Serialization tests.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "import base64\n",
    "import os\n",
    "\n",
    "KB = 1024\n",
    "MB = 1024 * KB\n",
    "\n",
    "messages = [\n",
    "    {'data': os.urandom(num_bytes)}\n",
    "    for num_bytes in [1*KB, 100*KB, 1*MB, 100*MB]\n",
    "]\n",
    "messages_base64 = [\n",
    "    {'data': base64.b64encode(message['data']).decode('ascii')}\n",
    "    for message in messages\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import ujson\n",
    "import orjson\n",
    "import msgpack\n",
    "import cbor\n",
    "import ubjson"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "from humanfriendly import format_size\n",
    "\n",
    "def print_size(dumps, messages=messages):\n",
    "    size = sum(len(dumps(m)) for m in messages)\n",
    "    print('Total serialized size:', format_size(size))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# JSON (standard library)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total serialized size: 141.35 MB\n"
     ]
    }
   ],
   "source": [
    "print_size(json.dumps, messages_base64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "472 ms ± 1.62 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for m in messages_base64:\n",
    "    json.loads(json.dumps(m))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# JSON (ujson)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total serialized size: 143.55 MB\n"
     ]
    }
   ],
   "source": [
    "print_size(ujson.dumps, messages_base64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "779 ms ± 4.2 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for m in messages_base64:\n",
    "    ujson.loads(ujson.dumps(m))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# ORJSON (orjson)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total serialized size: 141.35 MB\n"
     ]
    }
   ],
   "source": [
    "print_size(orjson.dumps, messages_base64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "238 ms ± 1.59 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for m in messages_base64:\n",
    "    orjson.loads(orjson.dumps(m))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MessagePack (official lib)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total serialized size: 106.01 MB\n"
     ]
    }
   ],
   "source": [
    "print_size(msgpack.packb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "92.1 ms ± 248 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for m in messages:\n",
    "    msgpack.unpackb(msgpack.packb(m))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# CBOR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total serialized size: 106.01 MB\n"
     ]
    }
   ],
   "source": [
    "print_size(cbor.dumps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "92.7 ms ± 576 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for m in messages:\n",
    "    cbor.loads(cbor.dumps(m))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# UBJSON"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total serialized size: 106.01 MB\n"
     ]
    }
   ],
   "source": [
    "print_size(ubjson.dumpb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "61.7 ms ± 461 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for m in messages:\n",
    "    ubjson.loadb(ubjson.dumpb(m))"
   ]
  }
 ],
 "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": "3.9.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}