feat(detail): replace SATs text tables with cascade bar charts, add admissions bar and history accordion

Redesign the School Details page for better parent comprehension:
- New SatsChart component: horizontal cascade bars with ruler scale and
  national average marker (teal/coral palette matching site theme)
- Admissions section: visual progress bar showing 1st-preference demand
  vs available places, colour-coded by oversubscription status
- Historical data: collapse raw year-by-year table behind a disclosure
  element while keeping the performance line chart always visible
- EAL metric: add national average comparison via DeltaChip (backend now
  includes eal_pct in national averages endpoint)
- New formatWithSuppression utility for null/suppressed data handling

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.gitea/workflows/build-and-push.yml

@@ -12,8 +12,6 @@ env:
   REGISTRY: privaterepo.sitaru.org
   BACKEND_IMAGE_NAME: ${{ gitea.repository }}-backend
   FRONTEND_IMAGE_NAME: ${{ gitea.repository }}-frontend
-  INTEGRATOR_IMAGE_NAME: ${{ gitea.repository }}-integrator
-  KESTRA_INIT_IMAGE_NAME: ${{ gitea.repository }}-kestra-init
   PIPELINE_IMAGE_NAME: ${{ gitea.repository }}-pipeline
 
 jobs:
@@ -112,94 +110,6 @@ jobs:
           # cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ env.FRONTEND_IMAGE_NAME }}:buildcache
           # cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ env.FRONTEND_IMAGE_NAME }}:buildcache,mode=max
 
-  build-integrator:
-    name: Build Integrator
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          buildkitd-config-inline: |
-            [registry."docker.io"]
-              mirrors = ["10.0.1.224:6000"]
-            [registry."10.0.1.224:6000"]
-              http = true
-              insecure = true
-
-      - name: Log in to Gitea Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ gitea.actor }}
-          password: ${{ secrets.REGISTRY_TOKEN }}
-
-      - name: Extract metadata for Integrator Docker image
-        id: meta-integrator
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.INTEGRATOR_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=pr
-            type=sha,prefix=integrator-
-            type=raw,value=latest,enable=${{ gitea.ref == 'refs/heads/main' }}
-
-      - name: Build and push Integrator Docker image
-        uses: docker/build-push-action@v5
-        with:
-          context: ./integrator
-          file: ./integrator/Dockerfile
-          push: ${{ gitea.event_name != 'pull_request' }}
-          tags: ${{ steps.meta-integrator.outputs.tags }}
-          labels: ${{ steps.meta-integrator.outputs.labels }}
-
-  build-kestra-init:
-    name: Build Kestra Init
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          buildkitd-config-inline: |
-            [registry."docker.io"]
-              mirrors = ["10.0.1.224:6000"]
-            [registry."10.0.1.224:6000"]
-              http = true
-              insecure = true
-
-      - name: Log in to Gitea Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ gitea.actor }}
-          password: ${{ secrets.REGISTRY_TOKEN }}
-
-      - name: Extract metadata for Kestra Init Docker image
-        id: meta-kestra-init
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.KESTRA_INIT_IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=pr
-            type=sha,prefix=kestra-init-
-            type=raw,value=latest,enable=${{ gitea.ref == 'refs/heads/main' }}
-
-      - name: Build and push Kestra Init Docker image
-        uses: docker/build-push-action@v5
-        with:
-          context: ./integrator
-          file: ./integrator/Dockerfile.init
-          push: ${{ gitea.event_name != 'pull_request' }}
-          tags: ${{ steps.meta-kestra-init.outputs.tags }}
-          labels: ${{ steps.meta-kestra-init.outputs.labels }}
-
   build-pipeline:
     name: Build Pipeline (Meltano + dbt + Airflow)
     runs-on: ubuntu-latest
@@ -249,7 +159,7 @@ jobs:
   trigger-deployment:
     name: Trigger Portainer Update
     runs-on: ubuntu-latest
-    needs: [build-backend, build-frontend, build-integrator, build-kestra-init, build-pipeline]
+    needs: [build-backend, build-frontend, build-pipeline]
     if: gitea.event_name != 'pull_request'
     steps:
       - name: Trigger Portainer stack update

Dockerfile

@@ -22,13 +22,10 @@ RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy application code
 COPY backend/ ./backend/
-COPY frontend/ ./frontend/
 COPY scripts/ ./scripts/
-COPY data/ ./data/
 
 # Expose the application port
 EXPOSE 80
 
 # Run the application (using module import)
 CMD ["python", "-m", "uvicorn", "backend.app:app", "--host", "0.0.0.0", "--port", "80"]
-

README.md

@@ -26,7 +26,7 @@ The application tracks these Key Stage 2 performance indicators:
 | **Reading Expected %** | Percentage meeting expected standard in reading |
 | **Writing Expected %** | Percentage meeting expected standard in writing |
 | **Maths Expected %** | Percentage meeting expected standard in maths |
-| **RWM Combined %** | Percentage meeting expected standard in all three subjects |
+| **Reading, Writing & Maths Combined %** | Percentage meeting expected standard in all three subjects |
 
 ## Quick Start
 
@@ -131,7 +131,7 @@ If using your own CSV data, ensure it includes these columns (or similar):
 | READPROG | Float | Reading progress score |
 | WRITPROG | Float | Writing progress score |
 | MATPROG | Float | Maths progress score |
-| PTRWM_EXP | Float | % meeting expected standard in RWM |
+| PTRWM_EXP | Float | % meeting expected standard in reading, writing & maths |
 | PTREAD_EXP | Float | % meeting expected standard in reading |
 | PTWRIT_EXP | Float | % meeting expected standard in writing |
 | PTMAT_EXP | Float | % meeting expected standard in maths |

backend/app.py

@@ -1,6 +1,6 @@
 """
 SchoolCompare.co.uk API
-Serves primary school (KS2) performance data for comparing schools.
+Serves primary and secondary school performance data for comparing schools.
 Uses real data from UK Government Compare School Performance downloads.
 """
 
@@ -26,13 +26,91 @@ from .data_loader import (
     load_school_data,
     geocode_single_postcode,
     get_supplementary_data,
+    search_schools_typesense,
 )
 from .data_loader import get_data_info as get_db_info
-from .database import check_and_migrate_if_needed
-from .migration import run_full_migration
 from .schemas import METRIC_DEFINITIONS, RANKING_COLUMNS, SCHOOL_COLUMNS
 from .utils import clean_for_json
 
+# Values to exclude from filter dropdowns (empty strings, non-applicable labels)
+EXCLUDED_FILTER_VALUES = {"", "Not applicable", "Does not apply"}
+
+# Maps user-facing phase filter values to the GIAS PhaseOfEducation values they include.
+# All-through schools appear in both primary and secondary results.
+PHASE_GROUPS: dict[str, set[str]] = {
+    "primary": {"primary", "middle deemed primary", "all-through"},
+    "secondary": {"secondary", "middle deemed secondary", "all-through", "16 plus"},
+    "all-through": {"all-through"},
+}
+
+BASE_URL = "https://schoolcompare.co.uk"
+MAX_SLUG_LENGTH = 60
+
+# In-memory sitemap cache
+_sitemap_xml: str | None = None
+
+
+def _slugify(text: str) -> str:
+    text = text.lower()
+    text = re.sub(r"[^\w\s-]", "", text)
+    text = re.sub(r"\s+", "-", text)
+    text = re.sub(r"-+", "-", text)
+    return text.strip("-")
+
+
+def _school_url(urn: int, school_name: str) -> str:
+    slug = _slugify(school_name)
+    if len(slug) > MAX_SLUG_LENGTH:
+        slug = slug[:MAX_SLUG_LENGTH].rstrip("-")
+    return f"/school/{urn}-{slug}"
+
+
+def build_sitemap() -> str:
+    """Generate sitemap XML from in-memory school data. Returns the XML string."""
+    df = load_school_data()
+
+    static_urls = [
+        (BASE_URL + "/",          "daily",   "1.0"),
+        (BASE_URL + "/rankings",  "weekly",  "0.8"),
+        (BASE_URL + "/compare",   "weekly",  "0.8"),
+    ]
+
+    lines = ['<?xml version="1.0" encoding="UTF-8"?>',
+             '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">']
+
+    for url, freq, priority in static_urls:
+        lines.append(
+            f"  <url><loc>{url}</loc>"
+            f"<changefreq>{freq}</changefreq>"
+            f"<priority>{priority}</priority></url>"
+        )
+
+    if not df.empty and "urn" in df.columns and "school_name" in df.columns:
+        seen = set()
+        for _, row in df[["urn", "school_name"]].drop_duplicates(subset="urn").iterrows():
+            urn = int(row["urn"])
+            name = str(row["school_name"])
+            if urn in seen:
+                continue
+            seen.add(urn)
+            path = _school_url(urn, name)
+            lines.append(
+                f"  <url><loc>{BASE_URL}{path}</loc>"
+                f"<changefreq>monthly</changefreq>"
+                f"<priority>0.6</priority></url>"
+            )
+
+    lines.append("</urlset>")
+    return "\n".join(lines)
+
+
+def clean_filter_values(series: pd.Series) -> list[str]:
+    """Return sorted unique values from a Series, excluding NaN and junk labels."""
+    return sorted(
+        v for v in series.dropna().unique().tolist()
+        if v not in EXCLUDED_FILTER_VALUES
+    )
+
 
 # =============================================================================
 # SECURITY MIDDLEWARE & HELPERS
@@ -138,26 +216,28 @@ def validate_postcode(postcode: Optional[str]) -> Optional[str]:
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """Application lifespan - startup and shutdown events."""
-    # Startup: check schema version and migrate if needed
+    global _sitemap_xml
-    print("Starting up: Checking database schema...")
+    print("Loading school data from marts...")
-    check_and_migrate_if_needed()
-
-    print("Loading school data from database...")
     df = load_school_data()
     if df.empty:
-        print("Warning: No data in database. Check CSV files in data/ folder.")
+        print("Warning: No data in marts. Run the annual EES pipeline to populate KS2 data.")
     else:
         print(f"Data loaded successfully: {len(df)} records.")
+    try:
+        _sitemap_xml = build_sitemap()
+        n = _sitemap_xml.count("<url>")
+        print(f"Sitemap built: {n} URLs.")
+    except Exception as e:
+        print(f"Warning: sitemap build failed on startup: {e}")
 
-    yield  # Application runs here
+    yield
 
-    # Shutdown: cleanup if needed
     print("Shutting down...")
 
 
 app = FastAPI(
     title="SchoolCompare API",
-    description="API for comparing primary school (KS2) performance data - schoolcompare.co.uk",
+    description="API for comparing primary and secondary school performance data - schoolcompare.co.uk",
     version="2.0.0",
     lifespan=lifespan,
     # Disable docs in production for security
@@ -219,21 +299,26 @@ async def get_schools(
         None, description="Filter by local authority", max_length=100
     ),
     school_type: Optional[str] = Query(None, description="Filter by school type", max_length=100),
+    phase: Optional[str] = Query(None, description="Filter by phase: primary, secondary, all-through", max_length=50),
     postcode: Optional[str] = Query(None, description="Search near postcode", max_length=10),
-    radius: float = Query(5.0, ge=0.1, le=50, description="Search radius in miles"),
+    radius: float = Query(5.0, ge=0.1, le=5, description="Search radius in miles"),
     page: int = Query(1, ge=1, le=1000, description="Page number"),
-    page_size: int = Query(None, ge=1, le=100, description="Results per page"),
+    page_size: int = Query(25, ge=1, le=500, description="Results per page"),
+    gender: Optional[str] = Query(None, description="Filter by gender (Mixed/Boys/Girls)", max_length=50),
+    admissions_policy: Optional[str] = Query(None, description="Filter by admissions policy", max_length=100),
+    has_sixth_form: Optional[str] = Query(None, description="Filter by sixth form presence: yes/no", max_length=3),
 ):
     """
-    Get list of unique primary schools with pagination.
+    Get list of schools with pagination.
 
     Returns paginated results with total count for efficient loading.
-    Supports location-based search using postcode.
+    Supports location-based search using postcode and phase filtering.
     """
     # Sanitize inputs
     search = sanitize_search_input(search)
     local_authority = sanitize_search_input(local_authority)
     school_type = sanitize_search_input(school_type)
+    phase = sanitize_search_input(phase)
     postcode = validate_postcode(postcode)
 
     df = load_school_data()
@@ -245,6 +330,11 @@ async def get_schools(
     if page_size is None:
         page_size = settings.default_page_size
 
+    # Schools with no performance data (special schools, PRUs, newly opened, etc.)
+    # have NULL year from the LEFT JOIN — keep them but skip the groupby/trend logic.
+    df_no_perf = df[df["year"].isna()].drop_duplicates(subset=["urn"])
+    df = df[df["year"].notna()]
+
     # Get unique schools (latest year data for each)
     latest_year = df.groupby("urn")["year"].max().reset_index()
     df_latest = df.merge(latest_year, on=["urn", "year"])
@@ -257,26 +347,59 @@ async def get_schools(
         prev_rwm = df_prev[["urn", "rwm_expected_pct"]].rename(
             columns={"rwm_expected_pct": "prev_rwm_expected_pct"}
         )
+        if "attainment_8_score" in df_prev.columns:
+            prev_rwm = prev_rwm.merge(
+                df_prev[["urn", "attainment_8_score"]].rename(
+                    columns={"attainment_8_score": "prev_attainment_8_score"}
+                ),
+                on="urn", how="outer"
+            )
         df_latest = df_latest.merge(prev_rwm, on="urn", how="left")
 
+    # Merge back schools with no performance data
+    df_latest = pd.concat([df_latest, df_no_perf], ignore_index=True)
+
+    # Phase filter — uses PHASE_GROUPS so all-through/middle schools appear
+    # in the correct phase(s) rather than being invisible to both filters.
+    if phase:
+        phase_lower = phase.lower().replace("_", "-")
+        allowed = PHASE_GROUPS.get(phase_lower)
+        if allowed:
+            df_latest = df_latest[df_latest["phase"].str.lower().isin(allowed)]
+
+    # Secondary-specific filters (after phase filter)
+    if gender:
+        df_latest = df_latest[df_latest["gender"].str.lower() == gender.lower()]
+    if admissions_policy:
+        df_latest = df_latest[df_latest["admissions_policy"].str.lower() == admissions_policy.lower()]
+    if has_sixth_form == "yes":
+        df_latest = df_latest[df_latest["age_range"].str.contains("18", na=False)]
+    elif has_sixth_form == "no":
+        df_latest = df_latest[~df_latest["age_range"].str.contains("18", na=False)]
+
     # Include key result metrics for display on cards
     location_cols = ["latitude", "longitude"]
     result_cols = [
+        "phase",
         "year",
         "rwm_expected_pct",
         "rwm_high_pct",
         "prev_rwm_expected_pct",
+        "prev_attainment_8_score",
         "reading_expected_pct",
         "writing_expected_pct",
         "maths_expected_pct",
         "total_pupils",
+        "attainment_8_score",
+        "english_maths_standard_pass_pct",
     ]
     available_cols = [
         c
         for c in SCHOOL_COLUMNS + location_cols + result_cols
         if c in df_latest.columns
     ]
-    schools_df = df_latest[available_cols].drop_duplicates(subset=["urn"])
+    # fact_performance guarantees one row per (urn, year); df_latest has one row per urn.
+    schools_df = df_latest[available_cols]
 
     # Location-based search (uses pre-geocoded data from database)
     search_coords = None
@@ -321,15 +444,19 @@ async def get_schools(
 
     # Apply filters
     if search:
-        search_lower = search.lower()
+        ts_urns = search_schools_typesense(search)
-        mask = (
+        if ts_urns:
-            schools_df["school_name"].str.lower().str.contains(search_lower, na=False)
+            urn_order = {urn: i for i, urn in enumerate(ts_urns)}
-        )
+            schools_df = schools_df[schools_df["urn"].isin(set(ts_urns))].copy()
-        if "address" in schools_df.columns:
+            schools_df["_ts_rank"] = schools_df["urn"].map(urn_order)
-            mask = mask | schools_df["address"].str.lower().str.contains(
+            schools_df = schools_df.sort_values("_ts_rank").drop(columns=["_ts_rank"])
-                search_lower, na=False
+        else:
-            )
+            # Fallback: Typesense unavailable, use substring match
-        schools_df = schools_df[mask]
+            search_lower = search.lower()
+            mask = schools_df["school_name"].str.lower().str.contains(search_lower, na=False)
+            if "address" in schools_df.columns:
+                mask = mask | schools_df["address"].str.lower().str.contains(search_lower, na=False)
+            schools_df = schools_df[mask]
 
     if local_authority:
         schools_df = schools_df[
@@ -341,6 +468,18 @@ async def get_schools(
             schools_df["school_type"].str.lower() == school_type.lower()
         ]
 
+    # Compute result-scoped filter values (before pagination).
+    # Gender and admissions are secondary-only filters — scope them to schools
+    # with KS4 data so they don't appear for purely primary result sets.
+    _sec_mask = schools_df["attainment_8_score"].notna() if "attainment_8_score" in schools_df.columns else pd.Series(False, index=schools_df.index)
+    result_filters = {
+        "local_authorities": clean_filter_values(schools_df["local_authority"]) if "local_authority" in schools_df.columns else [],
+        "school_types": clean_filter_values(schools_df["school_type"]) if "school_type" in schools_df.columns else [],
+        "phases": clean_filter_values(schools_df["phase"]) if "phase" in schools_df.columns else [],
+        "genders": clean_filter_values(schools_df.loc[_sec_mask, "gender"]) if "gender" in schools_df.columns and _sec_mask.any() else [],
+        "admissions_policies": clean_filter_values(schools_df.loc[_sec_mask, "admissions_policy"]) if "admissions_policy" in schools_df.columns and _sec_mask.any() else [],
+    }
+
     # Pagination
     total = len(schools_df)
     start_idx = (page - 1) * page_size
@@ -353,6 +492,7 @@ async def get_schools(
         "page": page,
         "page_size": page_size,
         "total_pages": (total + page_size - 1) // page_size if page_size > 0 else 0,
+        "result_filters": result_filters,
         "location_info": {
             "postcode": postcode,
             "radius": radius * 1.60934,  # Convert miles to km for frontend display
@@ -366,7 +506,7 @@ async def get_schools(
 @app.get("/api/schools/{urn}")
 @limiter.limit(f"{settings.rate_limit_per_minute}/minute")
 async def get_school_details(request: Request, urn: int):
-    """Get detailed KS2 data for a specific primary school across all years."""
+    """Get detailed performance data for a specific school across all years."""
     # Validate URN range (UK school URNs are 6 digits)
     if not (100000 <= urn <= 999999):
         raise HTTPException(status_code=400, detail="Invalid URN format")
@@ -408,11 +548,12 @@ async def get_school_details(request: Request, urn: int):
             "age_range": latest.get("age_range", ""),
             "latitude": latest.get("latitude"),
             "longitude": latest.get("longitude"),
-            "phase": "Primary",
+            "phase": latest.get("phase"),
             # GIAS fields
             "website": latest.get("website"),
             "headteacher_name": latest.get("headteacher_name"),
             "capacity": latest.get("capacity"),
+            "total_pupils": latest.get("gias_total_pupils"),
             "trust_name": latest.get("trust_name"),
             "gender": latest.get("gender"),
         },
@@ -435,7 +576,7 @@ async def compare_schools(
     request: Request,
     urns: str = Query(..., description="Comma-separated URNs", max_length=100)
 ):
-    """Compare multiple primary schools side by side."""
+    """Compare multiple schools side by side."""
     df = load_school_data()
 
     if df.empty:
@@ -468,7 +609,11 @@ async def compare_schools(
                     "urn": urn,
                     "school_name": latest.get("school_name", ""),
                     "local_authority": latest.get("local_authority", ""),
+                    "school_type": latest.get("school_type", ""),
                     "address": latest.get("address", ""),
+                    "phase": latest.get("phase", ""),
+                    "attainment_8_score": float(latest["attainment_8_score"]) if pd.notna(latest.get("attainment_8_score")) else None,
+                    "rwm_expected_pct": float(latest["rwm_expected_pct"]) if pd.notna(latest.get("rwm_expected_pct")) else None,
                 },
                 "yearly_data": clean_for_json(school_data),
             }
@@ -489,10 +634,132 @@ async def get_filter_options(request: Request):
             "years": [],
         }
 
+    # Phases: return values from data, ordered sensibly
+    phases = clean_filter_values(df["phase"]) if "phase" in df.columns else []
+
+    secondary_df = df[df["attainment_8_score"].notna()] if "attainment_8_score" in df.columns else df.iloc[0:0]
+    genders = clean_filter_values(secondary_df["gender"]) if "gender" in secondary_df.columns else []
+    admissions_policies = clean_filter_values(secondary_df["admissions_policy"]) if "admissions_policy" in secondary_df.columns else []
+
     return {
-        "local_authorities": sorted(df["local_authority"].dropna().unique().tolist()),
+        "local_authorities": clean_filter_values(df["local_authority"]) if "local_authority" in df.columns else [],
-        "school_types": sorted(df["school_type"].dropna().unique().tolist()),
+        "school_types": clean_filter_values(df["school_type"]) if "school_type" in df.columns else [],
         "years": sorted(df["year"].dropna().unique().tolist()),
+        "phases": phases,
+        "genders": genders,
+        "admissions_policies": admissions_policies,
+    }
+
+
+@app.get("/api/la-averages")
+@limiter.limit(f"{settings.rate_limit_per_minute}/minute")
+async def get_la_averages(request: Request):
+    """Get per-LA average Attainment 8 score for secondary schools in the latest year."""
+    df = load_school_data()
+    if df.empty:
+        return {"year": 0, "secondary": {"attainment_8_by_la": {}}}
+    latest_year = int(df["year"].max())
+    sec_df = df[(df["year"] == latest_year) & df["attainment_8_score"].notna()]
+    la_avg = sec_df.groupby("local_authority")["attainment_8_score"].mean().round(1).to_dict()
+    return {"year": latest_year, "secondary": {"attainment_8_by_la": la_avg}}
+
+
+@app.get("/api/national-averages")
+@limiter.limit(f"{settings.rate_limit_per_minute}/minute")
+async def get_national_averages(request: Request):
+    """
+    Compute national average for each metric from the latest data year.
+    Returns separate averages for primary (KS2) and secondary (KS4) schools.
+    Values are derived from the loaded DataFrame so they automatically
+    stay current when new data is loaded.
+    """
+    df = load_school_data()
+    if df.empty:
+        return {"primary": {}, "secondary": {}}
+
+    ks2_metrics = [
+        "rwm_expected_pct", "rwm_high_pct",
+        "reading_expected_pct", "writing_expected_pct", "maths_expected_pct",
+        "reading_avg_score", "maths_avg_score", "gps_avg_score",
+        "reading_progress", "writing_progress", "maths_progress",
+        "overall_absence_pct", "persistent_absence_pct",
+        "disadvantaged_gap", "disadvantaged_pct", "sen_support_pct", "eal_pct",
+    ]
+    ks4_metrics = [
+        "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", "gcse_grade_91_pct",
+    ]
+
+    def _means(sub_df, metric_list):
+        out = {}
+        for col in metric_list:
+            if col in sub_df.columns:
+                val = sub_df[col].dropna()
+                if len(val) > 0:
+                    out[col] = round(float(val.mean()), 2)
+        return out
+
+    latest_year = int(df["year"].max())
+    df_latest = df[df["year"] == latest_year]
+
+    # Primary: schools where KS2 data is non-null
+    primary_df = df_latest[df_latest["rwm_expected_pct"].notna()]
+    # Secondary: schools where KS4 data is non-null
+    secondary_df = df_latest[df_latest["attainment_8_score"].notna()]
+
+    latest_primary = _means(primary_df, ks2_metrics)
+    latest_secondary = _means(secondary_df, ks4_metrics)
+
+    # Per-year KS2 primary averages: use official DfE figures from the mart table.
+    # Per-year KS4 secondary averages: computed from our dataset (no DfE dataset yet).
+    from .database import SessionLocal
+    from .models import Ks2NationalAverage
+
+    by_year = []
+    try:
+        db = SessionLocal()
+        nat_rows = db.query(Ks2NationalAverage).order_by(Ks2NationalAverage.year).all()
+        # Build a lookup of computed secondary averages per year as fallback
+        secondary_by_year = {}
+        for yr in sorted(df["year"].dropna().unique()):
+            yr = int(yr)
+            df_yr = df[df["year"] == yr]
+            secondary_by_year[yr] = _means(
+                df_yr[df_yr["attainment_8_score"].notna()], ks4_metrics
+            )
+        # Merge: official KS2 figures + computed KS4 figures per year
+        ks2_years = {r.year for r in nat_rows}
+        all_years = sorted(ks2_years | set(secondary_by_year.keys()))
+        nat_lookup = {r.year: r for r in nat_rows}
+        for yr in all_years:
+            primary_yr: dict = {}
+            if yr in nat_lookup:
+                r = nat_lookup[yr]
+                for col in ks2_metrics:
+                    val = getattr(r, col, None)
+                    if val is not None:
+                        primary_yr[col] = val
+            by_year.append({
+                "year": yr,
+                "primary": primary_yr,
+                "secondary": secondary_by_year.get(yr, {}),
+            })
+    finally:
+        db.close()
+
+    # Update latest_primary with official DfE figure for the latest year if available
+    if by_year:
+        latest_official = next((e["primary"] for e in reversed(by_year) if e["primary"]), None)
+        if latest_official:
+            latest_primary = latest_official
+
+    return {
+        "year": latest_year,
+        "primary": latest_primary,
+        "secondary": latest_secondary,
+        "by_year": by_year,
     }
 
 
@@ -500,7 +767,7 @@ async def get_filter_options(request: Request):
 @limiter.limit(f"{settings.rate_limit_per_minute}/minute")
 async def get_available_metrics(request: Request):
     """
-    Get list of available KS2 performance metrics for primary schools.
+    Get list of available performance metrics for schools.
 
     This is the single source of truth for metric definitions.
     Frontend should consume this to avoid duplication.
@@ -519,7 +786,7 @@ async def get_available_metrics(request: Request):
 @limiter.limit(f"{settings.rate_limit_per_minute}/minute")
 async def get_rankings(
     request: Request,
-    metric: str = Query("rwm_expected_pct", description="KS2 metric to rank by", max_length=50),
+    metric: str = Query("rwm_expected_pct", description="Metric to rank by", max_length=50),
     year: Optional[int] = Query(
         None, description="Specific year (defaults to most recent)", ge=2000, le=2100
     ),
@@ -527,8 +794,11 @@ async def get_rankings(
     local_authority: Optional[str] = Query(
         None, description="Filter by local authority", max_length=100
     ),
+    phase: Optional[str] = Query(
+        None, description="Filter by phase: primary or secondary", max_length=20
+    ),
 ):
-    """Get primary school rankings by a specific KS2 metric."""
+    """Get school rankings by a specific metric."""
     # Sanitize local authority input
     local_authority = sanitize_search_input(local_authority)
 
@@ -556,6 +826,12 @@ async def get_rankings(
     if local_authority:
         df = df[df["local_authority"].str.lower() == local_authority.lower()]
 
+    # Filter by phase
+    if phase == "primary" and "rwm_expected_pct" in df.columns:
+        df = df[df["rwm_expected_pct"].notna()]
+    elif phase == "secondary" and "attainment_8_score" in df.columns:
+        df = df[df["attainment_8_score"].notna()]
+
     # Sort and rank (exclude rows with no data for this metric)
     df = df.dropna(subset=[metric])
     total = len(df)
@@ -585,7 +861,7 @@ async def get_data_info(request: Request):
     if db_info["total_schools"] == 0:
         return {
             "status": "no_data",
-            "message": "No data in database. Run the migration script: python scripts/migrate_csv_to_db.py",
+            "message": "No data in marts. Run the annual EES pipeline to load KS2 data.",
             "data_source": "PostgreSQL",
         }
 
@@ -599,10 +875,10 @@ async def get_data_info(request: Request):
             "data_source": "PostgreSQL",
         }
 
-    years = [int(y) for y in sorted(df["year"].unique())]
+    years = [int(y) for y in sorted(df["year"].dropna().unique())]
     schools_per_year = {
         str(int(k)): int(v)
-        for k, v in df.groupby("year")["urn"].nunique().to_dict().items()
+        for k, v in df.dropna(subset=["year"]).groupby("year")["urn"].nunique().to_dict().items()
     }
     la_counts = {
         str(k): int(v)
@@ -635,56 +911,6 @@ async def reload_data(
     return {"status": "reloaded"}
 
 
-_reimport_status: dict = {"running": False, "done": False, "error": None}
-
-
-@app.post("/api/admin/reimport-ks2")
-@limiter.limit("2/minute")
-async def reimport_ks2(
-    request: Request,
-    geocode: bool = True,
-    _: bool = Depends(verify_admin_api_key)
-):
-    """
-    Start a full KS2 CSV migration in the background and return immediately.
-    Poll GET /api/admin/reimport-ks2/status to check progress.
-    Pass ?geocode=false to skip postcode → lat/lng resolution.
-    Requires X-API-Key header with valid admin API key.
-    """
-    global _reimport_status
-    if _reimport_status["running"]:
-        return {"status": "already_running"}
-
-    _reimport_status = {"running": True, "done": False, "error": None}
-
-    def _run():
-        global _reimport_status
-        try:
-            success = run_full_migration(geocode=geocode)
-            if not success:
-                _reimport_status = {"running": False, "done": False, "error": "No CSV data found"}
-                return
-            clear_cache()
-            load_school_data()
-            _reimport_status = {"running": False, "done": True, "error": None}
-        except Exception as exc:
-            _reimport_status = {"running": False, "done": False, "error": str(exc)}
-
-    import threading
-    threading.Thread(target=_run, daemon=True).start()
-    return {"status": "started"}
-
-
-@app.get("/api/admin/reimport-ks2/status")
-async def reimport_ks2_status(
-    request: Request,
-    _: bool = Depends(verify_admin_api_key)
-):
-    """Poll this endpoint to check reimport progress."""
-    s = _reimport_status
-    if s["error"]:
-        raise HTTPException(status_code=500, detail=s["error"])
-    return {"running": s["running"], "done": s["done"]}
 
 
 # =============================================================================
@@ -707,7 +933,26 @@ async def robots_txt():
 @app.get("/sitemap.xml")
 async def sitemap_xml():
     """Serve sitemap.xml for search engine indexing."""
-    return FileResponse(settings.frontend_dir / "sitemap.xml", media_type="application/xml")
+    global _sitemap_xml
+    if _sitemap_xml is None:
+        try:
+            _sitemap_xml = build_sitemap()
+        except Exception as e:
+            raise HTTPException(status_code=503, detail=f"Sitemap unavailable: {e}")
+    return Response(content=_sitemap_xml, media_type="application/xml")
+
+
+@app.post("/api/admin/regenerate-sitemap")
+@limiter.limit("10/minute")
+async def regenerate_sitemap(
+    request: Request,
+    _: bool = Depends(verify_admin_api_key),
+):
+    """Rebuild and cache the sitemap from current school data. Called by Airflow after data updates."""
+    global _sitemap_xml
+    _sitemap_xml = build_sitemap()
+    n = _sitemap_xml.count("<url>")
+    return {"status": "ok", "urls": n}
 
 
 # Mount static files directly (must be after all routes to avoid catching API calls)

backend/config.py

@@ -38,6 +38,10 @@ class Settings(BaseSettings):
     rate_limit_burst: int = 10  # Allow burst of requests
     max_request_size: int = 1024 * 1024  # 1MB max request size
 
+    # Typesense
+    typesense_url: str = "http://localhost:8108"
+    typesense_api_key: str = ""
+
     # Analytics
     ga_measurement_id: Optional[str] = "G-J0PCVT14NY"  # Google Analytics 4 Measurement ID
 

backend/database.py

@@ -1,36 +1,30 @@
 """
 Database connection setup using SQLAlchemy.
+The schema is managed by dbt — the backend only reads from marts.* tables.
 """
 
-from datetime import datetime
-from typing import Optional
-
-from sqlalchemy import create_engine, inspect
-from sqlalchemy.orm import sessionmaker, declarative_base
 from contextlib import contextmanager
 
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker, declarative_base
+
 from .config import settings
 
-# Create engine
 engine = create_engine(
     settings.database_url,
     pool_size=10,
     max_overflow=20,
-    pool_pre_ping=True,  # Verify connections before use
+    pool_pre_ping=True,
-    echo=False,  # Set to True for SQL debugging
+    echo=False,
 )
 
-# Session factory
 SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
 
-# Base class for models
 Base = declarative_base()
 
 
 def get_db():
-    """
+    """Dependency for FastAPI routes."""
-    Dependency for FastAPI routes to get a database session.
-    """
     db = SessionLocal()
     try:
         yield db
@@ -40,10 +34,7 @@ def get_db():
 
 @contextmanager
 def get_db_session():
-    """
+    """Context manager for non-FastAPI contexts."""
-    Context manager for database sessions.
-    Use in non-FastAPI contexts (scripts, etc).
-    """
     db = SessionLocal()
     try:
         yield db
@@ -53,95 +44,3 @@ def get_db_session():
         raise
     finally:
         db.close()
-
-
-def init_db():
-    """
-    Initialize database - create all tables.
-    """
-    Base.metadata.create_all(bind=engine)
-
-
-def drop_db():
-    """
-    Drop all tables - use with caution!
-    """
-    Base.metadata.drop_all(bind=engine)
-
-
-def get_db_schema_version() -> Optional[int]:
-    """
-    Get the current schema version from the database.
-    Returns None if table doesn't exist or no version is set.
-    """
-    from .models import SchemaVersion  # Import here to avoid circular imports
-
-    # Check if schema_version table exists
-    inspector = inspect(engine)
-    if "schema_version" not in inspector.get_table_names():
-        return None
-
-    try:
-        with get_db_session() as db:
-            row = db.query(SchemaVersion).first()
-            return row.version if row else None
-    except Exception:
-        return None
-
-
-def set_db_schema_version(version: int):
-    """
-    Set/update the schema version in the database.
-    Creates the row if it doesn't exist.
-    """
-    from .models import SchemaVersion
-
-    with get_db_session() as db:
-        row = db.query(SchemaVersion).first()
-        if row:
-            row.version = version
-            row.migrated_at = datetime.utcnow()
-        else:
-            db.add(SchemaVersion(id=1, version=version, migrated_at=datetime.utcnow()))
-
-
-def check_and_migrate_if_needed():
-    """
-    Check schema version and run migration if needed.
-    Called during application startup.
-    """
-    from .version import SCHEMA_VERSION
-    from .migration import run_full_migration
-
-    db_version = get_db_schema_version()
-
-    if db_version == SCHEMA_VERSION:
-        print(f"Schema version {SCHEMA_VERSION} matches. Fast startup.")
-        # Still ensure tables exist (they should if version matches)
-        init_db()
-        return
-
-    if db_version is None:
-        print(f"No schema version found. Running initial migration (v{SCHEMA_VERSION})...")
-    else:
-        print(f"Schema mismatch: DB has v{db_version}, code expects v{SCHEMA_VERSION}")
-        print("Running full migration...")
-
-    try:
-        # Set schema version BEFORE migration so a crash mid-migration
-        # doesn't cause an infinite re-migration loop on every restart.
-        init_db()
-        set_db_schema_version(SCHEMA_VERSION)
-
-        success = run_full_migration(geocode=False)
-
-        if success:
-            print(f"Migration complete. Schema version {SCHEMA_VERSION}.")
-        else:
-            print("Warning: Migration completed but no data was imported.")
-
-    except Exception as e:
-        print(f"FATAL: Migration failed: {e}")
-        print("Application cannot start. Please check database and CSV files.")
-        raise
-

backend/models.py

@@ -1,408 +1,239 @@
 """
-SQLAlchemy database models for school data.
+SQLAlchemy models — all tables live in the marts schema, built by dbt.
-Normalized schema with separate tables for schools and yearly results.
+Read-only: the pipeline writes to these tables; the backend only reads.
 """
 
-from datetime import datetime
+from sqlalchemy import Column, Integer, String, Float, Boolean, Date, Text, Index
 
-from sqlalchemy import (
-    Column, Integer, String, Float, ForeignKey, Index, UniqueConstraint,
-    Text, Boolean, DateTime, Date
-)
-from sqlalchemy.orm import relationship
 from .database import Base
 
+MARTS = {"schema": "marts"}
 
-class School(Base):
+
-    """
+class DimSchool(Base):
-    Core school information - relatively static data.
+    """Canonical school dimension — one row per active URN."""
-    """
+    __tablename__ = "dim_school"
-    __tablename__ = "schools"
+    __table_args__ = MARTS
-    
+
-    id = Column(Integer, primary_key=True, autoincrement=True)
+    urn = Column(Integer, primary_key=True)
-    urn = Column(Integer, unique=True, nullable=False, index=True)
     school_name = Column(String(255), nullable=False)
-    local_authority = Column(String(100))
+    phase = Column(String(100))
-    local_authority_code = Column(Integer)
     school_type = Column(String(100))
-    school_type_code = Column(String(10))
+    academy_trust_name = Column(String(255))
-    religious_denomination = Column(String(100))
+    academy_trust_uid = Column(String(20))
+    religious_character = Column(String(100))
+    gender = Column(String(20))
     age_range = Column(String(20))
-    
+    capacity = Column(Integer)
-    # Address
+    total_pupils = Column(Integer)
-    address1 = Column(String(255))
+    headteacher_name = Column(String(200))
-    address2 = Column(String(255))
+    website = Column(String(255))
+    telephone = Column(String(30))
+    status = Column(String(50))
+    nursery_provision = Column(Boolean)
+    admissions_policy = Column(String(50))
+    # Denormalised Ofsted summary (updated by monthly pipeline)
+    ofsted_grade = Column(Integer)
+    ofsted_date = Column(Date)
+    ofsted_framework = Column(String(20))
+
+
+class DimLocation(Base):
+    """School location — address, lat/lng from easting/northing (BNG→WGS84)."""
+    __tablename__ = "dim_location"
+    __table_args__ = MARTS
+
+    urn = Column(Integer, primary_key=True)
+    address_line1 = Column(String(255))
+    address_line2 = Column(String(255))
     town = Column(String(100))
-    postcode = Column(String(20), index=True)
+    county = Column(String(100))
-    
+    postcode = Column(String(20))
-    # Geocoding (cached)
+    local_authority_code = Column(Integer)
+    local_authority_name = Column(String(100))
+    parliamentary_constituency = Column(String(100))
+    urban_rural = Column(String(50))
+    easting = Column(Integer)
+    northing = Column(Integer)
     latitude = Column(Float)
     longitude = Column(Float)
-
+    # geom is a PostGIS geometry — not mapped to SQLAlchemy (accessed via raw SQL)
-    # GIAS enrichment fields
-    website = Column(String(255))
-    headteacher_name = Column(String(200))
-    capacity = Column(Integer)
-    trust_name = Column(String(255))
-    trust_uid = Column(String(20))
-    gender = Column(String(20))        # Mixed / Girls / Boys
-    nursery_provision = Column(Boolean)
-
-    # Relationships
-    results = relationship("SchoolResult", back_populates="school", cascade="all, delete-orphan")
-    
-    def __repr__(self):
-        return f"<School(urn={self.urn}, name='{self.school_name}')>"
-    
-    @property
-    def address(self):
-        """Combine address fields into single string."""
-        parts = [self.address1, self.address2, self.town, self.postcode]
-        return ", ".join(p for p in parts if p)
 
 
-class SchoolResult(Base):
+class KS2Performance(Base):
-    """
+    """KS2 attainment — one row per URN per year (includes predecessor data)."""
-    Yearly KS2 results for a school.
+    __tablename__ = "fact_ks2_performance"
-    Each school can have multiple years of results.
+    __table_args__ = (
-    """
+        Index("ix_ks2_urn_year", "urn", "year"),
-    __tablename__ = "school_results"
+        MARTS,
-    
+    )
-    id = Column(Integer, primary_key=True, autoincrement=True)
+
-    school_id = Column(Integer, ForeignKey("schools.id", ondelete="CASCADE"), nullable=False)
+    urn = Column(Integer, primary_key=True)
-    year = Column(Integer, nullable=False, index=True)
+    year = Column(Integer, primary_key=True)
-    
+    source_urn = Column(Integer)
-    # Pupil numbers
     total_pupils = Column(Integer)
     eligible_pupils = Column(Integer)
-    
+    # Core attainment
-    # Core KS2 metrics - Expected Standard
     rwm_expected_pct = Column(Float)
-    reading_expected_pct = Column(Float)
-    writing_expected_pct = Column(Float)
-    maths_expected_pct = Column(Float)
-    gps_expected_pct = Column(Float)
-    science_expected_pct = Column(Float)
-    
-    # Higher Standard
     rwm_high_pct = Column(Float)
+    reading_expected_pct = Column(Float)
     reading_high_pct = Column(Float)
-    writing_high_pct = Column(Float)
-    maths_high_pct = Column(Float)
-    gps_high_pct = Column(Float)
-    
-    # Progress Scores
-    reading_progress = Column(Float)
-    writing_progress = Column(Float)
-    maths_progress = Column(Float)
-    
-    # Average Scores
     reading_avg_score = Column(Float)
+    reading_progress = Column(Float)
+    writing_expected_pct = Column(Float)
+    writing_high_pct = Column(Float)
+    writing_progress = Column(Float)
+    maths_expected_pct = Column(Float)
+    maths_high_pct = Column(Float)
     maths_avg_score = Column(Float)
+    maths_progress = Column(Float)
+    gps_expected_pct = Column(Float)
+    gps_high_pct = Column(Float)
     gps_avg_score = Column(Float)
-    
+    science_expected_pct = Column(Float)
-    # School Context
+    # Absence
+    reading_absence_pct = Column(Float)
+    writing_absence_pct = Column(Float)
+    maths_absence_pct = Column(Float)
+    gps_absence_pct = Column(Float)
+    science_absence_pct = Column(Float)
+    # Gender
+    rwm_expected_boys_pct = Column(Float)
+    rwm_high_boys_pct = Column(Float)
+    rwm_expected_girls_pct = Column(Float)
+    rwm_high_girls_pct = Column(Float)
+    # Disadvantaged
+    rwm_expected_disadvantaged_pct = Column(Float)
+    rwm_expected_non_disadvantaged_pct = Column(Float)
+    disadvantaged_gap = Column(Float)
+    # Context
     disadvantaged_pct = Column(Float)
     eal_pct = Column(Float)
     sen_support_pct = Column(Float)
     sen_ehcp_pct = Column(Float)
     stability_pct = Column(Float)
 
-    # Pupil Absence from Tests
-    reading_absence_pct = Column(Float)
-    gps_absence_pct = Column(Float)
-    maths_absence_pct = Column(Float)
-    writing_absence_pct = Column(Float)
-    science_absence_pct = Column(Float)
 
