{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from collections import Counter\n",
    "\n",
    "import gzip\n",
    "import json\n",
    "import time\n",
    "import pickle \n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import xml.etree.ElementTree as ET\n",
    "root = ET.parse('c:/tmp/langs.model.xml')\n",
    "\n",
    "keywords = []\n",
    "\n",
    "for elem in root.findall('.//Keywords'):\n",
    "    if elem.text:\n",
    "        keywords.extend(elem.text.split(' '))\n",
    "\n",
    "keywords = {s.strip() for s in keywords}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "18:38:26 processing 10000s line...\n",
      "18:38:33 processing 20000s line...\n",
      "18:38:46 processing 30000s line...\n",
      "18:38:51 processing 40000s line...\n",
      "18:38:58 processing 50000s line...\n",
      "18:39:05 processing 60000s line...\n",
      "18:39:11 processing 70000s line...\n",
      "18:39:15 processing 80000s line...\n",
      "18:39:22 processing 90000s line...\n",
      "18:39:28 processing 100000s line...\n",
      "18:39:34 processing 110000s line...\n",
      "18:39:40 processing 120000s line...\n",
      "18:39:46 processing 130000s line...\n",
      "18:39:53 processing 140000s line...\n",
      "18:40:02 processing 150000s line...\n",
      "18:40:10 processing 160000s line...\n",
      "18:40:15 processing 170000s line...\n",
      "18:40:21 processing 180000s line...\n",
      "18:40:31 processing 190000s line...\n",
      "18:40:39 processing 200000s line...\n",
      "18:40:52 processing 210000s line...\n",
      "18:41:02 processing 220000s line...\n",
      "18:41:11 processing 230000s line...\n",
      "18:41:17 processing 240000s line...\n",
      "18:41:25 processing 250000s line...\n",
      "18:41:33 processing 260000s line...\n",
      "18:41:42 processing 270000s line...\n"
     ]
    },
    {
     "ename": "IOError",
     "evalue": "CRC check failed 0x53eb3d85 != 0xf33a3631L",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mIOError\u001b[0m                                   Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-4-45a29b8aedb2>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0mi\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 6\u001b[1;33m \u001b[1;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mgzip\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'c:/tmp/out.json.gz'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'r'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      7\u001b[0m     \u001b[0mraw\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mline\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m     \u001b[0mtokens\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstrip\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mel\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mraw\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'source'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\soft\\anaconda\\2.0.1\\lib\\gzip.pyc\u001b[0m in \u001b[0;36mreadline\u001b[1;34m(self, size)\u001b[0m\n\u001b[0;32m    462\u001b[0m         \u001b[0mbufs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    463\u001b[0m         \u001b[1;32mwhile\u001b[0m \u001b[0msize\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 464\u001b[1;33m             \u001b[0mc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mreadsize\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    465\u001b[0m             \u001b[0mi\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'\\n'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    466\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\soft\\anaconda\\2.0.1\\lib\\gzip.pyc\u001b[0m in \u001b[0;36mread\u001b[1;34m(self, size)\u001b[0m\n\u001b[0;32m    266\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    267\u001b[0m                 \u001b[1;32mwhile\u001b[0m \u001b[0msize\u001b[0m \u001b[1;33m>\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextrasize\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 268\u001b[1;33m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_read\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mreadsize\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    269\u001b[0m                     \u001b[0mreadsize\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmax_read_chunk\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreadsize\u001b[0m \u001b[1;33m*\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    270\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mEOFError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\soft\\anaconda\\2.0.1\\lib\\gzip.pyc\u001b[0m in \u001b[0;36m_read\u001b[1;34m(self, size)\u001b[0m\n\u001b[0;32m    313\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mbuf\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m\"\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    314\u001b[0m             \u001b[0muncompress\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdecompress\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mflush\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 315\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_read_eof\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    316\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_add_read_data\u001b[0m\u001b[1;33m(\u001b[0m \u001b[0muncompress\u001b[0m \u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    317\u001b[0m             \u001b[1;32mraise\u001b[0m \u001b[0mEOFError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'Reached EOF'\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\soft\\anaconda\\2.0.1\\lib\\gzip.pyc\u001b[0m in \u001b[0;36m_read_eof\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    352\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mcrc32\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcrc\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    353\u001b[0m             raise IOError(\"CRC check failed %s != %s\" % (hex(crc32),\n\u001b[1;32m--> 354\u001b[1;33m                                                          hex(self.crc)))\n\u001b[0m\u001b[0;32m    355\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misize\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msize\u001b[0m \u001b[1;33m&\u001b[0m \u001b[1;36m0xffffffffL\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    356\u001b[0m             \u001b[1;32mraise\u001b[0m \u001b[0mIOError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"Incorrect length of data produced\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mIOError\u001b[0m: CRC check failed 0x53eb3d85 != 0xf33a3631L"
     ]
    }
   ],
   "source": [
    "code = []\n",
    "languages = []\n",
    "\n",
    "i = 0\n",
    "\n",
    "for line in gzip.open('c:/tmp/out.json.gz', mode='r'):\n",
    "    raw = json.loads(line)\n",
    "    tokens = [el.strip() for el in raw['source']]\n",
    "    tokens = {el for el in tokens if el and el in keywords}\n",
    "    if tokens:\n",
    "        code.append(tokens)\n",
    "        languages.append(raw['language'])\n",
