create_summa_dummy_csv_file.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a109d639",
   "metadata": {},
   "source": [
    "## Generating a Dummy CSV File for Summa\n",
    "\n",
    "Note that it would be better to check for duplicates, especially when generating a large dataset.\n",
    "\n",
    "Also, check that the maximum balance multiplied by the number of users is less than $2^{64}\\$ to prevent overflow cases.\n",
    "\n",
    "The overflow threshold is 18,446,744,073,709,551,616 (= 1 << 64) on the range chip."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "5cec3828",
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "import string\n",
    "\n",
    "def generate_random_string(length=8):\n",
    "    return ''.join(random.choice(string.ascii_letters) for _ in range(length))\n",
    "\n",
    "def generate_random_balance(max_balance=90000):\n",
    "    return str(random.randint(1000, max_balance))\n",
    "\n",
    "def generate_csv_entry(num_asset):\n",
    "    username = generate_random_string()\n",
    "    balance = generate_random_balance()\n",
    "    result = f\"{username},{balance}\"\n",
    "    \n",
    "    for i in range(1, num_asset):\n",
    "        balance = generate_random_balance()\n",
    "        result += f\",{balance}\"\n",
    "        \n",
    "    return result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "866d989b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Generate Dummy CSV file \n",
    "#\n",
    "# number of user: 1 << 10\n",
    "# number of currencies: 2\n",
    "l = 10\n",
    "u = 1 << l\n",
    "c = 2\n",
    "csv_file_name = f\"{c}_entry_2_{l}.csv\"\n",
    "\n",
    "with open(csv_file_name, \"w\") as f:\n",
    "    header = \"username,\" + \",\".join([f'balance_ETH{i+1}_ETH' for i in range(c)])\n",
    "    f.write(f\"{header}\\n\")  # Header\n",
    "    for _ in range(u):\n",
    "        f.write(generate_csv_entry(c) + \"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "faf8f3df",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>username</th>\n",
       "      <th>balance_ETH1_ETH</th>\n",
       "      <th>balance_ETH2_ETH</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>FNSkKHIq</td>\n",
       "      <td>54616</td>\n",
       "      <td>8135</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>oCqQqFdC</td>\n",
       "      <td>53960</td>\n",
       "      <td>58498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>JNSOqfCp</td>\n",
       "      <td>50719</td>\n",
       "      <td>10905</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>pXOmRAxh</td>\n",
       "      <td>5088</td>\n",
       "      <td>16052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>sNkUXewl</td>\n",
       "      <td>84047</td>\n",
       "      <td>67946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1019</th>\n",
       "      <td>ygsALHDO</td>\n",
       "      <td>22914</td>\n",
       "      <td>13596</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1020</th>\n",
       "      <td>BpserFft</td>\n",
       "      <td>28307</td>\n",
       "      <td>60563</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1021</th>\n",
       "      <td>ITmPewPT</td>\n",
       "      <td>4815</td>\n",
       "      <td>88183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1022</th>\n",
       "      <td>gpdURoww</td>\n",
       "      <td>9244</td>\n",
       "      <td>38372</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1023</th>\n",
       "      <td>gLXlSPEV</td>\n",
       "      <td>52895</td>\n",
       "      <td>45712</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1024 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      username  balance_ETH1_ETH  balance_ETH2_ETH\n",
       "0     FNSkKHIq             54616              8135\n",
       "1     oCqQqFdC             53960             58498\n",
       "2     JNSOqfCp             50719             10905\n",
       "3     pXOmRAxh              5088             16052\n",
       "4     sNkUXewl             84047             67946\n",
       "...        ...               ...               ...\n",
       "1019  ygsALHDO             22914             13596\n",
       "1020  BpserFft             28307             60563\n",
       "1021  ITmPewPT              4815             88183\n",
       "1022  gpdURoww              9244             38372\n",
       "1023  gLXlSPEV             52895             45712\n",
       "\n",
       "[1024 rows x 3 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check Dummy Data\n",
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(csv_file_name)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a63e0442",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}