From ed333e1714fa9ff3a4f09bc789e5aa37bca0bc8e Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Thu, 20 Feb 2025 09:04:26 +0000
Subject: [PATCH] refactored est no floors

---
 asset_list/AssetList.py                 | 27 +++++++++++++++++++++++++
 etl/route_march_data_pull/app.py        | 12 +++++------
 recommendations/recommendation_utils.py |  7 +++++--
 3 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/asset_list/AssetList.py b/asset_list/AssetList.py
index 4ca4c2b8..74469c63 100644
--- a/asset_list/AssetList.py
+++ b/asset_list/AssetList.py
@@ -15,6 +15,12 @@ import asset_list.mappings.walls as walls_mappings
 import asset_list.mappings.heating_systems as heating_mappings
 import asset_list.mappings.exising_pv as existing_pv_mappings
 
+from recommendations.recommendation_utils import (
+    estimate_perimeter,
+    estimate_external_wall_area,
+    estimate_number_of_floors
+)
+
 logger = setup_logger()
 
 # OpenAI API Key (set this in your environment variables for security)
@@ -224,6 +230,7 @@ class AssetList:
         "secondheat-description": "epc_secondary_heating",
         "transaction-type": "epc_reason",
         "energy-consumption-current": "epc_heat_demand",
+        "photo-supply": "epc_photo_supply"
     }
     FIND_EPC_DATA_NAMES = {
         "heating_text": "epc_estiamted_heating_kwh",
@@ -274,6 +281,7 @@ class AssetList:
 
     # Attributes - these are columns that we produce, calcualted based on other pieces of data
     ATTRIBUTE_HAS_SOLAR = "attribute_has_solar"
+    ATTRIBUTE_NUMBER_OF_FLOORS = "attribute_est_number_floors"
 
     def __init__(
         self,
@@ -645,3 +653,22 @@ class AssetList:
             self.standardised_asset_list[self.FIND_EPC_DATA_NAMES["Solar photovoltaics"]] |
             ~self.standardised_asset_list[self.EPC_API_DATA_NAMES["photo-supply"]].isin(["0.0", 0, None, ""])
         )
+
+        accepted_epc_property_types = ["House", "Flat", "Bungalow", "Maisonette"]
+
+        # The logic here is:
+        # 1) Take the property type provided by the HA themselves
+        # 2) In absence of that, take the EPC property type
+        # 3) Otherwise use None
+        self.standardised_asset_list[self.ATTRIBUTE_NUMBER_OF_FLOORS] = self.standardised_asset_list.apply(
+            lambda x: estimate_number_of_floors(
+                property_type=(
+                    x[self.STANDARD_PROPERTY_TYPE].title() if
+                    x[self.STANDARD_PROPERTY_TYPE].title() in accepted_epc_property_types else (
+                        x[self.EPC_API_DATA_NAMES["property-type"]] if not
+                        pd.isnull(x[self.EPC_API_DATA_NAMES["property-type"]]) else None
+                    )
+                )
+            ),
+            axis=1
+        )
diff --git a/etl/route_march_data_pull/app.py b/etl/route_march_data_pull/app.py
index 8b112ea2..9754e726 100644
--- a/etl/route_march_data_pull/app.py
+++ b/etl/route_march_data_pull/app.py
@@ -514,7 +514,6 @@ def app():
         find_my_epc_data["Solar photovoltaics"] = False
 
     # Retrieve just the data we need
-
     epc_df = epc_df[
         [asset_list.DOMNA_PROPERTY_ID] + list(asset_list.EPC_API_DATA_NAMES.keys())
         ].rename(
@@ -529,15 +528,14 @@ def app():
     )
 
     asset_list.merge_data(epc_df)
+    # TODO: TEMP!!!
+    epc_df["epc_os_uprn"] = epc_df["epc_os_uprn"].astype("Int64").astype(str)
+    asset_list.standardised_asset_list = asset_list.standardised_asset_list.merge(
+        epc_df, how="left", left_on="ordnance_survey_uprn", right_on="epc_os_uprn"
+    )
 
     asset_list.extract_attributes()
 
-    asset_list["Has Solar PV"] = asset_list["Has Solar PV"] | ~asset_list["photo-supply"].isin(["0.0", 0, None, ""])
-    asset_list = asset_list.drop(columns=["photo-supply"])
-
-    # Rename the columns
-    asset_list = asset_list
-
     asset_list["Estimated Number of Floors"] = asset_list.apply(
         lambda x: estimate_number_of_floors(property_type=x["Property Type"]) if not pd.isnull(
             x["Property Type"]) else None, axis=1
diff --git a/recommendations/recommendation_utils.py b/recommendations/recommendation_utils.py
index 00da6107..602684cf 100644
--- a/recommendations/recommendation_utils.py
+++ b/recommendations/recommendation_utils.py
@@ -205,7 +205,7 @@ def get_wall_u_value(
 
         mapped_value = wall_uvalues_df[
             wall_uvalues_df["Wall_type"] == mapped_description
-        ][age_band].values[0]
+            ][age_band].values[0]
 
         if pd.isnull(mapped_value) and "Park home" in mapped_description:
             # We don't know enough in this case so we default to 0
@@ -428,6 +428,9 @@ def estimate_number_of_floors(property_type):
     Using the property type, we estimate the number of floors in the property
     """
 
+    if property_type is None:
+        return None
+
     if property_type == "House":
         number_of_floors = 2
     elif property_type in ["Flat", "Bungalow"]:
@@ -560,7 +563,7 @@ def get_floor_u_value(
         insulation_lookup = s11[
             s11["Age_band"].str.contains(age_band) & s11["Floor_construction"]
             == floor_type
-        ]
+            ]
         if insulation_lookup.empty:
             insulation_thickness = 0
         else: