feat(dbt): fact_ks4_la_averages from DfE's LA rows (H2)

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

pipeline/transform/models/marts/_marts_schema.yml

@@ -279,11 +279,24 @@ models:
         tests: [not_null, unique]
 
   - name: fact_ks4_national_averages
-    description: Computed national KS4 averages (means across state schools in our dataset — not official DfE figures) — one row per academic year
+    description: Official DfE KS4 national headline averages (England, all state-funded schools, all pupils) — one row per academic year
     columns:
       - name: year
         tests: [not_null, unique]
 
+  - name: fact_ks4_la_averages
+    description: Official DfE KS4 local-authority averages (all state-funded schools, all pupils) — one row per academic year and LA; la_code is the GIAS LA code
+    columns:
+      - name: year
+        tests: [not_null]
+      - name: la_code
+        tests: [not_null]
+      - name: la_name
+        tests: [not_null]
+    tests:
+      - unique:
+          column_name: "year || '-' || la_code"
+
   - name: fact_deprivation
     description: IDACI deprivation index — one row per URN
     columns:

pipeline/transform/models/marts/fact_ks4_la_averages.sql

@@ -0,0 +1,22 @@
+{{ config(materialized='table') }}
+
+-- Mart: OFFICIAL DfE KS4 local-authority averages — one row per academic year
+-- and LA (all state-funded schools, all pupils), from the same EES data set
+-- as fact_ks4_national_averages. Feeds "vs LA avg" on search rows and map
+-- cards, replacing a mean the API took over every school in the LA,
+-- independent and special included (audit H2). la_code is the GIAS LA code.
+
+select
+    year,
+    la_code,
+    la_name,
+    attainment_8_score,
+    progress_8_score,
+    english_maths_standard_pass_pct,
+    english_maths_strong_pass_pct,
+    ebacc_entry_pct,
+    ebacc_standard_pass_pct,
+    ebacc_strong_pass_pct,
+    ebacc_avg_score
+from {{ ref('stg_ees_ks4_la') }}
+order by year, la_code

pipeline/transform/models/staging/_stg_sources.yml

@@ -79,6 +79,9 @@ sources:
       - name: ees_ks4_national
         description: Official KS4 national headline averages from DfE EES data catalogue — one row per academic year
 
+      - name: ees_ks4_la
+        description: Official KS4 local-authority averages (all state-funded schools) from the same DfE EES data set as ees_ks4_national — one row per academic year and LA
+
       # Phonics: no school-level data on EES (only national/LA level)
 
       - name: fbit_finance

pipeline/transform/models/staging/stg_ees_ks4_la.sql

@@ -0,0 +1,21 @@
+-- Staging model: official DfE KS4 local-authority averages — one row per
+-- academic year and LA (all state-funded schools, all pupils). Same EES data
+-- set as stg_ees_ks4_national. la_code is the GIAS LA code
+-- (dim_location.local_authority_code). Suppressed values ('z', 'x') are
+-- coerced to NULL by safe_numeric.
+
+select
+    cast(trim(time_period) as integer)                        as year,
+    cast(trim(old_la_code) as integer)                        as la_code,
+    trim(la_name)                                             as la_name,
+    {{ safe_numeric('attainment_8_score') }}                  as attainment_8_score,
+    {{ safe_numeric('progress_8_score') }}                    as progress_8_score,
+    {{ safe_numeric('english_maths_standard_pass_pct') }}     as english_maths_standard_pass_pct,
+    {{ safe_numeric('english_maths_strong_pass_pct') }}       as english_maths_strong_pass_pct,
+    {{ safe_numeric('ebacc_entry_pct') }}                     as ebacc_entry_pct,
+    {{ safe_numeric('ebacc_standard_pass_pct') }}             as ebacc_standard_pass_pct,
+    {{ safe_numeric('ebacc_strong_pass_pct') }}               as ebacc_strong_pass_pct,
+    {{ safe_numeric('ebacc_avg_score') }}                     as ebacc_avg_score
+from {{ source('raw', 'ees_ks4_la') }}
+where time_period ~ '^[0-9]+$'
+  and old_la_code ~ '^[0-9]+$'

pipeline/transform/models/staging/stg_ees_ks4_la.yml

@@ -0,0 +1,15 @@
+version: 2
+
+unit_tests:
+  - name: stg_ees_ks4_la_casts_codes_years_and_measures
+    description: DfE's LA rows, keyed by the GIAS LA code. Suppressed values ('z') become null.
+    model: stg_ees_ks4_la
+    given:
+      - input: source('raw', 'ees_ks4_la')
+        rows:
+          - {time_period: '202425', old_la_code: '207', new_la_code: 'E09000020', la_name: 'Kensington and Chelsea', attainment_8_score: '54.5', progress_8_score: 'z', english_maths_standard_pass_pct: '77'}
+          - {time_period: '202324', old_la_code: '207', new_la_code: 'E09000020', la_name: 'Kensington and Chelsea', attainment_8_score: '54.5', progress_8_score: '0.29', english_maths_standard_pass_pct: '76'}
+    expect:
+      rows:
+        - {year: 202425, la_code: 207, la_name: 'Kensington and Chelsea', attainment_8_score: 54.5, progress_8_score: null, english_maths_standard_pass_pct: 77}
+        - {year: 202324, la_code: 207, la_name: 'Kensington and Chelsea', attainment_8_score: 54.5, progress_8_score: 0.29, english_maths_standard_pass_pct: 76}