-    # Gender Breakdown
+class FactOfstedInspection(Base):
-    rwm_expected_boys_pct = Column(Float)
+    """Full Ofsted inspection history — one row per inspection."""
-    rwm_expected_girls_pct = Column(Float)
+    __tablename__ = "fact_ofsted_inspection"
-    rwm_high_boys_pct = Column(Float)
-    rwm_high_girls_pct = Column(Float)
-    
-    # Disadvantaged Performance
-    rwm_expected_disadvantaged_pct = Column(Float)
-    rwm_expected_non_disadvantaged_pct = Column(Float)
-    disadvantaged_gap = Column(Float)
-    
-    # 3-Year Averages
-    rwm_expected_3yr_pct = Column(Float)
-    reading_avg_3yr = Column(Float)
-    maths_avg_3yr = Column(Float)
-    
-    # Relationship
-    school = relationship("School", back_populates="results")
-    
-    # Constraints
     __table_args__ = (
-        UniqueConstraint('school_id', 'year', name='uq_school_year'),
+        Index("ix_ofsted_urn_date", "urn", "inspection_date"),
-        Index('ix_school_results_school_year', 'school_id', 'year'),
+        MARTS,
     )
-    
-    def __repr__(self):
-        return f"<SchoolResult(school_id={self.school_id}, year={self.year})>"
-
-
-class SchemaVersion(Base):
-    """
-    Tracks database schema version for automatic migrations.
-    Single-row table that stores the current schema version.
-    """
-    __tablename__ = "schema_version"
-
-    id = Column(Integer, primary_key=True, default=1)
-    version = Column(Integer, nullable=False)
-    migrated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
-
-    def __repr__(self):
-        return f"<SchemaVersion(version={self.version}, migrated_at={self.migrated_at})>"
-
-
-# ---------------------------------------------------------------------------
-# Supplementary data tables (populated by the Kestra data integrator)
-# ---------------------------------------------------------------------------
-
-class OfstedInspection(Base):
-    """Latest Ofsted inspection judgement per school."""
-    __tablename__ = "ofsted_inspections"
 
     urn = Column(Integer, primary_key=True)
-    inspection_date = Column(Date)
+    inspection_date = Column(Date, primary_key=True)
-    publication_date = Column(Date)
+    inspection_type = Column(String(100))
-    inspection_type = Column(String(100))   # Section 5 / Section 8 etc.
-    # Which inspection framework was used: 'OEIF' or 'ReportCard'
     framework = Column(String(20))
-
-    # --- OEIF grades (old framework, pre-Nov 2025) ---
-    # 1=Outstanding 2=Good 3=Requires improvement 4=Inadequate
     overall_effectiveness = Column(Integer)
     quality_of_education = Column(Integer)
     behaviour_attitudes = Column(Integer)
     personal_development = Column(Integer)
     leadership_management = Column(Integer)
-    early_years_provision = Column(Integer)   # nullable — not all schools
+    early_years_provision = Column(Integer)
-    previous_overall = Column(Integer)        # for trend display
+    sixth_form_provision = Column(Integer)
-
+    rc_safeguarding_met = Column(Boolean)
-    # --- Report Card grades (new framework, from Nov 2025) ---
-    # 1=Exceptional 2=Strong 3=Expected standard 4=Needs attention 5=Urgent improvement
-    rc_safeguarding_met = Column(Boolean)          # True=Met, False=Not met
     rc_inclusion = Column(Integer)
     rc_curriculum_teaching = Column(Integer)
     rc_achievement = Column(Integer)
     rc_attendance_behaviour = Column(Integer)
     rc_personal_development = Column(Integer)
     rc_leadership_governance = Column(Integer)
-    rc_early_years = Column(Integer)               # nullable — not all schools
+    rc_early_years = Column(Integer)
-    rc_sixth_form = Column(Integer)                # nullable — secondary only
+    rc_sixth_form = Column(Integer)
-
+    report_url = Column(Text)
-    def __repr__(self):
-        return f"<OfstedInspection(urn={self.urn}, framework={self.framework}, overall={self.overall_effectiveness})>"
 
 
-class OfstedParentView(Base):
+class FactParentView(Base):
-    """Ofsted Parent View survey — latest per school. 14 questions, % saying Yes."""
+    """Ofsted Parent View survey — latest per school."""
-    __tablename__ = "ofsted_parent_view"
+    __tablename__ = "fact_parent_view"
+    __table_args__ = MARTS
 
     urn = Column(Integer, primary_key=True)
     survey_date = Column(Date)
     total_responses = Column(Integer)
-    q_happy_pct = Column(Float)          # My child is happy at this school
+    q_happy_pct = Column(Float)
-    q_safe_pct = Column(Float)           # My child feels safe at this school
+    q_safe_pct = Column(Float)
-    q_bullying_pct = Column(Float)       # School deals with bullying well
+    q_behaviour_pct = Column(Float)
-    q_communication_pct = Column(Float)  # School keeps me informed
+    q_bullying_pct = Column(Float)
-    q_progress_pct = Column(Float)       # My child does well / good progress
+    q_communication_pct = Column(Float)
-    q_teaching_pct = Column(Float)       # Teaching is good
+    q_progress_pct = Column(Float)
-    q_information_pct = Column(Float)    # I receive valuable info about progress
+    q_teaching_pct = Column(Float)
-    q_curriculum_pct = Column(Float)     # Broad range of subjects taught
+    q_information_pct = Column(Float)
-    q_future_pct = Column(Float)         # Prepares child well for the future
+    q_curriculum_pct = Column(Float)
-    q_leadership_pct = Column(Float)     # Led and managed effectively
+    q_future_pct = Column(Float)
-    q_wellbeing_pct = Column(Float)      # Supports wider personal development
+    q_leadership_pct = Column(Float)
-    q_behaviour_pct = Column(Float)      # Pupils are well behaved
+    q_wellbeing_pct = Column(Float)
-    q_recommend_pct = Column(Float)      # I would recommend this school
+    q_recommend_pct = Column(Float)
-    q_sen_pct = Column(Float)            # Good information about child's SEN (where applicable)
-
-    def __repr__(self):
-        return f"<OfstedParentView(urn={self.urn}, responses={self.total_responses})>"
 
 
-class SchoolCensus(Base):
+class FactAdmissions(Base):
-    """Annual school census snapshot — class sizes and ethnicity breakdown."""
+    """School admissions — one row per URN per year."""
-    __tablename__ = "school_census"
+    __tablename__ = "fact_admissions"
-
-    urn = Column(Integer, primary_key=True)
-    year = Column(Integer, primary_key=True)
-    class_size_avg = Column(Float)
-    ethnicity_white_pct = Column(Float)
-    ethnicity_asian_pct = Column(Float)
-    ethnicity_black_pct = Column(Float)
-    ethnicity_mixed_pct = Column(Float)
-    ethnicity_other_pct = Column(Float)
-
     __table_args__ = (
-        Index('ix_school_census_urn_year', 'urn', 'year'),
+        Index("ix_admissions_urn_year", "urn", "year"),
+        MARTS,
     )
 
-    def __repr__(self):
-        return f"<SchoolCensus(urn={self.urn}, year={self.year})>"
-
-
-class SchoolAdmissions(Base):
-    """Annual admissions statistics per school."""
-    __tablename__ = "school_admissions"
-
     urn = Column(Integer, primary_key=True)
     year = Column(Integer, primary_key=True)
-    published_admission_number = Column(Integer)   # PAN
+    school_phase = Column(String(50))
+    published_admission_number = Column(Integer)
     total_applications = Column(Integer)
-    first_preference_offers_pct = Column(Float)    # % receiving 1st choice
+    first_preference_applications = Column(Integer)
+    first_preference_offers = Column(Integer)
+    first_preference_offer_pct = Column(Float)
+    oversubscription_ratio = Column(Float)
     oversubscribed = Column(Boolean)
-
+    admissions_policy = Column(String(100))
-    __table_args__ = (
-        Index('ix_school_admissions_urn_year', 'urn', 'year'),
-    )
-
-    def __repr__(self):
-        return f"<SchoolAdmissions(urn={self.urn}, year={self.year})>"
 
 
-class SenDetail(Base):
+class FactDeprivation(Base):
-    """SEN primary need type breakdown — more granular than school_results context fields."""
+    """IDACI deprivation index — one row per URN."""
-    __tablename__ = "sen_detail"
+    __tablename__ = "fact_deprivation"
-
+    __table_args__ = MARTS
-    urn = Column(Integer, primary_key=True)
-    year = Column(Integer, primary_key=True)
-    primary_need_speech_pct = Column(Float)    # SLCN
-    primary_need_autism_pct = Column(Float)    # ASD
-    primary_need_mld_pct = Column(Float)       # Moderate learning difficulty
-    primary_need_spld_pct = Column(Float)      # Specific learning difficulty (dyslexia etc.)
-    primary_need_semh_pct = Column(Float)      # Social, emotional, mental health
-    primary_need_physical_pct = Column(Float)  # Physical/sensory
-    primary_need_other_pct = Column(Float)
-
-    __table_args__ = (
-        Index('ix_sen_detail_urn_year', 'urn', 'year'),
-    )
-
-    def __repr__(self):
-        return f"<SenDetail(urn={self.urn}, year={self.year})>"
-
-
-class Phonics(Base):
-    """Phonics Screening Check pass rates."""
-    __tablename__ = "phonics"
-
-    urn = Column(Integer, primary_key=True)
-    year = Column(Integer, primary_key=True)
-    year1_phonics_pct = Column(Float)   # % reaching expected standard in Year 1
-    year2_phonics_pct = Column(Float)   # % reaching standard in Year 2 (re-takers)
-
-    __table_args__ = (
-        Index('ix_phonics_urn_year', 'urn', 'year'),
-    )
-
-    def __repr__(self):
-        return f"<Phonics(urn={self.urn}, year={self.year})>"
-
-
-class SchoolDeprivation(Base):
-    """IDACI deprivation index — derived via postcode → LSOA lookup."""
-    __tablename__ = "school_deprivation"
 
     urn = Column(Integer, primary_key=True)
     lsoa_code = Column(String(20))
-    idaci_score = Column(Float)    # 0–1, higher = more deprived
+    idaci_score = Column(Float)
-    idaci_decile = Column(Integer) # 1 = most deprived, 10 = least deprived
+    idaci_decile = Column(Integer)
-
-    def __repr__(self):
-        return f"<SchoolDeprivation(urn={self.urn}, decile={self.idaci_decile})>"
 
 
-class SchoolFinance(Base):
+class FactFinance(Base):
-    """FBIT financial benchmarking data."""
+    """FBIT financial benchmarking — one row per URN per year."""
-    __tablename__ = "school_finance"
+    __tablename__ = "fact_finance"
+    __table_args__ = (
+        Index("ix_finance_urn_year", "urn", "year"),
+        MARTS,
+    )
 
     urn = Column(Integer, primary_key=True)
     year = Column(Integer, primary_key=True)
-    per_pupil_spend = Column(Float)          # £ total expenditure per pupil
+    per_pupil_spend = Column(Float)
-    staff_cost_pct = Column(Float)           # % of budget on all staff
+    staff_cost_pct = Column(Float)
-    teacher_cost_pct = Column(Float)         # % on teachers specifically
+    teacher_cost_pct = Column(Float)
     support_staff_cost_pct = Column(Float)
     premises_cost_pct = Column(Float)
 
-    __table_args__ = (
-        Index('ix_school_finance_urn_year', 'urn', 'year'),
-    )
 
-    def __repr__(self):
+class Ks2NationalAverage(Base):
-        return f"<SchoolFinance(urn={self.urn}, year={self.year})>"
+    """Official DfE KS2 national headline averages — one row per academic year."""
-
+    __tablename__ = "fact_ks2_national_averages"
-
+    __table_args__ = MARTS
-# Mapping from CSV columns to model fields
-SCHOOL_FIELD_MAPPING = {
-    'urn': 'urn',
-    'school_name': 'school_name',
-    'local_authority': 'local_authority',
-    'local_authority_code': 'local_authority_code',
-    'school_type': 'school_type',
-    'school_type_code': 'school_type_code',
-    'religious_denomination': 'religious_denomination',
-    'age_range': 'age_range',
-    'address1': 'address1',
-    'address2': 'address2',
-    'town': 'town',
-    'postcode': 'postcode',
-}
-
-RESULT_FIELD_MAPPING = {
-    'year': 'year',
-    'total_pupils': 'total_pupils',
-    'eligible_pupils': 'eligible_pupils',
-    # Expected Standard
-    'rwm_expected_pct': 'rwm_expected_pct',
-    'reading_expected_pct': 'reading_expected_pct',
-    'writing_expected_pct': 'writing_expected_pct',
-    'maths_expected_pct': 'maths_expected_pct',
-    'gps_expected_pct': 'gps_expected_pct',
-    'science_expected_pct': 'science_expected_pct',
-    # Higher Standard
-    'rwm_high_pct': 'rwm_high_pct',
-    'reading_high_pct': 'reading_high_pct',
-    'writing_high_pct': 'writing_high_pct',
-    'maths_high_pct': 'maths_high_pct',
-    'gps_high_pct': 'gps_high_pct',
-    # Progress
-    'reading_progress': 'reading_progress',
-    'writing_progress': 'writing_progress',
-    'maths_progress': 'maths_progress',
-    # Averages
-    'reading_avg_score': 'reading_avg_score',
-    'maths_avg_score': 'maths_avg_score',
-    'gps_avg_score': 'gps_avg_score',
-    # Context
-    'disadvantaged_pct': 'disadvantaged_pct',
-    'eal_pct': 'eal_pct',
-    'sen_support_pct': 'sen_support_pct',
-    'sen_ehcp_pct': 'sen_ehcp_pct',
-    'stability_pct': 'stability_pct',
-    # Absence
-    'reading_absence_pct': 'reading_absence_pct',
-    'gps_absence_pct': 'gps_absence_pct',
-    'maths_absence_pct': 'maths_absence_pct',
-    'writing_absence_pct': 'writing_absence_pct',
-    'science_absence_pct': 'science_absence_pct',
-    # Gender
-    'rwm_expected_boys_pct': 'rwm_expected_boys_pct',
-    'rwm_expected_girls_pct': 'rwm_expected_girls_pct',
-    'rwm_high_boys_pct': 'rwm_high_boys_pct',
-    'rwm_high_girls_pct': 'rwm_high_girls_pct',
-    # Disadvantaged
-    'rwm_expected_disadvantaged_pct': 'rwm_expected_disadvantaged_pct',
-    'rwm_expected_non_disadvantaged_pct': 'rwm_expected_non_disadvantaged_pct',
-    'disadvantaged_gap': 'disadvantaged_gap',
-    # 3-Year
-    'rwm_expected_3yr_pct': 'rwm_expected_3yr_pct',
-    'reading_avg_3yr': 'reading_avg_3yr',
-    'maths_avg_3yr': 'maths_avg_3yr',
-}
 
+    year = Column(Integer, primary_key=True)
+    rwm_expected_pct = Column(Float)
+    rwm_high_pct = Column(Float)
+    reading_expected_pct = Column(Float)
+    reading_high_pct = Column(Float)
+    reading_avg_score = Column(Float)
+    writing_expected_pct = Column(Float)
+    writing_gd_pct = Column(Float)
+    maths_expected_pct = Column(Float)
+    maths_high_pct = Column(Float)
+    maths_avg_score = Column(Float)
+    gps_expected_pct = Column(Float)
+    gps_high_pct = Column(Float)
+    gps_avg_score = Column(Float)
+    science_expected_pct = Column(Float)

backend/schemas.py

@@ -142,7 +142,7 @@ NULL_VALUES = ["SUPP", "NE", "NA", "NP", "NEW", "LOW", ""]
 METRIC_DEFINITIONS = {
     # Expected Standard
     "rwm_expected_pct": {
-        "name": "RWM Combined %",
+        "name": "Reading, Writing & Maths Combined %",
         "short_name": "RWM %",
         "description": "% meeting expected standard in reading, writing and maths",
         "type": "percentage",
@@ -185,9 +185,9 @@ METRIC_DEFINITIONS = {
     },
     # Higher Standard
     "rwm_high_pct": {
-        "name": "RWM Combined Higher %",
+        "name": "Reading, Writing & Maths Combined Higher %",
         "short_name": "RWM Higher %",
-        "description": "% achieving higher standard in RWM combined",
+        "description": "% achieving higher standard in reading, writing & maths combined",
         "type": "percentage",
         "category": "higher",
     },
@@ -265,28 +265,28 @@ METRIC_DEFINITIONS = {
     },
     # Gender Performance
     "rwm_expected_boys_pct": {
-        "name": "RWM Expected % (Boys)",
+        "name": "Reading, Writing & Maths Expected % (Boys)",
         "short_name": "Boys RWM %",
         "description": "% of boys meeting expected standard",
         "type": "percentage",
         "category": "gender",
     },
     "rwm_expected_girls_pct": {
-        "name": "RWM Expected % (Girls)",
+        "name": "Reading, Writing & Maths Expected % (Girls)",
         "short_name": "Girls RWM %",
         "description": "% of girls meeting expected standard",
         "type": "percentage",
         "category": "gender",
     },
     "rwm_high_boys_pct": {
-        "name": "RWM Higher % (Boys)",
+        "name": "Reading, Writing & Maths Higher % (Boys)",
         "short_name": "Boys Higher %",
         "description": "% of boys at higher standard",
         "type": "percentage",
         "category": "gender",
     },
     "rwm_high_girls_pct": {
-        "name": "RWM Higher % (Girls)",
+        "name": "Reading, Writing & Maths Higher % (Girls)",
         "short_name": "Girls Higher %",
         "description": "% of girls at higher standard",
         "type": "percentage",
@@ -294,14 +294,14 @@ METRIC_DEFINITIONS = {
     },
     # Disadvantaged Performance
     "rwm_expected_disadvantaged_pct": {
-        "name": "RWM Expected % (Disadvantaged)",
+        "name": "Reading, Writing & Maths Expected % (Disadvantaged)",
         "short_name": "Disadvantaged %",
         "description": "% of disadvantaged pupils meeting expected",
         "type": "percentage",
         "category": "equity",
     },
     "rwm_expected_non_disadvantaged_pct": {
-        "name": "RWM Expected % (Non-Disadvantaged)",
+        "name": "Reading, Writing & Maths Expected % (Non-Disadvantaged)",
         "short_name": "Non-Disadv %",
         "description": "% of non-disadvantaged pupils meeting expected",
         "type": "percentage",
@@ -381,7 +381,7 @@ METRIC_DEFINITIONS = {
     },
     # 3-Year Averages
     "rwm_expected_3yr_pct": {
-        "name": "RWM Expected % (3-Year Avg)",
+        "name": "Reading, Writing & Maths Expected % (3-Year Avg)",
         "short_name": "RWM 3yr %",
         "description": "3-year average % meeting expected",
         "type": "percentage",
@@ -401,6 +401,70 @@ METRIC_DEFINITIONS = {
         "type": "score",
         "category": "trends",
     },
+    # ── GCSE Performance (KS4) ────────────────────────────────────────────
+    "attainment_8_score": {
+        "name": "Attainment 8",
+        "short_name": "Att 8",
+        "description": "Average grade across a pupil's best 8 GCSEs including English and Maths",
+        "type": "score",
+        "category": "gcse",
+    },
+    "progress_8_score": {
+        "name": "Progress 8",
+        "short_name": "P8",
+        "description": "Progress from KS2 baseline to GCSE relative to similar pupils nationally (0 = national average)",
+        "type": "score",
+        "category": "gcse",
+    },
+    "english_maths_standard_pass_pct": {
+        "name": "English & Maths Grade 4+",
+        "short_name": "E&M 4+",
+        "description": "% of pupils achieving grade 4 (standard pass) or above in both English and Maths",
+        "type": "percentage",
+        "category": "gcse",
+    },
+    "english_maths_strong_pass_pct": {
+        "name": "English & Maths Grade 5+",
+        "short_name": "E&M 5+",
+        "description": "% of pupils achieving grade 5 (strong pass) or above in both English and Maths",
+        "type": "percentage",
+        "category": "gcse",
+    },
+    "ebacc_entry_pct": {
+        "name": "EBacc Entry %",
+        "short_name": "EBacc Entry",
+        "description": "% of pupils entered for the English Baccalaureate (English, Maths, Sciences, Languages, Humanities)",
+        "type": "percentage",
+        "category": "gcse",
+    },
+    "ebacc_standard_pass_pct": {
+        "name": "EBacc Grade 4+",
+        "short_name": "EBacc 4+",
+        "description": "% of pupils achieving grade 4+ across all EBacc subjects",
+        "type": "percentage",
+        "category": "gcse",
+    },
+    "ebacc_strong_pass_pct": {
+        "name": "EBacc Grade 5+",
+        "short_name": "EBacc 5+",
+        "description": "% of pupils achieving grade 5+ across all EBacc subjects",
+        "type": "percentage",
+        "category": "gcse",
+    },
+    "ebacc_avg_score": {
+        "name": "EBacc Average Score",
+        "short_name": "EBacc Avg",
+        "description": "Average points score across EBacc subjects",
+        "type": "score",
+        "category": "gcse",
+    },
+    "gcse_grade_91_pct": {
+        "name": "GCSE Grade 9–1 %",
+        "short_name": "GCSE 9–1",
+        "description": "% of GCSE entries achieving a grade 9 to 1",
+        "type": "percentage",
+        "category": "gcse",
+    },
 }
 
 # Ranking columns to include in rankings response
@@ -456,6 +520,16 @@ RANKING_COLUMNS = [
     "rwm_expected_3yr_pct",
     "reading_avg_3yr",
     "maths_avg_3yr",
+    # GCSE (KS4)
+    "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",
+    "gcse_grade_91_pct",
 ]
 
 # School listing columns
@@ -469,6 +543,11 @@ SCHOOL_COLUMNS = [
     "postcode",
     "religious_denomination",
     "age_range",
+    "gender",
+    "admissions_policy",
+    "ofsted_grade",
+    "ofsted_date",
+    "ofsted_framework",
     "latitude",
     "longitude",
 ]

data/.gitkeep

@@ -1,3 +0,0 @@
-# Place your CSV data files here
-# Download from: https://www.compare-school-performance.service.gov.uk/download-data
-

data/meta/census_meta.csv

@@ -1,24 +0,0 @@
-Field Number,Field Reference,Field Name,Values,Data Format,LA level field?,National level field?
-1,URN,School Unique Reference Number,999999,I6,No,No
-2,LA,LA number,999,I3,Yes,No
-3,ESTAB,ESTAB number,9999,I4,No,No
-4,SCHOOLTYPE,Type of school,String,,No,No
-5,NOR,Total number of pupils on roll,9999 or NA,,Yes,Yes
-6,NORG,Number of girls on roll,9999 or NA,,Yes,Yes
-7,NORB,Number of boys on roll,9999 or NA,,Yes,Yes
-8,PNORG,Percentage of girls on roll,99.9 or NA,,Yes,Yes
-9,PNORB,Percentage of boys on roll,99.9 or NA,,Yes,Yes
-10,TSENELSE,Number of eligible pupils with an EHC plan,9999 or NA,A4,Yes,Yes
-11,PSENELSE,Percentage of eligible pupils with an EHC plan,99.9 or NA,A4,Yes,Yes
-12,TSENELK,Number of eligible pupils with SEN support,9999 or NA,A4,Yes,Yes
-13,PSENELK,Percentage of eligible pupils with SEN support,99.9 or NA,A4,Yes,Yes
-14,NUMEAL,No.  pupils where English not first language,9999 or NA,A4,Yes,Yes
-15,NUMENGFL,No. pupils with English first language,9999 or NA,A4,Yes,Yes
-16,NUMUNCFL,No. pupils where first language is unclassified,9999 or NA,A4,Yes,Yes
-17,PNUMEAL,%  pupils where English not first language,99.9 or NA,A4,Yes,Yes
-18,PNUMENGFL,% pupils with English first language,99.9 or NA,A4,Yes,Yes
-19,PNUMUNCFL,% pupils where first language is unclassified,99.9 or NA,A4,Yes,Yes
-20,NUMFSM,No. pupils eligible for free school meals,9999 or NA,A4,Yes,Yes
-21,NUMFSMEVER,Number of pupils eligible for FSM at any time during the past 6 years,9999 or NA,A6,Yes,Yes
-22,NORFSMEVER,Total pupils for FSMEver,9999 or NA,,Yes,Yes
-23,PNUMFSMEVER,Percentage of pupils eligible for FSM at any time during the past 6 years,99.9 or NA,A4,Yes,Yes

data/meta/ks2_meta.csv

@@ -1,312 +0,0 @@
-Column,Field Name,Label/Description
-1,RECTYPE,Record type
-2,AlphaIND,Alphabetic index
-3,LEA,Local authority number
-4,ESTAB,Establishment number
-5,URN,School unique reference number
-6,SCHNAME,School/Local authority name
-7,ADDRESS1,School address (1)
-8,ADDRESS2,School address (2)
-9,ADDRESS3,School address (3)
-10,TOWN,School town
-11,PCODE,School postcode
-12,TELNUM,School telephone number 
-13,PCON_CODE,School parliamentary constituency code
-14,PCON_NAME,School parliamentary constituency name
-15,URN_AC,Converter academy: URN 
-16,SCHNAME_AC,Converter academy: name
-17,OPEN_AC,Converter academy: open date
-18,NFTYPE,School type
-19,ICLOSE,Closed Flag
-20,RELDENOM,Religious denomination
-21,AGERANGE,Age range
-22,TAB15,School published in secondary school (key stage 4) performance tables
-23,TAB1618,School published in school and college (key stage 5) performance tables
-24,TOTPUPS,Total number of pupils (including part-time pupils)
-25,TPUPYEAR,Number of pupils aged 11 
-26,TELIG,Published eligible pupil number
-27,BELIG,Eligible boys on school roll at time of tests
-28,GELIG,Eligible girls on school roll at time of tests
-29,PBELIG,Percentage of eligible boys on school roll at time of tests
-30,PGELIG,Percentage of eligible girls on school roll at time of tests
-31,TKS1AVERAGE,Cohort level key stage 1 average points score [not populated in 2025]
-32,TKS1GROUP_L,Number of pupils in cohort with low KS1 attainment [not populated in 2025]
-33,PTKS1GROUP_L,Percentage of pupils in cohort with low KS1 attainment [not populated in 2025]
-34,TKS1GROUP_M,Number of pupils in cohort with medium KS1 attainment [not populated in 2025]
-35,PTKS1GROUP_M,Percentage of pupils in cohort with medium KS1 attainment [not populated in 2025]
-36,TKS1GROUP_H,Number of pupils in cohort high KS1 attainment [not populated in 2025]
-37,PTKS1GROUP_H,Percentage of pupils in cohort with high KS1 attainment [not populated in 2025]
-38,TKS1GROUP_NA,No. of pupils in KS1 group not calculable [not populated in 2025]
-39,PTKS1GROUP_NA,Percentage of pupils in KS1group not calculable [not populated in 2025]
-40,TFSM6CLA1A,Number of key stage 2 disadvantaged pupils (those who were eligible for free school meals in last 6 years or are looked after by the LA for a day or more or who have been adopted from care)
-41,PTFSM6CLA1A,Percentage of key stage 2 disadvantaged pupils
-42,TNotFSM6CLA1A,Number of key stage 2 pupils who are not disadvantaged
-43,PTNotFSM6CLA1A,Percentage of key stage 2 pupils who are not disadvantaged
-44,TEALGRP2,Number of eligible pupils with English as additional language (EAL)
-45,PTEALGRP2,Percentage of eligible pupils with English as additional language (EAL)
-46,TMOBN,Number of eligible pupils classified as non-mobile
-47,PTMOBN,Percentage of eligible pupils classified as non-mobile
-48,PTRWM_EXP,"Percentage of pupils reaching the expected standard in reading, writing and maths"
-49,PTRWM_HIGH,Percentage of pupils achieving a high score in reading and maths and working at greater depth in writing
-50,READPROG,Reading progress measure [not populated in 2025]
-51,READPROG_LOWER,Reading progress measure - lower confidence limit [not populated in 2025]
-52,READPROG_UPPER,Reading progress measure - upper confidence limit [not populated in 2025]
-53,READCOV,Reading progress measure - coverage [not populated in 2025]
-54,WRITPROG,Writing progress measure [not populated in 2025]
-55,WRITPROG_LOWER,Writing progress measure - lower confidence limit [not populated in 2025]
-56,WRITPROG_UPPER,Writing progress measure - upper confidence limit [not populated in 2025]
-57,WRITCOV,Writing progress measure - coverage [not populated in 2025]
-58,MATPROG,Maths progress measure [not populated in 2025]
-59,MATPROG_LOWER,Maths progress measure - lower confidence limit [not populated in 2025]
-60,MATPROG_UPPER,Maths progress measure - upper confidence limit [not populated in 2025]
-61,MATCOV,Maths progress measure - coverage [not populated in 2025]
-62,PTREAD_EXP,Percentage of pupils reaching the expected standard in reading
-63,PTREAD_HIGH,Percentage of pupils achieving a high score in reading
-64,PTREAD_AT,Percentage of pupils absent from or not able to access the test in reading
-65,READ_AVERAGE,Average scaled score in reading
-66,PTGPS_EXP,"Percentage of pupils reaching the expected standard in grammar, punctuation and spelling"
-67,PTGPS_HIGH,"Percentage of pupils achieving a high score in grammar, punctuation and spelling"
-68,PTGPS_AT,"Percentage of pupils absent from or not able to access the test in grammar, punctuation and spelling"
-69,GPS_AVERAGE,"Average scaled score in grammar, punctuation and spelling"
-70,PTMAT_EXP,Percentage of pupils reaching the expected standard in maths
-71,PTMAT_HIGH,Percentage of pupils achieving a high score in maths
-72,PTMAT_AT,Percentage of pupils absent from or not able to access the test in maths
-73,MAT_AVERAGE,Average scaled score in maths
-74,PTWRITTA_EXP,Percentage of pupils reaching the expected standard in writing
-75,PTWRITTA_HIGH,Percentage of pupils working at greater depth within the expected standard in writing
-76,PTWRITTA_WTS,Percentage of pupils working towards the expected standard in writing
-77,PTWRITTA_AD,Percentage of pupils absent or disapplied in writing TA
-78,PTSCITA_EXP,Percentage of pupils reaching the expected standard in science TA
-79,PTSCITA_AD,Percentage of pupils absent or disapplied in science TA
-80,PTRWM_EXP_B,"Percentage of boys reaching the expected standard in reading, writing and maths"
-81,PTRWM_EXP_G,"Percentage of girls reaching the expected standard in reading, writing and maths"
-82,PTRWM_EXP_L,"Percentage of pupils with low prior attainment reaching the expected standard in reading, writing and maths [not populated in 2025]"
-83,PTRWM_EXP_M,"Percentage of pupils with medium prior attainment reaching the expected standard in reading, writing and maths [not populated in 2025]"
-84,PTRWM_EXP_H,"Percentage of pupils with high prior attainment reaching the expected standard in reading, writing and maths [not populated in 2025]"
-85,PTRWM_EXP_FSM6CLA1A,"Percentage of disadvantaged pupils reaching the expected standard in reading, writing and maths"
-86,PTRWM_EXP_NotFSM6CLA1A,"Percentage of non-disadvantaged pupils reaching the expected standard in reading, writing and maths"
-87,DIFFN_RWM_EXP,"Difference between school percentage of disavantaged pupils and national percentage of other pupils reaching the expected standard in reading, writing and maths "
-88,PTRWM_EXP_EAL,"Percentage of EAL pupils reaching the expected standard in reading, writing and maths"
-89,PTRWM_EXP_MOBN,"Percentage of non-mobile pupils reaching the expected standard in reading, writing and maths"
-90,PTRWM_HIGH_B,Percentage of boys achieving a high score in reading and maths and working at greater depth in writing
-91,PTRWM_HIGH_G,"Percentage of girls reaching the HIGHected standard in reading, writing and maths"
-92,PTRWM_HIGH_L,Percentage of pupils with low prior attainment achieving a high score in reading and maths and working at greater depth in writing [not populated in 2025]
-93,PTRWM_HIGH_M,Percentage of pupils with medium prior attainment achieving a high score in reading and maths and working at greater depth in writing [not populated in 2025]
-94,PTRWM_HIGH_H,Percentage of pupils with high prior attainment achieving a high score in reading and maths and working at greater depth in writing [not populated in 2025]
-95,PTRWM_HIGH_FSM6CLA1A,Percentage of disadvantaged pupils achieving a high score in reading and maths and working at greater depth in writing
-96,PTRWM_HIGH_NotFSM6CLA1A,Percentage of non-disadvantaged pupils achieving a high score in reading and maths and working at greater depth in writing
-97,DIFFN_RWM_HIGH,"Difference between school percentage of disavantaged pupils and national percentage of other pupils achieving a high score in reading, writing and maths "
-98,PTRWM_HIGH_EAL,Percentage of EAL pupils achieving a high score in reading and maths and working at greater depth in writing
-99,PTRWM_HIGH_MOBN,Percentage of non-mobile pupils achieving a high score in reading and maths and working at greater depth in writing
-100,READPROG_B,Reading progress measure for boys [not populated in 2025]
-101,READPROG_B_LOWER,Reading progress measure for boys - lower confidence limit [not populated in 2025]
-102,READPROG_B_UPPER,Reading progress measure for boys - upper confidence limit [not populated in 2025]
-103,READPROG_G,Reading progress measure for girls [not populated in 2025]
-104,READPROG_G_LOWER,Reading progress measure for girls - lower confidence limit [not populated in 2025]
-105,READPROG_G_UPPER,Reading progress measure for girls - upper confidence limit [not populated in 2025]
-106,READPROG_L,Reading progress measure for pupils with low prior attainment [not populated in 2025]
-107,READPROG_L_LOWER,Reading progress measure for pupils with low prior attainment - lower confidence limit [not populated in 2025]
-108,READPROG_L_UPPER,Reading progress measure for pupils with low prior attainment - upper confidence limit [not populated in 2025]
-109,READPROG_M,Reading progress measure for pupils with medium prior attainment [not populated in 2025]
-110,READPROG_M_LOWER,Reading progress measure for pupils with medium prior attainment - lower confidence limit [not populated in 2025]
-111,READPROG_M_UPPER,Reading progress measure for pupils with medium prior attainment - upper confidence limit [not populated in 2025]
-112,READPROG_H,Reading progress measure for pupils with high prior attainment [not populated in 2025]
-113,READPROG_H_LOWER,Reading progress measure for pupils with high prior attainment - lower confidence limit [not populated in 2025]
-114,READPROG_H_UPPER,Reading progress measure for pupils with high prior attainment - upper confidence limit [not populated in 2025]
-115,READPROG_FSM6CLA1A,Reading progress measure for disadvantaged pupils [not populated in 2025]
-116,READPROG_FSM6CLA1A_LOWER,Reading progress measure for disadvantaged pupils - lower confidence limit [not populated in 2025]
-117,READPROG_FSM6CLA1A_UPPER,Reading progress measure for disadvantaged pupils - upper confidence limit [not populated in 2025]
-118,READPROG_NotFSM6CLA1A,Reading progress measure for non-disadvantaged pupils [not populated in 2025]
-119,READPROG_NotFSM6CLA1A_LOWER,Reading progress measure for non-disadvantaged pupils - lower confidence limit [not populated in 2025]
-120,READPROG_NotFSM6CLA1A_UPPER,Reading progress measure for non-disadvantaged pupils - upper confidence limit [not populated in 2025]
-121,DIFFN_READPROG,Difference between reading progress measure for disadvantaged pupils in school and other pupils nationally [not populated in 2025]
-122,READPROG_EAL,Reading progress measure for EAL pupils [not populated in 2025]
-123,READPROG_EAL_LOWER,Reading progress measure for EAL pupils - lower confidence limit [not populated in 2025]
-124,READPROG_EAL_UPPER,Reading progress measure for EAL pupils - upper confidence limit [not populated in 2025]
-125,READPROG_MOBN,Reading progress measure for non-mobile pupils [not populated in 2025]
-126,READPROG_MOBN_LOWER,Reading progress measure for non-mobile pupils - lower confidence limit [not populated in 2025]
-127,READPROG_MOBN_UPPER,Reading progress measure for non-mobile pupils - upper confidence limit [not populated in 2025]
-128,WRITPROG_B,Writing progress measure for boys [not populated in 2025]
-129,WRITPROG_B_LOWER,Writing progress measure for boys - lower confidence limit [not populated in 2025]
-130,WRITPROG_B_UPPER,Writing progress measure for boys - upper confidence limit [not populated in 2025]
-131,WRITPROG_G,Writing progress measure for girls [not populated in 2025]
-132,WRITPROG_G_LOWER,Writing progress measure for girls - lower confidence limit [not populated in 2025]
-133,WRITPROG_G_UPPER,Writing progress measure for girls - upper confidence limit [not populated in 2025]
-134,WRITPROG_L,Writing progress measure for pupils with low prior attainment [not populated in 2025]
-135,WRITPROG_L_LOWER,Writing progress measure for pupils with low prior attainment - lower confidence limit [not populated in 2025]
-136,WRITPROG_L_UPPER,Writing progress measure for pupils with low prior attainment - upper confidence limit [not populated in 2025]
-137,WRITPROG_M,Writing progress measure for pupils with medium prior attainment [not populated in 2025]
-138,WRITPROG_M_LOWER,Writing progress measure for pupils with medium prior attainment - lower confidence limit [not populated in 2025]
-139,WRITPROG_M_UPPER,Writing progress measure for pupils with medium prior attainment - upper confidence limit [not populated in 2025]
-140,WRITPROG_H,Writing progress measure for pupils with high prior attainment [not populated in 2025]
-141,WRITPROG_H_LOWER,Writing progress measure for pupils with high prior attainment - lower confidence limit [not populated in 2025]
-142,WRITPROG_H_UPPER,Writing progress measure for pupils with high prior attainment - upper confidence limit [not populated in 2025]
-143,WRITPROG_FSM6CLA1A,Writing progress measure for disadvantaged pupils [not populated in 2025]
-144,WRITPROG_FSM6CLA1A_LOWER,Writing progress measure for disadvantaged pupils - lower confidence limit [not populated in 2025]
-145,WRITPROG_FSM6CLA1A_UPPER,Writing progress measure for disadvantaged pupils - upper confidence limit [not populated in 2025]
-146,WRITPROG_NotFSM6CLA1A,Writing progress measure for non-disadvantaged pupils [not populated in 2025]
-147,WRITPROG_NotFSM6CLA1A_LOWER,Writing progress measure for non-disadvantaged pupils - lower confidence limit [not populated in 2025]
-148,WRITPROG_NotFSM6CLA1A_UPPER,Writing progress measure for non-disadvantaged pupils - upper confidence limit [not populated in 2025]
-149,DIFFN_WRITPROG,Difference between writing progress measure for disadvantaged pupils in school and other pupils nationally [not populated in 2025]
-150,WRITPROG_EAL,Writing progress measure for EAL pupils [not populated in 2025]
-151,WRITPROG_EAL_LOWER,Writing progress measure for EAL pupils - lower confidence limit [not populated in 2025]
-152,WRITPROG_EAL_UPPER,Writing progress measure for EAL pupils - upper confidence limit [not populated in 2025]
-153,WRITPROG_MOBN,Writing progress measure for non-mobile pupils [not populated in 2025]
-154,WRITPROG_MOBN_LOWER,Writing progress measure for non-mobile pupils - lower confidence limit [not populated in 2025]
-155,WRITPROG_MOBN_UPPER,Writing progress measure for non-mobile pupils - upper confidence limit [not populated in 2025]
-156,MATPROG_B,Maths progress measure for boys [not populated in 2025]
-157,MATPROG_B_LOWER,Maths progress measure for boys - lower confidence limit [not populated in 2025]
-158,MATPROG_B_UPPER,Maths progress measure for boys - upper confidence limit [not populated in 2025]
-159,MATPROG_G,Maths progress measure for girls [not populated in 2025]
-160,MATPROG_G_LOWER,Maths progress measure for girls - lower confidence limit [not populated in 2025]
-161,MATPROG_G_UPPER,Maths progress measure for girls - upper confidence limit [not populated in 2025]
-162,MATPROG_L,Maths progress measure for pupils with low prior attainment [not populated in 2025]
-163,MATPROG_L_LOWER,Maths progress measure for pupils with low prior attainment - lower confidence limit [not populated in 2025]
-164,MATPROG_L_UPPER,Maths progress measure for pupils with low prior attainment - upper confidence limit [not populated in 2025]
-165,MATPROG_M,Maths progress measure for pupils with medium prior attainment [not populated in 2025]
-166,MATPROG_M_LOWER,Maths progress measure for pupils with medium prior attainment - lower confidence limit [not populated in 2025]
-167,MATPROG_M_UPPER,Maths progress measure for pupils with medium prior attainment - upper confidence limit [not populated in 2025]
-168,MATPROG_H,Maths progress measure for pupils with high prior attainment [not populated in 2025]
-169,MATPROG_H_LOWER,Maths progress measure for pupils with high prior attainment - lower confidence limit [not populated in 2025]
-170,MATPROG_H_UPPER,Maths progress measure for pupils with high prior attainment - upper confidence limit [not populated in 2025]
-171,MATPROG_FSM6CLA1A,Maths progress measure for disadvantaged pupils [not populated in 2025]
-172,MATPROG_FSM6CLA1A_LOWER,Maths progress measure for disadvantaged pupils - lower confidence limit [not populated in 2025]
-173,MATPROG_FSM6CLA1A_UPPER,Maths progress measure for disadvantaged pupils - upper confidence limit [not populated in 2025]
-174,MATPROG_NotFSM6CLA1A,Maths progress measure for non-disadvantaged pupils [not populated in 2025]
-175,MATPROG_NotFSM6CLA1A_LOWER,Maths progress measure for non-disadvantaged pupils - lower confidence limit [not populated in 2025]
-176,MATPROG_NotFSM6CLA1A_UPPER,Maths progress measure for non-disadvantaged pupils - upper confidence limit [not populated in 2025]
-177,DIFFN_MATPROG,Difference between maths progress measure for disadvantaged pupils in school and other pupils nationally [not populated in 2025]
-178,MATPROG_EAL,Maths progress measure for EAL pupils [not populated in 2025]
-179,MATPROG_EAL_LOWER,Maths progress measure for EAL pupils - lower confidence limit [not populated in 2025]
-180,MATPROG_EAL_UPPER,Maths progress measure for EAL pupils - upper confidence limit [not populated in 2025]
-181,MATPROG_MOBN,Maths progress measure for non-mobile pupils [not populated in 2025]
-182,MATPROG_MOBN_LOWER,Maths progress measure for non-mobile pupils - lower confidence limit [not populated in 2025]
-183,MATPROG_MOBN_UPPER,Maths progress measure for non-mobile pupils - upper confidence limit [not populated in 2025]
-184,READ_AVERAGE_B,Average scaled score in reading for boys
-185,READ_AVERAGE_G,Average scaled score in reading for girls
-186,READ_AVERAGE_L,Average scaled score in reading for pupils with low prior attainment [not populated in 2025]
-187,READ_AVERAGE_M,Average scaled score in reading for pupils with medium prior attainment [not populated in 2025]
-188,READ_AVERAGE_H,Average scaled score in reading for pupils with high prior attainment [not populated in 2025]
-189,READ_AVERAGE_FSM6CLA1A,Average scaled score in reading for disadvantaged pupils
-190,READ_AVERAGE_NotFSM6CLA1A,Average scaled score in reading for non-disadvantaged pupils
-191,READ_AVERAGE_EAL,Average scaled score in reading for EAL pupils
-192,READ_AVERAGE_MOBN,Average scaled score in reading for MOBN pupils
-193,MAT_AVERAGE_B,Average scaled score in maths for boys
-194,MAT_AVERAGE_G,Average scaled score in maths for girls
-195,MAT_AVERAGE_L,Average scaled score in maths for pupils with low prior attainment [not populated in 2025]
-196,MAT_AVERAGE_M,Average scaled score in maths for pupils with medium prior attainment [not populated in 2025]
-197,MAT_AVERAGE_H,Average scaled score in maths for pupils with high prior attainment [not populated in 2025]
-198,MAT_AVERAGE_FSM6CLA1A,Average scaled score in maths for disadvantaged pupils
-199,MAT_AVERAGE_NotFSM6CLA1A,Average scaled score in maths for non-disadvantaged pupils
-200,MAT_AVERAGE_EAL,Average scaled score in maths for EAL pupils
-201,MAT_AVERAGE_MOBN,Average scaled score in maths for MOBN pupils
-202,GPS_AVERAGE_B,Average scaled score in GPS for boys
-203,GPS_AVERAGE_G,Average scaled score in GPS for girls
-204,GPS_AVERAGE_L,Average scaled score in GPS for pupils with low prior attainment [not populated in 2025]
-205,GPS_AVERAGE_M,Average scaled score in GPS for pupils with medium prior attainment [not populated in 2025]
-206,GPS_AVERAGE_H,Average scaled score in GPS for pupils with high prior attainment [not populated in 2025]
-207,GPS_AVERAGE_FSM6CLA1A,Average scaled score in GPS for disadvantaged pupils
-208,GPS_AVERAGE_NotFSM6CLA1A,Average scaled score in GPS for non-disadvantaged pupils
-209,GPS_AVERAGE_EAL,Average scaled score in GPS for EAL pupils
-210,GPS_AVERAGE_MOBN,Average scaled score in GPS for MOBN pupils
-211,PTREAD_EXP_L,Percentage of pupils with low prior attainment reaching the expected standard in reading [not populated in 2025]
-212,PTREAD_EXP_M,Percentage of pupils with medium prior attainment reaching the expected standard in reading [not populated in 2025]
-213,PTREAD_EXP_H,Percentage of pupils with high prior attainment reaching the expected standard in reading [not populated in 2025]
-214,PTREAD_EXP_FSM6CLA1A,Percentage of disadvantaged pupils reaching the expected standard in reading
-215,PTREAD_EXP_NotFSM6CLA1A,Percentage of non-disadvantaged pupils reaching the expected standard in reading
-216,PTGPS_EXP_L,"Percentage of pupils with low prior attainment reaching the expected standard in grammar, punctuation and spelling [not populated in 2025]"
-217,PTGPS_EXP_M,"Percentage of pupils with medium prior attainment reaching the expected standard in grammar, punctuation and spelling [not populated in 2025]"
-218,PTGPS_EXP_H,"Percentage of pupils with high prior attainment reaching the expected standard in grammar, punctuation and spelling [not populated in 2025]"
-219,PTGPS_EXP_FSM6CLA1A,"Percentage of disadvantaged pupils reaching the expected standard in grammar, punctuation and spelling"
-220,PTGPS_EXP_NotFSM6CLA1A,"Percentage of non-disadvantaged pupils reaching the expected standard in grammar, punctuation and spelling"
-221,PTMAT_EXP_L,Percentage of pupils with low prior attainment reaching the expected standard in maths [not populated in 2025]
-222,PTMAT_EXP_M,Percentage of pupils with medium prior attainment reaching the expected standard in maths [not populated in 2025]
-223,PTMAT_EXP_H,Percentage of pupils with high prior attainment reaching the expected standard in maths [not populated in 2025]
-224,PTMAT_EXP_FSM6CLA1A,Percentage of disadvantaged pupils reaching the expected standard in maths
-225,PTMAT_EXP_NotFSM6CLA1A,Percentage of non-disadvantaged pupils reaching the expected standard in maths
-226,PTWRITTA_EXP_L,Percentage of pupils with low prior attainment reaching the expected standard in writing [not populated in 2025]
-227,PTWRITTA_EXP_M,Percentage of pupils with medium prior attainment reaching the expected standard in writing [not populated in 2025]
-228,PTWRITTA_EXP_H,Percentage of pupils with high prior attainment reaching the expected standard in writing [not populated in 2025]
-229,PTWRITTA_EXP_FSM6CLA1A,Percentage of disadvantaged pupils reaching the expected standard in writing
-230,PTWRITTA_EXP_NotFSM6CLA1A,Percentage of non-disadvantaged pupils reaching the expected standard in writing
-231,PTREAD_HIGH_L,Percentage of pupils with low prior attainment achieving a high score in reading [not populated in 2025]
-232,PTREAD_HIGH_M,Percentage of pupils with medium prior attainment achieving a high score in reading [not populated in 2025]
-233,PTREAD_HIGH_H,Percentage of pupils with high prior attainment achieving a high score in reading [not populated in 2025]
-234,PTREAD_HIGH_FSM6CLA1A,Percentage of disadvantaged pupils achieving a high score in reading
-235,PTREAD_HIGH_NotFSM6CLA1A,Percentage of non-disadvantaged pupils achieving a high score in reading
-236,PTGPS_HIGH_L,"Percentage of pupils with low prior attainment achieving a high score in grammar, punctuation and spelling [not populated in 2025]"
-237,PTGPS_HIGH_M,"Percentage of pupils with medium prior attainment achieving a high score in grammar, punctuation and spelling [not populated in 2025]"
-238,PTGPS_HIGH_H,"Percentage of pupils with high prior attainment achieving a high score in grammar, punctuation and spelling [not populated in 2025]"
-239,PTGPS_HIGH_FSM6CLA1A,"Percentage of disadvantaged pupils achieving a high score in grammar, punctuation and spelling"
-240,PTGPS_HIGH_NotFSM6CLA1A,"Percentage of non-disadvantaged pupils achieving a high score in grammar, punctuation and spelling"
-241,PTMAT_HIGH_L,Percentage of pupils with low prior attainment achieving a high score in maths [not populated in 2025]
-242,PTMAT_HIGH_M,Percentage of pupils with medium prior attainment achieving a high score in maths [not populated in 2025]
-243,PTMAT_HIGH_H,Percentage of pupils with high prior attainment achieving a high score in maths [not populated in 2025]
-244,PTMAT_HIGH_FSM6CLA1A,Percentage of disadvantaged pupils achieving a high score in maths
-245,PTMAT_HIGH_NotFSM6CLA1A,Percentage of non-disadvantaged pupils achieving a high score in maths
-246,PTWRITTA_HIGH_L,Percentage of pupils with low prior attainment working at greater depth in writing [not populated in 2025]
-247,PTWRITTA_HIGH_M,Percentage of pupils with medium prior attainment working at greater depth in writing [not populated in 2025]
-248,PTWRITTA_HIGH_H,Percentage of pupils with high prior attainment working at greater depth in writing [not populated in 2025]
-249,PTWRITTA_HIGH_FSM6CLA1A,Percentage of disadvantaged pupils working at greater depth in writing
-250,PTWRITTA_HIGH_NotFSM6CLA1A,Percentage of non-disadvantaged pupils working at greater depth in writing
-251,TEALGRP1,Number of eligible pupils with English as first language
-252,PTEALGRP1,Percentage of eligible pupils with English as first language
-253,TEALGRP3,Number of eligible pupils with unclassified language
-254,PTEALGRP3,Percentage of eligible pupils with unclassified language
-255,TSENELE,Number of eligible pupils with EHC plan
-256,PSENELE,Percentage of eligible pupils with EHC plan
-257,TSENELK,Number of eligible pupils with SEN support
-258,PSENELK,Percentage of eligible pupils with SEN support
-259,TSENELEK,Number of eligible pupils with SEN (EHC plan or SEN support)
-260,PSENELEK,Percentage of eligible pupils with SEN  (EHC plan or SEN support)
-261,TELIG_24,Number of eligible pupils 2024
-262,PTFSM6CLA1A_24,Percentage of key stage 2 disadvantaged pupils one year prior
-263,PTNOTFSM6CLA1A_24,Percentage of key stage 2 pupils who are not disadvantaged one year prior
-264,PTRWM_EXP_24,"Percentage of pupils reaching the expected standard in reading, writing and maths one year prior"
-265,PTRWM_HIGH_24,Percentage of pupils achieving a high score in reading and maths and working at greater depth in writing  one year prior
-266,PTRWM_EXP_FSM6CLA1A_24,"Percentage of disadvantaged pupils reaching the expected standard in reading, writing and maths one year prior"
-267,PTRWM_HIGH_FSM6CLA1A_24,Percentage of disadvantaged pupils achieving a high score in reading and maths and working at greater depth in writing one year prior
-268,PTRWM_EXP_NotFSM6CLA1A_24,"Percentage of non-disadvantaged pupils reaching the expected standard in reading, writing and maths one year prior"
-269,PTRWM_HIGH_NotFSM6CLA1A_24,Percentage of non-disadvantaged pupils achieving a high score in reading and maths and working at greater depth in writing one year prior
-270,READPROG_24,Reading progress measure - one year prior [not populated in 2025]
-271,READPROG_LOWER_24,Reading progress measure - lower confidence limit - one year prior [not populated in 2025]
-272,READPROG_UPPER_24,Reading progress measure - upper confidence limit - one year prior [not populated in 2025]
-273,WRITPROG_24,Writing progress measure - one year prior [not populated in 2025]
-274,WRITPROG_LOWER_24,Writing progress measure - lower confidence limit - one year prior [not populated in 2025]
-275,WRITPROG_UPPER_24,Writing progress measure - upper confidence limit - one year prior [not populated in 2025]
-276,MATPROG_24,Maths progress measure - one year prior [not populated in 2025]
-277,MATPROG_LOWER_24,Maths progress measure - lower confidence limit - one year prior [not populated in 2025]
-278,MATPROG_UPPER_24,Maths progress measure - upper confidence limit - one year prior [not populated in 2025]
-279,READ_AVERAGE_24,Average scaled score in reading - one year prior
-280,MAT_AVERAGE_24,Average scaled score in maths - one year prior
-281,TELIG_23,Number of eligible pupils 2023
-282,PTFSM6CLA1A_23,Percentage of key stage 2 disadvantaged pupils - two years prior
-283,PTNOTFSM6CLA1A_23,Percentage of key stage 2 pupils who are not disadvantaged - two years prior
-284,PTRWM_EXP_23,"Percentage of pupils reaching the expected standard in reading, writing and maths - two years prior"
-285,PTRWM_HIGH_23,Percentage of pupils achieving a high score in reading and maths and working at greater depth in writing - two years prior
-286,PTRWM_EXP_FSM6CLA1A_23,"Percentage of disadvantaged pupils reaching the expected standard in reading, writing and maths - two years prior"
-287,PTRWM_HIGH_FSM6CLA1A_23,Percentage of disadvantaged pupils achieving a high score in reading and maths and working at greater depth in writing - two years prior
-288,PTRWM_EXP_NotFSM6CLA1A_23,"Percentage of non-disadvantaged pupils reaching the expected standard in reading, writing and maths - two years prior"
-289,PTRWM_HIGH_NotFSM6CLA1A_23,Percentage of non-disadvantaged pupils achieving a high score in reading and maths and working at greater depth in writing - two years prior
-290,READPROG_23,Reading progress measure - two years prior
-291,READPROG_LOWER_23,Reading progress measure - lower confidence limit - two years prior
-292,READPROG_UPPER_23,Reading progress measure - upper confidence limit - two years prior
-293,WRITPROG_23,Writing progress measure - two years prior
-294,WRITPROG_LOWER_23,Writing progress measure - lower confidence limit - two years prior
-295,WRITPROG_UPPER_23,Writing progress measure - upper confidence limit -  two years prior
-296,MATPROG_23,Maths progress measure - two years prior
-297,MATPROG_LOWER_23,Maths progress measure - lower confidence limit - two years prior
-298,MATPROG_UPPER_23,Maths progress measure - upper confidence limit  - two years prior
-299,READ_AVERAGE_23,Average scaled score in reading - two years prior
-300,MAT_AVERAGE_23,Average scaled score in maths - two years prior
-301,TELIG_3YR,Total number of pupils at the end of Key Stage 2 over the past three years
-302,PTRWM_EXP_3YR,"Percentage of pupils reaching the expected standard in reading, writing and maths  - 3 year total"
-303,PTRWM_HIGH_3YR,Percentage of pupils achieving a high score in reading and maths and working at greater depth in writing  - 3 year total
-304,READ_AVERAGE_3YR,Average scaled score in reading - 3 year average
-305,MAT_AVERAGE_3YR,Average scaled score in maths - 3 year average
-306,READPROG_UNADJUSTED,Unadjusted reading progress measure [not populated in 2025]
-307,WRITPROG_UNADJUSTED,Unadjusted writing progress measure [not populated in 2025]
-308,MATPROG_UNADJUSTED,Unadjusted maths progress measure [not populated in 2025]
-309,READPROG_DESCR,Reading progress measure 'description' [not populated in 2025]
-310,WRITPROG_DESCR,Writing progress measure 'description' [not populated in 2025]
-311,MATPROG_DESCR,Maths progress measure 'description' [not populated in 2025]

