temporary script built

.devcontainer/asset_list/devcontainer.json

@@ -22,7 +22,8 @@
         "jgclark.vscode-todo-highlight",
         "corentinartaud.pdfpreview",
         "ms-python.vscode-python-envs",
-        "ms-python.black-formatter"
+        "ms-python.black-formatter",
+        "GrapeCity.gc-excelviewer"
       ],
       "settings": {
         "files.defaultWorkspace": "/workspaces/model",

.devcontainer/backend/devcontainer.json

@@ -22,7 +22,8 @@
         "corentinartaud.pdfpreview",
         "ms-python.vscode-python-envs",
         "ms-python.black-formatter",
-        "waderyan.gitblame"
+        "waderyan.gitblame",
+        "GrapeCity.gc-excelviewer"
       ],
       "settings": {
         "files.defaultWorkspace": "/workspaces/model",

asset_list/app.py

@@ -70,23 +70,23 @@ def app():
     """
 
     data_folder = "/workspaces/model/asset_list/"
-    data_filename = "assets.xlsx"
-    sheet_name = "Sheet1"
-    postcode_column = "Postcode"
-    address1_column = "junte found address"
+    data_filename = "manchester.xlsx"
+    sheet_name = "PW0099 - Property List"
+    postcode_column = "post Code"
+    address1_column = "address"
     address1_method = None
     fulladdress_column = None
-    address_cols_to_concat = ["junte found address"]
+    address_cols_to_concat = ["address"]
     missing_postcodes_method = None
     landlord_year_built = None
-    landlord_os_uprn = "juntes uprn"
+    landlord_os_uprn = None
     landlord_property_type = None
     landlord_built_form = None
     landlord_wall_construction = None
     landlord_roof_construction = None
     landlord_heating_system = None
     landlord_existing_pv = None
-    landlord_property_id = "landlordid"
+    landlord_property_id = "UHTprop Ref"
     landlord_sap = None
     outcomes_filename = None
     outcomes_sheetname = None

backend/address2UPRN/main.py

@@ -302,7 +302,11 @@ def get_uprn_candidates(
 
 
 def get_uprn(
-    user_inputed_address: str, postcode: str, return_address=False, return_EPC=False
+    user_inputed_address: str,
+    postcode: str,
+    return_address=False,
+    return_EPC=False,
+    return_score=True,
 ):
     """
     Return uprn (str)
@@ -335,6 +339,7 @@ def get_uprn(
     address = top_rank_df["address"].values[0]
     lexiscore = float(top_rank_df["lexiscore"].values[0])
     epc = top_rank_df["current-energy-rating"].values[0]
+    score = float(top_rank_df["lexiscore"].values[0])
 
     # logger.info(f"Address found to be: {address}, with lexiscore {lexiscore}")
     # Safe to return the agreed UPRN
@@ -347,7 +352,15 @@ def get_uprn(
         if return_EPC is False:
             return found_uprn, address
         else:
-            return found_uprn, address, epc
+            if return_score is False:
+                return found_uprn, address, epc
+            else:
+                return (
+                    found_uprn,
+                    address,
+                    epc,
+                    score,
+                )
     return found_uprn
 
 

backend/address2UPRN/script.py

@@ -5,7 +5,7 @@ from backend.address2UPRN.main import get_uprn
 # Enable tqdm for pandas
 tqdm.pandas()
 
-file_name = "brentwood.xlsx"
+file_name = "forhousing.xlsx"
 
 df = pd.read_excel(file_name)
 
@@ -13,17 +13,27 @@ df = pd.read_excel(file_name)
 def extract_uprn(row):
     user_input = "Address"
     postcode = "Postcode"
-    result = get_uprn(row[user_input], row[postcode], return_address=True)
+    result = get_uprn(
+        row[user_input],
+        row[postcode],
+        return_address=True,
+        return_EPC=True,
+        return_score=True,
+    )
 
     if result is None:
-        return pd.Series([None, None])
+        return pd.Series([None, None, None, None])
 
-    uprn, found_address = result
-    return pd.Series([uprn, found_address])
+    uprn, found_address, epc, score = result
+    return pd.Series([uprn, found_address, epc, score])
 
 
-df[["juntes uprn", "junte found address", "junte found epc"]] = df.progress_apply(
-    extract_uprn, axis=1
+df[["juntes uprn", "junte found address", "junte found epc", "junte score"]] = (
+    df.progress_apply(extract_uprn, axis=1)
 )
 
 df.to_excel(f"{file_name}_outputs.xlsx", index=False)
+
+# TODO: add lexiscore
+# TODO: run it
+# TODO: give it to danny

sfr/principal_pitch/2_export_data.py

@@ -28,14 +28,16 @@ from sqlalchemy import func
 
 # PORTFOLIO_ID = 206
 # SCENARIOS = [389]
-PORTFOLIO_ID = 506
+PORTFOLIO_ID = 544
 SCENARIOS = [
-    987,
+    1027,
 ]
 scenario_names = {
-    987: "EPC C",
+    1027: "EPC C",
 }
 
+project_name = "manchester"
+
 
 def get_data(portfolio_id, scenario_ids):
     session = sessionmaker(bind=db_engine)()
@@ -329,6 +331,6 @@ for scenario_id in SCENARIOS:
     df[df["predicted_post_works_sap"] == ""]
 
     # Create excel to store to
-    filename = f"{scenario_names[scenario_id]} - 20250113 final.xlsx"
+    filename = f"{scenario_names[scenario_id]} - {project_name}.xlsx"
     with pd.ExcelWriter(filename) as writer:
         df.to_excel(writer, sheet_name="properties", index=False)