    "\n",
    "    i = i + 1\n",
    "    if i % 10000 == 0:\n",
    "        print time.strftime('%H:%M:%S'), 'processing %ds line...' % i"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(u'GNU C++', 112994),\n",
       " (u'GNU C++11', 107595),\n",
       " (u'MS C++', 16066),\n",
       " (u'Java 8', 9585),\n",
       " (u'GNU C', 6287),\n",
       " (u'Java 7', 5545),\n",
       " (u'Python 3', 3192),\n",
       " (u'Python 2', 3173),\n",
       " (u'FPC', 3111),\n",
       " (u'MS C#', 1398),\n",
       " (u'GNU C11', 1097),\n",
       " (u'Delphi', 618),\n",
       " (u'PyPy 3', 472),\n",
       " (u'PyPy 2', 440),\n",
       " (u'Scala', 377),\n",
       " (u'Haskell', 367),\n",
       " (u'Ruby', 324),\n",
       " (u'JavaScript', 147),\n",
       " (u'PHP', 144),\n",
       " (u'Perl', 143),\n",
       " (u'Go', 143),\n",
       " (u'Mono C#', 128),\n",
       " (u'Ocaml', 63),\n",
       " (u'D', 34)]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(languages).most_common()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "pl_norm = {'GNU C++': u'C/C++', 'GNU C++11': u'C/C++', 'MS C++': u'C/C++', 'GNU C': u'C/C++', 'GNU C11': u'C/C++',\n",
    "           'Java 8': u'Java', 'Java 7': u'Java', \n",
    "           'Python 3': u'Python', 'Python 2': u'Python', 'PyPy 2': u'Python', 'PyPy 3': u'Python',\n",
    "           'FPC': u'Pascal', 'Delphi': u'Pascal',\n",
    "           'MS C#': u'C#', 'Mono C#': u'C#' }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(u'C/C++', 244039),\n",
       " (u'Java', 15130),\n",
       " (u'Python', 7277),\n",
       " (u'Pascal', 3729),\n",
       " (u'C#', 1526),\n",
       " (u'Scala', 377),\n",
       " (u'Haskell', 367),\n",
       " (u'Ruby', 324),\n",
       " (u'JavaScript', 147),\n",
       " (u'PHP', 144),\n",
       " (u'Perl', 143),\n",
       " (u'Go', 143),\n",
       " (u'Ocaml', 63),\n",
       " (u'D', 34)]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "languages_normalized = [pl_norm[l] if l in pl_norm else l for l in languages]\n",
    "freqs = Counter(languages_normalized).most_common()\n",
    "freqs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAagAAAFgCAYAAADuCe0ZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xm8JFV9/vHPwyCLggJCIOLAoIJKREUQ1OQXRlEcjQIu\nEYgLKi4RETUkisbA4E7UBMVdB0SDLIoiBoUBZBA1si8jO9ExMAoogoqiMPD8/jjVc2sud+7M3FtV\nvdzn/Xr1a7pOd59v9dzu/tY5deoc2SYiImLQrNXvHYiIiJhIElRERAykJKiIiBhISVARETGQkqAi\nImIgJUFFRMRAmjRBSZot6VxJV0n6iaSDq/L5km6WdFl1e17tNe+SdIOkayXtUSvfSdLi6rGP18rX\nlXRSVf5jSVvXHttf0vXV7VXNvvWIiBhkmuw6KElbAFvYvlzSBsAlwN7Ay4Df2/6Pcc/fHvgq8FRg\nS+BsYFvblnQhcJDtCyV9B/iE7TMkHQg8wfaBkvYBXmR7X0mbABcBO1XVXwLsZPvOBt9/REQMqElb\nULZvsX15df8u4BpK4gHQBC/ZCzjB9r22lwA3ArtK+ktgQ9sXVs/7MiXRAewJHFfdPwXYvbr/XGCh\n7TurpHQWMG8N319ERAyp1T4HJWkOsCPw46roLZKukLRA0kZV2SOAm2svu5mS0MaXL2Us0W0J3ARg\nexnwW0kPn6SuiIiYAdZenSdV3XtfB95q+y5JnwHeWz38PuBjwAHt7OIq9y1zNUVEDDHbE/XIrboF\nJelBlK63/7J9alXZba4AXwR2qZ6+FJhde/kjKS2fpdX98eW912xVxVobeJjt2yeoazYrtqhWeHNr\ncgOOWNPXTPXWVaxRizOK7yn/d8MRa9TiDPp7miz/rGoUn4AFwNW2j6qV/2XtaS8CFlf3TwP2lbSO\npG2AbYELbd8C/E7SrlWdrwS+VXvN/tX9lwLnVPcXAntI2kjSxsBzgDMn29+IiBgdq+ri+2vgFcCV\nki6ryt4N7CfpyYCBnwFvBLB9taSTgauBZcCB9vJhggcCXwLWB75j+4yqfAHwFUk3ALcD+1Z1/UbS\n+ygj+aBk5glH8E2lm0/S4ZM9vqrMHhER7Zo0Qdn+ARO3sr47yWs+CHxwgvJLgB0mKP8zZdj6RHUd\nCxw72T5Wz1z1U1awCJg7yeON5qZFTVY2g+J0GWvU4nQZq6s4XcYatThdxmo0jjzk60GV1lPT70Fp\nQUVEdECSV/Z7m6mOIiJiICVBRUTEQEqCioiIgZQEFRERAykJKiIiBlISVEREDKQkqIiIGEhJUBER\nMZCSoCIiYiAlQUVExEBKgoqIiIG0quU2Zks6V9JVkn4i6eCqfBNJZ0m6XtLC2oq6SHqXpBskXStp\nj1r5TpIWV499vFa+rqSTqvIfS9q69tj+VYzrJb2q2bceERGDbFUtqHuBt9v+K+BpwJslPR44FDjL\n9naU9ZsOBZC0PbAPsD0wD/h0tf4TwGeAA2xvC2wraV5VfgBwe1X+n8CRVV2bAIdRFkPcBTi8nggj\nImK0TZqgbN9i+/Lq/l3ANcCWwJ7AcdXTjgP2ru7vBZxg+17bS4AbgV2rBQ43tH1h9bwv115Tr+sU\nYPfq/nOBhbbvrNaBOouS9CIiYgZY7XNQkuYAOwIXAJvbvrV66FZg8+r+I1hxWfabKQltfPnSqpzq\n35sAbC8Dfivp4ZPUFRERM8CqVtQFQNIGlNbNW23/fqzXDmx7KivaNmt+7f5cJl+MMCIi+kXSXFbz\nR3qVCUrSgyjJ6Su2T62Kb5W0he1bqu6726rypcDs2ssfSWn5LK3ujy/vvWYr4BeS1gYeZvt2SUvH\nvYnZwPcm3sv5q3obERExAGwvorbyrqTDV/bcVY3iE7AAuNr2UbWHTgP2r+7vD5xaK99X0jqStgG2\nBS60fQvwO0m7VnW+EvjWBHW9lDLoAmAhsIekjSRtDDwHOHOy/Y2IiNEx6ZLvkv4G+D5wJWPrqr8L\nuBA4mdLyWQK8rBrIgKR3A68FllG6BM+syncCvgSsD3zHdm/I+rrAVyjnt24H9q0GWCDpNcC7q7jv\nt90bTFHfxyz5HhExpCZb8n3SBDUMkqAiIobXZAkqM0lERMRASoKKiIiBlAQVEREDKQkqIiIGUhJU\nREQMpCSoiIgYSElQERExkJKgIiJiICVBRUTEQEqCioiIgZQEFRERA2mVCUrSMZJulbS4VjZf0s2S\nLqtuz6s99i5JN0i6VtIetfKdJC2uHvt4rXxdSSdV5T+WtHXtsf0lXV/dXtXMW46IiGGwOi2oY3ng\nUusG/sP2jtXtuwCStgf2AbavXvNpja1u+BngANvbAttK6tV5AHB7Vf6fwJFVXZsAhwG7VLfDJW00\nxfcZERFDZpUJyvb5wB0TPDTR7LN7ASfYvrdaMuNGYNdqUcMNbV9YPe/LwN7V/T2B3jIapwC7V/ef\nCyy0fWe1lMdZPDBRRkTEiJrOOai3SLpC0oJay+YRjK2US3V/ywnKl1blVP/eBGB7GfBbSQ+fpK6I\niJgBVrnk+0p8Bnhvdf99wMcoXXV9Mr92fy6rudx9RER0TNJcVvNHekoJyvZttWBfBL5dbS4FZtee\n+khKy2dpdX98ee81WwG/kLQ28DDbt0tayopvYjbwvYn3aP5U3kZERHTM9iJgUW9b0uEre+6Uuviq\nc0o9LwJ6I/xOA/aVtI6kbYBtgQtt3wL8TtKu1aCJVwLfqr1m/+r+S4FzqvsLgT0kbSRpY+A5wJlT\n2d+IiBg+q2xBSToB2A3YVNJNwOHAXElPpozm+xnwRgDbV0s6GbgaWAYc6LE15Q8EvgSsD3zH9hlV\n+QLgK5JuAG4H9q3q+o2k9wEXVc87ohosERERM4DG8sdwkuSSJxutFdsTjVKMiIgGSfLKfm8zk0RE\nRAykJKiIiBhISVARETGQkqAiImIgJUFFRMRASoKKiIiBlAQVEREDKQkqIiIGUhJUREQMpCSoiIgY\nSElQERExkJKgIiJiIK0yQUk6RtKtkhbXyjaRdJak6yUtrK2oi6R3SbpB0rWS9qiV7yRpcfXYx2vl\n60o6qSr/saSta4/tX8W4XtKrmnnLERExDFanBXUsMG9c2aHAWba3o6zfdCiApO2BfYDtq9d8ulr/\nCcoqvAfY3hbYVlKvzgOA26vy/wSOrOraBDgM2KW6HV5PhBERMdpWmaBsnw/cMa54T+C46v5xwN7V\n/b2AE2zfa3sJcCOwa7XA4Ya2L6ye9+Xaa+p1nQLsXt1/LrDQ9p3VOlBn8cBEGRERI2qq56A2t31r\ndf9WYPPq/iMYW8qd6v6WE5Qvrcqp/r0JwPYy4LeSHj5JXRERMQOsckXdVbHtsmhgP82v3Z9b3SIi\nYtBImstq/khPNUHdKmkL27dU3Xe3VeVLgdm15z2S0vJZWt0fX957zVbALyStDTzM9u2Slo57E7OB\n7028O/On+DYiIqJLthcBi3rbkg5f2XOn2sV3GrB/dX9/4NRa+b6S1pG0DbAtcKHtW4DfSdq1GjTx\nSuBbE9T1UsqgC4CFwB6SNpK0MfAc4Mwp7m9ERAyZVbagJJ0A7AZsKukmysi6DwMnSzoAWAK8DMD2\n1ZJOBq4GlgEH2u51/x0IfAlYH/iO7TOq8gXAVyTdANwO7FvV9RtJ7wMuqp53RDVYIiIiZgCN5Y/h\nVM5/Nf0ehG2t+nkRETEdkryy39vMJBEREQMpCSoiIgZSElRERAykJKiIiBhISVARETGQkqAiImIg\nJUFFRMRASoKKiIiBlAQVEREDKQkqIiIGUhJUREQMpGklKElLJF0p6TJJF1Zlm0g6S9L1khbWl2mX\n9C5JN0i6VtIetfKdJC2uHvt4rXxdSSdV5T+WtPV09jciIobHdFtQBuba3tH2LlXZocBZtrejLJ1x\nKICk7YF9gO0pS7d/ulp6A+AzwAG2twW2ldRb2v0A4Paq/D+BI6e5vxERMSSa6OIbPwvtnsBx1f3j\ngL2r+3sBJ9i+1/YS4EZg12rBww1tX1g978u119TrOgXYvYH9jYiIIdBEC+psSRdLen1VtrntW6v7\ntwKbV/cfwdgqulT3t5ygfGlVTvXvTQC2lwG/lbTJNPc5IiKGwFSXfO/5a9u/lLQZcJaka+sP2nZZ\nrykiImLNTCtB2f5l9e+vJH0T2AW4VdIWtm+puu9uq56+FJhde/kjKS2npdX98eW912wF/ELS2sDD\nbP/mgXsyv3Z/bnWLiIhBI2kuq/kjPeUVdSU9GJhl+/eSHgIsBI4Ank0Z2HCkpEOBjWwfWg2S+Col\niW0JnA08pmplXQAcDFwInA58wvYZkg4EdrD9Jkn7Anvb3nfcfmRF3YiIITXZirrTaUFtDnyzGoi3\nNnC87YWSLgZOlnQAsAR4GYDtqyWdDFwNLAMO9Fh2PBD4ErA+8B3bZ1TlC4CvSLoBuB1YITlFRMTo\nmnILalCkBRURMbwma0FlJomIiBhISVARETGQkqAiImIgJUFFRMRASoKKiIiBlAQVEREDKQkqIiIG\nUhJUREQMpCSoiIgYSElQERExkKa73MaM0dayIZlSKSJiYklQa6T5Of8iImJiA9/FJ2mepGsl3SDp\nnc3UuqiZagYoVrXGysjE6TLWqMXpMlbe0+DH6TJW03EGOkFJmgV8EpgHbA/sJ+nx06950fSraDGW\nJK/pDTh3NZ7ThLkN1TNIsUYtTpexuorTZaxRi9NlrEbjDHSCoixueKPtJbbvBU4E9urzPnXEa3g7\nfBWPR0QMl0E/B7UlcFNt+2Zg1z7ty8iZaqtK0uGTPZ6BHxHRhIFesFDSS4B5tl9fbb8C2NX2W2rP\nGdw3EBERq9TGku9dWArMrm3PprSilsvRekTEaBr0c1AXA9tKmiNpHWAf4LQ+71NERHRgoFtQtpdJ\nOgg4E5gFLLB9TZ93KyIiOjDQ56AiImLmGugWVPSPpEMmedi2/6OznRkyknZikrH9ti/tcHeGlqRN\nbf+63/sRk5O0GYDtXzVd94xKUJJOsf2SjmL9BbBeb9v2/7VQ/+uBOYz9HW37tQ2F2JCJf2S1kvJp\nk/Ra28e0Ufe4OE8HPkG5+HsdSvfxXbYf2lCIjzH5/9EzG4qznKSDga/YvqPpusfFOdL2O1dVNs0Y\nLwSOAZZJug/Yx/YPm6q/FmfxJA/b9hNbiLkO8FjK5+O66vrOJuu/i5V/9tzUZ1ySKBdfHkT5/lD9\nrY4G3uuGuuZmVBefpMts79hyjD0pP1CPAG4Dtgausf1XDcf5H+D7wCXA/VWxbZ/SZJwuSNqX8l5O\n7/19JJ1je/eW4l0C7AucDOwMvAp4rO1D24jXBUkfoAwiupTy435mUz8S4+I84DskabHtHRqMsRj4\ne9vXStoV+Ijtv22q/lqcOdVdM8HEmLaXNBxvLnAc8POqaCtgf9vnNRmnC5L+CXge8AbbP6vKHgV8\nFjijqR6WkU9QkrZm7AP4Hcp/qig/5o22aqp4VwLPAs6yvaOkZwKvbLBl04tzue0nN1nnSuKsDxxA\naW2sT3V01uT7kfQ24G+BPSh/oyuA1wBPtn1XU3Fq8S6xvZOkK3tHyU3+f1bX703WxfeNJuJMEHct\nyv/hqymJ92TKwKL/baDuNwEHAo8G6vVtCPzQ9sunG6MWa4Uk2OaBpaS1Kd/Vxlu1E8S6FNjP9nXV\n9nbAibaf0lK8jSmX5izvKWuqe1nS5cBzxnfrVd19ZzX1XZoJXXzHMfZjsVW13dPGh/Je27+WtJak\nWbbPlfTxFuL8t6S/s316C3XXfQW4hjIf4hHAK6rtJp1q+yhJlwH/DDwJeAhwqqQH2d6t4Xh/kLQu\ncIWkfwduodmp5V/I5F18rSQo2/dLugW4FbgP2Bj4uqSzbf/LNKv/KvBd4MNAvTvvLtu3T7Pu8Tar\njtA1wXaj5z+rkcL3S9rI9p1N1bsSa/eSUxX7+ipBNk7S+ygHKj9lrIcFmvvNW3uic062f9Xkexr5\nFlRdR118ZwMvAj4EbErp5tvZ9jMajnMX8GDgHqDXj91YH3MtzuW2n9xrbUh6EPAD241NOSXpq5Rz\naY8D3gdcCfxnL14L/fRzKD/i6wBvBx4KfNr2jU3G6ZKkt1K6Km8Hvgh80/a9VavqBtuPbjDWTsDf\nUH74ftj0oA9J81kxwffOe/YS1BENxzsN2BE4C/hDVWzbBzcc51jKgcN/Ud7Ly4G1mu5dqWJdDzzB\n9j1N113Vv9Lf0iZ/Z2dCC6prewF/ovzwvZzy49foFwrA9gZN17kSvQ/4byXtQGltbNZkANv/ACDp\nKsrci88GtpL0A+ByyonYJuMtqe7eDcxvsu46SVsAHwC2tD1P0vbA020vaCHcJsCLbf+8Xli1ql7Y\nVBBJhwF/T2kFCjhW0tdtv6+pGLbnN1XXavpGdeslxbYGAr0JeDNwcFX/+cBnWogDcBWlBX1rS/U/\nUdLvV/LY+k0FmWktqNfYPrblGIdQ+pWXthmnirUX5dyNgfNsf7uFGK8HTgF2AL4EbAD8m+3PthDr\n+N65jKq7byfgKbYvbqj+TkdtSToDOBb411rr8zLbT2gyTi1eqy2bKsb1wBNt/6naXh+4wvZ2DcY4\nurY5fgBD4y2bKuaDga1sX9tC3XsDj7T9yWr7QsYO8t5h+2stxHwq8C3gJ8Cfq2Lb3rPpWG2aUS2o\ntpNTZUNgoaQ7KMuDfM1240cxkj4MPBU4nvIFPljSM2y/q8k4tr9Q3T0P2KbJunskbQtsPu5E+78C\nzwB+2WCoxloSq2lT2ydJOhSg6nJb1kagLlo2laWUI+Q/VdvrMW5+zAZcwlhiOgI4jLEk1cbIxD2B\njwDrAnMk7Qgc0eCP+Tsoo0Z71qEMYnkI5aCv8QQFfJlyvvAn1Eb5thCnXbZnzI0ypLOrWE+idO9c\nB5zTQv2LgVm17VnA4hbifBDYuLa9MfD+hmOcTjkqH1/+RODb/f7cTON9LQIeTmk1ATyN0tJtI9b1\nwHq17fWB61uI8y3gF5Qf1i9REtY3Kde/fKKFeJd18He6FNioHgv4SYP1Xzxu+1O1+xe09J4uavv/\nrYvbjGpBAW9jxVF8bbqNcr7mdho+Z1Mx5UvVG0G1Ee0cIT3f9ruXB7XvkPR3wHsajLG57SvHF9q+\nUlLjrbYOLtTtOQT4NvAoST+ifA5e2nCMni5aNlCS0Tdr24tq94fvCL241/ad5drT5e5f2ZOnYOP6\nhu031zbb+G0AOF/ShyiTa/e6+PCQzWIy0xJU6yQdCLwM+AtK0/11tq9uIdSHgEslLaq2dwPauNB0\nLUnrecVzDus0HGOjSR5bb5LHpuqTTHChbgtxfkP5uzyW0kV1HaVl3Zja+ZrfAldJWlhtPwe4sMlY\nALa/1HSdA+AqSS8H1q66mw8GftRg/RdIeoPtz9cLJf0jcEGDceqeQjlgeNq48tav92rSyA+SkHRu\nbXNnyhIeUE4YPquFeB+mDJK4vOm6J4j1CMp5KAMX2r6lhRjvBPakzE4gygW0p9k+ssEYJwLfm+AL\n/Hrg2bb3aSpWVW+rF+rW4lwK7Gn75mp7N0r3TmODJCS9mpXMhED5jDfSYyDpa7b/XtJPeGBLyW5w\ngIlWnK7nwcAfx8Vq+lKKB1N6BPaois4E3tc7KGug/s2BUyktmV4L5imUg6+92/jejoqZkKDmMPYF\nPh14fnUfNzyVybi4rc7FV8XYkrG5+HozPHy/hTjPA3rTDp1l+8yG69+C0m10D+UEOZQRfOsCL7Ld\n5EAJJH2f0sL4ImUQxi2U85NNt26eShlG/ALKD9KHgBfYvqnJOF2Q9Ajbv1CZmaX1aYG6UPUG/CPw\nGMq1d8e44WvuarFEmWHmryjf1atsf6+NWLWYL6B0Y9d/h97bZsymjXyCquvoQt2u5uI7kjL32tWU\ni/8AsN3oSDVJDwH+ZPs+SY+ldFd9t+kvcvUFfibwBFr+And5oa6kZwCfo1xz9QLbtzUdo4rzswmK\nbftRDcboZFqgWuJ4NGUw0ALbjY9+lHQy5aDoB5SZUn5u+61Nx+kHSZ+jnJN8FvAFygjPC2wf0Ncd\nW0MzLUF9w/aLW47R1Vx81wM72P7zKp88vTiXUq6t2Rj4IXARcI8bnHuta5I2AO62fV+1PQtY1/Yf\nJ3/latc//nq0x1NaanfS0rUokjatba5HGYzxcNv/1nCcc4CXuMVpgcYljucBS9pIHKpNclsl34va\nPoDtSu+91WaA2YAyievf9Hvf1sSMGiTRdnKqdDUX3/9SWgCtJijKQcwfJR1AaWX8u6QrWo7ZtnMo\nXZa9iWgfTDnv0NR0VB+boKzVI0E/cN2ko6qDi0YTFGUqoMXVYIxeQrebvXj28bXE8UXKQVEblrfK\nXObkaylMX9xd/fvH6lTA7cAWfdyfKRnpBCVpHrChx12pLemlwG9tn9VC2DskbUiZxuR4Sbcx9kM4\nbbVRW38ELq+OaOtXirdxlf3TKdM29boH1mo6RsfWdW2WdNu/r06UN8L2IlixpVbvHm0qTp1WXCRx\nLcqAoFkthOpiWqCuEsf46XrWr203PhijY/+tMpv5Rxg7r/uFSZ4/kEa6i6+69mTv8f3+KlPCf9v2\n+CGYTcR8COXoZS3Kj/rDgOPd0IzPtVFbsOKPQ28izUav86pGnh1CmTrnSEmPBt7aRiLsiqQfAgfb\nvqTa3hk42vbTG47TWfdodblB77OwDFgCfNS12bMbijNR9+h6tv8w+SvXKMZ9rDhyb33GWgTDnjg6\nJ2k9yt+o7dnaGzfqCeoS2zut5LGmF1mbbCXLPwM3Au+xfXZD8d5m+6hVlcUDVaPrTmRsGqUtgH3d\n0Jx/tTiXVech3wKs3+sebXq04EpiC3iZ7ZMarvfHlKH/d1XbG1IWR2x0tv6YHklvBr7qaoXlqjW1\nn+1P93fP1sywd9WsyoYqE3SuoCpr9AJQ2xvY3nCiG+UH8I1Ak+ei9p+g7NUN1g+U4fKSPirpO5LO\nrW6tDo9ti6RdJP2l7YsoAxdOpJyMP5Oybk4bMXvdo711uxr9zknaQNIhkj4t6cDq3OeLKLNZtzGQ\nZb3x3aOUc3gxWN7QS05QZoAB3tDH/ZmSUU9Q3wA+X3VLAMuP+D5HS4vGTcT2MttXUOYrmxZJ+1Wj\nxLaR9O3abRFj0x416XjgWuBRlKUpljB2sfOw+Rxj5+ueRpmQ9lPAHcDnV/aiaXgb8C7K2kxXVd2j\n567iNWvqy5SZ5q+kDPz4MWXo/D+0MVqQstjj8l6Jqnv07kmeH/2xlspaYMDyrtgHHKwPulHv4nsQ\nZQG81wG9C2W3AhZQuttauSivTdWFkttQLvo8lLGLJn8HXNn09SKSLrX9FK0468LFtnduMk4X6t1r\nkj4F/MrV2kNddb01bdzfZRal23Jr260kjQm6R/8S2Kfp7tGYHkkfpVyD+VnKb8Qbgf+zfUhfd2wN\njfQoPmAz24dKei/lanGAG5u63qUfXBak+7mkEygJ6Y5VvWaaegsW3qJyZfovGDf55RCZpbEVep/N\nil0ejX8XVGYTeQflav7eIm52s1Ns1S/Svk/S0raSUxXjIkmPp4xINHDdMB7ozQCHUQ7M30z5Oy2k\nzJwyVEY9QS2QtAmlW+UMylLlrazH0webAxdVI8WOoZyobqM5/H5JG1FG8h1NmXXh7S3E6cIJwHmS\nfk0ZJXY+0FuPqo0RTscDJ1GmOnoj5RzhrxqO0clQaUm7ADfZ/qXteyQ9BXgJsETSfNu/aSJOTE/V\na/QB4LWUXiMBsynnWNeidkAzDEa6iw+WT5sylzKVyV9TlhT/LuWq6sbnx+tS1ce8B+WHb2fK7NwL\nbP9vA3WPn6eslelmulYNWtgCWNgbGi1pO2ADN7wUwYh1j14G7G77N5L+lpJ4DwJ2BB5nu61lRGIN\nSDqKsur126sBLEh6KOXi8T+2MSNHm0a6BaWxlVq/S3WBpKRHAa8APitpU9u79HMfp8P2/ZJuocwr\ndx+l6+3rks62/S/TrP44Svfe+ZQJdrcHhurDPRHb/zNB2fUthRul7tG1aq2kfYDP2T4FOEXDP7PI\nKHkBsJ3t5etZ2f6dytIe1zFk3+GRTlDAUZRRVMvZ/qmkU4FdKBdRDiVJb6WsY3Q7pW/5n12WFF8L\nuAGYboKqTzezgPammxllHxih7tFOz9/FlN1fT0491fnJJhdh7MSof7AmW6l1ju17JnrRkNgEeHE1\naGK5qlXVxIzmozxPWSds9yaNvZPSzTzMuj5/F1NzjaT9x88oI+mVlMtFhspIn4OSdKPtx6zpY4Os\nq3NDmW5m6jQ2XyI8cDFBD+s0UV2ev4upkfRIyjWed7Pi2moPpqytdnO/9m0qRr0FdbEmXmr59Yz9\n8YZNJ+eGbLcx0ehMcQljiekIypDfXpIa2iPC+vk7jS3I+afqFgPA9s2SdmXFxRFPt31Of/dsaka9\nBdXpSq1d0AivYTOK1MEimV1SRwtyRsCIt6Bs36Kyoml9pdb/dstLLbcs54ain94PPJ1xC3L2eZ9i\nRI10goLS4Q98r7qNglFewyYGX1cLckaMfoIaNTk3NPi04tIr6487oBj2g4hWF+SMqBvpc1AR0SyV\nBTn/xNiCnA+lwQU5I+qSoCJitUk6BDjR9tJ+70uMvlFfDyoimrUhsFDSDyQdJGnzfu9QjK60oCJi\njUl6EvAy4KXAzbZ37/MuxQhKCyoipuI24BbKXJCb9XlfYkQlQUXEapN0oKRFwDnApsDrekuJRDQt\nw8wjYk1sBbzN9uX93pEYfTkHFRFrrDYXHwDDvvhnDKZ08UXEapO0p6QbgJ8B5wFLqBYDjWhaElRE\nrIneXHzX294G2B24oL+7FKMqCSoi1sS9tn8NLJ+LD9i53zsVoymDJCJiTWQuvuhMBklExGqr5uK7\nm7G5+B5G5uKLliRBRcQqjZuhfbw/AzcC77F9dnd7FaMuCSoipqVa2fmvgK9mZd1oUgZJRMS02F5m\n+wrg6H7vS4yWtKAiImIgpQUVEREDKQkqIiIGUhJUREQMpCSoiIgYSElQERExkJKgIiJiICVBRUTE\nQEqCioiIgZQEFRERAykJKiIiBlISVEREDKQkqIiIGEgDu6KuJAHvBzYELrb95T7vUkREdGiQW1B7\nA1sC9wAC0U0FAAAbIUlEQVQ393lfIiKiY50mKEnHSLpV0uJx5fMkXSvpBknvrIq3A35o+5+BN3W5\nnxER0X9dt6COBebVCyTNAj5ZlW8P7Cfp8ZRW053V0+7vcicjIqL/Ok1Qts8H7hhXvAtwo+0ltu8F\nTgT2Ar4BPFfSJ4BFXe5nRET03yAMktgSuKm2fTOwq+27gdet6sWSsiRwRMQQs62JygdhkEQTCeYI\n4Jm2tTo34IjVfe50b13FGrU4o/ie8n83HLFGLc6gvifgmdVv90oNQoJaCsyubc8mo/YiIma8QUhQ\nFwPbSpojaR1gH+C0Pu9TRET0WdfDzE8AfgRsJ+kmSa+xvQw4CDgTuBo4yfY1Le/Kopbr70esUYvT\nZaxRi9NlrK7idBlr1OJ0GavROLKHe4yBJFf9mRERMWQm+w0fhFF80yZpPrDI9qI+70pERKwGSXOB\nuZM+Jy2oiIjol7SgIiJioKQFFRERA22y3/BBGGYeERHxAOnii4iIzs2YLr426k23YURE+0Z+kEQz\n0/nVJTdFRPTbiCSo+ZSW4ty+7kVERKyeGdTF13wLKl18ERHtG8pRfJLmSjpf0mck7dbv/YmIiG4N\nbIKiLPP+e2BdsvxGRMSM0/Vs5sdIulXS4nHl8yRdK+kGSe+sis+3/XzgUFaxqFVERIyerltQxwLz\n6gWSZgGfrMq3B/aT9HiPnRy7k9KKioiIGaTTUXy2z5c0Z1zxLsCNtpcASDoR2EvS44DnAhsBR09e\n8/za