{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4b208bf1",
   "metadata": {},
   "source": [
    "# Figure 5D: per-solute explicit-correction RMSE across the test set\n",
    "\n",
    "Per-solute bootstrap RMSE (¹H, solvent-averaged) for the explicit-solvent correction, ordered delta-22 -> olefin/pyridine isomers -> natural products, with a dashed \"scaled to solute\" baseline and a red \"scaled to test set\" line."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "66e2a22e",
   "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": "9b70b4ca",
   "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": "2da375fc",
   "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": "a6acf673",
   "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)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "889345fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "site_counts = (query_df_nn.drop_duplicates(subset=[\"solute\", \"nucleus\", \"site\"])\n",
    "               .groupby([\"solute\", \"nucleus\"]).size().unstack(fill_value=0))\n",
    "per_solute = applications.per_solute_fits(query_df_nn)\n",
    "all_solute = applications.per_solvent_fits(query_df_nn)\n",
    "preds_h = applications.apply_bootstrap_params_to_full_dataset(query_df_nn, seed[\"H\"], nucleus=\"H\")\n",
    "bootstrap_rmses_h = applications.compute_solute_rmses(preds_h)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "08869e35",
   "metadata": {},
   "outputs": [],
   "source": [
    "FIG5D_LABELS = {\n",
    "    \"isomer_1E\": \"Olefin 1 (E)\", \"isomer_1Z\": \"Olefin 1 (Z)\",\n",
    "    \"isomer_2E\": \"Olefin 2 (E)\", \"isomer_2Z\": \"Olefin 2 (Z)\",\n",
    "    \"isomer_3E\": \"Olefin 3 (E)\", \"isomer_3Z\": \"Olefin 3 (Z)\",\n",
    "    \"isomer_4N\": \"Pyridone 4\", \"isomer_4O\": \"Pyridine 4\",\n",
    "    \"vomicine\": \"Vomicine\", \"prednisone\": \"Prednisone\",\n",
    "    \"peptide\": \"Acetyl-L-alanyl-L-\\nglutamine\", \"flavone\": \"Flavone\",\n",
    "    \"dihydrotanshinone_I\": \"Dihydrotanshinone I\",\n",
    "}\n",
    "FIG5D_ORDER = [\"isomer_1E\", \"isomer_1Z\", \"isomer_2E\", \"isomer_2Z\", \"isomer_3E\", \"isomer_3Z\",\n",
    "               \"isomer_4N\", \"isomer_4O\", \"vomicine\", \"prednisone\", \"peptide\", \"flavone\",\n",
    "               \"dihydrotanshinone_I\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1ad5844c",
   "metadata": {},
   "outputs": [],
   "source": [
    "applications_plots.plot_nps_on_boxplot_delta22_simplified(\n",
    "    loader.rmse_distribution(\"H\"), bootstrap_rmses_h, per_solute[\"H\"],\n",
    "    nucleus=\"H\", formulas=[\"stationary_plus_qcd + openMM\"], colors=[\"#61a89a\"],\n",
    "    site_counts=site_counts, formula_remap=applications.FORMULA_REMAP,\n",
    "    solute_remap=FIG5D_LABELS, solute_order=FIG5D_ORDER,\n",
    "    title=\"Complex Molecules are Dominated by Additional Physics\",\n",
    "    solute_color_remap=applications.PEPTIDE_HIGHLIGHT_H,\n",
    "    figsize=(14, 8), box_width=0.20, box_gap=0.1,\n",
    "    show_baseline=True, baseline_annotation_text=\"Scaled to solute\",\n",
    "    baseline_annotation_x=0.215, baseline_annotation_y=0.39,\n",
    "    show_full_fit_line=True, full_fit_line_label=\"Scaled to Test Set\", full_fit_line_label_x=0.835,\n",
    "    all_solute_fitting_results=all_solute,\n",
    "    max_bar_height=0.06, site_count_axis_mode=\"inset\", site_count_inset_area_frac=0.1,\n",
    "    site_count_inset_axis_offset=-0.06,\n",
    "    save_path=figure_path(\"fig5d_complex_1H.png\"))"
   ]
  }
 ],
 "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
}