{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1205f9e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "\n",
    "import numpy as np\n",
    "from rdkit import Chem\n",
    "from collections import defaultdict\n",
    "import numpy as np\n",
    "import sys\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c1267f1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"/data/yzhouc01/FILIP-MS/data/magma/MassSpecGymID0191762.json\", 'r') as f:\n",
    "    data = json.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "db06e7e6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['mz', 'intensities', 'subformulas', 'substructures'])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "582e23d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['C4H8O4']"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['subformulas'][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "abe22e21",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.seed(42)\n",
    "\n",
    "formulas = []\n",
    "mzs = []\n",
    "intensities = []\n",
    "\n",
    "for f, m, i in zip(data['subformulas'], data['mz'], data['intensities']):\n",
    "    if f:\n",
    "        formulas.append(np.random.choice(f))\n",
    "        mzs.append(m)\n",
    "        intensities.append(i)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "161f95f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "69"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(data['mz'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0c622b13",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "spec",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}