feat: GIAS code->name dictionaries generated from live bulk CSV

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-09 10:38:19 +01:00
parent 08bd86db05
commit e188c2ff4b
5 changed files with 626 additions and 0 deletions
@@ -0,0 +1,152 @@
+"""GIAS code -> name dictionaries.
+
+GENERATED by pipeline/scripts/generate_gias_codes.py from the GIAS bulk CSV
+— do not edit by hand; rerun the script when the dbt drift test warns.
+The canonical file is backend/gias_codes.py; pipeline/scripts/gias_codes.py
+must be byte-identical (enforced by backend/tests/test_gias_codes.py).
+"""
+
+from __future__ import annotations
+
+import logging
+import math
+
+logger = logging.getLogger(__name__)
+
+
+SCHOOL_TYPE: dict[int, str] = {
+    1: "Community school",
+    2: "Voluntary aided school",
+    3: "Voluntary controlled school",
+    5: "Foundation school",
+    6: "City technology college",
+    7: "Community special school",
+    8: "Non-maintained special school",
+    10: "Other independent special school",
+    11: "Other independent school",
+    12: "Foundation special school",
+    14: "Pupil referral unit",
+    15: "Local authority nursery school",
+    18: "Further education",
+    24: "Secure units",
+    25: "Offshore schools",
+    26: "Service children's education",
+    27: "Miscellaneous",
+    28: "Academy sponsor led",
+    29: "Higher education institutions",
+    30: "Welsh establishment",
+    31: "Sixth form centres",
+    32: "Special post 16 institution",
+    33: "Academy special sponsor led",
+    34: "Academy converter",
+    35: "Free schools",
+    36: "Free schools special",
+    37: "British schools overseas",
+    38: "Free schools alternative provision",
+    39: "Free schools 16 to 19",
+    40: "University technical college",
+    41: "Studio schools",
+    42: "Academy alternative provision converter",
+    43: "Academy alternative provision sponsor led",
+    44: "Academy special converter",
+    45: "Academy 16-19 converter",
+    46: "Academy 16 to 19 sponsor led",
+    49: "Online provider",
+    56: "Institution funded by other government department",
+    57: "Academy secure 16 to 19",
+}
+
+ESTABLISHMENT_STATUS: dict[int, str] = {
+    1: "Open",
+    2: "Closed",
+    3: "Open, but proposed to close",
+    4: "Proposed to open",
+}
+
+PHASE_OF_EDUCATION: dict[int, str] = {
+    0: "Not applicable",
+    1: "Nursery",
+    2: "Primary",
+    3: "Middle deemed primary",
+    4: "Secondary",
+    5: "Middle deemed secondary",
+    6: "16 plus",
+    7: "All-through",
+}
+
+OFFICIAL_SIXTH_FORM: dict[int, str] = {
+    0: "Not applicable",
+    1: "Has a sixth form",
+    2: "Does not have a sixth form",
+}
+
+RELIGIOUS_CHARACTER: dict[int, str] = {
+    0: "Does not apply",
+    2: "Church of England",
+    3: "Roman Catholic",
+    4: "Methodist",
+    5: "Jewish",
+    6: "None",
+    7: "Muslim",
+    8: "Seventh Day Adventist",
+    9: "Church of England/Methodist",
+    10: "Methodist/Church of England",
+    11: "Church of England/Roman Catholic",
+    12: "Church of England/United Reformed Church",
+    13: "Roman Catholic/Church of England",
+    14: "Quaker",
+    15: "Christian",
+    16: "United Reformed Church",
+    17: "Congregational Church",
+    18: "Free Church",
+    19: "Church of England/Free Church",
+    20: "Church of England/Christian",
+    21: "Sikh",
+    22: "Greek Orthodox",
+    24: "Buddhist",
+    25: "Hindu",
+    26: "Moravian",
+    28: "Inter- / non- denominational",
+    29: "Multi-faith",
+    30: "Church of England/Methodist/United Reform Church/Baptist",
+    31: "Anglican",
+    32: "Anglican/Christian",
+    33: "Anglican/Evangelical",
+    34: "Anglican/Church of England",
+    35: "Catholic",
+    36: "Charadi Jewish",
+    37: "Christian/Evangelical",
+    38: "Christian Science",
+    39: "Christian/Methodist",
+    40: "Christian/non-denominational",
+    41: "Church of England/Evangelical",
+    42: "Islam",
+    43: "Orthodox Jewish",
+    44: "Plymouth Brethren Christian Church",
+    45: "Protestant",
+    46: "Protestant/Evangelical",
+    47: "Reformed Baptist",
+    48: "Roman Catholic/Anglican",
+    49: "Sunni Deobandi",
+}
+
+ADMISSIONS_POLICY: dict[int, str] = {
+    0: "Not applicable",
+    2: "Selective",
+    4: "Non-selective",
+}
+
+
+def translate(code, mapping: dict[int, str]) -> str | None:
+    """Translate a GIAS code to its display name.
