debugging asset list for ealing without wall

.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="AssetList" 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="AssetList" project-jdk-type="Python SDK" />
   <component name="PyCharmProfessionalAdvertiser">
     <option name="shown" value="true" />
   </component>

asset_list/AssetList.py

@@ -575,13 +575,18 @@ class AssetList:
 
         # We handle cleaning for walls, in the instance that the landlord provides us with EPC data and
         # we see instances of "average thermal transmittance" in the description
-        self.standardised_asset_list[self.landlord_wall_construction] = np.where(
-            self.standardised_asset_list[self.landlord_wall_construction].str.lower().str.contains(
-                "average thermal transmittance"
-            ) == True,
-            "new build - average thermal transmittance",
-            self.standardised_asset_list[self.landlord_wall_construction]
-        )
+        if self.landlord_wall_construction is not None:
+            self.standardised_asset_list[self.landlord_wall_construction] = np.where(
+                self.standardised_asset_list[self.landlord_wall_construction].str.lower().str.contains(
+                    "average thermal transmittance"
+                ) == True,
+                "new build - average thermal transmittance",
+                self.standardised_asset_list[self.landlord_wall_construction]
+            )
+        else:
+            # We want to make sure that we have a column for wall construction
+            self.landlord_wall_construction = "landlord_wall_construction"
+            self.standardised_asset_list[self.landlord_wall_construction] = None
 
         # Clear our build year column
         # We attempt to process the year built column
@@ -625,6 +630,11 @@ class AssetList:
                     if str(date_str).isdigit() & (len(str(date_str)) == 4):
                         return int(date_str)
 
+                    # Remove any non-numeric characters
+                    date_str = re.sub(r"\D", "", str(date_str))
+                    if str(date_str).isdigit() & (len(str(date_str)) == 4):
+                        return int(date_str)
+
                     raise NotImplementedError("Unhandled format for year built - implement me")
 
                 self.standardised_asset_list[self.landlord_year_built] = self.standardised_asset_list[

asset_list/app.py

@@ -246,40 +246,23 @@ def app():
     # - We want: fully insulated property (all wall types), EPC D or below (floors should be solid)
     # - Or the insulation required is loft/cavity (floors should be solid)
 
-    data_folder = "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Colchester"
-    data_filename = "Warmfront data- Colchester Borough Homes (Complete).xlsx"
-    sheet_name = "Sheet1"
-    postcode_column = 'Full Address.1'
-    fulladdress_column = "Full Address"
+    # Ealing
+    data_folder = "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Ealing/Programme data - 04032025"
+    data_filename = "Ealing BC - Property Plus Tenure 25.02.2025.xlsx"
+    sheet_name = "IGNORE - FULL MAIN"
+    postcode_column = 'Postcode'
+    fulladdress_column = "Address"
     address1_column = None
     address1_method = "first_word"
     address_cols_to_concat = []
     missing_postcodes_method = None
-    landlord_year_built = "Build Date"
+    landlord_year_built = "Year Built"
     landlord_os_uprn = None
-    landlord_property_type = "Property Type"
-    landlord_wall_construction = "Wallinsul"
-    landlord_heating_system = "HeatSorc"
+    landlord_property_type = "Property Type Code"
+    landlord_wall_construction = None
+    landlord_heating_system = None
     landlord_existing_pv = None
-    landlord_property_id = "Property Reference"
-
-    # For Westward
-    # data_folder = "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Westward"
-    # data_filename = "WESTWARD - completed list..xlsx"
-    # sheet_name = "Sheet1"
-    # postcode_column = "WFT EDIT Postcode"
-    # fulladdress_column = "Address"
-    # address1_column = None
-    # address1_method = "house_number_extraction"
-    # address_cols_to_concat = []
-    # missing_postcodes_method = None
-    # landlord_year_built = "Build date"
-    # landlord_os_uprn = "UPRN"
-    # landlord_property_type = "Location type"
-    # landlord_wall_construction = "Wall Construction (EPC)"
-    # landlord_heating_system = "Heat Source"
-    # landlord_existing_pv = "PV (Y/N)"
-    # landlord_property_id = "Place ref"
+    landlord_property_id = "Property Ref"
 
     # Maps addresses to uprn in problematic cases
     manual_uprn_map = {}

asset_list/mappings/property_type.py

@@ -21,5 +21,6 @@ PROPERTY_MAPPING = {
     'Flat': 'flat',
     'House': 'house',
     'Maisonette': 'maisonette',
-    'Stairwell': 'other'
+    'Stairwell': 'other',
+    'MAISON': 'maisonette'
 }