"""Single entry point for the timing study.  Regenerates every table, number and figure.

    python3 code/run_all.py            (about 5 minutes, single-threaded, peak memory about 2 GB)

Steps
  0. write data/events.csv (hand-compiled, cited table of dated events)
  1. download the Moody et al. (2024) time-tree archive from Zenodo (227 MB, cached in
     fermi_raw/timing/) and extract LUCA node ages -> data/moody_node_ages.csv
  2. analyses 1-5 -> data/*.csv and data/results.json
  3. figures -> figures/*.png
  4. print the key numbers (code/summary.py)
"""
from __future__ import annotations

import json
import os
import sys
import time

import numpy as np
import pandas as pd

HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE)

import config as cfg  # noqa: E402

np.seterr(all="ignore")


def jsonable(o):
    if isinstance(o, dict):
        return {str(k): jsonable(v) for k, v in o.items()}
    if isinstance(o, (list, tuple)):
        return [jsonable(v) for v in o]
    if isinstance(o, np.ndarray):
        return jsonable(o.tolist())
    if isinstance(o, (np.floating, float)):
        return None if not np.isfinite(o) else float(o)
    if isinstance(o, (np.integer,)):
        return int(o)
    if isinstance(o, (np.bool_,)):
        return bool(o)
    return o


def main():
    t_start = time.time()
    import events_table
    import fetch_moody
    import a1_kipping
    import a2_hardsteps
    import a3_snyder_beattie
    import a4_models
    import a5_fbio
    import figures

    def stamp(msg):
        print(f"[{time.time() - t_start:6.1f} s] {msg}", flush=True)

    n = events_table.write_events_csv(os.path.join(cfg.DATA, "events.csv"))
    stamp(f"events table: {n} rows")
    nm = fetch_moody.main(os.path.join(cfg.DATA, "moody_node_ages.csv"))
    stamp(f"Moody et al. repository: {nm} node-age rows extracted" if nm else "Moody table: using cached copy")

    results = {"seed": cfg.SEED}
    # each analysis gets its own generator so that they can be rerun independently
    results["a1_kipping"] = a1_kipping.run(np.random.default_rng([cfg.SEED, 1]))
    stamp("analysis 1 (Kipping reproduction, plateau theorem, LUCA variants) done")
    results["a2_hardsteps"] = a2_hardsteps.run(np.random.default_rng([cfg.SEED, 2]))
    stamp("analysis 2 (hard steps) done")
    results["a3_snyder_beattie"] = a3_snyder_beattie.run(np.random.default_rng([cfg.SEED, 3]))
    stamp("analysis 3 (Snyder-Beattie et al. reproduction) done")
    results["a4_models"] = a4_models.run(np.random.default_rng([cfg.SEED, 4]))
    stamp("analysis 4 (hard steps vs pacing) done")
    out5, samples, curves = a5_fbio.run(np.random.default_rng([cfg.SEED, 5]))
    results["a5_fbio"] = out5
    stamp("analysis 5 (f_bio) done")

    with open(os.path.join(cfg.DATA, "results.json"), "w") as f:
        json.dump(jsonable(results), f, indent=1)

    lam, tc = a1_kipping.theorem_curves()
    moody_tab = pd.read_csv(os.path.join(cfg.DATA, "a1_moody_luca_bf.csv"))
    figs = [figures.fig1_timeline(),
            figures.fig2_abiogenesis(lam, tc, moody_tab, results["a1_kipping"]["moody"]),
            figures.fig3_hardsteps(pd.read_csv(os.path.join(cfg.DATA, "a2_n_likelihoods.csv")),
                                   pd.read_csv(os.path.join(cfg.DATA, "a2_goodness_of_fit.csv"))),
            figures.fig4_snyder_beattie(pd.read_csv(os.path.join(cfg.DATA, "a3_table2_reproduction.csv"))),
            figures.fig5_fbio(samples, curves)]
    stamp("figures: " + ", ".join(os.path.basename(p) for p in figs))
    print("results written to", os.path.join(cfg.DATA, "results.json"))
    import summary
    summary.main()


if __name__ == "__main__":
    main()