data/meta/la_and_region_codes_meta.csv

@@ -1,154 +0,0 @@
-LEA,LA Name,REGION,REGION NAME
-841,Darlington,1,North East A
-840,County Durham,1,North East A
-805,Hartlepool,1,North East A
-806,Middlesbrough,1,North East A
-807,Redcar and Cleveland,1,North East A
-808,Stockton-on-Tees,1,North East A
-390,Gateshead,3,North East B
-391,Newcastle upon Tyne,3,North East B
-392,North Tyneside,3,North East B
-929,Northumberland,3,North East B
-393,South Tyneside,3,North East B
-394,Sunderland,3,North East B
-889,Blackburn with Darwen,6,North West A
-890,Blackpool,6,North West A
-942,Cumberland,6,North West A
-943,Westmorland and Furness ,6,North West A
-888,Lancashire,6,North West A
-350,Bolton,7,North West B
-351,Bury,7,North West B
-352,Manchester,7,North West B
-353,Oldham,7,North West B
-354,Rochdale,7,North West B
-355,Salford,7,North West B
-356,Stockport,7,North West B
-357,Tameside,7,North West B
-358,Trafford,7,North West B
-359,Wigan,7,North West B
-895,Cheshire East,9,North West C
-896,Cheshire West and Chester,9,North West C
-876,Halton,9,North West C
-340,Knowsley,9,North West C
-341,Liverpool,9,North West C
-343,Sefton,9,North West C
-342,St. Helens,9,North West C
-877,Warrington,9,North West C
-344,Wirral,9,North West C
-811,East Riding of Yorkshire,10,North Yorkshire and The Humber
-810,"Kingston Upon Hull, City of",10,North Yorkshire and The Humber
-812,North East Lincolnshire,10,North Yorkshire and The Humber
-813,North Lincolnshire,10,North Yorkshire and The Humber
-815,North Yorkshire,10,North Yorkshire and The Humber
-816,York,10,North Yorkshire and The Humber
-370,Barnsley,12,South and West Yorkshire
-380,Bradford,12,South and West Yorkshire
-381,Calderdale,12,South and West Yorkshire
-371,Doncaster,12,South and West Yorkshire
-382,Kirklees,12,South and West Yorkshire
-383,Leeds,12,South and West Yorkshire
-372,Rotherham,12,South and West Yorkshire
-373,Sheffield,12,South and West Yorkshire
-384,Wakefield,12,South and West Yorkshire
-831,Derby,14,East Midlands A
-830,Derbyshire,14,East Midlands A
-892,Nottingham,14,East Midlands A
-891,Nottinghamshire,14,East Midlands A
-856,Leicester,16,East Midlands B
-855,Leicestershire,16,East Midlands B
-925,Lincolnshire,16,East Midlands B
-940,North Northamptonshire,16,East Midlands B
-941,West Northamptonshire,16,East Midlands B
-857,Rutland,16,East Midlands B
-893,Shropshire,20,West Midlands A
-860,Staffordshire,20,West Midlands A
-861,Stoke-on-Trent,20,West Midlands A
-894,Telford and Wrekin,20,West Midlands A
-884,"Herefordshire, County of",22,West Midlands B
-885,Worcestershire,22,West Midlands B
-330,Birmingham,24,West Midlands C
-331,Coventry,24,West Midlands C
-332,Dudley,24,West Midlands C
-333,Sandwell,24,West Midlands C
-334,Solihull,24,West Midlands C
-335,Walsall,24,West Midlands C
-937,Warwickshire,24,West Midlands C
-336,Wolverhampton,24,West Midlands C
-822,Bedford,25,East of England A
-873,Cambridgeshire,25,East of England A
-823,Central Bedfordshire,25,East of England A
-919,Hertfordshire,25,East of England A
-821,Luton,25,East of England A
-874,Peterborough,25,East of England A
-881,Essex,27,East of England B
-926,Norfolk,27,East of England B
-882,Southend-on-Sea,27,East of England B
-935,Suffolk,27,East of England B
-883,Thurrock,27,East of England B
-202,Camden,31,London Central
-206,Islington,31,London Central
-207,Kensington and Chelsea,31,London Central
-208,Lambeth,31,London Central
-210,Southwark,31,London Central
-212,Wandsworth,31,London Central
-213,Westminster,31,London Central
-301,Barking and Dagenham,32,London East
-303,Bexley,32,London East
-201,City of London,32,London East
-203,Greenwich,32,London East
-204,Hackney,32,London East
-311,Havering,32,London East
-209,Lewisham,32,London East
-316,Newham,32,London East
-317,Redbridge,32,London East
-211,Tower Hamlets,32,London East
-302,Barnet,33,London North
-308,Enfield,33,London North
-309,Haringey,33,London North
-320,Waltham Forest,33,London North
-305,Bromley,34,London South
-306,Croydon,34,London South
-314,Kingston upon Thames,34,London South
-315,Merton,34,London South
-318,Richmond upon Thames,34,London South
-319,Sutton,34,London South
-304,Brent,35,London West
-307,Ealing,35,London West
-205,Hammersmith and Fulham,35,London West
-310,Harrow,35,London West
-312,Hillingdon,35,London West
-313,Hounslow,35,London West
-867,Bracknell Forest,36,South East A
-825,Buckinghamshire,36,South East A
-826,Milton Keynes,36,South East A
-931,Oxfordshire,36,South East A
-870,Reading,36,South East A
-871,Slough,36,South East A
-869,West Berkshire,36,South East A
-868,Windsor and Maidenhead,36,South East A
-872,Wokingham,36,South East A
-850,Hampshire,37,South East B
-921,Isle of Wight,37,South East B
-851,Portsmouth,37,South East B
-852,Southampton,37,South East B
-936,Surrey,38,South East C
-938,West Sussex,38,South East C
-846,Brighton and Hove,39,South East D
-845,East Sussex,39,South East D
-886,Kent,39,South East D
-887,Medway,39,South East D
-839,"Bournemouth, Christchurch and Poole",43,South West A
-908,Cornwall,43,South West A
-878,Devon,43,South West A
-838,Dorset,43,South West A
-420,Isles of Scilly,43,South West A
-879,Plymouth,43,South West A
-933,Somerset,43,South West A
-880,Torbay,43,South West A
-800,Bath and North East Somerset,45,South West B
-801,"Bristol, City of",45,South West B
-916,Gloucestershire,45,South West B
-802,North Somerset,45,South West B
-803,South Gloucestershire,45,South West B
-866,Swindon,45,South West B
-865,Wiltshire,45,South West B

docker-compose.portainer.yml

@@ -7,9 +7,7 @@
 #   ADMIN_API_KEY          — Backend admin API key
 #   TYPESENSE_API_KEY      — Typesense admin API key
 #   TYPESENSE_SEARCH_KEY   — Typesense search-only key (exposed to frontend)
-#   AIRFLOW_ADMIN_USER    — Airflow admin username (password auto-generated, see api-server logs)
+#   AIRFLOW_ADMIN_USER     — Airflow admin username (password auto-generated, see api-server logs)
-#   KESTRA_USER            — Kestra UI username (optional)
-#   KESTRA_PASSWORD        — Kestra UI password (optional)
 
 services:
 
@@ -103,87 +101,6 @@ services:
       retries: 5
       start_period: 10s
 
-  # ── Kestra — workflow orchestrator (legacy, kept during migration) ────
-  kestra:
-    image: kestra/kestra:latest
-    container_name: schoolcompare_kestra
-    command: server standalone
-    ports:
-      - "8090:8080"
-    volumes:
-      - kestra_storage:/app/storage
-    environment:
-      KESTRA_CONFIGURATION: |
-        datasources:
-          postgres:
-            url: jdbc:postgresql://sc_database:5432/kestra
-            driverClassName: org.postgresql.Driver
-            username: ${DB_USERNAME}
-            password: ${DB_PASSWORD}
-        kestra:
-          repository:
-            type: postgres
-          queue:
-            type: postgres
-          storage:
-            type: local
-            local:
-              base-path: /app/storage
-    depends_on:
-      sc_database:
-        condition: service_healthy
-    networks:
-      - backend
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD-SHELL", "curl -sf http://localhost:8081/health | grep -q '\"status\":\"UP\"'"]
-      interval: 15s
-      timeout: 10s
-      retries: 10
-      start_period: 60s
-
-  # ── Kestra init (legacy, kept during migration) ──────────────────────
-  kestra-init:
-    image: privaterepo.sitaru.org/tudor/school_compare-kestra-init:latest
-    container_name: schoolcompare_kestra_init
-    environment:
-      KESTRA_URL: http://kestra:8080
-      KESTRA_USER: ${KESTRA_USER:-}
-      KESTRA_PASSWORD: ${KESTRA_PASSWORD:-}
-    depends_on:
-      kestra:
-        condition: service_healthy
-    networks:
-      - backend
-    restart: "no"
-
-  # ── Data integrator (legacy, kept during migration) ──────────────────
-  integrator:
-    image: privaterepo.sitaru.org/tudor/school_compare-integrator:latest
-    container_name: schoolcompare_integrator
-    ports:
-      - "8001:8001"
-    environment:
-      DATABASE_URL: postgresql://${DB_USERNAME}:${DB_PASSWORD}@sc_database:5432/${DB_DATABASE_NAME}
-      DATA_DIR: /data
-      BACKEND_URL: http://backend:80
-      ADMIN_API_KEY: ${ADMIN_API_KEY:-changeme}
-      PYTHONUNBUFFERED: 1
-    volumes:
-      - supplementary_data:/data
-    depends_on:
-      sc_database:
-        condition: service_healthy
-    networks:
-      - backend
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8001/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 15s
-
   # ── Airflow API Server + UI ───────────────────────────────────────────
   airflow-api-server:
     image: privaterepo.sitaru.org/tudor/school_compare-pipeline:latest
@@ -282,7 +199,5 @@ networks:
 
 volumes:
   postgres_data:
-  kestra_storage:
-  supplementary_data:
   typesense_data:
   airflow_logs:

docker-compose.yml

@@ -9,6 +9,7 @@ services:
       POSTGRES_USER: schoolcompare
       POSTGRES_PASSWORD: schoolcompare
       POSTGRES_DB: schoolcompare
+      POSTGRES_INITDB_ARGS: "--locale=C --encoding=UTF8"
     volumes:
       - postgres_data:/var/lib/postgresql/data
     ports:
@@ -119,6 +120,8 @@ services:
       PG_DATABASE: schoolcompare
       TYPESENSE_URL: http://typesense:8108
       TYPESENSE_API_KEY: ${TYPESENSE_API_KEY:-changeme}
+      BACKEND_URL: http://backend:80
+      ADMIN_API_KEY: ${ADMIN_API_KEY:-changeme}
     volumes:
 
     depends_on:

frontend/favicon.svg

@@ -1,6 +0,0 @@
-<svg viewBox="0 0 40 40" fill="none" xmlns="http://www.w3.org/2000/svg">
-  <rect width="40" height="40" rx="8" fill="#1a1612"/>
-  <circle cx="20" cy="20" r="14" stroke="#e07256" stroke-width="2"/>
-  <path d="M20 8L20 32M12 14L28 14M10 20L30 20M12 26L28 26" stroke="#e07256" stroke-width="1.5" stroke-linecap="round"/>
-  <circle cx="20" cy="20" r="3" fill="#e07256"/>
-</svg>

frontend/index.html

@@ -1,663 +0,0 @@
-<!doctype html>
-<html lang="en">
-    <head>
-        <meta charset="UTF-8" />
-        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-        <title>SchoolCompare | Compare Primary School Performance</title>
-
-        <!-- Primary Meta Tags -->
-        <meta
-            name="description"
-            content="Compare primary school KS2 performance across England. Search, filter and compare Reading, Writing and Maths results for thousands of schools."
-        />
-        <meta
-            name="keywords"
-            content="school comparison, KS2 results, primary school performance, England schools, SATs results"
-        />
-        <meta name="author" content="SchoolCompare" />
-        <meta name="robots" content="index, follow" />
-
-        <!-- Analytics -->
-        <script
-            defer
-            src="https://analytics.schoolcompare.co.uk/script.js"
-            data-website-id="d7fb0c95-bb6c-4336-8209-bd10077e50dd"
-        ></script>
-
-        <!-- Favicon -->
-        <link rel="icon" type="image/svg+xml" href="/favicon.svg" />
-
-        <!-- Canonical -->
-        <link rel="canonical" href="https://schoolcompare.co.uk/" />
-
-        <!-- Open Graph / Facebook -->
-        <meta property="og:type" content="website" />
-        <meta property="og:url" content="https://schoolcompare.co.uk/" />
-        <meta
-            property="og:title"
-            content="SchoolCompare | Compare Primary School Performance"
-        />
-        <meta
-            property="og:description"
-            content="Compare primary school KS2 performance across England. Search and compare Reading, Writing and Maths results."
-        />
-        <meta property="og:site_name" content="SchoolCompare" />
-
-        <!-- Twitter -->
-        <meta name="twitter:card" content="summary" />
-        <meta name="twitter:url" content="https://schoolcompare.co.uk/" />
-        <meta
-            name="twitter:title"
-            content="SchoolCompare | Compare Primary School Performance"
-        />
-        <meta
-            name="twitter:description"
-            content="Compare primary school KS2 performance across England."
-        />
-
-        <!-- JSON-LD Structured Data -->
-        <script type="application/ld+json">
-            {
-                "@context": "https://schema.org",
-                "@type": "WebApplication",
-                "name": "SchoolCompare",
-                "url": "https://schoolcompare.co.uk",
-                "description": "Compare primary school KS2 performance across England",
-                "applicationCategory": "EducationalApplication",
-                "operatingSystem": "Web",
-                "offers": {
-                    "@type": "Offer",
-                    "price": "0",
-                    "priceCurrency": "GBP"
-                },
-                "author": {
-                    "@type": "Organization",
-                    "name": "SchoolCompare",
-                    "url": "https://schoolcompare.co.uk"
-                }
-            }
-        </script>
-
-        <link rel="preconnect" href="https://fonts.googleapis.com" />
-        <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
-        <link
-            href="https://fonts.googleapis.com/css2?family=DM+Sans:ital,opsz,wght@0,9..40,400;0,9..40,500;0,9..40,600;0,9..40,700&family=Playfair+Display:wght@600;700&display=swap"
-            rel="stylesheet"
-        />
-        <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
-        <!-- Leaflet Map Library -->
-        <link
-            rel="stylesheet"
-            href="https://unpkg.com/leaflet@1.9.4/dist/leaflet.css"
-            integrity="sha256-p4NxAoJBhIIN+hmNHrzRCf9tD/miZyoHS5obTRR9BMY="
-            crossorigin=""
-        />
-        <script
-            src="https://unpkg.com/leaflet@1.9.4/dist/leaflet.js"
-            integrity="sha256-20nQCchB9co0qIjJZRGuk2/Z9VM+kNiyxNV1lvTlZBo="
-            crossorigin=""
-        ></script>
-        <link rel="stylesheet" href="/static/styles.css" />
-    </head>
-    <body>
-        <div class="noise-overlay"></div>
-
-        <header class="header">
-            <div class="header-content">
-                <a href="/" class="logo">
-                    <div class="logo-icon">
-                        <svg
-                            viewBox="0 0 40 40"
-                            fill="none"
-                            xmlns="http://www.w3.org/2000/svg"
-                        >
-                            <circle
-                                cx="20"
-                                cy="20"
-                                r="18"
-                                stroke="currentColor"
-                                stroke-width="2"
-                            />
-                            <path
-                                d="M20 8L20 32M12 14L28 14M10 20L30 20M12 26L28 26"
-                                stroke="currentColor"
-                                stroke-width="1.5"
-                                stroke-linecap="round"
-                            />
-                            <circle cx="20" cy="20" r="4" fill="currentColor" />
-                        </svg>
-                    </div>
-                    <div class="logo-text">
-                        <span class="logo-title">SchoolCompare</span>
-                        <span class="logo-subtitle">schoolcompare.co.uk</span>
-                    </div>
-                </a>
-                <nav class="nav">
-                    <a href="/" class="nav-link active" data-view="home"
-                        >Home</a
-                    >
-                    <a href="/compare" class="nav-link" data-view="compare"
-                        >Compare</a
-                    >
-                    <a href="/rankings" class="nav-link" data-view="rankings"
-                        >Rankings</a
-                    >
-                </nav>
-            </div>
-        </header>
-
-        <main class="main">
-            <!-- Home View -->
-            <section id="home-view" class="view active">
-                <div class="hero">
-                    <h1 class="hero-title">
-                        Compare Primary School Performance
-                    </h1>
-                    <p class="hero-subtitle">
-                        Search and compare KS2 results across England's primary
-                        schools
-                    </p>
-                </div>
-
-                <div class="search-section">
-                    <div class="search-mode-toggle">
-                        <button class="search-mode-btn active" data-mode="name">
-                            <svg
-                                viewBox="0 0 24 24"
-                                fill="none"
-                                stroke="currentColor"
-                                stroke-width="2"
-                                width="16"
-                                height="16"
-                            >
-                                <circle cx="11" cy="11" r="8" />
-                                <path d="M21 21l-4.35-4.35" />
-                            </svg>
-                            Find by Name
-                        </button>
-                        <button class="search-mode-btn" data-mode="location">
-                            <svg
-                                viewBox="0 0 24 24"
-                                fill="none"
-                                stroke="currentColor"
-                                stroke-width="2"
-                                width="16"
-                                height="16"
-                            >
-                                <path
-                                    d="M21 10c0 7-9 13-9 13s-9-6-9-13a9 9 0 0 1 18 0z"
-                                />
-                                <circle cx="12" cy="10" r="3" />
-                            </svg>
-                            Find by Location
-                        </button>
-                    </div>
-
-                    <div id="name-search-panel" class="search-panel active">
-                        <div class="search-container">
-                            <input
-                                type="text"
-                                id="school-search"
-                                class="search-input"
-                                placeholder="Search primary schools by name..."
-                            />
-                            <div class="search-icon">
-                                <svg
-                                    viewBox="0 0 24 24"
-                                    fill="none"
-                                    stroke="currentColor"
-                                    stroke-width="2"
-                                >
-                                    <circle cx="11" cy="11" r="8" />
-                                    <path d="M21 21l-4.35-4.35" />
-                                </svg>
-                            </div>
-                        </div>
-                        <div class="filter-row">
-                            <select
-                                id="local-authority-filter"
-                                class="filter-select"
-                            >
-                                <option value="">All Areas</option>
-                            </select>
-                            <select id="type-filter" class="filter-select">
-                                <option value="">All School Types</option>
-                            </select>
-                        </div>
-                    </div>
-
-                    <div id="location-search-panel" class="search-panel">
-                        <div class="location-input-group">
-                            <input
-                                type="text"
-                                id="postcode-search"
-                                class="search-input postcode-input"
-                                placeholder="Enter postcode..."
-                            />
-                            <select
-                                id="radius-select"
-                                class="filter-select radius-select"
-                            >
-                                <option value="0.5" selected>1/2 mile</option>
-                                <option value="1">1 mile</option>
-                                <option value="2">2 miles</option>
-                            </select>
-                            <select
-                                id="type-filter-location"
-                                class="filter-select"
-                            >
-                                <option value="">All School Types</option>
-                            </select>
-                            <button
-                                id="location-search-btn"
-                                class="btn btn-primary location-btn"
-                            >
-                                Find Nearby
-                            </button>
-                        </div>
-                    </div>
-                </div>
-
-                <div class="view-toggle" id="view-toggle" style="display: none">
-                    <button class="view-toggle-btn active" data-view="list">
-                        <svg
-                            viewBox="0 0 24 24"
-                            fill="none"
-                            stroke="currentColor"
-                            stroke-width="2"
-                            width="16"
-                            height="16"
-                        >
-                            <line x1="8" y1="6" x2="21" y2="6" />
-                            <line x1="8" y1="12" x2="21" y2="12" />
-                            <line x1="8" y1="18" x2="21" y2="18" />
-                            <line x1="3" y1="6" x2="3.01" y2="6" />
-                            <line x1="3" y1="12" x2="3.01" y2="12" />
-                            <line x1="3" y1="18" x2="3.01" y2="18" />
-                        </svg>
-                        List
-                    </button>
-                    <button class="view-toggle-btn" data-view="map">
-                        <svg
-                            viewBox="0 0 24 24"
-                            fill="none"
-                            stroke="currentColor"
-                            stroke-width="2"
-                            width="16"
-                            height="16"
-                        >
-                            <path
-                                d="M21 10c0 7-9 13-9 13s-9-6-9-13a9 9 0 0 1 18 0z"
-                            />
-                            <circle cx="12" cy="10" r="3" />
-                        </svg>
-                        Map
-                    </button>
-                </div>
-
-                <div class="results-container" id="results-container">
-                    <div class="results-map" id="results-map"></div>
-                    <div class="schools-grid" id="schools-grid">
-                        <!-- School cards populated by JS -->
-                    </div>
-                </div>
-            </section>
-
-            <!-- Compare View -->
-            <section id="compare-view" class="view">
-                <div class="compare-header">
-                    <h2 class="section-title">Compare Primary Schools</h2>
-                    <p class="section-subtitle">
-                        Select schools to compare their KS2 performance over
-                        time
-                    </p>
-                </div>
-
-                <div class="compare-search-section">
-                    <input
-                        type="text"
-                        id="compare-search"
-                        class="search-input"
-                        placeholder="Add a school to compare..."
-                    />
-                    <div id="compare-results" class="compare-results"></div>
-                </div>
-
-                <div class="selected-schools" id="selected-schools">
-                    <div class="empty-selection">
-                        <div class="empty-icon">
-                            <svg
-                                viewBox="0 0 48 48"
-                                fill="none"
-                                stroke="currentColor"
-                                stroke-width="1.5"
-                            >
-                                <rect
-                                    x="6"
-                                    y="10"
-                                    width="36"
-                                    height="28"
-                                    rx="2"
-                                />
-                                <path d="M6 18h36" />
-                                <circle
-                                    cx="14"
-                                    cy="14"
-                                    r="2"
-                                    fill="currentColor"
-                                />
-                                <circle
-                                    cx="22"
-                                    cy="14"
-                                    r="2"
-                                    fill="currentColor"
-                                />
-                            </svg>
-                        </div>
-                        <p>Search and add schools to compare</p>
-                    </div>
-                </div>
-
-                <div
-                    class="charts-section"
-                    id="charts-section"
-                    style="display: none"
-                >
-                    <div class="metric-selector">
-                        <label>Select KS2 Metric:</label>
-                        <select id="metric-select" class="filter-select">
-                            <optgroup label="Expected Standard">
-                                <option value="rwm_expected_pct">
-                                    Reading, Writing & Maths Combined %
-                                </option>
-                                <option value="reading_expected_pct">
-                                    Reading Expected %
-                                </option>
-                                <option value="writing_expected_pct">
-                                    Writing Expected %
-                                </option>
-                                <option value="maths_expected_pct">
-                                    Maths Expected %
-                                </option>
-                                <option value="gps_expected_pct">
-                                    GPS Expected %
-                                </option>
-                                <option value="science_expected_pct">
-                                    Science Expected %
-                                </option>
-                            </optgroup>
-                            <optgroup label="Higher Standard">
-                                <option value="rwm_high_pct">
-                                    RWM Combined Higher %
-                                </option>
-                                <option value="reading_high_pct">
-                                    Reading Higher %
-                                </option>
-                                <option value="writing_high_pct">
-                                    Writing Higher %
-                                </option>
-                                <option value="maths_high_pct">
-                                    Maths Higher %
-                                </option>
-                                <option value="gps_high_pct">
-                                    GPS Higher %
-                                </option>
-                            </optgroup>
-                            <optgroup label="Progress Scores">
-                                <option value="reading_progress">
-                                    Reading Progress
-                                </option>
-                                <option value="writing_progress">
-                                    Writing Progress
-                                </option>
-                                <option value="maths_progress">
-                                    Maths Progress
-                                </option>
-                            </optgroup>
-                            <optgroup label="Average Scores">
-                                <option value="reading_avg_score">
-                                    Reading Avg Score
-                                </option>
-                                <option value="maths_avg_score">
-                                    Maths Avg Score
-                                </option>
-                                <option value="gps_avg_score">
-                                    GPS Avg Score
-                                </option>
-                            </optgroup>
-                            <optgroup label="Gender Performance">
-                                <option value="rwm_expected_boys_pct">
-                                    RWM Expected % (Boys)
-                                </option>
-                                <option value="rwm_expected_girls_pct">
-                                    RWM Expected % (Girls)
-                                </option>
-                                <option value="rwm_high_boys_pct">
-                                    RWM Higher % (Boys)
-                                </option>
-                                <option value="rwm_high_girls_pct">
-                                    RWM Higher % (Girls)
-                                </option>
-                            </optgroup>
-                            <optgroup label="Equity (Disadvantaged)">
-                                <option value="rwm_expected_disadvantaged_pct">
-                                    RWM Expected % (Disadvantaged)
-                                </option>
-                                <option
-                                    value="rwm_expected_non_disadvantaged_pct"
-                                >
-                                    RWM Expected % (Non-Disadvantaged)
-                                </option>
-                                <option value="disadvantaged_gap">
-                                    Disadvantaged Gap vs National
-                                </option>
-                            </optgroup>
-                            <optgroup label="School Context">
-                                <option value="disadvantaged_pct">
-                                    % Disadvantaged Pupils
-                                </option>
-                                <option value="eal_pct">% EAL Pupils</option>
-                                <option value="sen_support_pct">
-                                    % SEN Support
-                                </option>
-                                <option value="stability_pct">
-                                    % Pupil Stability
-                                </option>
-                            </optgroup>
-                            <optgroup label="3-Year Trends">
-                                <option value="rwm_expected_3yr_pct">
-                                    RWM Expected % (3-Year Avg)
-                                </option>
-                                <option value="reading_avg_3yr">
-                                    Reading Score (3-Year Avg)
-                                </option>
-                                <option value="maths_avg_3yr">
-                                    Maths Score (3-Year Avg)
-                                </option>
-                            </optgroup>
-                        </select>
-                    </div>
-
-                    <div class="chart-container">
-                        <canvas id="comparison-chart"></canvas>
-                    </div>
-
-                    <div class="data-table-container">
-                        <table class="data-table" id="comparison-table">
-                            <thead>
-                                <tr id="table-header"></tr>
-                            </thead>
-                            <tbody id="table-body"></tbody>
-                        </table>
-                    </div>
-                </div>
-            </section>
-
-            <!-- Rankings View -->
-            <section id="rankings-view" class="view">
-                <div class="rankings-header">
-                    <h2 class="section-title">Primary School Rankings</h2>
-                    <p class="section-subtitle">
-                        Top performing primary schools ranked by KS2 metric
-                    </p>
-                </div>
-
-                <div class="rankings-controls">
-                    <select id="ranking-area" class="filter-select">
-                        <option value="">All Areas</option>
-                        <!-- Populated by JS -->
-                    </select>
-                    <select id="ranking-metric" class="filter-select">
-                        <optgroup label="Expected Standard">
-                            <option value="rwm_expected_pct">
-                                Reading, Writing & Maths Combined %
-                            </option>
-                            <option value="reading_expected_pct">
-                                Reading Expected %
-                            </option>
-                            <option value="writing_expected_pct">
-                                Writing Expected %
-                            </option>
-                            <option value="maths_expected_pct">
-                                Maths Expected %
-                            </option>
-                            <option value="gps_expected_pct">
-                                GPS Expected %
-                            </option>
-                            <option value="science_expected_pct">
-                                Science Expected %
-                            </option>
-                        </optgroup>
-                        <optgroup label="Higher Standard">
-                            <option value="rwm_high_pct">
-                                RWM Combined Higher %
-                            </option>
-                            <option value="reading_high_pct">
-                                Reading Higher %
-                            </option>
-                            <option value="writing_high_pct">
-                                Writing Higher %
-                            </option>
-                            <option value="maths_high_pct">
-                                Maths Higher %
-                            </option>
-                            <option value="gps_high_pct">GPS Higher %</option>
-                        </optgroup>
-                        <optgroup label="Progress Scores">
-                            <option value="reading_progress">
-                                Reading Progress
-                            </option>
-                            <option value="writing_progress">
-                                Writing Progress
-                            </option>
-                            <option value="maths_progress">
-                                Maths Progress
-                            </option>
-                        </optgroup>
-                        <optgroup label="Average Scores">
-                            <option value="reading_avg_score">
-                                Reading Avg Score
-                            </option>
-                            <option value="maths_avg_score">
-                                Maths Avg Score
-                            </option>
-                            <option value="gps_avg_score">GPS Avg Score</option>
-                        </optgroup>
-                        <optgroup label="Gender Performance">
-                            <option value="rwm_expected_boys_pct">
-                                RWM Expected % (Boys)
-                            </option>
-                            <option value="rwm_expected_girls_pct">
-                                RWM Expected % (Girls)
-                            </option>
-                            <option value="rwm_high_boys_pct">
-                                RWM Higher % (Boys)
-                            </option>
-                            <option value="rwm_high_girls_pct">
-                                RWM Higher % (Girls)
-                            </option>
-                        </optgroup>
-                        <optgroup label="Equity (Disadvantaged)">
-                            <option value="rwm_expected_disadvantaged_pct">
-                                RWM Expected % (Disadvantaged)
-                            </option>
-                            <option value="rwm_expected_non_disadvantaged_pct">
-                                RWM Expected % (Non-Disadvantaged)
-                            </option>
-                        </optgroup>
-                        <optgroup label="3-Year Trends">
-                            <option value="rwm_expected_3yr_pct">
-                                RWM Expected % (3-Year Avg)
-                            </option>
-                        </optgroup>
-                    </select>
-                    <select id="ranking-year" class="filter-select">
-                        <!-- Populated by JS -->
-                    </select>
-                </div>
-
-                <div class="rankings-list" id="rankings-list">
-                    <!-- Rankings populated by JS -->
-                </div>
-            </section>
-        </main>
-
-        <!-- School Detail Modal -->
-        <div class="modal" id="school-modal">
-            <div class="modal-backdrop"></div>
-            <div class="modal-content">
-                <button class="modal-close" id="modal-close">
-                    <svg
-                        viewBox="0 0 24 24"
-                        fill="none"
-                        stroke="currentColor"
-                        stroke-width="2"
-                    >
-                        <path d="M18 6L6 18M6 6l12 12" />
-                    </svg>
-                </button>
-                <div class="modal-header">
-                    <button
-                        class="btn btn-primary modal-compare-btn"
-                        id="add-to-compare"
-                    >
-                        Add to Compare
-                    </button>
-                    <h2 id="modal-school-name"></h2>
-                    <div class="modal-meta" id="modal-meta"></div>
-                    <div class="modal-details" id="modal-details"></div>
-                </div>
-                <div class="modal-body">
-                    <div class="modal-chart-container">
-                        <canvas id="school-detail-chart"></canvas>
-                    </div>
-                    <div class="modal-stats" id="modal-stats"></div>
-                    <div class="modal-map-container" id="modal-map-container">
-                        <h4>Location</h4>
-                        <div class="modal-map" id="modal-map"></div>
-                    </div>
-                </div>
-            </div>
-        </div>
-
-        <footer class="footer">
-            <div class="footer-content">
-                <div class="footer-contact">
-                    <a href="mailto:contact@schoolcompare.co.uk">Contact Us</a>
-                </div>
-                <div class="footer-source">
-                    <p>
-                        Data source:
-                        <a
-                            href="https://www.compare-school-performance.service.gov.uk/"
-                            target="_blank"
-                            >UK Government - Compare School Performance</a
-                        >
-                    </p>
-                </div>
-            </div>
-        </footer>
-
-        <script src="/static/app.js"></script>
-    </body>
-</html>

frontend/robots.txt

@@ -1,8 +0,0 @@
-User-agent: *
-Allow: /
-Allow: /compare
-Allow: /rankings
-
-Disallow: /api/
-
-Sitemap: https://schoolcompare.co.uk/sitemap.xml

frontend/sitemap.xml

@@ -1,18 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
-  <url>
-    <loc>https://schoolcompare.co.uk/</loc>
-    <changefreq>weekly</changefreq>
-    <priority>1.0</priority>
-  </url>
-  <url>
-    <loc>https://schoolcompare.co.uk/compare</loc>
-    <changefreq>weekly</changefreq>
-    <priority>0.8</priority>
-  </url>
-  <url>
-    <loc>https://schoolcompare.co.uk/rankings</loc>
-    <changefreq>weekly</changefreq>
-    <priority>0.8</priority>
-  </url>
-</urlset>

integrator/Dockerfile

@@ -1,15 +0,0 @@
-FROM python:3.12-slim
-
-WORKDIR /app
-
-# Install dependencies
-COPY requirements.txt .
-RUN apt-get update && apt-get install -y --no-install-recommends curl && rm -rf /var/lib/apt/lists/*
-
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy application code
-COPY scripts/ ./scripts/
-COPY server.py .
-
-CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8001"]

integrator/Dockerfile.init

@@ -1,6 +0,0 @@
-FROM alpine:3.19
-RUN apk add --no-cache curl
-COPY flows/ /flows/
-COPY docker/kestra-init.sh /kestra-init.sh
-RUN chmod +x /kestra-init.sh
-CMD ["/kestra-init.sh"]

integrator/docker/kestra-init.sh

@@ -1,59 +0,0 @@
-#!/bin/sh
-set -e
-
-KESTRA_URL="${KESTRA_URL:-http://kestra:8080}"
-MAX_WAIT=120
-
-# Basic auth — set KESTRA_USER / KESTRA_PASSWORD if authentication is enabled
-AUTH=""
-if [ -n "$KESTRA_USER" ] && [ -n "$KESTRA_PASSWORD" ]; then
-  AUTH="-u ${KESTRA_USER}:${KESTRA_PASSWORD}"
-fi
-
-echo "Waiting for Kestra API at ${KESTRA_URL}..."
-elapsed=0
-until curl -sf $AUTH "${KESTRA_URL}/api/v1/flows/search" > /dev/null 2>&1; do
-  if [ "$elapsed" -ge "$MAX_WAIT" ]; then
-    echo "ERROR: Kestra API not reachable after ${MAX_WAIT}s"
-    exit 1
-  fi
-  sleep 5
-  elapsed=$((elapsed + 5))
-done
-echo "Kestra API is ready."
-
-echo "Importing flows..."
-
-for f in /flows/*.yml; do
-  name="$(basename "$f")"
-  echo "  -> $name"
-
-  http_code=$(curl -s $AUTH -o /tmp/kestra_resp -w "%{http_code}" \
-    -X POST "${KESTRA_URL}/api/v1/flows" \
-    -H "Content-Type: application/x-yaml" \
-    --data-binary "@${f}")
-
-  if [ "$http_code" = "200" ] || [ "$http_code" = "201" ]; then
-    echo "     created"
-  elif [ "$http_code" = "409" ]; then
-    ns=$(grep '^namespace:' "$f" | awk '{print $2}')
-    id=$(grep '^id:'        "$f" | awk '{print $2}')
-    http_code2=$(curl -s $AUTH -o /tmp/kestra_resp -w "%{http_code}" \
-      -X PUT "${KESTRA_URL}/api/v1/flows/${ns}/${id}" \
-      -H "Content-Type: application/x-yaml" \
-      --data-binary "@${f}")
-    if [ "$http_code2" = "200" ] || [ "$http_code2" = "201" ]; then
-      echo "     updated"
-    else
-      echo "     ERROR updating $name: HTTP $http_code2"
-      cat /tmp/kestra_resp; echo
-      exit 1
-    fi
-  else
-    echo "     ERROR importing $name: HTTP $http_code"
-    cat /tmp/kestra_resp; echo
-    exit 1
-  fi
-done
-
-echo "All flows imported."

