sample parsing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1741506"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(1 for line in open('globe.csv'))\n",
    "# 870,753 = 1741506/2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "globe 1 is 870753\n",
      "globe 2 is 870753\n"
     ]
    }
   ],
   "source": [
    "globe = sum(1 for line in open('globe.csv'))\n",
    "globe1 = sum(1 for line in open('globe1.csv'))\n",
    "globe2 = sum(1 for line in open('globe2.csv'))\n",
    "print(\"globe is \"+ str(globe))\n",
    "print(\"globe 1 is \"+ str(globe1))\n",
    "print(\"globe 2 is \"+ str(globe2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "smart is 1745425\n",
      "smart 1 is 872712\n",
      "smart 2 is 872713\n"
     ]
    }
   ],
   "source": [
    "smart = sum(1 for line in open('smart.csv'))\n",
    "smart1 = sum(1 for line in open('smart1.csv'))\n",
    "smart2 = sum(1 for line in open('smart2.csv'))\n",
    "\n",
    "print(\"smart is \"+ str(smart))\n",
    "print(\"smart 1 is \"+ str(smart1))\n",
    "print(\"smart 2 is \"+ str(smart2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1745425"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_lines\n",
    "# 1745425 = 872,712 + 872,713"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import csv\n",
    "with open('globe.csv', 'r') as csvfile:\n",
    "    reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
    "    for row in itertools.islice(csv.DictReader(csvfile), 100)::\n",
    "        for row in \n",
    "        print(row['first_name'], row['last_name'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Split Globe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import csv, itertools\n",
    "\n",
    "# as globe1 and globe2\n",
    "with open('globe1.csv', 'w') as newfile:\n",
    "    with open('globe.csv') as origfile:\n",
    "        for row in itertools.islice(csv.reader(origfile), 870753):\n",
    "            #print(row[0])\n",
    "            newfile.write(row[0]+'\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "with open('globe2.csv', 'w') as newfile:\n",
    "    with open('globe.csv') as origfile:\n",
    "        for row in itertools.islice(csv.reader(origfile), 870753, None):\n",
    "            #print(row[0])\n",
    "            newfile.write(row[0]+'\\n')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Split Smart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import csv, itertools\n",
    "\n",
    "# as globe1 and globe2\n",
    "with open('smart1.csv', 'w') as newfile:\n",
    "    with open('smart.csv') as origfile:\n",
    "        for row in itertools.islice(csv.reader(origfile), 872712):\n",
    "            #print(row[0])\n",
    "            newfile.write(row[0]+'\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import csv, itertools\n",
    "\n",
    "# as globe1 and globe2\n",
    "with open('smart2.csv', 'w') as newfile:\n",
    "    with open('smart.csv') as origfile:\n",
    "        for row in itertools.islice(csv.reader(origfile), 872712, None):\n",
    "            #print(row[0])\n",
    "            newfile.write(row[0]+'\\n')"
   ]
  },
  {
   "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}