{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "tutorials:\n",
    "\n",
    "- [Klintberg - Doc2Vec Tutorial Using Gensim](https://medium.com/@klintcho/doc2vec-tutorial-using-gensim-ab3ac03d3a1#.rccx4cq1p)\n",
    "\n",
    "- [Sentiment Analysis Using Doc2Vec](http://linanqiu.github.io/2015/10/07/word2vec-sentiment/)\n",
    "\n",
    "- [Official Gensim Doc2Vec Tutorial](https://rare-technologies.com/doc2vec-tutorial/)\n",
    "\n",
    "- [Doc2Vec IMDB notebook](https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/doc2vec-IMDB.ipynb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import logging\n",
    "\n",
    "from sklearn.datasets import fetch_rcv1\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.metrics import f1_score, precision_score, recall_score\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn import svm\n",
    "\n",
    "logging.basicConfig()\n",
    "rcv1 = fetch_rcv1()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "training_samples = 23149\n",
    "\n",
    "X_train = rcv1.data[:training_samples]\n",
    "X_test = rcv1.data[training_samples:]\n",
    "\n",
    "y_train = rcv1.target[:training_samples]\n",
    "y_test = rcv1.target[training_samples:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "sample_ids = rcv1.sample_id[:training_samples]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "26150"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_ids[-1]"
   ]
  },
  {
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}