age-band': 'England and Wales: 1983-1990', 'lodgement-datetime': '2012-02-20 10:20:54', + 'tenure': 'owner-occupied', 'fixed-lighting-outlets-count': 6.0, 'low-energy-fixed-light-count': 4.0, + 'uprn': 100090311351.0, 'uprn-source': 'Address Matched', 'property-type_y': None, 'built-form_y': None, + }, + "heating_recommendation_descriptions": [], + "heating_controls_recommendation_descriptions": [], + "notes": "This test has electric storage heaters with automatic charge control - this case should be researched" + "and checked that a high heat retention storage recommendation is actually sensible. If it's not, " + "we should adjust accordingly or perhaps have just a control recommendation" + }, + { + "epc": { + 'lmk-key': '1356416458532015082116515621278108', 'address1': '19a, St. Stephens Road', 'address2': None, + 'address3': None, 'postcode': 'TW3 2BH', 'building-reference-number': 5821158378, + 'current-energy-rating': 'E', 'potential-energy-rating': 'C', 'current-energy-efficiency': 54, + 'potential-energy-efficiency': 76, 'property-type': 'Maisonette', 'built-form': 'Semi-Detached', + 'inspection-date': '2015-08-21', 'local-authority': 'E09000018', 'constituency': 'E14000593', + 'county': 'Greater London Authority', 'lodgement-date': '2015-08-21', 'transaction-type': 'marketed sale', + 'environment-impact-current': 48, 'environment-impact-potential': 78, 'energy-consumption-current': 383, + 'energy-consumption-potential': 155, 'co2-emissions-current': 3.4, 'co2-emiss-curr-per-floor-area': 68, + 'co2-emissions-potential': 1.4, 'lighting-cost-current': 52, 'lighting-cost-potential': 34, + 'heating-cost-current': 560, 'heating-cost-potential': 255, 'hot-water-cost-current': 166, + 'hot-water-cost-potential': 102, 'total-floor-area': 51.0, 'energy-tariff': 'Single', 'mains-gas-flag': 'Y', + 'floor-level': '1st', 'flat-top-storey': 'Y', 'flat-storey-count': None, 'main-heating-controls': '2104', + 'multi-glaze-proportion': 100.0, 'glazed-type': 'double glazing, unknown install date', + 'glazed-area': 'Normal', 'extension-count': 0.0, 'number-habitable-rooms': 3.0, 'number-heated-rooms': 3.0, + 'low-energy-lighting': 50.0, 'number-open-fireplaces': 0.0, 'hotwater-description': 'From main system', + 'hot-water-energy-eff': 'Average', 'hot-water-env-eff': 'Average', + 'floor-description': '(another dwelling below)', 'floor-energy-eff': 'NO DATA!', 'floor-env-eff': None, + 'windows-description': 'Fully double glazed', 'windows-energy-eff': 'Average', 'windows-env-eff': 'Average', + 'walls-description': 'Solid brick, as built, no insulation (assumed)', 'walls-energy-eff': 'Very Poor', + 'walls-env-eff': 'Very Poor', 'secondheat-description': 'Room heaters, mains gas', + 'sheating-energy-eff': None, 'sheating-env-eff': None, + 'roof-description': 'Pitched, 100 mm loft insulation', + 'roof-energy-eff': 'Average', 'roof-env-eff': 'Average', + 'mainheat-description': 'Boiler and radiators, mains gas', 'mainheat-energy-eff': 'Good', + 'mainheat-env-eff': 'Good', 'mainheatcont-description': 'Programmer and room thermostat', + 'mainheatc-energy-eff': 'Average', 'mainheatc-env-eff': 'Average', + 'lighting-description': 'Low energy lighting in 50% of fixed outlets', 'lighting-energy-eff': 'Good', + 'lighting-env-eff': 'Good', 'main-fuel': 'mains gas (not community)', 'wind-turbine-count': 0.0, + 'heat-loss-corridor': 'no corridor', 'unheated-corridor-length': None, 'floor-height': 2.5, + 'photo-supply': None, 'solar-water-heating-flag': 'N', 'mechanical-ventilation': 'natural', + 'address': '19a, St. Stephens Road', 'local-authority-label': 'Hounslow', + 'constituency-label': 'Brentford and Isleworth', 'posttown': 'HOUNSLOW', + 'construction-age-band': 'England and Wales: 1930-1949', 'lodgement-datetime': '2015-08-21 16:51:56', + 