Model/model_data/app.py

from tqdm import tqdm
import os
from model_data.BoreholeClient import BoreholeClient
from model_data.LandRegistryClient import LandRegistryClient
from model_data.ConservationAreaClient import ConservationAreaClient

from model_data.temp_inputs import input_data
from model_data.Property import Property
from model_data.config import EPC_AUTH_TOKEN
from epc_api.client import EpcClient
from model_data.downloader import pagenated_epc_download
from model_data.EpcClean import EpcClean
from model_data.OpenUprnClient import OpenUprnClient

LAND_REGISTRY_PATHS = [
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-monthly-update-new-version.csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2022 (1).csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2021.csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2020.csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2019.csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2018.csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2017-part1.csv",
    os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/pp-2017-part2.csv",
]


def handler():
    # To begin with, the input data is a list of dictionaries, however we would read this file in

    epc_client = EpcClient(auth_token=EPC_AUTH_TOKEN)

    input_properties = [
        Property(postcode=config['postcode'], address1=config['address1'], epc_client=epc_client)
        for config in input_data
    ]

    for p in input_properties:
        p.search_address_epc()

    uprns = [p.data['uprn'] for p in input_properties]

    open_uprn_client = OpenUprnClient(
        path=os.path.abspath(
            os.path.dirname(__file__)
        ) + "/model_data/local_data/osopenuprn_202306_csv/osopenuprn_202305.csv",
        uprns=uprns
    )
    open_uprn_client.read()

    # We're using Ordinance Survey Open Uprn data
    # to find the coordinates of each address, which we will then be able to use at a later stage
    for p in input_properties:
        p.get_coordinates(open_uprn_client)

    conservation_area_client = ConservationAreaClient(
        historic_england_path=os.path.abspath(
            os.path.dirname(__file__)
        ) + "/model_data/local_data/Historic_Eng_Conservation_Areas/Conservation_Areas.shp",
        gov_path=os.path.abspath(
            os.path.dirname(__file__)
        ) + "/model_data/local_data/gov-conservation-area.geojson"
    )
    conservation_area_client.read()

    # Check if the property is in a conversation area
    for p in input_properties:
        p.set_is_in_conservation_area(conservation_area_client)

    local_authorities = {p.data['local-authority'] for p in input_properties}

    data = []
    for la in tqdm(local_authorities):
        data.extend(
            pagenated_epc_download(
                client=epc_client,
                params={"local-authority": la},
                page_size=5000,
                n_pages=10,
            )
        )

    # Incorporate input data into cleaning
    cleaner = EpcClean(data + [p.data for p in input_properties])
    cleaner.clean()

    address_meta = [
        {
            "postcode": x["postcode"].upper(),
            "address1": x["address1"].upper(),
            "address2": x["address2"].upper(),
            "address3": x["address3"].upper(),
            "address": x["address"],
            "uprn": x["uprn"]
        } for x in data
    ]

    # Land registry
    land_registry_client = LandRegistryClient(
        paths=LAND_REGISTRY_PATHS,
        addresses=address_meta
    )
    land_registry_client.read()

    # Borehole
    borehole_client = BoreholeClient(
        path=os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/borehole/borehole.dbf"
    )
    borehole_client.read()

    # Now, for our input properties, we need to identify the components of the building, based
    # on the cleaning we've done
    for p in input_properties:
        p.get_components(cleaner)

    # Now, given the components, we want to idenfity upgrade options
    import pandas as pd
    walls_df = pd.DataFrame(
        [{"address1": p.address1, **p.walls} for p in input_properties]
    )

    input_properties[6].data["address1"]
    input_properties[6].data["postcode"]
    walls_df["address1"].values[6]
    walls_df["original_description"].values[6]
    # Walls
    # Property 0
    # '28 Distillery Wharf', 'Average thermal transmittance 0.16 W/m-¦K'
    # Because the insulation is already within the max threshold for new builds
    # Also, I know that the property was built after 1990 so was built with insulation (let's get land registry data)
    # It's likely not worth doing an insulation upgrade, however if anything, we would do internal wall insulation
    # logic:
    # 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
    # Property 1
    # 'Flat 14 Godley V C House', Solid brick, as built, no insulation (assumed)
    # Since the wall is solid brick (therefore no cavity), we can recommend the following:
    # External wall insulation
    # Internal wall insulation
    # Property 2
    # '49, Elderfield Road', Solid brick, as built, no insulation (assumed)
    # Same as property 1
    # Property 3
    # 26, Stanhope Road', 'Average thermal transmittance 0.14 W/m-¦K'
    # Same as property 0
    # Property 4
    # 'Flat 3 Frederick Building' 'Solid brick, as built, no insulation (assumed)'
    # Same as property 1
    # 'Flat 4 Frederick Building' 'Solid brick, as built, no insulation (assumed)'
    # Same as property 1
    # 'Flat 28, 22 Adelina Grove' 'Solid brick, as built, insulated (assumed)'

    from model_data.recommendations.WallRecommendations import WallRecommendations
    self = WallRecommendations(property_instance=input_properties[6])

    # We need to deduce a U-value for "Good" energy effieciency

    df = pd.DataFrame(data)
    df = df[df["walls-description"].str.contains("Average thermal transmittance")]

    mainheating = pd.DataFrame(
        [{"address1": p.address1, "postcode": p.postcode, **p.main_heating} for p in input_properties])
    hotwater = pd.DataFrame([{"address1": p.address1, **p.hotwater} for p in input_properties])

    mainheating[["address1", "postcode"]]

    # TODO: I want to knwo what "Good" efficiency means for the description
    #  'Flat 28, 22 Adelina Grove' 'Solid brick, as built, insulated (assumed)'
    #    so to do this, filter on the local authority code and property type, where we have U
    #   values for the wall and take a median!