{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dce84895",
   "metadata": {},
   "source": [
    "# Table S8: Dataset Summary Statistics\n",
    "\n",
    "Molecule and ¹H/¹³C site counts for each training dataset (site counts from each HDF5's\n",
    "`atomic_numbers`, ¹H=1/¹³C=6; MagNET-Zero combines both sigma-pepper rounds with sigma-concentrate)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "df321bd6",
   "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\", \"analysis/code/shared\"):\n",
    "    sys.path.insert(0, os.path.join(REPO, _p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "88710ad5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import dataset_summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "84e5a441",
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_DIR = os.path.join(REPO, \"data\")\n",
    "\n",
    "def document_path(name):\n",
    "    os.makedirs(\"documents\", exist_ok=True)\n",
    "    return os.path.join(\"documents\", name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6a606891",
   "metadata": {},
   "outputs": [],
   "source": [
    "table_s8 = dataset_summary.summary_table(DATA_DIR)\n",
    "display(table_s8)\n",
    "\n",
    "# write the table to this notebook's documents/ folder\n",
    "out = document_path(\"si_table_s08_summary.xlsx\")\n",
    "with pd.ExcelWriter(out) as writer:\n",
    "    table_s8.to_excel(writer, sheet_name=\"Table S8\", index=False)\n",
    "print(\"wrote\", os.path.relpath(out, REPO))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3bf67791",
   "metadata": {},
   "source": [
    "## Exact-reproduction check"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4d5f4416",
   "metadata": {},
   "outputs": [],
   "source": [
    "# every count should match the published SI Table S8 value exactly\n",
    "for _, row in table_s8.iterrows():\n",
    "    pub = dataset_summary.PUBLISHED_S8[row[\"dataset\"]]\n",
    "    got = (row[\"molecules\"], row[\"n_1H_sites\"], row[\"n_13C_sites\"])\n",
    "    assert got == pub, f\"{row['dataset']}: {got} != published {pub}\"\n",
    "print(\"all rows match the published SI Table S8 exactly\")"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}