'tenure': 'owner-occupied', 'fixed-lighting-outlets-count': None, 'low-energy-fixed-light-count': None, + 'uprn': 100021560521.0, 'uprn-source': 'Address Matched', + }, + "heating_recommendation_descriptions": [], + "heating_controls_recommendation_descriptions": [], + "notes": "" + }, + { + "epc": { + 'lmk-key': '1164410099442014062611405027442168', 'address1': '31, Brightside Road', 'address2': None, + 'address3': None, 'postcode': 'SE13 6EP', 'building-reference-number': 5481394278, + 'current-energy-rating': 'E', 'potential-energy-rating': 'C', 'current-energy-efficiency': 48, + 'potential-energy-efficiency': 79, 'property-type': 'House', 'built-form': 'Mid-Terrace', + 'inspection-date': '2014-06-26', 'local-authority': 'E09000023', 'constituency': 'E14000789', + 'county': 'Greater London Authority', 'lodgement-date': '2014-06-26', + 'transaction-type': 'assessment for green deal', 'environment-impact-current': 44, + 'environment-impact-potential': 77, 'energy-consumption-current': 334, + 'energy-consumption-potential': 121.0, 'co2-emissions-current': 5.1, 'co2-emiss-curr-per-floor-area': 64, + 'co2-emissions-potential': 1.9, 'lighting-cost-current': 70.0, 'lighting-cost-potential': 49.0, + 'heating-cost-current': 964.0, 'heating-cost-potential': 571.0, 'hot-water-cost-current': 107.0, + 'hot-water-cost-potential': 72.0, 'total-floor-area': 80.0, 'energy-tariff': 'Single', + 'mains-gas-flag': 'Y', 'floor-level': 'NODATA!', 'flat-top-storey': None, 'flat-storey-count': None, + 'main-heating-controls': '2102', 'multi-glaze-proportion': 100.0, + 'glazed-type': 'double glazing installed before 2002', 'glazed-area': 'Normal', 'extension-count': 1.0, + 'number-habitable-rooms': 3.0, 'number-heated-rooms': 3.0, 'low-energy-lighting': 56.0, + 'number-open-fireplaces': 0.0, 'hotwater-description': 'From main system', 'hot-water-energy-eff': 'Good', + 'hot-water-env-eff': 'Good', 'floor-description': 'Suspended, no insulation (assumed)', + 'floor-energy-eff': None, 'floor-env-eff': None, 'windows-description': 'Fully double glazed', + 'windows-energy-eff': 'Average', 'windows-env-eff': 'Average', + 'walls-description': 'Solid brick, as built, no insulation (assumed)', 'walls-energy-eff': 'Very Poor', + 'walls-env-eff': 'Very Poor', 'secondheat-description': 'Room heaters, mains gas', + 'sheating-energy-eff': None, 'sheating-env-eff': None, + 'roof-description': 'Pitched, no insulation (assumed)', + 'roof-energy-eff': 'Very Poor', 'roof-env-eff': 'Very Poor', + 'mainheat-description': 'Boiler and radiators, mains gas', 'mainheat-energy-eff': 'Good', + 'mainheat-env-eff': 'Good', 'mainheatcont-description': 'Programmer, no room thermostat', + 'mainheatc-energy-eff': 'Very Poor', 'mainheatc-env-eff': 'Very Poor', + 'lighting-description': 'Low energy lighting in 56% of fixed outlets', 'lighting-energy-eff': 'Good', + 'lighting-env-eff': 'Good', 'main-fuel': 'mains gas (not community)', 'wind-turbine-count': 0.0, + 'heat-loss-corridor': 'NO DATA!', 'unheated-corridor-length': None, 'floor-height': 2.5, + 'photo-supply': 0.0, + 'solar-water-heating-flag': None, 'mechanical-ventilation': 'natural', 'address': '31, Brightside Road', + 'local-authority-label': 'Lewisham', 'constituency-label': 'Lewisham, Deptford', 'posttown': 'LONDON', + 'construction-age-band': 'England and Wales: before 1900', 'lodgement-datetime': '2014-06-26 11:40:50', + 'tenure': 'owner-occupied', 'fixed-lighting-outlets-count': 9.0, 'low-energy-fixed-light-count': 5.0, + 'uprn': 100021936225.0, 'uprn-source': 'Address Matched', + }, + "heating_recommendation_descriptions": [ + 'Install an air source heat pump, and upgrade heating controls to Smart Thermostats, room sensors and ' + 'smart radiator valves (time & temperature zone control). The cost includes