"""
VQWEN v3 Training Script
========================
Retrains the VQWEN market models using only the configured top leagues.
"""

from __future__ import annotations

import json
import os
import pickle
import sys
import time
from pathlib import Path
from typing import Any

import lightgbm as lgb
import pandas as pd
import psycopg2
from dotenv import load_dotenv

AI_DIR = Path(__file__).resolve().parent
ENGINE_DIR = AI_DIR.parent
REPO_DIR = ENGINE_DIR.parent
MODELS_DIR = ENGINE_DIR / "models" / "vqwen"
TOP_LEAGUES_PATH = REPO_DIR / "top_leagues.json"

if str(ENGINE_DIR) not in sys.path:
    sys.path.insert(0, str(ENGINE_DIR))

from features.vqwen_contract import (
    FEATURE_COLUMNS,
    VqwenFeatureInput,
    build_vqwen_feature_row,
)

def _load_env() -> None:
    load_dotenv(REPO_DIR / ".env", override=False)
    load_dotenv(ENGINE_DIR / ".env", override=False)


def get_clean_dsn() -> str:
    _load_env()
    raw = os.getenv("DATABASE_URL", "").strip().strip('"').strip("'")
    if not raw:
        raise RuntimeError("DATABASE_URL is missing.")
    return raw.split("?", 1)[0]


def load_top_league_ids() -> list[str]:
    if not TOP_LEAGUES_PATH.exists():
        raise FileNotFoundError(f"top_leagues.json not found at {TOP_LEAGUES_PATH}")

    raw = json.loads(TOP_LEAGUES_PATH.read_text(encoding="utf-8"))
    if not isinstance(raw, list):
        raise ValueError("top_leagues.json must contain a JSON array.")

    league_ids = [str(item).strip() for item in raw if str(item).strip()]
    deduped = list(dict.fromkeys(league_ids))
    if not deduped:
        raise ValueError("top_leagues.json is empty.")
    return deduped


