"""`collapse` figure — model collapse in REAL RNN weights, arrested by grounding (↔ E1/C1).

The existence proof: a GRU trained each generation on the previous generation's own samples
loses the rare tail and drifts from truth (forward-KL climbs), and even a little grounding
arrests it. Forward-KL is the operative neural collapse metric (the RNN's smoothing keeps
spurious tail support alive, so H barely moves — see the `grounding` finding).

Four panels: (A) forward-KL trajectories (dry climbs, grounded suppressed); (B) H trajectories
(barely moves — smoothing resists H-collapse); (C) stationary forward-KL vs g; (D) tail-item
survival vs g. Reads only the committed bundle.

Usage:  python figures/plot_collapse.py [results/collapse]
"""

from __future__ import annotations

import sys
from pathlib import Path

import matplotlib.pyplot as plt
import numpy as np

sys.path.insert(0, str(Path(__file__).parent))
from _figlib import load_bundle, mean_ci, savefig  # noqa: E402

sys.path.insert(0, str(Path(__file__).parents[1] / "src"))
from inheritance.metrics import heterozygosity  # noqa: E402
from neural.config import SyntheticCfg  # noqa: E402
from neural.synthetic import make_mode_truth  # noqa: E402


def main(results_dir: str = "results/collapse") -> None:
    df, cfg = load_bundle(results_dir)
    syn = SyntheticCfg(**cfg["synthetic"])
    H_star = heterozygosity(make_mode_truth(syn).p_star)

    g_values = sorted(df["g"].unique())
    last = int(cfg["generations"] * 0.6)
    stat = df[df["generation"] >= last]
    colors = plt.cm.viridis(np.linspace(0, 0.85, len(g_values)))

    fig, axes = plt.subplots(2, 2, figsize=(13, 9))

    # Panel A: forward-KL trajectories (dry climbs, grounded suppressed).
    ax = axes[0, 0]
    for g, c in zip(g_values, colors):
        s = df[df["g"] == g].groupby("generation")["forward_kl"].mean()
        ax.plot(s.index, s.values, "-o", color=c, ms=3, label=f"g={g:g}")
    ax.set(xlabel="generation", ylabel=r"forward-KL $D(p^*\Vert\hat p)$",
           title="Collapse in weights: dry KL climbs, grounding holds it")
    ax.legend(frameon=False, fontsize=9)

    # Panel B: H trajectories (barely moves — smoothing resists H-collapse).
    ax = axes[0, 1]
    for g, c in zip(g_values, colors):
        s = df[df["g"] == g].groupby("generation")["heterozygosity"].mean()
        ax.plot(s.index, s.values, "-o", color=c, ms=3, label=f"g={g:g}")
    ax.axhline(H_star, ls=":", color="gray", lw=1, label="$H^*$")
    ax.set(xlabel="generation", ylabel="heterozygosity $H$",
           title="H barely moves (RNN smoothing resists H-collapse)")
    ax.legend(frameon=False, fontsize=9)

    # Panel C: stationary forward-KL vs g.
    ax = axes[1, 0]
    kg, Km, Kci = mean_ci(stat, "g", "forward_kl")
    ax.errorbar(kg, Km, yerr=Kci, fmt="o-", color="#1f77b4", capsize=3)
    ax.set(xlabel="grounding fraction $g$", ylabel=r"stationary forward-KL",
           title="Grounding lowers stationary divergence")

    # Panel D: tail-item survival vs g.
    ax = axes[1, 1]
    tg, Tm, Tci = mean_ci(stat, "g", "tail_frac_alive")
    ax.errorbar(tg, Tm, yerr=Tci, fmt="s-", color="#d62728", capsize=3)
    ax.set(xlabel="grounding fraction $g$", ylabel="tail items alive",
           title="Grounding lifts tail survival")

    fig.suptitle("collapse — a trained GRU collapses under dry self-training; grounding arrests it "
                 f"($K$={syn.K}, $n$={cfg['dynamics']['n']})", y=1.0, fontsize=13)
    fig.tight_layout()
    savefig(fig, results_dir, "collapse")


if __name__ == "__main__":
    main(*sys.argv[1:])