test(dbt): fail the build when a published year loads empty (C2, H2)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

pipeline/transform/tests/assert_ks2_info_percentages_loaded.sql

@@ -0,0 +1,16 @@
+-- Where a year's KS2 school information loaded (pupil counts present), its
+-- percentages loaded too. DfE's files give a disadvantaged % for 96–97% of
+-- those schools; 2023/24 loaded none because the file writes "34%" (audit
+-- C2). A year without an information file (2022/23) has no pupil counts and
+-- is skipped.
+
+select
+    year,
+    count(total_pupils) as with_pupils,
+    count(*) filter (where total_pupils is not null and disadvantaged_pct is not null)
+        as with_disadvantaged
+from {{ ref('stg_ees_ks2') }}
+group by year
+having count(total_pupils) >= 1000
+   and count(*) filter (where total_pupils is not null and disadvantaged_pct is not null)
+       < 0.9 * count(total_pupils)

pipeline/transform/tests/assert_ks4_la_averages_cover_las.sql

@@ -0,0 +1,13 @@
+-- DfE publishes an average for about 152 LAs a year. Fewer than 145 in the
+-- latest year (or none at all) means the LA filter in tap_uk_ees
+-- (ks4_summary.headline_rows) stopped matching, e.g. after DfE renamed a label.
+
+with latest as (
+    select max(year) as year from {{ ref('fact_ks4_la_averages') }}
+)
+
+select l.year, count(f.la_code) as las
+from latest l
+left join {{ ref('fact_ks4_la_averages') }} f on f.year = l.year
+group by l.year
+having count(f.la_code) < 145

pipeline/transform/tests/assert_ks4_years_have_results.sql

@@ -0,0 +1,12 @@
+-- Every year loaded from EES has an Attainment 8 for at least half its
+-- schools. DfE's files reach 82% each year; 2023/24 loaded at 0% after DfE
+-- re-issued its file under older column names (audit C2). Pre-2019 years come
+-- from stg_legacy_ks4 and are not checked here.
+
+select
+    year,
+    count(*) as schools,
+    count(attainment_8_score) as with_attainment_8
+from {{ ref('stg_ees_ks4') }}
+group by year
+having count(attainment_8_score) < 0.5 * count(*)