{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import json\n",
    "import gzip\n",
    "\n",
    "import nltk\n",
    "\n",
    "# set the java environment variables:\n",
    "# CLASSPATH is the path to the stanford-postagger.jar in your local disk\n",
    "# STANFORD_MODELS is the path to the tagger file in your local disk\n",
    "import os\n",
    "os.environ['CLASSPATH']='/opt/local/stanford-postagger-2014-01-04/stanford-postagger.jar'\n",
    "os.environ['STANFORD_MODELS']='/opt/local/stanford-postagger-2014-01-04/models/english-left3words-distsim.tagger'\n",
    "\n",
    "# initialize tagger\n",
    "from nltk.tag.stanford import StanfordPOSTagger\n",
    "\n",
    "# function to read the compressed Amazon reviews for musical instruments\n",
    "def parse(path):\n",
    "  g = gzip.open(path, 'r')\n",
    "  for l in g:\n",
    "    yield json.dumps(eval(l))\n",
    "    \n",
    "# process the reviews: tokennizing, normalizing\n",
    "# input_filename is the path to the downloaded .json.gz file of the reviews\n",
    "\n",
    "def pre_process(input_filename):\n",
    "    # for each review\n",
    "    for l in parse(input_filename):\n",
    "        \n",
    "        # the variable \"review\" is a Python string containing the texts of the review.\n",
    "        review = json.loads(l)['reviewText']\n",
    "\n",
    "        # your codes to process the review text go below\n",
    "        \n",
    "def output_task_1(attributes, frequencies, labels, supp_sents):\n",
    "    \"\"\"\n",
    "        This function write your results to p1_t1.csv\n",
    "    \"\"\"\n",
    "    f = open('p1_t1.csv', 'w')\n",
    "    for a,f,l,s in zip(attributes, frequencies, labels, supp_sents):\n",
    "        f.write(a + ',' + str(f) + ',' + str(l) + ',' + s + '\\n')\n",
    "    f.close()\n",
    "    \n",
    "def output_task_2(pairs, labels, supp_sents):\n",
    "    f = open('p1_t2.csv', 'w')\n",
    "    for p, l, s in zip(pairs, labels, supp_sents):\n",
    "        f.write('(' + p[0] + ',' + p[1] +'),'+str(l) + ','+s+'\\n')\n",
    "    f.close()\n",
    "    \n",
    "# example to use stanford POS tagger\n",
    "st = StanfordPOSTagger('english-bidirectional-distsim.tagger')\n",
    "st.tag('Get your copy , today , along with \"The Green Violin ; Theory , Ear Training , and Musicianship for Violinists \" book to prepare for this concerto and for more advanced playing !'.split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [Root]",
   "language": "python",
   "name": "Python [Root]"
  },
  "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": 0
}