dialect_analysis/scoring.py

from __future__ import annotations

import math
from collections import Counter
from typing import Any, Dict, Mapping, Tuple

from .features import ENDINGS_PLAIN, INFINITIVE_ENDINGS_PLAIN, PARTICLES, compute_rates


DIALECTS: Tuple[str, ...] = ("Attic", "Ionic", "Doric", "Aeolic", "Koine")


def _clamp(x: float, lo: float, hi: float) -> float:
    return max(lo, min(hi, x))


def _softmax_percent(raw_scores: Mapping[str, float], *, temperature: float = 2.0) -> Dict[str, float]:
    """Softmax over dialect scores with temperature to reduce overconfidence."""

    if not raw_scores:
        return {d: 0.0 for d in DIALECTS}

    t = max(1e-6, float(temperature))
    max_raw = max(float(v) for v in raw_scores.values())
    exp_scores = {d: math.exp((float(raw_scores[d]) - max_raw) / t) for d in DIALECTS}
    total = sum(exp_scores.values()) or 1.0
    return {d: 100.0 * (exp_scores[d] / total) for d in DIALECTS}


def score_dialects(feature_dict: Mapping[str, Any]) -> Dict[str, float]:
    """Score dialects using a weighted, rule-based scoring system.



    Returns a dict mapping dialect -> confidence percentage (0-100).



    Weights are placeholders intended to be edited as the rule-set grows.

    """

    rates = compute_rates(feature_dict)

    token_count = int(feature_dict.get("token_count", 0) or 0)
    script = feature_dict.get("script", {}) or {}
    greek_alpha = int(script.get("greek_alpha_chars", 0) or 0)
    alpha_chars = int(script.get("alpha_chars", 0) or 0)
    greek_ratio = (greek_alpha / alpha_chars) if alpha_chars > 0 else 0.0

    particle_rates: Mapping[str, float] = rates["particles_per_100"]
    ending_rates: Mapping[str, float] = rates["endings_per_100"]
    infinitives: Mapping[str, int] = feature_dict.get("infinitives", {}) or {}
    poetic_morph: Mapping[str, int] = feature_dict.get("poetic_morph", {}) or {}
    epic_particle_rates: Mapping[str, float] = rates.get("epic_particles_per_100", {}) or {}
    epic_ending_rates: Mapping[str, float] = rates.get("epic_endings_per_100", {}) or {}
    epic_words: Mapping[str, int] = feature_dict.get("epic_words", {}) or {}
    dative_plural_rates: Mapping[str, float] = rates.get("dative_plural_endings_per_100", {}) or {}
    prepositions: Mapping[str, int] = feature_dict.get("prepositions", {}) or {}
    koine_words: Mapping[str, int] = feature_dict.get("koine_words", {}) or {}
    lexical_cues: Mapping[str, int] = feature_dict.get("lexical_cues", {}) or {}
    doric_cues: Mapping[str, int] = feature_dict.get("doric_cues", {}) or {}
    patterns: Mapping[str, int] = feature_dict.get("patterns", {}) or {}
    marked_rate = float(rates["marked_endings_per_100"])

    epic_oio_rate = float(epic_ending_rates.get("οιο", 0.0) or 0.0)
    epic_essi_rate = float(epic_ending_rates.get("εσσι", 0.0) or 0.0)
    epic_fi_rate = float(epic_ending_rates.get("φι", 0.0) or 0.0)

    epic_eta_os_rate = float(epic_ending_rates.get("ηοσ", 0.0) or 0.0)
    epic_adeo_rate = float(epic_ending_rates.get("αδεω", 0.0) or 0.0)
    epic_ideo_rate = float(epic_ending_rates.get("ιδεω", 0.0) or 0.0)

    epic_ke_rate = float(epic_particle_rates.get("κε", 0.0) or 0.0)
    epic_ken_rate = float(epic_particle_rates.get("κεν", 0.0) or 0.0)
    epic_ke_ken_rate = epic_ke_rate + epic_ken_rate

    epic_ar_rate = float(epic_particle_rates.get("αρ", 0.0) or 0.0)
    epic_min_rate = float(epic_particle_rates.get("μιν", 0.0) or 0.0)

    tt_count = int(patterns.get("tt", 0) or 0)
    ss_count = int(patterns.get("ss", 0) or 0)

