{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9f479dac",
   "metadata": {},
   "source": [
    "# Figure 5C: implicit vs explicit correction RMSE, delta-22 vs the natural-products test set\n",
    "\n",
    "Bootstrap RMSE of implicit (PCM) vs explicit (OpenMM + vibrations) corrections, delta-22 vs the pooled complex/natural-product test set, chloroform and benzene (bars = mean, error bars = 2.5-97.5 percentile). Produces the ¹H panel (saved) and a ¹³C companion (inline only)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c4fd38cc",
   "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/applications\", \"analysis/code\", \"analysis/code/shared\"):\n",
    "    sys.path.insert(0, os.path.join(REPO, _p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aef1da3f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from applications_reader import Applications\n",
    "import applications\n",
    "import applications_plots\n",
    "import paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "178e31b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "APPLICATIONS_HDF5 = paths.dataset_file(\"applications\", root=REPO)\n",
    "XLSX = os.path.join(REPO, \"data\", \"applications\", \"applications_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": "a013c941",
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = Applications(APPLICATIONS_HDF5, XLSX)\n",
    "query_df_nn = applications.build_query_df_nn(loader)\n",
    "seed = applications.build_bootstrap_seed_coeffs(loader)\n",
    "\n",
    "# pooled \"Test Set\" bootstrap RMSE distributions (one bin over all 13 complex molecules)\n",
    "grouped = {}\n",
    "for nuc in [\"H\", \"C\"]:\n",
    "    preds = applications.apply_bootstrap_params_to_full_dataset(query_df_nn, seed[nuc], nucleus=nuc)\n",
    "    grouped[nuc] = applications.compute_grouped_rmse(preds, applications.ALL_IN_ONE_BIN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3d3cf53a",
   "metadata": {},
   "outputs": [],
   "source": [
    "applications_plots.plot_nps_benefit_barplot(\n",
    "    loader.rmse_distribution(\"H\"), grouped[\"H\"], nucleus=\"H\",\n",
    "    solvents=[[\"chloroform\"], [\"benzene\"]], np_solute_groups=applications.ALL_IN_ONE_BIN,\n",
    "    formulas=[\"stationary_plus_pcm\", \"stationary_plus_qcd + openMM\"],\n",
    "    labels=[\"Implicit Solvent (SotA)\", \"Explicit Solvent + Vibrations (OpenMM)\"],\n",
    "    colors=[\"#A72608\", \"#61a89a\"], formula_remap=applications.FORMULA_REMAP,\n",
    "    figsize=(6, 5), y_min=0.0, y_max=0.37, save_path=figure_path(\"fig5c_benefit_1H.png\"))\n",
    "\n",
    "applications_plots.plot_nps_benefit_barplot(\n",
    "    loader.rmse_distribution(\"C\"), grouped[\"C\"], nucleus=\"C\",\n",
    "    solvents=[[\"chloroform\"], [\"benzene\"]], np_solute_groups=applications.ALL_IN_ONE_BIN,\n",
    "    formulas=[\"stationary_plus_pcm\", \"stationary_plus_op_vib + openMM\"],\n",
    "    labels=[\"Implicit Solvent (SotA)\", \"Explicit Solvent + Vibrations (OpenMM)\"],\n",
    "    colors=[\"#A72608\", \"#61a89a\"], formula_remap=applications.FORMULA_REMAP,\n",
    "    figsize=(6, 5), y_min=0.0, save_path=None)   # inline-only companion, not saved to disk"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}