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

addded # Storeys

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-10-29 13:55:18 +00:00
parent e22baed16f
commit b7f402ba9d
3 changed files with 9 additions and 6 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="Engine" jdkType="Python SDK" />
<orderEntry type="jdk" jdkName="Stonewater-wave-3" 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="Engine" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="Stonewater-wave-3" project-jdk-type="Python SDK" />
<component name="PyCharmProfessionalAdvertiser">
<option name="shown" value="true" />
</component>

11
etl/customers/stonewater/Wave 3 Preparation.py
View file

@ -19,6 +19,7 @@ def extract_summary_report(pdf_path):
data = {
"Address": None,
"Current SAP Rating": None,
"Number of Storeys": None,
"Fuel Bill": None,
"Window Age Description": None,
"Window Age Description Proportion (%)": None,
@ -32,13 +33,15 @@ def extract_summary_report(pdf_path):
# Extract Current SAP rating
sap_match = re.search(r"Current SAP rating:\s*([A-Z] \d+)", text)
if sap_match:
data["Current SAP Rating"] = sap_match.group(1)
data["Current SAP Rating"] = sap_match.group(1)
# Number of storeys
storeys_match = re.search(r"Number of Storeys:\s*(\d+)", text)
data["Number of Storeys"] = int(storeys_match.group(1))
# Extract Fuel Bill
fuel_bill_match = re.search(r"Fuel Bill:\s*£(\d+)", text)
if fuel_bill_match:
data["Fuel Bill"] = f"£{fuel_bill_match.group(1)}"
data["Fuel Bill"] = f"£{fuel_bill_match.group(1)}"
# Extract individual address components
postcode = re.search(r"Postcode:\s*(.*?)\nRegion:", text)