integrator/flows/admissions.yml

@@ -1,26 +0,0 @@
-id: admissions-annual-update
-namespace: schoolcompare.data
-description: Download and load school admissions data via EES API
-
-triggers:
-  - id: annual-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 4 1 7 *"   # 1 July annually at 04:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/admissions?action=download
-    method: POST
-    timeout: PT20M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/admissions?action=load
-    method: POST
-    timeout: PT30M
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT15M

integrator/flows/census.yml

@@ -1,26 +0,0 @@
-id: census-annual-update
-namespace: schoolcompare.data
-description: Download and load School Census (SPC) data via EES API
-
-triggers:
-  - id: annual-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 4 1 9 *"   # 1 September annually at 04:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/census?action=download
-    method: POST
-    timeout: PT20M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/census?action=load
-    method: POST
-    timeout: PT30M
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT15M

integrator/flows/finance.yml

@@ -1,26 +0,0 @@
-id: finance-annual-update
-namespace: schoolcompare.data
-description: Fetch FBIT financial benchmarking data from DfE API for all schools
-
-triggers:
-  - id: annual-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 4 1 12 *"   # 1 December annually at 04:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/finance?action=download
-    method: POST
-    timeout: PT120M   # Fetches per-school from API — ~20k schools
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/finance?action=load
-    method: POST
-    timeout: PT30M
-
-retry:
-  type: constant
-  maxAttempts: 2
-  interval: PT30M

integrator/flows/gias.yml

@@ -1,31 +0,0 @@
-id: gias-weekly-update
-namespace: schoolcompare.data
-description: Download and load GIAS (Get Information About Schools) bulk CSV
-
-triggers:
-  - id: weekly-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 3 * * 0"   # Every Sunday at 03:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/gias?action=download
-    method: POST
-    timeout: PT30M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/gias?action=load
-    method: POST
-    timeout: PT30M
-
-errors:
-  - id: notify-failure
-    type: io.kestra.plugin.core.log.Log
-    message: "GIAS update FAILED: {{ error.message }}"
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT10M

integrator/flows/idaci.yml

@@ -1,26 +0,0 @@
-id: idaci-annual-check
-namespace: schoolcompare.data
-description: Download IoD2019 IDACI file and compute deprivation scores for all schools
-
-triggers:
-  - id: annual-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 5 1 1 *"   # 1 January annually at 05:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/idaci?action=download
-    method: POST
-    timeout: PT10M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/idaci?action=load
-    method: POST
-    timeout: PT60M
-
-retry:
-  type: constant
-  maxAttempts: 2
-  interval: PT30M

integrator/flows/ks2.yml

@@ -1,23 +0,0 @@
-id: ks2-reimport
-namespace: schoolcompare.data
-description: Re-import KS2 attainment data from bundled CSV files (use after DB wipe)
-
-# No scheduled trigger — run manually from the Kestra UI when needed.
-
-tasks:
-  - id: reimport
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/ks2?action=load
-    method: POST
-    allowFailed: false
-    timeout: PT30S   # fire-and-forget; backend runs migration in background
-
-errors:
-  - id: notify-failure
-    type: io.kestra.plugin.core.log.Log
-    message: "KS2 re-import FAILED: {{ error.message }}"
-
-retry:
-  type: constant
-  maxAttempts: 2
-  interval: PT5M

integrator/flows/ofsted.yml

@@ -1,33 +0,0 @@
-id: ofsted-monthly-update
-namespace: schoolcompare.data
-description: Download and load Ofsted Monthly Management Information CSV
-
-triggers:
-  - id: monthly-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 2 1 * *"   # 1st of each month at 02:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/ofsted?action=download
-    method: POST
-    allowFailed: false
-    timeout: PT10M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/ofsted?action=load
-    method: POST
-    allowFailed: false
-    timeout: PT30M
-
-errors:
-  - id: notify-failure
-    type: io.kestra.plugin.core.log.Log
-    message: "Ofsted update FAILED: {{ error.message }}"
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT10M

integrator/flows/parent_view.yml

@@ -1,31 +0,0 @@
-id: parent-view-monthly-check
-namespace: schoolcompare.data
-description: Download and load Ofsted Parent View open data (released ~3x/year)
-
-triggers:
-  - id: monthly-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 3 1 * *"   # 1st of each month at 03:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/parent_view?action=download
-    method: POST
-    timeout: PT10M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/parent_view?action=load
-    method: POST
-    timeout: PT20M
-
-errors:
-  - id: notify-failure
-    type: io.kestra.plugin.core.log.Log
-    message: "Parent View update FAILED: {{ error.message }}"
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT10M

integrator/flows/phonics.yml

@@ -1,26 +0,0 @@
-id: phonics-annual-update
-namespace: schoolcompare.data
-description: Download and load Phonics Screening Check data via EES API
-
-triggers:
-  - id: annual-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 5 1 9 *"   # 1 September annually at 05:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/phonics?action=download
-    method: POST
-    timeout: PT20M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/phonics?action=load
-    method: POST
-    timeout: PT30M
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT15M

integrator/flows/sen_detail.yml

@@ -1,26 +0,0 @@
-id: sen-detail-annual-update
-namespace: schoolcompare.data
-description: Download and load SEN primary need breakdown via EES API
-
-triggers:
-  - id: annual-schedule
-    type: io.kestra.plugin.core.trigger.Schedule
-    cron: "0 4 15 9 *"   # 15 September annually at 04:00
-
-tasks:
-  - id: download
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/sen_detail?action=download
-    method: POST
-    timeout: PT20M
-
-  - id: load
-    type: io.kestra.plugin.core.http.Request
-    uri: http://integrator:8001/run/sen_detail?action=load
-    method: POST
-    timeout: PT30M
-
-retry:
-  type: constant
-  maxAttempts: 3
-  interval: PT15M

integrator/requirements.txt

@@ -1,7 +0,0 @@
-fastapi==0.115.0
-uvicorn[standard]==0.30.6
-requests==2.32.3
-pandas==2.2.3
-openpyxl==3.1.5
-psycopg2-binary==2.9.9
-sqlalchemy==2.0.35

integrator/scripts/config.py

@@ -1,14 +0,0 @@
-"""Configuration for the data integrator."""
-import os
-from pathlib import Path
-
-DATABASE_URL = os.environ.get(
-    "DATABASE_URL",
-    "postgresql://schoolcompare:schoolcompare@db:5432/schoolcompare",
-)
-
-DATA_DIR = Path(os.environ.get("DATA_DIR", "/data"))
-SUPPLEMENTARY_DIR = DATA_DIR / "supplementary"
-
-BACKEND_URL = os.environ.get("BACKEND_URL", "http://backend:80")
-ADMIN_API_KEY = os.environ.get("ADMIN_API_KEY", "changeme")

integrator/scripts/db.py

@@ -1,23 +0,0 @@
-"""Database connection for the integrator."""
-from contextlib import contextmanager
-
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker
-
-from config import DATABASE_URL
-
-engine = create_engine(DATABASE_URL, pool_pre_ping=True)
-SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
-
-
-@contextmanager
-def get_session():
-    session = SessionLocal()
-    try:
-        yield session
-        session.commit()
-    except Exception:
-        session.rollback()
-        raise
-    finally:
-        session.close()

integrator/scripts/sources/admissions.py

@@ -1,184 +0,0 @@
-"""
-School Admissions data downloader and loader.
-
-Source: EES publication "primary-and-secondary-school-applications-and-offers"
-        Content API release ZIP → supporting-files/AppsandOffers_*_SchoolLevel*.csv
-Update: Annual (June/July post-offer round)
-"""
-import argparse
-import re
-import sys
-from pathlib import Path
-
-import pandas as pd
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-from sources.ees import download_release_zip_csv
-
-DEST_DIR = SUPPLEMENTARY_DIR / "admissions"
-PUBLICATION_SLUG = "primary-and-secondary-school-applications-and-offers"
-
-NULL_VALUES = {"SUPP", "NE", "NA", "NP", "NEW", "LOW", "X", "Z", ""}
-
-# Maps actual CSV column names → internal field names
-COLUMN_MAP = {
-    # School identifier
-    "school_urn": "urn",
-    # Year — e.g. 202526 → 2025
-    "time_period": "time_period_raw",
-    # PAN (places offered)
-    "total_number_places_offered": "pan",
-    # Applications (total times put as any preference)
-    "times_put_as_any_preferred_school": "total_applications",
-    # 1st-preference applications
-    "times_put_as_1st_preference": "times_1st_pref",
-    # 1st-preference offers
-    "number_1st_preference_offers": "offers_1st_pref",
-}
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "admissions") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-    dest_file = dest / "admissions_school_level_latest.csv"
-    return download_release_zip_csv(
-        PUBLICATION_SLUG,
-        dest_file,
-        zip_member_keyword="schoollevel",
-    )
-
-
-def _parse_int(val) -> int | None:
-    if pd.isna(val):
-        return None
-    s = str(val).strip().upper().replace(",", "")
-    if s in NULL_VALUES:
-        return None
-    try:
-        return int(float(s))
-    except ValueError:
-        return None
-
-
-def _parse_pct(val) -> float | None:
-    if pd.isna(val):
-        return None
-    s = str(val).strip().upper().replace("%", "")
-    if s in NULL_VALUES:
-        return None
-    try:
-        return float(s)
-    except ValueError:
-        return None
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "admissions") if data_dir else DEST_DIR
-        files = sorted(dest.glob("*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No admissions CSV found in {dest}")
-        path = files[-1]
-
-    print(f"  Admissions: loading {path} ...")
-    df = pd.read_csv(path, encoding="utf-8-sig", low_memory=False)
-
-    # Rename columns we care about
-    df.rename(columns=COLUMN_MAP, inplace=True)
-
-    if "urn" not in df.columns:
-        raise ValueError(f"URN column not found. Available: {list(df.columns)[:20]}")
-
-    # Filter to primary schools only
-    if "school_phase" in df.columns:
-        df = df[df["school_phase"].str.lower() == "primary"]
-
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    # Derive year from time_period (e.g. 202526 → 2025)
-    def _extract_year(val) -> int | None:
-        s = str(val).strip()
-        m = re.match(r"(\d{4})\d{2}", s)
-        if m:
-            return int(m.group(1))
-        m2 = re.search(r"20(\d{2})", s)
-        if m2:
-            return int("20" + m2.group(1))
-        return None
-
-    if "time_period_raw" in df.columns:
-        df["year"] = df["time_period_raw"].apply(_extract_year)
-    else:
-        year_m = re.search(r"20(\d{2})", path.stem)
-        df["year"] = int("20" + year_m.group(1)) if year_m else None
-
-    df = df.dropna(subset=["year"])
-    df["year"] = df["year"].astype(int)
-
-    # Keep most recent year per school (file may contain multiple years)
-    df = df.sort_values("year", ascending=False).groupby("urn").first().reset_index()
-
-    inserted = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-            year = int(row["year"])
-
-            pan = _parse_int(row.get("pan"))
-            total_apps = _parse_int(row.get("total_applications"))
-            times_1st = _parse_int(row.get("times_1st_pref"))
-            offers_1st = _parse_int(row.get("offers_1st_pref"))
-
-            # % of 1st-preference applicants who received an offer
-            if times_1st and times_1st > 0 and offers_1st is not None:
-                pct_1st = round(offers_1st / times_1st * 100, 1)
-            else:
-                pct_1st = None
-
-            oversubscribed = (
-                True if (pan and times_1st and times_1st > pan) else
-                False if (pan and times_1st and times_1st <= pan) else
-                None
-            )
-
-            session.execute(
-                text("""
-                    INSERT INTO school_admissions
-                        (urn, year, published_admission_number, total_applications,
-                         first_preference_offers_pct, oversubscribed)
-                    VALUES (:urn, :year, :pan, :total_apps, :pct_1st, :oversubscribed)
-                    ON CONFLICT (urn, year) DO UPDATE SET
-                        published_admission_number  = EXCLUDED.published_admission_number,
-                        total_applications          = EXCLUDED.total_applications,
-                        first_preference_offers_pct = EXCLUDED.first_preference_offers_pct,
-                        oversubscribed              = EXCLUDED.oversubscribed
-                """),
-                {
-                    "urn": urn, "year": year, "pan": pan,
-                    "total_apps": total_apps, "pct_1st": pct_1st,
-                    "oversubscribed": oversubscribed,
-                },
-            )
-            inserted += 1
-            if inserted % 5000 == 0:
-                session.flush()
-                print(f"    Processed {inserted} records...")
-
-    print(f"  Admissions: upserted {inserted} records")
-    return {"inserted": inserted, "updated": 0, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/census.py

@@ -1,148 +0,0 @@
-"""
-School Census (SPC) downloader and loader.
-
-Source: EES publication "schools-pupils-and-their-characteristics"
-Update: Annual (June)
-Adds: class_size_avg, ethnicity breakdown by school
-"""
-import argparse
-import re
-import sys
-from pathlib import Path
-
-import pandas as pd
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-from sources.ees import get_latest_csv_url, download_csv
-
-DEST_DIR = SUPPLEMENTARY_DIR / "census"
-PUBLICATION_SLUG = "schools-pupils-and-their-characteristics"
-
-NULL_VALUES = {"SUPP", "NE", "NA", "NP", "NEW", "LOW", "X", ""}
-
-COLUMN_MAP = {
-    "URN": "urn",
-    "urn": "urn",
-    "YEAR": "year",
-    "Year": "year",
-    # Class size
-    "average_class_size": "class_size_avg",
-    "AVCLAS": "class_size_avg",
-    "avg_class_size": "class_size_avg",
-    # Ethnicity — DfE uses ethnicity major group percentages
-    "perc_white": "ethnicity_white_pct",
-    "perc_asian": "ethnicity_asian_pct",
-    "perc_black": "ethnicity_black_pct",
-    "perc_mixed": "ethnicity_mixed_pct",
-    "perc_other_ethnic": "ethnicity_other_pct",
-    "PTWHITE": "ethnicity_white_pct",
-    "PTASIAN": "ethnicity_asian_pct",
-    "PTBLACK": "ethnicity_black_pct",
-    "PTMIXED": "ethnicity_mixed_pct",
-    "PTOTHER": "ethnicity_other_pct",
-}
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "census") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    url = get_latest_csv_url(PUBLICATION_SLUG, keyword="school")
-    if not url:
-        raise RuntimeError(f"Could not find CSV URL for census publication")
-
-    filename = url.split("/")[-1].split("?")[0] or "census_latest.csv"
-    return download_csv(url, dest / filename)
-
-
-def _parse_pct(val) -> float | None:
-    if pd.isna(val):
-        return None
-    s = str(val).strip().upper().replace("%", "")
-    if s in NULL_VALUES:
-        return None
-    try:
-        return float(s)
-    except ValueError:
-        return None
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "census") if data_dir else DEST_DIR
-        files = sorted(dest.glob("*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No census CSV found in {dest}")
-        path = files[-1]
-
-    print(f"  Census: loading {path} ...")
-    df = pd.read_csv(path, encoding="latin-1", low_memory=False)
-    df.rename(columns=COLUMN_MAP, inplace=True)
-
-    if "urn" not in df.columns:
-        raise ValueError(f"URN column not found. Available: {list(df.columns)[:20]}")
-
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    year = None
-    m = re.search(r"20(\d{2})", path.stem)
-    if m:
-        year = int("20" + m.group(1))
-
-    inserted = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-            row_year = int(row["year"]) if "year" in df.columns and pd.notna(row.get("year")) else year
-            if not row_year:
-                continue
-
-            session.execute(
-                text("""
-                    INSERT INTO school_census
-                        (urn, year, class_size_avg,
-                         ethnicity_white_pct, ethnicity_asian_pct, ethnicity_black_pct,
-                         ethnicity_mixed_pct, ethnicity_other_pct)
-                    VALUES (:urn, :year, :class_size_avg,
-                            :white, :asian, :black, :mixed, :other)
-                    ON CONFLICT (urn, year) DO UPDATE SET
-                        class_size_avg       = EXCLUDED.class_size_avg,
-                        ethnicity_white_pct  = EXCLUDED.ethnicity_white_pct,
-                        ethnicity_asian_pct  = EXCLUDED.ethnicity_asian_pct,
-                        ethnicity_black_pct  = EXCLUDED.ethnicity_black_pct,
-                        ethnicity_mixed_pct  = EXCLUDED.ethnicity_mixed_pct,
-                        ethnicity_other_pct  = EXCLUDED.ethnicity_other_pct
-                """),
-                {
-                    "urn": urn,
-                    "year": row_year,
-                    "class_size_avg": _parse_pct(row.get("class_size_avg")),
-                    "white": _parse_pct(row.get("ethnicity_white_pct")),
-                    "asian": _parse_pct(row.get("ethnicity_asian_pct")),
-                    "black": _parse_pct(row.get("ethnicity_black_pct")),
-                    "mixed": _parse_pct(row.get("ethnicity_mixed_pct")),
-                    "other": _parse_pct(row.get("ethnicity_other_pct")),
-                },
-            )
-            inserted += 1
-            if inserted % 5000 == 0:
-                session.flush()
-
-    print(f"  Census: upserted {inserted} records")
-    return {"inserted": inserted, "updated": 0, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/ees.py

@@ -1,111 +0,0 @@
-"""
-Shared EES (Explore Education Statistics) API client.
-
-Two APIs are available:
-  - Statistics API: https://api.education.gov.uk/statistics/v1  (only ~13 publications)
-  - Content API:    https://content.explore-education-statistics.service.gov.uk/api
-    Covers all publications; use this for admissions and other data not in the stats API.
-    Download all files for a release as a ZIP from /api/releases/{id}/files.
-"""
-import io
-import zipfile
-from pathlib import Path
-from typing import Optional
-
-import requests
-
-STATS_API_BASE = "https://api.education.gov.uk/statistics/v1"
-CONTENT_API_BASE = "https://content.explore-education-statistics.service.gov.uk/api"
-TIMEOUT = 60
-
-
-def get_publication_files(publication_slug: str) -> list[dict]:
-    """Return list of data-set file descriptors for a publication (statistics API)."""
-    url = f"{STATS_API_BASE}/publications/{publication_slug}/data-set-files"
-    resp = requests.get(url, timeout=TIMEOUT)
-    resp.raise_for_status()
-    return resp.json().get("results", [])
-
-
-def get_latest_csv_url(publication_slug: str, keyword: str = "") -> Optional[str]:
-    """
-    Find the most recent CSV download URL for a publication (statistics API).
-    Optionally filter by a keyword in the file name.
-    """
-    files = get_publication_files(publication_slug)
-    for entry in files:
-        name = entry.get("name", "").lower()
-        if keyword and keyword.lower() not in name:
-            continue
-        csv_url = entry.get("csvDownloadUrl") or entry.get("file", {}).get("url")
-        if csv_url:
-            return csv_url
-    return None
-
-
-def get_content_release_id(publication_slug: str) -> str:
-    """Return the latest release ID for a publication via the content API."""
-    url = f"{CONTENT_API_BASE}/publications/{publication_slug}/releases/latest"
-    resp = requests.get(url, timeout=TIMEOUT)
-    resp.raise_for_status()
-    return resp.json()["id"]
-
-
-def download_release_zip_csv(
-    publication_slug: str,
-    dest_path: Path,
-    zip_member_keyword: str = "",
-) -> Path:
-    """
-    Download the full-release ZIP from the EES content API and extract one CSV.
-
-    If zip_member_keyword is given, the first member whose path contains that
-    keyword (case-insensitive) is extracted; otherwise the first .csv found is used.
-    Returns dest_path (the extracted CSV file).
-    """
-    if dest_path.exists():
-        print(f"    EES: {dest_path.name} already exists, skipping.")
-        return dest_path
-
-    release_id = get_content_release_id(publication_slug)
-    zip_url = f"{CONTENT_API_BASE}/releases/{release_id}/files"
-    print(f"    EES: downloading release ZIP for '{publication_slug}' ...")
-    resp = requests.get(zip_url, timeout=300, stream=True)
-    resp.raise_for_status()
-
-    data = b"".join(resp.iter_content(chunk_size=65536))
-    with zipfile.ZipFile(io.BytesIO(data)) as z:
-        members = z.namelist()
-        target = None
-        kw = zip_member_keyword.lower()
-        for m in members:
-            if m.endswith(".csv") and (not kw or kw in m.lower()):
-                target = m
-                break
-        if not target:
-            raise ValueError(
-                f"No CSV matching '{zip_member_keyword}' in ZIP. Members: {members}"
-            )
-        print(f"    EES: extracting '{target}' ...")
-        dest_path.parent.mkdir(parents=True, exist_ok=True)
-        with z.open(target) as src, open(dest_path, "wb") as dst:
-            dst.write(src.read())
-
-    print(f"    EES: saved {dest_path} ({dest_path.stat().st_size // 1024} KB)")
-    return dest_path
-
-
-def download_csv(url: str, dest_path: Path) -> Path:
-    """Download a CSV from EES to dest_path."""
-    if dest_path.exists():
-        print(f"    EES: {dest_path.name} already exists, skipping.")
-        return dest_path
-    print(f"    EES: downloading {url} ...")
-    resp = requests.get(url, timeout=300, stream=True)
-    resp.raise_for_status()
-    dest_path.parent.mkdir(parents=True, exist_ok=True)
-    with open(dest_path, "wb") as f:
-        for chunk in resp.iter_content(chunk_size=65536):
-            f.write(chunk)
-    print(f"    EES: saved {dest_path} ({dest_path.stat().st_size // 1024} KB)")
-    return dest_path

integrator/scripts/sources/finance.py

@@ -1,143 +0,0 @@
-"""
-FBIT (Financial Benchmarking and Insights Tool) financial data loader.
-
-Source: https://schools-financial-benchmarking.service.gov.uk/api/
-Update: Annual (December — data for the prior financial year)
-"""
-import argparse
-import sys
-import time
-from pathlib import Path
-
-import pandas as pd
-import requests
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-
-DEST_DIR = SUPPLEMENTARY_DIR / "finance"
-API_BASE = "https://schools-financial-benchmarking.service.gov.uk/api"
-RATE_LIMIT_DELAY = 0.1   # seconds between requests
-
-
-def download(data_dir: Path | None = None) -> Path:
-    """
-    Fetch per-URN financial data from FBIT API and save as CSV.
-    Batches all school URNs from the database.
-    """
-    dest = (data_dir / "supplementary" / "finance") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    # Determine year from API (use current year minus 1 for completed financials)
-    from datetime import date
-    year = date.today().year - 1
-    dest_file = dest / f"fbit_{year}.csv"
-
-    if dest_file.exists():
-        print(f"  Finance: {dest_file.name} already exists, skipping download.")
-        return dest_file
-
-    # Get all URNs from the database
-    with get_session() as session:
-        from sqlalchemy import text
-        rows = session.execute(text("SELECT urn FROM schools")).fetchall()
-    urns = [r[0] for r in rows]
-    print(f"  Finance: fetching FBIT data for {len(urns)} schools (year {year}) ...")
-
-    records = []
-    errors = 0
-    for i, urn in enumerate(urns):
-        if i % 500 == 0:
-            print(f"    {i}/{len(urns)} ...")
-        try:
-            resp = requests.get(
-                f"{API_BASE}/schoolFinancialDataObject/{urn}",
-                timeout=10,
-            )
-            if resp.status_code == 200:
-                data = resp.json()
-                if data:
-                    records.append({
-                        "urn": urn,
-                        "year": year,
-                        "per_pupil_spend": data.get("totalExpenditure") and
-                                           data.get("numberOfPupils") and
-                                           round(data["totalExpenditure"] / data["numberOfPupils"], 2),
-                        "staff_cost_pct": data.get("staffCostPercent"),
-                        "teacher_cost_pct": data.get("teachingStaffCostPercent"),
-                        "support_staff_cost_pct": data.get("educationSupportStaffCostPercent"),
-                        "premises_cost_pct": data.get("premisesStaffCostPercent"),
-                    })
-            elif resp.status_code not in (404, 400):
-                errors += 1
-        except Exception:
-            errors += 1
-
-        time.sleep(RATE_LIMIT_DELAY)
-
-    df = pd.DataFrame(records)
-    df.to_csv(dest_file, index=False)
-    print(f"  Finance: saved {len(records)} records to {dest_file} ({errors} errors)")
-    return dest_file
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "finance") if data_dir else DEST_DIR
-        files = sorted(dest.glob("fbit_*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No finance CSV found in {dest}")
-        path = files[-1]
-
-    print(f"  Finance: loading {path} ...")
-    df = pd.read_csv(path)
-
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    inserted = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            session.execute(
-                text("""
-                    INSERT INTO school_finance
-                        (urn, year, per_pupil_spend, staff_cost_pct, teacher_cost_pct,
-                         support_staff_cost_pct, premises_cost_pct)
-                    VALUES (:urn, :year, :per_pupil, :staff, :teacher, :support, :premises)
-                    ON CONFLICT (urn, year) DO UPDATE SET
-                        per_pupil_spend        = EXCLUDED.per_pupil_spend,
-                        staff_cost_pct         = EXCLUDED.staff_cost_pct,
-                        teacher_cost_pct       = EXCLUDED.teacher_cost_pct,
-                        support_staff_cost_pct = EXCLUDED.support_staff_cost_pct,
-                        premises_cost_pct      = EXCLUDED.premises_cost_pct
-                """),
-                {
-                    "urn": int(row["urn"]),
-                    "year": int(row["year"]),
-                    "per_pupil": float(row["per_pupil_spend"]) if pd.notna(row.get("per_pupil_spend")) else None,
-                    "staff": float(row["staff_cost_pct"]) if pd.notna(row.get("staff_cost_pct")) else None,
-                    "teacher": float(row["teacher_cost_pct"]) if pd.notna(row.get("teacher_cost_pct")) else None,
-                    "support": float(row["support_staff_cost_pct"]) if pd.notna(row.get("support_staff_cost_pct")) else None,
-                    "premises": float(row["premises_cost_pct"]) if pd.notna(row.get("premises_cost_pct")) else None,
-                },
-            )
-            inserted += 1
-            if inserted % 2000 == 0:
-                session.flush()
-
-    print(f"  Finance: upserted {inserted} records")
-    return {"inserted": inserted, "updated": 0, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/gias.py

@@ -1,159 +0,0 @@
-"""
-GIAS (Get Information About Schools) bulk CSV downloader and loader.
-
-Source: https://get-information-schools.service.gov.uk/Downloads
-Update: Daily; we refresh weekly.
-Adds: website, headteacher_name, capacity, trust_name, trust_uid, gender, nursery_provision
-"""
-import argparse
-import sys
-from datetime import date
-from pathlib import Path
-
-import pandas as pd
-import requests
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-
-DEST_DIR = SUPPLEMENTARY_DIR / "gias"
-
-# GIAS bulk download URL — date is injected at runtime
-GIAS_URL_TEMPLATE = "https://ea-edubase-api-prod.azurewebsites.net/edubase/downloads/public/edubasealldata{date}.csv"
-
-COLUMN_MAP = {
-    "URN": "urn",
-    "SchoolWebsite": "website",
-    "SchoolCapacity": "capacity",
-    "TrustName": "trust_name",
-    "TrustUID": "trust_uid",
-    "Gender (name)": "gender",
-    "NurseryProvision (name)": "nursery_provision_raw",
-    "HeadTitle": "head_title",
-    "HeadFirstName": "head_first",
-    "HeadLastName": "head_last",
-}
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "gias") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    today = date.today().strftime("%Y%m%d")
-    url = GIAS_URL_TEMPLATE.format(date=today)
-    filename = f"gias_{today}.csv"
-    dest_file = dest / filename
-
-    if dest_file.exists():
-        print(f"  GIAS: {filename} already exists, skipping download.")
-        return dest_file
-
-    print(f"  GIAS: downloading {url} ...")
-    resp = requests.get(url, timeout=300, stream=True)
-
-    # GIAS may not have today's file yet — fall back to yesterday
-    if resp.status_code == 404:
-        from datetime import timedelta
-        yesterday = (date.today() - timedelta(days=1)).strftime("%Y%m%d")
-        url = GIAS_URL_TEMPLATE.format(date=yesterday)
-        filename = f"gias_{yesterday}.csv"
-        dest_file = dest / filename
-        if dest_file.exists():
-            print(f"  GIAS: {filename} already exists, skipping download.")
-            return dest_file
-        resp = requests.get(url, timeout=300, stream=True)
-
-    resp.raise_for_status()
-    with open(dest_file, "wb") as f:
-        for chunk in resp.iter_content(chunk_size=65536):
-            f.write(chunk)
-
-    print(f"  GIAS: saved {dest_file} ({dest_file.stat().st_size // 1024} KB)")
-    return dest_file
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "gias") if data_dir else DEST_DIR
-        files = sorted(dest.glob("gias_*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No GIAS CSV found in {dest}")
-        path = files[-1]
-
-    print(f"  GIAS: loading {path} ...")
-    df = pd.read_csv(path, encoding="latin-1", low_memory=False)
-    df.rename(columns=COLUMN_MAP, inplace=True)
-
-    if "urn" not in df.columns:
-        raise ValueError(f"URN column not found. Available: {list(df.columns)[:20]}")
-
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    # Build headteacher_name from parts
-    def build_name(row):
-        parts = [
-            str(row.get("head_title", "") or "").strip(),
-            str(row.get("head_first", "") or "").strip(),
-            str(row.get("head_last", "") or "").strip(),
-        ]
-        return " ".join(p for p in parts if p) or None
-
-    df["headteacher_name"] = df.apply(build_name, axis=1)
-    df["nursery_provision"] = df.get("nursery_provision_raw", pd.Series()).apply(
-        lambda v: True if str(v).strip().lower().startswith("has") else False if pd.notna(v) else None
-    )
-
-    def clean_str(val):
-        s = str(val).strip() if pd.notna(val) else None
-        return s if s and s.lower() not in ("nan", "none", "") else None
-
-    updated = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-            session.execute(
-                text("""
-                    UPDATE schools SET
-                        website            = :website,
-                        headteacher_name   = :headteacher_name,
-                        capacity           = :capacity,
-                        trust_name         = :trust_name,
-                        trust_uid          = :trust_uid,
-                        gender             = :gender,
-                        nursery_provision  = :nursery_provision
-                    WHERE urn = :urn
-                """),
-                {
-                    "urn": urn,
-                    "website": clean_str(row.get("website")),
-                    "headteacher_name": row.get("headteacher_name"),
-                    "capacity": int(row["capacity"]) if pd.notna(row.get("capacity")) and str(row.get("capacity")).strip().isdigit() else None,
-                    "trust_name": clean_str(row.get("trust_name")),
-                    "trust_uid": clean_str(row.get("trust_uid")),
-                    "gender": clean_str(row.get("gender")),
-                    "nursery_provision": row.get("nursery_provision"),
-                },
-            )
-            updated += 1
-            if updated % 5000 == 0:
-                session.flush()
-                print(f"    Updated {updated} schools...")
-
-    print(f"  GIAS: updated {updated} school records")
-    return {"inserted": 0, "updated": updated, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-
-    if args.action in ("download", "all"):
-        path = download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/idaci.py

@@ -1,176 +0,0 @@
-"""
-IDACI (Income Deprivation Affecting Children Index) loader.
-
-Source: English Indices of Deprivation 2019
-https://www.gov.uk/government/statistics/english-indices-of-deprivation-2019
-
-This is a one-time download (5-yearly release). We join school postcodes to LSOAs
-via postcodes.io, then look up IDACI scores from the IoD2019 file.
-
-Update: ~5-yearly (next release expected 2025/26)
-"""
-import argparse
-import sys
-from pathlib import Path
-
-import pandas as pd
-import requests
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-
-DEST_DIR = SUPPLEMENTARY_DIR / "idaci"
-
-# IoD 2019 supplementary data — "Income Deprivation Affecting Children Index (IDACI)"
-IOD_2019_URL = (
-    "https://assets.publishing.service.gov.uk/government/uploads/system/uploads/"
-    "attachment_data/file/833970/File_1_-_IMD2019_Index_of_Multiple_Deprivation.xlsx"
-)
-
-POSTCODES_IO_BATCH = "https://api.postcodes.io/postcodes"
-BATCH_SIZE = 100
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "idaci") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    filename = "iod2019_idaci.xlsx"
-    dest_file = dest / filename
-    if dest_file.exists():
-        print(f"  IDACI: {filename} already exists, skipping download.")
-        return dest_file
-
-    print(f"  IDACI: downloading IoD2019 file ...")
-    resp = requests.get(IOD_2019_URL, timeout=300, stream=True)
-    resp.raise_for_status()
-    with open(dest_file, "wb") as f:
-        for chunk in resp.iter_content(chunk_size=65536):
-            f.write(chunk)
-
-    print(f"  IDACI: saved {dest_file}")
-    return dest_file
-
-
-def _postcode_to_lsoa(postcodes: list[str]) -> dict[str, str]:
-    """Batch-resolve postcodes to LSOA codes via postcodes.io."""
-    result = {}
-    valid = [p.strip().upper() for p in postcodes if p and len(str(p).strip()) >= 5]
-    valid = list(set(valid))
-
-    for i in range(0, len(valid), BATCH_SIZE):
-        batch = valid[i:i + BATCH_SIZE]
-        try:
-            resp = requests.post(POSTCODES_IO_BATCH, json={"postcodes": batch}, timeout=30)
-            if resp.status_code == 200:
-                for item in resp.json().get("result", []):
-                    if item and item.get("result"):
-                        lsoa = item["result"].get("lsoa")
-                        if lsoa:
-                            result[item["query"].upper()] = lsoa
-        except Exception as e:
-            print(f"  Warning: postcodes.io batch failed: {e}")
-
-    return result
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    dest = (data_dir / "supplementary" / "idaci") if data_dir else DEST_DIR
-    if path is None:
-        files = sorted(dest.glob("*.xlsx"))
-        if not files:
-            raise FileNotFoundError(f"No IDACI file found in {dest}")
-        path = files[-1]
-
-    print(f"  IDACI: loading IoD2019 from {path} ...")
-
-    # IoD2019 File 1 — sheet "IoD2019 IDACI" or similar
-    try:
-        iod_df = pd.read_excel(path, sheet_name=None)
-        # Find sheet with IDACI data
-        idaci_sheet = None
-        for name, df in iod_df.items():
-            if "IDACI" in name.upper() or "IDACI" in str(df.columns.tolist()).upper():
-                idaci_sheet = name
-                break
-        if idaci_sheet is None:
-            idaci_sheet = list(iod_df.keys())[0]
-        df_iod = iod_df[idaci_sheet]
-    except Exception as e:
-        raise RuntimeError(f"Could not read IoD2019 file: {e}")
-
-    # Normalise column names — IoD2019 uses specific headers
-    col_lsoa = next((c for c in df_iod.columns if "LSOA" in str(c).upper() and "code" in str(c).lower()), None)
-    col_score = next((c for c in df_iod.columns if "IDACI" in str(c).upper() and "score" in str(c).lower()), None)
-    col_rank = next((c for c in df_iod.columns if "IDACI" in str(c).upper() and "rank" in str(c).lower()), None)
-
-    if not col_lsoa or not col_score:
-        print(f"  IDACI columns available: {list(df_iod.columns)[:20]}")
-        raise ValueError("Could not find LSOA code or IDACI score columns")
-
-    df_iod = df_iod[[col_lsoa, col_score]].copy()
-    df_iod.columns = ["lsoa_code", "idaci_score"]
-    df_iod = df_iod.dropna()
-
-    # Compute decile from rank (or from score distribution)
-    total = len(df_iod)
-    df_iod = df_iod.sort_values("idaci_score", ascending=False)
-    df_iod["idaci_decile"] = (pd.qcut(df_iod["idaci_score"], 10, labels=False) + 1).astype(int)
-    # Decile 1 = most deprived (highest IDACI score)
-    df_iod["idaci_decile"] = 11 - df_iod["idaci_decile"]
-
-    lsoa_lookup = df_iod.set_index("lsoa_code")[["idaci_score", "idaci_decile"]].to_dict("index")
-    print(f"  IDACI: loaded {len(lsoa_lookup)} LSOA records")
-
-    # Fetch all school postcodes from the database
-    with get_session() as session:
-        from sqlalchemy import text
-        rows = session.execute(text("SELECT urn, postcode FROM schools WHERE postcode IS NOT NULL")).fetchall()
-
-    postcodes = [r[1] for r in rows]
-    print(f"  IDACI: resolving {len(postcodes)} postcodes via postcodes.io ...")
-    pc_to_lsoa = _postcode_to_lsoa(postcodes)
-    print(f"  IDACI: resolved {len(pc_to_lsoa)} postcodes to LSOAs")
-
-    inserted = skipped = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for urn, postcode in rows:
-            lsoa = pc_to_lsoa.get(str(postcode).strip().upper())
-            if not lsoa:
-                skipped += 1
-                continue
-            iod = lsoa_lookup.get(lsoa)
-            if not iod:
-                skipped += 1
-                continue
-
-            session.execute(
-                text("""
-                    INSERT INTO school_deprivation (urn, lsoa_code, idaci_score, idaci_decile)
-                    VALUES (:urn, :lsoa, :score, :decile)
-                    ON CONFLICT (urn) DO UPDATE SET
-                        lsoa_code    = EXCLUDED.lsoa_code,
-                        idaci_score  = EXCLUDED.idaci_score,
-                        idaci_decile = EXCLUDED.idaci_decile
-                """),
-                {"urn": urn, "lsoa": lsoa, "score": float(iod["idaci_score"]), "decile": int(iod["idaci_decile"])},
-            )
-            inserted += 1
-            if inserted % 2000 == 0:
-                session.flush()
-
-    print(f"  IDACI: upserted {inserted}, skipped {skipped}")
-    return {"inserted": inserted, "updated": 0, "skipped": skipped}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/ks2.py

