Truyện Kiều W2V - http://blog.duyet.net/2017/04/nlp-truyen-kieu-word2vec.html Raw

kieu_word2vec_gensim.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3258\n"
     ]
    }
   ],
   "source": [
    "df[\"context\"] = df[\"1gram\"] + df[\"2gram\"]\n",
    "train_data = df.context.tolist()\n",
    "print len(train_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Training gensim model\n",
    "from gensim.models import Word2Vec\n",
    "import logging\n",
    "\n",
    "logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)    \n",
    "model = Word2Vec(train_data, size=100, window=10, min_count=3, workers=4, sg=1)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [Root]",
   "language": "python",
   "name": "Python [Root]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}