lgtm

pipeline/transform/price_estimation/utils.py

@@ -16,6 +16,26 @@ LATEST_COMPLETE_YEAR = CURRENT_YEAR - 1
 _today = date.today()
 CURRENT_FRAC_YEAR = _today.year + (_today.month - 1) / 12
 
+# The two columns price estimation contributes to properties.parquet, kept here
+# so both the producer (estimate) and the joiner (join_price_estimates) agree.
+ESTIMATE_COLUMNS = ["Estimated current price", "Est. price per sqm"]
+
+# Natural join key from estimates back onto properties: postcode plus the
+# coalesced register/EPC address. This is unique and non-null on the deduped
+# dwelling universe (see property_base._dedupe_collapsed_properties), so it maps
+# estimates 1:1 onto properties regardless of row order — estimates are computed
+# from a separate price_inputs.parquet, so a positional key would not line up.
+JOIN_ADDRESS = "_join_address"
+JOIN_KEYS = ["Postcode", JOIN_ADDRESS]
+
+
+def join_address_expr() -> pl.Expr:
+    """The coalesced address half of the natural key, aliased to JOIN_ADDRESS."""
+    return pl.coalesce("Address per Property Register", "Address per EPC").alias(
+        JOIN_ADDRESS
+    )
+
+
 # Cap on log(index_ratio) to prevent wild estimates from thin sectors
 MAX_LOG_ADJUSTMENT = 3.0  # ~20x max price change
 TERRACE_TYPES = [