def _fetch_dataframe(cur: psycopg2.extensions.cursor, league_ids: list[str]) -> pd.DataFrame:
    query = """
        WITH match_data AS (
            SELECT
                m.id,
                m.league_id,
                m.home_team_id,
                m.away_team_id,
                m.score_home,
                m.score_away,
                m.mst_utc,
                ref.name AS referee_name,
                COALESCE(maf.home_elo, 1500) AS home_elo,
                COALESCE(maf.away_elo, 1500) AS away_elo,
                COALESCE(
                    (
                        SELECT AVG(m2.score_home)
                        FROM matches m2
                        WHERE m2.home_team_id = m.home_team_id
                          AND m2.status = 'FT'
                          AND m2.mst_utc < m.mst_utc
                    ),
                    1.2
                ) AS h_home_goals,
                COALESCE(
                    (
                        SELECT AVG(m2.score_away)
                        FROM matches m2
                        WHERE m2.away_team_id = m.away_team_id
                          AND m2.status = 'FT'
                          AND m2.mst_utc < m.mst_utc
                    ),
                    1.2
                ) AS a_away_goals,
                COALESCE(
                    (
                        SELECT EXTRACT(
                            EPOCH FROM (
                                to_timestamp(m.mst_utc / 1000.0)
                                - MAX(to_timestamp(m2.mst_utc / 1000.0))
                            )
                        ) / 86400.0
                        FROM matches m2
                        WHERE m2.home_team_id = m.home_team_id
                          AND m2.status = 'FT'
                          AND m2.mst_utc < m.mst_utc
                    ),
                    7
                ) AS h_rest,
                COALESCE(
                    (
                        SELECT EXTRACT(
                            EPOCH FROM (
                                to_timestamp(m.mst_utc / 1000.0)
                                - MAX(to_timestamp(m2.mst_utc / 1000.0))
                            )
                        ) / 86400.0
                        FROM matches m2
                        WHERE m2.away_team_id = m.away_team_id
                          AND m2.status = 'FT'
                          AND m2.mst_utc < m.mst_utc
                    ),
                    7
                ) AS a_rest,
                (
                    SELECT os.odd_value
                    FROM odd_categories oc
                    JOIN odd_selections os ON os.odd_category_db_id = oc.db_id
                    WHERE oc.match_id = m.id
                      AND oc.name ILIKE 'Maç Sonucu'
                      AND os.name = '1'
                    LIMIT 1
                ) AS oh,
                (
                    SELECT os.odd_value
                    FROM odd_categories oc
                    JOIN odd_selections os ON os.odd_category_db_id = oc.db_id
                    WHERE oc.match_id = m.id
                      AND oc.name ILIKE 'Maç Sonucu'
                      AND os.name = 'X'
                    LIMIT 1
                ) AS od,
                (
                    SELECT os.odd_value
                    FROM odd_categories oc
                    JOIN odd_selections os ON os.odd_category_db_id = oc.db_id
                    WHERE oc.match_id = m.id
                      AND oc.name ILIKE 'Maç Sonucu'
                      AND os.name = '2'
                    LIMIT 1
                ) AS oa
            FROM matches m
            LEFT JOIN football_ai_features maf ON maf.match_id = m.id
            LEFT JOIN match_officials ref ON ref.match_id = m.id AND ref.role_id = 1
            WHERE m.status = 'FT'
              AND m.score_home IS NOT NULL
              AND m.score_away IS NOT NULL
              AND m.sport = 'football'
              AND m.league_id = ANY(%s)
              AND EXISTS (SELECT 1 FROM odd_categories oc WHERE oc.match_id = m.id)
        )
        SELECT
            md.*,
            COALESCE(
                (
                    SELECT
                        (
                            COUNT(*) FILTER (
                                WHERE (
                                    (m2.home_team_id = md.home_team_id AND m2.score_home > m2.score_away)
                                    OR
                                    (m2.away_team_id = md.home_team_id AND m2.score_away > m2.score_home)
                                )
                            )::float
                            + COUNT(*) FILTER (WHERE m2.score_home = m2.score_away)::float * 0.5
                        ) / NULLIF(COUNT(*), 0)
                    FROM matches m2
                    WHERE m2.status = 'FT'
                      AND m2.mst_utc < md.mst_utc
                      AND (
                        (m2.home_team_id = md.home_team_id AND m2.away_team_id = md.away_team_id)
                        OR
                        (m2.home_team_id = md.away_team_id AND m2.away_team_id = md.home_team_id)
                      )
                ),
                0.5
            ) AS h2h_h_wr,
            COALESCE(
                (
                    SELECT SUM(points)
                    FROM (
                        SELECT
                            CASE
                                WHEN m2.score_home > m2.score_away THEN 3
                                WHEN m2.score_home = m2.score_away THEN 1
                                ELSE 0
                            END AS points
                        FROM matches m2
                        WHERE m2.home_team_id = md.home_team_id
                          AND m2.status = 'FT'
                          AND m2.mst_utc < md.mst_utc
                        ORDER BY m2.mst_utc DESC
                        LIMIT 5
                    ) home_form
                ),
                0
            ) AS h_form_pts,
            COALESCE(
                (
                    SELECT SUM(points)
                    FROM (
                        SELECT
                            CASE
                                WHEN m2.score_away > m2.score_home THEN 3
                                WHEN m2.score_away = m2.score_home THEN 1
                                ELSE 0
                            END AS points
                        FROM matches m2
                        WHERE m2.away_team_id = md.away_team_id
                          AND m2.status = 'FT'
                          AND m2.mst_utc < md.mst_utc
                        ORDER BY m2.mst_utc DESC
                        LIMIT 5
                    ) away_form
                ),
                0
            ) AS a_form_pts
        FROM match_data md
        ORDER BY md.mst_utc DESC
    """

    print("Top league verisi cekiliyor...")
    started_at = time.time()
    cur.execute(query, (league_ids,))
    rows = cur.fetchall()
    elapsed = time.time() - started_at
    print(f"{len(rows)} mac cekildi ({elapsed:.1f}s)")

