Merge pull request 'feat(pipeline): one current Ofsted status per school (C1/M1, part 1 of 2)' (#183) from fix/ofsted-current-status-pipeline into main

Reviewed-on: #183

pipeline/transform/models/intermediate/int_ofsted_latest.sql

@@ -1,18 +1,91 @@
--- Intermediate model: Latest Ofsted inspection per URN
--- Picks the most recent inspection for each school
+-- Intermediate model: the current Ofsted status per URN
+-- One row per school: its latest visit (report card, graded or ungraded
+-- inspection) and the overall grade still in force, if any. A grade is dated
+-- by the inspection that awarded or confirmed it, never by a later visit.
+-- Rule and examples: docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md
 
-with ranked as (
+with inspections as (
     select
         *,
+        -- The newest of the three inspections, read from the dates. (Report
+        -- cards began in Nov 2025, after the last legacy inspections, so today
+        -- a report card is always the latest; nothing below relies on that.)
+        greatest(rc_inspection_date, graded_inspection_date, ungraded_inspection_date)
+            as latest_visit_date
+    from {{ ref('stg_ofsted_inspections') }}
+),
+
+ranked as (
+    select
+        *,
+        -- Monthly loads can leave several rows per school. The newest visit
+        -- wins; the tie-breaks keep the choice deterministic.
         row_number() over (
             partition by urn
-            order by inspection_date desc
+            order by latest_visit_date desc,
+                     rc_inspection_date desc nulls last,
+                     graded_inspection_date desc nulls last,
+                     ungraded_inspection_date desc nulls last
         ) as rn
-    from {{ ref('stg_ofsted_inspections') }}
+    from inspections
+),
+
+latest as (
+    select
+        *,
+        -- Same-day ties resolve report card, then graded, then ungraded.
+        case
+            when rc_inspection_date = latest_visit_date then 'report_card'
+            when graded_inspection_date = latest_visit_date then 'graded'
+            else 'ungraded'
+        end as latest_visit_kind
+    from ranked
+    where rn = 1
+),
+
+graded as (
+    select
+        *,
+        -- The grade still in force. A report card replaced overall grades, so
+        -- none survives it. Otherwise: a graded inspection's own overall grade
+        -- (1-4; "Not judged" and the sentinel 9 are no grade); else an
+        -- ungraded visit's "School remains X"; else, after an ungraded visit
+        -- that names no grade, the graded inspection's grade.
+        case
+            when rc_inspection_date is not null
+                then null
+            when latest_visit_kind = 'graded' and overall_effectiveness between 1 and 4
+                then 'graded_latest'
+            when latest_visit_kind = 'ungraded' and ungraded_grade is not null
+                then 'confirmed'
+            when latest_visit_kind = 'ungraded' and overall_effectiveness between 1 and 4
+                then 'graded_earlier'
+        end as grade_case
+    from latest
 )
 
 select
     urn,
+    latest_visit_date,
+    latest_visit_kind,
+    case when latest_visit_kind = 'ungraded' then ungraded_outcome end as latest_visit_outcome,
+    case grade_case
+        when 'confirmed' then ungraded_grade
+        when 'graded_latest' then overall_effectiveness
+        when 'graded_earlier' then overall_effectiveness
+    end as current_grade,
+    case grade_case
+        when 'confirmed' then ungraded_inspection_date
+        when 'graded_latest' then graded_inspection_date
+        when 'graded_earlier' then graded_inspection_date
+    end as current_grade_date,
+    case grade_case
+        when 'confirmed' then 'confirmed'
+        when 'graded_latest' then 'graded'
+        when 'graded_earlier' then 'graded'
+    end as current_grade_basis,
+    graded_inspection_date,
+    ungraded_inspection_date,
     inspection_date,
     inspection_type,
     framework,
@@ -36,5 +109,4 @@ select
     rc_sixth_form,
     rc_inspection_date,
     report_url
-from ranked
-where rn = 1
+from graded

