"""Regenerates out/results.json and out/counterexample.csv from data/ (deterministic)."""
import json, os
import numpy as np, pandas as pd
from scipy import stats

ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
D, O = os.path.join(ROOT, "data"), os.path.join(ROOT, "out")
props = pd.read_csv(os.path.join(D, "propositions.csv"))
design = pd.read_csv(os.path.join(D, "design.csv"))
issues = []
if set(props["id"]) != {"A", "B"} or len(props) != 2:
    issues.append({"issue": "propositions.csv does not contain exactly ids A and B", "handling": "used ids present"})
dv = dict(zip(design["parameter"], design["value"]))
seed, n = int(dv["seed"]), int(dv["n"])

# Counterexample to A: X ~ N(0,1), S independent Rademacher (+/-1 w.p. 1/2), Y = S*X.
# Y ~ N(0,1) by symmetry of N(0,1); X+Y = (1+S)X equals 0 w.p. 1/2 and 2X otherwise.
rng = np.random.default_rng(seed)
x = rng.standard_normal(n)
s = rng.choice(np.array([-1.0, 1.0]), size=n)
y = s * x
pd.DataFrame({"x": x, "y": y}).to_csv(os.path.join(O, "counterexample.csv"), index=False)

z = x + y
ks = float(stats.kstest(z, "norm", args=(z.mean(), z.std(ddof=1))).statistic)
# auxiliary checks (reported in report, not required keys)
aux = {
    "ks_x_vs_N01": float(stats.kstest(x, "norm").statistic),
    "ks_y_vs_N01": float(stats.kstest(y, "norm").statistic),
    "frac_sum_exactly_zero": float(np.mean(z == 0.0)),
    "corr_xy": float(np.corrcoef(x, y)[0, 1]),
}
res = {
    "task_id": "F5-conf-03",
    "statement_true": False,
    "counterexample_provided": True,
    "counterexample_values": {
        "construction": "X ~ N(0,1); S independent of X with P(S=1)=P(S=-1)=1/2; Y = S*X. "
                        "Then Y ~ N(0,1) and X+Y = (1+S)X has an atom of mass 1/2 at 0 (and equals 2X otherwise), so it is not normal.",
        "n": n, "seed": seed,
        "mean_x": float(x.mean()), "sd_x": float(x.std(ddof=1)),
        "mean_y": float(y.mean()), "sd_y": float(y.std(ddof=1)),
        "mean_sum": float(z.mean()), "sd_sum": float(z.std(ddof=1)),
        "ks_sum_vs_normal": ks,
    },
    "statement_b_true": True,
    "feasibility": "complete",
    "feasibility_reason": None,
    "data_issues": issues,
    "n_input_rows": {"propositions.csv": int(len(props)), "design.csv": int(len(design))},
    "n_analysed": n,
    "random_seed": seed,
    "auxiliary_checks": aux,
}
with open(os.path.join(O, "results.json"), "w") as f:
    json.dump(res, f, indent=2)
print(json.dumps(res, indent=2))