"""Fantabeto PWA — FastAPI backend serving ML auction models."""

import logging
import sys
from pathlib import Path

PROJECT_ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(PROJECT_ROOT))

import numpy as np
import pandas as pd
from fastapi import FastAPI, Query
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles
from pydantic import BaseModel

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger("pwa-api")

app = FastAPI(title="Fantabeto PWA API", version="1.0")
app.add_middleware(CORSMiddleware, allow_origins=["*"], allow_methods=["*"], allow_headers=["*"])

# ── Global state ────────────────────────────────────────────────────

_player_pool: pd.DataFrame = None
_model_results: dict = {}
_auction_state: dict = {"roster": [], "budget_spent": 0}


def _init():
    global _player_pool, _model_results
    if _player_pool is not None:
        return

    logger.info("Loading data...")
    projections = pd.read_excel(PROJECT_ROOT / "data" / "player_projections_26_27.xlsx")
    stats = pd.read_excel(PROJECT_ROOT / "mid_outputs" / "players_stats.xlsx")

    p = projections.copy()
    s = stats.copy()
    p["name_lower"] = p["player"].str.lower().str.strip()
    s["name_lower"] = s["name"].str.lower().str.strip()

    stat_features = ["minutes", "xg_per90", "xa_per90", "sca_per90", "gca_per90",
                      "fouls", "fouled", "cards_yellow", "cards_red",
                      "progressive_passes", "progressive_carries", "tackles",
                      "interceptions", "clearances", "passes_into_final_third"]
    available = [c for c in stat_features if c in s.columns]
    merged = p.merge(s[["name_lower"] + available], on="name_lower", how="left")

    for c in available + ["fv_std", "qi", "goals", "assists", "cards_yellow",
                            "cards_red", "fouls", "fouled", "xg_per90", "xa_per90",
                            "sca_per90", "gca_per90", "minutes", "starter_pct",
                            "games"]:
        if c in merged.columns:
            merged[c] = merged[c].fillna(0)

    merged["rest_days"] = np.random.RandomState(42).uniform(2, 10, len(merged))
    merged["fatigue_rolling_3"] = (merged["minutes"] * 0.33).clip(0, 90)
    merged["goals_season"] = merged["goals"]
    merged["assists_season"] = merged["assists"]
    minutes = merged["minutes"].clip(lower=1)
    merged["yellow_per_game"] = (merged["cards_yellow"] / (minutes / 90)).clip(0, 1)
    merged["red_per_game"] = (merged["cards_red"] / (minutes / 90)).clip(0, 0.5)
    merged["fouls_p90"] = merged["fouls"] / (minutes / 90)
    merged["projected_points"] = merged["fv_proj"].fillna(6.0)
    merged["fv_std"] = merged["fv_std"].fillna(0.5)
    fvm_val = merged.get("fvm", merged["qi"] * 10).fillna(10)
    merged["market_value"] = np.maximum(3, (fvm_val * 0.4 + (merged["fv_proj"] - 5.5) * 20)).astype(int)
    merged["name"] = merged["player"]
    merged["starter_pct"] = merged["starter_pct"].fillna(0.7)
    merged["games_played"] = merged["games"].fillna(20)

    _player_pool = merged
    logger.info(f"Loaded {len(_player_pool)} players")

    # Train key models
    logger.info("Training ML models...")
    feature_cols = ["projected_points", "fv_std", "games_played", "starter_pct",
                     "goals_season", "assists_season", "yellow_per_game", "red_per_game",
                     "xg_per90", "xa_per90", "sca_per90", "gca_per90", "fouls_p90",
                     "minutes", "rest_days", "fatigue_rolling_3"]
    feature_cols = [c for c in feature_cols if c in merged.columns]
    X_full = merged[feature_cols].fillna(0)
    y_full = merged["projected_points"].values

    from src.models.quantile_model import QuantileEnsemble
    qe = QuantileEnsemble(quantiles=(0.10, 0.50, 0.90), n_estimators=60)
    qe.fit(X_full, pd.Series(y_full))
    _model_results["quantile"] = qe

    from src.models.survival_model import MinutesSurvivalModel
    surv_features = ["minutes", "games_played", "rest_days", "fatigue_rolling_3", "starter_pct"]
    surv_features = [c for c in surv_features if c in merged.columns]
    surv_df = merged[surv_features].fillna(0)
    durations = np.clip(merged["minutes"].fillna(60).values, 1, 90)
    events = (merged["starter_pct"].fillna(0.5).values > 0.5).astype(int)
    ms = MinutesSurvivalModel(force_scipy=True)
    ms.fit(surv_df, durations, events)
    _model_results["survival"] = ms

    from src.optimization.bandit_auction import BanditAuctionSolver
    from src.optimization.auction_solver import AuctionConfig
    config = AuctionConfig(total_budget=500, n_gk=3, n_def=8, n_mid=8, n_fwd=6)
    _model_results["bandit"] = BanditAuctionSolver(config=config)

    from src.optimization.opponent_bidding_model import OpponentBidModel
    _model_results["opponent"] = OpponentBidModel()

    from src.optimization.budget_optimizer import BudgetOptimizer
    _model_results["budget_opt"] = BudgetOptimizer(total_budget=500)

    logger.info(f"All models ready")