    # --- Weights (MVP placeholders) ---
    weights: Dict[str, Dict[str, float]] = {
        "particle_μεν": {"Attic": 0.25, "Ionic": 0.15, "Doric": 0.10, "Aeolic": 0.10, "Koine": 0.05},
        "particle_δε": {"Attic": 0.20, "Ionic": 0.20, "Doric": 0.15, "Aeolic": 0.15, "Koine": 0.10},
        "particle_γαρ": {"Attic": 0.20, "Ionic": 0.15, "Doric": 0.10, "Aeolic": 0.10, "Koine": 0.10},
        "particle_τε": {"Attic": 0.15, "Ionic": 0.10, "Doric": 0.20, "Aeolic": 0.12, "Koine": 0.05},
        "particle_δη": {"Attic": 0.10, "Ionic": 0.10, "Doric": 0.10, "Aeolic": 0.08, "Koine": 0.05},
        "particle_ουν": {"Attic": 0.15, "Ionic": 0.10, "Doric": 0.05, "Aeolic": 0.05, "Koine": 0.10},

        "ending_οισι": {"Ionic": 3.50, "Attic": -1.00, "Doric": 0.50, "Aeolic": 0.20, "Koine": -1.50},
        "ending_ηι": {"Attic": 1.10, "Ionic": 0.80, "Doric": 0.10, "Aeolic": 0.20, "Koine": -0.30},
        "ending_ᾳ": {"Attic": 0.80, "Ionic": 0.60, "Doric": 0.30, "Aeolic": 0.20, "Koine": -0.60},
        "ending_οι": {"Attic": 0.15, "Ionic": 0.15, "Doric": 0.15, "Aeolic": 0.15, "Koine": 0.15},
        "ending_αι": {"Attic": 0.15, "Ionic": 0.15, "Doric": 0.15, "Aeolic": 0.15, "Koine": 0.15},

        # NOTE: This is intentionally low-weight. "Few strong markers" is not
        # uniquely Koine; it can also describe many Attic passages.
        "low_marked_endings": {"Koine": 0.25, "Attic": 0.05, "Ionic": -0.05, "Doric": 0.05, "Aeolic": -0.05},

        # Homeric / epic-Ionic signal
        "epic_ending_οιο": {"Ionic": 4.00, "Attic": -0.50, "Doric": -0.50, "Aeolic": -0.30, "Koine": -0.50},

        # Epic endings and particles (conservative; only meaningful when present)
        "epic_ending_εσσι": {"Ionic": 3.00, "Attic": -0.40, "Doric": -0.20, "Aeolic": -0.20, "Koine": -0.80},
        "epic_ending_φι": {"Ionic": 1.50, "Attic": -0.20, "Doric": 0.10, "Aeolic": 0.05, "Koine": -0.50},
        "epic_particle_κεκεν": {"Ionic": 2.00, "Attic": -0.20, "Doric": 0.10, "Aeolic": 0.05, "Koine": -0.70},

        "epic_ending_ηοσ": {"Ionic": 2.60, "Attic": -0.30, "Doric": -0.10, "Aeolic": -0.10, "Koine": -0.60},
        "epic_ending_αδεω": {"Ionic": 2.80, "Attic": -0.20, "Doric": 0.00, "Aeolic": 0.00, "Koine": -0.70},
        "epic_ending_ιδεω": {"Ionic": 2.80, "Attic": -0.20, "Doric": 0.00, "Aeolic": 0.00, "Koine": -0.70},

        # Homeric / epic particles (ambiguous individually; keep weights modest)
        "epic_particle_αρ": {"Ionic": 0.80, "Attic": -0.05, "Doric": 0.00, "Aeolic": 0.00, "Koine": -0.15},
        "epic_particle_μιν": {"Ionic": 1.20, "Attic": -0.10, "Doric": 0.00, "Aeolic": 0.00, "Koine": -0.25},

        # Homeric vocabulary: apply only when multiple hits occur (see logic below)
        "epic_word_hits": {"Ionic": 1.80, "Attic": 0.00, "Doric": 0.00, "Aeolic": 0.00, "Koine": 0.00},

        # Orthographic patterns (COUNT-based; prevents short-text rate blowups)
        "pattern_tt": {"Attic": 0.45, "Ionic": 0.00, "Doric": 0.00, "Aeolic": 0.00, "Koine": 0.05},
        "pattern_ss": {"Ionic": 0.10, "Attic": 0.00, "Doric": 0.00, "Aeolic": 0.00, "Koine": 0.00},

        # Dative plural endings: -οισι/-αισι/-ηισι vs -οις/-αις
        "dative_οισι": {"Ionic": 0.90, "Attic": -0.20, "Doric": 0.10, "Aeolic": 0.05, "Koine": -0.40},
        "dative_αισι": {"Ionic": 2.20, "Attic": -0.40, "Doric": 0.20, "Aeolic": 0.10, "Koine": -0.80},
        "dative_ηισι": {"Ionic": 2.20, "Attic": -0.30, "Doric": 0.10, "Aeolic": 0.10, "Koine": -0.80},
        "dative_οις": {"Attic": 0.20, "Ionic": 0.05, "Doric": 0.10, "Aeolic": 0.10, "Koine": 0.15},
        "dative_αις": {"Attic": 0.20, "Ionic": 0.05, "Doric": 0.10, "Aeolic": 0.10, "Koine": 0.15},

