{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "6d0c4a9d",
   "metadata": {},
   "source": [
    "# Figure 4C: fit RMSE vs experimental range, implicit vs explicit\n",
    "\n",
    "Per-solvent fit RMSE vs experimental shift range (¹H), implicit (PCM) vs explicit (Desmond)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8a3ec572",
   "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": "79b3bd64",
   "metadata": {},
   "outputs": [],
   "source": [
    "import delta22\n",
    "import paths\n",
    "import fig4_plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "79171fdb",
   "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": "fdaaf850",
   "metadata": {},
   "outputs": [],
   "source": [
    "# solvent_mean is a synthetic pseudo-solvent representing the average across solvents; it is used below as the reference baseline.\n",
    "METHOD, BASIS, GEOM = \"b3lyp_d3bj\", \"pcSseg2\", \"aimnet2\"\n",
    "q = delta22.load_query_df_dft(DELTA22_HDF5, XLSX, verbose=False)\n",
    "one = q[(q[\"sap_nmr_method\"] == METHOD) & (q[\"sap_basis\"] == BASIS) & (q[\"sap_geometry_type\"] == GEOM)]\n",
    "one = delta22.add_solvent_mean(one)\n",
    "print(len(one), \"rows for\", METHOD, BASIS, GEOM)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e5527018",
   "metadata": {},
   "outputs": [],
   "source": [
    "FIG4C_LABELS = {\n",
    "    \"chloroform\": \"CDCl3\", \"dichloromethane\": \"DCM\", \"tetrahydrofuran\": \"THF\",\n",
    "    \"acetonitrile\": \"MeCN\", \"dimethylsulfoxide\": \"DMSO\", \"acetone\": \"acetone\",\n",
    "    \"methanol\": \"MeOD\", \"TIP4P\": \"TIP4P\", \"trifluoroethanol\": \"trifluoroethanol\",\n",
    "    \"benzene\": \"benzene\", \"toluene\": \"toluene\", \"chlorobenzene\": \"chlorobenzene\",\n",
    "}\n",
    "FIG4C_COLORS = {\"Implicit (PCM)\": \"#A72608\", \"Explicit (Desmond)\": \"#61a89a\"}  # red diamond / teal circle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3cdab0a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# differences are taken against the solvent-averaged pseudo-solvent so every real solvent, including chloroform, appears as a point.\n",
    "rmse_range_rows = []\n",
    "for solvent in delta22.DESMOND_SOLVENTS:\n",
    "    sp = delta22.solvent_pair_differences(one, solvent, \"solvent_mean\", nucleus=\"H\", explicit=\"desmond\")\n",
    "    if len(sp) == 0:\n",
    "        continue\n",
    "    rmse_range_rows.append({\n",
    "        \"solvent\": solvent,\n",
    "        \"range\": float(sp[\"exp_diff\"].max() - sp[\"exp_diff\"].min()),\n",
    "        \"implicit\": delta22.fit_differences_to_experimental(sp, \"implicit_diff\")[\"rmse\"],\n",
    "        \"explicit\": delta22.fit_differences_to_experimental(sp, \"explicit_diff\")[\"rmse\"],\n",
    "    })\n",
    "for r in sorted(rmse_range_rows, key=lambda r: r[\"range\"]):\n",
    "    print(f\"{FIG4C_LABELS[r['solvent']]:16s} range={r['range']:.3f}  \"\n",
    "          f\"implicit={r['implicit']:.3f}  explicit={r['explicit']:.3f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4601c2c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "fig4_plots.save_panel(\n",
    "    lambda ax: fig4_plots.draw_rmse_dumbbell(ax, rmse_range_rows, FIG4C_LABELS, FIG4C_COLORS),\n",
    "    figure_path(\"fig4c_rmse_range_1H.png\"),\n",
    ")"
   ]
  }
 ],
 "metadata": {},
 "nbformat": 4,
 "nbformat_minor": 5
}