Word2Vec.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from gensim.test.utils import common_texts, get_tmpfile\n",
    "from gensim.models import Word2Vec\n",
    "\n",
    "w2v_model = Word2Vec(common_texts, size=100, window=5, min_count=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['human', 'interface', 'computer'],\n",
       " ['survey', 'user', 'computer', 'system', 'response', 'time'],\n",
       " ['eps', 'user', 'interface', 'system'],\n",
       " ['system', 'human', 'system', 'eps'],\n",
       " ['user', 'response', 'time'],\n",
       " ['trees'],\n",
       " ['graph', 'trees'],\n",
       " ['graph', 'minors', 'trees'],\n",
       " ['graph', 'minors', 'survey']]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "common_texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['system',\n",
       " 'user',\n",
       " 'trees',\n",
       " 'graph',\n",
       " 'human',\n",
       " 'interface',\n",
       " 'computer',\n",
       " 'survey',\n",
       " 'response',\n",
       " 'time',\n",
       " 'eps',\n",
       " 'minors']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# index to word\n",
    "w2v_model.wv.index2word"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "我們需要利用 `index2word` 來算出 `word2index`，接著我們就能把 training / testing data 中的資料以 index 取代。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-1.4890118e-03, -4.5906939e-03,  1.7917742e-03, ...,\n",
       "         1.1652057e-03, -4.3145278e-03, -1.6234915e-03],\n",
       "       [ 4.1555176e-03, -1.7337966e-03, -4.5758467e-03, ...,\n",
       "        -2.7107631e-03,  4.7598602e-03,  4.2530061e-03],\n",
       "       [ 4.5080658e-05,  1.8863901e-03, -4.7816625e-03, ...,\n",
       "        -4.4701910e-03, -9.9671488e-05,  2.9279427e-03],\n",
       "       ...,\n",
       "       [ 7.8272796e-04, -1.6770075e-03, -4.0623671e-03, ...,\n",
       "         4.6074665e-03, -1.1475774e-03,  4.9830242e-03],\n",
       "       [-1.0417016e-03,  3.9325394e-03, -4.4449898e-03, ...,\n",
       "        -3.0505881e-03,  3.4645137e-03, -3.1374148e-03],\n",
       "       [-2.5614763e-03, -8.8947389e-04, -7.1159453e-04, ...,\n",
       "         1.5468400e-03, -3.7911797e-03,  2.8648013e-03]], dtype=float32)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# index to vectors\n",
    "# 之後會將這個對應表傳入 keras\n",
    "w2v_model.wv.vectors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}