Comparativo entre formas de remover itens de um dicionário no Python

HowToRemoveDictKeys.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def gen_dict(n):\n",
    "    \"\"\"Generate sample dict\"\"\"\n",
    "    return { 'item%d' % i : 'item%d' % i for i in xrange(n) }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_del(n):\n",
    "    \"\"\"Remove using dict.__del__(key)\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    del d1['item123']\n",
    "    del d1['item456']\n",
    "    del d1['item789']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_pop(n):\n",
    "    \"\"\"Remove using dict.pop(key, default)\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    d1.pop('item123', None)\n",
    "    d1.pop('item456', None)\n",
    "    d1.pop('item789', None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_map(n):\n",
    "    \"\"\"Map keys to dict.pop(key)\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    map(d1.pop, ['item123', 'item456', 'item789'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_map2(n):\n",
    "    \"\"\"Map keys to dict.pop(key, default)\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    map(lambda k: d1.pop(k, None), ['item123', 'item456', 'item789'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_regen(n):\n",
    "    \"\"\"Remove by recreating the dict\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    d1 = { key: d1[key] for key in d1 if key not in ['item123', 'item456', 'item789'] }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_regen2(n):\n",
    "    \"\"\"Remove by recreating the dict (avoid dict.__getitem__(key))\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    d1 = { key: value for key, value in d1.items() if key not in ['item123', 'item456', 'item789'] }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def dict_regen3(n):\n",
    "    \"\"\"Remove by recreating the dict (avoid dict.__getitem__(key), w/ iterator)\"\"\"\n",
    "    d1 = gen_dict(n)\n",
    "    d1 = { key: value for key, value in d1.iteritems() if key not in ['item123', 'item456', 'item789'] }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "n = 100000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 154 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_del(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 159 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_pop(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 158 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_map(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 160 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_map2(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 202 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_regen(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 222 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_regen2(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 198 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit -n100 dict_regen3(n)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

requirements.txt

Jinja2==2.8
MarkupSafe==0.23
Pygments==2.0.2
argparse==1.2.1
backports-abc==0.4
backports.ssl-match-hostname==3.5.0.1
certifi==2015.11.20.1
decorator==4.0.6
functools32==3.2.3-2
ipykernel==4.2.2
ipython==4.0.1
ipython-genutils==0.1.0
ipywidgets==4.1.1
jsonschema==2.5.1
jupyter==1.0.0
jupyter-client==4.1.1
jupyter-console==4.0.3
jupyter-core==4.0.6
mistune==0.7.1
nbconvert==4.1.0
nbformat==4.0.1
notebook==4.0.6
path.py==8.1.2
pexpect==4.0.1
pickleshare==0.5
ptyprocess==0.5
pyzmq==15.1.0
qtconsole==4.1.1
simplegeneric==0.8.1
singledispatch==3.4.0.3
six==1.10.0
terminado==0.6
tornado==4.3
traitlets==4.0.0
wsgiref==0.1.2