"""XL01 — Amihud Illiquidity Premium (cross-sectional).

Score = rolling mean of |ret| / (close * volume) over W days (Amihud ratio).
Higher score = more illiquid.

We test both signs:
  - Long illiquid (higher score = long): illiquidity premium hypothesis
  - Short illiquid (higher score = short): liquidity premium, more liquid = better

Grid (<=5 calls):
  1. LS W=30, all universe
  2. LS W=30, majors
  3. LS W=30, short sign (liquidity premium, flip sign)
  4. LS W=30, H=20 (slower rebal), all universe
  5. LS W=60, all universe
"""
import sys
sys.path.insert(0, "/opt/docker/PythagorasGoal/scripts/research/xsec")
import xslib as xs
import numpy as np


def amihud_score(close, vol, ret, W=30):
    """Amihud illiquidity ratio: mean(|ret| / (close * volume)) over W days.
    Higher = more illiquid.
    Values at bar i use data <= i (causal).
    """
    # dollar volume = close * volume (notional traded)
    dollar_vol = close * vol  # (n, A)
    # |return| / dollar_vol
    abs_ret = np.abs(ret)  # (n, A)
    # avoid division by zero
    dv_safe = np.where(dollar_vol > 0, dollar_vol, np.nan)
    amihud_raw = abs_ret / dv_safe  # (n, A)
    # rolling mean (causal)
    score = xs.roll_mean(amihud_raw, W)
    return score


def score_illiquid(W=30):
    """Long illiquid (high Amihud = illiquid -> buy)."""
    def fn(P):
        return amihud_score(P.close, P.vol, P.ret, W=W)
    return fn


def score_liquid(W=30):
    """Long liquid (flip sign: low Amihud = liquid -> buy)."""
    def fn(P):
        return -amihud_score(P.close, P.vol, P.ret, W=W)
    return fn


if __name__ == "__main__":
    print("XL01 — Amihud Illiquidity Premium")
    print("="*60)

    # 1. Baseline: long illiquid, W=30, all universe
    print("\n[1] Long ILLIQUID, W=30, universe=all, H=10, k=5, LS")
    r1 = xs.study_xs("XL01-ILL-30-all", score_illiquid(30),
                     universe="all", H=10, k=5, long_short=True)
    print(xs.fmt(r1))
    print("JSON:", xs.as_json(r1))

    # 2. Long illiquid, W=30, majors only
    print("\n[2] Long ILLIQUID, W=30, universe=majors, H=10, k=5, LS")
    r2 = xs.study_xs("XL01-ILL-30-maj", score_illiquid(30),
                     universe="majors", H=10, k=5, long_short=True)
    print(xs.fmt(r2))
    print("JSON:", xs.as_json(r2))

    # 3. Long LIQUID (flip sign), W=30, all universe
    print("\n[3] Long LIQUID (flip sign), W=30, universe=all, H=10, k=5, LS")
    r3 = xs.study_xs("XL01-LIQ-30-all", score_liquid(30),
                     universe="all", H=10, k=5, long_short=True)
    print(xs.fmt(r3))
    print("JSON:", xs.as_json(r3))

    # 4. Long illiquid, W=30, H=20 (slower rebal), all
    print("\n[4] Long ILLIQUID, W=30, universe=all, H=20, k=5, LS")
    r4 = xs.study_xs("XL01-ILL-30-H20", score_illiquid(30),
                     universe="all", H=20, k=5, long_short=True)
    print(xs.fmt(r4))
    print("JSON:", xs.as_json(r4))

    # 5. Long illiquid, W=60, all universe
    print("\n[5] Long ILLIQUID, W=60, universe=all, H=10, k=5, LS")
    r5 = xs.study_xs("XL01-ILL-60-all", score_illiquid(60),
                     universe="all", H=10, k=5, long_short=True)
    print(xs.fmt(r5))
    print("JSON:", xs.as_json(r5))

    # Summary
    results = [r1, r2, r3, r4, r5]
    print("\n" + "="*60)
    print("SUMMARY — pick best by: earns_slot > holdout > distinctness")
    for r in results:
        es = r["earns_slot"]
        fsh = r["full"]["sharpe"]
        hsh = r["holdout"].get("sharpe", 0)
        cxs = r["corr_xs01"]
        v = r["marginal"]["verdict"]
        print(f"  {r['name']:30s}  FULL={fsh:+.2f}  HOLD={hsh:+.2f}  corr_xs01={cxs}  "
              f"verdict={v}  earns_slot={es}")

    # Pick best: prefer earns_slot, then hold sharpe
    best = max(results, key=lambda r: (
        r["earns_slot"],
        r["holdout"].get("sharpe", -99),
        r["full"]["sharpe"],
    ))
    print(f"\nBEST CONFIG: {best['name']}")
    print(xs.fmt(best))
    print("BEST JSON:", xs.as_json(best))