{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1344ef50",
   "metadata": {},
   "source": [
    "# SI Figure S5: per-solvent PCM benefit vs bulk dielectric constant and polarizability\n",
    "\n",
    "Per-solvent PCM benefit (% test-RMSE reduction) vs bulk dielectric constant and polarizability, for\n",
    "the MagNET-Zero reference method per nucleus (WP04 ¹H, wB97X-D ¹³C). Panels A (¹H) and B (¹³C)\n",
    "show all solvents; C repeats ¹H excluding aromatics and trifluoroethanol."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dfffb6dc",
   "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/delta22\", \"analysis/code\", \"analysis/code/shared\"):\n",
    "    sys.path.insert(0, os.path.join(REPO, _p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "74921dd6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import delta22\n",
    "import delta22_plots\n",
    "import paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c3053b56",
   "metadata": {},
   "outputs": [],
   "source": [
    "DELTA22_HDF5 = paths.dataset_file(\"delta22\", root=REPO)\n",
    "XLSX = os.path.join(REPO, \"data\", \"delta22\", \"delta22_experimental.xlsx\")\n",
    "\n",
    "def figure_path(name):\n",
    "    os.makedirs(\"figures\", exist_ok=True)\n",
    "    return os.path.join(\"figures\", name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99b0ba9e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# the published panels use 250 seeded train/test splits\n",
    "N_SPLITS = 250"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9aa30554",
   "metadata": {},
   "outputs": [],
   "source": [
    "dft = delta22.load_query_df_dft(DELTA22_HDF5, XLSX, verbose=False)\n",
    "solutes = sorted(dft[\"solute\"].unique())\n",
    "benefit = {}\n",
    "for nucleus, label in [(\"H\", \"1H\"), (\"C\", \"13C\")]:\n",
    "    method = delta22.MAGNET_PCM_OUTPUT_METHODS[nucleus]\n",
    "    benefit[nucleus] = delta22.pcm_benefit_per_solvent(dft, method, \"pcSseg2\", \"aimnet2\",\n",
    "                                                       delta22.DESMOND_SOLVENTS, n_splits=N_SPLITS,\n",
    "                                                       solutes=solutes, nucleus=nucleus)\n",
    "    print(f\"{label} ({method}):\"); print(benefit[nucleus].round(1).to_string())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "329088d2",
   "metadata": {},
   "source": [
    "## S5A (1H, all solvents), S5B (13C, all solvents), and S5C (1H, excluding aromatics and trifluoroethanol)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2d519d66",
   "metadata": {},
   "outputs": [],
   "source": [
    "# panels A (1H) and B (13C): all solvents\n",
    "for nucleus, letter, nuc_label in [(\"H\", \"A\", \"H\"), (\"C\", \"B\", \"C\")]:\n",
    "    delta22_plots.plot_pcm_benefit_vs_properties(\n",
    "        benefit[nucleus], delta22.SOLVENT_DIELECTRIC, delta22.SOLVENT_POLARIZABILITY, nuc_label,\n",
    "        save_path=figure_path(f\"si_figure_s05{letter}_all.png\"))\n",
    "# panel C is 1H only, excluding the aromatic solvents and trifluoroethanol (matches the published SI)\n",
    "delta22_plots.plot_pcm_benefit_vs_properties(\n",
    "    benefit[\"H\"], delta22.SOLVENT_DIELECTRIC, delta22.SOLVENT_POLARIZABILITY, \"H\",\n",
    "    exclude=[\"benzene\", \"toluene\", \"chlorobenzene\", \"trifluoroethanol\"],\n",
    "    title_extra=\"Excluding Aromatic Solvents and Trifluoroethanol\",\n",
    "    save_path=figure_path(\"si_figure_s05A_no_aromatics_tfe.png\"))"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}