/blkNF9ExGBandF7PYMwzHxL4Kba9s3ArrY/DHxz9auZSxJTRMRgq2b8WbQ6iWoQBkkM9zj3\niIhoxSC0oJYCs2vbs1njUXvzm9ubiIhoXa0ldfjKnjMILaiLgW0lzZG0DrAPcNqaVTEfWNT0fkVE\nREuqa13nT/acroeZnwD8CNhO0k2SXmN7GXAQcCZwNXCS7Wu63K+IiBg8mepo4loz1VFERAdmwGzm\n88kovoiI4ZHJYqdea1pQEREdSAsqIiIGSlpQU681LaiIiA6kBRUREQMlLaip15oWVEREB4ZywcKI\niJjZkqAiImIg5RxURER0bujPQUl6CGWSvfm2T1/Jc3IOKiJiSA3zKL53ACf1eyeglwibl0QYETGx\nrieLPUbSrZIWjyufJ+laSTdIemdV9hzK5LG/6nIfJ+eGbxERsTKddvFJ+n/AXcCXbe9Qlc0CrgOe\nTVkb6iJgP+DlwEOA7YG7gRd5gp3tqosvXYkREc0bmC4+2+dLmjOueBfgRttLACSdCOxl+z3V9v7A\nryZKThERMboG4RzUlsBNte2bgV17G7aPW3UV82v355LRfBERg2l1Ru/1DEKCaqhlNJckpoiIwVZb\n6n0uq/jRHoQLdZcCs2vbsymtqIiImMEGoQV1MbBtdW7qF8A+lEESM1aGtEdEdD+K7wRgN+DhwG3A\nYbaPlfQ84ChgFrDA9ofWoM6RG8WXEYMRMVNMNopvoGeSWB3lx/xwmj0HlQQVEdGm2jmowzObeURE\nDJURaUGli2+qsSIi+mlgLtRtz3wyzDwiYngM/WzmqyMtqKnHymjBiOi3GdCCiqlrPhFGRDRhRBLU\nfNLFFxExPNLFN/VaZ1AXXwZjRET/TNbFl2HmERExkNLFFxERnUsX39RrTRdfg3EiIlZmKLv4JD1O\n0mcknSzpgH7vT0REdGvgW1CS1gJOtP2ylTw+cq2N0X1PzUtrLWK4DUwLStIxkm6VtHhc+TxJ10q6\nQdI7a+UvBE4HTuxyP6MtbvgWEaOs6+U2/h9wF/Bl2ztUZbOA64BnUxYvvAjYz/Y1tdd9y/ZeK6lz\nRFsbeU9TjRURw2NgZpKwfX61MGHdLsCNtpcASDoR2EvSXwAvBtYDzu1wNyMiYgAMwjDzLYGbats3\nA7vaPg84b/WqmAvMqW5zyXDziIjBVBtePqe6rdQgJKgG+n0WTb+KiIhone1F1H60JxtANQgJaikw\nu7Y9m9KKWgPzScspImJ4rM6FuoNwHdTFwLaS5khaB9gHOK3P+xQREX3W9TDzE4AfAdtJuknSa2wv\nAw4CzgSuBk6qj+CLiIiZaeAv1F2VDMmeeqxRfE8RMVwGZph5e+aTc1AREcMjk8VOvdYZ0doYxfcU\nEcMlLaiYMbqa8y9zC0ZMT1pQU691RrQ28p4GP07EqEsLKmKIpbUWoygtqKnXmtZGg3G6jDVqcbqO\nFdG1gVluIyIiYnUlQUVExEDKOaiIiOjc0J+DkrQX8HfAQ4EFts+a4Dk55zDFWHlPgx+n61gRXZvs\nHNRAJ6geSRsBH7X9ugkeyw/SFGPlPQ1+nK5jRXRtoIaZSzqG0iq6rbfse1U+DzgKmAV80faRtZe9\nB/hkpzsaMcMM+0XOXcbKhdvd6McgiWOBefUCSbMoCWgesD2wn6THqzgS+K7ty7vf1YiZxg3fuorT\nZax+x5k5Om9B2T5f0pxxxbsAN9peAiDpRGAv4NnA7sBDJT3G9uc63NWIiOijQRnFtyVwU237ZmBX\n228Bjl71y+fX7s8lo/kiIgbT6oze6xmUBNVAe3YuSUwREYPN9iJg0bAs+Q6wFJhd255NaUVFRMQM\nNSgJ6mJgW0lzJK0D7AOc1ud9ioiIPur8OihJJwC7AQ8HbgMOs32spOcxNsx8ge0PrWZ9ue5lirHy\nngY/TpexhjtOl7EG4fPQvH4NaR+o66Bs77eS8u8C351arfPJOaiImDmaT4ZdG6ZzUBERESsYiqmO\nJjO6Tfi8p6nEGrU4XcYa7jhdxpoZn4euDFQXXzvmky6+iIjhMfSzma+OHCFNPVbe0+DH6TLWcMfp\nMtbM+Dx0ZQa0oCIiokmDMFpwRBLUfNLFFxHRtPZGC6aLb+q1zogmfN7T4MfpMtZwx+kyVj4PTcdZ\nWasqw8wjImIgpYsvIiI6ly6+qdeaJnyDcbqMNWpxuow13HG6jJXPQ9Nxhq6LT9I2kr4o6Wv93peI\niOjewCYo2z+z/bp2al/UTrV9jTVqcbqMNWpxuozVVZwuY41anC5jNRun0wQl6RhJt0paPK58nqRr\nJd0g6Z3t78mi9kN0HmvU4nQZa9TidBmrqzhdxhq1OF3GajZO1y2oY4F59QJJs4BPVuXbA/tJenzH\n+xUREQOm0wRl+3zgjnHFuwA32l5i+17gRGAvSZtI+izw5G5aVRERMUj6sWDhHODbtneotl8KPNf2\n66vtVwC72n7LatY33MMQIyJmuEGei29aCaZfExxGRES7BmEU31Jgdm17NnBzn/YlIiIGxCAkqIuB\nbSXNkbQOsA9wWp/3KSIi+qzrYeYnAD8CtpN0k6TX2F4GHAScCVwNnGT7mi73KyIiBs/QT3U0qCT9\nBbBeb9v2/7VQ/+uBOYydS7Tt1zZU/yGTPGzb/9FEnHExX2v7mKbr7ZqknZjk3KrtS1uIeTDwFdvj\nR8kOLUmb2v51i/UvnuRh235iCzHXAR5L+XxcV41cHmqSNgOw/aum6x6EQRKdkXSK7Ze0HGNP4GPA\nI4DbgK2Ba4C/ajjUt4DvA2cB91dlTR5tbLiS+tRwHCTtS3kvbwGOqcrOsb17k3Fq8Z4OfIJy3d06\nwCzgLtsPbSjEx5j8/+iZDcWp2xy4SNKllP/DM93C0aekI22/c1Vl04zxQsp7WCbpPmAf2z9sqv6a\nF1b/mvpCRS2pJkc9Dvh5VbSVpP1tn9dgjLtY+WfPTX3GJQk4nNL7Nasquw84GnhvY5892zPmBlzW\nQYwrgU17sSg/Rse0EOfyfv9/Nvhe3gZ8A7gLOBn4V+BGYIOW4l0CbAtcVn25XgN8uN//Dw28r7Uo\nF7yfWP3/fRB4dMMxHvAdAhY3HGMx8Ljq/q7A91v8P1sbOLejv8+lwGNr29sBl/b7czPF9/JPlIPj\nbWpljwIWAv/UVJyRb0FJ2pqxI6R1JG1V3bcb7nar3Gv715LWkjTL9rmSPt5CnP+W9He2T2+h7uUk\nrQ8cQGltrE91dOaGuhIrp9o+StJlwD8DTwIeApwq6UG2d2swFgC2b6j+PvcBx0q6HDi0ibolvYTJ\nu/i+0UScCeq9X9ItwK3AfcDGwNclnW37X6ZTt6Q3AQcCjx7XNbYh0HTrZpntawFsXyBpw4brX872\nMkn3S9rI9p1txamsbfu6WuzrJbX2GyxpY8qo6OUx3Fz38quA57jWrWf7p5JeTklcjZwCGPkERWlS\n934stqq2e9roarmj+kKdDxwv6TZKy6BpbwPeLekeoNePbTfXTdXzFUoX5TzgCOAV1XaTPlhdwL01\n8BJKK/RXtp8t6UENxwL4g6R1gSsk/TtwC8128byQybv4Gk9Qkt5K+dG4Hfgi8M+275W0FnADMK0E\nBXwV+C7wYaDenXeX7dunWfd4m0n6J8b+JvVtu/nzn38AFks6q7pPFefghuNcIumLwH9R3svLKaOY\nGyfpfcCrgZ8ydgoAmvvNW9sTnHOy/asmk+6MGiQh6TLbO7Yc4yHAnyjdLS8HHgoc38KXuBOSLrf9\nZElX2n5ilTB+YHvXFmJdRenX3gl4E/ATSlfmQQ3HmUNpZawDvJ3yN/q07RubjNMlSUdQupJ/PsFj\n29u+usFYOwF/Q/nh+2GDR+W9+uezYoLvnffsJagjGo736upuL2YvznETv2LKcdYD3gz8dRXrfOAz\ntv/cZJwq1vXAE2zf03TdVf0r/S1t8nc2Car5GIcAJ9pe2macKtZewN9SPuzn2f52CzEutL2LpPMp\nXTy3ABfYflQLsY63/fLq/mWURPUU260cZbZN0hbAB4Atbc+TtD3wdNsLWorXauKoYhwG/D2lFShg\nL+Drtt/XdKwuSXowsFWva7HhuvcGHmn7k9X2hcBm1cPvsN34mneSvgn8o+1bm667qv8+4I8reXh9\n2420omZagnqN7WNbjjGf8gW+g3Ky+mttfEgkfRh4KnA85YdiX+Bi2+9qOM7rgVOAHYAvARsA/2b7\nsw3G2BbY3PYPamXPB34H/NL2/zYUp9NhxZLOoMzg/6+11udltp/QZJwqVieJozoyf6LtP1Xb6wNX\n2N6uwRhH1zbHj7BrvOutGnn7EWBd23Mk7QgcYXvPhur/EbBv75x3db5zd8p51i/ZflYTccbFfCpl\npO9PgF4LzU29p67MqATVJUlPAl4GvBS42Q0Pma5+bJ9cneTvLVtyuatJeIeJpNOBd9m+clz5E4EP\n2H7hxK9c4zhzJnvc9pIm4tTiXWx753rLvddl2mScqt7WE0dV77nAi11db1WdiD+lyR/Zqsutl5iO\nAA5jLEm10fV2KfAsymi+3t/pJ00dSPQ+B7XtT9l+c3X/gpa6y68BPkNJUMsvQ3GDQ9q7MBMGSSxX\nXXPQ6Id7ErdRusNuZ6w53yQDG1X1U91v47qXDwIfGfeDdIjt9zQYZvPxyQnA9pWStmkqSNMJaDXc\nJenhvQ1JTwN+21KspZRRln+qttejnTktfwdcJWlhtf0c4MKq1dNI68b2l3r3Jb21g+/svbbvLJf2\nLHf/yp48BRvXN3rJqdLGbwOUwSufaKnuzsyoBEUZ+dbqh13SgZSW018AXwNe1+QJ6poPAZdKWlRt\n70ZDw6THeb7td/c2bN8h6e+AJhPURpM8tt4kj02J2r9Qt+cQ4NvAo6puns0oLerG1LrDfssEiaPJ\nWJVvVreeRbX7w9odc1U1PHrtqrv5YMqUbE25QNIbbH++XijpH4ELGoxTd76kD1HmNV0+CKON85Jt\nmmkJqgtbAW+zfXmbQWyfIOk8ynkoA++0fUsLodaStN64rqN1Go5x8Uq+wK+nXFTbtE9SztmdDOxM\nGZ792Bbi/IZy4PBYShfVdZRrvJp0CeXvfwlwaq18ES0kjHrrZoQcRDng+jNwAmVe0CbP3b2dck3f\nP1Au1gV4CuXga+8G49Q9hfL3f9q48jYurWnNyJ+DqvrMe3Zm7LoDt3Fysha31bn4qhhbMjYXX+8C\n2u83HOOdwJ6UqWdEmXXhNNtHNhhjC8pR+T2MJaSdgHWBF9n+ZVOxqniX2N6pN3S+Kmv83FB1bmNP\n2zdX27sBn2pjkETbJH3N9t9L+gkPTHyNDjDRitP1PJgVR4u5qZZudbD1j8BjKNfeHeOW5sZT6T98\nFmXKMwNX2f5eG7FGyUxIUHMYO+F6OvD86n4r5yS0krn4bDc6F5+kIylLk1xNmTUAgKYGFIyL9TzK\nqCOAs2yf2UIMUY7unkDLX2BJ36d0gX0R+CXlXOH+thtt3VQjqT4DvIByRPsh4AW2b2oyThXrZxMU\nu6nLASQ9wvYvVGZmecBFzX04vzdtkk6mHBT9gHIh+s9tv7W/e9UcSS+gdGPXD5Tf2789WnMjn6Dq\nOroO6krKkdJZtneU9EzglW52aqDeqK0d3MJFfuPiPAT4k+37JD2W0l313baONLvQ5YW6kp4BfA64\nm5Kcbms6RhVn09rmepRzXQ+3/W8Nxlib8rlutZuo1rJ5NGVevgUuy/I0HWdxb9Rr9d4uavv3oSuS\nPkcZNPMs4AuUSxAusH1AX3dsDc20c1ATHWU2rau5+P6X8gPbaoKiXO3+N9XovTOBiygtt5e3HLdN\nvwbusX03ML8aor9uU5VLGn/B9PrAncACSa1ci+IHLktxVNXF2FiCcnfz1h3HWMvm+ZRWQBstm+VJ\nr3pvLYTom2fY3qHqxj5C0seAM/q9U2tqRiUo2y/uIEyrc/HVRm39Ebhc0jmseCFe0/OHyfYfJR1A\naWX8u6QrGo7RtXMoXZa9v8uDKcn3GQ3V/7EJylrtqtCKa1CtRTnfOquFUL156xYydm6o6c/d42st\nmy9SDora8ERJv69tr1/bbuxcV5/cXf37x+pc9e3AFn3cnykZ6QQlaR6wocdNJSLppcBvbZ/VQti9\nKB+Ot1FaGQ+jXGzYlN6oLShDmFeYP6zBOMtVw7JfTpnVHDpeibkF69peftBg+/cqU900wvYiAEkb\nAHeP7x5tKs449TWolgFLKJc7NO0b1a3Nz10nLRvbbSTwQfHfVa/HRxgbePSFPu7PlIz0Oajq2pO9\nx/f7q6wA+W3b44dgTifWZAuF/ZmyPs97bJ/dULy32T5qVWUNxNmNcj3PD20fKenRwFtbaKl1RtIP\ngYNtX1Jt7wwcbfvpDce5lDI33saUJSkuonQttt49Wg06eZntkxqud3nSrbZnAevZ/sPkr1yjGOPn\neVufsRbBsLdsOqcySe16LXfLtmLUE9QltndayWPLT5B2sB9rU4aXfrWp0XwTDfhoY6j0KKpG151I\nGcEHpetjXzc8KW3vbyTpLZQJNP9d0hVNjhasEsYbKQMKfgJ8ltKK/wBwY9PnuyT9GHh2rwVadWef\nabup7tFogKQ3U35v6jPA7Gf70/3dszUz0l18wIYqC96tMOJMZdLOxmcoWJlqBNIVWnESzCmRtB/w\nD8A2407Gb8jYtEeNqa7negdjCxZCy9eQtUXSLsBNti+S9HjgDcCLKeefftpSzLa7R79MmX7ox5Sh\n86+mTHf0Dy1dLL5em92j0Zg32P5Ub8NlBpg3AElQA+QbwOclvWXcEd/HaWHRuFVxMzOA/4hy5L8p\n8FHGrkn5HeViw6YdD5xEuZbnjZQfwAcsVDYkPsfY9VxPoywtfxCwI/B5Gp6GiHIe8l3AN21fVXWP\nnruK16ypx9QuNv4C5bOxdTVCsQ1/kLTTuO7RtmLF1K0laS3b98Pyrtg2Fv9s1ah38T2IMmXJ64De\nTA5bAQso54OG+Vqeg4Gv9JrwLca