@app.on_event("startup")
def startup():
    _init()


# ── API Endpoints ───────────────────────────────────────────────────


@app.get("/api/players")
def get_players(search: str = "", role: str = "", sort: str = "projected_points", limit: int = 50):
    """List players with optional search/filter/sort."""
    df = _player_pool.copy()
    if search:
        mask = df["name"].str.lower().str.contains(search.lower(), na=False)
        df = df[mask]
    if role and role in ("P", "D", "C", "A"):
        df = df[df["role"] == role]
    df = df.nlargest(min(limit, len(df)), sort)
    players = df[["name", "role", "team", "projected_points", "fv_std",
                    "market_value", "starter_pct", "games_played"]].to_dict(orient="records")
    return {"players": players, "total": len(df)}


@app.get("/api/player/{name}")
def get_player_detail(name: str):
    """Full detail + ML predictions for one player."""
    row = _player_pool[_player_pool["name"] == name]
    if row.empty:
        return {"error": "Player not found"}

    player = row.iloc[0]
    result = {
        "name": str(player["name"]), "role": str(player["role"]),
        "team": str(player["team"]), "projected_points": float(player["projected_points"]),
        "fv_std": float(player["fv_std"]), "market_value": int(player["market_value"]),
        "starter_pct": float(player["starter_pct"]),
        "games_played": int(player["games_played"]),
        "goals_season": int(player["goals_season"]),
        "assists_season": int(player["assists_season"]),
    }

    # Quantile predictions
    try:
        feature_cols = [c for c in _model_results["quantile"].feature_names if c in row.index]
        X_row = pd.DataFrame([row[feature_cols].fillna(0).values], columns=feature_cols)
        preds = _model_results["quantile"].predict(X_row)
        result["p10"] = round(float(preds["P10"][0]), 2)
        result["p50"] = round(float(preds["P50"][0]), 2)
        result["p90"] = round(float(preds["P90"][0]), 2)
        risk = _model_results["quantile"].predict_downside_risk(X_row, 5.5)
        result["downside_risk"] = round(float(risk[0]), 3)
    except Exception:
        result["p10"] = round(result["projected_points"] * 0.85, 2)
        result["p50"] = result["projected_points"]
        result["p90"] = round(result["projected_points"] * 1.15, 2)
        result["downside_risk"] = 0.1

    # Starter probability
    try:
        surv_features = ["minutes", "games_played", "rest_days", "fatigue_rolling_3", "starter_pct"]
        surv_features = [c for c in surv_features if c in row.index]
        X_surv = pd.DataFrame([row[surv_features].fillna(0).values], columns=surv_features)
        result["starter_prob"] = round(float(_model_results["survival"].predict_starter_probability(X_surv)[0]), 3)
    except Exception:
        result["starter_prob"] = round(float(player.get("starter_pct", 0.7)), 3)

    # Bandit recommendation
    try:
        from src.optimization.auction_solver import PlayerValuation
        pv = PlayerValuation(
            name=str(player["name"]), team=str(player["team"]), role=str(player["role"]),
            projected_points=float(player["projected_points"]),
            market_value=float(player["market_value"]),
            ceiling_price=max(int(float(player["market_value"]) * 1.3), 5),
        )
        state = {
            "budget_remaining": 500 - _auction_state["budget_spent"],
            "total_budget": 500,
            "slots_remaining": {"P": 3 - sum(1 for r in _auction_state["roster"] if r["role"] == "P"),
                                "D": 8 - sum(1 for r in _auction_state["roster"] if r["role"] == "D"),
                                "C": 8 - sum(1 for r in _auction_state["roster"] if r["role"] == "C"),
                                "A": 6 - sum(1 for r in _auction_state["roster"] if r["role"] == "A")},
            "role_quotas": {"P": 3, "D": 8, "C": 8, "A": 6},
            "slot_quotas": {"P": 3, "D": 8, "C": 8, "A": 6},
            "round_number": len(_auction_state["roster"]) + 1,
            "total_rounds": 25,
            "opponent_budgets": [400, 350, 420],
            "players_remaining_in_role": {"P": 15, "D": 50, "C": 50, "A": 30},
            "player_pool": [pv],
        }
        arm_idx, bid = _model_results["bandit"].select_bid(pv, state)
        mkt = int(player["market_value"])
        # Cold start: if bandit hasn't learned, use sensible defaults
        if bid < mkt * 0.3:
            bid = int(mkt * 0.85)
        result["recommended_bid"] = int(bid)
        result["max_bid"] = int(mkt * 1.3)
    except Exception:
        result["recommended_bid"] = int(player["market_value"] * 0.85)
        result["max_bid"] = int(player["market_value"] * 1.3)