the £7500 boiler upgrade ' + 'scheme grant', + ], + "heating_controls_recommendation_descriptions": [ + 'upgrade heating controls to Room thermostat, programmer and TRVs', + 'Upgrade heating controls to Smart Thermostats, room sensors and smart radiator valves (time & ' + 'temperature zone control)' + ], + "notes": "Because this property already has a boiler, we don't recommend HHR. We only have a " + "heating recommendation for an air source heat pump. Because the heating controls are " + "Programmer, no room thermostat, we have a programmer, room thermostat and trvs recommendation" + "for heating controls and for TTZC." + }, + { + "epc": { + 'lmk-key': '1139584119102014052116014126342698', 'address1': '13, Starbuck Street', 'address2': 'Rudry', + 'address3': None, 'postcode': 'CF83 3DP', 'building-reference-number': 2187913278, + 'current-energy-rating': 'E', 'potential-energy-rating': 'D', 'current-energy-efficiency': 44, + 'potential-energy-efficiency': 61, 'property-type': 'Flat', 'built-form': 'Semi-Detached', + 'inspection-date': '2014-05-21', 'local-authority': 'W06000018', 'constituency': 'W07000076', + 'county': None, + 'lodgement-date': '2014-05-21', 'transaction-type': 'rental (private)', 'environment-impact-current': 49, + 'environment-impact-potential': 64, 'energy-consumption-current': 343, + 'energy-consumption-potential': 240.0, 'co2-emissions-current': 4.0, 'co2-emiss-curr-per-floor-area': 61, + 'co2-emissions-potential': 2.8, 'lighting-cost-current': 49.0, 'lighting-cost-potential': 49.0, + 'heating-cost-current': 752.0, 'heating-cost-potential': 429.0, 'hot-water-cost-current': 281.0, + 'hot-water-cost-potential': 281.0, 'total-floor-area': 66.0, 'energy-tariff': 'Single', + 'mains-gas-flag': 'N', 'floor-level': '1st', 'flat-top-storey': 'Y', 'flat-storey-count': None, + 'main-heating-controls': 2602.0, 'multi-glaze-proportion': 100.0, + 'glazed-type': 'double glazing installed during or after 2002', 'glazed-area': 'Normal', + 'extension-count': 0.0, 'number-habitable-rooms': 4.0, 'number-heated-rooms': 4.0, + 'low-energy-lighting': 86.0, 'number-open-fireplaces': 0.0, + 'hotwater-description': 'Electric immersion, standard tariff', 'hot-water-energy-eff': 'Very Poor', + 'hot-water-env-eff': 'Very Poor', 'floor-description': '(other premises below)', 'floor-energy-eff': None, + 'floor-env-eff': None, 'windows-description': 'Fully double glazed', 'windows-energy-eff': 'Good', + 'windows-env-eff': 'Good', 'walls-description': 'Cavity wall, as built, no insulation (assumed)', + 'walls-energy-eff': 'Poor', 'walls-env-eff': 'Poor', 'secondheat-description': 'None', + 'sheating-energy-eff': None, 'sheating-env-eff': None, + 'roof-description': 'Pitched, 200 mm loft insulation', + 'roof-energy-eff': 'Good', 'roof-env-eff': 'Good', 'mainheat-description': 'Room heaters, electric', + 'mainheat-energy-eff': 'Very Poor', 'mainheat-env-eff': 'Very Poor', + 'mainheatcont-description': 'Appliance thermostats', 'mainheatc-energy-eff': 'Good', + 'mainheatc-env-eff': 'Good', 'lighting-description': 'Low energy lighting in 86% of fixed outlets', + 'lighting-energy-eff': 'Very Good', 'lighting-env-eff': 'Very Good', + 'main-fuel': 'electricity (not community)', 'wind-turbine-count': 0.0, 'heat-loss-corridor': 'no corridor', + 'unheated-corridor-length': None, 'floor-height': 2.5, 'photo-supply': 0.0, + 'solar-water-heating-flag': None, + 'mechanical-ventilation': 'natural', 'address': '13, Starbuck Street, Rudry', + 'local-authority-label': 'Caerphilly', 'constituency-label': 'Caerphilly', 'posttown': 'CAERPHILLY', + 'construction-age-band': 'England and Wales: 1950-1966', 'lodgement-datetime': '2014-05-21 16:01:41', + 'tenure': 'rental (private)', 'fixed-lighting-outlets-count': 7.0, 'low-energy-fixed-light-count': 