pipeline/transform/models/intermediate/int_ofsted_latest.yml

@@ -0,0 +1,113 @@
+version: 2
+
+unit_tests:
+  - name: graded_not_judged_has_no_grade
+    description: Rabbsfarm (102408). The 2025 inspection gave no overall grade, so the 2020 "remains Good" is not carried forward (audit C1).
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 102408, graded_inspection_date: '2025-06-17', ungraded_inspection_date: '2020-02-06', overall_effectiveness: null, ungraded_grade: 2, ungraded_outcome: 'School remains Good'}
+    expect:
+      rows:
+        - {urn: 102408, latest_visit_date: '2025-06-17', latest_visit_kind: graded, latest_visit_outcome: null, current_grade: null, current_grade_date: null, current_grade_basis: null}
+
+  - name: graded_with_overall_grade
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 1, graded_inspection_date: '2019-06-01', overall_effectiveness: 2}
+    expect:
+      rows:
+        - {urn: 1, latest_visit_date: '2019-06-01', latest_visit_kind: graded, current_grade: 2, current_grade_date: '2019-06-01', current_grade_basis: graded}
+
+  - name: ungraded_remains_good_confirms_the_grade
+    description: Robins Lane (104762). Graded Good 2020, "School remains Good" July 2024 — Good, dated by the confirming visit.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 104762, graded_inspection_date: '2020-01-07', ungraded_inspection_date: '2024-07-18', overall_effectiveness: 2, ungraded_grade: 2, ungraded_outcome: 'School remains Good'}
+    expect:
+      rows:
+        - {urn: 104762, latest_visit_date: '2024-07-18', latest_visit_kind: ungraded, latest_visit_outcome: 'School remains Good', current_grade: 2, current_grade_date: '2024-07-18', current_grade_basis: confirmed}
+
+  - name: post_2024_ungraded_keeps_graded_grade_with_its_own_date
+    description: Washwood Heath (139888). Graded Good 2020, "Standards maintained" May 2025 — Good, dated 2020; latest visit May 2025 (audit M1).
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 139888, graded_inspection_date: '2020-03-03', ungraded_inspection_date: '2025-05-21', overall_effectiveness: 2, ungraded_grade: null, ungraded_outcome: 'Standards maintained'}
+    expect:
+      rows:
+        - {urn: 139888, latest_visit_date: '2025-05-21', latest_visit_kind: ungraded, latest_visit_outcome: 'Standards maintained', current_grade: 2, current_grade_date: '2020-03-03', current_grade_basis: graded}
+
+  - name: ungraded_only_standards_maintained
+    description: Oakgrove (136454). Only an ungraded visit, outcome names no grade.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 136454, ungraded_inspection_date: '2024-11-13', ungraded_grade: null, ungraded_outcome: 'Standards maintained'}
+    expect:
+      rows:
+        - {urn: 136454, latest_visit_date: '2024-11-13', latest_visit_kind: ungraded, latest_visit_outcome: 'Standards maintained', current_grade: null, current_grade_date: null, current_grade_basis: null}
+
+  - name: report_card_wins
+    description: The Willink School (110048). A report card is the latest visit and no legacy grade stays in force.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 110048, ungraded_inspection_date: '2023-10-05', ungraded_grade: 2, ungraded_outcome: 'School remains Good', rc_inspection_date: '2026-05-06', rc_inclusion: 3}
+    expect:
+      rows:
+        - {urn: 110048, latest_visit_date: '2026-05-06', latest_visit_kind: report_card, latest_visit_outcome: null, current_grade: null, current_grade_date: null, current_grade_basis: null}
+
+  - name: duplicate_rows_newer_report_card_wins
+    description: Monthly loads can leave an older row beside a newer one for the same graded date; the row with the report card must win (audit H3).
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 138186, graded_inspection_date: '2023-06-13', overall_effectiveness: 3}
+          - {urn: 138186, graded_inspection_date: '2023-06-13', overall_effectiveness: 3, rc_inspection_date: '2026-06-02', rc_inclusion: 3}
+    expect:
+      rows:
+        - {urn: 138186, latest_visit_date: '2026-06-02', latest_visit_kind: report_card, current_grade: null}
+
+  - name: same_day_graded_wins
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 2, graded_inspection_date: '2024-03-01', ungraded_inspection_date: '2024-03-01', overall_effectiveness: 1, ungraded_grade: 2, ungraded_outcome: 'School remains Good'}
+    expect:
+      rows:
+        - {urn: 2, latest_visit_kind: graded, current_grade: 1, current_grade_basis: graded}
+
+  - name: overall_sentinel_is_not_a_grade
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 3, graded_inspection_date: '2018-05-01', overall_effectiveness: 9}
+    expect:
+      rows:
+        - {urn: 3, latest_visit_kind: graded, current_grade: null}
+
+  - name: newer_legacy_visit_after_a_report_card
+    description: >
+      Not in Ofsted's data today (0 of 2,451 report-card schools in the 31 Aug
+      2026 MI), but the latest visit is read from the dates, not assumed. The
+      report card still leaves no legacy grade in force.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 4, ungraded_inspection_date: '2026-03-02', ungraded_grade: 2, ungraded_outcome: 'School remains Good', rc_inspection_date: '2025-12-01', rc_inclusion: 3}
+    expect:
+      rows:
+        - {urn: 4, latest_visit_date: '2026-03-02', latest_visit_kind: ungraded, latest_visit_outcome: 'School remains Good', current_grade: null, current_grade_date: null, current_grade_basis: null}

pipeline/transform/models/marts/_marts_schema.yml

@@ -125,6 +125,30 @@ models:
       - name: inspection_date
         tests: [not_null]
 