        # εἰς vs ἐς (COUNT-based; keys are sigma-normalized: εισ / εσ)
        "prep_εισ": {"Koine": 0.30, "Attic": 0.05, "Ionic": 0.00, "Doric": 0.00, "Aeolic": 0.00},
        "prep_εσ": {"Attic": 0.25, "Ionic": 0.15, "Koine": 0.05, "Doric": 0.00, "Aeolic": 0.05},

        # Koine-ish function words (COUNT-based; sigma-normalized: καθωσ)
        "koine_ινα": {"Koine": 0.60, "Attic": 0.00, "Ionic": 0.00, "Doric": 0.00},
        "koine_οτι": {"Koine": 0.40, "Attic": 0.00, "Ionic": 0.00, "Doric": 0.00},
        "koine_καθωσ": {"Koine": 0.35, "Attic": 0.00, "Ionic": 0.00, "Doric": 0.00},
        "koine_εγενετο": {"Koine": 0.90, "Attic": 0.00, "Ionic": 0.00, "Doric": 0.00, "Aeolic": 0.00},

        # Lexicalized ττ/σσ stems (COUNT-based)
        "lexical_attic_tt": {"Attic": 0.75, "Koine": 0.08, "Ionic": 0.00, "Doric": 0.00},
        "lexical_ionic_ss": {"Ionic": 0.25, "Attic": 0.00, "Doric": 0.00, "Koine": 0.00},

        # Doric-ish ἁ- (very weak; COUNT-based)
        "doric_ha_initial": {"Doric": 0.12, "Attic": 0.00, "Ionic": 0.00, "Koine": 0.00},

        # Infinitives (morphology): strong signal when present
        # These are COUNT-based to avoid short-text rate blowups.
        "inf_μεναι": {"Aeolic": 2.40, "Doric": 0.40, "Ionic": 0.05, "Attic": 0.00, "Koine": 0.00},
        "inf_μεν": {"Doric": 1.20, "Aeolic": 0.80, "Ionic": 0.00, "Attic": 0.00, "Koine": 0.00},
        "inf_ειν": {"Koine": 0.55, "Attic": 0.35, "Ionic": 0.35, "Doric": 0.00, "Aeolic": 0.00},

        # Poetic morphology cues (COUNT-based)
        "verb_1pl_mes": {"Doric": 1.30, "Aeolic": 0.30, "Attic": 0.00, "Ionic": 0.00, "Koine": 0.00},
        "aeolic_ammi": {"Aeolic": 2.20, "Doric": 0.20, "Attic": 0.00, "Ionic": 0.00, "Koine": 0.00},
        "aeolic_ummi": {"Aeolic": 2.20, "Doric": 0.20, "Attic": 0.00, "Ionic": 0.00, "Koine": 0.00},
    }

    raw_scores: Dict[str, float] = {d: 1.0 for d in DIALECTS}
    contributions: Dict[str, Counter[str]] = {d: Counter() for d in DIALECTS}

    # Evidence scaling: short passages should not yield extreme confidence.
    evidence_scale = _clamp(token_count / 40.0, 0.0, 1.0)
    if greek_ratio < 0.30:
        evidence_scale *= 0.15

    def apply_feature(feature_name: str, feature_value: float) -> None:
        for dialect, w in weights.get(feature_name, {}).items():
            delta = w * feature_value * evidence_scale
            raw_scores[dialect] += delta
            contributions[dialect][feature_name] += delta

    def apply_tier_a(feature_name: str, feature_value: float) -> None:
        """Apply highly diagnostic features with a minimum evidence scale.



        Rationale: some morphology is genuinely strong evidence even in short

        passages; we still keep the scale modest to avoid overconfidence.

        """

        tier_scale = max(evidence_scale, 0.25)
        for dialect, w in weights.get(feature_name, {}).items():
            delta = w * feature_value * tier_scale
            raw_scores[dialect] += delta
            contributions[dialect][feature_name] += delta

    for p in PARTICLES:
        apply_feature(f"particle_{p}", float(particle_rates.get(p, 0.0)))

    for e in (*ENDINGS_PLAIN, "ᾳ"):
        apply_feature(f"ending_{e}", float(ending_rates.get(e, 0.0)))

    # Infinitive morphology
    apply_tier_a("inf_μεναι", float(int(infinitives.get("μεναι", 0) or 0)))
    apply_tier_a("inf_μεν", float(int(infinitives.get("μεν", 0) or 0)))
    apply_tier_a("inf_ειν", float(int(infinitives.get("ειν", 0) or 0)))