51PZTxs26sMLszMOi3r0m6VOUVXvnj39smIzv6m37Wr8Jukf/\nEtin6e7RmB5JH6VMEvBZykHsG4H/s31IX3dsDY16C2oz24dKei9lOhMo/fIrW2hrmGwOXFSdiD+G\nch6gjaON3oqct1RXpv+CcbMzD5FZtS7fZ1O6+Hoa/y501D3a6VDpWvfoYymDgq4b5gO9EXYY5cD8\nzZS/00LKzClDZdQT1AJJm1C6Vc6gLFXe+BXp/WD7XyX9G7AHpdvtk9XULQvc0AJ/lfdL2ogyku9o\nyqwLb2+w/i6dAJwn6deUUWLnA6jMYN3GCKfWu0e7GipdO3/3S9v3SHoK8BJgiaT5tn/TxX7E5Kpe\now8Ar6X0GgmYTTnHuha1adGGwUh38cHyaVPmUuba+mvgJsq1KGe4hQlcuybpyZQJXOcB36OcWznb\n9r9Ms97xE2m2Mt1M16pBC1sAC3tDoyVtB2zghpciGLHu0cuA3W3/RtLfUhJv7/zd42w3ff4upkDS\nUZRVr99u+/dV2UMp18n90UM21+BIJyhNvJT4o4BXUH7IN7W9S7/2bzokvZWyTMTtlKb7N23fK2kt\n4Abbj55m/b2JNM+nTDezZNg+3P0m6ce2n1bNuvAJSvfo16b7t+mHUTx/N4ok3Qhs1xscUSufRemO\nfczErxxMo97FdxRlFNVytn8q6VRgF8pFlMNqE8rS2z+vF9q+X1ITM5rXp5tZQHvTzYyyD4xQ92in\n5+9iyu4fn5wAqtlMmlwluBOj/sGabCnxObbvmehFg6zW9bYpME/SA7re3MwKvqM8kWYnbPeuU7uT\n0s08zLo+fxdTc42k/W2vsHK4pFcC1/Zpn6Zs1Lv4blxZk3ayxwZZV11vmW5m6sZdkN1bi2z59rBO\nE9Xl+buYGkmPpFzjeTcrLv75YMrinzf3a9+mYtRbUF0vJd6FTrreuhodNqJ6E/qKMlHwYYwlqaE9\nIrT9P737Glsx+k/VLQaA7Zsl7cqKq/eebvuc/u7Z1Ix6C6rTpcS70PWFmTE9o/b3UUcrRkfAiCco\nWD6rcydLiXchXW/DZQQTVCcrRkfA6HfxUc2u8L3qNvTS9RZ91tWK0RGjn6AiuqYV1warTz0Ew9/K\nbXXF6Ii6ke/ii4jmSHoIZVDEWpRlRB4KHG+78aVeIpKgImK1SToEONH20n7vS4y+phdPi4jRtiGw\nUNIPJB0kafN+71CMrrSgImKNSXoS8DLKIo832959FS+JWGNpQUXEVNwG3EKZrHizPu9LjKgkqIhY\nbZIOlLQIOIcyH+TrekuJRDQtw8wjYk1sBbzN9uX93pEYfTkHFRFrrDYXHwCjsPhnDJ508UXEapO0\np6QbgJ8B5wFLKCtURzQuCSoi1sT7gacD19veBtgduKC/uxSjKgkqItbEvbZ/DSyfiw/Yud87FaMp\ngyQiYk1kLr7oTAZJRMRqq+biu5uxufgeRubii5YkQUXEKo2boX28PwM3Au+xfXZ3exWjLgkqIqZF\n0tqU5cW/mpV1o0kZJBER02J7me0rgKP7vS8xWtKCioiIgZQWVEREDKQkqIiIGEhJUBERMZCSoCIi\nYiD9f/uNRKjIbxExAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x53c90240>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "langs, freqs = zip(*freqs)\n",
    "\n",
    "plt.figure(figsize=(6, 5))\n",
    "\n",
    "plt.subplot(2, 1, 1)\n",
    "plt.bar(range(len(langs)), freqs)\n",
    "plt.xticks(np.arange(len(langs)) + 0.5, langs, rotation='vertical')\n",
    "\n",
    "\n",
    "plt.subplot(2, 1, 2)\n",
    "plt.bar(range(len(langs)), freqs, log='true')\n",
    "plt.xticks(np.arange(len(langs)) + 0.5, langs, rotation='vertical')\n",
    "\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Most common\n",
      "[(u'=', 270969), (u'int', 266348), (u'<', 265763), (u'+', 264083), (u'}', 263338), (u'{', 263139), (u'>', 256898), (u'for', 247814), (u'i', 246505), (u'if', 242464), (u'std', 230431), (u'using', 230037), (u'namespace', 228943), (u'return', 219990), (u'-', 206954), (u'&', 176880), (u'a', 159431), (u'*', 158142), (u'#include', 145390), (u'long', 140629), (u'else', 134176), (u'x', 133884), (u'while', 128018), (u'vector', 124122), (u'printf', 100919), (u'b', 100296), (u'bits', 89250), (u'void', 78475), (u'const', 77856), (u'string', 76437), (u'bool', 75279), (u'size', 74457), (u'map', 73524), (u'm', 73000), (u'typedef', 69420), (u'set', 62022), (u'end', 61699), (u'false', 61470), (u'second', 61146), (u'first', 60624), (u'h', 59481), (u'queue', 59430), (u'c', 59295), (u'begin', 59285), (u'p', 58742), (u'y', 58300), (u's', 56589), (u'double', 56526), (u'break', 53990), (u'r', 53905)]\n",
      "\n",
      "Least common\n",
      "[(u'implement', 1), (u'.err', 1), (u'IntOp', 1), (u'sort_asc', 1), (u'c11', 1), (u'stored', 1), (u'das', 1), (u'getVolume', 1), (u'cmove', 1), (u'rename', 1), (u'vspace', 1), (u'corresponding', 1), (u'disconnect', 1), (u'btc', 1), (u'frame', 1), (u'scrolling', 1), (u'EXT', 1), (u'clog', 1), (u'_height', 1), (u'mkdir', 1), (u'category', 1), (u'sword', 1), (u'dget', 1), (u'%8', 1), (u'lgt', 1), (u'exports', 1), (u'try_run', 1), (u'named', 1), (u'receive', 1), (u'languages', 1), (u'excludes', 1), (u'nal', 1), (u'pwd', 1), (u'int4', 1), (u'isFinite', 1), (u'<=', 1), (u'array_flip', 1), (u'shutdown', 1), (u'spacing', 1), (u'missing', 1), (u'aas', 1), (u'cdq', 1), (u'session', 1), (u'CLASS', 1), (u'aad', 1), (u'myclass', 1), (u'$$', 1), (u'asa', 1), (u'asr', 1), (u'bless', 1)]\n"
     ]
    }
   ],
   "source": [
    "global_frequency = Counter()\n",
    "\n",
    "for c in code: \n",
    "    global_frequency.update(c)\n",
    "\n",
    "print 'Most common'\n",
    "print global_frequency.most_common(50)\n",
    "print \n",
    "\n",
    "print 'Least common'\n",
    "print global_frequency.most_common()[::-1][:50]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1786"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(global_frequency)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's remove some tokens that don't apear frequently enough (say <= 30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "for cnt in code:\n",
    "    for c in list(cnt):\n",
    "        if global_frequency[c] <= 30:\n",
    "            cnt.remove(c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1075"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "global_frequency = Counter()\n",
    "\n",
    "for c in code: \n",
    "    global_frequency.update(c)\n",
    "\n",
    "len(global_frequency)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = pd.DataFrame(data={'code_bow': code, 'language': languages_normalized})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "bow_total = []\n",
    "for lang, group in df.groupby('language'): \n",
    "    bows = Counter()\n",
    "\n",
    "    for c in group['code_bow'][:50]: \n",
    "        bows.update(c)\n",
    "\n",
    "    bow_total.extend(bows.most_common(50))\n",
    "\n",
    "del bows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from wordcloud import WordCloud\n",
    "from scipy.misc import imread"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\soft\\anaconda\\2.0.1\\lib\\site-packages\\wordcloud\\wordcloud.py:256: UserWarning: mask image should be unsigned byte between 0 and 255. Got a float array\n",
      "  warnings.warn(\"mask image should be unsigned byte between 0 and\"\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsEAAAHfCAYAAACxhQUCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/w+lhQSOTsbhygAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x53fe6cc0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "mask = imread('c:/tmp/ellipse.png', flatten=True)\n",
    "\n",
    "wc = WordCloud(background_color='white', mask=mask, font_path='c:/tmp/consola.ttf')\n",
    "wc.generate_from_frequencies(bow_total)\n",
    "\n",
    "plt.figure(figsize=(6 * 2, 4 * 2))\n",
    "plt.imshow(wc)\n",
    "plt.axis('off')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Let's build a classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.cross_validation import StratifiedKFold, StratifiedShuffleSplit\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def unwrap_set(s):\n",
    "    return list(s)\n",
    "\n",
    "vectorizer = CountVectorizer(analyzer=unwrap_set)\n",
    "X = vectorizer.fit_transform(code)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(273443, 1075)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, train a model C/C++ vs rest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({'C/C++': 244039, 'OTHER': 29404})"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c_not_c = np.where(df.language == 'C/C++', 'C/C++', 'OTHER')\n",
