corrected property exclusions

etl/ownership/Ownership.py

@@ -1038,7 +1038,7 @@ class Ownership:
 
         return asset_list
 
-    def create_final_outputs(self, portfolio_timestamp, exclusion_uprns=None):
+    def create_final_outputs(self, portfolio_timestamp, storage_date, exclusion_uprns=None):
         """
         Given the completed outputs of the matching process, this function creates the final outputs, after matching
         valuation data, and creates a "working" directory, which is our current view of the sfr portfolio. This means
@@ -1051,7 +1051,7 @@ class Ownership:
         exclusion_uprns = [] if exclusion_uprns is None else exclusion_uprns
 
         # Step 1: Read in the valuations data
-        valuatio_ns = read_excel_from_s3(
+        valuations = read_excel_from_s3(
             bucket_name=self.bucket,
             file_key=f"ownership/{self.project_name}/sfr property valuations.xlsx",
             header_row=0
@@ -1087,15 +1087,40 @@ class Ownership:
 
         # We make some final cuts based on UPRNs that at a later stage are found to be odd
         if portfolio_properties["UPRN"].isin(exclusion_uprns).sum():
+            raise Exception("Implement me!")
             # Identify who the owners are for thes uprns
-            owners = portfolio_properties[portfolio_properties["UPRN"].isin(exclusion_uprns)].groupby(
-                "Company Registration No. (1)"
-            )["UPRN"].nunique().reset_index().rename(
-                columns={"UPRN": "number_of_properties_to_exclude"}
-            )
+            # owners = portfolio_properties[portfolio_properties["UPRN"].isin(exclusion_uprns)].groupby(
+            #     "Company Registration No. (1)"
+            # )["UPRN"].nunique().reset_index().rename(
+            #     columns={"UPRN": "number_of_properties_to_exclude"}
+            # )
+            #
+            # min_owners_threshold = portfolio_owners["total_number_of_properties"].min()
+            #
+            # portfolio_owners = portfolio_owners.merge(
+            #     owners, how="left", on="Company Registration No. (1)", suffixes=("", "_excluded")
+            # )
 
-            min_owners_threshold = portfolio_owners["total_number_of_properties"].min()
+        # Step 2: Merge in the valuations data
+        portfolio_properties = portfolio_properties.merge(
+            valuations, how="left", on="UPRN"
+        )
 
-            portfolio_owners = portfolio_owners.merge(
-                owners, how="left", on="Company Registration No. (1)", suffixes=("", "_excluded")
-            )
+        # Step 3: Store the final outputs
+        save_excel_to_s3(
+            df=portfolio_owners,
+            bucket_name=self.bucket,
+            file_key=f"ownership/{self.project_name}/current/{storage_date}/portfolio_owners.xlsx",
+        )
+
+        save_excel_to_s3(
+            df=portfolio_properties,
+            bucket_name=self.bucket,
+            file_key=f"ownership/{self.project_name}/current/{storage_date}/portfolio_properties.xlsx",
+        )
+
+        save_excel_to_s3(
+            df=portfolio_epc_data,
+            bucket_name=self.bucket,
+            file_key=f"ownership/{self.project_name}/current/{storage_date}/portfolio_epc_data.xlsx",
+        )

etl/ownership/config.py

@@ -3,10 +3,10 @@ OWNERS_WHO_CANT_SELL = [
     # Al Rayan - they're the senior lender, not able to sell
     "4483430",
     # Ultrabarn - they're unwilling to sell and will sort any retrofits themselves
-    "2794851"
+    "2794851",
     # Mountview - Anna spoke with someone from Mounview - they acquire tenancies and sell them as soon as they become
     # vacant. They have no immediate opportunities but we may come back and remove this
-    "328090"
+    "328090",
 ]
 
 EXCLUDED_UPRNS = [

etl/ownership/projects/midlands_portfolio/app.py

@@ -1,4 +1,5 @@
-import pandas as pd
+import datetime
+
 from sqlalchemy.orm import sessionmaker
 from backend.app.db.connection import db_engine
 from backend.app.db.models.portfolio import Portfolio, PortfolioUsers
@@ -170,6 +171,13 @@ def app():
     # missed.to_csv("missed_valuations.csv")
 
     # We now need a distinct step to prepare final outputs
-    portfolio_timestamp = "2024-08-20 18:53:08.326351"
+    portfolio_timestamp = "2024-08-20 19:28:18.260205"
 
     exclusion_uprns = EXCLUDED_UPRNS
+
+    # Create a date in the yyyy-mm-dd format to store the data against
+    storage_date = datetime.datetime.now().strftime("%Y-%m-%d")
+
+    ownership_instance.create_final_outputs(
+        portfolio_timestamp=portfolio_timestamp, storage_date=storage_date, exclusion_uprns=EXCLUDED_UPRNS
+    )