    dataframe = pd.DataFrame(
        rows,
        columns=[
            "id",
            "league_id",
            "h_id",
            "a_id",
            "sh",
            "sa",
            "utc",
            "referee_name",
            "h_elo",
            "a_elo",
            "h_home_goals",
            "a_away_goals",
            "h_rest",
            "a_rest",
            "oh",
            "od",
            "oa",
            "h2h_h_wr",
            "h_form_pts",
            "a_form_pts",
        ],
    )
    return dataframe


def _compute_league_avg_goals(
    cur: psycopg2.extensions.cursor,
    league_id: str,
    before_ts: int,
) -> float:
    if not league_id:
        return 2.6

    cur.execute(
        """
        SELECT COALESCE(AVG(src.score_home + src.score_away), 2.6)
        FROM (
            SELECT score_home, score_away
            FROM matches
            WHERE league_id = %s
              AND sport = 'football'
              AND status = 'FT'
              AND score_home IS NOT NULL
              AND score_away IS NOT NULL
              AND mst_utc < %s
            ORDER BY mst_utc DESC
            LIMIT 100
        ) src
        """,
        (league_id, before_ts),
    )
    row = cur.fetchone()
    return float(row[0] or 2.6)


def _compute_referee_profile(
    cur: psycopg2.extensions.cursor,
    referee_name: str | None,
    before_ts: int,
) -> tuple[float, float]:
    if not referee_name:
        return 2.6, 0.0

    cur.execute(
        """
        SELECT
            COALESCE(AVG(score_home + score_away), 2.6) AS avg_goals,
            COALESCE(AVG(CASE WHEN score_home > score_away THEN 1.0 ELSE 0.0 END), 0.46) - 0.46 AS home_bias
        FROM (
            SELECT m.score_home, m.score_away
            FROM match_officials mo
            JOIN matches m ON m.id = mo.match_id
            WHERE mo.name = %s
              AND mo.role_id = 1
              AND m.sport = 'football'
              AND m.status = 'FT'
              AND m.score_home IS NOT NULL
              AND m.score_away IS NOT NULL
              AND m.mst_utc < %s
            ORDER BY m.mst_utc DESC
            LIMIT 30
        ) src
        """,
        (referee_name, before_ts),
    )
    row = cur.fetchone()
    if not row:
        return 2.6, 0.0
    return float(row[0] or 2.6), float(row[1] or 0.0)


def _compute_team_squad_profile(
    cur: psycopg2.extensions.cursor,
    team_id: str,
    before_ts: int,
) -> tuple[float, float]:
    if not team_id:
        return 0.5, 0.0

    cur.execute(
        """
        WITH recent_matches AS (
            SELECT m.id
            FROM matches m
            WHERE (m.home_team_id = %s OR m.away_team_id = %s)
              AND m.sport = 'football'
              AND m.status = 'FT'
              AND m.mst_utc < %s
            ORDER BY m.mst_utc DESC
            LIMIT 8
        ),
        player_base AS (
            SELECT
                mpp.player_id,
                COUNT(*)::float AS appearances,
                COUNT(*) FILTER (WHERE mpp.is_starting = true)::float AS starts
            FROM match_player_participation mpp
            JOIN recent_matches rm ON rm.id = mpp.match_id
            WHERE mpp.team_id = %s
            GROUP BY mpp.player_id
        ),
        player_goals AS (
            SELECT
                mpe.player_id,
                COUNT(*) FILTER (
                    WHERE mpe.event_type = 'goal'
                      AND COALESCE(mpe.event_subtype, '') NOT ILIKE '%%penaltı kaçırma%%'
                )::float AS goals,
                0.0::float AS assists
            FROM match_player_events mpe
            JOIN recent_matches rm ON rm.id = mpe.match_id
            WHERE mpe.team_id = %s
            GROUP BY mpe.player_id
            UNION ALL
            SELECT
                mpe.assist_player_id AS player_id,
                0.0::float AS goals,
                COUNT(*) FILTER (
                    WHERE mpe.event_type = 'goal'
                      AND mpe.assist_player_id IS NOT NULL
                )::float AS assists
            FROM match_player_events mpe
            JOIN recent_matches rm ON rm.id = mpe.match_id
            WHERE mpe.team_id = %s
              AND mpe.assist_player_id IS NOT NULL
            GROUP BY mpe.assist_player_id
        ),
        player_events AS (
            SELECT
                player_id,
                SUM(goals) AS goals,
                SUM(assists) AS assists
            FROM player_goals
            GROUP BY player_id
        ),
        player_scores AS (
            SELECT
                pb.player_id,
                (pb.starts * 1.5)
                + ((pb.appearances - pb.starts) * 0.5)
                + (COALESCE(pe.goals, 0.0) * 2.5)
                + (COALESCE(pe.assists, 0.0) * 1.5) AS score
            FROM player_base pb
            LEFT JOIN player_events pe ON pe.player_id = pb.player_id
        )
        SELECT
            COALESCE(AVG(top_players.score), 0.0) AS avg_top_score,
            COALESCE(COUNT(*) FILTER (WHERE top_players.score >= 6.0), 0) AS key_players
        FROM (
            SELECT score
            FROM player_scores
            ORDER BY score DESC
            LIMIT 11
        ) top_players
        """,
        (team_id, team_id, before_ts, team_id, team_id, team_id),
    )
    row = cur.fetchone()
    if not row:
        return 0.5, 0.0

