{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8a468c14",
   "metadata": {},
   "source": [
    "# Table S5: Performance statistics for predicting QCD corrections\n",
    "\n",
    "Foundation MagNET's accuracy at predicting the rovibrational (QCD) correction (stationary vs\n",
    "trajectory-averaged shielding) over qcdtraj2500 (2500 molecules), ¹H and ¹³C, all shieldings at\n",
    "PBE0/pcSseg-1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aca3e24b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os, sys\n",
    "\n",
    "# make the in-repo modules importable (not pip-installed)\n",
    "REPO = os.path.abspath(\"../..\")\n",
    "for _p in (\"data/magnet_test_predictions\", \"analysis/code\", \"analysis/code/shared\"):\n",
    "    sys.path.insert(0, os.path.join(REPO, _p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bbdcbe1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import magnet_test_predictions_reader\n",
    "import magnet_benchmark\n",
    "import paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c98484b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "PREDICTIONS = paths.dataset_file(\"magnet_test_predictions\", root=REPO)\n",
    "\n",
    "def document_path(name):\n",
    "    # table/spreadsheet outputs go under this notebook's documents/ folder, created on first save\n",
    "    os.makedirs(\"documents\", exist_ok=True)\n",
    "    return os.path.join(\"documents\", name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da4e04e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "rows = magnet_benchmark.qcd_stats_table(PREDICTIONS, magnet_test_predictions_reader)\n",
    "table_rows = []\n",
    "for r in rows:\n",
    "    nucleus = r[\"model\"].split(\"(\")[1].rstrip(\")\")   # \"1H\" / \"13C\"\n",
    "    pmed, pmae, prmse = magnet_benchmark.PUBLISHED_S5[nucleus]\n",
    "    table_rows.append(dict(model=r[\"model\"], n=int(r[\"n\"]),\n",
    "                           median_repro=round(r[\"median_ae\"], 8), median_SI=round(pmed, 8),\n",
    "                           mae_repro=round(r[\"mae\"], 8), mae_SI=round(pmae, 8),\n",
    "                           rmse_repro=round(r[\"rmse\"], 8), rmse_SI=round(prmse, 8)))\n",
    "table_s5 = pd.DataFrame(table_rows)\n",
    "print(\"Table S5 (QCD corrections):\"); display(table_s5)\n",
    "\n",
    "# write the reproduced table to this notebook's documents/ folder\n",
    "out = document_path(\"si_table_s05_qcd.xlsx\")\n",
    "with pd.ExcelWriter(out) as writer:\n",
    "    table_s5.to_excel(writer, sheet_name=\"Table S5\", index=False)\n",
    "print(\"wrote\", os.path.relpath(out, REPO))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9971c179",
   "metadata": {},
   "source": [
    "## Exact-reproduction check"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b2c792c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# every reproduced median/MAE/RMSE should match the published SI value to a few parts per million\n",
    "dev = max((table_s5[[\"median_repro\", \"median_SI\"]].diff(axis=1).iloc[:, -1].abs().max(),\n",
    "           table_s5[[\"mae_repro\", \"mae_SI\"]].diff(axis=1).iloc[:, -1].abs().max(),\n",
    "           table_s5[[\"rmse_repro\", \"rmse_SI\"]].diff(axis=1).iloc[:, -1].abs().max()))\n",
    "print(\"largest reproduced-vs-published deviation:\", dev)\n",
    "assert dev < 1e-3, \"a row diverged from the SI by more than float rounding\""
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}