+
+    None/NaN -> None (column absent or suppressed). Unknown codes degrade to
+    "Unknown (<code>)" with a warning so a new DfE value never blanks the UI.
+    """
+    if code is None or (isinstance(code, float) and math.isnan(code)):
+        return None
+    code = int(code)
+    if code not in mapping:
+        logger.warning("Unknown GIAS code %s (not in dictionary)", code)
+        return f"Unknown ({code})"
+    return mapping[code]
@@ -0,0 +1,83 @@
+"""Tests for the GIAS code->name dictionaries (spec 2026-07-09).
+
+The dictionaries are generated from the live GIAS bulk CSV by
+pipeline/scripts/generate_gias_codes.py — these tests assert the module's
+contract, key sentinel values the marts/UI depend on, and that the pipeline
+copy has not drifted from the canonical backend module.
+"""
+
+import math
+from pathlib import Path
+
+from backend.gias_codes import (
+    ADMISSIONS_POLICY,
+    ESTABLISHMENT_STATUS,
+    OFFICIAL_SIXTH_FORM,
+    PHASE_OF_EDUCATION,
+    RELIGIOUS_CHARACTER,
+    SCHOOL_TYPE,
+    translate,
+)
+
+REPO = Path(__file__).resolve().parents[2]
+
+
+def test_translate_known_code():
+    open_code = next(c for c, n in ESTABLISHMENT_STATUS.items() if n == "Open")
+    assert translate(open_code, ESTABLISHMENT_STATUS) == "Open"
+
+
+def test_translate_unknown_code_degrades_gracefully():
+    assert translate(9999, ESTABLISHMENT_STATUS) == "Unknown (9999)"
+
+
+def test_translate_none_and_nan_return_none():
+    assert translate(None, ESTABLISHMENT_STATUS) is None
+    assert translate(float("nan"), ESTABLISHMENT_STATUS) is None
+
+
+def test_translate_accepts_float_codes():
+    # pd.read_sql yields float columns when NULLs are present
+    open_code = next(c for c, n in ESTABLISHMENT_STATUS.items() if n == "Open")
+    assert translate(float(open_code), ESTABLISHMENT_STATUS) == "Open"
+
+
+def test_sentinel_names_present():
+    """Names the marts/UI compare against must exist verbatim."""
+    assert "Open" in ESTABLISHMENT_STATUS.values()
+    assert "Open, but proposed to close" in ESTABLISHMENT_STATUS.values()
+    assert "Has a sixth form" in OFFICIAL_SIXTH_FORM.values()
+    assert "Primary" in PHASE_OF_EDUCATION.values()
+    assert "Secondary" in PHASE_OF_EDUCATION.values()
+    assert "Does not apply" in RELIGIOUS_CHARACTER.values()
+    assert all(len(d) > 0 for d in (
+        SCHOOL_TYPE, ESTABLISHMENT_STATUS, PHASE_OF_EDUCATION,
+        OFFICIAL_SIXTH_FORM, RELIGIOUS_CHARACTER, ADMISSIONS_POLICY,
+    ))
+
+
+def test_pipeline_copy_is_identical():
+    canonical = (REPO / "backend" / "gias_codes.py").read_text()
+    copy = (REPO / "pipeline" / "scripts" / "gias_codes.py").read_text()
+    assert canonical == copy, (
+        "pipeline/scripts/gias_codes.py has drifted from backend/gias_codes.py — "
+        "regenerate with pipeline/scripts/generate_gias_codes.py and copy the file"
+    )
+
+
+def test_seed_matches_dictionaries():
+    import csv
+    fields = {
+        "school_type": SCHOOL_TYPE,
+        "establishment_status": ESTABLISHMENT_STATUS,
+        "phase_of_education": PHASE_OF_EDUCATION,
+        "official_sixth_form": OFFICIAL_SIXTH_FORM,
+        "religious_character": RELIGIOUS_CHARACTER,
+        "admissions_policy": ADMISSIONS_POLICY,
+    }
+    seed_path = REPO / "pipeline" / "transform" / "seeds" / "gias_code_names.csv"
+    seed: dict[str, dict[int, str]] = {k: {} for k in fields}
+    with open(seed_path, newline="") as fh:
+        for row in csv.DictReader(fh):
+            seed[row["field"]][int(row["code"])] = row["name"]
+    assert seed == fields