http://qiita.com/yukinoi/items/42f8b5461dc1b62db7f9

Japanese text processing benchmark.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 日本語文字列変換モジュールの比較"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ドグラマグラをとってくる"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current',\n",
       " '                                 Dload  Upload   Total   Spent    Left  Speed',\n",
       " '',\n",
       " '  0     0    0     0    0     0      0      0 --:--:-- --:--:-- --:--:--     0',\n",
       " '100  411k  100  411k    0     0   707k      0 --:--:-- --:--:-- --:--:--  707k',\n",
       " 'Archive:  /tmp/2093_ruby_28087.zip',\n",
       " 'Made with MacWinZipper™',\n",
       " '  inflating: /tmp/dogura_magura.txt  ']"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%system\n",
    "rm -f /tmp/2093_ruby_28087.zip /tmp/dogura_magura.txt\n",
    "curl -o /tmp/2093_ruby_28087.zip http://www.aozora.gr.jp/cards/000096/files/2093_ruby_28087.zip\n",
    "unzip -d /tmp /tmp/2093_ruby_28087.zip\n",
    "nkf -Sw --overwrite /tmp/dogura_magura.txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "with open('/tmp/dogura_magura.txt') as fd:\n",
    "    dogura_magura = fd.read()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 短文を半角→全角"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000 loops, best of 3: 27.1 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import jaconv\n",
    "%timeit jaconv.h2z(dogura_magura[:140], ascii=False, digit=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000 loops, best of 3: 96.4 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import cnvk\n",
    "%timeit cnvk.convert(dogura_magura[:140], cnvk.Z_KATA, cnvk.H_ASCII, cnvk.H_SPACE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100000 loops, best of 3: 5.04 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import mojimoji\n",
    "%timeit mojimoji.han_to_zen(dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000 loops, best of 3: 75.8 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import zenhan\n",
    "%timeit zenhan.h2z(dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000 loops, best of 3: 222 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import rfZenHan\n",
    "%timeit rfZenHan.h2z(dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000 loops, best of 3: 23 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import nkf\n",
    "%timeit nkf.nkf('-x -m0 --z1', dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 長文を半角→全角"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 89.9 ms per loop\n"
     ]
    }
   ],
   "source": [
    "import jaconv\n",
    "%timeit jaconv.h2z(dogura_magura, ascii=False, digit=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 38.6 ms per loop\n"
     ]
    }
   ],
   "source": [
    "import cnvk\n",
    "%timeit cnvk.convert(dogura_magura, cnvk.Z_KATA, cnvk.H_ASCII, cnvk.H_SPACE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 23.1 ms per loop\n"
     ]
    }
   ],
   "source": [
    "import mojimoji\n",
    "%timeit mojimoji.han_to_zen(dogura_magura)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 360 ms per loop\n"
     ]
    }
   ],
   "source": [
    "import zenhan\n",
    "%timeit zenhan.h2z(dogura_magura)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 237 ms per loop\n"
     ]
    }
   ],
   "source": [
    "import rfZenHan\n",
    "%timeit rfZenHan.h2z(dogura_magura)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 95.4 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit nkf.nkf('-x -m0 --z1', dogura_magura)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 短文をひらがな→カタカナ"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100000 loops, best of 3: 18.1 µs per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit jaconv.hira2kata(dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000 loops, best of 3: 79.1 µs per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit cnvk.convert(dogura_magura[:140], cnvk.HIRA2KATA, cnvk.Z_KATA)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000 loops, best of 3: 25.4 µs per loop\n"
     ]
    }
   ],
   "source": [
    "import mohayonao\n",
    "%timeit mohayonao.katakana(dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The slowest run took 4.00 times longer than the fastest. This could mean that an intermediate result is being cached.\n",
      "10000 loops, best of 3: 23.2 µs per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit nkf.nkf('-x -m0 --katakana', dogura_magura[:140])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 長文をひらがな→カタカナ"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 51.6 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit jaconv.hira2kata(dogura_magura)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 41.8 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit cnvk.convert(dogura_magura, cnvk.HIRA2KATA, cnvk.Z_KATA)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 246 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit mohayonao.katakana(dogura_magura)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 98.6 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit nkf.nkf('-x -m0 --katakana', dogura_magura)"
   ]
  },
  {
   "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}