Profiling ways to concatenate chunked bytes

bytes_concat.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%load_ext memory_profiler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "import struct\n",
    "def gen(size, count):\n",
    "    return ( struct.pack('B', random.randrange(255)) * size for b in range(count) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[b'\\xb6\\xb6\\xb6\\xb6\\xb6', b'\\x9a\\x9a\\x9a\\x9a\\x9a', b'DDDDD', b'\\xc3\\xc3\\xc3\\xc3\\xc3', b'\\xd0\\xd0\\xd0\\xd0\\xd0']\n"
     ]
    }
   ],
   "source": [
    "print(list(gen(5,5)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def concat_join(items):\n",
    "    buf = []\n",
    "    for item in items:\n",
    "        buf.append(item)\n",
    "    return b''.join(buf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def concat_bytes(items):\n",
    "    buf = bytearray()\n",
    "    for item in items:\n",
    "        buf.extend(item)\n",
    "    return buf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100000 loops, best of 10: 2.47 µs per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit -r 10 -n 100000 data = gen(10000,5000)\n",
    "concat_bytes(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100000 loops, best of 10: 890 ns per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit  -r 10 -n 100000 data = gen(10000,5000)\n",
    "concat_join(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "peak memory: 96.49 MiB, increment: 43.43 MiB\n"
     ]
    }
   ],
   "source": [
    "%%memit data = gen(10000,5000)\n",
    "concat_bytes(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "peak memory: 52.93 MiB, increment: -2.66 MiB\n"
     ]
    }
   ],
   "source": [
    "%%memit data = gen(10000,5000)\n",
    "concat_join(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}