PythonでのMeCabを速くするtips

1_parse_vs_parseToNode.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Python 3.5.0']"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%system python -V"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ドグラマグラをとってくる"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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",
       " '  0     0    0     0    0     0      0      0 --:--:-- --:--:-- --:--:--     0',\n",
       " '100  411k  100  411k    0     0   568k      0 --:--:-- --:--:-- --:--:--  568k',\n",
       " 'Archive:  /tmp/2093_ruby_28087.zip',\n",
       " 'Made with MacWinZipper™',\n",
       " '  inflating: /tmp/dogura_magura.txt  ']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%system\n",
    "rm /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": "markdown",
   "metadata": {},
   "source": [
    "## ここからベンチマーク"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import MeCab\n",
    "\n",
    "tagger = MeCab.Tagger('-d /usr/local/lib/mecab/dic/ipadic')\n",
    "\n",
    "\n",
    "def preprocessing(sentence):\n",
    "    return sentence.rstrip()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loops, best of 3: 667 ms per loop\n"
     ]
    }
   ],
   "source": [
    "def extract_noun_by_parse(path):\n",
    "    with open(path) as fd:\n",
    "        nouns = []\n",
    "        for sentence in map(preprocessing, fd):\n",
    "            for chunk in tagger.parse(sentence).splitlines()[:-1]:\n",
    "                (surface, feature) = chunk.split('\\t')\n",
    "                if feature.startswith('名詞'):\n",
    "                    nouns.append(surface)\n",
    "    return nouns\n",
    "\n",
    "\n",
    "%timeit extract_noun_by_parse('/tmp/dogura_magura.txt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loops, best of 3: 1.62 s per loop\n"
     ]
    }
   ],
   "source": [
    "def extract_noun_by_parsetonode(path):\n",
    "    with open(path) as fd:\n",
    "        nouns = []\n",
    "        for sentence in map(preprocessing, fd):\n",
    "            node = tagger.parseToNode(sentence)\n",
    "            while node:\n",
    "                if node.feature.startswith('名詞'):\n",
    "                    nouns.append(node.surface)\n",
    "                node = node.next\n",
    "    return nouns\n",
    "\n",
    "\n",
    "%timeit extract_noun_by_parsetonode('/tmp/dogura_magura.txt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " "
     ]
    }
   ],
   "source": [
    "%prun extract_noun_by_parsetonode('/tmp/dogura_magura.txt')"
   ]
  },
  {
   "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": "3.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

2_asis_vs_joblib.ipynb