From 806213ce3c381b88e98a3f67df7394a82706e097 Mon Sep 17 00:00:00 2001
From: Andras Schmelczer <andras@schmelczer.dev>
Date: Sun, 1 Feb 2026 11:05:46 +0000
Subject: [PATCH] Add actual construction age

---
 pipeline/transform/join_epc_pp.py | 32 +++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/pipeline/transform/join_epc_pp.py b/pipeline/transform/join_epc_pp.py
index aa42b4e..630813a 100644
--- a/pipeline/transform/join_epc_pp.py
+++ b/pipeline/transform/join_epc_pp.py
@@ -4,6 +4,8 @@ from pathlib import Path
 from ..utils import fuzzy_join_on_postcode
 
 
+MIN_FLOOR_AREA_M2 = 10
+
 pl.Config.set_tbl_cols(-1)
 
 
@@ -69,6 +71,7 @@ def main():
             "locality",
             "town_city",
             pl.col("duration").replace(duration_map),
+            "old_new",
         )
         .filter(pl.col("pp_property_type") != "Other")
         .with_columns(
@@ -89,6 +92,8 @@ def main():
             pl.col("duration").last(),
             pl.col("price").last().alias("latest_price"),
             pl.col("date_of_transfer").last(),
+            pl.col("date_of_transfer").first().alias("first_transfer_date"),
+            pl.col("old_new").first(),
         )
     ).filter(pl.col("pp_address").is_not_null())
 
@@ -116,6 +121,33 @@ def main():
     print(f"Matched: {matched.height} ({100 * matched.height / total:.1f}%)")
     print(f"Unmatched: {total - matched.height}")
 
+    matched = matched.filter(pl.col("TOTAL_FLOOR_AREA") >= MIN_FLOOR_AREA_M2)
+
+    # For new-builds (old_new == "Y"), use the first transaction date year as
+    # the exact construction date; otherwise fall back to the EPC age band.
+    epc_band_year = (
+        pl.col("CONSTRUCTION_AGE_BAND")
+        .str.replace("England and Wales: ", "")
+        .str.replace(" onwards", "")
+        .str.extract(r"(\d{4})", 1)
+        .cast(pl.UInt16, strict=False)
+    )
+    transfer_year = pl.col("first_transfer_date").dt.year().cast(pl.UInt16, strict=False)
+    is_new_build = pl.col("old_new") == "Y"
+
+    matched = matched.with_columns(
+        pl.when(is_new_build & transfer_year.is_not_null())
+        .then(transfer_year)
+        .otherwise(epc_band_year)
+        .alias("CONSTRUCTION_AGE_BAND"),
+        pl.when(is_new_build & transfer_year.is_not_null())
+        .then(pl.lit(0, dtype=pl.UInt8))
+        .when(epc_band_year.is_not_null())
+        .then(pl.lit(1, dtype=pl.UInt8))
+        .otherwise(pl.lit(None, dtype=pl.UInt8))
+        .alias("is_construction_date_approximate"),
+    ).drop("old_new", "first_transfer_date")
+
     matched = matched.rename({col: col.lower() for col in joined.columns})
 
     print(matched.head())