    "Counter(c_not_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "done in 2.018000s\n",
      "done in 1.847000s\n",
      "done in 1.826000s\n",
      "done in 1.885000s\n",
      "done in 1.882000s\n",
      "done in 1.946000s\n",
      "done in 1.949000s\n",
      "done in 1.913000s\n",
      "done in 1.970000s\n",
      "done in 1.882000s\n",
      "0.995918627319 0.00089198819262\n"
     ]
    }
   ],
   "source": [
    "skf = StratifiedKFold(c_not_c, 10)\n",
    "out_of_fold_pred = c_not_c.copy()\n",
    "\n",
    "aucs = []\n",
    "for i, (train, test) in enumerate(skf):\n",
    "    t0 = time.time()\n",
    "\n",
    "    y_train = c_not_c[train]\n",
    "    y_test = c_not_c[test]\n",
    "    X_train = X[train]\n",
    "    X_test = X[test]\n",
    "\n",
    "    dt = DecisionTreeClassifier(max_depth=3)\n",
    "    dt.fit(X_train, y_train)\n",
    "\n",
    "    pred = dt.predict(X_test)\n",
    "    out_of_fold_pred[test] = pred\n",
    "\n",
    "    y_pred = dt.predict_proba(X_test)\n",
    "    auc = roc_auc_score(y_test == 'C/C++', y_pred[:, 0])\n",
    "    aucs.append(auc)\n",
    "\n",
    "    print \"done in %fs\" % (time.time() - t0)\n",
    "\n",
    "print np.mean(aucs), np.std(aucs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>243367</td>\n",
       "      <td>672</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>236</td>\n",
       "      <td>29168</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        0      1\n",
       "0  243367    672\n",
       "1     236  29168"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(confusion_matrix(c_not_c, out_of_fold_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's see what is misclassified"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Java: 0.08%\n",
      "D: 2.94%\n",
      "C/C++: 0.28%\n",
      "Python: 1.15%\n",
      "JavaScript: 2.04%\n",
      "Ocaml: 71.43%\n",
      "Perl: 2.10%\n",
      "C#: 1.83%\n",
      "Pascal: 0.78%\n",
      "Haskell: 1.09%\n",
      "Go: 13.29%\n",
      "PHP: 2.08%\n",
      "Ruby: 1.54%\n"
     ]
    }
   ],
   "source": [
    "totl = Counter(languages_normalized)\n",
    "\n",
    "for l, c in Counter(df.language[c_not_c != out_of_fold_pred]).items():\n",
    "    print '%s: %0.2f%%' % (l, c * 100.0 / totl[l])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Almost all Ocaml sumbissions are misclassified, and ~ 13% of Go. The rest seems fine. Will use this model for further analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(29404, 1075)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_not_c = X[np.where(df.language != 'C/C++')]\n",
    "lang_not_c = df.language[df.language != 'C/C++']\n",
    "lang_not_c = np.array(lang_not_c)\n",
    "y_dummies = pd.get_dummies(lang_not_c)\n",
    "X_not_c.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's reduce dimensionality with one-vs-all LASSO SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from sklearn.svm import LinearSVC\n",
    "from sklearn.feature_selection import SelectFromModel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(29404, 94)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lsvc = LinearSVC(C=0.01, penalty=\"l1\", dual=False).fit(X_not_c, lang_not_c)\n",
    "selection_model = SelectFromModel(lsvc, prefit=True)\n",
    "X_new = selection_model.transform(X_not_c)\n",
    "X_new.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Important features:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([u'$', u'&', u'*', u'+', u'-', u'<', u'=', u'>', u'?', u'@',\n",
       "       u'Array', u'String', u'System', u'Var', u'\\\\', u'_', u'a', u'and',\n",
       "       u'args', u'begin', u'boolean', u'chomp', u'class', u'close',\n",
       "       u'conv', u'count', u'def', u'div', u'do', u'echo', u'else', u'end',\n",
       "       u'explode', u'extends', u'fmt', u'for', u'fun', u'func',\n",
       "       u'function', u'gets', u'i', u'if', u'import', u'in', u'inc',\n",
       "       u'input', u'int', u'integer', u'io', u'java', u'join', u'len',\n",
       "       u'length', u'let', u'map', u'namespace', u'new', u'object', u'of',\n",
       "       u'out', u'p', u'parseInt', u'print', u'printf', u'public', u'puts',\n",
       "       u'range', u'read', u'readline', u'return', u's', u'show', u'solve',\n",
       "       u'split', u'static', u'std', u'stdin', u'string', u'then',\n",
       "       u'throws', u'to', u'trim', u'using', u'val', u'var', u'vector',\n",
       "       u'void', u'where', u'while', u'words', u'write', u'x', u'{', u'}'], \n",
       "      dtype='<U12')"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(vectorizer.get_feature_names())[selection_model._get_support_mask()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "done in 7.863000s\n",
      "done in 8.281000s\n",
      "done in 8.332000s\n",
      "done in 7.611000s\n",
      "done in 8.565000s\n",
      "0.975321149448 0.0137730002439\n"
     ]
    }
   ],
   "source": [
    "skf = StratifiedKFold(lang_not_c, 5)\n",
    "out_of_fold_pred = lang_not_c.copy()\n",
    "\n",
    "aucs = []\n",
    "\n",
    "for i, (train, test) in enumerate(skf):\n",
    "    t0 = time.time()\n",
    "\n",
    "    y_train = lang_not_c[train]\n",
    "    y_test = lang_not_c[test]\n",
    "    X_train = X_not_c[train]\n",
    "    X_test = X_not_c[test]\n",
    "\n",
    "    lsvc = LinearSVC(C=0.01, penalty=\"l1\", dual=False).fit(X_train, y_train)\n",
    "    selection_model = SelectFromModel(lsvc, prefit=True)\n",
    "    X_train = selection_model.transform(X_train)\n",
    "    X_test = selection_model.transform(X_test)\n",
    "\n",
    "    dt_rest = DecisionTreeClassifier(max_depth=6)\n",
    "    dt_rest.fit(X_train, y_train)\n",
    "\n",
    "    pred = dt_rest.predict(X_test)\n",
    "    out_of_fold_pred[test] = pred\n",
    "\n",
    "    pred_score = dt_rest.predict_proba(X_test)\n",
    "    auc = roc_auc_score(y_dummies.ix[test], pred_score)\n",
    "    aucs.append(auc)\n",
    "    \n",
    "    print \"done in %fs\" % (time.time() - t0)\n",
    "print np.mean(aucs), np.std(aucs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "actual | predicted -->\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>C#</th>\n",
       "      <th>D</th>\n",
       "      <th>Go</th>\n",
       "      <th>Haskell</th>\n",
       "      <th>Java</th>\n",
       "      <th>JavaScript</th>\n",
       "      <th>Ocaml</th>\n",
       "      <th>PHP</th>\n",
       "      <th>Pascal</th>\n",
       "      <th>Perl</th>\n",
       "      <th>Python</th>\n",
       "      <th>Ruby</th>\n",
       "      <th>Scala</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>C#</th>\n",
       "      <td>1476</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>36</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Go</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>126</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Haskell</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>159</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>170</td>\n",
