"""Factor evaluation utilities compatible with qlib and GP outputs."""

from __future__ import annotations

import numpy as np
import pandas as pd
import scipy.stats


def cross_sectional_rank(series: pd.Series) -> pd.Series:
    return series.rank(pct=True)


def daily_rank_ic(factor_df: pd.DataFrame, label_col: str = "label", factor_col: str = "factor") -> pd.Series:
    """Compute daily Rank IC from long-format panel (date, symbol, factor, label)."""
    ics = []
    dates = []
    for dt, group in factor_df.groupby("date"):
        if group[factor_col].nunique() <= 1 or group[label_col].nunique() <= 1:
            continue
        ic, _ = scipy.stats.spearmanr(group[factor_col], group[label_col])
        if np.isfinite(ic):
            ics.append(ic)
            dates.append(dt)
    return pd.Series(ics, index=dates, name="rank_ic")


def ic_summary(ic_series: pd.Series) -> dict:
    if ic_series.empty:
        return {"ic_mean": np.nan, "ic_std": np.nan, "icir": np.nan, "pos_ratio": np.nan}
    return {
        "ic_mean": float(ic_series.mean()),
        "ic_std": float(ic_series.std()),
        "icir": float(ic_series.mean() / (ic_series.std() + 1e-8)),
        "pos_ratio": float((ic_series > 0).mean()),
        "n_days": len(ic_series),
    }


def quantile_spread(
    factor_df: pd.DataFrame,
    label_col: str = "label",
    factor_col: str = "factor",
    n_groups: int = 5,
) -> pd.DataFrame:
    """Long-short spread by factor quantile groups."""
    rows = []
    for dt, group in factor_df.groupby("date"):
        if len(group) < n_groups * 2:
            continue
        group = group.copy()
        group["group"] = pd.qcut(group[factor_col].rank(method="first"), n_groups, labels=False)
        grp_ret = group.groupby("group")[label_col].mean()
        rows.append({"date": dt, "long_short": grp_ret.iloc[-1] - grp_ret.iloc[0]})
    return pd.DataFrame(rows)


def evaluate_factor_panel(factor_df: pd.DataFrame) -> dict:
    ic = daily_rank_ic(factor_df)
    spread = quantile_spread(factor_df)
    result = ic_summary(ic)
    if not spread.empty:
        result["long_short_ann_return"] = float(spread["long_short"].mean() * 252)
        result["long_short_sharpe"] = float(
            spread["long_short"].mean() / (spread["long_short"].std() + 1e-8) * np.sqrt(252)
        )
    return result