    # Opponent bid estimate
    try:
        bid_row = pd.DataFrame([{"player_name": str(player["name"]),
                                  "player_role": str(player["role"]),
                                  "player_projected_points": float(player["projected_points"])}])
        opp_state = {
            "budget_remaining": 400, "total_budget": 500, "initial_budget": 500,
            "slots_total": {"P": 3, "D": 8, "C": 8, "A": 6},
            "slots_filled": {"P": 1, "D": 2, "C": 2, "A": 2},
            "slots_remaining": {"P": 2, "D": 6, "C": 6, "A": 4},
            "role_quotas": {"P": 3, "D": 8, "C": 8, "A": 6},
            "aggression_factor": 1.0,
        }
        opp_bid = float(_model_results["opponent"].predict_opponent_bids(bid_row, opp_state).values[0])
        # Calibrate: opponent heuristic underestimates, use market value as floor
        if opp_bid < mkt * 0.5:
            opp_bid = int(mkt * 0.75)
        result["opponent_bid"] = int(opp_bid)
    except Exception:
        result["opponent_bid"] = int(player["market_value"] * 0.75)

    return result


@app.get("/api/roster")
def get_roster():
    """Current auction roster."""
    total_fv = round(sum(r.get("projected_points", 0) for r in _auction_state["roster"]), 1)
    return {
        "roster": _auction_state["roster"],
        "budget_spent": _auction_state["budget_spent"],
        "budget_remaining": 500 - _auction_state["budget_spent"],
        "total_fv": total_fv,
        "role_counts": {
            r: sum(1 for p in _auction_state["roster"] if p["role"] == r)
            for r in ["P", "D", "C", "A"]
        },
        "role_quotas": {"P": 3, "D": 8, "C": 8, "A": 6},
    }


class AddPlayerRequest(BaseModel):
    name: str
    price: int


@app.post("/api/roster/add")
def add_to_roster(req: AddPlayerRequest):
    """Add a player to the auction roster."""
    row = _player_pool[_player_pool["name"] == req.name]
    if row.empty:
        return {"error": "Player not found"}

    player = row.iloc[0]
    role = str(player["role"])
    role_counts = {r: sum(1 for p in _auction_state["roster"] if p["role"] == r)
                   for r in ["P", "D", "C", "A"]}
    quotas = {"P": 3, "D": 8, "C": 8, "A": 6}

    if role_counts[role] >= quotas[role]:
        return {"error": f"Role {role} quota full"}

    if _auction_state["budget_spent"] + req.price > 500:
        return {"error": "Budget exceeded"}

    entry = {
        "name": str(player["name"]), "role": role,
        "team": str(player["team"]),
        "projected_points": round(float(player["projected_points"]), 2),
        "price": req.price, "market_value": int(player["market_value"]),
    }
    _auction_state["roster"].append(entry)
    _auction_state["budget_spent"] += req.price

    return {"ok": True, "roster": get_roster()}


class RemovePlayerRequest(BaseModel):
    name: str


@app.post("/api/roster/remove")
def remove_from_roster(req: RemovePlayerRequest):
    """Remove a player from the roster."""
    for p in _auction_state["roster"]:
        if p["name"] == req.name:
            _auction_state["budget_spent"] -= p["price"]
            _auction_state["roster"].remove(p)
            return {"ok": True, "roster": get_roster()}
    return {"error": "Player not in roster"}


@app.post("/api/roster/reset")
def reset_roster():
    """Reset the auction roster."""
    _auction_state["roster"] = []
    _auction_state["budget_spent"] = 0
    return {"ok": True}


@app.get("/api/stats")
def get_stats():
    """League-wide statistics."""
    return {
        "total_players": len(_player_pool),
        "price_range": [int(_player_pool["market_value"].min()), int(_player_pool["market_value"].max())],
        "median_price": int(_player_pool["market_value"].median()),
        "elite_count": int((_player_pool["market_value"] >= 100).sum()),
        "role_counts": {r: int((_player_pool["role"] == r).sum()) for r in ["P", "D", "C", "A"]},
    }


# ── Static files ────────────────────────────────────────────────────

app.mount("/", StaticFiles(directory=str(PROJECT_ROOT / "pwa" / "static"), html=True), name="static")