@@ -1,49 +0,0 @@
-"""
-KS2 attainment data re-importer.
-
-Triggers a full re-import of the KS2 CSV data by calling the backend's
-admin endpoint. The backend owns the migration logic and CSV column mappings;
-this module is a thin trigger so the re-import can be orchestrated via Kestra
-like all other data sources.
-
-The CSV files must already be present in the data volume under
-  /data/{year}/england_ks2final.csv
-(populated at deploy time from the repo's data/ directory).
-"""
-import requests
-from config import BACKEND_URL, ADMIN_API_KEY
-
-HEADERS = {"X-API-Key": ADMIN_API_KEY}
-
-
-def download():
-    """No download step — CSVs are shipped with the repo."""
-    print("KS2 CSVs are bundled in the data volume; no download needed.")
-    return {"skipped": True}
-
-
-def load():
-    """Trigger KS2 re-import on the backend and return immediately.
-
-    The migration (including geocoding) runs as a background thread on the
-    backend and can take up to an hour. Poll GET /api/admin/reimport-ks2/status
-    to check progress, or simply wait for schools to appear in the UI.
-    """
-    url = f"{BACKEND_URL}/api/admin/reimport-ks2?geocode=true"
-    print(f"POST {url}")
-    resp = requests.post(url, headers=HEADERS, timeout=30)
-    resp.raise_for_status()
-    result = resp.json()
-    print(f"Result: {result}")
-    return result
-
-
-if __name__ == "__main__":
-    import argparse
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download()
-    if args.action in ("load", "all"):
-        load()

integrator/scripts/sources/ofsted.py

@@ -1,418 +0,0 @@
-"""
-Ofsted Monthly Management Information CSV downloader and loader.
-
-Source: https://www.gov.uk/government/statistical-data-sets/monthly-management-information-ofsteds-school-inspections-outcomes
-Update: Monthly (released ~2 weeks into each month)
-"""
-import argparse
-import re
-import sys
-from datetime import date, datetime
-from pathlib import Path
-
-import pandas as pd
-import requests
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-
-# Current Ofsted MI download URL — update this when Ofsted releases a new file.
-# The URL follows a predictable pattern; we attempt to discover it from the GOV.UK page.
-GOV_UK_PAGE = "https://www.gov.uk/government/statistical-data-sets/monthly-management-information-ofsteds-school-inspections-outcomes"
-
-# Column name → internal field, listed in priority order per field.
-# First matching column wins; later entries are fallbacks for older file formats.
-COLUMN_PRIORITY = {
-    "urn": ["URN", "Urn", "urn"],
-    "inspection_date": [
-        "Inspection start date of latest OEIF graded inspection",
-        "Inspection start date",
-        "Inspection date",
-        "InspectionDate",
-    ],
-    "publication_date": [
-        "Publication date of latest OEIF graded inspection",
-        "Publication date",
-        "PublicationDate",
-    ],
-    "inspection_type": [
-        "Inspection type of latest OEIF graded inspection",
-        "Inspection type",
-        "InspectionType",
-    ],
-    "overall_effectiveness": [
-        "Latest OEIF overall effectiveness",
-        "Overall effectiveness",
-        "OverallEffectiveness",
-    ],
-    "quality_of_education": [
-        "Latest OEIF quality of education",
-        "Quality of education",
-        "QualityOfEducation",
-    ],
-    "behaviour_attitudes": [
-        "Latest OEIF behaviour and attitudes",
-        "Behaviour and attitudes",
-        "BehaviourAndAttitudes",
-    ],
-    "personal_development": [
-        "Latest OEIF personal development",
-        "Personal development",
-        "PersonalDevelopment",
-    ],
-    "leadership_management": [
-        "Latest OEIF effectiveness of leadership and management",
-        "Leadership and management",
-        "LeadershipAndManagement",
-    ],
-    "early_years_provision": [
-        "Latest OEIF early years provision (where applicable)",
-        "Early years provision",
-        "EarlyYearsProvision",
-    ],
-}
-
-GRADE_MAP = {
-    "Outstanding": 1, "1": 1, 1: 1,
-    "Good": 2, "2": 2, 2: 2,
-    "Requires improvement": 3, "3": 3, 3: 3,
-    "Requires Improvement": 3,
-    "Inadequate": 4, "4": 4, 4: 4,
-}
-
-# Report Card grade text → integer (1=Exceptional … 5=Urgent improvement)
-RC_GRADE_MAP = {
-    "exceptional": 1,
-    "strong standard": 2,
-    "strong": 2,
-    "expected standard": 3,
-    "expected": 3,
-    "needs attention": 4,
-    "urgent improvement": 5,
-}
-
-# Column name priority for Report Card fields (best-guess names; Ofsted may vary)
-RC_COLUMN_PRIORITY = {
-    "rc_safeguarding": [
-        "Safeguarding",
-        "safeguarding",
-        "Safeguarding standards",
-    ],
-    "rc_inclusion": [
-        "Inclusion",
-        "inclusion",
-    ],
-    "rc_curriculum_teaching": [
-        "Curriculum and teaching",
-        "curriculum_and_teaching",
-        "Curriculum & teaching",
-    ],
-    "rc_achievement": [
-        "Achievement",
-        "achievement",
-    ],
-    "rc_attendance_behaviour": [
-        "Attendance and behaviour",
-        "attendance_and_behaviour",
-        "Attendance & behaviour",
-    ],
-    "rc_personal_development": [
-        "Personal development and well-being",
-        "Personal development and wellbeing",
-        "personal_development_and_wellbeing",
-        "Personal development & well-being",
-    ],
-    "rc_leadership_governance": [
-        "Leadership and governance",
-        "leadership_and_governance",
-        "Leadership & governance",
-    ],
-    "rc_early_years": [
-        "Early years",
-        "early_years",
-        "Early years provision",
-    ],
-    "rc_sixth_form": [
-        "Sixth form",
-        "sixth_form",
-        "Sixth form in schools",
-    ],
-}
-
-DEST_DIR = SUPPLEMENTARY_DIR / "ofsted"
-
-
-def _discover_csv_url() -> str | None:
-    """Scrape the GOV.UK page for the most recent CSV/ZIP link."""
-    try:
-        resp = requests.get(GOV_UK_PAGE, timeout=30)
-        resp.raise_for_status()
-        # Look for links to assets.publishing.service.gov.uk CSV or ZIP files
-        pattern = r'href="(https://assets\.publishing\.service\.gov\.uk[^"]+\.(?:csv|zip))"'
-        urls = re.findall(pattern, resp.text, re.IGNORECASE)
-        if urls:
-            return urls[0]
-    except Exception as e:
-        print(f"  Warning: could not scrape GOV.UK page: {e}")
-    return None
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "ofsted") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    url = _discover_csv_url()
-    if not url:
-        raise RuntimeError(
-            "Could not discover Ofsted MI download URL. "
-            "Visit https://www.gov.uk/government/statistical-data-sets/"
-            "monthly-management-information-ofsteds-school-inspections-outcomes "
-            "to get the latest URL and update MANUAL_URL in ofsted.py"
-        )
-
-    filename = url.split("/")[-1]
-    dest_file = dest / filename
-
-    if dest_file.exists():
-        print(f"  Ofsted: {filename} already exists, skipping download.")
-        return dest_file
-
-    print(f"  Ofsted: downloading {url} ...")
-    resp = requests.get(url, timeout=120, stream=True)
-    resp.raise_for_status()
-    with open(dest_file, "wb") as f:
-        for chunk in resp.iter_content(chunk_size=65536):
-            f.write(chunk)
-
-    print(f"  Ofsted: saved {dest_file} ({dest_file.stat().st_size // 1024} KB)")
-    return dest_file
-
-
-def _parse_grade(val) -> int | None:
-    if pd.isna(val):
-        return None
-    key = str(val).strip()
-    return GRADE_MAP.get(key)
-
-
-def _parse_rc_grade(val) -> int | None:
-    """Parse a Report Card grade text to integer 1–5."""
-    if pd.isna(val):
-        return None
-    key = str(val).strip().lower()
-    return RC_GRADE_MAP.get(key)
-
-
-def _parse_safeguarding(val) -> bool | None:
-    """Parse safeguarding 'Met'/'Not met' to boolean."""
-    if pd.isna(val):
-        return None
-    s = str(val).strip().lower()
-    if s == "met":
-        return True
-    if s in ("not met", "not_met"):
-        return False
-    return None
-
-
-def _parse_date(val) -> date | None:
-    if pd.isna(val):
-        return None
-    for fmt in ("%d/%m/%Y", "%Y-%m-%d", "%d-%m-%Y", "%d %B %Y"):
-        try:
-            return datetime.strptime(str(val).strip(), fmt).date()
-        except ValueError:
-            pass
-    return None
-
-
-def _framework_for_row(row) -> str | None:
-    """Determine inspection framework for a single school row.
-
-    Check RC columns first — if any have a value, it's a Report Card inspection.
-    Fall back to OEIF columns. If neither has data, the school has no graded
-    inspection on record (return None).
-    """
-    rc_check_cols = [
-        "rc_inclusion", "rc_curriculum_teaching", "rc_achievement",
-        "rc_attendance_behaviour", "rc_personal_development",
-        "rc_leadership_governance", "rc_safeguarding",
-    ]
-    for col in rc_check_cols:
-        val = row.get(col)
-        if val is not None and not (isinstance(val, float) and pd.isna(val)):
-            return "ReportCard"
-
-    oeif_check_cols = ["overall_effectiveness", "quality_of_education"]
-    for col in oeif_check_cols:
-        val = row.get(col)
-        if val is not None and not (isinstance(val, float) and pd.isna(val)):
-            return "OEIF"
-
-    return None
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "ofsted") if data_dir else DEST_DIR
-        files = sorted(dest.glob("*.csv")) + sorted(dest.glob("*.zip"))
-        if not files:
-            raise FileNotFoundError(f"No Ofsted MI file found in {dest}")
-        path = files[-1]
-
-    print(f"  Ofsted: loading {path} ...")
-
-    def _find_header_row(filepath, encoding="latin-1"):
-        """Scan up to 10 rows to find the one containing a URN column."""
-        for i in range(10):
-            peek = pd.read_csv(filepath, encoding=encoding, header=i, nrows=0)
-            if any(str(c).strip() in ("URN", "Urn", "urn") for c in peek.columns):
-                return i
-        return 0
-
-    if str(path).endswith(".zip"):
-        import zipfile, io
-        with zipfile.ZipFile(path) as z:
-            csv_names = [n for n in z.namelist() if n.endswith(".csv")]
-            if not csv_names:
-                raise ValueError("No CSV found inside Ofsted ZIP")
-            # Extract to a temp file so we can scan for the header row
-            import tempfile, os
-            with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as tmp:
-                tmp.write(z.read(csv_names[0]))
-                tmp_path = tmp.name
-            try:
-                hdr = _find_header_row(tmp_path)
-                df = pd.read_csv(tmp_path, encoding="latin-1", low_memory=False, header=hdr)
-            finally:
-                os.unlink(tmp_path)
-    else:
-        hdr = _find_header_row(path)
-        df = pd.read_csv(path, encoding="latin-1", low_memory=False, header=hdr)
-
-    # Normalise OEIF column names: for each target field pick the first source column present
-    available = set(df.columns)
-    for target, sources in COLUMN_PRIORITY.items():
-        for src in sources:
-            if src in available:
-                df.rename(columns={src: target}, inplace=True)
-                break
-
-    # Normalise Report Card column names (if present)
-    available = set(df.columns)
-    for target, sources in RC_COLUMN_PRIORITY.items():
-        for src in sources:
-            if src in available:
-                df.rename(columns={src: target}, inplace=True)
-                break
-
-    if "urn" not in df.columns:
-        raise ValueError(f"URN column not found. Available: {list(df.columns)[:20]}")
-
-    # Only keep rows with a valid URN
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    inserted = updated = skipped = 0
-
-    with get_session() as session:
-        # Keep only the most recent inspection per URN
-        if "inspection_date" in df.columns:
-            df["_date_parsed"] = df["inspection_date"].apply(_parse_date)
-            df = df.sort_values("_date_parsed", ascending=False).groupby("urn").first().reset_index()
-
-        from sqlalchemy import text
-
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-
-            record = {
-                "urn": urn,
-                "framework": _framework_for_row(row),
-                "inspection_date": _parse_date(row.get("inspection_date")),
-                "publication_date": _parse_date(row.get("publication_date")),
-                "inspection_type": str(row.get("inspection_type", "")).strip() or None,
-                # OEIF fields
-                "overall_effectiveness": _parse_grade(row.get("overall_effectiveness")),
-                "quality_of_education": _parse_grade(row.get("quality_of_education")),
-                "behaviour_attitudes": _parse_grade(row.get("behaviour_attitudes")),
-                "personal_development": _parse_grade(row.get("personal_development")),
-                "leadership_management": _parse_grade(row.get("leadership_management")),
-                "early_years_provision": _parse_grade(row.get("early_years_provision")),
-                "previous_overall": None,
-                # Report Card fields
-                "rc_safeguarding_met": _parse_safeguarding(row.get("rc_safeguarding")),
-                "rc_inclusion": _parse_rc_grade(row.get("rc_inclusion")),
-                "rc_curriculum_teaching": _parse_rc_grade(row.get("rc_curriculum_teaching")),
-                "rc_achievement": _parse_rc_grade(row.get("rc_achievement")),
-                "rc_attendance_behaviour": _parse_rc_grade(row.get("rc_attendance_behaviour")),
-                "rc_personal_development": _parse_rc_grade(row.get("rc_personal_development")),
-                "rc_leadership_governance": _parse_rc_grade(row.get("rc_leadership_governance")),
-                "rc_early_years": _parse_rc_grade(row.get("rc_early_years")),
-                "rc_sixth_form": _parse_rc_grade(row.get("rc_sixth_form")),
-            }
-
-            session.execute(
-                text("""
-                    INSERT INTO ofsted_inspections
-                        (urn, framework, inspection_date, publication_date, inspection_type,
-                         overall_effectiveness, quality_of_education, behaviour_attitudes,
-                         personal_development, leadership_management, early_years_provision,
-                         previous_overall,
-                         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)
-                    VALUES
-                        (:urn, :framework, :inspection_date, :publication_date, :inspection_type,
-                         :overall_effectiveness, :quality_of_education, :behaviour_attitudes,
-                         :personal_development, :leadership_management, :early_years_provision,
-                         :previous_overall,
-                         :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)
-                    ON CONFLICT (urn) DO UPDATE SET
-                        previous_overall      = ofsted_inspections.overall_effectiveness,
-                        framework             = EXCLUDED.framework,
-                        inspection_date       = EXCLUDED.inspection_date,
-                        publication_date      = EXCLUDED.publication_date,
-                        inspection_type       = EXCLUDED.inspection_type,
-                        overall_effectiveness = EXCLUDED.overall_effectiveness,
-                        quality_of_education  = EXCLUDED.quality_of_education,
-                        behaviour_attitudes   = EXCLUDED.behaviour_attitudes,
-                        personal_development  = EXCLUDED.personal_development,
-                        leadership_management = EXCLUDED.leadership_management,
-                        early_years_provision = EXCLUDED.early_years_provision,
-                        rc_safeguarding_met      = EXCLUDED.rc_safeguarding_met,
-                        rc_inclusion             = EXCLUDED.rc_inclusion,
-                        rc_curriculum_teaching   = EXCLUDED.rc_curriculum_teaching,
-                        rc_achievement           = EXCLUDED.rc_achievement,
-                        rc_attendance_behaviour  = EXCLUDED.rc_attendance_behaviour,
-                        rc_personal_development  = EXCLUDED.rc_personal_development,
-                        rc_leadership_governance = EXCLUDED.rc_leadership_governance,
-                        rc_early_years           = EXCLUDED.rc_early_years,
-                        rc_sixth_form            = EXCLUDED.rc_sixth_form
-                """),
-                record,
-            )
-            inserted += 1
-
-            if inserted % 5000 == 0:
-                session.flush()
-                print(f"    Processed {inserted} records...")
-
-    print(f"  Ofsted: upserted {inserted} records")
-    return {"inserted": inserted, "updated": updated, "skipped": skipped}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-
-    if args.action in ("download", "all"):
-        path = download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/parent_view.py

@@ -1,229 +0,0 @@
-"""
-Ofsted Parent View open data downloader and loader.
-
-Source: https://parentview.ofsted.gov.uk/open-data
-Update: ~3 times/year (Spring, Autumn, Summer)
-"""
-import argparse
-import re
-import sys
-from datetime import date, datetime
-from pathlib import Path
-
-import pandas as pd
-import requests
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-
-DEST_DIR = SUPPLEMENTARY_DIR / "parent_view"
-OPEN_DATA_PAGE = "https://parentview.ofsted.gov.uk/open-data"
-
-# Question column mapping — Parent View open data uses descriptive column headers
-# Map any variant to our internal field names
-QUESTION_MAP = {
-    # Q1 — happiness
-    "My child is happy at this school": "q_happy_pct",
-    "Happy": "q_happy_pct",
-    # Q2 — safety
-    "My child feels safe at this school": "q_safe_pct",
-    "Safe": "q_safe_pct",
-    # Q3 — bullying
-    "The school makes sure its pupils are well behaved": "q_behaviour_pct",
-    "Well Behaved": "q_behaviour_pct",
-    # Q4 — bullying dealt with (sometimes separate)
-    "My child has been bullied and the school dealt with the bullying quickly and effectively": "q_bullying_pct",
-    "Bullying": "q_bullying_pct",
-    # Q5 — curriculum info
-    "The school makes me aware of what my child will learn during the year": "q_communication_pct",
-    "Aware of learning": "q_communication_pct",
-    # Q6 — concerns dealt with
-    "When I have raised concerns with the school, they have been dealt with properly": "q_communication_pct",
-    # Q7 — child does well
-    "My child does well at this school": "q_progress_pct",
-    "Does well": "q_progress_pct",
-    # Q8 — teaching
-    "The teaching is good at this school": "q_teaching_pct",
-    "Good teaching": "q_teaching_pct",
-    # Q9 — progress info
-    "I receive valuable information from the school about my child's progress": "q_information_pct",
-    "Progress information": "q_information_pct",
-    # Q10 — curriculum breadth
-    "My child is taught a broad range of subjects": "q_curriculum_pct",
-    "Broad subjects": "q_curriculum_pct",
-    # Q11 — prepares for future
-    "The school prepares my child well for the future": "q_future_pct",
-    "Prepared for future": "q_future_pct",
-    # Q12 — leadership
-    "The school is led and managed effectively": "q_leadership_pct",
-    "Led well": "q_leadership_pct",
-    # Q13 — wellbeing
-    "The school supports my child's wider personal development": "q_wellbeing_pct",
-    "Personal development": "q_wellbeing_pct",
-    # Q14 — recommendation
-    "I would recommend this school to another parent": "q_recommend_pct",
-    "Recommend": "q_recommend_pct",
-}
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "parent_view") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    # Scrape the open data page for the download link
-    try:
-        resp = requests.get(OPEN_DATA_PAGE, timeout=30)
-        resp.raise_for_status()
-        pattern = r'href="([^"]+\.(?:xlsx|csv|zip))"'
-        urls = re.findall(pattern, resp.text, re.IGNORECASE)
-        if not urls:
-            raise RuntimeError("No download link found on Parent View open data page")
-        url = urls[0] if urls[0].startswith("http") else "https://parentview.ofsted.gov.uk" + urls[0]
-    except Exception as e:
-        raise RuntimeError(f"Could not discover Parent View download URL: {e}")
-
-    filename = url.split("/")[-1].split("?")[0]
-    dest_file = dest / filename
-
-    if dest_file.exists():
-        print(f"  ParentView: {filename} already exists, skipping download.")
-        return dest_file
-
-    print(f"  ParentView: downloading {url} ...")
-    resp = requests.get(url, timeout=120, stream=True)
-    resp.raise_for_status()
-    with open(dest_file, "wb") as f:
-        for chunk in resp.iter_content(chunk_size=65536):
-            f.write(chunk)
-
-    print(f"  ParentView: saved {dest_file}")
-    return dest_file
-
-
-def _positive_pct(row: pd.Series, q_col_base: str) -> float | None:
-    """Sum 'Strongly agree' + 'Agree' percentages for a question."""
-    # Parent View open data has columns like "Q1 - Strongly agree %", "Q1 - Agree %"
-    strongly = row.get(f"{q_col_base} - Strongly agree %") or row.get(f"{q_col_base} - Strongly Agree %")
-    agree = row.get(f"{q_col_base} - Agree %")
-    try:
-        total = 0.0
-        if pd.notna(strongly):
-            total += float(strongly)
-        if pd.notna(agree):
-            total += float(agree)
-        return round(total, 1) if total > 0 else None
-    except (TypeError, ValueError):
-        return None
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "parent_view") if data_dir else DEST_DIR
-        files = sorted(dest.glob("*.xlsx")) + sorted(dest.glob("*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No Parent View file found in {dest}")
-        path = files[-1]
-
-    print(f"  ParentView: loading {path} ...")
-
-    if str(path).endswith(".xlsx"):
-        df = pd.read_excel(path)
-    else:
-        df = pd.read_csv(path, encoding="latin-1", low_memory=False)
-
-    # Normalise URN column
-    urn_col = next((c for c in df.columns if c.strip().upper() == "URN"), None)
-    if not urn_col:
-        raise ValueError(f"URN column not found. Columns: {list(df.columns)[:20]}")
-    df.rename(columns={urn_col: "urn"}, inplace=True)
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    # Try to find total responses column
-    resp_col = next((c for c in df.columns if "total" in c.lower() and "respon" in c.lower()), None)
-
-    inserted = 0
-    today = date.today()
-
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-            total = int(row[resp_col]) if resp_col and pd.notna(row.get(resp_col)) else None
-
-            # Try to extract % positive per question from wide-format columns
-            # Parent View has numbered questions Q1–Q12 (or Q1–Q14 depending on year)
-            record = {
-                "urn": urn,
-                "survey_date": today,
-                "total_responses": total,
-                "q_happy_pct": _positive_pct(row, "Q1"),
-                "q_safe_pct": _positive_pct(row, "Q2"),
-                "q_behaviour_pct": _positive_pct(row, "Q3"),
-                "q_bullying_pct": _positive_pct(row, "Q4"),
-                "q_communication_pct": _positive_pct(row, "Q5"),
-                "q_progress_pct": _positive_pct(row, "Q7"),
-                "q_teaching_pct": _positive_pct(row, "Q8"),
-                "q_information_pct": _positive_pct(row, "Q9"),
-                "q_curriculum_pct": _positive_pct(row, "Q10"),
-                "q_future_pct": _positive_pct(row, "Q11"),
-                "q_leadership_pct": _positive_pct(row, "Q12"),
-                "q_wellbeing_pct": _positive_pct(row, "Q13"),
-                "q_recommend_pct": _positive_pct(row, "Q14"),
-                "q_sen_pct": None,
-            }
-
-            session.execute(
-                text("""
-                    INSERT INTO ofsted_parent_view
-                        (urn, survey_date, total_responses,
-                         q_happy_pct, q_safe_pct, q_behaviour_pct, q_bullying_pct,
-                         q_communication_pct, q_progress_pct, q_teaching_pct,
-                         q_information_pct, q_curriculum_pct, q_future_pct,
-                         q_leadership_pct, q_wellbeing_pct, q_recommend_pct, q_sen_pct)
-                    VALUES
-                        (:urn, :survey_date, :total_responses,
-                         :q_happy_pct, :q_safe_pct, :q_behaviour_pct, :q_bullying_pct,
-                         :q_communication_pct, :q_progress_pct, :q_teaching_pct,
-                         :q_information_pct, :q_curriculum_pct, :q_future_pct,
-                         :q_leadership_pct, :q_wellbeing_pct, :q_recommend_pct, :q_sen_pct)
-                    ON CONFLICT (urn) DO UPDATE SET
-                        survey_date = EXCLUDED.survey_date,
-                        total_responses = EXCLUDED.total_responses,
-                        q_happy_pct = EXCLUDED.q_happy_pct,
-                        q_safe_pct = EXCLUDED.q_safe_pct,
-                        q_behaviour_pct = EXCLUDED.q_behaviour_pct,
-                        q_bullying_pct = EXCLUDED.q_bullying_pct,
-                        q_communication_pct = EXCLUDED.q_communication_pct,
-                        q_progress_pct = EXCLUDED.q_progress_pct,
-                        q_teaching_pct = EXCLUDED.q_teaching_pct,
-                        q_information_pct = EXCLUDED.q_information_pct,
-                        q_curriculum_pct = EXCLUDED.q_curriculum_pct,
-                        q_future_pct = EXCLUDED.q_future_pct,
-                        q_leadership_pct = EXCLUDED.q_leadership_pct,
-                        q_wellbeing_pct = EXCLUDED.q_wellbeing_pct,
-                        q_recommend_pct = EXCLUDED.q_recommend_pct,
-                        q_sen_pct = EXCLUDED.q_sen_pct
-                """),
-                record,
-            )
-            inserted += 1
-            if inserted % 2000 == 0:
-                session.flush()
-
-    print(f"  ParentView: upserted {inserted} records")
-    return {"inserted": inserted, "updated": 0, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/phonics.py

@@ -1,132 +0,0 @@
-"""
-Phonics Screening Check downloader and loader.
-
-Source: EES publication "phonics-screening-check-and-key-stage-1-assessments-england"
-Update: Annual (September/October)
-"""
-import argparse
-import sys
-from pathlib import Path
-
-import pandas as pd
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-from sources.ees import get_latest_csv_url, download_csv
-
-DEST_DIR = SUPPLEMENTARY_DIR / "phonics"
-PUBLICATION_SLUG = "phonics-screening-check-and-key-stage-1-assessments-england"
-
-# Known column names in the phonics CSV (vary by year)
-COLUMN_MAP = {
-    "URN": "urn",
-    "urn": "urn",
-    # Year 1 pass rate
-    "PPTA1": "year1_phonics_pct",          # % meeting expected standard Y1
-    "PPTA1B": "year1_phonics_pct",
-    "PT_MET_PHON_Y1": "year1_phonics_pct",
-    "Y1_MET_EXPECTED_PCT": "year1_phonics_pct",
-    # Year 2 (re-takers)
-    "PPTA2": "year2_phonics_pct",
-    "PT_MET_PHON_Y2": "year2_phonics_pct",
-    "Y2_MET_EXPECTED_PCT": "year2_phonics_pct",
-    # Year label
-    "YEAR": "year",
-    "Year": "year",
-}
-
-NULL_VALUES = {"SUPP", "NE", "NA", "NP", "NEW", "LOW", ""}
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "phonics") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    url = get_latest_csv_url(PUBLICATION_SLUG, keyword="school")
-    if not url:
-        raise RuntimeError(f"Could not find CSV URL for phonics publication")
-
-    filename = url.split("/")[-1].split("?")[0] or "phonics_latest.csv"
-    return download_csv(url, dest / filename)
-
-
-def _parse_pct(val) -> float | None:
-    if pd.isna(val):
-        return None
-    s = str(val).strip().upper().replace("%", "")
-    if s in NULL_VALUES:
-        return None
-    try:
-        return float(s)
-    except ValueError:
-        return None
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "phonics") if data_dir else DEST_DIR
-        files = sorted(dest.glob("*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No phonics CSV found in {dest}")
-        path = files[-1]
-
-    print(f"  Phonics: loading {path} ...")
-    df = pd.read_csv(path, encoding="latin-1", low_memory=False)
-    df.rename(columns=COLUMN_MAP, inplace=True)
-
-    if "urn" not in df.columns:
-        raise ValueError(f"URN column not found. Available: {list(df.columns)[:20]}")
-
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    # Infer year from filename if not in data
-    year = None
-    import re
-    m = re.search(r"20(\d{2})", path.stem)
-    if m:
-        year = int("20" + m.group(1))
-
-    inserted = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-            row_year = int(row["year"]) if "year" in df.columns and pd.notna(row.get("year")) else year
-            if not row_year:
-                continue
-
-            session.execute(
-                text("""
-                    INSERT INTO phonics (urn, year, year1_phonics_pct, year2_phonics_pct)
-                    VALUES (:urn, :year, :y1, :y2)
-                    ON CONFLICT (urn, year) DO UPDATE SET
-                        year1_phonics_pct = EXCLUDED.year1_phonics_pct,
-                        year2_phonics_pct = EXCLUDED.year2_phonics_pct
-                """),
-                {
-                    "urn": urn,
-                    "year": row_year,
-                    "y1": _parse_pct(row.get("year1_phonics_pct")),
-                    "y2": _parse_pct(row.get("year2_phonics_pct")),
-                },
-            )
-            inserted += 1
-            if inserted % 5000 == 0:
-                session.flush()
-
-    print(f"  Phonics: upserted {inserted} records")
-    return {"inserted": inserted, "updated": 0, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/scripts/sources/sen_detail.py

@@ -1,150 +0,0 @@
-"""
-SEN (Special Educational Needs) primary need type breakdown.
-
-Source: EES publication "special-educational-needs-in-england"
-Update: Annual (September)
-"""
-import argparse
-import re
-import sys
-from pathlib import Path
-
-import pandas as pd
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-from config import SUPPLEMENTARY_DIR
-from db import get_session
-from sources.ees import get_latest_csv_url, download_csv
-
-DEST_DIR = SUPPLEMENTARY_DIR / "sen_detail"
-PUBLICATION_SLUG = "special-educational-needs-in-england"
-
-NULL_VALUES = {"SUPP", "NE", "NA", "NP", "NEW", "LOW", "X", ""}
-
-COLUMN_MAP = {
-    "URN": "urn",
-    "urn": "urn",
-    "YEAR": "year",
-    "Year": "year",
-    # Primary need types — DfE abbreviated codes
-    "PT_SPEECH": "primary_need_speech_pct",       # SLCN
-    "PT_ASD": "primary_need_autism_pct",           # ASD
-    "PT_MLD": "primary_need_mld_pct",             # Moderate learning difficulty
-    "PT_SPLD": "primary_need_spld_pct",           # Specific learning difficulty
-    "PT_SEMH": "primary_need_semh_pct",           # Social, emotional, mental health
-    "PT_PHYSICAL": "primary_need_physical_pct",   # Physical/sensory
-    "PT_OTHER": "primary_need_other_pct",
-    # Alternative naming
-    "SLCN_PCT": "primary_need_speech_pct",
-    "ASD_PCT": "primary_need_autism_pct",
-    "MLD_PCT": "primary_need_mld_pct",
-    "SPLD_PCT": "primary_need_spld_pct",
-    "SEMH_PCT": "primary_need_semh_pct",
-    "PHYSICAL_PCT": "primary_need_physical_pct",
-    "OTHER_PCT": "primary_need_other_pct",
-}
-
-
-def download(data_dir: Path | None = None) -> Path:
-    dest = (data_dir / "supplementary" / "sen_detail") if data_dir else DEST_DIR
-    dest.mkdir(parents=True, exist_ok=True)
-
-    url = get_latest_csv_url(PUBLICATION_SLUG, keyword="school")
-    if not url:
-        url = get_latest_csv_url(PUBLICATION_SLUG)
-    if not url:
-        raise RuntimeError("Could not find CSV URL for SEN publication")
-
-    filename = url.split("/")[-1].split("?")[0] or "sen_latest.csv"
-    return download_csv(url, dest / filename)
-
-
-def _parse_pct(val) -> float | None:
-    if pd.isna(val):
-        return None
-    s = str(val).strip().upper().replace("%", "")
-    if s in NULL_VALUES:
-        return None
-    try:
-        return float(s)
-    except ValueError:
-        return None
-
-
-def load(path: Path | None = None, data_dir: Path | None = None) -> dict:
-    if path is None:
-        dest = (data_dir / "supplementary" / "sen_detail") if data_dir else DEST_DIR
-        files = sorted(dest.glob("*.csv"))
-        if not files:
-            raise FileNotFoundError(f"No SEN CSV found in {dest}")
-        path = files[-1]
-
-    print(f"  SEN Detail: loading {path} ...")
-    df = pd.read_csv(path, encoding="latin-1", low_memory=False)
-    df.rename(columns=COLUMN_MAP, inplace=True)
-
-    if "urn" not in df.columns:
-        raise ValueError(f"URN column not found. Available: {list(df.columns)[:20]}")
-
-    df["urn"] = pd.to_numeric(df["urn"], errors="coerce")
-    df = df.dropna(subset=["urn"])
-    df["urn"] = df["urn"].astype(int)
-
-    year = None
-    m = re.search(r"20(\d{2})", path.stem)
-    if m:
-        year = int("20" + m.group(1))
-
-    inserted = 0
-    with get_session() as session:
-        from sqlalchemy import text
-        for _, row in df.iterrows():
-            urn = int(row["urn"])
-            row_year = int(row["year"]) if "year" in df.columns and pd.notna(row.get("year")) else year
-            if not row_year:
-                continue
-
-            session.execute(
-                text("""
-                    INSERT INTO sen_detail
-                        (urn, year, primary_need_speech_pct, primary_need_autism_pct,
-                         primary_need_mld_pct, primary_need_spld_pct, primary_need_semh_pct,
-                         primary_need_physical_pct, primary_need_other_pct)
-                    VALUES (:urn, :year, :speech, :autism, :mld, :spld, :semh, :physical, :other)
-                    ON CONFLICT (urn, year) DO UPDATE SET
-                        primary_need_speech_pct   = EXCLUDED.primary_need_speech_pct,
-                        primary_need_autism_pct   = EXCLUDED.primary_need_autism_pct,
-                        primary_need_mld_pct      = EXCLUDED.primary_need_mld_pct,
-                        primary_need_spld_pct     = EXCLUDED.primary_need_spld_pct,
-                        primary_need_semh_pct     = EXCLUDED.primary_need_semh_pct,
-                        primary_need_physical_pct = EXCLUDED.primary_need_physical_pct,
-                        primary_need_other_pct    = EXCLUDED.primary_need_other_pct
-                """),
-                {
-                    "urn": urn, "year": row_year,
-                    "speech": _parse_pct(row.get("primary_need_speech_pct")),
-                    "autism": _parse_pct(row.get("primary_need_autism_pct")),
-                    "mld": _parse_pct(row.get("primary_need_mld_pct")),
-                    "spld": _parse_pct(row.get("primary_need_spld_pct")),
-                    "semh": _parse_pct(row.get("primary_need_semh_pct")),
-                    "physical": _parse_pct(row.get("primary_need_physical_pct")),
-                    "other": _parse_pct(row.get("primary_need_other_pct")),
-                },
-            )
-            inserted += 1
-            if inserted % 5000 == 0:
-                session.flush()
-
-    print(f"  SEN Detail: upserted {inserted} records")
-    return {"inserted": inserted, "updated": 0, "skipped": 0}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--action", choices=["download", "load", "all"], default="all")
-    parser.add_argument("--data-dir", type=Path, default=None)
-    args = parser.parse_args()
-    if args.action in ("download", "all"):
-        download(args.data_dir)
-    if args.action in ("load", "all"):
-        load(data_dir=args.data_dir)

integrator/server.py

@@ -1,70 +0,0 @@
-"""
-Data integrator HTTP server.
-Kestra calls this server via HTTP tasks to trigger download/load operations.
-"""
-import importlib
-import sys
-import traceback
-from pathlib import Path
-
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import JSONResponse
-
-sys.path.insert(0, "/app/scripts")
-
-app = FastAPI(title="SchoolCompare Data Integrator", version="1.0.0")
-
-SOURCES = {
-    "ofsted", "gias", "parent_view",
-    "census", "admissions", "sen_detail",
-    "phonics", "idaci", "finance", "ks2",
-}
-
-
-@app.get("/health")
-def health():
-    return {"status": "ok"}
-
-
-@app.post("/run/{source}")
-def run_source(source: str, action: str = "all"):
-    """
-    Trigger a data source download and/or load.
-    action: "download" | "load" | "all"
-    """
-    if source not in SOURCES:
-        raise HTTPException(status_code=404, detail=f"Unknown source '{source}'. Available: {sorted(SOURCES)}")
-    if action not in ("download", "load", "all"):
-        raise HTTPException(status_code=400, detail="action must be 'download', 'load', or 'all'")
-
-    try:
-        mod = importlib.import_module(f"sources.{source}")
-        result = {}
-
-        if action in ("download", "all"):
-            mod.download()
-
-        if action in ("load", "all"):
-            result = mod.load()
-
-        return {"source": source, "action": action, "result": result}
-
-    except Exception as e:
-        tb = traceback.format_exc()
-        raise HTTPException(status_code=500, detail={"error": str(e), "traceback": tb})
-
-
-@app.post("/run-all")
-def run_all(action: str = "all"):
-    """Trigger all sources in sequence."""
-    results = {}
-    for source in sorted(SOURCES):
-        try:
-            mod = importlib.import_module(f"sources.{source}")
-            if action in ("download", "all"):
-                mod.download()
-            if action in ("load", "all"):
-                results[source] = mod.load()
-        except Exception as e:
-            results[source] = {"error": str(e)}
-    return results

nextjs-app/QA_CHECKLIST.md

@@ -53,7 +53,7 @@
 
 ### Rankings Page
 - [ ] Rankings page loads with SSR
-- [ ] Default metric displays (RWM Expected)
+- [ ] Default metric displays (Reading, Writing & Maths Expected)
 - [ ] Metric selector updates rankings
 - [ ] Area filter updates rankings
 - [ ] Year filter updates rankings

nextjs-app/__tests__/lib/utils.test.ts

@@ -8,6 +8,7 @@ import {
   calculateTrend,
   isValidPostcode,
   debounce,
+  buildOfstedListBadge,
 } from '@/lib/utils';
 
 describe('formatPercentage', () => {
@@ -102,3 +103,41 @@ describe('debounce', () => {
 
   jest.useRealTimers();
 });
+
+describe('buildOfstedListBadge', () => {
+  it('returns grade word + year for OEIF Outstanding', () => {
+    const badge = buildOfstedListBadge({ ofsted_grade: 1, ofsted_date: '2023-11-15', ofsted_framework: 'OEIF' });
+    expect(badge.label).toBe('Outstanding · 2023');
+    expect(badge.cssClass).toBe('ofsted1');
+  });
+
+  it('returns grade word for each OEIF grade', () => {
+    expect(buildOfstedListBadge({ ofsted_grade: 2, ofsted_date: '2022-05-01' }).label).toBe('Good · 2022');
+    expect(buildOfstedListBadge({ ofsted_grade: 3, ofsted_date: '2021-01-01' }).label).toBe('Req. Improvement · 2021');
+    expect(buildOfstedListBadge({ ofsted_grade: 4, ofsted_date: '2020-03-01' }).label).toBe('Inadequate · 2020');
+  });
+
+  it('returns grade word without year when date is missing', () => {
+    const badge = buildOfstedListBadge({ ofsted_grade: 2, ofsted_date: null });
+    expect(badge.label).toBe('Good');
+    expect(badge.cssClass).toBe('ofsted2');
+  });
+
+  it('returns Report Card badge when framework is ReportCard', () => {
+    const badge = buildOfstedListBadge({ ofsted_grade: null, ofsted_date: '2025-11-01', ofsted_framework: 'ReportCard' });
+    expect(badge.label).toBe('Report Card · 2025');
+    expect(badge.cssClass).toBe('ofstedRc');
+  });
+
+  it('returns pending badge when no grade and no ReportCard framework', () => {
+    const badge = buildOfstedListBadge({ ofsted_grade: null, ofsted_date: null, ofsted_framework: null });
+    expect(badge.label).toBe('Not yet inspected');
+    expect(badge.cssClass).toBe('ofstedPending');
+  });
+
+  it('returns pending badge when all fields are undefined', () => {
+    const badge = buildOfstedListBadge({});
+    expect(badge.label).toBe('Not yet inspected');
+    expect(badge.cssClass).toBe('ofstedPending');
+  });
+});

nextjs-app/app/globals.css

@@ -58,6 +58,23 @@
     
     --transition: 0.2s ease;
     --transition-slow: 0.4s ease;
+
+    /* Phase indicators */
+    --phase-primary: #5b8cbf;
+    --phase-primary-bg: rgba(91, 140, 191, 0.10);
+    --phase-primary-text: #3d6a99;
+    --phase-secondary: #9b6bb0;
+    --phase-secondary-bg: rgba(155, 107, 176, 0.10);
+    --phase-secondary-text: #7a4f93;
+    --phase-all-through: #7a9a6d;
+    --phase-all-through-bg: rgba(122, 154, 109, 0.10);
+    --phase-all-through-text: #5a7a4d;
+    --phase-post16: #c4915e;
+    --phase-post16-bg: rgba(196, 145, 94, 0.10);
+    --phase-post16-text: #9a6d3a;
+    --phase-nursery: #e0a0b0;
+    --phase-nursery-bg: rgba(224, 160, 176, 0.10);
+    --phase-nursery-text: #b06070;
 }
 
 * {
@@ -274,6 +291,8 @@ body {
     max-width: 1400px;
     margin: 0 auto;
     padding: 1.25rem 1.5rem;
+    min-width: 0;
+    overflow-x: clip;
 }
 
 .view {

nextjs-app/app/layout.tsx

@@ -23,11 +23,11 @@ const playfairDisplay = Playfair_Display({
 
 export const metadata: Metadata = {
   title: {
-    default: 'SchoolCompare | Compare Primary School Performance',
+    default: 'SchoolCompare | Compare School Performance',
     template: '%s | SchoolCompare',
   },
-  description: 'Compare primary school KS2 performance across England',
+  description: 'Compare primary and secondary school SATs and GCSE performance across England',
-  keywords: 'school comparison, KS2 results, primary school performance, England schools, SATs results',
+  keywords: 'school comparison, KS2 results, KS4 results, primary school, secondary school, England schools, SATs results, GCSE results',
   authors: [{ name: 'SchoolCompare' }],
   manifest: '/manifest.json',
   icons: {
@@ -37,15 +37,15 @@ export const metadata: Metadata = {
   },
   openGraph: {
     type: 'website',
-    title: 'SchoolCompare | Compare Primary School Performance',
+    title: 'SchoolCompare | Compare School Performance',
-    description: 'Compare primary school KS2 performance across England',
+    description: 'Compare primary and secondary school SATs and GCSE performance across England',
     url: 'https://schoolcompare.co.uk',
     siteName: 'SchoolCompare',
   },
   twitter: {
     card: 'summary',
-    title: 'SchoolCompare | Compare Primary School Performance',
+    title: 'SchoolCompare | Compare School Performance',
-    description: 'Compare primary school KS2 performance across England',
+    description: 'Compare primary and secondary school SATs and GCSE performance across England',
   },
 };
 

nextjs-app/app/page.tsx

@@ -11,15 +11,20 @@ interface HomePageProps {
     search?: string;
     local_authority?: string;
     school_type?: string;
+    phase?: string;
     page?: string;
     postcode?: string;
     radius?: string;
+    sort?: string;
+    gender?: string;
+    admissions_policy?: string;
+    has_sixth_form?: string;
   }>;
 }
 
 export const metadata = {
   title: 'Home',
-  description: 'Search and compare primary school KS2 performance across England',
+  description: 'Search and compare school performance across England',
 };
 
 // Force dynamic rendering (no static generation at build time)
@@ -38,7 +43,11 @@ export default async function HomePage({ searchParams }: HomePageProps) {
     params.search ||
     params.local_authority ||
     params.school_type ||
-    params.postcode
+    params.phase ||
+    params.postcode ||
+    params.gender ||
+    params.admissions_policy ||
+    params.has_sixth_form
   );
 
   // Fetch data on server with error handling
@@ -52,10 +61,14 @@ export default async function HomePage({ searchParams }: HomePageProps) {
         search: params.search,
         local_authority: params.local_authority,
         school_type: params.school_type,
+        phase: params.phase,
         postcode: params.postcode,
         radius,
         page,
         page_size: 50,
+        gender: params.gender,
+        admissions_policy: params.admissions_policy,
+        has_sixth_form: params.has_sixth_form,
       });
     } else {
       // Empty state by default
@@ -65,7 +78,7 @@ export default async function HomePage({ searchParams }: HomePageProps) {
     return (
       <HomeView
         initialSchools={schoolsData}
-        filters={filtersData || { local_authorities: [], school_types: [], years: [] }}
+        filters={filtersData || { local_authorities: [], school_types: [], years: [], phases: [], genders: [], admissions_policies: [] }}
         totalSchools={dataInfo?.total_schools ?? null}
       />
     );
@@ -76,7 +89,7 @@ export default async function HomePage({ searchParams }: HomePageProps) {
     return (
       <HomeView
         initialSchools={{ schools: [], page: 1, page_size: 50, total: 0, total_pages: 0 }}
-        filters={{ local_authorities: [], school_types: [], years: [] }}
+        filters={{ local_authorities: [], school_types: [], years: [], phases: [], genders: [], admissions_policies: [] }}
         totalSchools={null}
       />
     );

nextjs-app/app/rankings/page.tsx

@@ -12,22 +12,24 @@ interface RankingsPageProps {
     metric?: string;
     local_authority?: string;
     year?: string;
+    phase?: string;
   }>;
 }
 
 export const metadata: Metadata = {
   title: 'School Rankings',
-  description: 'Top-ranked primary schools by KS2 performance across England',
+  description: 'Top-ranked schools by SATs and GCSE performance across England',
-  keywords: 'school rankings, top schools, best schools, KS2 rankings, school league tables',
+  keywords: 'school rankings, top schools, best schools, KS2 rankings, KS4 rankings, school league tables',
 };
 
 // Force dynamic rendering
 export const dynamic = 'force-dynamic';
 
 export default async function RankingsPage({ searchParams }: RankingsPageProps) {
-  const { metric: metricParam, local_authority, year: yearParam } = await searchParams;
+  const { metric: metricParam, local_authority, year: yearParam, phase: phaseParam } = await searchParams;
 
-  const metric = metricParam || 'rwm_expected_pct';
+  const phase = phaseParam || 'primary';
+  const metric = metricParam || (phase === 'secondary' ? 'attainment_8_score' : 'rwm_expected_pct');
   const year = yearParam ? parseInt(yearParam) : undefined;
 
