created triggering backend script and handling find epc errors

backend/scripts/retrigger_backend.py

@@ -0,0 +1,74 @@
+import csv
+import ast
+import re
+import json
+import boto3
+from backend.app.db.models.tasks import SourceEnum
+from backend.app.db.functions.tasks.Tasks import TasksInterface
+
+SQS_QUEUE_URL = "https://sqs.eu-west-2.amazonaws.com/337213553626/model-engine-queue"
+file_path = "/Users/khalimconn-kowlessar/Downloads/assessment-model-log-export-2026-04-21T19-57-35.csv"
+
+payloads = []
+
+
+def clean_js_object(js_str):
+    # Extract object after "Triggering plan with body:"
+    match = re.search(r"Triggering plan with body:\s*(\{.*\})", js_str, re.DOTALL)
+    if not match:
+        return None
+
+    obj = match.group(1)
+
+    # Convert JS → Python
+    obj = re.sub(r"(\w+):", r'"\1":', obj)  # quote keys
+    obj = obj.replace("true", "True")
+    obj = obj.replace("false", "False")
+    obj = obj.replace("null", "None")
+
+    return obj
+
+
+with open(file_path, newline='', encoding='utf-8') as csvfile:
+    reader = csv.DictReader(csvfile)
+
+    for row in reader:
+        message = row.get("message", "")
+
+        if "Triggering plan with body:" in message:
+            cleaned = clean_js_object(message)
+            if cleaned:
+                try:
+                    payload = ast.literal_eval(cleaned)
+                    payloads.append(payload)
+                except Exception as e:
+                    print("Failed to parse:", e)
+
+# Print ready-to-copy output
+print("payloads = [")
+for p in payloads:
+    print(f"    {p},")
+print("]")
+
+# For this, we don't retrigger portfolio 685 since that was internal
+payloads_to_retrigger = [x for x in payloads if x["portfolio_id"] != "685"]
+
+sqs_client = boto3.client("sqs")
+
+# Re-trigger:
+for payload in payloads_to_retrigger:
+    task_id, subtask_id = TasksInterface.create_task(
+        task_source="backend/plan/router.py:trigger_plan_entrypoint",
+        service="plan_engine",
+        inputs=payload,
+        task_only=False,
+        source=SourceEnum.PORTFOLIO,
+        source_id=str(payload["portfolio_id"]),
+    )
+    payload["task_id"] = str(task_id)
+    payload["subtask_id"] = str(subtask_id)
+    message_body = json.dumps(payload)
+    response = sqs_client.send_message(
+        QueueUrl=SQS_QUEUE_URL, MessageBody=message_body
+    )
+    print(f"SQS message sent. Message ID: {response.get('MessageId')}")

etl/find_my_epc/RetrieveFindMyEpc.py

@@ -784,6 +784,7 @@ class RetrieveFindMyEpc:
             "Install cavity wall insulation": ["cavity_wall_insulation"],
             "Install solar water heating": ["solar_water_heating"],
             'Install photovoltaics, 25% of roof area': ["solar_pv"],
+            "Internal and cavity wall insulation": ["internal_wall_insulation"],
         }
 
         survey = True
@@ -794,7 +795,7 @@ class RetrieveFindMyEpc:
 
         formatted_recommendations = []
         for rec in recommendations:
-            mapped = measure_map[rec["measure"]]
+            mapped = measure_map.get(rec["measure"], [])
             for measure in mapped:
                 if measure == "cavity_wall_insulation" and "solid brick" in self.walls[0].lower():
                     measure = "extension_cavity_wall_insulation"

etl/webscrape/Zoopla.py

@@ -164,16 +164,16 @@ def parse_price(p):
 
 if __name__ == "__main__":
     asset_list = pd.read_excel(
-        "/Users/khalimconn-kowlessar/Documents/hestia/Customers/Peabody/Nov 2025 Consulting "
-        "Project/modelling_sample.xlsx",
-        sheet_name="Standardised Asset List"
+        "/Users/khalimconn-kowlessar/Downloads/Book.xlsx",
+        sheet_name="PFH"
     )
 
-    asset_list = asset_list[~pd.isnull(asset_list["epc_os_uprn"])]
-    asset_list = asset_list.drop_duplicates("epc_os_uprn")
-    asset_list["epc_os_uprn"] = asset_list["epc_os_uprn"].astype(int).astype(str)
+    asset_list = asset_list[~pd.isnull(asset_list["UPRN"])]
+    asset_list = asset_list.drop_duplicates("UPRN")
+    asset_list = asset_list[~asset_list["UPRN"].isin(["Check address"])]
+    asset_list["UPRN"] = asset_list["UPRN"].astype(int).astype(str)
 
-    uprns = asset_list["epc_os_uprn"].tolist()
+    uprns = asset_list["UPRN"].tolist()
     urls = [f"https://www.zoopla.co.uk/property/uprn/{uprn}/" for uprn in uprns]
 
     with Pool(processes=2) as pool:
@@ -188,14 +188,14 @@ if __name__ == "__main__":
     df.to_csv("zoopla_estimates.csv", index=False)
 
     merged = asset_list.merge(
-        df[["uprn", "valuation"]],
-        left_on="epc_os_uprn",
+        df,
+        left_on="UPRN",
         right_on="uprn",
         how="left"
     )
 
     merged.to_excel(
-        "20251029 AL Portfolio - Standardised - with valuations.xlsx",
+        "BH - with enhanced property data",
         index=False
     )