Fixed getting property type and built form for ha107

etl/eligibility/ha_15_32/ha_analysis_batch_3.py

@@ -223,12 +223,67 @@ class DataLoader:
 
         return asset_list
 
+    @staticmethod
+    def extract_property_info_ha107(properties):
+        property_types = {
+            "House": "House",
+            "Flat": "Flat",
+            "Bungalow": "Bungalow",
+            "Maisonette": "Maisonette",
+            "Bedsit": None
+        }
+
+        built_forms = {
+            "Detached": "Detached",
+            "Semi Detached": "Semi-Detached",
+            "End Terrace": "End-Terrace",
+            "Mid Terrace": "Mid-Terrace"
+        }
+
+        # Function to extract property type and built form from a description
+        def extract_from_description(description):
+            property_type = None
+            built_form = None
+
+            for key in property_types:
+                if key in description:
+                    property_type = property_types[key]
+                    break
+
+            for key in built_forms:
+                if key in description:
+                    built_form = built_forms[key]
+                    break
+
+            return property_type, built_form
+
+        # Process each property in the list
+        results = []
+        for property_description in properties:
+            property_type, built_form = extract_from_description(property_description)
+            results.append(
+                {
+                    "Property type": property_description,
+                    "property_type": property_type,
+                    "built_form": built_form
+                }
+            )
+        results = pd.DataFrame(results)
+
+        return results
+
     def append_asset_list_built_form(self, ha_name, asset_list):
 
         # Finally, we process property_type or built form, where needed
         if ha_name == "HA6":
             asset_list["built_form"] = asset_list["Property Type"].apply(self.identify_built_form_ha6)
 
+        if ha_name == "HA107":
+            mapped_df = self.extract_property_info_ha107(asset_list["Property type"].unique())
+            asset_list = asset_list.merge(
+                mapped_df, how="left", on="Property type"
+            )
+
         return asset_list
 
     @staticmethod
@@ -1280,26 +1335,8 @@ def get_property_type_and_built_form(property_meta, ha_name):
                 property_type = "House"
     elif ha_name == "HA107":
 
-        dwelling_style = property_meta["Dwelling Style"]
-        if isinstance(dwelling_style, str):
-            dwelling_style = dwelling_style.strip()
-
-        property_type = PROPERTY_TYPE_LOOKUP[ha_name]["property_type"].get(property_meta["DwellingType"])
-        built_form = PROPERTY_TYPE_LOOKUP[ha_name]["built_form"].get(dwelling_style, None)
-
-        if property_type is None:
-            if built_form in ["Semi-Detached", "Mid-Terrace", "End-Terrace", "Detached"]:
-                property_type = "House"
-
-            if "flat" in property_meta["Wall Construction"].lower():
-                property_type = "Flat"
-
-            if (property_meta["DwellingType"] == "UNKNOWN") & (property_meta["Dwelling Style"] == 0):
-                # Hand a few specific cases
-                property_type = "Bungalow"
-
-            if property_meta["Street"] == "School View":
-                property_type = "Bungalow"
+        property_type = property_meta.get("property_type", None)
+        built_form = property_meta.get("built_form", None)
 
     else:
         raise NotImplementedError("Implement me")