6.0, + 'uprn': 43088770.0, 'uprn-source': 'Address Matched', + }, + "heating_recommendation_descriptions": [ + 'Install high heat retention electric storage heaters and upgrade heating controls to High Heat Retention ' + 'Storage Heater Controls' + ], + "heating_controls_recommendation_descriptions": [], + "notes": "This property is a flat so we don't have an ASHP recommendation. It also doesn't have access to the " + "mains and so it can't have a gas boiler. We don't expect any controls recommendations" + }, + { + "epc": { + 'lmk-key': '492646189022010060208143796198410', 'address1': '67, Ridgeway Road', 'address2': None, + 'address3': None, 'postcode': 'HP5 2EW', 'building-reference-number': 1976846768, + 'current-energy-rating': 'D', 'potential-energy-rating': 'D', 'current-energy-efficiency': 64, + 'potential-energy-efficiency': 68, 'property-type': 'Bungalow', 'built-form': 'Detached', + 'inspection-date': '2010-06-01', 'local-authority': 'E07000005', 'constituency': 'E14000631', + 'county': 'Buckinghamshire', 'lodgement-date': '2010-06-02', 'transaction-type': 'marketed sale', + 'environment-impact-current': 67, 'environment-impact-potential': 70, 'energy-consumption-current': 249, + 'energy-consumption-potential': 231.0, 'co2-emissions-current': 3.5, 'co2-emiss-curr-per-floor-area': 35, + 'co2-emissions-potential': 3.2, 'lighting-cost-current': 89.0, 'lighting-cost-potential': 51.0, + 'heating-cost-current': 627.0, 'heating-cost-potential': 603.0, 'hot-water-cost-current': 105.0, + 'hot-water-cost-potential': 105.0, 'total-floor-area': 76.0, 'energy-tariff': 'Single', + 'mains-gas-flag': 'Y', 'floor-level': 'NO DATA!', 'flat-top-storey': None, 'flat-storey-count': None, + 'main-heating-controls': 2104.0, 'multi-glaze-proportion': 100.0, + 'glazed-type': 'double glazing installed during or after 2002', 'glazed-area': 'Normal', + 'extension-count': 0.0, 'number-habitable-rooms': 7.0, 'number-heated-rooms': 7.0, + 'low-energy-lighting': 25.0, 'number-open-fireplaces': 1.0, 'hotwater-description': 'From main system', + 'hot-water-energy-eff': 'Very Good', 'hot-water-env-eff': 'Very Good', + 'floor-description': 'Suspended, no insulation (assumed)', 'floor-energy-eff': None, 'floor-env-eff': None, + 'windows-description': 'Fully double glazed', 'windows-energy-eff': 'Good', 'windows-env-eff': 'Good', + 'walls-description': 'Cavity wall, filled cavity', 'walls-energy-eff': 'Good', 'walls-env-eff': 'Good', + 'secondheat-description': 'Room heaters, wood logs', 'sheating-energy-eff': None, 'sheating-env-eff': None, + 'roof-description': 'Pitched, 150 mm loft insulation', 'roof-energy-eff': 'Good', 'roof-env-eff': 'Good', + 'mainheat-description': 'Boiler and radiators, mains gas', 'mainheat-energy-eff': 'Very Good', + 'mainheat-env-eff': 'Very Good', 'mainheatcont-description': 'Programmer and room thermostat', + 'mainheatc-energy-eff': 'Average', 'mainheatc-env-eff': 'Average', + 'lighting-description': 'Low energy lighting in 25% of fixed outlets', 'lighting-energy-eff': 'Average', + 'lighting-env-eff': 'Average', + 'main-fuel': 'mains gas - this is for backwards compatibility only and should not be used', + 'wind-turbine-count': 0.0, 'heat-loss-corridor': 'NO DATA!', 'unheated-corridor-length': None, + 'floor-height': 2.4, 'photo-supply': 0.0, 'solar-water-heating-flag': 'N', + 'mechanical-ventilation': 'natural', 'address': '67, Ridgeway Road', 'local-authority-label': 'Chiltern', + 'constituency-label': 'Chesham and Amersham', 'posttown': 'CHESHAM', + 'construction-age-band': 'England and Wales: 1930-1949', 'lodgement-datetime': '2010-06-02 08:14:37', + 'tenure': 'owner-occupied', 'fixed-lighting-outlets-count': None, 'low-energy-fixed-light-count': None, + 'uprn': 100080513604.0, 'uprn-source': 'Address