    avg_top_score = float(row[0] or 0.0)
    return min(max(avg_top_score / 10.0, 0.0), 1.0), float(row[1] or 0.0)


def _enrich_pre_match_context(
    cur: psycopg2.extensions.cursor,
    df: pd.DataFrame,
) -> pd.DataFrame:
    league_avg_goals: list[float] = []
    referee_avg_goals: list[float] = []
    referee_home_bias: list[float] = []
    home_squad_strength: list[float] = []
    away_squad_strength: list[float] = []
    home_key_players: list[float] = []
    away_key_players: list[float] = []

    print("Pre-match context enrich ediliyor...")
    started_at = time.time()

    for row in df.itertuples(index=False):
        before_ts = int(getattr(row, "utc") or 0)
        league_id = str(getattr(row, "league_id") or "")
        ref_name_raw: Any = getattr(row, "referee_name", None)
        referee_name = str(ref_name_raw).strip() if ref_name_raw else None

        lg_avg = _compute_league_avg_goals(cur, league_id, before_ts)
        ref_avg, ref_bias = _compute_referee_profile(cur, referee_name, before_ts)
        h_sq, h_key = _compute_team_squad_profile(cur, str(getattr(row, "h_id")), before_ts)
        a_sq, a_key = _compute_team_squad_profile(cur, str(getattr(row, "a_id")), before_ts)

        league_avg_goals.append(lg_avg)
        referee_avg_goals.append(ref_avg)
        referee_home_bias.append(ref_bias)
        home_squad_strength.append(h_sq)
        away_squad_strength.append(a_sq)
        home_key_players.append(h_key)
        away_key_players.append(a_key)

    enriched = df.copy()
    enriched["league_avg_goals"] = league_avg_goals
    enriched["referee_avg_goals"] = referee_avg_goals
    enriched["referee_home_bias"] = referee_home_bias
    enriched["home_squad_strength"] = home_squad_strength
    enriched["away_squad_strength"] = away_squad_strength
    enriched["home_key_players"] = home_key_players
    enriched["away_key_players"] = away_key_players

    print(f"Pre-match context tamam ({time.time() - started_at:.1f}s)")
    return enriched


def _prepare_features(df: pd.DataFrame) -> pd.DataFrame:
    numeric_columns = [
        "sh",
        "sa",
        "utc",
        "league_avg_goals",
        "referee_avg_goals",
        "referee_home_bias",
        "home_squad_strength",
        "away_squad_strength",
        "home_key_players",
        "away_key_players",
        "h_elo",
        "a_elo",
        "h_home_goals",
        "a_away_goals",
        "h_rest",
        "a_rest",
        "oh",
        "od",
        "oa",
        "h2h_h_wr",
        "h_form_pts",
        "a_form_pts",
    ]
    for column in numeric_columns:
        df[column] = pd.to_numeric(df[column], errors="coerce")

    df = df.fillna(df.median(numeric_only=True))
    df = df[(df["oh"] > 1.0) & (df["od"] > 1.0) & (df["oa"] > 1.0)].copy()
    if df.empty:
        raise RuntimeError("No valid rows remained after odds filtering.")