    # Poetic morphology
    apply_tier_a("verb_1pl_mes", float(int(poetic_morph.get("verb_1pl_mes", 0) or 0)))
    apply_tier_a("aeolic_ammi", float(int(poetic_morph.get("aeolic_ammi", 0) or 0)))
    apply_tier_a("aeolic_ummi", float(int(poetic_morph.get("aeolic_ummi", 0) or 0)))

    # Only apply the Koine scarcity heuristic when we have enough text.
    if token_count >= 20:
        apply_feature("low_marked_endings", max(0.0, 1.5 - marked_rate))

    # Epic marker
    apply_feature("epic_ending_οιο", epic_oio_rate)

    # Additional epic markers
    apply_feature("epic_ending_εσσι", epic_essi_rate)
    apply_feature("epic_ending_φι", epic_fi_rate)
    apply_feature("epic_particle_κεκεν", epic_ke_ken_rate)
    apply_feature("epic_ending_ηοσ", epic_eta_os_rate)
    apply_feature("epic_ending_αδεω", epic_adeo_rate)
    apply_feature("epic_ending_ιδεω", epic_ideo_rate)
    apply_feature("epic_particle_αρ", epic_ar_rate)
    apply_feature("epic_particle_μιν", epic_min_rate)

    epic_word_hits = sum(
        int(epic_words.get(w, 0) or 0)
        for w in ("εννεπε", "αειδε", "μουσα", "μηνιν", "θεα")
    )
    if epic_word_hits >= 2:
        apply_tier_a("epic_word_hits", float(min(4, epic_word_hits)))

    # tt/ss orthography (separate, conservative)
    apply_feature("pattern_tt", float(tt_count))
    apply_feature("pattern_ss", float(ss_count))

    # Dative plural endings
    apply_feature("dative_οισι", float(dative_plural_rates.get("οισι", 0.0) or 0.0))
    apply_feature("dative_αισι", float(dative_plural_rates.get("αισι", 0.0) or 0.0))
    apply_feature("dative_ηισι", float(dative_plural_rates.get("ηισι", 0.0) or 0.0))
    apply_feature("dative_οις", float(dative_plural_rates.get("οις", 0.0) or 0.0))
    apply_feature("dative_αις", float(dative_plural_rates.get("αις", 0.0) or 0.0))

    # εἰς / ἐς (counts; sigma-normalized)
    apply_feature("prep_εισ", float(int(prepositions.get("εισ", 0) or 0)))
    apply_feature("prep_εσ", float(int(prepositions.get("εσ", 0) or 0)))

    # Koine-ish function words (counts; sigma-normalized)
    apply_feature("koine_ινα", float(int(koine_words.get("ινα", 0) or 0)))
    apply_feature("koine_οτι", float(int(koine_words.get("οτι", 0) or 0)))
    apply_feature("koine_καθωσ", float(int(koine_words.get("καθωσ", 0) or 0)))
    apply_feature("koine_εγενετο", float(int(koine_words.get("εγενετο", 0) or 0)))

    # Lexicalized ττ/σσ stems (counts)
    apply_feature("lexical_attic_tt", float(int(lexical_cues.get("attic_tt", 0) or 0)))
    apply_feature("lexical_ionic_ss", float(int(lexical_cues.get("ionic_ss", 0) or 0)))

    # Doric cue (very noisy): require longer text + multiple hits
    ha_hits = int(doric_cues.get("ha_initial", 0) or 0)
    if token_count >= 30 and ha_hits >= 2:
        apply_feature("doric_ha_initial", float(ha_hits))

    # If mutable, persist diagnostics for explainability.
    if isinstance(feature_dict, dict):
        feature_dict["rates"] = rates
        feature_dict["diagnostics"] = {
            "greek_ratio": greek_ratio,
            "evidence_scale": evidence_scale,
        }
        feature_dict["_raw_scores"] = dict(raw_scores)
        feature_dict["_contributions"] = {d: dict(contributions[d]) for d in DIALECTS}

    # Slightly increase confidence only when evidence is strong.
    temperature = _clamp(2.0 - 0.6 * evidence_scale, 1.4, 2.0)
    scores = _softmax_percent(raw_scores, temperature=temperature)

    # Post-hoc discrimination diagnostics.
    ordered = sorted(scores.items(), key=lambda kv: kv[1], reverse=True)
    best_pct = float(ordered[0][1]) if ordered else 0.0
    second_pct = float(ordered[1][1]) if len(ordered) > 1 else 0.0
    top_gap_pct = best_pct - second_pct

    if isinstance(feature_dict, dict):
        diagnostics = feature_dict.get("diagnostics", {}) or {}
        diagnostics.update(
            {
                "best_pct": best_pct,
                "second_pct": second_pct,
                "top_gap_pct": top_gap_pct,
            }
        )
        feature_dict["diagnostics"] = diagnostics

    return scores