import numpy as np
import pandas as pd

import data_manager
import universe_history as uh
from research.event_factors import breakout_after_compression_score
from research.regime_filters import build_regime_filter
from research.us_alpha_report import summarize_equity_window
from research.us_universe import build_tradable_mask


MIN_PRICE = 5.0
MIN_DOLLAR_VOLUME = 20_000_000.0
MIN_HISTORY_DAYS = 252
MIN_VALID_VOLUME_DAYS = 40
LIQUIDITY_WINDOW = 60

TREND_WINDOW = 126
RECOVERY_WINDOW = 63
HIGH_PROX_WINDOW = 126
ETF_TICKERS = ["SPY", "QQQ", "IWM", "MDY", "XLK", "XLF", "XLI", "XLV"]


def _price_rank_blend_score(close: pd.DataFrame) -> pd.DataFrame:
    """Simple price-only cross-sectional blend, shifted for next-day trading."""
    trend = close.pct_change(TREND_WINDOW, fill_method=None)
    recovery = close / close.rolling(RECOVERY_WINDOW, min_periods=RECOVERY_WINDOW).min() - 1
    high_proximity = close / close.rolling(HIGH_PROX_WINDOW, min_periods=HIGH_PROX_WINDOW).max().replace(0, np.nan)

    trend_rank = trend.rank(axis=1, pct=True, na_option="keep")
    recovery_rank = recovery.rank(axis=1, pct=True, na_option="keep")
    high_rank = high_proximity.rank(axis=1, pct=True, na_option="keep")
    return ((trend_rank + recovery_rank + high_rank) / 3.0).shift(1)


def _build_equal_weight_portfolio(
    score: pd.DataFrame,
    tradable_mask: pd.DataFrame,
    regime_filter: pd.Series,
    top_n: int,
) -> pd.DataFrame:
    """Build equal-weight top-n long-only weights from aligned scores."""
    aligned_score = score.reindex(index=tradable_mask.index, columns=tradable_mask.columns)
    eligible_score = aligned_score.where(tradable_mask)
    rank = eligible_score.rank(axis=1, ascending=False, na_option="bottom", method="first")
    selected = (rank <= top_n) & eligible_score.notna()
    selected = selected & regime_filter.reindex(tradable_mask.index, fill_value=False).to_numpy().reshape(-1, 1)

    raw = selected.astype(float)
    row_sums = raw.sum(axis=1).replace(0.0, np.nan)
    return raw.div(row_sums, axis=0).fillna(0.0)


def _equity_curve(close: pd.DataFrame, weights: pd.DataFrame) -> pd.Series:
    """Convert daily weights into a simple close-to-close equity curve."""
    returns = close.pct_change(fill_method=None).fillna(0.0)
    portfolio_returns = (returns * weights).sum(axis=1)
    return (1.0 + portfolio_returns).cumprod()


def _read_panel_csv(path: str) -> pd.DataFrame:
    return pd.read_csv(path, index_col=0, parse_dates=True).sort_index()


def load_saved_pit_market_data(data_dir: str = "data", prefix: str = "us_pit") -> dict[str, pd.DataFrame]:
    """Load saved PIT OHLCV panels from disk."""
    panels = {}
    for field in ("close", "high", "low", "volume"):
        panels[field] = _read_panel_csv(f"{data_dir}/{prefix}_{field}.csv")
    return panels


def load_saved_etf_close(data_dir: str = "data", market: str = "us_etf") -> pd.DataFrame:
    """Load saved ETF closes or populate them on demand."""
    path = f"{data_dir}/{market}.csv"
    try:
        return _read_panel_csv(path)
    except FileNotFoundError:
        original_data_dir = data_manager.DATA_DIR
        try:
            data_manager.DATA_DIR = data_dir
            return data_manager.update_market_data(market, ETF_TICKERS, ["close"])["close"]
        finally:
            data_manager.DATA_DIR = original_data_dir


def run_alpha_pipeline(
    market_data,
    etf_close,
    pit_membership=None,
    windows=(1, 2, 3, 5, 10),
    top_n=10,
) -> pd.DataFrame:
    """Run a lightweight strict US alpha pipeline and summarize trailing windows."""
    close = market_data["close"].sort_index()
    high = market_data["high"].reindex(index=close.index, columns=close.columns).sort_index()
    low = market_data["low"].reindex(index=close.index, columns=close.columns).sort_index()
    volume = market_data["volume"].reindex(index=close.index, columns=close.columns).sort_index()

    tradable_mask = build_tradable_mask(
        close=close,
        volume=volume,
        pit_membership=pit_membership,
        min_price=MIN_PRICE,
        min_dollar_volume=MIN_DOLLAR_VOLUME,
        min_history_days=MIN_HISTORY_DAYS,
        min_valid_volume_days=MIN_VALID_VOLUME_DAYS,
        liquidity_window=LIQUIDITY_WINDOW,
    )
    regime_filter = build_regime_filter(etf_close).reindex(close.index, fill_value=False)

    strategy_scores = {
        "breakout_regime": breakout_after_compression_score(close, high, low, volume),
        "rank_blend_regime": _price_rank_blend_score(close),
    }

    summary_rows = []
    for strategy_name, score in strategy_scores.items():
        weights = _build_equal_weight_portfolio(score, tradable_mask, regime_filter, top_n)
        equity = _equity_curve(close, weights)
        for window_years in windows:
            summary_rows.append(summarize_equity_window(equity, strategy_name, window_years))

    return pd.DataFrame(summary_rows)


def run_saved_pit_alpha_pipeline(
    data_dir: str = "data",
    windows=(1, 2, 3, 5, 10),
    top_n: int = 10,
) -> pd.DataFrame:
    """Load saved PIT OHLCV inputs and run the strict alpha pipeline."""
    market_data = load_saved_pit_market_data(data_dir=data_dir)
    etf_close = load_saved_etf_close(data_dir=data_dir)
    intervals = uh.load_sp500_history()
    pit_membership = uh.membership_mask(
        market_data["close"].index,
        intervals=intervals,
        tickers=list(market_data["close"].columns),
    )
    return run_alpha_pipeline(
        market_data=market_data,
        etf_close=etf_close,
        pit_membership=pit_membership,
        windows=windows,
        top_n=top_n,
    )


def main() -> None:
    summary = run_saved_pit_alpha_pipeline()
    print(summary.to_string(index=False))


if __name__ == "__main__":
    main()