junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

modified the hug postcodes data

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-11-29 15:12:14 +00:00
parent c6e02836a8
commit c806ef7151
4 changed files with 30 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.idea/Model.iml generated
View file

@ -7,7 +7,7 @@
<sourceFolder url="file://$MODULE_DIR$/open_uprn" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/recommendations" isTestSource="false" />
</content>
<orderEntry type="jdk" jdkName="Lodgment-spreadsheet" jdkType="Python SDK" />
<orderEntry type="jdk" jdkName="Fastapi-backend" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
<component name="PyNamespacePackagesService">

2
.idea/misc.xml generated
View file

@ -3,7 +3,7 @@
<component name="Black">
<option name="sdkName" value="Python 3.10 (backend)" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Lodgment-spreadsheet" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="Fastapi-backend" project-jdk-type="Python SDK" />
<component name="PyCharmProfessionalAdvertiser">
<option name="shown" value="true" />
</component>

0
etl/access_reporting/app.py Normal file
View file

29
etl/customers/gla/hug_postcodes.py
View file

@ -3,6 +3,7 @@ import pandas as pd
from pathlib import Path
from tqdm import tqdm
from etl.epc.settings import EARLIEST_EPC_DATE
from etl.spatial.OpenUprnClient import OpenUprnClient
src_file_path = inspect.getfile(lambda: None)
@ -22,6 +23,7 @@ for directory in tqdm(epc_directories):
data = data[data["lodgement-date"] >= EARLIEST_EPC_DATE]
data = data[~pd.isnull(data["uprn"])]
data["uprn"] = data["uprn"].astype(int)
# Take just the newest EPC per uprn, based on lodgement-date
data = data.sort_values("lodgement-date", ascending=False).drop_duplicates("uprn")
# Take EPC D and below
@ -31,16 +33,41 @@ for directory in tqdm(epc_directories):
# Take homes that don't have a gas boiler
off_gas = data[~data["main-fuel"].str.contains("mains gas", case=False, na=False)]
if off_gas.empty:
continue
# Remote properties with conservation area issues
uprns = off_gas["uprn"].unique()
# Get data
ca_data = OpenUprnClient.get_spatial_data(uprns, "retrofit-data-dev")
off_gas = off_gas.merge(
ca_data[["UPRN", "conservation_status", "is_listed_building", "is_heritage_building"]].rename(
columns={"UPRN": "uprn"}
),
how="left",
on="uprn",
)
# Remove any restricted units
off_gas = off_gas[
(off_gas["conservation_status"] != True)
& (off_gas["is_listed_building"] != True)
& (off_gas["is_heritage_building"] != True)
]
region_summary = off_gas.groupby("postal_region").size().reset_index(name="count")
aggregation.append(region_summary)
postal_region_aggregation = pd.concat(aggregation)
# Re-aggregate
postal_region_aggregation = postal_region_aggregation.groupby("postal_region")["count"].sum().reset_index()
postal_region_aggregation = postal_region_aggregation.sort_values("count", ascending=False)
postal_region_aggregation = postal_region_aggregation.rename(
columns={"postal_region": "Postcode Region", "count": "Number of Homes"}
)
postal_region_aggregation.to_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/Customers/GLA/Off Gas EPC D-G Postal Regions.xlsx",
"/Users/khalimconn-kowlessar/Documents/hestia/Customers/GLA/Off Gas EPC D-G Postal Regions - without conservation "
"area.xlsx",
index=False
)