Add council house

pipeline/transform/join_epc_pp.py

@@ -37,6 +37,7 @@ def main():
             "NUMBER_HABITABLE_ROOMS",
             "FLOOR_HEIGHT",
             "CONSTRUCTION_AGE_BAND",
+            "TENURE",
         )
         .filter(pl.col("epc_address").is_not_null())
         .with_columns(
@@ -52,6 +53,7 @@ def main():
         epc_base.sort("INSPECTION_DATE", descending=True)
         .group_by("epc_address", "POSTCODE")
         .first()
+        .drop("TENURE")
     )
 
     # Events fork: detect renovation events between consecutive certificates
@@ -124,11 +126,29 @@ def main():
     print(f"Renovation events: {events.height} properties with events")
     print(event_counts)
 
-    # Left-join events back onto dedup EPC
+    # Social tenure fork: flag properties that were ever social housing
+    social_tenure = (
+        epc_base.filter(
+            pl.col("TENURE").str.to_lowercase().str.contains("social")
+        )
+        .select("epc_address", "POSTCODE")
+        .unique()
+        .with_columns(pl.lit("Yes").alias("was_council_house"))
+        .collect()
+    )
+    print(f"Former council houses (EPC social tenure): {social_tenure.height}")
+
+    # Left-join events and social tenure back onto dedup EPC
     epc = epc.join(
         events.lazy(),
         on=["epc_address", "POSTCODE"],
         how="left",
+    ).join(
+        social_tenure.lazy(),
+        on=["epc_address", "POSTCODE"],
+        how="left",
+    ).with_columns(
+        pl.col("was_council_house").fill_null("No"),
     )
 
     print("EPC dataset")