Hang Bug

Hang Bug.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:d99a34c369aaf929f7ae1503d75078a0d05aaa23c1c9ba015ceb1f172d3d9ea3"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from __future__ import division\n",
      "\n",
      "import numpy as np\n",
      "import ujson as json\n",
      "import matplotlib.pyplot as plt\n",
      "import pandas as pd\n",
      "import IPython\n",
      "\n",
      "from moztelemetry.spark import get_pings\n",
      "from moztelemetry.histogram import Histogram\n",
      "\n",
      "IPython.core.pylabtools.figsize(18, 7)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 17
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Number of cores:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sc.defaultParallelism"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 29,
       "text": [
        "48"
       ]
      }
     ],
     "prompt_number": 29
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Number of pings analyzed:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%capture\n",
      "pings = get_pings(sc, \"Firefox\", \"release\", \"34.0.5\", \"*\", (\"20150110\"))\n",
      "pings.count()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "3886604"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%capture\n",
      "\n",
      "def extract(ping):\n",
      "    ping = json.loads(ping)    \n",
      "    locale = ping[\"info\"].get(\"locale\", None)\n",
      "    return locale.decode(\"utf-8\") #locale is the winner\n",
      "\n",
      "pings.map(extract).distinct().collect()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}