   // Fetch rankings data with error handling
@@ -38,6 +40,7 @@ export default async function RankingsPage({ searchParams }: RankingsPageProps)
         local_authority,
         year,
         limit: 100,
+        phase,
       }),
       fetchFilters(),
       fetchMetrics(),
@@ -49,11 +52,12 @@ export default async function RankingsPage({ searchParams }: RankingsPageProps)
     return (
       <RankingsView
         rankings={rankingsResponse?.rankings || []}
-        filters={filtersResponse || { local_authorities: [], school_types: [], years: [] }}
+        filters={filtersResponse || { local_authorities: [], school_types: [], years: [], phases: [], genders: [], admissions_policies: [] }}
         metrics={metricsArray}
         selectedMetric={metric}
         selectedArea={local_authority}
         selectedYear={year}
+        selectedPhase={phase}
       />
     );
   } catch (error) {
@@ -63,11 +67,12 @@ export default async function RankingsPage({ searchParams }: RankingsPageProps)
     return (
       <RankingsView
         rankings={[]}
-        filters={{ local_authorities: [], school_types: [], years: [] }}
+        filters={{ local_authorities: [], school_types: [], years: [], phases: [], genders: [], admissions_policies: [] }}
         metrics={[]}
         selectedMetric={metric}
         selectedArea={local_authority}
         selectedYear={year}
+        selectedPhase={phase}
       />
     );
   }

nextjs-app/app/school/[slug]/page.tsx

@@ -0,0 +1,180 @@
+/**
+ * Individual School Page (SSR)
+ * Dynamic route for school details with full SEO optimization
+ * URL format: /school/138267-school-name-here
+ */
+
+import { fetchSchoolDetails } from '@/lib/api';
+import { notFound, redirect } from 'next/navigation';
+import { SchoolDetailView } from '@/components/SchoolDetailView';
+import { SecondarySchoolDetailView } from '@/components/SecondarySchoolDetailView';
+import { parseSchoolSlug, schoolUrl } from '@/lib/utils';
+import type { Metadata } from 'next';
+
+interface SchoolPageProps {
+  params: Promise<{ slug: string }>;
+}
+
+export async function generateMetadata({ params }: SchoolPageProps): Promise<Metadata> {
+  const { slug } = await params;
+  const urn = parseSchoolSlug(slug);
+
+  if (!urn || urn < 100000 || urn > 999999) {
+    return {
+      title: 'School Not Found',
+    };
+  }
+
+  try {
+    const data = await fetchSchoolDetails(urn);
+    const { school_info } = data;
+
+    const canonicalPath = schoolUrl(urn, school_info.school_name);
+    const phaseStr = (school_info.phase ?? '').toLowerCase();
+    const isAllThrough = phaseStr === 'all-through';
+    const isSecondary = !isAllThrough && (
+      phaseStr.includes('secondary')
+      || (data.yearly_data ?? []).some((d: any) => d.attainment_8_score != null)
+    );
+    const la = school_info.local_authority ? ` in ${school_info.local_authority}` : '';
+    const title = `${school_info.school_name} | ${school_info.local_authority || 'England'}`;
+    const description = isAllThrough
+      ? `View KS2 SATs and GCSE results for ${school_info.school_name}${la}. All-through school covering primary and secondary education.`
+      : isSecondary
+        ? `View GCSE results, Attainment 8, Progress 8 and school statistics for ${school_info.school_name}${la}.`
+        : `View KS2 performance data, results, and statistics for ${school_info.school_name}${la}. Compare reading, writing, and maths results.`;
+
+    return {
+      title,
+      description,
+      keywords: isAllThrough
+        ? `${school_info.school_name}, KS2 results, GCSE results, all-through school, ${school_info.local_authority}, SATs, Attainment 8`
+        : isSecondary
+          ? `${school_info.school_name}, GCSE results, secondary school, ${school_info.local_authority}, Attainment 8, Progress 8`
+          : `${school_info.school_name}, KS2 results, primary school, ${school_info.local_authority}, school performance, SATs results`,
+      openGraph: {
+        title,
+        description,
+        type: 'website',
+        url: `https://schoolcompare.co.uk${canonicalPath}`,
+        siteName: 'SchoolCompare',
+      },
+      twitter: {
+        card: 'summary',
+        title,
+        description,
+      },
+      alternates: {
+        canonical: `https://schoolcompare.co.uk${canonicalPath}`,
+      },
+    };
+  } catch {
+    return {
+      title: 'School Not Found',
+    };
+  }
+}
+
+// Force dynamic rendering
+export const dynamic = 'force-dynamic';
+
+export default async function SchoolPage({ params }: SchoolPageProps) {
+  const { slug } = await params;
+  const urn = parseSchoolSlug(slug);
+
+  // Validate URN format
+  if (!urn || urn < 100000 || urn > 999999) {
+    notFound();
+  }
+
+  // Fetch school data
+  let data;
+  try {
+    data = await fetchSchoolDetails(urn);
+  } catch (error) {
+    console.error(`Failed to fetch school ${urn}:`, error);
+    notFound();
+  }
+
+  const { school_info, yearly_data, absence_data, ofsted, parent_view, census, admissions, sen_detail, phonics, deprivation, finance } = data;
+
+  // Redirect bare URN to canonical slug URL
+  const canonicalSlug = schoolUrl(urn, school_info.school_name).replace('/school/', '');
+  if (slug !== canonicalSlug) {
+    redirect(`/school/${canonicalSlug}`);
+  }
+
+  const phaseStr = (school_info.phase ?? '').toLowerCase();
+  const isAllThrough = phaseStr === 'all-through';
+  // All-through schools go to SchoolDetailView (renders both KS2 + KS4 sections).
+  // SecondarySchoolDetailView is KS4-only, so all-through schools would lose SATs data.
+  const isSecondary = !isAllThrough && (
+    phaseStr.includes('secondary')
+    || yearly_data.some((d: any) => d.attainment_8_score != null)
+  );
+
+  // Generate JSON-LD structured data for SEO
+  const structuredData = {
+    '@context': 'https://schema.org',
+    '@type': 'EducationalOrganization',
+    name: school_info.school_name,
+    identifier: school_info.urn.toString(),
+    ...(school_info.address && {
+      address: {
+        '@type': 'PostalAddress',
+        streetAddress: school_info.address,
+        addressLocality: school_info.local_authority || undefined,
+        postalCode: school_info.postcode || undefined,
+        addressCountry: 'GB',
+      },
+    }),
+    ...(school_info.latitude && school_info.longitude && {
+      geo: {
+        '@type': 'GeoCoordinates',
+        latitude: school_info.latitude,
+        longitude: school_info.longitude,
+      },
+    }),
+    ...(school_info.school_type && {
+      additionalType: school_info.school_type,
+    }),
+  };
+
+  return (
+    <>
+      <script
+        type="application/ld+json"
+        dangerouslySetInnerHTML={{ __html: JSON.stringify(structuredData) }}
+      />
+      {isSecondary ? (
+        <SecondarySchoolDetailView
+          schoolInfo={school_info}
+          yearlyData={yearly_data}
+          absenceData={absence_data}
+          ofsted={ofsted ?? null}
+          parentView={parent_view ?? null}
+          census={census ?? null}
+          admissions={admissions ?? null}
+          senDetail={sen_detail ?? null}
+          phonics={phonics ?? null}
+          deprivation={deprivation ?? null}
+          finance={finance ?? null}
+        />
+      ) : (
+        <SchoolDetailView
+          schoolInfo={school_info}
+          yearlyData={yearly_data}
+          absenceData={absence_data}
+          ofsted={ofsted ?? null}
+          parentView={parent_view ?? null}
+          census={census ?? null}
+          admissions={admissions ?? null}
+          senDetail={sen_detail ?? null}
+          phonics={phonics ?? null}
+          deprivation={deprivation ?? null}
+          finance={finance ?? null}
+        />
+      )}
+    </>
+  );
+}

nextjs-app/app/school/[urn]/page.tsx

@@ -1,130 +0,0 @@
-/**
- * Individual School Page (SSR)
- * Dynamic route for school details with full SEO optimization
- */
-
-import { fetchSchoolDetails } from '@/lib/api';
-import { notFound } from 'next/navigation';
-import { SchoolDetailView } from '@/components/SchoolDetailView';
-import type { Metadata } from 'next';
-
-interface SchoolPageProps {
-  params: Promise<{ urn: string }>;
-}
-
-export async function generateMetadata({ params }: SchoolPageProps): Promise<Metadata> {
-  const { urn: urnString } = await params;
-  const urn = parseInt(urnString);
-
-  if (isNaN(urn) || urn < 100000 || urn > 999999) {
-    return {
-      title: 'School Not Found',
-    };
-  }
-
-  try {
-    const data = await fetchSchoolDetails(urn);
-    const { school_info } = data;
-
-    const title = `${school_info.school_name} | ${school_info.local_authority || 'England'}`;
-    const description = `View KS2 performance data, results, and statistics for ${school_info.school_name}${school_info.local_authority ? ` in ${school_info.local_authority}` : ''}. Compare reading, writing, and maths results.`;
-
-    return {
-      title,
-      description,
-      keywords: `${school_info.school_name}, KS2 results, primary school, ${school_info.local_authority}, school performance, SATs results`,
-      openGraph: {
-        title,
-        description,
-        type: 'website',
-        url: `https://schoolcompare.co.uk/school/${urn}`,
-        siteName: 'SchoolCompare',
-      },
-      twitter: {
-        card: 'summary',
-        title,
-        description,
-      },
-      alternates: {
-        canonical: `https://schoolcompare.co.uk/school/${urn}`,
-      },
-    };
-  } catch {
-    return {
-      title: 'School Not Found',
-    };
-  }
-}
-
-// Force dynamic rendering
-export const dynamic = 'force-dynamic';
-
-export default async function SchoolPage({ params }: SchoolPageProps) {
-  const { urn: urnString } = await params;
-  const urn = parseInt(urnString);
-
-  // Validate URN format
-  if (isNaN(urn) || urn < 100000 || urn > 999999) {
-    notFound();
-  }
-
-  // Fetch school data
-  let data;
-  try {
-    data = await fetchSchoolDetails(urn);
-  } catch (error) {
-    console.error(`Failed to fetch school ${urn}:`, error);
-    notFound();
-  }
-
-  const { school_info, yearly_data, absence_data, ofsted, parent_view, census, admissions, sen_detail, phonics, deprivation, finance } = data;
-
-  // Generate JSON-LD structured data for SEO
-  const structuredData = {
-    '@context': 'https://schema.org',
-    '@type': 'EducationalOrganization',
-    name: school_info.school_name,
-    identifier: school_info.urn.toString(),
-    ...(school_info.address && {
-      address: {
-        '@type': 'PostalAddress',
-        streetAddress: school_info.address,
-        addressLocality: school_info.local_authority || undefined,
-        postalCode: school_info.postcode || undefined,
-        addressCountry: 'GB',
-      },
-    }),
-    ...(school_info.latitude && school_info.longitude && {
-      geo: {
-        '@type': 'GeoCoordinates',
-        latitude: school_info.latitude,
-        longitude: school_info.longitude,
-      },
-    }),
-    ...(school_info.school_type && {
-      additionalType: school_info.school_type,
-    }),
-  };
-
-  return (
-    <>
-      <script
-        type="application/ld+json"
-        dangerouslySetInnerHTML={{ __html: JSON.stringify(structuredData) }}
-      />
-      <SchoolDetailView
-        schoolInfo={school_info}
-        yearlyData={yearly_data}
-        absenceData={absence_data}
-        ofsted={ofsted ?? null}
-        parentView={parent_view ?? null}
-        census={census ?? null}
-        admissions={admissions ?? null}
-        senDetail={sen_detail ?? null}
-        phonics={phonics ?? null}
-        deprivation={deprivation ?? null}
-        finance={finance ?? null}
-      />
-    </>
-  );
-}

nextjs-app/app/sitemap.ts

@@ -1,54 +0,0 @@
-/**
- * Dynamic Sitemap Generation
- * Generates sitemap with all school pages and main routes
- */
-
-import { MetadataRoute } from 'next';
-import { fetchSchools } from '@/lib/api';
-
-const BASE_URL = 'https://schoolcompare.co.uk';
-
-export default async function sitemap(): Promise<MetadataRoute.Sitemap> {
-  // Static pages
-  const staticPages: MetadataRoute.Sitemap = [
-    {
-      url: BASE_URL,
-      lastModified: new Date(),
-      changeFrequency: 'daily',
-      priority: 1.0,
-    },
-    {
-      url: `${BASE_URL}/compare`,
-      lastModified: new Date(),
-      changeFrequency: 'weekly',
-      priority: 0.8,
-    },
-    {
-      url: `${BASE_URL}/rankings`,
-      lastModified: new Date(),
-      changeFrequency: 'weekly',
-      priority: 0.8,
-    },
-  ];
-
-  // Fetch all schools (in batches if necessary)
-  try {
-    const schoolsData = await fetchSchools({
-      page: 1,
-      page_size: 10000, // Fetch all schools
-    });
-
-    const schoolPages: MetadataRoute.Sitemap = schoolsData.schools.map((school) => ({
-      url: `${BASE_URL}/school/${school.urn}`,
-      lastModified: new Date(),
-      changeFrequency: 'monthly',
-      priority: 0.6,
-    }));
-
-    return [...staticPages, ...schoolPages];
-  } catch (error) {
-    console.error('Failed to generate sitemap:', error);
-    // Return just static pages if school fetch fails
-    return staticPages;
-  }
-}

nextjs-app/components/ComparisonChart.tsx

@@ -18,7 +18,7 @@ import {
   ChartOptions,
 } from 'chart.js';
 import type { ComparisonData } from '@/lib/types';
-import { CHART_COLORS } from '@/lib/utils';
+import { CHART_COLORS, formatAcademicYear } from '@/lib/utils';
 
 // Register Chart.js components
 ChartJS.register(
@@ -68,7 +68,7 @@ export function ComparisonChart({ comparisonData, metric, metricLabel }: Compari
   });
 
   const chartData = {
-    labels: years.map(String),
+    labels: years.map(formatAcademicYear),
     datasets,
   };
 

nextjs-app/components/ComparisonToast.module.css

@@ -23,18 +23,12 @@
   flex-direction: column;
   gap: 0;
   padding: 1rem 1.25rem;
-  background: var(--bg-accent, #1a1612);
+  background: var(--bg-primary, #faf7f2);
-  color: var(--text-inverse, #faf7f2);
+  color: var(--text-primary, #2c2420);
   border-radius: 16px;
-  box-shadow: 0 10px 30px rgba(26, 22, 18, 0.3);
+  box-shadow: 0 8px 32px rgba(44, 36, 32, 0.18), 0 2px 8px rgba(44, 36, 32, 0.08);
-  border: 1px solid rgba(255, 255, 255, 0.1);
+  border: 1px solid var(--border-color, #e8ddd4);
-  min-width: 260px;
+  min-width: 280px;
-}
-
-.toastInfo {
-  display: flex;
-  align-items: center;
-  gap: 0.75rem;
 }
 
 .toastBadge {
@@ -48,38 +42,7 @@
   border-radius: 50%;
   font-weight: 700;
   font-size: 0.9rem;
-}
+  flex-shrink: 0;
-
-.toastText {
-  font-weight: 500;
-  font-size: 0.95rem;
-  white-space: nowrap;
-}
-
-.toastActions {
-  display: flex;
-  align-items: center;
-  gap: 0.75rem;
-  padding-top: 0.25rem;
-  border-top: 1px solid rgba(255, 255, 255, 0.1);
-}
-
-
-.btnCompare {
-  background: white;
-  color: var(--bg-accent, #1a1612);
-  padding: 0.6rem 1.25rem;
-  border-radius: 25px;
-  font-weight: 600;
-  font-size: 0.9rem;
-  text-decoration: none;
-  transition: transform 0.2s ease, background-color 0.2s ease;
-  white-space: nowrap;
-}
-
-.btnCompare:hover {
-  transform: translateY(-1px);
-  background: var(--bg-secondary, #f3ede4);
 }
 
 .toastHeader {
@@ -93,10 +56,19 @@
   margin-bottom: 0;
 }
 
+.toastTitle {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  font-weight: 600;
+  font-size: 0.875rem;
+  color: var(--text-primary, #2c2420);
+}
+
 .collapseBtn {
   background: none;
   border: none;
-  color: rgba(250, 247, 242, 0.6);
+  color: var(--text-muted, #8a7a72);
   cursor: pointer;
   padding: 0.25rem;
   line-height: 1;
@@ -107,16 +79,7 @@
 }
 
 .collapseBtn:hover {
-  color: var(--text-inverse, #faf7f2);
+  color: var(--text-primary, #2c2420);
-}
-
-.toastTitle {
-  display: flex;
-  align-items: center;
-  gap: 0.5rem;
-  font-weight: 600;
-  font-size: 0.875rem;
-  color: var(--text-inverse, #faf7f2);
 }
 
 .schoolList {
@@ -124,8 +87,6 @@
   flex-direction: column;
   gap: 0.25rem;
   margin-bottom: 0.75rem;
-  max-height: 120px;
-  overflow-y: auto;
 }
 
 .schoolItem {
@@ -133,14 +94,14 @@
   align-items: center;
   justify-content: space-between;
   gap: 0.5rem;
-  padding: 0.25rem 0.375rem;
+  padding: 0.3rem 0.5rem;
-  background: rgba(255, 255, 255, 0.08);
+  background: var(--bg-secondary, #f3ede4);
   border-radius: var(--radius-sm, 4px);
 }
 
 .schoolName {
   font-size: 0.8rem;
-  color: var(--text-inverse, #faf7f2);
+  color: var(--text-primary, #2c2420);
   overflow: hidden;
   text-overflow: ellipsis;
   white-space: nowrap;
@@ -150,7 +111,7 @@
 .removeSchoolBtn {
   background: none;
   border: none;
-  color: rgba(250, 247, 242, 0.5);
+  color: var(--text-muted, #8a7a72);
   cursor: pointer;
   font-size: 1rem;
   padding: 0 0.25rem;
@@ -160,7 +121,50 @@
 }
 
 .removeSchoolBtn:hover {
-  color: var(--text-inverse, #faf7f2);
+  color: var(--accent-coral, #e07256);
+}
+
+.toastActions {
+  display: flex;
+  align-items: center;
+  gap: 0.75rem;
+  padding-top: 0.625rem;
+  border-top: 1px solid var(--border-color, #e8ddd4);
+}
+
+.btnClearAll {
+  background: none;
+  border: none;
+  color: var(--text-muted, #8a7a72);
+  font-size: 0.85rem;
+  font-weight: 500;
+  cursor: pointer;
+  padding: 0.5rem 0.25rem;
+  transition: color 0.2s ease;
+  white-space: nowrap;
+}
+
+.btnClearAll:hover {
+  color: var(--accent-coral, #e07256);
+}
+
+.btnCompare {
+  flex: 1;
+  background: var(--accent-coral, #e07256);
+  color: white;
+  padding: 0.6rem 1.25rem;
+  border-radius: 25px;
+  font-weight: 600;
+  font-size: 0.9rem;
+  text-decoration: none;
+  text-align: center;
+  transition: transform 0.2s ease, background-color 0.2s ease;
+  white-space: nowrap;
+}
+
+.btnCompare:hover {
+  transform: translateY(-1px);
+  background: var(--accent-coral-dark, #c9614a);
 }
 
 @media (max-width: 640px) {
@@ -179,4 +183,4 @@
     width: 100%;
     justify-content: space-between;
   }
-}
+}

nextjs-app/components/ComparisonToast.tsx

@@ -9,7 +9,7 @@ import styles from './ComparisonToast.module.css';
 export function ComparisonToast() {
   const { selectedSchools, clearAll, removeSchool } = useComparison();
   const [mounted, setMounted] = useState(false);
-  const [collapsed, setCollapsed] = useState(false);
+  const [collapsed, setCollapsed] = useState(true);
   const pathname = usePathname();
 
   useEffect(() => {
@@ -62,7 +62,7 @@ export function ComparisonToast() {
               ))}
             </div>
             <div className={styles.toastActions}>
-              <button onClick={clearAll} className="btn btn-tertiary btn-sm" style={{ color: 'rgba(250,247,242,0.7)', borderColor: 'rgba(255,255,255,0.15)' }}>Clear all</button>
+              <button onClick={clearAll} className={styles.btnClearAll}>Clear all</button>
               <Link href="/compare" className={styles.btnCompare}>Compare Now</Link>
             </div>
           </>

nextjs-app/components/ComparisonView.module.css

@@ -31,6 +31,47 @@
 }
 
 
+/* Phase Tabs */
+.phaseTabs {
+  display: flex;
+  gap: 0;
+  margin-bottom: 1.5rem;
+  border: 1px solid var(--border-color, #e5dfd5);
+  border-radius: 8px;
+  overflow: hidden;
+  width: fit-content;
+}
+
+.phaseTab {
+  padding: 0.625rem 1.5rem;
+  font-size: 0.9375rem;
+  font-weight: 500;
+  background: var(--bg-card, white);
+  color: var(--text-secondary, #5c564d);
+  border: none;
+  cursor: pointer;
+  transition: all 0.15s ease;
+  font-family: inherit;
+}
+
+.phaseTab:not(:last-child) {
+  border-right: 1px solid var(--border-color, #e5dfd5);
+}
+
+.phaseTab:hover {
+  background: var(--bg-secondary, #f3ede4);
+}
+
+.phaseTabActive {
+  background: var(--accent-coral, #e07256);
+  color: white;
+  font-weight: 600;
+}
+
+.phaseTabActive:hover {
+  background: var(--accent-coral, #e07256);
+}
+
 /* Metric Selector */
 .metricSelector {
   background: var(--bg-card, white);
@@ -260,12 +301,15 @@
 
 .tableWrapper {
   overflow-x: auto;
+  max-width: 100%;
   margin-top: 1rem;
+  -webkit-overflow-scrolling: touch;
 }
 
 .comparisonTable {
   width: 100%;
-  border-collapse: collapse;
+  border-collapse: separate;
+  border-spacing: 0;
   font-size: 0.9375rem;
 }
 
@@ -279,6 +323,7 @@
   font-weight: 600;
   color: var(--text-primary, #1a1612);
   border-bottom: 2px solid var(--border-color, #e5dfd5);
+  background: var(--bg-secondary, #f3ede4);
   white-space: nowrap;
   text-transform: uppercase;
   font-size: 0.75rem;
@@ -290,6 +335,24 @@
   border-bottom: 1px solid var(--border-color, #e5dfd5);
   color: var(--text-secondary, #5c564d);
   text-align: left;
+  background: var(--bg-card, white);
+}
+
+/* Sticky first column (Year) so labels remain visible while scrolling */
+.comparisonTable th:first-child,
+.comparisonTable td:first-child {
+  position: sticky;
+  left: 0;
+  z-index: 1;
+  box-shadow: 2px 0 4px -2px rgba(26, 22, 18, 0.08);
+}
+
+.comparisonTable thead th:first-child {
+  z-index: 2;
+}
+
+.comparisonTable tbody tr:hover td:first-child {
+  background: var(--bg-secondary, #f3ede4);
 }
 
 .comparisonTable tbody tr:last-child td {

nextjs-app/components/ComparisonView.tsx

@@ -1,6 +1,6 @@
 /**
  * ComparisonView Component
- * Client-side comparison interface with charts and tables
+ * Client-side comparison interface with phase tabs, charts, and tables
  */
 
 'use client';
@@ -12,11 +12,30 @@ import { ComparisonChart } from './ComparisonChart';
 import { SchoolSearchModal } from './SchoolSearchModal';
 import { EmptyState } from './EmptyState';
 import { LoadingSkeleton } from './LoadingSkeleton';
-import type { ComparisonData, MetricDefinition } from '@/lib/types';
+import type { ComparisonData, MetricDefinition, School } from '@/lib/types';
-import { formatPercentage, formatProgress, CHART_COLORS } from '@/lib/utils';
+import { formatPercentage, formatProgress, formatAcademicYear, CHART_COLORS, schoolUrl } from '@/lib/utils';
 import { fetchComparison } from '@/lib/api';
 import styles from './ComparisonView.module.css';
 
+const PRIMARY_CATEGORIES = ['expected', 'higher', 'progress', 'average', 'gender', 'equity', 'context', 'absence', 'trends'];
+const SECONDARY_CATEGORIES = ['gcse'];
+
+const PRIMARY_OPTGROUPS: { label: string; category: string }[] = [
+  { label: 'Expected Standard', category: 'expected' },
+  { label: 'Higher Standard', category: 'higher' },
+  { label: 'Progress Scores', category: 'progress' },
+  { label: 'Average Scores', category: 'average' },
+  { label: 'Gender Performance', category: 'gender' },
+  { label: 'Equity (Disadvantaged)', category: 'equity' },
+  { label: 'School Context', category: 'context' },
+  { label: 'Absence', category: 'absence' },
+  { label: '3-Year Trends', category: 'trends' },
+];
+
+const SECONDARY_OPTGROUPS: { label: string; category: string }[] = [
+  { label: 'GCSE Performance', category: 'gcse' },
+];
+
 interface ComparisonViewProps {
   initialData: Record<string, ComparisonData> | null;
   initialUrns: number[];
@@ -39,6 +58,7 @@ export function ComparisonView({
   const [isModalOpen, setIsModalOpen] = useState(false);
   const [comparisonData, setComparisonData] = useState(initialData);
   const [shareConfirm, setShareConfirm] = useState(false);
+  const [comparePhase, setComparePhase] = useState<'primary' | 'secondary'>('primary');
 
   // Seed context from initialData when component mounts and localStorage is empty
   useEffect(() => {
@@ -84,6 +104,37 @@ export function ComparisonView({
     }
   }, [selectedSchools, selectedMetric, pathname, searchParams, router]);
 
+  // Classify schools by phase using comparison data
+  const classifySchool = (school: School): 'primary' | 'secondary' => {
+    const info = comparisonData?.[school.urn]?.school_info;
+    if (info?.attainment_8_score != null) return 'secondary';
+    if (info?.rwm_expected_pct != null) return 'primary';
+    // Fallback: check yearly data
+    const yearlyData = comparisonData?.[school.urn]?.yearly_data;
+    if (yearlyData?.some((d: any) => d.attainment_8_score != null)) return 'secondary';
+    return 'primary';
+  };
+
+  const primarySchools = selectedSchools.filter(s => classifySchool(s) === 'primary');
+  const secondarySchools = selectedSchools.filter(s => classifySchool(s) === 'secondary');
+
+  // Auto-select tab with more schools
+  useEffect(() => {
+    if (comparisonData && selectedSchools.length > 0) {
+      if (secondarySchools.length > primarySchools.length) {
+        setComparePhase('secondary');
+      } else {
+        setComparePhase('primary');
+      }
+    }
+  }, [comparisonData]); // eslint-disable-line react-hooks/exhaustive-deps
+
+  const handlePhaseChange = (phase: 'primary' | 'secondary') => {
+    setComparePhase(phase);
+    const defaultMetric = phase === 'secondary' ? 'attainment_8_score' : 'rwm_expected_pct';
+    setSelectedMetric(defaultMetric);
+  };
+
   const handleMetricChange = (metric: string) => {
     setSelectedMetric(metric);
   };
@@ -100,6 +151,12 @@ export function ComparisonView({
     } catch { /* fallback: do nothing */ }
   };
 
+  const isPrimary = comparePhase === 'primary';
+  const allowedCategories = isPrimary ? PRIMARY_CATEGORIES : SECONDARY_CATEGORIES;
+  const optgroups = isPrimary ? PRIMARY_OPTGROUPS : SECONDARY_OPTGROUPS;
+  const filteredMetrics = metrics.filter(m => allowedCategories.includes(m.category));
+  const activeSchools = isPrimary ? primarySchools : secondarySchools;
+
   // Get metric definition
   const currentMetricDef = metrics.find((m) => m.key === selectedMetric);
   const metricLabel = currentMetricDef?.label || selectedMetric;
@@ -129,10 +186,20 @@ export function ComparisonView({
     );
   }
 
+  // Build filtered comparison data for active phase
+  const activeComparisonData: Record<string, ComparisonData> = {};
+  if (comparisonData) {
+    activeSchools.forEach(s => {
+      if (comparisonData[s.urn]) {
+        activeComparisonData[s.urn] = comparisonData[s.urn];
+      }
+    });
+  }
+
   // Get years for table
   const years =
-    comparisonData && Object.keys(comparisonData).length > 0
+    Object.keys(activeComparisonData).length > 0
-      ? comparisonData[Object.keys(comparisonData)[0]].yearly_data.map((d) => d.year)
+      ? activeComparisonData[Object.keys(activeComparisonData)[0]].yearly_data.map((d) => d.year)
       : [];
 
   return (
@@ -158,208 +225,206 @@ export function ComparisonView({
         </div>
       </header>
 
-      {/* Metric Selector */}
+      {/* Phase Tabs */}
-      <section className={styles.metricSelector}>
+      <div className={styles.phaseTabs}>
-        <label htmlFor="metric-select" className={styles.metricLabel}>
+        <button
-          Select Metric:
+          className={`${styles.phaseTab} ${isPrimary ? styles.phaseTabActive : ''}`}
-        </label>
+          onClick={() => handlePhaseChange('primary')}
-        <select
-          id="metric-select"
-          value={selectedMetric}
-          onChange={(e) => handleMetricChange(e.target.value)}
-          className={styles.metricSelect}
         >
-          <optgroup label="Expected Standard">
+          Primary ({primarySchools.length})
-            {metrics.filter(m => m.category === 'expected').map((metric) => (
+        </button>
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
+        <button
-            ))}
+          className={`${styles.phaseTab} ${!isPrimary ? styles.phaseTabActive : ''}`}
-          </optgroup>
+          onClick={() => handlePhaseChange('secondary')}
-          <optgroup label="Higher Standard">
+        >
-            {metrics.filter(m => m.category === 'higher').map((metric) => (
+          Secondary ({secondarySchools.length})
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
+        </button>
-            ))}
+      </div>
-          </optgroup>
-          <optgroup label="Progress Scores">
-            {metrics.filter(m => m.category === 'progress').map((metric) => (
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
-            ))}
-          </optgroup>
-          <optgroup label="Average Scores">
-            {metrics.filter(m => m.category === 'average').map((metric) => (
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
-            ))}
-          </optgroup>
-          <optgroup label="Gender Performance">
-            {metrics.filter(m => m.category === 'gender').map((metric) => (
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
-            ))}
-          </optgroup>
-          <optgroup label="Equity (Disadvantaged)">
-            {metrics.filter(m => m.category === 'disadvantaged').map((metric) => (
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
-            ))}
-          </optgroup>
-          <optgroup label="School Context">
-            {metrics.filter(m => m.category === 'context').map((metric) => (
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
-            ))}
-          </optgroup>
-          <optgroup label="3-Year Trends">
-            {metrics.filter(m => m.category === '3yr').map((metric) => (
-              <option key={metric.key} value={metric.key}>{metric.label}</option>
-            ))}
-          </optgroup>
-        </select>
-        {currentMetricDef?.description && (
-          <p className={styles.metricDescription}>{currentMetricDef.description}</p>
-        )}
-      </section>
 
-      {/* Progress score explanation */}
+      {activeSchools.length === 0 ? (
-      {selectedMetric.includes('progress') && (
+        <EmptyState
-        <p className={styles.progressNote}>
+          title={`No ${comparePhase} schools in your comparison`}
-          Progress scores measure pupils' progress from KS1 to KS2. A score of 0 equals the national average; positive scores are above average.
+          message={`Add ${comparePhase} schools from search results to compare them here.`}
-        </p>
+          action={{
-      )}
+            label: '+ Add Schools',
-
+            onClick: () => setIsModalOpen(true),
-      {/* School Cards */}
+          }}
-      <section className={styles.schoolsSection}>
+        />
-        <div className={styles.schoolsGrid}>
+      ) : (
-          {selectedSchools.map((school, index) => (
+        <>
-            <div
+          {/* Metric Selector */}
-              key={school.urn}
+          <section className={styles.metricSelector}>
-              className={styles.schoolCard}
+            <label htmlFor="metric-select" className={styles.metricLabel}>
-              style={{ borderLeft: `3px solid ${CHART_COLORS[index % CHART_COLORS.length]}` }}
+              Select Metric:
+            </label>
+            <select
+              id="metric-select"
+              value={selectedMetric}
+              onChange={(e) => handleMetricChange(e.target.value)}
+              className={styles.metricSelect}
             >
-              <button
+              {optgroups.map(({ label, category }) => {
-                onClick={() => handleRemoveSchool(school.urn)}
+                const groupMetrics = filteredMetrics.filter(m => m.category === category);
-                className={styles.removeButton}
+                if (groupMetrics.length === 0) return null;
-                aria-label={`Remove ${school.school_name}`}
+                return (
-                title="Remove from comparison"
+                  <optgroup key={category} label={label}>
-              >
+                    {groupMetrics.map((metric) => (
-                ×
+                      <option key={metric.key} value={metric.key}>{metric.label}</option>
-              </button>
+                    ))}
-              <h2 className={styles.schoolName}>
+                  </optgroup>
-                <a href={`/school/${school.urn}`}>{school.school_name}</a>
+                );
-              </h2>
+              })}
-              <div className={styles.schoolMeta}>
+            </select>
-                {school.local_authority && (
+            {currentMetricDef?.description && (
-                  <span className={styles.metaItem}>{school.local_authority}</span>
+              <p className={styles.metricDescription}>{currentMetricDef.description}</p>
-                )}
+            )}
-                {school.school_type && (
+          </section>
-                  <span className={styles.metaItem}>{school.school_type}</span>
-                )}
-              </div>
 
-              {/* Latest metric value */}
+          {/* Progress score explanation */}
-              {comparisonData && comparisonData[school.urn] && (
+          {selectedMetric.includes('progress') && (
-                <div className={styles.latestValue}>
+            <p className={styles.progressNote}>
-                  <div className={styles.latestLabel}>{metricLabel}</div>
+              Progress scores measure pupils&apos; progress from KS1 to KS2. A score of 0 equals the national average; positive scores are above average.
-                  <div className={styles.latestNumber} style={{ color: CHART_COLORS[index % CHART_COLORS.length] }}>
+            </p>
-                    <span
+          )}
-                      style={{
-                        display: 'inline-block',
-                        width: '10px',
-                        height: '10px',
-                        borderRadius: '50%',
-                        background: CHART_COLORS[index % CHART_COLORS.length],
-                        marginRight: '0.4rem',
-                        verticalAlign: 'middle',
-                      }}
-                    />
-                    {(() => {
-                      const yearlyData = comparisonData[school.urn].yearly_data;
-                      if (yearlyData.length === 0) return '-';
 
-                      const latestData = yearlyData[yearlyData.length - 1];
+          {/* School Cards */}
-                      const value = latestData[selectedMetric as keyof typeof latestData];
+          <section className={styles.schoolsSection}>
-
+            <div className={styles.schoolsGrid}>
-                      if (value === null || value === undefined) return '-';
+              {activeSchools.map((school, index) => (
-
+                <div
-                      // Format based on metric type
+                  key={school.urn}
-                      if (selectedMetric.includes('progress')) {
+                  className={styles.schoolCard}
-                        return formatProgress(value as number);
+                  style={{ borderLeft: `3px solid ${CHART_COLORS[index % CHART_COLORS.length]}` }}
-                      } else if (selectedMetric.includes('pct') || selectedMetric.includes('rate')) {
+                >
-                        return formatPercentage(value as number);
+                  <button
-                      } else {
+                    onClick={() => handleRemoveSchool(school.urn)}
-                        return typeof value === 'number' ? value.toFixed(1) : String(value);
+                    className={styles.removeButton}
-                      }
+                    aria-label={`Remove ${school.school_name}`}
-                    })()}
+                    title="Remove from comparison"
+                  >
+                    ×
+                  </button>
+                  <h2 className={styles.schoolName}>
+                    <a href={schoolUrl(school.urn, school.school_name)}>{school.school_name}</a>
+                  </h2>
+                  <div className={styles.schoolMeta}>
+                    {school.local_authority && (
+                      <span className={styles.metaItem}>{school.local_authority}</span>
+                    )}
+                    {school.school_type && (
+                      <span className={styles.metaItem}>{school.school_type}</span>
+                    )}
                   </div>
+
+                  {/* Latest metric value */}
+                  {activeComparisonData[school.urn] && (
+                    <div className={styles.latestValue}>
+                      <div className={styles.latestLabel}>{metricLabel}</div>
+                      <div className={styles.latestNumber} style={{ color: CHART_COLORS[index % CHART_COLORS.length] }}>
+                        <span
+                          style={{
+                            display: 'inline-block',
+                            width: '10px',
+                            height: '10px',
+                            borderRadius: '50%',
+                            background: CHART_COLORS[index % CHART_COLORS.length],
+                            marginRight: '0.4rem',
+                            verticalAlign: 'middle',
+                          }}
+                        />
+                        {(() => {
+                          const yearlyData = activeComparisonData[school.urn].yearly_data;
+                          if (yearlyData.length === 0) return '-';
+
+                          const latestData = yearlyData[yearlyData.length - 1];
+                          const value = latestData[selectedMetric as keyof typeof latestData];
+
+                          if (value === null || value === undefined) return '-';
+
+                          if (selectedMetric.includes('progress')) {
+                            return formatProgress(value as number);
+                          } else if (selectedMetric.includes('pct') || selectedMetric.includes('rate')) {
+                            return formatPercentage(value as number);
+                          } else {
+                            return typeof value === 'number' ? value.toFixed(1) : String(value);
+                          }
+                        })()}
+                      </div>
+                    </div>
+                  )}
                 </div>
-              )}
+              ))}
             </div>
-          ))}
+          </section>
-        </div>
-      </section>
 
-      {/* Comparison Chart */}
+          {/* Comparison Chart */}
-      {comparisonData && Object.keys(comparisonData).length > 0 ? (
+          {Object.keys(activeComparisonData).length > 0 ? (
-        <section className={styles.chartSection}>
+            <section className={styles.chartSection}>
-          <h2 className={styles.sectionTitle}>Performance Over Time</h2>
+              <h2 className={styles.sectionTitle}>Performance Over Time</h2>
-          <div className={styles.chartContainer}>
+              <div className={styles.chartContainer}>
-            <ComparisonChart
+                <ComparisonChart
-              comparisonData={comparisonData}
+                  comparisonData={activeComparisonData}
-              metric={selectedMetric}
+                  metric={selectedMetric}
-              metricLabel={metricLabel}
+                  metricLabel={metricLabel}
-            />
+                />
-          </div>
+              </div>
-        </section>
+            </section>
-      ) : selectedSchools.length > 0 ? (
+          ) : activeSchools.length > 0 ? (
-        <section className={styles.chartSection}>
+            <section className={styles.chartSection}>
-          <LoadingSkeleton type="list" />
+              <LoadingSkeleton type="list" />
-        </section>
+            </section>
-      ) : null}
+          ) : null}
 
-      {/* Comparison Table */}
+          {/* Comparison Table */}
-      {comparisonData && Object.keys(comparisonData).length > 0 && years.length > 0 && (
+          {Object.keys(activeComparisonData).length > 0 && years.length > 0 && (
-        <section className={styles.tableSection}>
+            <section className={styles.tableSection}>
-          <h2 className={styles.sectionTitle}>Detailed Comparison</h2>
+              <h2 className={styles.sectionTitle}>Detailed Comparison</h2>
-          <div className={styles.tableWrapper}>
+              <div className={styles.tableWrapper}>
-            <table className={styles.comparisonTable}>
+                <table className={styles.comparisonTable}>
-              <thead>
+                  <thead>
-                <tr>
+                    <tr>
-                  <th>Year</th>
+                      <th>Year</th>
-                  {selectedSchools.map((school) => (
+                      {activeSchools.map((school) => (
-                    <th key={school.urn}>{school.school_name}</th>
+                        <th key={school.urn}>{school.school_name}</th>
-                  ))}
+                      ))}
-                </tr>
+                    </tr>
-              </thead>
+                  </thead>
-              <tbody>
+                  <tbody>
-                {years.map((year) => (
+                    {years.map((year) => (
-                  <tr key={year}>
+                      <tr key={year}>
-                    <td className={styles.yearCell}>{year}</td>
+                        <td className={styles.yearCell}>{formatAcademicYear(year)}</td>
-                    {selectedSchools.map((school) => {
+                        {activeSchools.map((school) => {
-                      const schoolData = comparisonData[school.urn];
+                          const schoolData = activeComparisonData[school.urn];
-                      if (!schoolData) return <td key={school.urn}>-</td>;
+                          if (!schoolData) return <td key={school.urn}>-</td>;
 
-                      const yearData = schoolData.yearly_data.find((d) => d.year === year);
+                          const yearData = schoolData.yearly_data.find((d) => d.year === year);
-                      if (!yearData) return <td key={school.urn}>-</td>;
+                          if (!yearData) return <td key={school.urn}>-</td>;
 
-                      const value = yearData[selectedMetric as keyof typeof yearData];
+                          const value = yearData[selectedMetric as keyof typeof yearData];
 
-                      if (value === null || value === undefined) {
+                          if (value === null || value === undefined) {
-                        return <td key={school.urn}>-</td>;
+                            return <td key={school.urn}>-</td>;
-                      }
+                          }
 
-                      // Format based on metric type
+                          let displayValue: string;
-                      let displayValue: string;
+                          if (selectedMetric.includes('progress')) {
-                      if (selectedMetric.includes('progress')) {
+                            displayValue = formatProgress(value as number);
-                        displayValue = formatProgress(value as number);
+                          } else if (selectedMetric.includes('pct') || selectedMetric.includes('rate')) {
-                      } else if (selectedMetric.includes('pct') || selectedMetric.includes('rate')) {
+                            displayValue = formatPercentage(value as number);
-                        displayValue = formatPercentage(value as number);
+                          } else {
-                      } else {
+                            displayValue = typeof value === 'number' ? value.toFixed(1) : String(value);
-                        displayValue = typeof value === 'number' ? value.toFixed(1) : String(value);
+                          }
-                      }
 
-                      return <td key={school.urn}>{displayValue}</td>;
+                          return <td key={school.urn}>{displayValue}</td>;
-                    })}
+                        })}
-                  </tr>
+                      </tr>
-                ))}
+                    ))}
-              </tbody>
+                  </tbody>
-            </table>
+                </table>
-          </div>
+              </div>
-        </section>
+            </section>
+          )}
+        </>
       )}
 
       {/* School Search Modal */}

nextjs-app/components/DeltaChip.module.css

@@ -0,0 +1,38 @@
+.chip {
+  display: inline-flex;
+  align-items: baseline;
+  gap: 0.25rem;
+  padding: 0.2rem 0.55rem;
+  font-size: 0.75rem;
+  font-weight: 600;
+  line-height: 1;
+  border-radius: 999px;
+  white-space: nowrap;
+  letter-spacing: 0.01em;
+  font-variant-numeric: tabular-nums;
+}
+
+.sm {
+  padding: 0.1rem 0.4rem;
+  font-size: 0.6875rem;
+}
+
+.suffix {
+  font-weight: 500;
+  opacity: 0.75;
+}
+
+.good {
+  background: var(--accent-teal-bg, rgba(45, 125, 125, 0.12));
+  color: var(--accent-teal, #2d7d7d);
+}
+
+.bad {
+  background: var(--accent-coral-bg, rgba(224, 114, 86, 0.12));
+  color: var(--accent-coral, #e07256);
+}
+
+.neutral {
+  background: var(--bg-secondary, #f3ede4);
+  color: var(--text-muted, #8a847a);
+}

nextjs-app/components/DeltaChip.tsx

@@ -0,0 +1,57 @@
+/**
+ * DeltaChip — small coloured chip showing how a value compares to a baseline.
+ *
+ * Example: <DeltaChip value={70} baseline={60} unit="pts" />  →  "+10 pts"
+ *
+ * Colours (reuse globals.css status tokens):
+ *   above baseline  → statusGood   (teal)
+ *   below baseline  → statusBad    (coral)
+ *   within ±tolerance → statusWarn (gold, "in line")
+ */
+
+import styles from './DeltaChip.module.css';
+
+interface DeltaChipProps {
+  value: number | null | undefined;
+  baseline: number | null | undefined;
+  /** Unit suffix for the delta (e.g. "pts", "%") */
+  unit?: string;
+  /** Absolute delta below which the chip is treated as neutral */
+  tolerance?: number;
+  /** Override label when we want "vs national" under a number */
+  suffix?: string;
+  /** Smaller variant for inline use next to metric values */
+  size?: 'sm' | 'md';
+}
+
+export function DeltaChip({
+  value,
+  baseline,
+  unit = 'pts',
+  tolerance = 1,
+  suffix,
+  size = 'md',
+}: DeltaChipProps) {
+  if (value == null || baseline == null) return null;
+
+  const delta = value - baseline;
+  const rounded = Math.round(delta);
+
+  let tone: 'good' | 'bad' | 'neutral';
+  if (Math.abs(delta) < tolerance) tone = 'neutral';
+  else if (delta > 0) tone = 'good';
+  else tone = 'bad';
+
+  const toneClass =
+    tone === 'good' ? styles.good : tone === 'bad' ? styles.bad : styles.neutral;
+
+  const sign = rounded > 0 ? '+' : '';
+  const label = `${sign}${rounded} ${unit}`.trim();
+
+  return (
+    <span className={`${styles.chip} ${toneClass} ${size === 'sm' ? styles.sm : ''}`}>
+      {label}
+      {suffix && <span className={styles.suffix}>{suffix}</span>}
+    </span>
+  );
+}

nextjs-app/components/FilterBar.module.css

@@ -32,8 +32,12 @@
   padding: 1.25rem 2.5rem;
 }
 
+.heroMode .searchSection {
+  margin-bottom: 0;
+}
+
 .searchSection {
-  margin-bottom: 1rem;
+  margin-bottom: 0;
 }
 
