"""Compute Ofsted-rated school proximity counts per postcode."""

import argparse
from pathlib import Path

import polars as pl

from pipeline.utils.poi_counts import count_pois_per_postcode

SCHOOL_GROUPS = {
    "good_primary": ["good_primary", "outstanding_primary"],
    "good_secondary": ["good_secondary", "outstanding_secondary"],
    "outstanding_primary": ["outstanding_primary"],
    "outstanding_secondary": ["outstanding_secondary"],
}


# Age thresholds for deciding which phase(s) a school serves. A school serves
# PRIMARY-age children if its statutory lowest age is <= 10, and SECONDARY-age
# children if its statutory highest age is >= 12. All-through (e.g. 3-18) and
# middle-deemed-secondary (e.g. 9-13) schools satisfy BOTH and so are counted in
# both the primary and the secondary proximity metrics — Ofsted's coarse "Ofsted
# phase" labels such schools as just "Secondary", which previously hid them from
# every postcode's primary-school count.
PRIMARY_MAX_AGE = 10
SECONDARY_MIN_AGE = 12


def classify_good_plus_schools(
    ofsted: pl.DataFrame, open_urns: set[int] | None = None
) -> pl.DataFrame:
    """Label good+/outstanding primary & secondary schools for proximity counts.

    Derives a grade ("1" = outstanding, "2" = good) and one or two proximity
    ``category`` rows per school, returning a ``(postcode, category)`` frame.

    Schools with a recent GRADED inspection carry a 1-4 grade in "Latest OEIF
    overall effectiveness" (OEIF = the previous Ofsted Education Inspection
    Framework). A large and growing share of schools were last inspected under an
    UNGRADED (Section 8) inspection or the post-2024 report-card framework, so
    that column is null/"Not judged" for them even when they are demonstrably
    good — their status lives in "Ungraded inspection overall outcome" ("School
    remains Good"/"School remains Outstanding"). Filtering on the graded column
    alone dropped ~7,000 genuinely good/outstanding schools. We fall back to the
    ungraded outcome, but ONLY when there is no usable graded result
    (null/"Not judged"), so a genuine grade 3/4 is never overridden.

    Outcomes flagged "(Concerns)" are NOT treated as good+: a "remains Good
    (Concerns)" outcome signals inspectors found issues warranting an earlier
    graded re-inspection, so marketing it as a good+ school is misleading.

    Phase assignment uses the statutory age range when available (so all-through
    and middle schools count toward BOTH primary and secondary), falling back to
    the coarse "Ofsted phase" label when age columns are absent. When
    ``open_urns`` is given, schools whose URN is not in the current GIAS open
    register are dropped so closed/merged schools are not counted.
    """
    # Cast to Utf8 so the string predicates below are well-defined even if a
    # column happens to be entirely null (read back as a Null dtype).
    oeif = pl.col("Latest OEIF overall effectiveness").cast(pl.Utf8, strict=False)
    ungraded = pl.col("Ungraded inspection overall outcome").cast(pl.Utf8, strict=False)
    no_usable_grade = oeif.is_null() | (oeif == "Not judged")
    has_concern = ungraded.str.contains(r"\(Concerns\)")
    remains_outstanding = (
        ungraded.str.starts_with("School remains Outstanding") & ~has_concern
    )
    remains_good = ungraded.str.starts_with("School remains Good") & ~has_concern
    graded = (
        ofsted.filter(pl.col("Ofsted phase").is_in(["Primary", "Secondary"]))
        .with_columns(
            pl.when(oeif.is_in(["1", "2"]))
            .then(oeif)
            .when(no_usable_grade & remains_outstanding)
            .then(pl.lit("1"))
            .when(no_usable_grade & remains_good)
            .then(pl.lit("2"))
            .otherwise(None)
            .alias("_ofsted_grade")
        )
        .filter(pl.col("_ofsted_grade").is_not_null())
    )

    # Drop schools no longer open (closed/merged) when the GIAS open register is
    # provided, so stale Ofsted "latest inspection" rows are not counted.
    if open_urns is not None and "URN" in graded.columns:
        graded = graded.filter(pl.col("URN").is_in(list(open_urns)))

