file serialization test

Untitled.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import io\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class FileIOPicklable(io.FileIO):\n",
    "    def __init__(self, name):\n",
    "        super().__init__(name, mode='r')\n",
    "\n",
    "    def __getstate__(self):\n",
    "        return self.name, self.tell()\n",
    "\n",
    "    def __setstate__(self, args):\n",
    "        name = args[0]\n",
    "        super().__init__(name, mode='r')\n",
    "        self.seek(args[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stdopen():\n",
    "    raw = io.FileIO('Untitled.ipynb')\n",
    "    file = io.TextIOWrapper(raw)\n",
    "    lines = file.readlines()\n",
    "    file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "74 µs ± 938 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit stdopen()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def standard_open():\n",
    "    file = open('Untitled.ipynb')\n",
    "    liens = file.readlines()\n",
    "    file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "80.9 µs ± 441 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit standard_open()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pickle_open():\n",
    "    raw = FileIOPicklable('Untitled.ipynb')\n",
    "    file = io.TextIOWrapper(raw)\n",
    "    lines = file.readlines()\n",
    "    file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "79.8 µs ± 1.09 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit pickle_open()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "class TextIOPicklable(io.TextIOWrapper):\n",
    "    def __init__(self, raw):\n",
    "        super().__init__(raw)\n",
    "        self.raw_class = raw.__class__\n",
    "\n",
    "    def __getstate__(self):\n",
    "        return self.raw_class, self.name, self.tell()\n",
    "\n",
    "    def __setstate__(self, args):\n",
    "        raw_class = args[0]\n",
    "        name = args[1]\n",
    "        # raw_class is used for further expansion this functionality to\n",
    "        # GZip files, which also requires a text wrapper.\n",
    "        raw = raw_class(name)\n",
    "        super().__init__(raw)\n",
    "        self.seek(args[2])\n",
    "        \n",
    "class BufferIOPicklable(io.BufferedReader):\n",
    "    def __init__(self, raw):\n",
    "        super().__init__(raw)\n",
    "        self.raw_class = raw.__class__\n",
    "\n",
    "    def __getstate__(self):\n",
    "        return self.raw_class, self.name, self.tell()\n",
    "\n",
    "    def __setstate__(self, args):\n",
    "        raw_class = args[0]\n",
    "        name = args[1]\n",
    "        raw = raw_class(name)\n",
    "        super().__init__(raw)\n",
    "        self.seek(args[2])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pickle_open2():\n",
    "    raw = FileIOPicklable('Untitled.ipynb')\n",
    "    file = TextIOPicklable(raw)\n",
    "    lines = file.readlines()\n",
    "    file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "133 µs ± 5.33 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit pickle_open2()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pickle_open3():\n",
    "    raw = FileIOPicklable('Untitled.ipynb')\n",
    "    file = TextIOPicklable(BufferIOPicklable(raw))\n",
    "    lines = file.readlines()\n",
    "    file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "153 µs ± 9.6 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit pickle_open3()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "class NonWrapper():\n",
    "    def __init__(self, name, mode='r'):\n",
    "        self._name = name\n",
    "        self._mode = mode\n",
    "        self._fh = open(name, mode)\n",
    "        \n",
    "    def __getstate__(self):\n",
    "        return self._name, self._mode, self._fh.tell()\n",
    "    \n",
    "    def __setstate__(self, args):\n",
    "        self._name = args[0]\n",
    "        self._mode = args[1]\n",
    "        self._fh = open(self._name, self._mode)\n",
    "        self._fh.seek(args[2])\n",
    "        \n",
    "    def readlines(self):\n",
    "        return self._fh.readlines()\n",
    "    \n",
    "    def close(self):\n",
    "        self._fh.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def my_open():\n",
    "    file = NonWrapper('Untitled.ipynb')\n",
    "    lines = file.readlines()\n",
    "    file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "91.2 µs ± 6.51 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit my_open()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}