Finished GLA proposal

backend/Property.py

@@ -1204,7 +1204,7 @@ class Property:
             return False
 
         suitable_house = self.data["property-type"] == "House" and self.data["built-form"] in [
-            "Detached", "Semi-Detached",
+            "Detached", "Semi-Detached", "End-Terrace",
         ]
 
         suitable_bungalow = self.data["property-type"] == "Bungalow" and self.data["built-form"] in [

backend/app/plan/router.py

@@ -543,7 +543,11 @@ async def trigger_plan(body: PlanTriggerRequest):
         representative_recommendations = {}
         for p in tqdm(input_properties):
             recommender = Recommendations(
-                property_instance=p, materials=materials, exclusions=body.exclusions, inclusions=body.inclusions
+                property_instance=p,
+                materials=materials,
+                exclusions=body.exclusions,
+                inclusions=body.inclusions,
+                default_u_values=body.default_u_values
             )
             property_recommendations, property_representative_recommendations = recommender.recommend()
 

backend/app/plan/schemas.py

@@ -89,6 +89,9 @@ class PlanTriggerRequest(BaseModel):
     # if False, allows optimisation to be switched off
     optimise: Optional[bool] = True
 
+    # If True, uses default u-values for models
+    default_u_values: Optional[bool] = True
+
     _allowed_goals = {"Increasing EPC"}
 
     _allowed_housing_types = {"Social", "Private"}

backend/ml_models/Valuation.py

@@ -103,6 +103,8 @@ class PropertyValuation:
         # Vander Elliot Intrusive surveys
         12103116: 1_537_000,
         12103117: 1_404_000,
+        # GLA Proposal
+        100020606627: 409_000
     }
 
     # We base our valuation uplifts on a number of sources

etl/customers/gla/example_model_outputs.py

@@ -0,0 +1,38 @@
+import pandas as pd
+from utils.s3 import save_csv_to_s3
+
+asset_list = [
+    {
+        "address": "4, King Henrys Drive",
+        "postcode": "CR0 0PA"
+    },
+]
+portfolio_id = 110
+user_id = 8
+
+asset_list = pd.DataFrame(asset_list)
+
+filename = f"{user_id}/{portfolio_id}/asset_list.csv"
+save_csv_to_s3(
+    dataframe=asset_list,
+    bucket_name="retrofit-plan-inputs-dev",
+    file_name=filename
+)
+
+body1 = {
+    "portfolio_id": str(portfolio_id),
+    "housing_type": "Private",
+    "goal": "Increasing EPC",
+    "goal_value": "A",
+    "trigger_file_path": filename,
+    "already_installed_file_path": "",
+    "patches_file_path": "",
+    "non_invasive_recommendations_file_path": "",
+    "inclusions": [
+        "cavity_wall_insulation", "loft_insulation", "air_source_heat_pump", "solar_pv"
+    ],
+    "budget": None,
+    "scenario_name": "Whole House",
+    "multi_plan": False,
+}
+print(body1)

etl/customers/gla/proposal_investigation.py

@@ -76,13 +76,20 @@ ownership.prepare_for_matching()
 # Step 4: Match EPC data to ownership data
 ownership.match()
 
-from utils.s3 import save_excel_to_s3
+from utils.s3 import save_excel_to_s3, read_excel_from_s3
 
 # Save the data to S3
-save_excel_to_s3(
-    df=ownership.matched_addresses,
+# save_excel_to_s3(
+#     df=ownership.matched_addresses,
+#     bucket_name=ownership.bucket,
+#     file_key=ownership.matched_addresses_pre_filter_filepath
+# )
+
+# Read in matches
+matches = read_excel_from_s3(
     bucket_name=ownership.bucket,
-    file_key=ownership.matched_addresses_pre_filter_filepath
+    file_key="ownership/gla-proposal/2024-10-10 19:02:34.131365/matched_addresses_pre_filter.xlsx",
+    header_row=0
 )
 
 # We have the matches, which we now need to match to the postcodes
@@ -95,6 +102,7 @@ matches = matches[~matches["TENURE"].isin(
      "Not defined - use in the case of a new dwelling for which the intended tenure in not known. It is not to be "
      "used for an existing dwelling", "NO DATA!"])
 ]
+matches["is_prs"] = matches["TENURE"].isin(["rental (private)", "Rented (private)"])
 # Look at the EPC ratings
 epc_ratings = matches.groupby(["CURRENT_ENERGY_RATING"]).size().reset_index()
 epc_ratings.columns = ["EPC Rating", "Count"]
@@ -103,6 +111,8 @@ epc_ratings["Percentage"] = epc_ratings["Count"] / epc_ratings["Count"].sum() *
 # Take properties that are below an EPC C rating, as defined by the guidance and remove any new builds
 matches = matches[matches["CURRENT_ENERGY_RATING"].isin(["D", "E", "F", "G"])]
 # 11,694 properties
+matches["epc_postcode"].nunique()
+# 6899
 
 owners_count = matches.groupby(['Proprietor Name (1)', 'Company Registration No. (1)']).size().reset_index()
 owners_count.columns = ['Owner', 'Owner Registration #', 'Count']
@@ -111,7 +121,26 @@ owners_count["Percentage"] = owners_count["Count"] / owners_count["Count"].sum()
 
 # Take an example postal region
 matches = matches.sort_values("epc_postcode", ascending=True)
-example = matches[matches["epc_postcode"].str.startswith("BR1 ")].copy()
+# BR1, BR5
+example = matches[matches["epc_postcode"].str.startswith("CR0 ")].copy()
+example = example[example["TENURE"].isin(["rental (private)", "Rented (private)"])]
+
+pd.set_option('display.max_rows', 500)
+pd.set_option('display.max_columns', 500)
+pd.set_option('display.width', 1000)
+example[
+    ["epc_address", "epc_postcode", "CURRENT_ENERGY_RATING", "CURRENT_ENERGY_EFFICIENCY", "Proprietor Name (1)",
+     "Company Registration No. (1)"]
+].head(4)
+
+ownership.epc_data["UPRN"] = ownership.epc_data["UPRN"].astype(int)
+example = example.merge(
+    ownership.epc_data[["UPRN", "BUILT_FORM", "PROPERTY_TYPE", "WALLS_DESCRIPTION", "ROOF_DESCRIPTION"]],
+    on="UPRN",
+    how="left"
+)
+z = example[example["CURRENT_ENERGY_RATING"] == "E"]
+z = z[z["TENURE"].isin(["rental (private)", "Rented (private)"])]
 
 companies_house_api_key = "1d9c2877-3271-4642-80ed-a6170971653f"