More

pipeline/transform/price_estimate.py

@@ -36,9 +36,10 @@ def main():
     df = pl.read_parquet(args.input)
     print(f"  {len(df):,} rows, {len(df.columns)} columns")
 
-    # Drop existing estimated price column if re-running
-    if "Estimated current price" in df.columns:
-        df = df.drop("Estimated current price")
+    # Drop existing estimated columns if re-running
+    for col in ["Estimated current price", "Est. price per sqm"]:
+        if col in df.columns:
+            df = df.drop(col)
 
     # Derive helper columns for the join
     has_price = (
@@ -126,6 +127,14 @@ def main():
         .alias("Estimated current price"),
     )
 
+    # Derive estimated price per sqm where both estimated price and floor area exist
+    df = df.with_columns(
+        (pl.col("Estimated current price") / pl.col("Total floor area (sqm)"))
+        .round(0)
+        .cast(pl.Int32)
+        .alias("Est. price per sqm"),
+    )
+
     n_adjusted = df.filter(
         has_price & pl.col("_log_index_sale").is_not_null()
     ).height