+  - name: fact_ofsted_latest
+    description: >
+      Current Ofsted status, one row per URN: the latest visit and the overall
+      grade still in force. See int_ofsted_latest for the rule.
+    columns:
+      - name: urn
+        tests: [not_null, unique]
+      - name: latest_visit_date
+        tests: [not_null]
+      - name: latest_visit_kind
+        tests:
+          - not_null
+          - accepted_values:
+              values: ['report_card', 'graded', 'ungraded']
+      - name: current_grade
+        tests:
+          - accepted_values:
+              values: [1, 2, 3, 4]
+              quote: false
+      - name: current_grade_basis
+        tests:
+          - accepted_values:
+              values: ['graded', 'confirmed']
+
   - name: fact_pupil_characteristics
     description: Pupil demographics — one row per URN per year
     columns:

pipeline/transform/models/marts/fact_ofsted_latest.sql

@@ -0,0 +1,37 @@
+-- Mart: current Ofsted status — one row per URN
+-- The backend reads this instead of choosing the latest row of
+-- fact_ofsted_inspection itself. The rule lives in int_ofsted_latest.
+
+select
+    urn,
+    latest_visit_date,
+    latest_visit_kind,
+    latest_visit_outcome,
+    current_grade,
+    current_grade_date,
+    current_grade_basis,
+    graded_inspection_date,
+    ungraded_inspection_date,
+    rc_inspection_date,
+    inspection_type,
+    framework,
+    overall_effectiveness,
+    quality_of_education,
+    behaviour_attitudes,
+    personal_development,
+    leadership_management,
+    early_years_provision,
+    sixth_form_provision,
+    ungraded_outcome,
+    ungraded_grade,
+    rc_safeguarding_met,
+    rc_inclusion,
+    rc_curriculum_teaching,
+    rc_achievement,
+    rc_attendance_behaviour,
+    rc_personal_development,
+    rc_leadership_governance,
+    rc_early_years,
+    rc_sixth_form,
+    report_url
+from {{ ref('int_ofsted_latest') }}

pipeline/transform/models/staging/stg_ofsted_inspections.sql

@@ -1,5 +1,10 @@
 -- Staging model: Ofsted inspection records
--- Handles both OEIF (pre-Nov 2025) and Report Card (post-Nov 2025) frameworks
+-- Handles both OEIF (pre-Nov 2025) and Report Card (post-Nov 2025) frameworks.
+--
+-- Ofsted's MI carries up to three inspections per school: the latest graded
+-- one, the latest ungraded one and the latest report card. Their dates stay
+-- separate here so int_ofsted_latest can tell which came last and which one a
+-- grade belongs to (docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md).
 
 with source as (
     select * from {{ source('raw', 'ofsted_inspections') }}
@@ -8,17 +13,12 @@ with source as (
 renamed as (
     select
         cast(urn as integer)                                                    as urn,
-        -- Inspection event date: the graded inspection when present, otherwise the
-        -- ungraded (Section 8) inspection so schools with only an ungraded
-        -- inspection are still retained.
-        coalesce(
-            to_date(nullif(trim(inspection_date), 'NULL'), 'DD/MM/YYYY'),
-            to_date(nullif(trim(ungraded_inspection_date), 'NULL'), 'DD/MM/YYYY')
-        )                                                                       as inspection_date,
+        to_date(nullif(trim(inspection_date), 'NULL'), 'DD/MM/YYYY')            as graded_inspection_date,
+        to_date(nullif(trim(ungraded_inspection_date), 'NULL'), 'DD/MM/YYYY')   as ungraded_inspection_date,
         inspection_type,
         event_type_grouping                                                     as framework,
 
-        -- OEIF grades (1-4 scale)
+        -- OEIF grades (1-4 scale; 9 = not applicable)
         {{ safe_numeric('overall_effectiveness') }}::integer                    as overall_effectiveness,
         {{ safe_numeric('quality_of_education') }}::integer                     as quality_of_education,
         {{ safe_numeric('behaviour_and_attitudes') }}::integer                  as behaviour_attitudes,
@@ -27,9 +27,9 @@ renamed as (
         {{ safe_numeric('early_years_provision') }}::integer                    as early_years_provision,
         {{ safe_numeric('sixth_form_provision') }}::integer                     as sixth_form_provision,
 
-        -- Ungraded (Section 8) inspection outcome — free text, plus a grade
-        -- parsed from it (1/2/null) used as a last-resort fallback for schools
-        -- with no graded overall effectiveness.
+        -- Ungraded (Section 8) inspection outcome — free text, plus the grade
+        -- it confirms ("School remains Good" → 2); null for outcomes that
+        -- name no grade.
         nullif(trim(ungraded_outcome), 'NULL')                                  as ungraded_outcome,
         {{ parse_ungraded_outcome('ungraded_outcome') }}::integer               as ungraded_grade,
 
