Model/etl/customers/livewest/route_march.py
2024-05-02 00:37:36 +01:00

134 lines
4.1 KiB
Python

import os
import pandas as pd
from tqdm import tqdm
from dotenv import load_dotenv
from utils.s3 import read_excel_from_s3
from backend.SearchEpc import SearchEpc
from epc_api.client import EpcClient
from utils.s3 import save_csv_to_s3
load_dotenv(dotenv_path="backend/.env")
EPC_AUTH_TOKEN = os.getenv("EPC_AUTH_TOKEN")
def route_march_may_2024():
"""
This code pulls supplementary data for a route march that is expected to happen in May 2024. This code
was authored on the 30th April 2024.
"""
asset_list = read_excel_from_s3(
bucket_name="retrofit-datalake-dev",
file_key="customers/Livewest/Livewest proposed route march Apr-May 2024.xlsx",
header_row=0
)
epc_data = []
for _, unit in tqdm(asset_list.iterrows(), total=len(asset_list)):
lst = [unit["NO"], unit["ADDRESS 1"], unit["ADDRESS 2"], unit["ADDRESS 3"], unit["POSTCODE"]]
lst = [str(x).strip() for x in lst if not pd.isnull(x)]
full_address = ", ".join(lst)
searcher = SearchEpc(
address1=str(unit["NO"]),
postcode=unit["POSTCODE"],
auth_token=EPC_AUTH_TOKEN,
os_api_key="",
property_type=None,
fast=True,
full_address=full_address
)
# Force the skipping of estimating the EPC
searcher.ordnance_survey_client.property_type = None
searcher.ordnance_survey_client.built_form = None
searcher.find_property(skip_os=True)
if searcher.newest_epc is None:
# We try with a different address 1
add1 = str(unit["NO"]).lower()
add1 = (
add1
.replace("flat", "")
.replace("ft", "")
.replace("t", "").strip()
)
searcher = SearchEpc(
address1=add1,
postcode=unit["POSTCODE"],
auth_token=EPC_AUTH_TOKEN,
os_api_key="",
property_type=None,
fast=True,
full_address=full_address
)
# Force the skipping of estimating the EPC
searcher.ordnance_survey_client.property_type = None
searcher.ordnance_survey_client.built_form = None
searcher.find_property(skip_os=True)
if searcher.newest_epc is None:
continue
epc = {
"asset_list_house_no": unit["NO"],
"asset_list_address1": unit["ADDRESS 1"],
"asset_list_postcode": unit["POSTCODE"],
**searcher.newest_epc.copy()
}
epc_data.append(epc)
epc_df = pd.DataFrame(epc_data)
#
# Retrieve just the data we need
epc_df = epc_df[
[
"asset_list_house_no",
"asset_list_address1",
"asset_list_postcode",
"uprn",
"address",
"property-type",
"built-form",
"inspection-date",
"current-energy-rating",
"current-energy-efficiency",
"roof-description",
"walls-description",
"transaction-type"
]
].rename(columns={"address": "Matched EPC Address"})
asset_list = asset_list.merge(
epc_df,
how="left",
left_on=["NO", "ADDRESS 1", "POSTCODE"],
right_on=["asset_list_house_no", "asset_list_address1", "asset_list_postcode"]
)
asset_list = asset_list.drop_duplicates(subset=["NO", "ADDRESS 1", "POSTCODE"])
asset_list = asset_list.drop(columns=["asset_list_house_no", "asset_list_address1", "asset_list_postcode"])
# Rename the columns
asset_list = asset_list.rename(columns={
"property-type": "Property Type",
"built-form": "Archetype",
"inspection-date": "Last EPC Inspection Date",
"current-energy-rating": "Last survey EPC Rating",
"current-energy-efficiency": "Last survey SAP Score",
"roof-description": "Roof Construction",
"walls-description": "Wall Construction",
"transaction-type": "Last EPC Reason"
})
# Store as an excel
filename = "Livewest EPC data.xlsx"
asset_list.to_excel(filename, index=False)