tokenize_time.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from hashlib import md5\n",
    "from dask.utils import Dispatch\n",
    "from toolz import identity\n",
    "import random\n",
    "import string\n",
    "\n",
    "def tokenize_simplified(descriptor):\n",
    "    return md5(str(tuple(map(normalize_token, descriptor))).encode()).hexdigest()\n",
    "\n",
    "def tokenize_dask(*args, **kwargs):\n",
    "    # Tokenize method from dask\n",
    "    if kwargs:\n",
    "        args = args + (kwargs,)\n",
    "    return md5(str(tuple(map(normalize_token, args))).encode()).hexdigest()\n",
    "\n",
    "def tokenize_new(*args):\n",
    "    return md5(str(tuple(map(normalize_token, args))).encode()).hexdigest()\n",
    "\n",
    "def tokenize_new2(args):\n",
    "    return md5(str(tuple(map(normalize_token, args))).encode()).hexdigest()\n",
    "\n",
    "normalize_token = Dispatch()\n",
    "normalize_token.register(\n",
    "    (int, float, str, bytes, type(None), type, slice, complex, type(Ellipsis)), identity\n",
    ")\n",
    "\n",
    "@normalize_token.register(dict)\n",
    "def normalize_dict(d):\n",
    "    return normalize_token(sorted(d.items(), key=str))\n",
    "\n",
    "@normalize_token.register(set)\n",
    "def normalize_set(s):\n",
    "    return normalize_token(sorted(s, key=str))\n",
    "\n",
    "\n",
    "@normalize_token.register((tuple, list))\n",
    "def normalize_seq(seq):\n",
    "    return type(seq).__name__, list(map(normalize_token, seq))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "descriptor = {random.choice(string.ascii_letters): \n",
    "                  {random.choice(string.ascii_letters): 1000 * random.choice(string.ascii_letters) for _ in range(1000)} \n",
    "              for _ in range(1000)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "19.4 µs ± 161 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "tokenize_simplified(descriptor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "24.2 ms ± 274 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "tokenize_dask(descriptor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "24.2 ms ± 248 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "tokenize_new(descriptor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "19.4 µs ± 176 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "tokenize_new2(descriptor)"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}