mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
142 lines
4.6 KiB
Python
142 lines
4.6 KiB
Python
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
|
|
|
|
|
|
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,
|
|
)["rows"]
|
|
)
|
|
|
|
# TODO: Temp - pull in sample
|
|
from collections import Counter
|
|
import pickle
|
|
from pprint import pprint
|
|
with open("./epc_data/test_epc_data.obj", "rb") as f:
|
|
data = pickle.load(f)
|
|
|
|
# TODO: Fill this
|
|
ClEANING_FIELDS = [
|
|
"roof-description",
|
|
"floor-description",
|
|
"walls-description",
|
|
"mainheat-description"
|
|
]
|
|
|
|
field = "roof-description"
|
|
unique_vals = Counter([v[field] for v in data])
|
|
pprint(unique_vals)
|
|
|
|
def search_description_options(desc):
|
|
if desc == "insulated":
|
|
return "average"
|
|
raise Exception("Handle me")
|
|
|
|
def find_insulation_thickness(description_lower, is_pitched, is_roof_room, is_flat):
|
|
|
|
if "no insulation" in description_lower:
|
|
return 0
|
|
|
|
if is_pitched:
|
|
try:
|
|
return int(description_lower.split("pitched,")[-1].split("mm")[0].lstrip().rstrip())
|
|
except ValueError as _:
|
|
desc = description_lower.split("pitched,")[-1].lstrip().split(" ")[0]
|
|
return search_description_options(desc)
|
|
|
|
if is_roof_room:
|
|
# Just search for specific phrases
|
|
desc = description_lower.split("roof room(s),")[-1].lstrip().split(" ")[0]
|
|
return search_description_options(desc)
|
|
|
|
if is_flat:
|
|
# Just search for specific phrases
|
|
desc = description_lower.split("flat,")[-1].lstrip().split(" ")[0]
|
|
return search_description_options(desc)
|
|
|
|
raise Exception("Unhandled")
|
|
|
|
def clean_roof(description):
|
|
"""
|
|
We aim to extract features about the roof, so we can characterise it. We will check:
|
|
- If the roof is pitched
|
|
- If there is a room roof
|
|
- if there is a loft
|
|
- If it has insulation
|
|
- if so, what degree of insulation
|
|
-
|
|
|
|
:param x:
|
|
:return:
|
|
"""
|
|
description_lower = description.lower().lstrip().rstrip()
|
|
|
|
if "another dwelling above" in description_lower:
|
|
return {
|
|
"is_pitched": False,
|
|
"is_roof_room": False,
|
|
"has_loft": False,
|
|
"insulation_thickness": 0,
|
|
"has_dwelling_above": True,
|
|
"assumed": "assumed" in description_lower,
|
|
"is_flat": "flat" in description_lower
|
|
}
|
|
|
|
is_pitched = "pitched" in description_lower
|
|
is_roof_room = "roof room" in description_lower
|
|
has_loft = "loft" in description_lower
|
|
is_flat = "flat" in description_lower
|
|
|
|
if "insulation" in description_lower or "insulated" in description_lower:
|
|
# if has_loft and is_pitched:
|
|
# insulation_thickness = find_insulation_thickness(description_lower)
|
|
# elif not has_loft and is_pitched:
|
|
# insulation_thickness = find_insulation_thickness(description_lower)
|
|
# else:
|
|
# raise Exception("Implement me")
|
|
insulation_thickness = find_insulation_thickness(description_lower, is_pitched, is_roof_room, is_flat)
|
|
else:
|
|
raise Exception("Implment me 2")
|
|
|
|
attributes = {
|
|
"is_pitched": is_pitched,
|
|
"is_roof_room": is_roof_room,
|
|
"has_loft": has_loft,
|
|
"insulation_thickness": insulation_thickness,
|
|
"has_dwelling_above": False,
|
|
"assumed": "assumed" in description_lower,
|
|
"is_flat": is_flat
|
|
}
|
|
|
|
return attributes
|
|
|
|
cleaned_roof = []
|
|
for description in unique_vals.keys():
|
|
cleaned_roof.append(
|
|
{"original": description, "cleaned": clean_roof(description)}
|
|
)
|