"""
Gerçek Odds Bazlı Backtest
============================
Model olasılığı vs gerçek bookmaker odds karşılaştırır.
Edge varsa bahis açıldığı varsayılır, gerçek ROI hesaplanır.
"""

import os, sys, json
import numpy as np
import pandas as pd
import xgboost as xgb

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

DATA_PATH  = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'data', 'training_data.csv')
MODELS_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'models', 'v25')
REPORT_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'reports')

SKIP_COLS = {
    'match_id','home_team_id','away_team_id','league_id','mst_utc',
    'score_home','score_away','total_goals','ht_score_home','ht_score_away','ht_total_goals',
    'label_ms','label_ou05','label_ou15','label_ou25','label_ou35','label_btts',
    'label_ht_result','label_ht_ou05','label_ht_ou15','label_ht_ft',
    'label_odd_even','label_yellow_cards','label_cards_ou45','label_handicap_ms',
}

# (model_key, n_class, pred_class, label_col, odds_col, isim)
MARKETS = [
    ('ms',   3, 0, 'label_ms',   'odds_ms_h',   'MS-Ev'),
    ('ms',   3, 1, 'label_ms',   'odds_ms_d',   'MS-Ber'),
    ('ms',   3, 2, 'label_ms',   'odds_ms_a',   'MS-Dep'),
    ('ou15', 2, 1, 'label_ou15', 'odds_ou15_o', 'OU15-Ust'),
    ('ou15', 2, 0, 'label_ou15', 'odds_ou15_u', 'OU15-Alt'),
    ('ou25', 2, 1, 'label_ou25', 'odds_ou25_o', 'OU25-Ust'),
    ('ou25', 2, 0, 'label_ou25', 'odds_ou25_u', 'OU25-Alt'),
    ('ou35', 2, 1, 'label_ou35', 'odds_ou35_o', 'OU35-Ust'),
    ('ou35', 2, 0, 'label_ou35', 'odds_ou35_u', 'OU35-Alt'),
    ('btts', 2, 1, 'label_btts', 'odds_btts_y', 'BTTS-Var'),
    ('btts', 2, 0, 'label_btts', 'odds_btts_n', 'BTTS-Yok'),
]

MIN_ODDS = 1.10
MAX_ODDS = 10.0


def load_model(market):
    path = os.path.join(MODELS_DIR, f'xgb_v25_{market}.json')
    if not os.path.exists(path):
        return None
    b = xgb.Booster()
    b.load_model(path)
    return b


def main():
    print('Veri yukleniyor...')
    df = pd.read_csv(DATA_PATH, low_memory=False)
    df = df.sort_values('mst_utc')
    n_test = int(len(df) * 0.20)
    df_test = df.tail(n_test).copy().reset_index(drop=True)
    print(f'Test seti: {len(df_test):,} mac')

    feature_cols = [c for c in df.columns if c not in SKIP_COLS]
    X = df_test[feature_cols].fillna(0).values

    # Modelleri yukle
    loaded = {}
    for mkey, n_class, *_ in MARKETS:
        if mkey not in loaded:
            m = load_model(mkey)
            if m:
                loaded[mkey] = (m, n_class)
    print(f'Modeller: {list(loaded.keys())}')

    # Toplu tahmin
    raw_preds = {}
    for mkey, (model, n_class) in loaded.items():
        dmat = xgb.DMatrix(pd.DataFrame(X, columns=feature_cols))
        raw = model.predict(dmat)
        raw_preds[mkey] = raw.reshape(-1, n_class) if n_class > 2 else np.column_stack([1-raw, raw])

    # Backtest
    all_results = []
    print(f'\n{"Market":<12} {"Edge>=":>7} {"Bahis":>7} {"Hit%":>7} {"AvgOdds":>9} {"ROI/b":>8} {"Toplam":>10}')
    print('-' * 65)

    for mkey, n_class, pred_cls, label_col, odds_col, isim in MARKETS:
        if mkey not in raw_preds or label_col not in df_test.columns or odds_col not in df_test.columns:
            continue

        mp  = raw_preds[mkey][:, pred_cls]
        act = pd.to_numeric(df_test[label_col], errors='coerce').values
        bko = pd.to_numeric(df_test[odds_col],  errors='coerce').values

        valid = (~np.isnan(act) & ~np.isnan(bko) &
                 (bko >= MIN_ODDS) & (bko <= MAX_ODDS))
        mp, act, bko = mp[valid], act[valid].astype(int), bko[valid]
        implied = 1.0 / bko
        edge = mp - implied

        print(f'\n{isim}:')
        for min_e in [0.02, 0.03, 0.05, 0.07, 0.10]:
            mask = edge >= min_e
            n = mask.sum()
            if n < 20:
                continue
            won = (act[mask] == pred_cls).astype(int)
            roi = (bko[mask] - 1) * won - (1 - won)
            hit = won.mean()
            avg_roi = roi.mean()
            total = roi.sum()
            avg_odds = bko[mask].mean()
            sign = '+' if total > 0 else ''
            print(f'  edge>={min_e:+.0%}  n={n:>5,}  hit={hit:.1%}  odds={avg_odds:.2f}  roi/b={avg_roi:+.3f}  toplam={sign}{total:.1f}')
            all_results.append({'market': isim, 'min_edge': min_e, 'n': n,
                                 'hit': round(hit, 4), 'avg_odds': round(avg_odds, 3),
                                 'avg_roi': round(avg_roi, 4), 'total_roi': round(total, 2)})

    # En iyi
    winners = sorted([r for r in all_results if r['total_roi'] > 0],
                     key=lambda x: x['avg_roi'], reverse=True)
    print(f'\n{"="*65}')
    print('KAZANCLI KOMBINASYONLAR (total_roi > 0):')
    print(f'{"="*65}')
    for r in winners[:20]:
        print(f'  {r["market"]:<12} edge>={r["min_edge"]:+.0%} | n={r["n"]:>5,} | '
              f'hit={r["hit"]:.0%} | roi/b={r["avg_roi"]:+.3f} | toplam={r["total_roi"]:+.1f}')

    os.makedirs(REPORT_DIR, exist_ok=True)
    with open(os.path.join(REPORT_DIR, 'backtest_real_odds.json'), 'w') as f:
        json.dump(all_results, f, indent=2)
    print(f'\nRapor kaydedildi.')


if __name__ == '__main__':
    main()