       "      <td>15</td>\n",
       "      <td>15</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Java</th>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15104</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>JavaScript</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>69</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ocaml</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PHP</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>97</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pascal</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3714</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Perl</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>128</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Python</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>200</td>\n",
       "      <td>2</td>\n",
       "      <td>7052</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ruby</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>32</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>284</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Scala</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>347</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              C#  D  Go  Haskell   Java  JavaScript  Ocaml  PHP  Pascal  Perl  \\\n",
       "C#          1476  0   0        0     10           0      0    0      36     0   \n",
       "D              1  0   0        0      0           0      0    0      31     0   \n",
       "Go             0  0   0        0      0          13      0    0     126     0   \n",
       "Haskell        0  0   0      159      0           0      0    0     170    15   \n",
       "Java           9  0   0        0  15104           0      0    0      14     0   \n",
       "JavaScript     0  0   0        0      3          67      0    0      69     0   \n",
       "Ocaml          0  0   0        0      1           0     18    0      44     0   \n",
       "PHP            0  0   0        0      0           0      0   45      97     0   \n",
       "Pascal         1  0   0        0      1           0      0    0    3714     0   \n",
       "Perl           0  0   0        5      0           0      0    0      10   128   \n",
       "Python         1  0   0        3      2          11      0    0     200     2   \n",
       "Ruby           0  0   0        0      0           0      0    0      32     2   \n",
       "Scala          0  0   0        0      0           2      0    0      17     0   \n",
       "\n",
       "            Python  Ruby  Scala  \n",
       "C#               4     0      0  \n",
       "D                1     0      1  \n",
       "Go               1     0      3  \n",
       "Haskell         15     2      6  \n",
       "Java             2     0      1  \n",
       "JavaScript       8     0      0  \n",
       "Ocaml            0     0      0  \n",
       "PHP              1     1      0  \n",
       "Pascal           3     9      1  \n",
       "Perl             0     0      0  \n",
       "Python        7052     3      3  \n",
       "Ruby             6   284      0  \n",
       "Scala           11     0    347  "
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cm = confusion_matrix(lang_not_c, out_of_fold_pred)\n",
    "\n",
    "print 'actual | predicted -->'\n",
    "cm = pd.DataFrame(cm, columns=dt_rest.classes_)\n",
    "cm.index = dt_rest.classes_\n",
    "cm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "Model has some problems with Pascal, D and Go, but other than that the performance seems OK.\n",
    "\n",
    "So, the final model is:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# http://chrisstrelioff.ws/sandbox/2015/06/08/decision_trees_in_python_with_scikit_learn_and_pandas.html\n",
    "# http://stackoverflow.com/a/30104792\n",
    "\n",
    "def get_code(tree, feature_names, spacer_base='  '):\n",
    "    left      = tree.tree_.children_left\n",
    "    right     = tree.tree_.children_right\n",
    "    threshold = tree.tree_.threshold\n",
    "    features  = [feature_names[i] for i in tree.tree_.feature]\n",
    "    value = tree.tree_.value\n",
    "    target_names = tree.classes_\n",
    "\n",
    "    def recurse(left, right, threshold, features, node, depth):\n",
    "        spacer = spacer_base * depth\n",
    "        if threshold[node] != -2:\n",
    "            # replace <= with > - it reads better for this problem\n",
    "            # print spacer + \"if \" + features[node] + \" > \" + str(threshold[node]) + \":\"\n",
    "            print spacer + \"if contains('\" + features[node] + \"'):\"\n",
    "            if right[node] != -1:\n",
    "                recurse(left, right, threshold, features, right[node], depth + 1)\n",
    "            print spacer + \"else: # doesn't contain '\" + features[node] + \"'\"\n",
    "            if left[node] != -1:\n",
    "                recurse(left, right, threshold, features, left[node], depth + 1)\n",
    "        else:\n",
    "            target = value[node]\n",
    "            \n",
    "            total_sum = np.sum(target)\n",
    "            target_name = target_names[target.argmax()]\n",
    "            target_count = target.max()\n",
    "\n",
    "            print spacer + \"return '%s' # (%0.3f, %d/%d examples)\" %  \\\n",
    "                  (target_name, target_count / total_sum, target_count, total_sum)\n",
    "\n",
    "    recurse(left, right, threshold, features, 0, 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=6,\n",
       "            max_features=None, max_leaf_nodes=None, min_samples_leaf=1,\n",
       "            min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "            presort=False, random_state=None, splitter='best')"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt_first = DecisionTreeClassifier(max_depth=3)\n",
    "dt_first.fit(X, np.where(df.language == 'C/C++', 'C/C++', 'OTHER'))\n",
    "\n",
    "y_noc = df.language[df.language != 'C/C++']\n",
    "X_noc = X[np.where(df.language != 'C/C++')]\n",
    "\n",
    "lsvc = LinearSVC(C=0.01, penalty=\"l1\", dual=False).fit(X_noc, y_noc)\n",
    "selection_model = SelectFromModel(lsvc, prefit=True)\n",
    "X_noc = selection_model.transform(X_noc)\n",
    "\n",
    "dt_rest = DecisionTreeClassifier(max_depth=6)\n",
    "dt_rest.fit(X_noc, y_noc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "if contains('std'):\n",
      "  if contains('import'):\n",
      "    if contains('scan'):\n",
      "      return 'C/C++' # (1.000, 3/3 examples)\n",
      "    else: # doesn't contain 'scan'\n",
      "      return 'OTHER' # (1.000, 47/47 examples)\n",
      "  else: # doesn't contain 'import'\n",
      "    if contains('String'):\n",
      "      return 'C/C++' # (0.800, 4/5 examples)\n",
      "    else: # doesn't contain 'String'\n",
      "      return 'C/C++' # (0.999, 230230/230376 examples)\n",
      "else: # doesn't contain 'std'\n",
      "  if contains('printf'):\n",
      "    if contains('String'):\n",
