bag_of_words.ipynb

{
 "cells": [
  {
   "metadata": {
    "trusted": true,
    "collapsed": false,
    "editable": true,
    "deletable": true
   },
   "cell_type": "code",
   "source": "from sklearn.feature_extraction.text import CountVectorizer\nSentence_1 = [\"John likes to watch movies. Mary likes movies too.\"]\nvectorizer = CountVectorizer()\nX = vectorizer.fit_transform(Sentence_1)\nprint(X)",
   "execution_count": 8,
   "outputs": [
    {
     "text": "  (0, 5)\t1\n  (0, 2)\t1\n  (0, 3)\t2\n  (0, 6)\t1\n  (0, 4)\t1\n  (0, 1)\t2\n  (0, 0)\t1\n",
     "name": "stdout",
     "output_type": "stream"
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false,
    "editable": true,
    "deletable": true
   },
   "cell_type": "code",
   "source": "print(vectorizer.get_feature_names())\n",
   "execution_count": 9,
   "outputs": [
    {
     "text": "['john', 'likes', 'mary', 'movies', 'to', 'too', 'watch']\n",
     "name": "stdout",
     "output_type": "stream"
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true,
    "editable": true,
    "deletable": true
   },
   "cell_type": "code",
   "source": "",
   "execution_count": null,
   "outputs": []
  }
 ],
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "version": 3,
    "name": "ipython"
   },
   "mimetype": "text/x-python",
   "file_extension": ".py",
   "pygments_lexer": "ipython3",
   "version": "3.6.7",
   "nbconvert_exporter": "python",
   "name": "python"
  },
  "kernelspec": {
   "name": "conda-env-faq-py",
   "display_name": "Python [conda env:faq]",
   "language": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}