@@ -50,31 +50,36 @@ renamed as (
         {{ parse_report_card_grade('rc_sixth_form') }}::integer           as rc_sixth_form,
 
         -- Start date of the latest FULL inspection (the report-card
-        -- inspection in the renewed framework). Guarded in the final select:
-        -- only kept when the row actually carries report-card grades, because
-        -- in legacy-format files this column is the legacy inspection date.
+        -- inspection in the renewed framework). Only kept when the row
+        -- carries report-card grades, because in legacy-format files this
+        -- column is the legacy inspection date.
         to_date(nullif(trim(rc_inspection_date), 'NULL'), 'DD/MM/YYYY')   as rc_inspection_date_raw,
 
         nullif(trim(report_url), 'NULL')                                  as report_url
     from source
     where urn is not null
-      and (
-          nullif(trim(inspection_date), 'NULL') is not null
-          or nullif(trim(ungraded_inspection_date), 'NULL') is not null
-      )
+),
+
+dated as (
+    select
+        *,
+        case
+            when rc_safeguarding_met is not null
+              or rc_inclusion is not null
+              or rc_curriculum_teaching is not null
+              or rc_achievement is not null
+              or rc_attendance_behaviour is not null
+              or rc_personal_development is not null
+              or rc_leadership_governance is not null
+            then rc_inspection_date_raw
+        end as rc_inspection_date
+    from renamed
 )
 
 select
     *,
-    case
-        when rc_safeguarding_met is not null
-          or rc_inclusion is not null
-          or rc_curriculum_teaching is not null
-          or rc_achievement is not null
-          or rc_attendance_behaviour is not null
-          or rc_personal_development is not null
-          or rc_leadership_governance is not null
-        then rc_inspection_date_raw
-    end as rc_inspection_date
-from renamed
-where inspection_date is not null
+    -- For readers that predate the separate dates (fact_ofsted_inspection and
+    -- the backend until it reads fact_ofsted_latest). Never null below.
+    coalesce(graded_inspection_date, ungraded_inspection_date, rc_inspection_date) as inspection_date
+from dated
+where coalesce(graded_inspection_date, ungraded_inspection_date, rc_inspection_date) is not null

pipeline/transform/models/staging/stg_ofsted_inspections.yml

@@ -0,0 +1,25 @@
+version: 2
+
+unit_tests:
+  - name: stg_ofsted_keeps_the_three_dates_apart
+    description: The graded and ungraded dates must stay separate so the latest visit can be found.
+    model: stg_ofsted_inspections
+    given:
+      - input: source('raw', 'ofsted_inspections')
+        rows:
+          - {urn: 102408, inspection_date: '17/06/2025', ungraded_inspection_date: '06/02/2020', overall_effectiveness: 'Not judged', ungraded_outcome: 'School remains Good', rc_inspection_date: '17/06/2025', rc_inclusion: 'NULL'}
+    expect:
+      rows:
+        - {urn: 102408, graded_inspection_date: '2025-06-17', ungraded_inspection_date: '2020-02-06', rc_inspection_date: null, inspection_date: '2025-06-17', ungraded_grade: 2}
+
+  - name: stg_ofsted_keeps_report_card_only_rows
+    description: A school whose only inspection is a report card used to be dropped (audit H3).
+    model: stg_ofsted_inspections
+    given:
+      - input: source('raw', 'ofsted_inspections')
+        rows:
+          - {urn: 149612, inspection_date: 'NULL', ungraded_inspection_date: 'NULL', rc_inspection_date: '10/02/2026', rc_inclusion: 'Expected standard', rc_safeguarding_met: 'Met'}
+          - {urn: 1, inspection_date: 'NULL', ungraded_inspection_date: 'NULL', rc_inspection_date: 'NULL'}
+    expect:
+      rows:
+        - {urn: 149612, graded_inspection_date: null, ungraded_inspection_date: null, rc_inspection_date: '2026-02-10', inspection_date: '2026-02-10', rc_inclusion: 3}

pipeline/transform/tests/assert_ofsted_current_grade_consistent.sql

@@ -0,0 +1,10 @@
+-- A grade is dated by the inspection that awarded or confirmed it, never
+-- after the latest visit, and has a date and a basis exactly when it exists.
+-- A report card leaves no legacy grade in force.
+
+select urn
+from {{ ref('fact_ofsted_latest') }}
+where current_grade_date > latest_visit_date
+   or (current_grade is null) <> (current_grade_date is null)
+   or (current_grade is null) <> (current_grade_basis is null)
+   or (rc_inspection_date is not null and current_grade is not null)