Fmt

pipeline/transform/price_estimation/knn.py

@@ -43,48 +43,39 @@ def build_knn_pool(
     """
     print("Building kNN pool...")
     lf = pl.scan_parquet(source) if isinstance(source, Path) else source
-    query = (
-        lf
-        .select(
-            "Postcode",
-            "Property type",
-            "lat",
-            "lon",
-            "Total floor area (sqm)",
-            "Last known price",
-            "Date of last transaction",
-        )
-        .filter(
-            pl.col("lat").is_not_null(),
-            pl.col("lon").is_not_null(),
-            pl.col("Total floor area (sqm)").is_not_null(),
-            pl.col("Total floor area (sqm)") > 0,
-            pl.col("Last known price").is_not_null(),
-            pl.col("Last known price") > 0,
-            pl.col("Postcode").is_not_null(),
-            pl.col("Date of last transaction").is_not_null(),
-        )
+    query = lf.select(
+        "Postcode",
+        "Property type",
+        "lat",
+        "lon",
+        "Total floor area (sqm)",
+        "Last known price",
+        "Date of last transaction",
+    ).filter(
+        pl.col("lat").is_not_null(),
+        pl.col("lon").is_not_null(),
+        pl.col("Total floor area (sqm)").is_not_null(),
+        pl.col("Total floor area (sqm)") > 0,
+        pl.col("Last known price").is_not_null(),
+        pl.col("Last known price") > 0,
+        pl.col("Postcode").is_not_null(),
+        pl.col("Date of last transaction").is_not_null(),
     )
     if max_sale_year is not None:
         query = query.filter(
             pl.col("Date of last transaction").dt.year() < max_sale_year
         )
 
-    pool = (
-        query.with_columns(
-            sector_expr(),
-            type_group_expr(),
-            (
-                pl.col("Date of last transaction").dt.year().cast(pl.Float64)
-                + (
-                    pl.col("Date of last transaction").dt.month().cast(pl.Float64)
-                    - 1.0
-                )
-                / 12.0
-            ).alias("_sale_fy"),
-            pl.lit(ref_frac_year).alias("_ref_fy"),
-        ).collect()
-    )
+    pool = query.with_columns(
+        sector_expr(),
+        type_group_expr(),
+        (
+            pl.col("Date of last transaction").dt.year().cast(pl.Float64)
+            + (pl.col("Date of last transaction").dt.month().cast(pl.Float64) - 1.0)
+            / 12.0
+        ).alias("_sale_fy"),
+        pl.lit(ref_frac_year).alias("_ref_fy"),
+    ).collect()
     pool = pool.filter(pl.col("type_group").is_not_null())
     print(f"  {len(pool):,} pool properties with lat/lon, floor area, price")