.

pipeline/transform/test_join_epc_pp.py

@@ -315,7 +315,7 @@ def test_run_tenure_history_tracks_rent_owner_transitions(tmp_path: Path):
 
 def test_run_tenure_history_empty_when_always_owner_occupied(tmp_path: Path):
     # A property only ever observed as owner-occupied has no tenure change worth
-    # surfacing — the timeline column is null (no events), not a noisy baseline.
+    # surfacing: the timeline column is null (no events), not a noisy baseline.
     zip_path = tmp_path / "domestic-csv.zip"
     _write_epc_zip(
         zip_path,
@@ -339,6 +339,37 @@ def test_run_tenure_history_empty_when_always_owner_occupied(tmp_path: Path):
     assert df.get_column("tenure_history").to_list() == [None]
 
 
+def test_run_latest_tenure_status_reflects_most_recent_certificate(tmp_path: Path):
+    # Two certificates for one dwelling: an older social-rented cert and a newer
+    # owner-occupied one. The published latest_tenure_status must carry the
+    # LATEST certificate's normalized tenure ("Owner-occupied"), while
+    # was_council_house stays "Yes" because the dwelling was social at some
+    # point. This also confirms latest_tenure_status reaches the epc_pp parquet.
+    zip_path = tmp_path / "domestic-csv.zip"
+    _write_epc_zip(
+        zip_path,
+        [
+            _row(inspection_date="2016-04-01", tenure="Rented (social)"),
+            _row(inspection_date="2024-04-01", tenure="owner-occupied"),
+        ],
+    )
+
+    price_paid_path = tmp_path / "price-paid.parquet"
+    _price_paid_frame(prices=[250_000], dates=[date(2024, 2, 3)]).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
+    assert df.select("latest_tenure_status", "was_council_house").to_dicts() == [
+        {"latest_tenure_status": "Owner-occupied", "was_council_house": "Yes"}
+    ]
+
+
 def test_run_dedup_prefers_valid_dated_cert_over_garbled_date(tmp_path: Path):
     # Two certificates for the same property. The cert with the garbled,
     # unparseable inspection_date must NOT be chosen as "latest": a string sort
@@ -565,7 +596,7 @@ 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(
         {
-            # 5_000 is below MIN_PRICE (10_000) — a nominal/junk transfer that
+            # 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],
@@ -603,7 +634,7 @@ def test_run_caps_band_year_at_first_transfer_year(tmp_path: Path):
     # lands AFTER its first Land Registry sale (1998). A dwelling cannot have
     # been built after it was first sold, so the published build year must be
     # capped at the first transfer year (1998), not the later band estimate.
-    # It stays flagged as an estimate (approximate=1) — it is still EPC-derived.
+    # It stays flagged as an estimate (approximate=1). It is still EPC-derived.
     zip_path = tmp_path / "domestic-csv.zip"
     _write_epc_zip(
         zip_path, [_row(construction_age_band="England and Wales: 2003 onwards")]
@@ -627,7 +658,7 @@ def test_run_caps_band_year_at_first_transfer_year(tmp_path: Path):
 
 def test_run_keeps_band_year_when_earlier_than_first_transfer(tmp_path: Path):
     # The common case: the EPC band (1950-1966 -> 1958) predates the first
-    # recorded sale (2020). The cap must NOT fire — the band estimate stands.
+    # recorded sale (2020). The cap must NOT fire. The band estimate stands.
     zip_path = tmp_path / "domestic-csv.zip"
     _write_epc_zip(zip_path)
 
@@ -649,7 +680,7 @@ def test_run_keeps_band_year_when_earlier_than_first_transfer(tmp_path: Path):
 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
+    # 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:
@@ -748,8 +779,8 @@ def test_run_collapses_duplicate_transactions(tmp_path: Path):
     # The duplicated 250_000 sale collapses to one entry; two distinct sales.
     assert df.get_column("historical_prices").to_list() == [
         [
-            {"year": 2020, "month": 2, "price": 200_000},
-            {"year": 2024, "month": 2, "price": 250_000},
+            {"year": 2020, "month": 2, "price": 200_000, "is_new": False},
+            {"year": 2024, "month": 2, "price": 250_000, "is_new": False},
         ]
     ]
     assert df.get_column("latest_price").to_list() == [250_000]
@@ -777,7 +808,7 @@ def test_run_excludes_implausible_price_jump_but_keeps_property(tmp_path: Path):
     assert df.height == 1
     assert df.get_column("latest_price").to_list() == [140_000]
     assert df.get_column("historical_prices").to_list() == [
-        [{"year": 2016, "month": 6, "price": 140_000}]
+        [{"year": 2016, "month": 6, "price": 140_000, "is_new": False}]
     ]