{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "01850ff6",
   "metadata": {},
   "source": [
    "# Figure 1A: CP3 per-site ¹H shift spread vs the DFT and experimental resolution limits\n",
    "\n",
    "Histogram of per-site ¹H shift spread across the Goodman CP3 stereoisomers (Goodman, JOC 2009, 74,\n",
    "4597), against the experimental noise floor (0.02 ppm) and DFT's resolving power (0.10 ppm)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a460d80b",
   "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 (\"analysis/code\",):\n",
    "    sys.path.insert(0, os.path.join(REPO, _p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e0adf094",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from matplotlib.ticker import FixedLocator\n",
    "\n",
    "import cp3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b68e0918",
   "metadata": {},
   "outputs": [],
   "source": [
    "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": "f599e59b",
   "metadata": {},
   "outputs": [],
   "source": [
    "variations = cp3.load_variations(nucleus=\"H\")\n",
    "frac = cp3.fraction_below_dft(variations)\n",
    "print(f\"{len(variations)} proton sites; {frac:.1%} fall between the experimental floor \"\n",
    "      f\"({cp3.EXPERIMENTAL_LIMIT} ppm) and the DFT limit ({cp3.DFT_LIMIT} ppm)\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c88605cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# color per zone; keys match cp3._zone's return values\n",
    "zone_colors = {\n",
    "    \"below_experimental\": \"#2c4553\",  # < 0.02 ppm: within experimental noise\n",
    "    \"below_dft\": \"#a72608\",           # 0.02 - 0.10 ppm: informative but DFT cannot resolve\n",
    "    \"dft_zone\": \"#dacd82\",            # 0.10 - 0.30 ppm: resolvable by DFT\n",
    "    \"large\": \"#68a79a\",               # >= 0.30 ppm\n",
    "}\n",
    "boundaries = (cp3.EXPERIMENTAL_LIMIT, cp3.DFT_LIMIT, cp3.LARGE_VARIATION)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "03efe205",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set_theme(context=\"paper\", style=\"white\")\n",
    "fig, ax = plt.subplots(figsize=(8, 4))\n",
    "\n",
    "bins = 30\n",
    "edges = np.linspace(0.0, float(variations.max()), bins + 1)\n",
    "counts, edge = np.histogram(variations, bins=edges)\n",
    "\n",
    "# Draw each bar, splitting any bin that straddles a zone boundary so each segment gets its color.\n",
    "for height, left, right in zip(counts, edge[:-1], edge[1:]):\n",
    "    splits = sorted({left, right} | {b for b in boundaries if left < b < right})\n",
    "    for a, b in zip(splits[:-1], splits[1:]):\n",
    "        ax.bar(a, height, width=b - a, align=\"edge\",\n",
    "               color=zone_colors[cp3._zone(0.5 * (a + b))],\n",
    "               edgecolor=\"white\", linewidth=0.6, alpha=0.9)\n",
    "\n",
    "ax.set_xlim(left=0.0)\n",
    "ax.set_ylim(0, ax.get_ylim()[1])\n",
    "ax.margins(x=0)\n",
    "ax.set_title(\"Chemical shift variation (¹H)\", pad=8, fontsize=16)\n",
    "ax.set_xlabel(\"Variation at Site (standard deviation, ¹H ppm)\", fontsize=13)\n",
    "ax.set_ylabel(\"Count\", fontsize=13)\n",
    "sns.despine(ax=ax, top=True, right=True)\n",
    "for side in (\"left\", \"bottom\"):\n",
    "    ax.spines[side].set_linewidth(0.6)\n",
    "ax.xaxis.set_major_locator(FixedLocator([0.0, 0.1, 0.2, 0.3, 0.4, 0.5]))\n",
    "ax.tick_params(axis=\"both\", which=\"major\", labelsize=10, size=1.5, width=0.6)\n",
    "ax.minorticks_off()\n",
    "fig.tight_layout()\n",
    "\n",
    "fig.savefig(figure_path(\"fig1a_cp3_1H.png\"), dpi=300, bbox_inches=\"tight\", pad_inches=0.02)\n",
    "plt.show()"
   ]
  }
 ],
 "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
}