Matched' + }, + "heating_recommendation_descriptions": [ + 'Install an air source heat pump, and upgrade heating controls to Smart Thermostats, room sensors and ' + 'smart radiator valves (time & temperature zone control). The cost includes the £7500 boiler upgrade ' + 'scheme grant' + ], + "heating_controls_recommendation_descriptions": [ + 'upgrade heating controls to Room thermostat, programmer and TRVs', + 'Upgrade heating controls to Smart Thermostats, room sensors and smart radiator valves (time & ' + 'temperature zone control)' + + ], + "notes": "This has a very efficient boiler and is a detached bungalow, but only has " + "Programmer and room thermostat for heating controls so we'd expect an ASHP heating recommendation" + "as the only option, and heating controls recommendations for programmer, room thermostats and trvs" + "as well as ttzc" + } +] + +import random +from pathlib import Path +import inspect +import pandas as pd + +# this can be used to get example data to build the test cases +src_file_path = inspect.getfile(lambda: None) +EPC_DIRECTORY = Path(src_file_path).parent / "local_data" / "all-domestic-certificates" +epc_directories = [entry for entry in EPC_DIRECTORY.iterdir() if entry.is_dir()] +directory = random.sample(epc_directories, 1)[0] +data = pd.read_csv(directory / "certificates.csv", low_memory=False) +# Rename the columns to the same format as the api returns +data.columns = [c.replace("_", "-").lower() for c in data.columns] +data["floor-height"] = data["floor-height"].fillna(2.45) + +used_examples = pd.DataFrame( + [ + { + "mainheat-description": x["epc"]["mainheat-description"], + "mainheat-energy-eff": x["epc"]["mainheat-energy-eff"], + "property-type": x["epc"]["property-type"], + "built-form": x["epc"]["built-form"], + "used": True + } for x in testing_examples + ] +) + +data = data.merge( + used_examples, how="left", on=["mainheat-description", "mainheat-energy-eff", "built-form", "property-type"] +) +data = data[pd.isnull(data["used"])].drop(columns=["used"]) + +eg = data.sample(1).to_dict("records")[0] +print(eg["mainheat-description"]) +print(eg["mainheat-energy-eff"]) +print(eg["property-type"]) +print(eg["built-form"]) +print(eg["mainheatcont-description"]) diff --git a/recommendations/tests/test_heating_recommendations.py b/recommendations/tests/test_heating_recommendations.py new file mode 100644 index 00000000..968583e4 --- /dev/null +++ b/recommendations/tests/test_heating_recommendations.py @@ -0,0 +1,124 @@ +from datetime import datetime +import pandas as pd +import msgpack +from utils.s3 import read_dataframe_from_s3_parquet, read_from_s3 +import pytest +from backend.Property import Property +from etl.epc.Record import EPCRecord +from etl.bill_savings.KwhData import KwhData +from recommendations.HeatingRecommender import HeatingRecommender +from recommendations.tests.test_data.heating_recommendations_data import testing_examples + + +class TestHeatingRecommendations: + + @pytest.fixture + def cleaning_data(self): + return read_dataframe_from_s3_parquet( + bucket_name="retrofit-data-dev", file_key="sap_change_model/cleaning_dataset.parquet", + ) + + @pytest.fixture + def cleaned(self): + df = read_from_s3( + s3_file_name="cleaned_epc_data/cleaned.bson", + bucket_name="retrofit-data-dev" + ) + + df = msgpack.unpackb(df, raw=False) + return df + + @pytest.fixture + def kwh_client(self): + client = KwhData(bucket="retrofit-data-dev", read_consumption_data=False) + # We fix this pricing table for these tests + client.retail_price_comparison = pd.DataFrame( + [ + { + "Date": datetime.today().strftime("%Y-%m-%d"), + 'Average standard variable tariff (Large legacy suppliers)': 1 + } + ] + ) + client.retail_price_comparison["Date"] = pd.to_datetime(client.retail_price_comparison["Date"]) + return