 .omniBoxContainer {
@@ -84,30 +88,49 @@
 
 .filters {
   display: flex;
-  gap: 0.75rem;
+  gap: 0.625rem;
   flex-wrap: wrap;
+  margin-top: 0.625rem;
+  padding-top: 0.625rem;
+  border-top: 1px solid var(--border-color, #e5dfd5);
 }
 
 .filterSelect {
+  appearance: none;
+  -webkit-appearance: none;
   flex: 1;
-  min-width: 200px;
+  min-width: 180px;
-  padding: 0.75rem 1rem;
+  padding: 0.625rem 2.25rem 0.625rem 1rem;
-  font-size: 0.95rem;
+  font-size: 0.875rem;
-  border: 1px solid var(--border-color, #e5dfd5);
+  font-weight: 500;
-  border-radius: 6px;
+  font-family: inherit;
-  background: var(--bg-card, white);
+  border: 1.5px solid var(--border-color, #e5dfd5);
+  border-radius: 8px;
+  background-color: var(--bg-card, white);
+  background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='10' height='6' viewBox='0 0 10 6'%3E%3Cpath d='M1 1l4 4 4-4' stroke='%238a847a' stroke-width='1.5' fill='none' stroke-linecap='round' stroke-linejoin='round'/%3E%3C/svg%3E");
+  background-repeat: no-repeat;
+  background-position: right 0.875rem center;
+  background-size: 10px 6px;
   cursor: pointer;
   outline: none;
   color: var(--text-primary, #1a1612);
+  transition: border-color 0.15s ease, box-shadow 0.15s ease;
+}
+
+.filterSelect:hover {
+  border-color: var(--text-muted, #8a847a);
 }
 
 .filterSelect:focus {
   border-color: var(--accent-coral, #e07256);
+  box-shadow: 0 0 0 3px rgba(224, 114, 86, 0.12);
 }
 
 .clearButton {
-  padding: 0.75rem 1.25rem;
+  padding: 0.4rem 1rem;
-  font-size: 0.95rem;
+  font-size: 0.8125rem;
+  font-weight: 500;
+  border-radius: 999px;
 }
 
 @media (max-width: 768px) {
@@ -130,6 +153,19 @@
   .filterSelect {
     min-width: 100%;
   }
+
+  .controlsRow {
+    gap: 0.5rem;
+  }
+
+  .controlsRow .advancedToggle {
+    margin-left: 0;
+  }
+
+  .controlSelect {
+    flex: 1;
+    min-width: 140px;
+  }
 }
 
 .radiusWrapper {
@@ -140,17 +176,104 @@
 }
 
 .radiusLabel {
-  font-size: 0.875rem;
+  font-size: 0.8125rem;
-  color: var(--text-secondary);
+  font-weight: 500;
+  color: var(--text-secondary, #5a554d);
   white-space: nowrap;
 }
 
-.radiusSelect {
+/* ── Controls row (radius + phase + advanced toggle) ─── */
-  padding: 0.375rem 0.75rem;
+.controlsRow {
-  border: 1px solid var(--border-color, #e0ddd8);
+  display: flex;
-  border-radius: var(--radius-md);
+  align-items: center;
-  background: var(--bg-card);
+  gap: 0.5rem;
-  color: var(--text-secondary);
+  flex-wrap: wrap;
-  font-size: 0.875rem;
+  margin-top: 0.875rem;
-  cursor: pointer;
+  padding-top: 0.875rem;
+  border-top: 1px solid var(--border-color, #e5dfd5);
+}
+
+.controlsRow .advancedToggle {
+  margin-left: auto;
+}
+
+.radiusControl {
+  display: flex;
+  align-items: center;
+  gap: 0.375rem;
+  flex-shrink: 0;
+}
+
+/* Pill-style inline filter controls (radius + phase) */
+.controlSelect {
+  appearance: none;
+  -webkit-appearance: none;
+  padding: 0.4rem 2rem 0.4rem 0.875rem;
+  font-size: 0.8125rem;
+  font-weight: 500;
+  font-family: inherit;
+  border: 1.5px solid var(--border-color, #e5dfd5);
+  border-radius: 999px;
+  background-color: var(--bg-card, white);
+  background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='10' height='6' viewBox='0 0 10 6'%3E%3Cpath d='M1 1l4 4 4-4' stroke='%238a847a' stroke-width='1.5' fill='none' stroke-linecap='round' stroke-linejoin='round'/%3E%3C/svg%3E");
+  background-repeat: no-repeat;
+  background-position: right 0.65rem center;
+  background-size: 10px 6px;
+  color: var(--text-primary, #1a1612);
+  cursor: pointer;
+  outline: none;
+  transition: border-color 0.15s ease, background-color 0.15s ease, box-shadow 0.15s ease;
+  white-space: nowrap;
+}
+
+.controlSelect:hover {
+  border-color: var(--text-muted, #8a847a);
+  background-color: var(--bg-secondary, #f8f4ef);
+}
+
+.controlSelect:focus {
+  border-color: var(--accent-coral, #e07256);
+  box-shadow: 0 0 0 3px rgba(224, 114, 86, 0.12);
+}
+
+/* ── Advanced filters toggle ─────────────────────────── */
+
+.advancedToggle {
+  display: inline-flex;
+  align-items: center;
+  gap: 0.375rem;
+  background: none;
+  border: 1.5px solid var(--border-color, #e5dfd5);
+  border-radius: 999px;
+  padding: 0.4rem 0.875rem;
+  font-size: 0.8125rem;
+  font-weight: 500;
+  color: var(--text-secondary, #5a554d);
+  cursor: pointer;
+  font-family: inherit;
+  transition: all 0.15s ease;
+  white-space: nowrap;
+}
+
+.advancedToggle:hover {
+  border-color: var(--text-muted, #8a847a);
+  background-color: var(--bg-secondary, #f8f4ef);
+  color: var(--text-primary, #1a1612);
+}
+
+.chevronDown,
+.chevronUp {
+  display: inline-block;
+  width: 0;
+  height: 0;
+  border-left: 3.5px solid transparent;
+  border-right: 3.5px solid transparent;
+}
+
+.chevronDown {
+  border-top: 4.5px solid currentColor;
+}
+
+.chevronUp {
+  border-bottom: 4.5px solid currentColor;
 }

nextjs-app/components/FilterBar.tsx

@@ -1,77 +1,106 @@
-'use client';
+"use client";
 
-import { useState, useCallback, useTransition, useRef, useEffect } from 'react';
+import { useState, useCallback, useTransition, useRef, useEffect } from "react";
-import { useRouter, useSearchParams, usePathname } from 'next/navigation';
+import { useRouter, useSearchParams, usePathname } from "next/navigation";
-import { isValidPostcode } from '@/lib/utils';
+import { isValidPostcode } from "@/lib/utils";
-import type { Filters } from '@/lib/types';
+import type { Filters, ResultFilters } from "@/lib/types";
-import styles from './FilterBar.module.css';
+import styles from "./FilterBar.module.css";
 
 interface FilterBarProps {
   filters: Filters;
   isHero?: boolean;
+  resultFilters?: ResultFilters;
 }
 
-export function FilterBar({ filters, isHero }: FilterBarProps) {
+export function FilterBar({ filters, isHero, resultFilters }: FilterBarProps) {
   const router = useRouter();
   const pathname = usePathname();
   const searchParams = useSearchParams();
   const [isPending, startTransition] = useTransition();
   const inputRef = useRef<HTMLInputElement>(null);
 
-  const currentSearch = searchParams.get('search') || '';
+  const currentSearch = searchParams.get("search") || "";
-  const currentPostcode = searchParams.get('postcode') || '';
+  const currentPostcode = searchParams.get("postcode") || "";
-  const currentRadius = searchParams.get('radius') || '1';
+  const currentRadius = searchParams.get("radius") || "1";
   const initialOmniValue = currentPostcode || currentSearch;
 
   const [omniValue, setOmniValue] = useState(initialOmniValue);
 
-  const currentLA = searchParams.get('local_authority') || '';
+  const currentLA = searchParams.get("local_authority") || "";
-  const currentType = searchParams.get('school_type') || '';
+  const currentType = searchParams.get("school_type") || "";
+  const currentPhase = searchParams.get("phase") || "";
+  const currentGender = searchParams.get("gender") || "";
+  const currentAdmissionsPolicy = searchParams.get("admissions_policy") || "";
+  const currentHasSixthForm = searchParams.get("has_sixth_form") || "";
+
+  // Count active dropdown filters (not search/postcode, not phase since it's always visible)
+  const activeDropdownFilters = [
+    currentLA,
+    currentType,
+    currentGender,
+    currentAdmissionsPolicy,
+    currentHasSixthForm,
+  ].filter(Boolean);
+  const hasActiveDropdownFilters = activeDropdownFilters.length > 0;
+  const [filtersOpen, setFiltersOpen] = useState(hasActiveDropdownFilters);
+
+  // Auto-open if filters become active (e.g. URL change)
+  useEffect(() => {
+    if (hasActiveDropdownFilters) setFiltersOpen(true);
+  }, [hasActiveDropdownFilters]);
 
   useEffect(() => {
     const handleKeyDown = (e: KeyboardEvent) => {
-      // Focus search on '/' or Ctrl+K, but not when typing in an input
+      if (
-      if ((e.key === '/' || (e.key === 'k' && (e.ctrlKey || e.metaKey))) &&
+        (e.key === "/" || (e.key === "k" && (e.ctrlKey || e.metaKey))) &&
-          document.activeElement?.tagName !== 'INPUT' &&
+        document.activeElement?.tagName !== "INPUT" &&
-          document.activeElement?.tagName !== 'TEXTAREA' &&
+        document.activeElement?.tagName !== "TEXTAREA" &&
-          document.activeElement?.tagName !== 'SELECT') {
+        document.activeElement?.tagName !== "SELECT"
+      ) {
         e.preventDefault();
         inputRef.current?.focus();
       }
     };
-    document.addEventListener('keydown', handleKeyDown);
+    document.addEventListener("keydown", handleKeyDown);
-    return () => document.removeEventListener('keydown', handleKeyDown);
+    return () => document.removeEventListener("keydown", handleKeyDown);
   }, []);
 
-  const updateURL = useCallback((updates: Record<string, string>) => {
+  const updateURL = useCallback(
-    const params = new URLSearchParams(searchParams);
+    (updates: Record<string, string>) => {
+      const params = new URLSearchParams(searchParams);
 
-    Object.entries(updates).forEach(([key, value]) => {
+      Object.entries(updates).forEach(([key, value]) => {
-      if (value && value !== '') {
+        if (value && value !== "") {
-        params.set(key, value);
+          params.set(key, value);
-      } else {
+        } else {
-        params.delete(key);
+          params.delete(key);
-      }
+        }
-    });
+      });
 
-    params.delete('page');
+      params.delete("page");
 
-    startTransition(() => {
+      startTransition(() => {
-      router.push(`${pathname}?${params.toString()}`);
+        router.push(`${pathname}?${params.toString()}`);
-    });
+      });
-  }, [searchParams, pathname, router]);
+    },
+    [searchParams, pathname, router],
+  );
 
   const handleSearchSubmit = (e: React.FormEvent) => {
     e.preventDefault();
     if (!omniValue.trim()) {
-      updateURL({ search: '', postcode: '', radius: '' });
+      updateURL({ search: "", postcode: "", radius: "" });
       return;
     }
 
     if (isValidPostcode(omniValue)) {
-      updateURL({ postcode: omniValue.trim().toUpperCase(), radius: currentRadius || '1', search: '' });
+      updateURL({
+        postcode: omniValue.trim().toUpperCase(),
+        radius: currentRadius || "1",
+        search: "",
+      });
     } else {
-      updateURL({ search: omniValue.trim(), postcode: '', radius: '' });
+      updateURL({ search: omniValue.trim(), postcode: "", radius: "" });
     }
   };
 
@@ -80,16 +109,38 @@ export function FilterBar({ filters, isHero }: FilterBarProps) {
   };
 
   const handleClearFilters = () => {
-    setOmniValue('');
+    setOmniValue("");
     startTransition(() => {
       router.push(pathname);
     });
   };
 
-  const hasActiveFilters = currentSearch || currentLA || currentType || currentPostcode;
+  const hasActiveFilters =
+    currentSearch ||
+    currentLA ||
+    currentType ||
+    currentPhase ||
+    currentPostcode ||
+    currentGender ||
+    currentAdmissionsPolicy ||
+    currentHasSixthForm;
+
+  // Use result-scoped filter values when available, fall back to global
+  const laOptions =
+    resultFilters?.local_authorities ?? filters.local_authorities;
+  const typeOptions = resultFilters?.school_types ?? filters.school_types;
+  const phaseOptions = resultFilters?.phases ?? filters.phases ?? [];
+  const genderOptions = resultFilters?.genders ?? filters.genders ?? [];
+  const admissionsPolicyOptions =
+    resultFilters?.admissions_policies ?? filters.admissions_policies ?? [];
+
+  const isSecondaryMode =
+    currentPhase === "secondary" || genderOptions.length > 0;
 
   return (
-    <div className={`${styles.filterBar} ${isPending ? styles.isLoading : ''} ${isHero ? styles.heroMode : ''}`}>
+    <div
+      className={`${styles.filterBar} ${isPending ? styles.isLoading : ""} ${isHero ? styles.heroMode : ""}`}
+    >
       <form onSubmit={handleSearchSubmit} className={styles.searchSection}>
         <div className={styles.omniBoxContainer}>
           <input
@@ -97,67 +148,171 @@ export function FilterBar({ filters, isHero }: FilterBarProps) {
             type="search"
             value={omniValue}
             onChange={(e) => setOmniValue(e.target.value)}
-            placeholder="Search by school name or postcode (e.g., SW1A 1AA)..."
+            placeholder="School name or postcode"
             className={styles.omniInput}
           />
-          <button type="submit" className={`btn btn-primary ${styles.searchButton}`} disabled={isPending}>
+          <button
-            {isPending ? <div className={styles.spinner}></div> : 'Search'}
+            type="submit"
+            className={`btn btn-primary ${styles.searchButton}`}
+            disabled={isPending}
+          >
+            {isPending ? <div className={styles.spinner}></div> : "Search"}
           </button>
         </div>
-        {currentPostcode && (
-          <div className={styles.radiusWrapper}>
-            <label className={styles.radiusLabel}>Within:</label>
-            <select
-              value={currentRadius}
-              onChange={e => updateURL({ radius: e.target.value })}
-              className={styles.radiusSelect}
-              disabled={isPending}
-            >
-              <option value="0.5">0.5 miles</option>
-              <option value="1">1 mile</option>
-              <option value="3">3 miles</option>
-              <option value="5">5 miles</option>
-              <option value="10">10 miles</option>
-            </select>
-          </div>
-        )}
       </form>
 
-      <div className={styles.filters}>
+      {!isHero && (
-        <select
+        <>
-          value={currentLA}
+          <div className={styles.controlsRow}>
-          onChange={(e) => handleFilterChange('local_authority', e.target.value)}
+            {currentPostcode && (
-          className={styles.filterSelect}
+              <div className={styles.radiusControl}>
-          disabled={isPending}
+                <label className={styles.radiusLabel}>Within:</label>
-        >
+                <select
-          <option value="">All Local Authorities</option>
+                  value={currentRadius}
-          {filters.local_authorities.map((la) => (
+                  onChange={(e) => updateURL({ radius: e.target.value })}
-            <option key={la} value={la}>
+                  className={styles.controlSelect}
-              {la}
+                  disabled={isPending}
-            </option>
+                >
-          ))}
+                  <option value="0.5">0.5 miles</option>
-        </select>
+                  <option value="1">1 mile</option>
+                  <option value="3">3 miles</option>
+                  <option value="5">5 miles</option>
+                </select>
+              </div>
+            )}
 
-        <select
+            {phaseOptions.length > 0 && (
-          value={currentType}
+              <select
-          onChange={(e) => handleFilterChange('school_type', e.target.value)}
+                value={currentPhase}
-          className={styles.filterSelect}
+                onChange={(e) => handleFilterChange("phase", e.target.value)}
-          disabled={isPending}
+                className={styles.controlSelect}
-        >
+                disabled={isPending}
-          <option value="">All School Types</option>
+              >
-          {filters.school_types.map((type) => (
+                <option value="">All Phases</option>
-            <option key={type} value={type}>
+                {phaseOptions.map((p) => (
-              {type}
+                  <option key={p} value={p.toLowerCase()}>
-            </option>
+                    {p}
-          ))}
+                  </option>
-        </select>
+                ))}
+              </select>
+            )}
 
-        {hasActiveFilters && (
+            <button
-          <button onClick={handleClearFilters} className={`btn btn-tertiary ${styles.clearButton}`} type="button" disabled={isPending}>
+              type="button"
-            Clear Filters
+              className={styles.advancedToggle}
-          </button>
+              onClick={() => setFiltersOpen((v) => !v)}
-        )}
+            >
-      </div>
+              Advanced
+              {hasActiveDropdownFilters
+                ? ` (${activeDropdownFilters.length})`
+                : ""}
+              <span
+                className={filtersOpen ? styles.chevronUp : styles.chevronDown}
+              />
+            </button>
+
+            {hasActiveFilters && (
+              <button
+                onClick={handleClearFilters}
+                className={`btn btn-tertiary ${styles.clearButton}`}
+                type="button"
+                disabled={isPending}
+              >
+                Clear
+              </button>
+            )}
+          </div>
+
+          {filtersOpen && (
+            <div className={styles.filters}>
+              <select
+                value={currentLA}
+                onChange={(e) =>
+                  handleFilterChange("local_authority", e.target.value)
+                }
+                className={styles.filterSelect}
+                disabled={isPending}
+              >
+                <option value="">All Local Authorities</option>
+                {laOptions.map((la) => (
+                  <option key={la} value={la}>
+                    {la}
+                  </option>
+                ))}
+              </select>
+
+              <select
+                value={currentType}
+                onChange={(e) =>
+                  handleFilterChange("school_type", e.target.value)
+                }
+                className={styles.filterSelect}
+                disabled={isPending}
+              >
+                <option value="">All School Types</option>
+                {typeOptions.map((type) => (
+                  <option key={type} value={type}>
+                    {type}
+                  </option>
+                ))}
+              </select>
+
+              {isSecondaryMode && (
+                <>
+                  {genderOptions.length > 0 && (
+                    <select
+                      value={currentGender}
+                      onChange={(e) =>
+                        handleFilterChange("gender", e.target.value)
+                      }
+                      className={styles.filterSelect}
+                      disabled={isPending}
+                    >
+                      <option value="">Boys, Girls &amp; Mixed</option>
+                      {genderOptions.map((g) => (
+                        <option key={g} value={g.toLowerCase()}>
+                          {g}
+                        </option>
+                      ))}
+                    </select>
+                  )}
+
+                  <select
+                    value={currentHasSixthForm}
+                    onChange={(e) =>
+                      handleFilterChange("has_sixth_form", e.target.value)
+                    }
+                    className={styles.filterSelect}
+                    disabled={isPending}
+                  >
+                    <option value="">With or without sixth form</option>
+                    <option value="yes">With sixth form (11-18)</option>
+                    <option value="no">Without sixth form (11-16)</option>
+                  </select>
+
+                  {admissionsPolicyOptions.length > 0 && (
+                    <select
+                      value={currentAdmissionsPolicy}
+                      onChange={(e) =>
+                        handleFilterChange("admissions_policy", e.target.value)
+                      }
+                      className={styles.filterSelect}
+                      disabled={isPending}
+                    >
+                      <option value="">All admissions types</option>
+                      {admissionsPolicyOptions.map((p) => (
+                        <option key={p} value={p.toLowerCase()}>
+                          {p}
+                        </option>
+                      ))}
+                    </select>
+                  )}
+                </>
+              )}
+            </div>
+          )}
+        </>
+      )}
     </div>
   );
 }

nextjs-app/components/Footer.tsx

@@ -15,7 +15,7 @@ export function Footer() {
           <div className={styles.section}>
             <h3 className={styles.title}>SchoolCompare</h3>
             <p className={styles.description}>
-              Compare primary schools across England.
+              Compare primary and secondary schools across England.
             </p>
           </div>
 

nextjs-app/components/HomeView.module.css

@@ -33,33 +33,6 @@
   }
 }
 
-.locationBannerWrapper {
-  display: flex;
-  align-items: center;
-  justify-content: space-between;
-  gap: 0.75rem;
-  margin-bottom: 1rem;
-  flex-wrap: wrap;
-}
-
-.locationBanner {
-  display: flex;
-  align-items: center;
-  gap: 0.5rem;
-  padding: 0.5rem 1rem;
-  background: var(--accent-teal-bg);
-  border: 1px solid rgba(45, 125, 125, 0.25);
-  border-radius: 8px;
-  font-size: 0.875rem;
-  color: var(--accent-teal, #2d7d7d);
-  font-weight: 500;
-}
-
-.locationIcon {
-  font-size: 1.25rem;
-  color: var(--accent-teal, #2d7d7d);
-}
-
 /* View Toggle */
 .viewToggle {
   display: flex;
@@ -111,7 +84,9 @@
   display: grid;
   grid-template-columns: 1fr 340px;
   gap: 1rem;
-  height: 480px;
+  height: calc(100vh - 280px);
+  min-height: 520px;
+  max-height: 800px;
 }
 
 .mapContainer {
@@ -308,16 +283,14 @@
 }
 
 @media (max-width: 768px) {
-  .locationBannerWrapper {
+  .resultsHeader {
     flex-direction: column;
-    align-items: stretch;
+    align-items: flex-start;
-    margin-bottom: 0.75rem;
   }
 
-  .locationBanner {
+  .resultsHeaderActions {
-    padding: 0.5rem 0.75rem;
+    width: 100%;
-    font-size: 0.8125rem;
+    justify-content: space-between;
-    border-radius: 6px;
   }
 
   .viewToggle {
@@ -509,6 +482,13 @@
   padding: 0 0 1rem;
 }
 
+.resultsHeaderActions {
+  display: flex;
+  align-items: center;
+  gap: 0.75rem;
+  flex-shrink: 0;
+}
+
 .sortSelect {
   padding: 0.375rem 0.75rem;
   border: 1px solid var(--border-color, #e0ddd8);
@@ -549,3 +529,21 @@
 .chipRemove:hover {
   color: var(--text-primary);
 }
+
+.loadMoreSection {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  gap: 0.75rem;
+  padding: 1.5rem 0;
+}
+
+.loadMoreCount {
+  font-size: 0.875rem;
+  color: var(--text-muted, #8a847a);
+  margin: 0;
+}
+
+.loadMoreButton {
+  min-width: 160px;
+}

nextjs-app/components/HomeView.tsx

@@ -5,15 +5,17 @@
 
 'use client';
 
-import { useState, useEffect } from 'react';
+import React, { useState, useEffect, useRef } from 'react';
-import { useSearchParams } from 'next/navigation';
+import { useSearchParams, useRouter, usePathname } from 'next/navigation';
 import { FilterBar } from './FilterBar';
 import { SchoolRow } from './SchoolRow';
+import { SecondarySchoolRow } from './SecondarySchoolRow';
 import { SchoolMap } from './SchoolMap';
-import { Pagination } from './Pagination';
 import { EmptyState } from './EmptyState';
 import { useComparisonContext } from '@/context/ComparisonContext';
+import { fetchSchools, fetchLAaverages, fetchNationalAverages } from '@/lib/api';
 import type { SchoolsResponse, Filters, School } from '@/lib/types';
+import { schoolUrl, buildOfstedListBadge } from '@/lib/utils';
 import styles from './HomeView.module.css';
 
 interface HomeViewProps {
@@ -24,23 +26,102 @@ interface HomeViewProps {
 
 export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProps) {
   const searchParams = useSearchParams();
+  const router = useRouter();
+  const pathname = usePathname();
   const { addSchool, removeSchool, selectedSchools } = useComparisonContext();
   const [resultsView, setResultsView] = useState<'list' | 'map'>('list');
   const [selectedMapSchool, setSelectedMapSchool] = useState<School | null>(null);
-  const [sortOrder, setSortOrder] = useState<string>('default');
+  const sortOrder = searchParams.get('sort') || 'default';
+  const [allSchools, setAllSchools] = useState<School[]>(initialSchools.schools);
+  const [currentPage, setCurrentPage] = useState(initialSchools.page);
+  const [hasMore, setHasMore] = useState(initialSchools.total_pages > 1);
+  const [isLoadingMore, setIsLoadingMore] = useState(false);
+  const [laAverages, setLaAverages] = useState<Record<string, number>>({});
+  const [nationalAvgRwm, setNationalAvgRwm] = useState<number | null>(null);
+  const [mapSchools, setMapSchools] = useState<School[]>([]);
+  const [isLoadingMap, setIsLoadingMap] = useState(false);
+  const prevSearchParamsRef = useRef(searchParams.toString());
 
   const hasSearch = searchParams.get('search') || searchParams.get('postcode');
   const isLocationSearch = !!searchParams.get('postcode');
   const isSearchActive = !!(hasSearch || searchParams.get('local_authority') || searchParams.get('school_type'));
+  const currentPhase = searchParams.get('phase') || '';
+  const secondaryCount = allSchools.filter(s => s.attainment_8_score != null).length;
+  const primaryCount = allSchools.filter(s => s.rwm_expected_pct != null).length;
+  const isSecondaryView = currentPhase.toLowerCase().includes('secondary')
+    || (!currentPhase && secondaryCount > primaryCount);
+  const isMixedView = primaryCount > 0 && secondaryCount > 0 && !currentPhase;
+
+  // Reset pagination state when search params change
+  useEffect(() => {
+    const newParamsStr = searchParams.toString();
+    if (newParamsStr !== prevSearchParamsRef.current) {
+      prevSearchParamsRef.current = newParamsStr;
+      setAllSchools(initialSchools.schools);
+      setCurrentPage(initialSchools.page);
+      setHasMore(initialSchools.total_pages > 1);
+      setMapSchools([]);
+    }
+  }, [searchParams, initialSchools]);
 
   // Close bottom sheet if we change views or search
   useEffect(() => {
     setSelectedMapSchool(null);
   }, [resultsView, searchParams]);
 
-  const sortedSchools = [...initialSchools.schools].sort((a, b) => {
+  // Fetch all schools within radius when map view is active
+  useEffect(() => {
+    if (resultsView !== 'map' || !isLocationSearch) return;
+    setIsLoadingMap(true);
+    const params: Record<string, any> = {};
+    searchParams.forEach((value, key) => { params[key] = value; });
+    params.page = 1;
+    params.page_size = 500;
+    fetchSchools(params, { cache: 'no-store' })
+      .then(r => setMapSchools(r.schools))
+      .catch(() => setMapSchools(initialSchools.schools))
+      .finally(() => setIsLoadingMap(false));
+  }, [resultsView, searchParams]);
+
+  // Fetch LA averages when secondary or mixed schools are visible
+  useEffect(() => {
+    if (!isSecondaryView && !isMixedView) return;
+    fetchLAaverages({ cache: 'force-cache' })
+      .then(data => setLaAverages(data.secondary.attainment_8_by_la))
+      .catch(() => {});
+  }, [isSecondaryView, isMixedView]);
+
+  // Fetch national averages (supplementary — never blocks render)
+  useEffect(() => {
+    fetchNationalAverages()
+      .then(data => setNationalAvgRwm(data.primary?.rwm_expected_pct ?? null))
+      .catch(() => {});
+  }, []);
+
+  const handleLoadMore = async () => {
+    if (isLoadingMore || !hasMore) return;
+    setIsLoadingMore(true);
+    try {
+      const params: Record<string, any> = {};
+      searchParams.forEach((value, key) => { params[key] = value; });
+      params.page = currentPage + 1;
+      params.page_size = initialSchools.page_size;
+      const response = await fetchSchools(params, { cache: 'no-store' });
+      setAllSchools(prev => [...prev, ...response.schools]);
+      setCurrentPage(response.page);
+      setHasMore(response.page < response.total_pages);
+    } catch {
+      // silently ignore
+    } finally {
+      setIsLoadingMore(false);
+    }
+  };
+
+  const sortedSchools = [...allSchools].sort((a, b) => {
     if (sortOrder === 'rwm_desc') return (b.rwm_expected_pct ?? -Infinity) - (a.rwm_expected_pct ?? -Infinity);
     if (sortOrder === 'rwm_asc') return (a.rwm_expected_pct ?? Infinity) - (b.rwm_expected_pct ?? Infinity);
+    if (sortOrder === 'att8_desc') return (b.attainment_8_score ?? -Infinity) - (a.attainment_8_score ?? -Infinity);
+    if (sortOrder === 'att8_asc') return (a.attainment_8_score ?? Infinity) - (b.attainment_8_score ?? Infinity);
     if (sortOrder === 'distance') return (a.distance ?? Infinity) - (b.distance ?? Infinity);
     if (sortOrder === 'name_asc') return a.school_name.localeCompare(b.school_name);
     return 0;
@@ -51,20 +132,21 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
       {/* Combined Hero + Search and Filters */}
       {!isSearchActive && (
         <div className={styles.heroSection}>
-          <h1 className={styles.heroTitle}>Compare Primary School Performance</h1>
+          <h1 className={styles.heroTitle}>Find Local Schools</h1>
-          <p className={styles.heroDescription}>Search and compare KS2 results for thousands of schools across England</p>
+          <p className={styles.heroDescription}>Compare school results (SATs and GCSE), for thousands of schools across England</p>
         </div>
       )}
 
       <FilterBar
         filters={filters}
         isHero={!isSearchActive}
+        resultFilters={initialSchools.result_filters}
       />
 
       {/* Discovery section shown on landing page before any search */}
       {!isSearchActive && initialSchools.schools.length === 0 && (
         <div className={styles.discoverySection}>
-          {totalSchools && <p className={styles.discoveryCount}><strong>{totalSchools.toLocaleString()}+</strong> primary schools across England</p>}
+          {totalSchools && <p className={styles.discoveryCount}><strong>{totalSchools.toLocaleString()}+</strong> primary and secondary schools across England</p>}
           <p className={styles.discoveryHints}>Try searching for a school name, or enter a postcode to find schools near you.</p>
           <div className={styles.quickSearches}>
             <span className={styles.quickSearchLabel}>Quick searches:</span>
@@ -75,46 +157,6 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
         </div>
       )}
 
-      {/* Location Info Banner with View Toggle */}
-      {isLocationSearch && initialSchools.location_info && (
-        <div className={styles.locationBannerWrapper}>
-          <div className={styles.locationBanner}>
-            <span>
-              Showing schools within {(initialSchools.location_info.radius / 1.60934).toFixed(1)} miles of{' '}
-              <strong>{initialSchools.location_info.postcode}</strong>
-            </span>
-          </div>
-          {initialSchools.schools.length > 0 && (
-            <div className={styles.viewToggle}>
-              <button
-                className={`${styles.viewToggleBtn} ${resultsView === 'list' ? styles.active : ''}`}
-                onClick={() => setResultsView('list')}
-              >
-                <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" width="16" height="16">
-                  <line x1="8" y1="6" x2="21" y2="6"/>
-                  <line x1="8" y1="12" x2="21" y2="12"/>
-                  <line x1="8" y1="18" x2="21" y2="18"/>
-                  <line x1="3" y1="6" x2="3.01" y2="6"/>
-                  <line x1="3" y1="12" x2="3.01" y2="12"/>
-                  <line x1="3" y1="18" x2="3.01" y2="18"/>
-                </svg>
-                List
-              </button>
-              <button
-                className={`${styles.viewToggleBtn} ${resultsView === 'map' ? styles.active : ''}`}
-                onClick={() => setResultsView('map')}
-              >
-                <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" width="16" height="16">
-                  <path d="M21 10c0 7-9 13-9 13s-9-6-9-13a9 9 0 0 1 18 0z"/>
-                  <circle cx="12" cy="10" r="3"/>
-                </svg>
-                Map
-              </button>
-            </div>
-          )}
-        </div>
-      )}
-
       {/* Results Section */}
       <section className={`${styles.results} ${resultsView === 'map' && isLocationSearch ? styles.mapViewResults : ''}`}>
         {!hasSearch && initialSchools.schools.length > 0 && (
@@ -126,19 +168,67 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
           </div>
         )}
 
-        {hasSearch && resultsView === 'list' && (
+        {hasSearch && (
           <div className={styles.resultsHeader}>
             <h2 aria-live="polite" aria-atomic="true">
-              {initialSchools.total.toLocaleString()} school
+              {isLocationSearch && initialSchools.location_info
-              {initialSchools.total !== 1 ? 's' : ''} found
+                ? `${initialSchools.total.toLocaleString()} school${initialSchools.total !== 1 ? 's' : ''} within ${(initialSchools.location_info.radius / 1.60934).toFixed(1)} miles of ${initialSchools.location_info.postcode}`
+                : `${initialSchools.total.toLocaleString()} school${initialSchools.total !== 1 ? 's' : ''} found`
+              }
             </h2>
-            <select value={sortOrder} onChange={e => setSortOrder(e.target.value)} className={styles.sortSelect}>
+            <div className={styles.resultsHeaderActions}>
-              <option value="default">Sort: Relevance</option>
+              {isLocationSearch && initialSchools.schools.length > 0 && (
-              <option value="rwm_desc">Highest R, W &amp; M %</option>
+                <div className={styles.viewToggle}>
-              <option value="rwm_asc">Lowest R, W &amp; M %</option>
+                  <button
-              {isLocationSearch && <option value="distance">Nearest first</option>}
+                    className={`${styles.viewToggleBtn} ${resultsView === 'list' ? styles.active : ''}`}
-              <option value="name_asc">Name A–Z</option>
+                    onClick={() => setResultsView('list')}
-            </select>
+                  >
+                    <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" width="16" height="16">
+                      <line x1="8" y1="6" x2="21" y2="6"/>
+                      <line x1="8" y1="12" x2="21" y2="12"/>
+                      <line x1="8" y1="18" x2="21" y2="18"/>
+                      <line x1="3" y1="6" x2="3.01" y2="6"/>
+                      <line x1="3" y1="12" x2="3.01" y2="12"/>
+                      <line x1="3" y1="18" x2="3.01" y2="18"/>
+                    </svg>
+                    List
+                  </button>
+                  <button
+                    className={`${styles.viewToggleBtn} ${resultsView === 'map' ? styles.active : ''}`}
+                    onClick={() => setResultsView('map')}
+                  >
+                    <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" width="16" height="16">
+                      <path d="M21 10c0 7-9 13-9 13s-9-6-9-13a9 9 0 0 1 18 0z"/>
+                      <circle cx="12" cy="10" r="3"/>
+                    </svg>
+                    Map
+                  </button>
+                </div>
+              )}
+              {resultsView === 'list' && (
+                <select
+                  value={sortOrder}
+                  onChange={e => {
+                    const params = new URLSearchParams(searchParams);
+                    if (e.target.value === 'default') {
+                      params.delete('sort');
+                    } else {
+                      params.set('sort', e.target.value);
+                    }
+                    router.push(`${pathname}?${params.toString()}`);
+                  }}
+                  className={styles.sortSelect}
+                >
+                  <option value="default">Sort: Relevance</option>
+                  {(!isSecondaryView || isMixedView) && <option value="rwm_desc">Highest Reading, Writing &amp; Maths %</option>}
+                  {(!isSecondaryView || isMixedView) && <option value="rwm_asc">Lowest Reading, Writing &amp; Maths %</option>}
+                  {(isSecondaryView || isMixedView) && <option value="att8_desc">Highest Attainment 8</option>}
+                  {(isSecondaryView || isMixedView) && <option value="att8_asc">Lowest Attainment 8</option>}
+                  {isLocationSearch && <option value="distance">Nearest first</option>}
+                  <option value="name_asc">Name A–Z</option>
+                </select>
+              )}
+            </div>
           </div>
         )}
 
@@ -147,7 +237,6 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
             {searchParams.get('search') && <span className={styles.filterChip}>Search: {searchParams.get('search')}<a href="/" className={styles.chipRemove} onClick={e => { e.preventDefault(); }}>×</a></span>}
             {searchParams.get('local_authority') && <span className={styles.filterChip}>{searchParams.get('local_authority')}</span>}
             {searchParams.get('school_type') && <span className={styles.filterChip}>{searchParams.get('school_type')}</span>}
-            {searchParams.get('postcode') && <span className={styles.filterChip}>Near {searchParams.get('postcode')} ({parseFloat(searchParams.get('radius') || '1')} mi)</span>}
           </div>
         )}
 
@@ -167,13 +256,16 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
           <div className={styles.mapViewContainer}>
             <div className={styles.mapContainer}>
               <SchoolMap
-                schools={initialSchools.schools}
+                schools={isLoadingMap ? initialSchools.schools : mapSchools}
                 center={initialSchools.location_info?.coordinates}
+                referencePoint={initialSchools.location_info?.coordinates}
                 onMarkerClick={setSelectedMapSchool}
+                nationalAvgRwm={nationalAvgRwm}
+                laAverages={laAverages}
               />
             </div>
             <div className={styles.compactList}>
-              {initialSchools.schools.map((school) => (
+              {(isLoadingMap ? initialSchools.schools : mapSchools).map((school) => (
                 <div
                   key={school.urn}
                   className={`${styles.listItemWrapper} ${selectedMapSchool?.urn === school.urn ? styles.highlightedItem : ''}`}
@@ -182,6 +274,7 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
                     school={school}
                     onAddToCompare={addSchool}
                     isInCompare={selectedSchools.some(s => s.urn === school.urn)}
+                    nationalAvgRwm={nationalAvgRwm}
                   />
                 </div>
               ))}
@@ -196,6 +289,7 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
                     school={selectedMapSchool}
                     onAddToCompare={addSchool}
                     isInCompare={selectedSchools.some(s => s.urn === selectedMapSchool.urn)}
+                    nationalAvgRwm={nationalAvgRwm}
                   />
                 </div>
               </div>
@@ -206,23 +300,45 @@ export function HomeView({ initialSchools, filters, totalSchools }: HomeViewProp
           <>
             <div className={styles.schoolList}>
               {sortedSchools.map((school) => (
-                <SchoolRow
+                school.attainment_8_score != null ? (
-                  key={school.urn}
+                  <SecondarySchoolRow
-                  school={school}
+                    key={school.urn}
-                  isLocationSearch={isLocationSearch}
+                    school={school}
-                  onAddToCompare={addSchool}
+                    isLocationSearch={isLocationSearch}
-                  onRemoveFromCompare={removeSchool}
+                    onAddToCompare={addSchool}
-                  isInCompare={selectedSchools.some(s => s.urn === school.urn)}
+                    onRemoveFromCompare={removeSchool}
-                />
+                    isInCompare={selectedSchools.some(s => s.urn === school.urn)}
+                    laAvgAttainment8={school.local_authority ? laAverages[school.local_authority] ?? null : null}
+                  />
+                ) : (
+                  <SchoolRow
+                    key={school.urn}
+                    school={school}
+                    isLocationSearch={isLocationSearch}
+                    onAddToCompare={addSchool}
+                    onRemoveFromCompare={removeSchool}
+                    isInCompare={selectedSchools.some(s => s.urn === school.urn)}
+                    nationalAvgRwm={nationalAvgRwm}
+                  />
+                )
               ))}
             </div>
 
-            {initialSchools.total_pages > 1 && (
+            {(hasMore || allSchools.length < initialSchools.total) && (
-              <Pagination
+              <div className={styles.loadMoreSection}>
-                currentPage={initialSchools.page}
+                <p className={styles.loadMoreCount}>
-                totalPages={initialSchools.total_pages}
+                  Showing {allSchools.length.toLocaleString()} of {initialSchools.total.toLocaleString()} schools
-                total={initialSchools.total}
+                </p>
-              />
+                {hasMore && (
+                  <button
+                    onClick={handleLoadMore}
+                    disabled={isLoadingMore}
+                    className={`btn btn-secondary ${styles.loadMoreButton}`}
+                  >
+                    {isLoadingMore ? 'Loading...' : 'Load more schools'}
+                  </button>
+                )}
+              </div>
             )}
           </>
         )}
@@ -236,14 +352,33 @@ interface CompactSchoolItemProps {
   school: School;
   onAddToCompare: (school: School) => void;
   isInCompare: boolean;
+  nationalAvgRwm?: number | null;
 }
 
-function CompactSchoolItem({ school, onAddToCompare, isInCompare }: CompactSchoolItemProps) {
+function CompactSchoolItem({ school, onAddToCompare, isInCompare, nationalAvgRwm }: CompactSchoolItemProps) {
+  const ofstedBadge = buildOfstedListBadge(school);
+  const isSecondary = school.attainment_8_score != null;
+
+  // vs-national delta for primary schools
+  const rwmDelta =
+    !isSecondary && school.rwm_expected_pct != null && nationalAvgRwm != null
+      ? Math.round(school.rwm_expected_pct - nationalAvgRwm)
+      : null;
+
+  const deltaStyle: React.CSSProperties =
+    rwmDelta == null
+      ? {}
+      : rwmDelta >= 2
+      ? { fontSize: '0.7rem', color: 'var(--accent-teal, #2d7d7d)', fontWeight: 600 }
+      : rwmDelta <= -2
+      ? { fontSize: '0.7rem', color: 'var(--accent-coral, #e07256)', fontWeight: 600 }
+      : { fontSize: '0.7rem', color: 'var(--text-muted, #8a847a)' };
+
   return (
     <div className={styles.compactItem}>
       <div className={styles.compactItemContent}>
         <div className={styles.compactItemHeader}>
-          <a href={`/school/${school.urn}`} className={styles.compactItemName}>
+          <a href={schoolUrl(school.urn, school.school_name)} className={styles.compactItemName}>
             {school.school_name}
           </a>
           {school.distance !== undefined && school.distance !== null && (
@@ -252,17 +387,48 @@ function CompactSchoolItem({ school, onAddToCompare, isInCompare }: CompactSchoo
             </span>
           )}
         </div>
-        <div className={styles.compactItemMeta}>
+        {/* Ofsted badge */}
-          {school.school_type && <span>{school.school_type}</span>}
+        <div style={{ marginBottom: '0.25rem' }}>
-          {school.local_authority && <span>{school.local_authority}</span>}
+          <span
+            style={{
+              display: 'inline-block',
+              padding: '0.0625rem 0.375rem',
+              fontSize: '0.625rem',
+              fontWeight: 600,
+              borderRadius: '3px',
+              whiteSpace: 'nowrap',
+              ...(ofstedBadge.cssClass === 'ofsted1' ? { background: 'var(--accent-teal-bg)', color: 'var(--accent-teal, #2d7d7d)' } :
+                  ofstedBadge.cssClass === 'ofsted2' ? { background: 'rgba(60,140,60,0.12)', color: '#3c8c3c' } :
+                  ofstedBadge.cssClass === 'ofsted3' ? { background: 'var(--accent-gold-bg)', color: '#b8920e' } :
+                  ofstedBadge.cssClass === 'ofsted4' ? { background: 'var(--accent-coral-bg)', color: 'var(--accent-coral, #e07256)' } :
+                  ofstedBadge.cssClass === 'ofstedRc' ? { background: '#5a3a6e', color: '#fff' } :
+                  ofstedBadge.cssClass === 'ofstedPending' ? { background: '#e0e0e0', color: '#666' } :
+                  { background: '#e0e0e0', color: '#666' }),
+            }}
+          >
+            {ofstedBadge.label}
+          </span>
         </div>
+        {/* Headline metric + delta */}
         <div className={styles.compactItemStats}>
           <span className={styles.compactStat}>
-            <strong>{school.rwm_expected_pct !== null ? `${school.rwm_expected_pct}%` : '-'}</strong> RWM
+            <strong>
-          </span>
+              {isSecondary
-          <span className={styles.compactStat}>
+                ? (school.attainment_8_score != null ? school.attainment_8_score.toFixed(1) : '-')
-            <strong>{school.total_pupils || '-'}</strong> pupils
+                : (school.rwm_expected_pct != null ? `${school.rwm_expected_pct}%` : '-')}
+            </strong>
+            {' '}
+            {isSecondary ? 'Att 8' : 'RWM'}
           </span>
+          {rwmDelta != null && (
+            <span style={deltaStyle}>
+              {rwmDelta >= 2
+                ? `+${rwmDelta} pts vs national`
+                : rwmDelta <= -2
+                ? `${rwmDelta} pts vs national`
+                : '≈ national avg'}
+            </span>
+          )}
         </div>
       </div>
       <div className={styles.compactItemActions}>
@@ -272,7 +438,7 @@ function CompactSchoolItem({ school, onAddToCompare, isInCompare }: CompactSchoo
         >
           {isInCompare ? '✓ Comparing' : '+ Compare'}
         </button>
-        <a href={`/school/${school.urn}`} className="btn btn-tertiary btn-sm">
+        <a href={schoolUrl(school.urn, school.school_name)} className="btn btn-tertiary btn-sm">
           View
         </a>
       </div>

nextjs-app/components/LeafletMapInner.tsx

@@ -9,6 +9,7 @@ import { useEffect, useRef } from 'react';
 import L from 'leaflet';
 import 'leaflet/dist/leaflet.css';
 import type { School } from '@/lib/types';
+import { schoolUrl } from '@/lib/utils';
 
