{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e8c73ac7",
   "metadata": {},
   "source": [
    "# Figure 2B: inter-method correlation of delta-22 ¹H stationary shieldings\n",
    "\n",
    "Lower-triangle Pearson correlation matrix of per-site ¹H delta-22 stationary shieldings across methods\n",
    "(pcSseg-2 basis). The colorbar is Pearson r; the published panel mislabels it r², a typo, corrected here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ae047e23",
   "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": "3d783476",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "import delta22\n",
    "import paths\n",
    "import fig2b_plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9f91feb0",
   "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": "569d9eef",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Gas-phase (\"stationary\") shieldings, one value per (solute, geometry, basis, site, nucleus, method).\n",
    "# The stationary shielding does not depend on solvent, so keep one solvent (TIP4P) to deduplicate.\n",
    "NUCLEUS = \"H\"\n",
    "BASIS = \"pcSseg2\"\n",
    "\n",
    "dft = delta22.load_query_df_dft(DELTA22_HDF5, XLSX, verbose=False)\n",
    "corr_df = dft[[\"solute\", \"sap_geometry_type\", \"sap_nmr_method\", \"sap_basis\",\n",
    "               \"nucleus\", \"site\", \"solvent\", \"stationary\"]].copy()\n",
    "corr_df.columns = [c.replace(\"sap_\", \"\") for c in corr_df.columns]\n",
    "corr_df = corr_df.query('solvent == \"TIP4P\"').drop(columns=[\"solvent\"])\n",
    "\n",
    "pivot = corr_df.pivot(index=[\"solute\", \"geometry_type\", \"basis\", \"site\", \"nucleus\"],\n",
    "                      columns=\"nmr_method\", values=\"stationary\")\n",
    "sub = pivot.query(\"nucleus == @NUCLEUS and basis == @BASIS\")\n",
    "correlations = sub.corr()\n",
    "off_diag = correlations.where(~np.eye(len(correlations), dtype=bool))\n",
    "print(f\"{correlations.shape[0]} methods; worst pairwise Pearson r = {off_diag.min().min():.5f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f866aab1",
   "metadata": {},
   "outputs": [],
   "source": [
    "fig2b_plots.plot_correlation_matrix(correlations, save_png=figure_path(\"fig2b_correlation_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
}