{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "007f5b29",
   "metadata": {},
   "source": [
    "# SI Figure S4: correlation of implicit (PCM) corrections across solvents and methods\n",
    "\n",
    "**S4A** correlation across solvents (both nuclei), **S4B** one solvent vs another (¹H), **S4C**\n",
    "correlation across methods (both nuclei). Cells show -log10(1-r), so 3 means r=0.999."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "34163231",
   "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": "d4fced82",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import delta22\n",
    "import delta22_plots\n",
    "import paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2d316f79",
   "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": "cb9e3ebb",
   "metadata": {},
   "outputs": [],
   "source": [
    "METHOD, BASIS, GEOM = \"b3lyp_d3bj\", \"pcSseg2\", \"pbe0_tz\"\n",
    "dft = delta22.load_query_df_dft(DELTA22_HDF5, XLSX, verbose=False)\n",
    "base = dft[(dft[\"sap_nmr_method\"] == METHOD) & (dft[\"sap_basis\"] == BASIS)\n",
    "           & (dft[\"sap_geometry_type\"] == GEOM)]\n",
    "one = base[base[\"nucleus\"] == \"H\"]\n",
    "\n",
    "# solvent order that groups polar-aprotic -> polar-protic -> aromatic (matches the published panel)\n",
    "ORDERED_SOLVENTS = [\"chloroform\", \"tetrahydrofuran\", \"dichloromethane\", \"acetone\", \"acetonitrile\",\n",
    "                    \"dimethylsulfoxide\", \"trifluoroethanol\", \"methanol\", \"TIP4P\",\n",
    "                    \"benzene\", \"toluene\", \"chlorobenzene\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee2d20ba",
   "metadata": {},
   "source": [
    "## S4A: solvent-vs-solvent PCM correlation (¹H and ¹³C)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c8664491",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nucleus, label in [(\"H\", \"1H\"), (\"C\", \"13C\")]:\n",
    "    solvent_corr = delta22.correlation_matrix(base[base[\"nucleus\"] == nucleus], \"pcm\", [\"solute\", \"site\"], \"solvent\")\n",
    "    solvent_corr = solvent_corr.reindex(index=ORDERED_SOLVENTS, columns=ORDERED_SOLVENTS)\n",
    "    vals = solvent_corr.values[np.triu_indices_from(solvent_corr.values, k=1)]\n",
    "    print(f\"solvent PCM correlation ({label}): mean r={np.nanmean(vals):.4f}  min r={np.nanmin(vals):.4f}\")\n",
    "    caption = (\"Correlation coefficients between solvents across all 22 solutes.\\n\"\n",
    "               f\"PCM corrections computed with {METHOD} with the {BASIS} basis.\\n\"\n",
    "               \"A value of 3 means the coefficient is 0.999.\")\n",
    "    delta22_plots.plot_correlation_matrix(solvent_corr, f\"Solvents are Highly Correlated ({nucleus})\", caption,\n",
    "                                          colormap=\"Reds\", show_values=True,\n",
    "                                          save_path=figure_path(f\"si_figure_s04a_{label}.png\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "133ed792",
   "metadata": {},
   "source": [
    "## S4B: PCM corrections, chloroform vs acetonitrile (1H) -- one square of S4A"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "21db6810",
   "metadata": {},
   "outputs": [],
   "source": [
    "pair = one.pivot_table(index=[\"solute\", \"site\"], columns=\"solvent\", values=\"pcm\")[\n",
    "    [\"chloroform\", \"acetonitrile\"]].dropna()\n",
    "delta22_plots.plot_pcm_scatter(pair[\"chloroform\"], pair[\"acetonitrile\"], \"chloroform\", \"acetonitrile\", \"H\",\n",
    "                               save_path=figure_path(\"si_figure_s04b_1H.png\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f0e76f9",
   "metadata": {},
   "source": [
    "## S4C: method-vs-method correlation (chloroform, double hybrids excluded, ¹H and ¹³C)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f75897e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# one solvent, exclude the double hybrids whose PCM is the substituted reference value\n",
    "for nucleus, label in [(\"H\", \"1H\"), (\"C\", \"13C\")]:\n",
    "    chcl3 = dft[(dft[\"sap_basis\"] == BASIS) & (dft[\"sap_geometry_type\"] == GEOM)\n",
    "                & (dft[\"nucleus\"] == nucleus) & (dft[\"solvent\"] == \"chloroform\")\n",
    "                & (~dft[\"sap_nmr_method\"].isin(delta22.DOUBLE_HYBRID_METHODS))]\n",
    "    method_corr = delta22.correlation_matrix(chcl3, \"pcm\", [\"solute\", \"site\"], \"sap_nmr_method\")\n",
    "    method_order = sorted(method_corr.index)          # alphabetical, matches the published panel\n",
    "    method_corr = method_corr.reindex(index=method_order, columns=method_order)\n",
    "    mvals = method_corr.values[np.triu_indices_from(method_corr.values, k=1)]\n",
    "    print(f\"method PCM correlation ({label}): mean r={np.nanmean(mvals):.4f}  min r={np.nanmin(mvals):.4f}\")\n",
    "    caption = (\"Correlation coefficients between NMR methods across all 22 solutes.\\n\"\n",
    "               f\"PCM corrections for chloroform with the {BASIS} basis.\")\n",
    "    delta22_plots.plot_correlation_matrix(method_corr, f\"NMR Methods are Highly Correlated ({nucleus})\", caption,\n",
    "                                          colormap=\"Reds\", show_values=True,\n",
    "                                          save_path=figure_path(f\"si_figure_s04c_{label}.png\"))"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}