    margin = (1.0 / df["oh"]) + (1.0 / df["od"]) + (1.0 / df["oa"])
    df["imp_h"] = (1.0 / df["oh"]) / margin
    df["imp_d"] = (1.0 / df["od"]) / margin
    df["imp_a"] = (1.0 / df["oa"]) / margin

    feature_rows = df.apply(
        lambda row: build_vqwen_feature_row(
            VqwenFeatureInput(
                home_elo=float(row["h_elo"]),
                away_elo=float(row["a_elo"]),
                home_avg_goals_scored=float(row["h_home_goals"]),
                away_avg_goals_scored=float(row["a_away_goals"]),
                home_avg_goals_conceded=float(row["a_away_goals"]),
                away_avg_goals_conceded=float(row["h_home_goals"]),
                home_avg_shots_on_target=4.0,
                away_avg_shots_on_target=4.0,
                home_avg_possession=50.0,
                away_avg_possession=50.0,
                home_rest_days=float(row["h_rest"]),
                away_rest_days=float(row["a_rest"]),
                implied_prob_home=float(row["imp_h"]),
                implied_prob_draw=float(row["imp_d"]),
                implied_prob_away=float(row["imp_a"]),
                # Historical training must not leak actual match lineups.
                # Runtime also often defaults to 1.0 when pre-match lineup data
                # is unavailable, so training should mirror that behavior.
                home_lineup_availability=1.0,
                away_lineup_availability=1.0,
                h2h_home_win_rate=float(row["h2h_h_wr"]),
                home_form_score=float(row["h_form_pts"]),
                away_form_score=float(row["a_form_pts"]),
                league_avg_goals=float(row["league_avg_goals"]),
                referee_avg_goals=float(row["referee_avg_goals"]),
                referee_home_bias=float(row["referee_home_bias"]),
                home_squad_strength=float(row["home_squad_strength"]),
                away_squad_strength=float(row["away_squad_strength"]),
                home_key_players=float(row["home_key_players"]),
                away_key_players=float(row["away_key_players"]),
            ),
        ),
        axis=1,
        result_type="expand",
    )
    for column in FEATURE_COLUMNS:
        df[column] = feature_rows[column]

    df["t_ms"] = df.apply(
        lambda row: 0 if row["sh"] > row["sa"] else (2 if row["sh"] < row["sa"] else 1),
        axis=1,
    )
    df["t_ou"] = ((df["sh"] + df["sa"]) > 2.5).astype(int)
    df["t_btts"] = ((df["sh"] > 0) & (df["sa"] > 0)).astype(int)

    return df


def _temporal_split(df: pd.DataFrame, validation_ratio: float = 0.15) -> tuple[pd.DataFrame, pd.DataFrame]:
    if df.empty:
        raise RuntimeError("Cannot split an empty dataframe.")

    ordered = df.sort_values("utc").reset_index(drop=True)
    split_index = max(int(len(ordered) * (1.0 - validation_ratio)), 1)
    split_index = min(split_index, len(ordered) - 1)
    return ordered.iloc[:split_index].copy(), ordered.iloc[split_index:].copy()


def _save_metadata(df: pd.DataFrame, league_ids: list[str]) -> None:
    metadata = {
        "trained_at": time.strftime("%Y-%m-%d %H:%M:%S"),
        "contract_version": "vqwen.shared.v1",
        "league_count": len(league_ids),
        "league_ids": league_ids,
        "sample_count": int(len(df)),
        "feature_columns": FEATURE_COLUMNS,
        "target_distribution": {
            "ms_home": int((df["t_ms"] == 0).sum()),
            "ms_draw": int((df["t_ms"] == 1).sum()),
            "ms_away": int((df["t_ms"] == 2).sum()),
            "ou25_over": int(df["t_ou"].sum()),
            "ou25_under": int(len(df) - df["t_ou"].sum()),
            "btts_yes": int(df["t_btts"].sum()),
            "btts_no": int(len(df) - df["t_btts"].sum()),
        },
    }
    MODELS_DIR.mkdir(parents=True, exist_ok=True)
    (MODELS_DIR / "vqwen_training_meta.json").write_text(
        json.dumps(metadata, indent=2),
        encoding="utf-8",
    )