      "      return 'OTHER' # (0.992, 604/609 examples)\n",
      "    else: # doesn't contain 'String'\n",
      "      return 'C/C++' # (0.993, 12940/13029 examples)\n",
      "  else: # doesn't contain 'printf'\n",
      "    if contains('#include'):\n",
      "      return 'C/C++' # (1.000, 193/193 examples)\n",
      "    else: # doesn't contain '#include'\n",
      "      return 'OTHER' # (0.977, 28517/29181 examples)\n"
     ]
    }
   ],
   "source": [
    "get_code(dt_first, feature_names=vectorizer.get_feature_names())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "if contains('out'):\n",
      "  if contains('public'):\n",
      "    if contains('object'):\n",
      "      if contains('var'):\n",
      "        return 'C#' # (1.000, 19/19 examples)\n",
      "      else: # doesn't contain 'var'\n",
      "        return 'Java' # (1.000, 3/3 examples)\n",
      "    else: # doesn't contain 'object'\n",
      "      if contains('String'):\n",
      "        if contains('class'):\n",
      "          if contains('in'):\n",
      "            return 'Java' # (1.000, 14979/14980 examples)\n",
      "          else: # doesn't contain 'in'\n",
      "            return 'Java' # (0.976, 82/84 examples)\n",
      "        else: # doesn't contain 'class'\n",
      "          return 'JavaScript' # (1.000, 1/1 examples)\n",
      "      else: # doesn't contain 'String'\n",
      "        if contains('java'):\n",
      "          return 'Java' # (1.000, 7/7 examples)\n",
      "        else: # doesn't contain 'java'\n",
      "          if contains('io'):\n",
      "            return 'Java' # (1.000, 1/1 examples)\n",
      "          else: # doesn't contain 'io'\n",
      "            return 'C#' # (1.000, 8/8 examples)\n",
      "  else: # doesn't contain 'public'\n",
      "    if contains('object'):\n",
      "      return 'Scala' # (1.000, 39/39 examples)\n",
      "    else: # doesn't contain 'object'\n",
      "      if contains('static'):\n",
      "        return 'C#' # (1.000, 34/34 examples)\n",
      "      else: # doesn't contain 'static'\n",
      "        if contains('?'):\n",
      "          if contains('in'):\n",
      "            return 'Ruby' # (1.000, 4/4 examples)\n",
      "          else: # doesn't contain 'in'\n",
      "            return 'PHP' # (1.000, 7/7 examples)\n",
      "        else: # doesn't contain '?'\n",
      "          if contains('var'):\n",
      "            return 'JavaScript' # (1.000, 1/1 examples)\n",
      "          else: # doesn't contain 'var'\n",
      "            return 'Python' # (0.967, 29/30 examples)\n",
      "else: # doesn't contain 'out'\n",
      "  if contains('print'):\n",
      "    if contains('$'):\n",
      "      if contains('do'):\n",
      "        if contains('end'):\n",
      "          if contains('count'):\n",
      "            return 'Ruby' # (1.000, 1/1 examples)\n",
      "          else: # doesn't contain 'count'\n",
      "            return 'Pascal' # (1.000, 9/9 examples)\n",
      "        else: # doesn't contain 'end'\n",
      "          if contains('and'):\n",
      "            return 'Perl' # (0.625, 5/8 examples)\n",
      "          else: # doesn't contain 'and'\n",
      "            return 'Haskell' # (1.000, 120/120 examples)\n",
      "      else: # doesn't contain 'do'\n",
      "        if contains('trim'):\n",
      "          return 'PHP' # (1.000, 38/38 examples)\n",
      "        else: # doesn't contain 'trim'\n",
      "          if contains('solve'):\n",
      "            return 'Haskell' # (0.917, 11/12 examples)\n",
      "          else: # doesn't contain 'solve'\n",
      "            return 'Perl' # (0.962, 128/133 examples)\n",
      "    else: # doesn't contain '$'\n",
      "      if contains('var'):\n",
      "        if contains('val'):\n",
      "          return 'Scala' # (1.000, 33/33 examples)\n",
      "        else: # doesn't contain 'val'\n",
      "          if contains('begin'):\n",
      "            return 'Pascal' # (1.000, 30/30 examples)\n",
      "          else: # doesn't contain 'begin'\n",
      "            return 'JavaScript' # (0.750, 78/104 examples)\n",
      "      else: # doesn't contain 'var'\n",
      "        if contains('words'):\n",
      "          if contains('s'):\n",
      "            return 'Haskell' # (0.750, 3/4 examples)\n",
      "          else: # doesn't contain 's'\n",
      "            return 'Haskell' # (1.000, 34/34 examples)\n",
      "        else: # doesn't contain 'words'\n",
      "          if contains('do'):\n",
      "            return 'Ruby' # (0.333, 10/30 examples)\n",
      "          else: # doesn't contain 'do'\n",
      "            return 'Python' # (0.995, 7009/7045 examples)\n",
      "  else: # doesn't contain 'print'\n",
      "    if contains('begin'):\n",
      "      if contains('printf'):\n",
      "        if contains('using'):\n",
      "          if contains('a'):\n",
      "            return 'Python' # (0.750, 9/12 examples)\n",
      "          else: # doesn't contain 'a'\n",
      "            return 'Java' # (0.400, 2/5 examples)\n",
      "        else: # doesn't contain 'using'\n",
      "          return 'Ocaml' # (1.000, 18/18 examples)\n",
      "      else: # doesn't contain 'printf'\n",
      "        if contains('std'):\n",
      "          if contains('do'):\n",
      "            return 'Haskell' # (1.000, 1/1 examples)\n",
      "          else: # doesn't contain 'do'\n",
      "            return 'Python' # (0.786, 11/14 examples)\n",
      "        else: # doesn't contain 'std'\n",
      "          if contains('gets'):\n",
      "            return 'Ruby' # (1.000, 7/7 examples)\n",
      "          else: # doesn't contain 'gets'\n",
      "            return 'Pascal' # (0.999, 3447/3451 examples)\n",
      "    else: # doesn't contain 'begin'\n",
      "      if contains('static'):\n",
      "        if contains('java'):\n",
      "          return 'Java' # (1.000, 30/30 examples)\n",
      "        else: # doesn't contain 'java'\n",
      "          if contains('System'):\n",
      "            return 'C#' # (0.996, 1418/1423 examples)\n",
      "          else: # doesn't contain 'System'\n",
      "            return 'Java' # (0.462, 6/13 examples)\n",
      "      else: # doesn't contain 'static'\n",
      "        if contains('gets'):\n",
      "          if contains('explode'):\n",
      "            return 'PHP' # (1.000, 1/1 examples)\n",
      "          else: # doesn't contain 'explode'\n",
      "            return 'Ruby' # (1.000, 281/281 examples)\n",
      "        else: # doesn't contain 'gets'\n",
      "          if contains('val'):\n",
      "            return 'Scala' # (0.949, 282/297 examples)\n",
      "          else: # doesn't contain 'val'\n",
      "            return 'Pascal' # (0.221, 228/1032 examples)\n"
     ]
    }
   ],
   "source": [
    "features = np.array(vectorizer.get_feature_names())\n",
    "features = features[selection_model._get_support_mask()]\n",
    "get_code(dt_rest, feature_names=features)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}