    # Decide which phase(s) each school serves.
    if {"Statutory lowest age", "Statutory highest age"} <= set(graded.columns):
        low = pl.col("Statutory lowest age").cast(pl.Int64, strict=False)
        high = pl.col("Statutory highest age").cast(pl.Int64, strict=False)
        serves_primary = (
            pl.when(low.is_not_null())
            .then(low <= PRIMARY_MAX_AGE)
            .otherwise(pl.col("Ofsted phase") == "Primary")
        )
        serves_secondary = (
            pl.when(high.is_not_null())
            .then(high >= SECONDARY_MIN_AGE)
            .otherwise(pl.col("Ofsted phase") == "Secondary")
        )
    else:
        serves_primary = pl.col("Ofsted phase") == "Primary"
        serves_secondary = pl.col("Ofsted phase") == "Secondary"

    graded = graded.with_columns(
        serves_primary.alias("_serves_primary"),
        serves_secondary.alias("_serves_secondary"),
    )

    # Good+ groups include both grade variants; outstanding groups count grade 1.
    # A school can yield up to two rows (primary and secondary).
    primary = graded.filter(pl.col("_serves_primary")).with_columns(
        pl.when(pl.col("_ofsted_grade") == "1")
        .then(pl.lit("outstanding_primary"))
        .otherwise(pl.lit("good_primary"))
        .alias("category")
    )
    secondary = graded.filter(pl.col("_serves_secondary")).with_columns(
        pl.when(pl.col("_ofsted_grade") == "1")
        .then(pl.lit("outstanding_secondary"))
        .otherwise(pl.lit("good_secondary"))
        .alias("category")
    )
    return pl.concat([primary, secondary]).select(
        pl.col("Postcode").alias("postcode"),
        "category",
    )


def main():
    parser = argparse.ArgumentParser(
        description="Count good+ and outstanding primary/secondary schools near each postcode"
    )
    parser.add_argument(
        "--ofsted", type=Path, required=True, help="Ofsted inspection parquet"
    )
    parser.add_argument(
        "--arcgis", type=Path, required=True, help="ArcGIS postcode parquet"
    )
    parser.add_argument(
        "--gias",
        type=Path,
        default=None,
        help="GIAS open-school parquet; if given, only currently-open schools are counted",
    )
    parser.add_argument(
        "--output", type=Path, required=True, help="Output parquet path"
    )
    args = parser.parse_args()

    open_urns: set[int] | None = None
    if args.gias is not None:
        gias_urns = pl.read_parquet(args.gias).select("urn").to_series().drop_nulls()
        open_urns = set(gias_urns.cast(pl.Int64, strict=False).to_list())
        print(f"GIAS open register: {len(open_urns):,} open school URNs")

    ofsted = classify_good_plus_schools(pl.read_parquet(args.ofsted), open_urns=open_urns)
    if ofsted.is_empty():
        raise ValueError("No good+ primary/secondary Ofsted schools found")

    print(f"Good+ schools: {len(ofsted):,}")
    print(
        "Outstanding schools: "
        f"{ofsted.filter(pl.col('category').str.starts_with('outstanding')).height:,}"
    )

    # Join with arcgis to get lat/lng for each school's postcode
    arcgis = pl.read_parquet(args.arcgis).select(
        pl.col("pcds").alias("postcode"),
        "lat",
        pl.col("long").alias("lng"),
    )

    schools = ofsted.join(arcgis, on="postcode", how="inner")
    if schools.is_empty():
        raise ValueError("No Ofsted schools matched ArcGIS postcode coordinates")
    print(f"Schools with coordinates: {len(schools):,}")

    # Load all postcodes for proximity counting
    postcodes = arcgis.rename({"lng": "lon"})

    counts_5km = count_pois_per_postcode(
        postcodes, schools, radius_km=5, groups=SCHOOL_GROUPS
    )
    counts_2km = count_pois_per_postcode(
        postcodes, schools, radius_km=2, groups=SCHOOL_GROUPS
    )

    result = counts_5km.join(counts_2km, on="postcode")

    args.output.parent.mkdir(parents=True, exist_ok=True)
    result.write_parquet(args.output)
    size_mb = args.output.stat().st_size / (1024 * 1024)
    print(f"Wrote {args.output} ({size_mb:.1f} MB)")


if __name__ == "__main__":
    main()