stonewater extracting age

.idea/Model.iml

@@ -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="Fastapi-backend" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Stonewater-wave-3" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyNamespacePackagesService">

.idea/misc.xml

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

etl/customers/stonewater/Wave 3 Preparation.py

@@ -125,6 +125,7 @@ def extract_summary_report(pdf_path):
     - Address
     """
 
+    blah
     data = {
         "Address": None,
         "Postcode": None,
@@ -701,6 +702,7 @@ def extract_epr(pdf_path):
         "Primary Energy Use (kWh/yr)": None,
         "Primary Energy Use Intensity (kWh/m2/yr)": None,
         "Number of Storeys": None,
+        "Main Building Age Band": None,
         "Fuel Bill": None,
         "Window Age Description": None,
         "Window Age Description Proportion (%)": None,
@@ -779,6 +781,10 @@ def extract_epr(pdf_path):
             floor_area = re.search(r"Total Floor Area\s(?P<floor_area>\d+)\s?m2", text).group("floor_area")
             data["Primary Energy Use Intensity (kWh/m2/yr)"] = data["Primary Energy Use (kWh/yr)"] / int(floor_area)
 
+        # Extract age band
+        age_band_match = re.search(r"Building part:\s*Main\s*-\s*built in\s*(?:[A-Z]\s*)?(\d{4}-\d{4})", text)
+        data["Main Building Age Band"] = age_band_match.group(1)
+
         # Extract Number of Storeys
         storeys_match = re.search(r"Number of Storeys:\s*(\d+)", text)
         data["Number of Storeys"] = int(storeys_match.group(1))
@@ -3022,7 +3028,6 @@ def revised_model():
     # We now do a large pull of all of the data
     extracted_data = []
     for survey_folder in tqdm(survey_folders):
-
         survey_folder_path = os.path.join(CUSTOMER_FOLDER_PATH, survey_folder)
 
         # Check that the survey folder is actually a folder