started work on peabody

asset_list/utils.py

@@ -2,7 +2,6 @@ import time
 import random
 import pandas as pd
 
-from adhoc.investigation import newest_epc
 from backend.SearchEpc import SearchEpc
 from etl.find_my_epc.RetrieveFindMyEpc import RetrieveFindMyEpc
 from tqdm import tqdm

backend/app/config.py

@@ -3,7 +3,6 @@ from pydantic_settings import BaseSettings
 from typing import Optional
 
 
-
 class Settings(BaseSettings):
     API_KEY: str
     API_KEY_NAME: str = "X-API-KEY"
@@ -43,7 +42,8 @@ class Settings(BaseSettings):
     AWS_DEFAULT_REGION: Optional[str] = None
 
     class Config:
-        env_file = "backend.env"
+        env_file = "backend/.env"
+
 
 @lru_cache()
 def get_settings():

backend/app/db/connection.py

@@ -14,6 +14,7 @@ db_string = connection_string.format(
 
 db_engine = create_engine(db_string, pool_size=5, max_overflow=5)
 
+
 def get_db_session():
     if db_engine is None:
         raise RuntimeError("Database is not configured. Set DATABASE_URL in environment variables.")

backend/app/plan/utils.py

@@ -64,7 +64,7 @@ def extract_property_request_data(
         x for x in already_installed if
         (x["address"] == config["address"]) and (x["postcode"] == config["postcode"])
     ), [])
-
+    
     # Because we have some non-invasive recommendations that match on address and postcode, but not UPRN
     # we need to check existence of uprn
     has_uprn = "uprn" in non_invasive_recommendations[0] if non_invasive_recommendations else False

backend/engine/engine.py

@@ -392,6 +392,26 @@ def parse_heating_system(config):
     return None
 
 
+def check_duplicate_uprns(plan_input):
+    """
+    Simple function to check if the input data contains duplicated UPRNS.
+    If there are duplicates, an exception will be rasied
+    :return:
+    """
+    # Check for duplicate UPRNS
+    input_uprns = [x.get("uprn") for x in plan_input if "uprn" in x and x.get("uprn")]
+
+    if input_uprns:
+        # Check for dupes
+        if len(input_uprns) != len(set(input_uprns)):
+            # Find the duplicate UPRNs
+            duplicates = set([x for x in input_uprns if input_uprns.count(x) > 1])
+            # de-dupe input_uprns
+            raise ValueError(f"Duplicate UPRNs in the input data: {duplicates}")
+
+    return True
+
+
 async def model_engine(body: PlanTriggerRequest):
     logger.info("Model Engine triggered with body: %s", json.loads(body.model_dump_json()))
 
@@ -480,16 +500,8 @@ async def model_engine(body: PlanTriggerRequest):
         if body.index_start is not None and body.index_end is not None:
             plan_input = plan_input[body.index_start:body.index_end]
 
-        # Check for duplicate UPRNS
-        input_uprns = [x.get("uprn") for x in plan_input if "uprn" in x and x.get("uprn")]
-
-        if input_uprns:
-            # Check for dupes
-            if len(input_uprns) != len(set(input_uprns)):
-                # Find the duplicate UPRNs
-                duplicates = set([x for x in input_uprns if input_uprns.count(x) > 1])
-                # de-dupe input_uprns
-                raise ValueError(f"Duplicate UPRNs in the input data: {duplicates}")
+        # Confirm no duplicate UPRNS
+        check_duplicate_uprns(plan_input)
 
         # If we have patches or overrides, we should read them in here
         patches, already_installed, non_invasive_recommendations, valuation_data = get_request_property_data(body)
@@ -528,9 +540,7 @@ async def model_engine(body: PlanTriggerRequest):
             if (body.event_type == "remote_assessment") and config.get("property_type") == "Flat":
                 # We're running a remote assessment for a flat - we go and grab the associated
                 # UPRNS for other units in the same building
-                associated_uprns = get_associated_uprns(
-                    session, postcode=config["postcode"], uprn=uprn
-                )
+                associated_uprns = get_associated_uprns(session, postcode=config["postcode"], uprn=uprn)
 
             epc_searcher = SearchEpc(
                 address1=address1,
@@ -1140,6 +1150,7 @@ async def model_engine(body: PlanTriggerRequest):
                     )
                     property_value_increase_ranges[p.id] = valuations
 
+                    # TODO - this is not right, especially if the existing run failed
                     if p.is_new:
                         property_details_epc = p.get_property_details_epc(
                             portfolio_id=body.portfolio_id, rating_lookup=rating_lookup,

etl/customers/peabody/Nov 2025 Consulting Project/data_prep.py

@@ -77,6 +77,14 @@ archetypes = sustainability_data[
      "Floor Area Band"]
 ].drop_duplicates()
 
+# Potential reductions:
+# 1) Split roof insulation into > 100mm loft and <= 100mm loft
+# 2) Group all of the glazed together (e.g. double glazed, secondary glazed, triple glazed)
+# 3) Group up boiler efficiency A-C, D - F, G? or someting like this
+# 4) Group up main fuel into gas, electric, oil, other?
+# 5) Wall Construction - group up Sandstone and Granite into one category
+# 6) Reduce or remove floor construction
+
 # Maps the property types to the format recognised by the EPC api
 property_type_map = {}
 # Maps the build form to the format recognised by the OS api

etl/find_my_epc/RetrieveFindMyEpc.py

@@ -398,6 +398,7 @@ class RetrieveFindMyEpc:
                 extracted_address_cleaned = (
                     extracted_address.replace(",", "").replace(" ", "").lower()
                 )
+
                 if not extracted_address_cleaned.startswith(self.address_cleaned):
                     continue