"""
validation/factor_validator.py — Validates a factor's predictive power.

Tests: IC, ICIR, Hit Ratio, Quantile Spread, Lead-Lag analysis.
Answers: "Does this factor predict future returns?"
"""

from datetime import date as Date
from typing import Optional
import sqlite3
import logging

import numpy as np
import pandas as pd

from config import config
from .metrics import (
    information_coefficient, icir, hit_ratio,
    quantile_spread, lead_lag_ic,
)

logger = logging.getLogger(__name__)


class FactorReport:
    """Structured report for a single factor's validation results."""

    def __init__(self, factor_name: str):
        self.factor_name = factor_name
        self.ic_mean: float = 0.0
        self.ic_std: float = 0.0
        self.icir: float = 0.0
        self.hit_ratio: float = 0.0
        self.quantile_spread: float = 0.0
        self.is_leading: bool = False
        self.lead_days: int = 0
        self.lead_ic: float = 0.0
        self.n_observations: int = 0
        self.conclusion: str = ""

    def summary(self) -> str:
        lines = [
            f"Factor: {self.factor_name}",
            f"  N={self.n_observations}",
            f"  IC mean={self.ic_mean:.4f}  std={self.ic_std:.4f}  ICIR={self.icir:.2f}",
            f"  Hit Ratio={self.hit_ratio:.1%}  Top-Bot Spread={self.quantile_spread:.4f}",
            f"  Best Lead: {self.lead_days}d (IC={self.lead_ic:.4f})" if self.is_leading else "  Leading: No (synchronous/lagging)",
            f"  → {self.conclusion}",
        ]
        return "\n".join(lines)


class FactorValidator:
    """
    Validates a factor's predictive power using standard quant metrics.

    For each forward horizon (1d, 3d, 5d, 7d, 14d), computes:
      - IC (Spearman rank correlation)
      - ICIR (IC stability)
      - Hit Ratio (direction accuracy)
      - Quantile spread (top vs bottom bucket)
      - Lead-lag profile

    A factor is valid if IC > 0.03 and ICIR > 0.5.
    For regime factors, also check regime_validator.
    """

    def __init__(self, db_path: Optional[str] = None):
        self.db_path = db_path or config.db_path

    def validate(self, factor_name: str, factor_scores: pd.Series,
                 forward_returns: dict[str, pd.Series]) -> FactorReport:
        """
        Args:
            factor_name: Human-readable name
            factor_scores: Series indexed by date, values 0-100
            forward_returns: Dict of horizon → Series indexed by date (e.g. "1d" → returns)
        """
        report = FactorReport(factor_name)

        # Align series to common dates
        common_idx = factor_scores.index
        for ret in forward_returns.values():
            common_idx = common_idx.intersection(ret.index)

        if len(common_idx) < 30:
            report.conclusion = "INSUFFICIENT DATA (< 30 observations)"
            return report

        f = factor_scores[common_idx]
        report.n_observations = len(common_idx)

        # Test against 7d forward returns (primary horizon)
        primary_ret = forward_returns.get("7d")
        if primary_ret is None:
            # Use first available
            primary_ret = list(forward_returns.values())[0]

        r = primary_ret[common_idx]

        # IC
        ic = information_coefficient(f, r)
        report.ic_mean = round(ic, 4)

        # Rolling IC for ICIR
        rolling_ics = []
        for i in range(30, len(f)):
            ic_i = information_coefficient(f.iloc[:i], r.iloc[:i])
            rolling_ics.append(ic_i)
        ic_series = pd.Series(rolling_ics)
        report.ic_std = round(ic_series.std(), 4)
        report.icir = round(icir(ic_series), 2)

        # Hit ratio
        report.hit_ratio = round(hit_ratio(f, r), 4)

        # Quantile spread
        report.quantile_spread = round(quantile_spread(f, r), 4)

        # Lead-lag
        lead = lead_lag_ic(f, r, max_lag=14)
        report.is_leading = lead["is_leading"]
        report.lead_days = lead["lead_days"]
        report.lead_ic = round(lead["best_ic"], 4)

        # Conclusion
        if abs(report.ic_mean) > 0.05 and report.icir > 1.0:
            report.conclusion = "STRONG: significant predictive power"
        elif abs(report.ic_mean) > 0.03 and report.icir > 0.5:
            report.conclusion = "VALID: moderate predictive power"
        elif abs(report.ic_mean) < 0.02:
            report.conclusion = "CONFIRMING: describes current state, not predictive"
        else:
            report.conclusion = "WEAK: borderline, monitor or downweight"

        return report

    def validate_from_db(self, factor_name: str,
                         score_query: str,
                         horizon_days: int = 7) -> FactorReport:
        """
        Convenience: load scores from DB and OHLCV returns, then validate.

        score_query: SQL that returns (date, score) pairs.
        """
        conn = sqlite3.connect(self.db_path)

        scores_df = pd.read_sql_query(score_query, conn)
        if scores_df.empty:
            conn.close()
            r = FactorReport(factor_name)
            r.conclusion = "NO DATA"
            return r

        scores_df["date"] = pd.to_datetime(scores_df["date"])
        scores = scores_df.set_index("date")["score"]

        # Load forward returns from OHLCV
        ohlcv = pd.read_sql_query(
            "SELECT date, close FROM ohlcv_daily WHERE symbol='BTC/USDT:USDT' ORDER BY date",
            conn
        )
        conn.close()

        ohlcv["date"] = pd.to_datetime(ohlcv["date"])
        ohlcv = ohlcv.set_index("date")
        ohlcv["ret"] = ohlcv["close"].pct_change().shift(-1)  # forward 1d

        # Build forward returns for multiple horizons
        forward = {}
        for h in [1, 3, 5, 7, 14]:
            forward[str(h) + "d"] = ohlcv["close"].pct_change(periods=h).shift(-h)

        return self.validate(factor_name, scores, forward)