"""Null tests: is the pre-2025 +0.027 uplift distinguishable from 'any zero-mean low-corr
noise asset dampens a Sharpe-1.3 portfolio at w=0.25'? And bootstrap CI on the uplift."""
from __future__ import annotations
import importlib.util, sys
from pathlib import Path
import numpy as np
import pandas as pd

HERE = Path(__file__).resolve().parent
sys.path.insert(0, str(HERE))
sys.path.insert(0, "/opt/docker/PythagorasGoal/scripts/research/alt")
import ortholib as ol
import altlib as al
AGENTS = HERE / "agents"
rng = np.random.default_rng(42)


def _book(path):
    spec = importlib.util.spec_from_file_location(path.stem, path)
    mod = importlib.util.module_from_spec(spec); spec.loader.exec_module(mod)
    return mod.book


def _sh(s):
    r = np.asarray(pd.Series(s).dropna().values, float)
    return float(np.mean(r) / np.std(r) * np.sqrt(365.25)) if len(r) > 2 and np.std(r) > 0 else 0.0


def uplift(B, C, lo=None, hi=None, w=0.25):
    J = pd.concat({"B": B, "C": C}, axis=1, join="inner").dropna()
    if lo is not None: J = J[J.index >= pd.Timestamp(lo, tz="UTC")]
    if hi is not None: J = J[J.index < pd.Timestamp(hi, tz="UTC")]
    if len(J) < 30: return float("nan")
    return _sh((1-w)*J["B"] + w*J["C"]) - _sh(J["B"])


def main():
    B = al.tp01_baseline_daily()
    excl = ["12_rebalance_harvest"]
    rows = {}
    for p in sorted(AGENTS.glob("agent_*.py")):
        nm = p.stem.replace("agent_", "")
        if nm in excl: continue
        ev = ol.eval_book(_book(p))
        if ev["daily"].std() > 0:
            rows[nm] = ev["daily"]
    M = pd.concat(rows, axis=1, join="inner").dropna()
    basket = M.mean(axis=1)

    # ---- NULL 1: a synthetic zero-corr asset with the SAME standalone Sharpe & vol as the
    # basket. If it gives the same ~+0.03 pre-2025 uplift, the uplift is just diversification
    # math, not a specific edge.
    Jb = pd.concat({"B": B, "C": basket}, axis=1, join="inner").dropna()
    pre = Jb[Jb.index < pd.Timestamp("2025-01-01", tz="UTC")]
    bk_pre = pre["C"]
    mu, sd = bk_pre.mean(), bk_pre.std()
    print(f"Pre-2025 basket: mean {mu:.5f}/day  vol {sd:.5f}  Sharpe {_sh(bk_pre):.3f}  "
          f"corr->TP01 {pre['B'].corr(pre['C']):.3f}")
    print(f"Pre-2025 ACTUAL basket uplift (w=0.25): {uplift(B,basket,hi='2025-01-01'):+.3f}\n")

    print("NULL: 500 synthetic zero-corr assets, same daily mean & vol as pre-2025 basket,")
    print("      independent random sign each day. Pre-2025 uplift distribution:")
    null_u = []
    for _ in range(500):
        noise = pd.Series(rng.normal(mu, sd, len(pre)), index=pre.index)
        null_u.append(uplift(B, noise, hi="2025-01-01"))
    null_u = np.array(null_u)
    print(f"  null uplift: mean {null_u.mean():+.3f}  sd {null_u.std():.3f}  "
          f"5-95pct [{np.percentile(null_u,5):+.3f}, {np.percentile(null_u,95):+.3f}]")
    actual = uplift(B, basket, hi="2025-01-01")
    pctile = (null_u < actual).mean()*100
    print(f"  ACTUAL pre-2025 uplift {actual:+.3f} sits at the {pctile:.0f}th percentile of the null")
    print("  (if ~50th pct, the pre-2025 'edge' is INDISTINGUISHABLE from a positive-drift noise asset)\n")

    # ---- NULL 2: same but ZERO mean (pure diversification, no standalone return) ----
    null_u0 = []
    for _ in range(500):
        noise = pd.Series(rng.normal(0.0, sd, len(pre)), index=pre.index)
        null_u0.append(uplift(B, noise, hi="2025-01-01"))
    null_u0 = np.array(null_u0)
    print(f"  ZERO-mean noise null uplift: mean {null_u0.mean():+.3f}  "
          f"5-95pct [{np.percentile(null_u0,5):+.3f}, {np.percentile(null_u0,95):+.3f}]")
    print(f"  => pure diversification of a zero-return asset gives ~{null_u0.mean():+.3f} uplift\n")

    # ---- bootstrap CI on the FULL-sample and pre-2025 basket uplift (block bootstrap) ----
    print("Block-bootstrap (30d blocks, 1000 draws) CI on uplift:")
    for lbl, lo, hi in [("full", "2018-01-01", None), ("pre-2025", "2018-01-01", "2025-01-01"),
                        ("2025+", "2025-01-01", None)]:
        J = pd.concat({"B": B, "C": basket}, axis=1, join="inner").dropna()
        if lo: J = J[J.index >= pd.Timestamp(lo, tz="UTC")]
        if hi: J = J[J.index < pd.Timestamp(hi, tz="UTC")]
        n = len(J); bl = 30; nb = n // bl
        ups = []
        for _ in range(1000):
            starts = rng.integers(0, n - bl, nb)
            idx = np.concatenate([np.arange(s, s+bl) for s in starts])
            sub = J.iloc[idx]
            ups.append(_sh(0.75*sub["B"]+0.25*sub["C"]) - _sh(sub["B"]))
        ups = np.array(ups)
        frac_pos = (ups > 0).mean()*100
        print(f"  {lbl:9s}: median {np.median(ups):+.3f}  "
              f"5-95pct [{np.percentile(ups,5):+.3f}, {np.percentile(ups,95):+.3f}]  "
              f"P(uplift>0)={frac_pos:.0f}%")


if __name__ == "__main__":
    main()