mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
110 lines
4.8 KiB
Python
110 lines
4.8 KiB
Python
from tqdm import tqdm
|
|
import os
|
|
import pandas as pd
|
|
|
|
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.analysis.UvalueEstimations import UvalueEstimations
|
|
from model_data.simulation_system.core.Settings import EARLIEST_EPC_DATE
|
|
from pathlib import Path
|
|
|
|
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",
|
|
]
|
|
|
|
EPC_DIRECTORY = Path(__file__).parent / "model_data" / "simulation_system" / "data" / "all-domestic-certificates"
|
|
|
|
|
|
def app():
|
|
"""
|
|
For a pre-defined list of constituencies and property data_types, we'll download EPC data from the API
|
|
and produce a dataset of cleaned fields so that when we get new properties, we can quickly
|
|
sanitise any description data
|
|
:return:
|
|
"""
|
|
|
|
# epc_client = EpcClient(auth_token=EPC_AUTH_TOKEN)
|
|
#
|
|
# constituencies = {'E14000555', 'E14000726', 'E14000720', 'E14000721', 'E14000553', 'E14000752'}
|
|
# property_types = ["bungalow", "flat", "house", "maisonette", "park home"]
|
|
# floor_areas = ["unknown", "s", "m", "l", "xl", "xxl", "xxxl"]
|
|
#
|
|
# # We pull properties from local authorities, by property type. This will allow us to build
|
|
# # a dataset of up to 10k properties per local authority/property type combination
|
|
# # For particularly old EPC data, we have inconsistent records so we'll only include EPCS that were
|
|
# # conducted after 2010, since SAP09 was introduced in 2009 an later SAP12 was introduced in England
|
|
# # and Wales from 31 July 2014
|
|
# # Download data from August 2014 onwards
|
|
# data = []
|
|
# for c in tqdm(constituencies):
|
|
# for pt in property_types:
|
|
# for fa in floor_areas:
|
|
# data.extend(
|
|
# pagenated_epc_download(
|
|
# client=epc_client,
|
|
# params={
|
|
# "constituency": c,
|
|
# "property-type": pt,
|
|
# "from-month": 8,
|
|
# "from-year": 2014,
|
|
# "floor-area": fa,
|
|
# },
|
|
# page_size=5000,
|
|
# n_pages=10,
|
|
# )
|
|
# )
|
|
|
|
# Production of sample data for land registry
|
|
# 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
|
|
# ]
|
|
#
|
|
# import pickle
|
|
# with open("sample_addresses.pkl", "wb") as f:
|
|
# pickle.dump(address_meta, f)
|
|
|
|
epc_directories = [entry for entry in EPC_DIRECTORY.iterdir() if entry.is_dir()]
|
|
for directory in epc_directories:
|
|
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]
|
|
|
|
# Convert to list of dictioaries as returned by the api
|
|
data = data.to_dict("records")
|
|
|
|
# Incorporate input data into cleaning
|
|
cleaner = EpcClean(data)
|
|
lighting_averages = cleaner.lighting_averages
|
|
#
|
|
# TODO: All of these outputs can be stored by constituency so we can reduce the amount
|
|
# of data we fetch
|
|
#
|
|
# TODO: WE need to store lighting_averages to a s3
|
|
# We should also extend these averages so they're by more variables (property type, age band,
|
|
# constituency,
|
|
# etc)
|
|
cleaner.clean()
|
|
# TODO: cleaner.cleaned datasets to s3
|
|
|
|
# TODO: Add property age band into this
|
|
uvalue_estimates = UvalueEstimations(data=data)
|
|
uvalue_estimates.get_estimates(cleaner=cleaner)
|
|
# TODO: Store these to a s3
|