client + + @pytest.mark.parametrize( + "test_case", + testing_examples + ) + def test_recommend(self, test_case, cleaning_data, cleaned, kwh_client): + """ + With this function, we test out multiple heating descriptions and check which recomendations + we retrieve alongside them + :return: + """ + + if test_case["epc"]["uprn"] == 100090311351: + raise Exception( + "This test has electric storage heaters with automatic charge control - this case should be researched" + "and checked that a high heat retention storage recommendation is actually sensible. If it's not, " + "we should adjust accordingly or perhaps have just a control recommendation" + ) + + if test_case["epc"]["uprn"] == 100021560521: + raise Exception("Finish this test - could do so while on the train") + + epc_records = {"original_epc": test_case["epc"].copy(), "full_sap_epc": {}, "old_data": []} + + epc_record = EPCRecord( + epc_records=epc_records, + run_mode="newdata", + cleaning_data=cleaning_data + ) + + p = Property( + id=0, + postcode=test_case["epc"]["postcode"], + address=test_case["epc"]["address"], + epc_record=epc_record, + energy_assessment={ + "condition": {}, + "energy_assessment_is_newer": False + } + ) + + # For these tests, this can be fixed + kwh_predictions = { + "heating_kwh_predictions": pd.DataFrame( + [ + {"id": p.uprn, "predictions": 12000} + ] + ), + "hotwater_kwh_predictions": pd.DataFrame( + [ + {"id": p.uprn, "predictions": 3000} + ] + ), + } + + p.set_features(cleaned=cleaned, kwh_client=kwh_client, kwh_predictions=kwh_predictions) + + recommender = HeatingRecommender(property_instance=p) + # Check they're empty + assert not recommender.heating_recommendations + assert not recommender.heating_control_recommendations + + recommender.recommend(has_cavity_or_loft_recommendations=False) + + assert len(recommender.heating_recommendations) == len(test_case["heating_recommendation_descriptions"]) + assert ( + len(recommender.heating_control_recommendations) == + len(test_case["heating_controls_recommendation_descriptions"]) + ) + + # Check the exact descriptions + assert ( + {x["description"] for x in recommender.heating_recommendations} == + set(test_case["heating_recommendation_descriptions"]) + ) + + assert ( + {x["description"] for x in recommender.heating_control_recommendations} == + set(test_case["heating_controls_recommendation_descriptions"]) + ) diff --git a/utils/s3.py b/utils/s3.py index b3553824..ca0cbfac 100644 --- a/utils/s3.py +++ b/utils/s3.py @@ -229,6 +229,39 @@ def read_excel_from_s3(bucket_name, file_key, header_row, drop_all_na=True): return df +def save_excel_to_s3(df, bucket_name, file_key): + """ + Save a pandas DataFrame as an Excel file on S3. + + :param df: DataFrame to save. + :param bucket_name: S3 bucket name. + :param file_key: S3 file key. This includes the file name and path. + """ + # Ensure the DataFrame is not empty + if df.empty: + raise ValueError("The DataFrame is empty. Nothing to save to Excel.") + + # Ensure the file_key ends with an appropriate Excel file extension + if not file_key.endswith((".xls", ".xlsx")): + raise ValueError("The specified file key does not appear to be an Excel file.") + + # Create a BytesIO buffer + output = BytesIO() + # Save DataFrame to an Excel file buffer + df.to_excel(output, index=False) + output.seek(0) # Important: move back to the beginning of the buffer + + # Initialize a session using boto3 + session = boto3.session.Session() + s3 = session.resource('s3') + + # Upload the Excel file from the buffer to S3 + bucket = s3.Bucket(bucket_name) + bucket.put_object(Body=output, Key=file_key) + + logger.info(f"Excel file saved to S3 bucket '{bucket_name}' with key '{file_key}'") + + def read_csv_from_s3(bucket_name, filepath): s3 = boto3.client('s3')