def train_vqwen_v3() -> None:
    print("VQWEN v3 MODEL EGITIMI (TOP LEAGUES)")
    print("=" * 60)

    league_ids = load_top_league_ids()
    print(f"League filter aktif: {len(league_ids)} lig")

    dsn = get_clean_dsn()
    conn = psycopg2.connect(dsn)
    cur = conn.cursor()

    try:
        df = _fetch_dataframe(cur, league_ids)
        df = _enrich_pre_match_context(cur, df)
        df = _prepare_features(df)
        print(f"Temiz egitim orneklemi: {len(df)} mac")

        train_df, valid_df = _temporal_split(df)
        X_train = train_df[FEATURE_COLUMNS]
        X_valid = valid_df[FEATURE_COLUMNS]
        y_train = train_df["t_ms"]
        y_valid = valid_df["t_ms"]

        print(
            "Temporal split:"
            f" train={len(train_df)}"
            f" valid={len(valid_df)}"
            f" train_end_utc={int(train_df['utc'].max())}"
            f" valid_start_utc={int(valid_df['utc'].min())}"
        )

        print("MS modeli egitiliyor...")
        model_ms = lgb.train(
            {
                "objective": "multiclass",
                "num_class": 3,
                "metric": "multi_logloss",
                "verbose": -1,
                "num_leaves": 63,
                "learning_rate": 0.03,
                "feature_fraction": 0.85,
                "bagging_fraction": 0.85,
                "bagging_freq": 1,
            },
            lgb.Dataset(X_train, y_train),
            num_boost_round=1000,
            valid_sets=[lgb.Dataset(X_valid, y_valid)],
            callbacks=[lgb.early_stopping(50)],
        )

        print("OU2.5 modeli egitiliyor...")
        model_ou25 = lgb.train(
            {
                "objective": "binary",
                "metric": "binary_logloss",
                "verbose": -1,
                "learning_rate": 0.03,
                "num_leaves": 31,
            },
            lgb.Dataset(train_df[FEATURE_COLUMNS], train_df["t_ou"]),
            num_boost_round=1000,
            valid_sets=[lgb.Dataset(valid_df[FEATURE_COLUMNS], valid_df["t_ou"])],
            callbacks=[lgb.early_stopping(50)],
        )

        print("BTTS modeli egitiliyor...")
        model_btts = lgb.train(
            {
                "objective": "binary",
                "metric": "binary_logloss",
                "verbose": -1,
                "learning_rate": 0.03,
                "num_leaves": 31,
            },
            lgb.Dataset(train_df[FEATURE_COLUMNS], train_df["t_btts"]),
            num_boost_round=1000,
            valid_sets=[lgb.Dataset(valid_df[FEATURE_COLUMNS], valid_df["t_btts"])],
            callbacks=[lgb.early_stopping(50)],
        )

        MODELS_DIR.mkdir(parents=True, exist_ok=True)
        artifacts = {
            "vqwen_ms.pkl": model_ms,
            "vqwen_ou25.pkl": model_ou25,
            "vqwen_btts.pkl": model_btts,
        }
        for filename, model in artifacts.items():
            with (MODELS_DIR / filename).open("wb") as handle:
                pickle.dump(model, handle)
            print(f"Kaydedildi: {filename}")

        _save_metadata(df, league_ids)
        print("Kaydedildi: vqwen_training_meta.json")
        print("VQWEN v3 top league egitimi tamamlandi.")
    finally:
        cur.close()
        conn.close()


if __name__ == "__main__":
    train_vqwen_v3()