Model/epc_data/app.py

import pandas as pd
from tqdm import tqdm

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


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()

    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,
            )
        )

    cleaner = EpcClean(data)

    cleaner.clean()

    # For testing:
    from epc_data.attributes.MainFuelAttributes import MainFuelAttributes
    from collections import Counter
    count = Counter([x["main-fuel"] for x in data])
    descriptions = {x["main-fuel"] for x in data}
    out = []
    for description in descriptions:
        res = MainFuelAttributes(description).process()
        out.append(
            {
                "original_description": description,
                **res
            }
        )
    df = pd.DataFrame(out)
    df = df.sort_values("original_description")
    df = df.reset_index(drop=True)

    import numpy as np
    idx = 1
    record = df[df.index == idx].to_dict("records")[0]
    record = {k: v for k, v in record.items() if v not in [None, np.nan, False]}
    from pprint import pprint
    pprint(record)

    # Issues:
    # 1) '2207 Time and temperature zone control' - we don't pick up any reference to the fact this is a time and
    # temperature zone control
    #     and we only pick up temperature zone control at the moment. Can we capture this too
    # 2) 'Charging system linked to use of community heating, programmer and at least two room stats' - what are room
    # stats and how should
    #     we capture this?

    df.to_dict("records")