try

pipeline/transform/test_join_epc_pp.py

@@ -378,7 +378,10 @@ def test_run_new_build_keeps_early_first_transfer_when_sub_min_price(tmp_path: P
     price_paid_path = tmp_path / "price-paid.parquet"
     pl.DataFrame(
         {
-            "price": [30_000, 300_000],
+            # 5_000 is below MIN_PRICE (10_000) — a nominal/junk transfer that
+            # must still anchor the construction year but stay out of the price
+            # aggregations.
+            "price": [5_000, 300_000],
             "date_of_transfer": [date(2015, 2, 3), date(2022, 2, 3)],
             "property_type": ["T", "T"],
             "postcode": ["AA1 1AA", "AA1 1AA"],
@@ -408,6 +411,48 @@ def test_run_new_build_keeps_early_first_transfer_when_sub_min_price(tmp_path: P
     assert df.get_column("historical_prices").list.len().to_list() == [1]
 
 
+def test_run_keeps_sale_above_lowered_min_price(tmp_path: Path):
+    # A genuine cheap sale of 30_000 sits between the OLD floor (50k) and the
+    # NEW floor (10k): it must now be RETAINED in the price aggregations. This
+    # pins the 50k->10k change — it fails on the pre-fix 50k floor (where 30k was
+    # excluded, giving historical_prices length 1 / latest_price 250_000).
+    zip_path = tmp_path / "domestic-csv.zip"
+    with zipfile.ZipFile(zip_path, "w", compression=zipfile.ZIP_DEFLATED) as archive:
+        csv_buffer = io.StringIO()
+        writer = csv.DictWriter(csv_buffer, fieldnames=EPC_SOURCE_COLUMNS)
+        writer.writeheader()
+        writer.writerow(_row())
+        archive.writestr("certificates-2024.csv", csv_buffer.getvalue())
+
+    price_paid_path = tmp_path / "price-paid.parquet"
+    pl.DataFrame(
+        {
+            "price": [250_000, 30_000],
+            "date_of_transfer": [date(2018, 2, 3), date(2022, 2, 3)],
+            "property_type": ["T", "T"],
+            "postcode": ["AA1 1AA", "AA1 1AA"],
+            "paon": ["1", "1"],
+            "saon": [None, None],
+            "street": ["Example Street", "Example Street"],
+            "locality": [None, None],
+            "town_city": ["Exampletown", "Exampletown"],
+            "duration": ["F", "F"],
+            "old_new": ["N", "N"],
+            "ppd_category": ["A", "A"],
+        }
+    ).write_parquet(price_paid_path)
+
+    output_path = tmp_path / "epc-pp.parquet"
+    _run(zip_path, price_paid_path, output_path, tmp_path)
+
+    df = pl.read_parquet(output_path)
+
+    assert df.height == 1
+    # Both sales now survive the 10k floor; the 30_000 (2022) is the most recent.
+    assert df.get_column("historical_prices").list.len().to_list() == [2]
+    assert df.get_column("latest_price").to_list() == [30_000]
+
+
 def test_epc_band_to_year_uses_midpoint_and_clamps():
     import polars as pl