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

minor initial scoping

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-04-18 11:07:15 +01:00
parent 25c95fb749
commit fb6ab43b76
4 changed files with 25 additions and 5 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="Python 3.10 (backend)" jdkType="Python SDK" />
<orderEntry type="jdk" jdkName="Python 3.10 (model_data)" 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="Python 3.10 (backend)" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (model_data)" project-jdk-type="Python SDK" />
<component name="PythonCompatibilityInspectionAdvertiser">
<option name="version" value="3" />
</component>

3
etl/customers/gla_croydon_demo/asset_list.py
View file

@ -34,9 +34,6 @@ def app():
low_memory=False
)
z = epc_data.groupby(["WALLS_DESCRIPTION", "WALLS_ENERGY_EFF"]).size().reset_index(name="count")
z = z[z["MAINHEAT_DESCRIPTION"] == "Boiler and radiators, mains gas"]
# Filter on entries where we have a UPRN
epc_data = epc_data[~pd.isnull(epc_data["UPRN"])]

23
etl/customers/vander_elliot/initial_scoping.py Normal file
View file

@ -0,0 +1,23 @@
import pandas as pd
from utils.s3 import save_csv_to_s3
def app():
# Check how many properties there are at EPC F/G in Birmingham
epc_data = pd.read_csv(
"local_data/all-domestic-certificates/domestic-E08000025-Birmingham/certificates.csv",
low_memory=False
)
# Filter on entries where we have a UPRN
epc_data = epc_data[~pd.isnull(epc_data["UPRN"])]
# Get the newest EPC for each UPRN. We use LODGEMENT_DATE as a proxy for this
epc_data["LODGEMENT_DATE"] = pd.to_datetime(epc_data["LODGEMENT_DATE"])
epc_data = epc_data.sort_values("LODGEMENT_DATE", ascending=False).drop_duplicates("UPRN")
epc_data = epc_data[epc_data["CURRENT_ENERGY_RATING"].isin(["F", "G"])]
one_years_ago = pd.Timestamp.now() - pd.DateOffset(days=int(1 * 365))
epc_data = epc_data[epc_data["LODGEMENT_DATE"] >= one_years_ago]