 // Fix for default marker icons in Next.js
 delete (L.Icon.Default.prototype as any)._getIconUrl;
@@ -22,12 +23,48 @@ interface LeafletMapInnerProps {
   schools: School[];
   center: [number, number];
   zoom: number;
+  referencePoint?: [number, number];
   onMarkerClick?: (school: School) => void;
+  nationalAvgRwm?: number | null;
+  laAverages?: Record<string, number | null>;
 }
 
-export default function LeafletMapInner({ schools, center, zoom, onMarkerClick }: LeafletMapInnerProps) {
+// ---------------------------------------------------------------------------
+// Popup helpers (must work in plain JS string templates — no React / CSS Modules)
+// ---------------------------------------------------------------------------
+
+function escapeHtml(s: string): string {
+  return s.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;').replace(/"/g, '&quot;');
+}
+
+interface PopupBadge {
+  label: string;
+  style: string;
+}
+
+function buildPopupBadge(school: School): PopupBadge {
+  const year = school.ofsted_date ? new Date(school.ofsted_date).getFullYear() : null;
+  const yearStr = year ? ` · ${year}` : '';
+  if (school.ofsted_grade) {
+    const labels: Record<number, string> = { 1: 'Outstanding', 2: 'Good', 3: 'Req. Improvement', 4: 'Inadequate' };
+    const colours: Record<number, string> = {
+      1: 'background:#d4f0ea;color:#2d7d7d',
+      2: 'background:rgba(60,140,60,0.12);color:#3c8c3c',
+      3: 'background:#fef3cd;color:#b8920e',
+      4: 'background:#fde8e0;color:#e07256',
+    };
+    return { label: `${labels[school.ofsted_grade]}${yearStr}`, style: colours[school.ofsted_grade] };
+  }
+  if (school.ofsted_framework === 'ReportCard') {
+    return { label: `Report Card${yearStr}`, style: 'background:#5a3a6e;color:#fff' };
+  }
+  return { label: 'Not yet inspected', style: 'background:#e0e0e0;color:#666' };
+}
+
+export default function LeafletMapInner({ schools, center, zoom, referencePoint, onMarkerClick, nationalAvgRwm, laAverages }: LeafletMapInnerProps) {
   const mapRef = useRef<L.Map | null>(null);
   const mapContainerRef = useRef<HTMLDivElement>(null);
+  const refMarkerRef = useRef<L.Marker | null>(null);
 
   useEffect(() => {
     if (!mapContainerRef.current) return;
@@ -42,27 +79,109 @@ export default function LeafletMapInner({ schools, center, zoom, onMarkerClick }
       }).addTo(mapRef.current);
     }
 
-    // Clear existing markers
+    // Clear existing school markers (not the reference pin)
     mapRef.current.eachLayer((layer) => {
-      if (layer instanceof L.Marker) {
+      if (layer instanceof L.Marker && layer !== refMarkerRef.current) {
         mapRef.current!.removeLayer(layer);
       }
     });
 
+    // Add reference pin (search location)
+    if (refMarkerRef.current) {
+      refMarkerRef.current.remove();
+      refMarkerRef.current = null;
+    }
+    if (referencePoint && mapRef.current) {
+      const refIcon = L.divIcon({
+        html: `<div style="
+          width: 20px; height: 20px;
+          background: #e07256;
+          border: 3px solid white;
+          border-radius: 50%;
+          box-shadow: 0 2px 8px rgba(0,0,0,0.35);
+        "></div>`,
+        iconSize: [20, 20],
+        iconAnchor: [10, 10],
+        className: '',
+      });
+      refMarkerRef.current = L.marker(referencePoint, { icon: refIcon, zIndexOffset: 1000 })
+        .addTo(mapRef.current)
+        .bindPopup('<strong>Search location</strong>');
+    }
+
     // Add markers for schools
     schools.forEach((school) => {
       if (school.latitude && school.longitude && mapRef.current) {
         const marker = L.marker([school.latitude, school.longitude]).addTo(mapRef.current);
 
         // Create popup content
-        const popupContent = `
+        const badge = buildPopupBadge(school);
-          <div style="min-width: 200px;">
+        const isSecondary = school.attainment_8_score != null;
-            <strong style="font-size: 14px; display: block; margin-bottom: 8px;">${school.school_name}</strong>
+
-            ${school.local_authority ? `<div style="font-size: 12px; color: #666; margin-bottom: 4px;">${school.local_authority}</div>` : ''}
+        // Phase label
-            ${school.school_type ? `<div style="font-size: 12px; color: #666; margin-bottom: 8px;">${school.school_type}</div>` : ''}
+        const rawPhase = (school.phase ?? '').toLowerCase();
-            <a href="/school/${school.urn}" style="display: inline-block; margin-top: 8px; padding: 6px 12px; background: #e07256; color: white; text-decoration: none; border-radius: 4px; font-size: 12px;">View Details</a>
+        const phaseLabel =
-          </div>
+          rawPhase.includes('secondary') ? 'Secondary' :
-        `;
+          rawPhase === 'all-through' ? 'All-through' :
+          rawPhase.includes('primary') ? 'Primary' :
+          isSecondary ? 'Secondary' : 'Primary';
+
+        // Distance string
+        const distanceStr =
+          school.distance != null ? ` · ${school.distance.toFixed(1)} mi` : '';
+
+        // Headline metric
+        let metricHtml = '';
+        if (isSecondary) {
+          const score = school.attainment_8_score!;
+          const laAvg = school.local_authority ? (laAverages?.[school.local_authority] ?? null) : null;
+          let deltaLine = '';
+          if (laAvg != null) {
+            const diff = Math.round((score - laAvg) * 10) / 10;
+            const sign = diff >= 0 ? '+' : '';
+            // Att8 scores range 0–90 in 0.1 increments; ±0.5 is meaningful here
+            // vs primary RWM % where ±2 pts is the threshold
+            const colour = diff >= 0.5 ? '#2d7d7d' : diff <= -0.5 ? '#e07256' : '#8a847a';
+            const laName = escapeHtml(school.local_authority ?? 'LA');
+            deltaLine = `<div style="font-size:11px;font-weight:600;color:${colour}">${sign}${diff} vs ${laName} avg</div>`;
+          }
+          metricHtml = `<div style="margin-bottom:4px">
+  <span style="font-size:20px;font-weight:700;color:#1a1612;font-family:Georgia,serif">${score.toFixed(1)}</span>
+  <span style="font-size:11px;color:#8a847a;margin-left:4px">Attainment 8</span>
+  ${deltaLine}
+</div>`;
+        } else if (school.rwm_expected_pct != null) {
+          const rwm = school.rwm_expected_pct;
+          let deltaLine = '';
+          if (nationalAvgRwm != null) {
+            const diff = Math.round(rwm - nationalAvgRwm);
+            const colour = diff >= 2 ? '#2d7d7d' : diff <= -2 ? '#e07256' : '#8a847a';
+            const text =
+              diff >= 2 ? `+${diff} pts vs national` :
+              diff <= -2 ? `${diff} pts vs national` :
+              '≈ national avg';
+            deltaLine = `<div style="font-size:11px;font-weight:600;color:${colour}">${text}</div>`;
+          }
+          metricHtml = `<div style="margin-bottom:4px">
+  <span style="font-size:20px;font-weight:700;color:#1a1612;font-family:Georgia,serif">${rwm}%</span>
+  <span style="font-size:11px;color:#8a847a;margin-left:4px">Reading, Writing &amp; Maths</span>
+  ${deltaLine}
+</div>`;
+        }
+
+        const slug = schoolUrl(school.urn, school.school_name);
+
+        const popupContent = `<div style="font-family:system-ui,sans-serif;min-width:240px;max-width:280px;padding:0">
+  <div style="display:flex;justify-content:space-between;align-items:flex-start;gap:8px;margin-bottom:6px">
+    <strong style="font-size:13px;color:#1a1612;line-height:1.3">${escapeHtml(school.school_name)}</strong>
+    <span style="font-size:10px;font-weight:700;padding:2px 6px;border-radius:3px;white-space:nowrap;flex-shrink:0;${badge.style}">${badge.label}</span>
+  </div>
+  <div style="font-size:11px;color:#8a847a;margin-bottom:8px">
+    ${phaseLabel}${school.local_authority ? ` · ${escapeHtml(school.local_authority)}` : ''}${distanceStr}
+  </div>
+  ${metricHtml}
+  <a href="${slug}" style="display:block;text-align:center;padding:6px;background:#2d7d7d;color:white;border-radius:5px;text-decoration:none;font-size:12px;font-weight:600;margin-top:8px">View Details →</a>
+</div>`;
 
         marker.bindPopup(popupContent);
 
@@ -88,7 +207,7 @@ export default function LeafletMapInner({ schools, center, zoom, onMarkerClick }
     return () => {
       // Don't destroy map on every update, just clean markers
     };
-  }, [schools, center, zoom, onMarkerClick]);
+  }, [schools, center, zoom, referencePoint, onMarkerClick, nationalAvgRwm, laAverages]);
 
   // Cleanup map on unmount
   useEffect(() => {

nextjs-app/components/MetricTooltip.module.css

@@ -0,0 +1,83 @@
+.wrapper {
+  position: relative;
+  display: inline-flex;
+  align-items: center;
+  margin-left: 0.3em;
+}
+
+.icon {
+  font-size: 0.85em;
+  color: var(--text-muted, #8a7a72);
+  cursor: help;
+  line-height: 1;
+  user-select: none;
+  transition: color 0.15s ease;
+}
+
+.wrapper:hover .icon {
+  color: var(--accent-coral, #e07256);
+}
+
+.tooltip {
+  visibility: hidden;
+  opacity: 0;
+  position: absolute;
+  bottom: calc(100% + 6px);
+  left: 50%;
+  transform: translateX(-50%);
+  z-index: 9999;
+  width: 220px;
+  background: var(--bg-primary, #faf7f2);
+  border: 1px solid var(--border-color, #e8ddd4);
+  border-radius: 10px;
+  box-shadow: 0 4px 16px rgba(44, 36, 32, 0.15);
+  padding: 0.6rem 0.75rem;
+  display: flex;
+  flex-direction: column;
+  gap: 0.3rem;
+  pointer-events: none;
+  transition: opacity 0.15s ease, visibility 0.15s ease;
+}
+
+/* Keep tooltip visible when hovering over it */
+.wrapper:hover .tooltip {
+  visibility: visible;
+  opacity: 1;
+}
+
+/* Small arrow pointing down */
+.tooltip::after {
+  content: '';
+  position: absolute;
+  top: 100%;
+  left: 50%;
+  transform: translateX(-50%);
+  border: 5px solid transparent;
+  border-top-color: var(--border-color, #e8ddd4);
+}
+
+.tooltipLabel {
+  font-weight: 600;
+  font-size: 0.75rem;
+  color: var(--text-primary, #2c2420);
+}
+
+.tooltipPlain {
+  font-size: 0.75rem;
+  color: var(--text-secondary, #5a4a44);
+  line-height: 1.4;
+}
+
+.tooltipDetail {
+  font-size: 0.7rem;
+  color: var(--text-muted, #8a7a72);
+  line-height: 1.4;
+  margin-top: 0.1rem;
+}
+
+/* Flip tooltip below when near top of screen */
+@media (max-width: 480px) {
+  .tooltip {
+    width: 180px;
+  }
+}

nextjs-app/components/MetricTooltip.tsx

@@ -0,0 +1,31 @@
+'use client';
+
+import { METRIC_EXPLANATIONS } from '@/lib/metrics';
+import styles from './MetricTooltip.module.css';
+
+interface MetricTooltipProps {
+  metricKey?: string;
+  label?: string;
+  plain?: string;
+  detail?: string;
+}
+
+export function MetricTooltip({ metricKey, label, plain, detail }: MetricTooltipProps) {
+  const explanation = metricKey ? METRIC_EXPLANATIONS[metricKey] : undefined;
+  const tooltipLabel = label ?? explanation?.label;
+  const tooltipPlain = plain ?? explanation?.plain;
+  const tooltipDetail = detail ?? explanation?.detail;
+
+  if (!tooltipPlain) return null;
+
+  return (
+    <span className={styles.wrapper}>
+      <span className={styles.icon} aria-label={tooltipLabel ?? 'More information'} role="img">ⓘ</span>
+      <span className={styles.tooltip} role="tooltip">
+        {tooltipLabel && <span className={styles.tooltipLabel}>{tooltipLabel}</span>}
+        <span className={styles.tooltipPlain}>{tooltipPlain}</span>
+        {tooltipDetail && <span className={styles.tooltipDetail}>{tooltipDetail}</span>}
+      </span>
+    </span>
+  );
+}

nextjs-app/components/PerformanceChart.module.css

@@ -1,9 +1,34 @@
+.chartOuter {
+  display: flex;
+  flex-direction: column;
+  gap: 0.75rem;
+}
+
+.trendSummary {
+  font-size: 0.875rem;
+  font-weight: 600;
+  color: var(--text-secondary, #5c564d);
+  padding: 0.5rem 0.875rem;
+  background: var(--bg-secondary, #f3ede4);
+  border-left: 3px solid var(--accent-teal, #2d7d7d);
+  border-radius: 0 4px 4px 0;
+  align-self: flex-start;
+}
+
 .chartWrapper {
   width: 100%;
   height: 100%;
   position: relative;
 }
 
+.covidNote,
+.chartHint {
+  font-size: 0.75rem;
+  color: var(--text-muted, #8a847a);
+  margin: 0;
+  font-style: italic;
+}
+
 @media (max-width: 768px) {
   .chartWrapper {
     font-size: 0.875rem;

nextjs-app/components/PerformanceChart.tsx

@@ -16,190 +16,285 @@ import {
   Tooltip,
   Legend,
   ChartOptions,
+  ChartDataset,
 } from 'chart.js';
 import type { SchoolResult } from '@/lib/types';
+import { formatAcademicYear } from '@/lib/utils';
 import styles from './PerformanceChart.module.css';
 
-// Register Chart.js components
+ChartJS.register(CategoryScale, LinearScale, PointElement, LineElement, Title, Tooltip, Legend);
-ChartJS.register(
+
-  CategoryScale,
+interface NationalByYear {
-  LinearScale,
+  year: number;
-  PointElement,
+  primary: Record<string, number>;
-  LineElement,
+  secondary: Record<string, number>;
-  Title,
+}
-  Tooltip,
-  Legend
-);
 
 interface PerformanceChartProps {
   data: SchoolResult[];
   schoolName: string;
+  isSecondary?: boolean;
+  /** National average RWM expected % for the latest year — fallback if no by_year data */
+  nationalRwmAvg?: number | null;
+  /** National average Attainment 8 for the latest year — fallback if no by_year data */
+  nationalAtt8Avg?: number | null;
+  /** Per-year national averages — used to draw a changing reference line */
+  nationalByYear?: NationalByYear[];
 }
 
-export function PerformanceChart({ data, schoolName }: PerformanceChartProps) {
+// Academic years when SATs/GCSEs were cancelled due to COVID
-  // Sort data by year
+const COVID_YEARS = new Set([201920, 202021]);
-  const sortedData = [...data].sort((a, b) => a.year - b.year);
-  const years = sortedData.map(d => d.year.toString());
 
-  // Prepare datasets
+export function PerformanceChart({
-  const datasets = [
+  data,
+  isSecondary = false,
+  nationalRwmAvg,
+  nationalAtt8Avg,
+  nationalByYear,
+}: PerformanceChartProps) {
+  const sortedData = [...data].sort((a, b) => a.year - b.year);
+  const years = sortedData.map(d => formatAcademicYear(d.year));
+
+  // Build per-year national average series aligned to the school's data years.
+  // Falls back to a flat line using the scalar prop if by_year isn't available.
+  const natRefRwm: (number | null)[] = sortedData.map(d => {
+    if (nationalByYear) {
+      const match = nationalByYear.find(n => n.year === d.year);
+      return match?.primary?.rwm_expected_pct ?? null;
+    }
+    return nationalRwmAvg ?? null;
+  });
+  const natRefAtt8: (number | null)[] = sortedData.map(d => {
+    if (nationalByYear) {
+      const match = nationalByYear.find(n => n.year === d.year);
+      return match?.secondary?.attainment_8_score ?? null;
+    }
+    return nationalAtt8Avg ?? null;
+  });
+  const hasNatRwm = natRefRwm.some(v => v != null);
+  const hasNatAtt8 = natRefAtt8.some(v => v != null);
+
+  // ── Trend summary (primary only) ──────────────────────────────────────
+  const trendSummary = (() => {
+    if (isSecondary) return null;
+    const rwm = sortedData.filter(d => d.rwm_expected_pct != null);
+    if (rwm.length < 2) return null;
+    const latest = rwm[rwm.length - 1];
+    const prev = rwm[rwm.length - 2];
+    const best = rwm.reduce((a, b) => (b.rwm_expected_pct! > a.rwm_expected_pct! ? b : a));
+    const latestPct = Math.round(latest.rwm_expected_pct!);
+    const bestPct = Math.round(best.rwm_expected_pct!);
+    const delta = latest.rwm_expected_pct! - prev.rwm_expected_pct!;
+    const arrow = delta > 1 ? '↑' : delta < -1 ? '↓' : '→';
+    if (best.year === latest.year) {
+      return `${arrow} Best year on record — ${latestPct}% Reading, Writing & Maths`;
+    }
+    return `${arrow} Peaked at ${bestPct}% (${formatAcademicYear(best.year)}), currently ${latestPct}%`;
+  })();
+
+  // ── COVID gap note ─────────────────────────────────────────────────────
+  const hasCovidGap = isSecondary
+    ? false
+    : COVID_YEARS.size > 0 &&
+      [...COVID_YEARS].some(y => !sortedData.find(d => d.year === y));
+
+  // ── Datasets ──────────────────────────────────────────────────────────
+  const refLineStyle = {
+    borderColor: 'rgba(90,80,70,0.35)',
+    backgroundColor: 'transparent',
+    borderWidth: 1.5,
+    borderDash: [6, 4] as number[],
+    pointRadius: 0,
+    tension: 0,
+    order: 10,
+  };
+
+  const datasets: ChartDataset<'line'>[] = isSecondary ? [
     {
-      label: 'RWM Expected %',
+      label: 'Attainment 8',
+      data: sortedData.map(d => d.attainment_8_score),
+      borderColor: '#2d7d7d',
+      backgroundColor: 'rgba(45,125,125,0.08)',
+      borderWidth: 2.5,
+      tension: 0.3,
+      pointRadius: 4,
+      pointHoverRadius: 6,
+      yAxisID: 'y',
+    },
+    {
+      label: 'English & Maths Grade 4+',
+      data: sortedData.map(d => d.english_maths_standard_pass_pct),
+      borderColor: '#c9a227',
+      backgroundColor: 'rgba(201,162,39,0.08)',
+      borderWidth: 1.5,
+      tension: 0.3,
+      pointRadius: 3,
+      yAxisID: 'y',
+    },
+    {
+      label: 'Progress 8',
+      data: sortedData.map(d => d.progress_8_score),
+      borderColor: 'rgb(139,92,246)',
+      backgroundColor: 'rgba(139,92,246,0.08)',
+      borderWidth: 1.5,
+      tension: 0.3,
+      pointRadius: 3,
+      hidden: true,
+      yAxisID: 'y1',
+    },
+    ...(hasNatAtt8 ? [{
+      ...refLineStyle,
+      label: 'National average',
+      data: natRefAtt8,
+      yAxisID: 'y',
+    } as ChartDataset<'line'>] : []),
+  ] : [
+    {
+      label: 'Reading, Writing & Maths expected %',
       data: sortedData.map(d => d.rwm_expected_pct),
-      borderColor: 'rgb(59, 130, 246)',
+      borderColor: '#2d7d7d',
-      backgroundColor: 'rgba(59, 130, 246, 0.1)',
+      backgroundColor: 'rgba(45,125,125,0.08)',
+      borderWidth: 2.5,
       tension: 0.3,
+      pointRadius: 4,
+      pointHoverRadius: 6,
+      yAxisID: 'y',
     },
     {
-      label: 'RWM Higher %',
+      label: 'Exceeding expected level',
       data: sortedData.map(d => d.rwm_high_pct),
-      borderColor: 'rgb(16, 185, 129)',
+      borderColor: '#c9a227',
-      backgroundColor: 'rgba(16, 185, 129, 0.1)',
+      backgroundColor: 'rgba(201,162,39,0.08)',
+      borderWidth: 1.5,
       tension: 0.3,
+      pointRadius: 3,
+      yAxisID: 'y',
     },
+    ...(hasNatRwm ? [{
+      ...refLineStyle,
+      label: 'National average',
+      data: natRefRwm,
+      yAxisID: 'y',
+    } as ChartDataset<'line'>] : []),
     {
-      label: 'Reading Progress',
+      label: 'Reading progress',
       data: sortedData.map(d => d.reading_progress),
-      borderColor: 'rgb(245, 158, 11)',
+      borderColor: 'rgb(59,130,246)',
-      backgroundColor: 'rgba(245, 158, 11, 0.1)',
+      backgroundColor: 'rgba(59,130,246,0.08)',
+      borderWidth: 1.5,
       tension: 0.3,
+      pointRadius: 3,
+      hidden: true,
       yAxisID: 'y1',
     },
     {
-      label: 'Writing Progress',
+      label: 'Writing progress',
       data: sortedData.map(d => d.writing_progress),
-      borderColor: 'rgb(139, 92, 246)',
+      borderColor: 'rgb(139,92,246)',
-      backgroundColor: 'rgba(139, 92, 246, 0.1)',
+      backgroundColor: 'rgba(139,92,246,0.08)',
+      borderWidth: 1.5,
       tension: 0.3,
+      pointRadius: 3,
+      hidden: true,
       yAxisID: 'y1',
     },
     {
-      label: 'Maths Progress',
+      label: 'Maths progress',
       data: sortedData.map(d => d.maths_progress),
-      borderColor: 'rgb(236, 72, 153)',
+      borderColor: 'rgb(236,72,153)',
-      backgroundColor: 'rgba(236, 72, 153, 0.1)',
+      backgroundColor: 'rgba(236,72,153,0.08)',
+      borderWidth: 1.5,
       tension: 0.3,
+      pointRadius: 3,
+      hidden: true,
       yAxisID: 'y1',
     },
   ];
 
-  const chartData = {
-    labels: years,
-    datasets,
-  };
-
   const options: ChartOptions<'line'> = {
     responsive: true,
     maintainAspectRatio: false,
-    interaction: {
+    interaction: { mode: 'index', intersect: false },
-      mode: 'index' as const,
-      intersect: false,
-    },
     plugins: {
       legend: {
-        position: 'top' as const,
+        position: 'top',
         labels: {
           usePointStyle: true,
-          padding: 15,
+          padding: 14,
-          font: {
+          font: { size: 12 },
-            size: 12,
+          filter: item => item.text !== 'National average' || true,
+        },
+      },
+      title: { display: false },
+      tooltip: {
+        backgroundColor: 'rgba(26,22,18,0.92)',
+        padding: 12,
+        titleFont: { size: 13 },
+        bodyFont: { size: 12 },
+        callbacks: {
+          label: ctx => {
+            const label = ctx.dataset.label ?? '';
+            if (ctx.parsed.y == null) return label;
+            const isProgress = ctx.dataset.yAxisID === 'y1';
+            const suffix = isProgress ? '' : '%';
+            const val = ctx.parsed.y.toFixed(1);
+            return `${label}: ${val}${suffix}`;
           },
         },
       },
-      title: {
-        display: true,
-        text: `${schoolName} - Performance Over Time`,
-        font: {
-          size: 16,
-          weight: 'bold',
-        },
-        padding: {
-          bottom: 20,
-        },
-      },
-      tooltip: {
-        backgroundColor: 'rgba(0, 0, 0, 0.8)',
-        padding: 12,
-        titleFont: {
-          size: 14,
-        },
-        bodyFont: {
-          size: 13,
-        },
-        callbacks: {
-          label: function(context) {
-            let label = context.dataset.label || '';
-            if (label) {
-              label += ': ';
-            }
-            if (context.parsed.y !== null) {
-              if (context.dataset.yAxisID === 'y1') {
-                // Progress scores
-                label += context.parsed.y.toFixed(1);
-              } else {
-                // Percentages
-                label += context.parsed.y.toFixed(1) + '%';
-              }
-            }
-            return label;
-          }
-        }
-      },
     },
     scales: {
       y: {
-        type: 'linear' as const,
+        type: 'linear',
         display: true,
-        position: 'left' as const,
+        position: 'left',
         title: {
           display: true,
-          text: 'Percentage (%)',
+          text: isSecondary ? 'Score / %' : 'Percentage (%)',
-          font: {
+          font: { size: 11 },
-            size: 12,
-            weight: 'bold',
-          },
         },
         min: 0,
-        max: 100,
+        max: isSecondary ? undefined : 100,
-        grid: {
+        grid: { color: 'rgba(0,0,0,0.05)' },
-          color: 'rgba(0, 0, 0, 0.05)',
+        ticks: { font: { size: 11 } },
-        },
       },
       y1: {
-        type: 'linear' as const,
+        type: 'linear',
         display: true,
-        position: 'right' as const,
+        position: 'right',
         title: {
           display: true,
-          text: 'Progress Score',
+          text: isSecondary ? 'Progress 8' : 'Progress score',
-          font: {
+          font: { size: 11 },
-            size: 12,
-            weight: 'bold',
-          },
-        },
-        grid: {
-          drawOnChartArea: false,
         },
+        grid: { drawOnChartArea: false },
+        ticks: { font: { size: 11 } },
       },
       x: {
-        grid: {
+        grid: { display: false },
-          display: false,
+        ticks: { font: { size: 11 } },
-        },
-        title: {
-          display: true,
-          text: 'Year',
-          font: {
-            size: 12,
-            weight: 'bold',
-          },
-        },
       },
     },
   };
 
   return (
-    <div className={styles.chartWrapper}>
+    <div className={styles.chartOuter}>
-      <Line data={chartData} options={options} />
+      {trendSummary && (
+        <div className={styles.trendSummary}>{trendSummary}</div>
+      )}
+      <div className={styles.chartWrapper}>
+        <Line data={{ labels: years, datasets }} options={options} />
+      </div>
+      {hasCovidGap && (
+        <p className={styles.covidNote}>
+          * No data for 2019/20 or 2020/21 — national assessments were cancelled due to COVID-19.
+        </p>
+      )}
+      {!isSecondary && (
+        <p className={styles.chartHint}>
+          Progress scores (Reading, Writing, Maths) are hidden by default — click them in the legend to show.
+        </p>
+      )}
     </div>
   );
 }

nextjs-app/components/RankingsView.module.css

@@ -1,5 +1,6 @@
 .container {
   width: 100%;
+  min-width: 0;
 }
 
 /* Header */
@@ -22,6 +23,47 @@
   line-height: 1.6;
 }
 
+/* Phase Tabs */
+.phaseTabs {
+  display: flex;
+  gap: 0;
+  margin-bottom: 1.5rem;
+  border: 1px solid var(--border-color, #e5dfd5);
+  border-radius: 8px;
+  overflow: hidden;
+  width: fit-content;
+}
+
+.phaseTab {
+  padding: 0.625rem 1.5rem;
+  font-size: 0.9375rem;
+  font-weight: 500;
+  background: var(--bg-card, white);
+  color: var(--text-secondary, #5c564d);
+  border: none;
+  cursor: pointer;
+  transition: all 0.15s ease;
+  font-family: inherit;
+}
+
+.phaseTab:not(:last-child) {
+  border-right: 1px solid var(--border-color, #e5dfd5);
+}
+
+.phaseTab:hover {
+  background: var(--bg-secondary, #f3ede4);
+}
+
+.phaseTabActive {
+  background: var(--accent-coral, #e07256);
+  color: white;
+  font-weight: 600;
+}
+
+.phaseTabActive:hover {
+  background: var(--accent-coral, #e07256);
+}
+
 /* Filters */
 .filters {
   background: var(--bg-card, white);
@@ -52,6 +94,8 @@
 
 .filterSelect {
   flex: 1;
+  min-width: 0;
+  max-width: 100%;
   padding: 0.625rem 1rem;
   font-size: 0.9375rem;
   border: 1px solid var(--border-color, #e5dfd5);
@@ -96,6 +140,8 @@
 
 .tableWrapper {
   overflow-x: auto;
+  max-width: 100%;
+  -webkit-overflow-scrolling: touch;
 }
 
 .rankingsTable {
@@ -304,7 +350,8 @@
   .filterGroup {
     flex-direction: column;
     align-items: stretch;
-    min-width: 100%;
+    min-width: 0;
+    width: 100%;
   }
 
   .rankingsSection {
@@ -327,13 +374,30 @@
     font-size: 0.875rem;
   }
 
-  .schoolHeader {
+  /* Hide less-critical columns on mobile so the metric value stays visible */
-    min-width: 180px;
+  .typeHeader,
+  .typeCell,
+  .actionHeader,
+  .actionCell {
+    display: none;
   }
 
-  .areaHeader,
+  .schoolHeader {
-  .typeHeader {
+    min-width: 140px;
-    min-width: 100px;
+  }
+
+  .areaHeader {
+    min-width: 80px;
+  }
+
+  .valueHeader,
+  .valueCell {
+    width: auto;
+    min-width: 60px;
+  }
+
+  .rankHeader {
+    width: 40px;
   }
 }
 

nextjs-app/components/RankingsView.tsx

@@ -1,6 +1,6 @@
 /**
  * RankingsView Component
- * Client-side rankings interface with filters
+ * Client-side rankings interface with phase tabs and filters
  */
 
 'use client';
@@ -8,10 +8,29 @@
 import { useRouter, usePathname, useSearchParams } from 'next/navigation';
 import { useComparison } from '@/hooks/useComparison';
 import type { RankingEntry, Filters, MetricDefinition } from '@/lib/types';
-import { formatPercentage, formatProgress } from '@/lib/utils';
+import { formatPercentage, formatProgress, formatAcademicYear, schoolUrl } from '@/lib/utils';
 import { EmptyState } from './EmptyState';
 import styles from './RankingsView.module.css';
 
+const PRIMARY_CATEGORIES = ['expected', 'higher', 'progress', 'average', 'gender', 'equity', 'context', 'absence', 'trends'];
+const SECONDARY_CATEGORIES = ['gcse'];
+
+const PRIMARY_OPTGROUPS: { label: string; category: string }[] = [
+  { label: 'Expected Standard', category: 'expected' },
+  { label: 'Higher Standard', category: 'higher' },
+  { label: 'Progress Scores', category: 'progress' },
+  { label: 'Average Scores', category: 'average' },
+  { label: 'Gender Performance', category: 'gender' },
+  { label: 'Equity (Disadvantaged)', category: 'equity' },
+  { label: 'School Context', category: 'context' },
+  { label: 'Absence', category: 'absence' },
+  { label: '3-Year Trends', category: 'trends' },
+];
+
+const SECONDARY_OPTGROUPS: { label: string; category: string }[] = [
+  { label: 'GCSE Performance', category: 'gcse' },
+];
+
 interface RankingsViewProps {
   rankings: RankingEntry[];
   filters: Filters;
@@ -19,6 +38,7 @@ interface RankingsViewProps {
   selectedMetric: string;
   selectedArea?: string;
   selectedYear?: number;
+  selectedPhase?: string;
 }
 
 export function RankingsView({
@@ -28,12 +48,17 @@ export function RankingsView({
   selectedMetric,
   selectedArea,
   selectedYear,
+  selectedPhase = 'primary',
 }: RankingsViewProps) {
   const router = useRouter();
   const pathname = usePathname();
   const searchParams = useSearchParams();
   const { addSchool, isSelected } = useComparison();
 
+  const isPrimary = selectedPhase === 'primary';
+  const allowedCategories = isPrimary ? PRIMARY_CATEGORIES : SECONDARY_CATEGORIES;
+  const optgroups = isPrimary ? PRIMARY_OPTGROUPS : SECONDARY_OPTGROUPS;
+
   const updateFilters = (updates: Record<string, string | undefined>) => {
     const params = new URLSearchParams(searchParams);
 
@@ -48,6 +73,11 @@ export function RankingsView({
     router.push(`${pathname}?${params.toString()}`);
   };
 
+  const handlePhaseChange = (phase: string) => {
+    const defaultMetric = phase === 'secondary' ? 'attainment_8_score' : 'rwm_expected_pct';
+    updateFilters({ phase, metric: defaultMetric });
+  };
+
   const handleMetricChange = (metric: string) => {
     updateFilters({ metric });
   };
@@ -63,7 +93,6 @@ export function RankingsView({
   const handleAddToCompare = (ranking: RankingEntry) => {
     addSchool({
       ...ranking,
-      // Ensure required School fields are present
       address: null,
       postcode: null,
       latitude: null,
@@ -77,6 +106,9 @@ export function RankingsView({
   const isProgressScore = selectedMetric.includes('progress');
   const isPercentage = selectedMetric.includes('pct') || selectedMetric.includes('rate');
 
+  // Filter metrics to only show relevant categories
+  const filteredMetrics = metrics.filter(m => allowedCategories.includes(m.category));
+
   return (
     <div className={styles.container}>
       {/* Header */}
@@ -84,10 +116,26 @@ export function RankingsView({
         <h1>School Rankings</h1>
         <p className={styles.subtitle}>
           Top-performing schools by {metricLabel.toLowerCase()}
-          {!selectedArea && <span className={styles.limitNote}> — showing top {rankings.length}</span>}
+          {!selectedArea && rankings.length > 0 && <span className={styles.limitNote}> — showing top {rankings.length}</span>}
         </p>
       </header>
 
+      {/* Phase Tabs */}
+      <div className={styles.phaseTabs}>
+        <button
+          className={`${styles.phaseTab} ${isPrimary ? styles.phaseTabActive : ''}`}
+          onClick={() => handlePhaseChange('primary')}
+        >
+          Primary (KS2)
+        </button>
+        <button
+          className={`${styles.phaseTab} ${!isPrimary ? styles.phaseTabActive : ''}`}
+          onClick={() => handlePhaseChange('secondary')}
+        >
+          Secondary (GCSE)
+        </button>
+      </div>
+
       {currentMetricDef?.description && (
         <p className={styles.metricDescription}>{currentMetricDef.description}</p>
       )}
@@ -107,46 +155,17 @@ export function RankingsView({
             onChange={(e) => handleMetricChange(e.target.value)}
             className={styles.filterSelect}
           >
-            <optgroup label="Expected Standard">
+            {optgroups.map(({ label, category }) => {
-              {metrics.filter(m => m.category === 'expected').map((metric) => (
+              const groupMetrics = filteredMetrics.filter(m => m.category === category);
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
+              if (groupMetrics.length === 0) return null;
-              ))}
+              return (
-            </optgroup>
+                <optgroup key={category} label={label}>
-            <optgroup label="Higher Standard">
+                  {groupMetrics.map((metric) => (
-              {metrics.filter(m => m.category === 'higher').map((metric) => (
+                    <option key={metric.key} value={metric.key}>{metric.label}</option>
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
+                  ))}
-              ))}
+                </optgroup>
-            </optgroup>
+              );
-            <optgroup label="Progress Scores">
+            })}
-              {metrics.filter(m => m.category === 'progress').map((metric) => (
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
-              ))}
-            </optgroup>
-            <optgroup label="Average Scores">
-              {metrics.filter(m => m.category === 'average').map((metric) => (
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
-              ))}
-            </optgroup>
-            <optgroup label="Gender Performance">
-              {metrics.filter(m => m.category === 'gender').map((metric) => (
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
-              ))}
-            </optgroup>
-            <optgroup label="Equity (Disadvantaged)">
-              {metrics.filter(m => m.category === 'disadvantaged').map((metric) => (
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
-              ))}
-            </optgroup>
-            <optgroup label="School Context">
-              {metrics.filter(m => m.category === 'context').map((metric) => (
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
-              ))}
-            </optgroup>
-            <optgroup label="3-Year Trends">
-              {metrics.filter(m => m.category === '3yr').map((metric) => (
-                <option key={metric.key} value={metric.key}>{metric.label}</option>
-              ))}
-            </optgroup>
           </select>
         </div>
 
@@ -180,11 +199,11 @@ export function RankingsView({
             className={styles.filterSelect}
           >
             <option value="">
-              {filters.years.length > 0 ? `${Math.max(...filters.years)} (Latest)` : 'Latest'}
+              {filters.years.length > 0 ? `${formatAcademicYear(Math.max(...filters.years))} (Latest)` : 'Latest'}
             </option>
             {filters.years.map((year) => (
               <option key={year} value={year}>
-                {year}
+                {formatAcademicYear(year)}
               </option>
             ))}
           </select>
@@ -199,7 +218,7 @@ export function RankingsView({
             message="Try selecting a different metric, area, or year."
             action={{
               label: 'Clear filters',
-              onClick: () => router.push(pathname),
+              onClick: () => router.push(`${pathname}?phase=${selectedPhase}`),
             }}
           />
         ) : (
@@ -248,7 +267,7 @@ export function RankingsView({
                         )}
                       </td>
                       <td className={styles.schoolCell}>
-                        <a href={`/school/${ranking.urn}`} className={styles.schoolLink}>
+                        <a href={schoolUrl(ranking.urn, ranking.school_name)} className={styles.schoolLink}>
                           {ranking.school_name}
                         </a>
                       </td>
@@ -258,7 +277,7 @@ export function RankingsView({
                         <strong>{displayValue}</strong>
                       </td>
                       <td className={styles.actionCell}>
-                        <a href={`/school/${ranking.urn}`} className="btn btn-tertiary btn-sm">View</a>
+                        <a href={schoolUrl(ranking.urn, ranking.school_name)} className="btn btn-tertiary btn-sm">View</a>
                         <button
                           onClick={() => handleAddToCompare(ranking)}
                           disabled={alreadyInComparison}

nextjs-app/components/SatsChart.module.css

@@ -0,0 +1,190 @@
+/* SatsChart — Cascade bar chart for KS2 SATs results */
+
+.container {
+  display: grid;
+  grid-template-columns: repeat(3, 1fr);
+  gap: 2rem;
+}
+
+/* ── Individual subject column ── */
+.subjectChart {
+  position: relative;
+}
+
+.subjectName {
+  font-size: 0.7rem;
+  font-weight: 600;
+  text-transform: uppercase;
+  letter-spacing: 0.08em;
+  color: var(--text-muted, #6d685f);
+  margin-bottom: 0.65rem;
+}
+
+.chartArea {
+  position: relative;
+  padding-bottom: 0.25rem;
+}
+
+/* ── Gridlines ── */
+.gridlines {
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  bottom: 20px;
+  pointer-events: none;
+}
+
+.gridline {
+  position: absolute;
+  top: 0;
+  height: 100%;
+  width: 1px;
+  background: var(--bg-secondary, #f3ede4);
+}
+
+/* ── National average marker ── */
+.natLine {
+  position: absolute;
+  top: 0;
+  height: calc(100% - 20px);
+  width: 1.5px;
+  background: rgba(224, 114, 86, 0.25); /* --accent-coral at 25% */
+  z-index: 2;
+  pointer-events: none;
+}
+
+.natPill {
+  position: absolute;
+  top: -8px;
+  transform: translateX(-50%);
+  background: var(--accent-coral, #e07256);
+  color: #fff;
+  font-size: 0.55rem;
+  font-weight: 700;
+  padding: 0.1rem 0.4rem;
+  border-radius: 4px;
+  white-space: nowrap;
+  z-index: 3;
+  letter-spacing: 0.02em;
+}
+
+/* ── Bar rows ── */
+.barGroup {
+  position: relative;
+  z-index: 1;
+  display: flex;
+  flex-direction: column;
+  gap: 0.5rem;
+  padding-top: 0.9rem;
+}
+
+.barRow {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.bar {
+  height: 22px;
+  border-radius: 6px;
+  position: relative;
+  transition: width 0.8s cubic-bezier(0.25, 0.46, 0.45, 0.94);
+}
+
+.barExpected {
+  background: var(--accent-teal-light, #3a9e9e);
+}
+
+.barExceeding {
+  background: var(--accent-teal, #2d7d7d);
+}
+
+.barLabel {
+  font-size: 0.72rem;
+  font-weight: 600;
+  color: var(--text-primary, #1a1612);
+  white-space: nowrap;
+  flex-shrink: 0;
+  position: relative;
+  z-index: 3;
+}
+
+.barLabelSuffix {
+  font-weight: 400;
+  color: var(--text-muted, #6d685f);
+  font-size: 0.68rem;
+}
+
+/* ── Ruler ── */
+.ruler {
+  position: relative;
+  height: 16px;
+  margin-top: 0.5rem;
+  border-top: 1px solid var(--border-color, #e5dfd5);
+}
+
+.rulerTick {
+  position: absolute;
+  top: 0;
+  width: 1px;
+  height: 4px;
+  background: var(--border-color, #e5dfd5);
+}
+
+.rulerLabel {
+  position: absolute;
+  top: 6px;
+  font-size: 0.5rem;
+  font-weight: 500;
+  color: var(--text-muted, #6d685f);
+  transform: translateX(-50%);
+  letter-spacing: 0.01em;
+  opacity: 0.7;
+}
+
+/* Anchor first/last labels to edges */
+.rulerLabelFirst {
+  transform: translateX(0);
+}
+
+.rulerLabelLast {
+  transform: translateX(-100%);
+}
+
+/* ── Legend ── */
+.legend {
+  margin-top: 1rem;
+  display: flex;
+  gap: 1.25rem;
+  justify-content: center;
+}
+
+.legendItem {
+  display: flex;
+  align-items: center;
+  gap: 0.35rem;
+  font-size: 0.65rem;
+  font-weight: 500;
+  color: var(--text-muted, #6d685f);
+}
+
+.legendSwatch {
+  width: 8px;
+  height: 8px;
+  border-radius: 3px;
+  flex-shrink: 0;
+}
+
+/* ── Responsive ── */
+@media (max-width: 640px) {
+  .container {
+    grid-template-columns: 1fr;
+    gap: 1.5rem;
+  }
+
+  .legend {
+    flex-wrap: wrap;
+    gap: 0.75rem;
+  }
+}