Flash Updates in September.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Flash updates in a month\n",
    "1. ayup.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is a very a brief introduction to Spark and Telemetry in Python. You should have a look at the [tutorial](https://gist.github.com/vitillo/25a20b7c8685c0c82422) in Scala and the associated [talk](http://www.slideshare.net/RobertoAgostinoVitil/spark-meets-telemetry) if you are interested to learn more about Spark."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "import ujson as json\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import plotly.plotly as py\n",
    "\n",
    "import time\n",
    "import collections\n",
    "\n",
    "from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history\n",
    "\n",
    "%pylab inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## number of flash upgrade events in the last month\n",
    "\n",
    "(for rebecca weiss, who is amazing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "invalid syntax (<ipython-input-34-aa309596518a>, line 12)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;36m  File \u001b[1;32m\"<ipython-input-34-aa309596518a>\"\u001b[1;36m, line \u001b[1;32m12\u001b[0m\n\u001b[1;33m    flash == .... whatever\u001b[0m\n\u001b[1;37m             ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m invalid syntax\n"
     ]
    }
   ],
   "source": [
    "pings = get_pings(sc, app=\"Firefox\", channel=\"release\", submission_date=(\"20150901\", \"20150930\"), fraction=0.001)\n",
    "\n",
    "#cohortStart = math.floor(time.mktime(time.strptime(\"01 Sep 15\", \"%d %b %y\"))/86400)\n",
    "#cohortEnd = math.floor(time.mktime(time.strptime(\"30 Sep 15\", \"%d %b %y\"))/86400)\n",
    "# \n",
    "def hasFlash(ping):\n",
    "    ##\n",
    "    ## \n",
    "    return true\n",
    "\n",
    "def updatedInTheMonth(ping):\n",
    "    flash == .... whatever\n",
    "    ping['creationDate']  # client time, made the record\n",
    "    # rescale to...\n",
    "    ping['meta/submissionDate'] # server received\n",
    "    \n",
    "    ## pretend the clocs are right.\n",
    "    return (cohortStart <= flash['update'] <= cohortEnd)\n",
    "    \n",
    "def maybeFlashUpdate(ping):\n",
    "    flash = ping['env']....\n",
    "    if not (cohortStart <= flash['update'] <= cohortEnd):\n",
    "        return \n",
    "    \n",
    "    #return (ping['clientId'], flash['version'])\n",
    "    return (ping['clientId'], flash['updateDay'])\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "pings.filter(hasFlash).map(maybeFlashUpdate).distinct().count()   # numerator\n",
    "get_one_per_client(pings).count() # demoninator\n",
    "\n",
    "#\n",
    "for ping in pings:\n",
    "    if has flash\n",
    "    if flash update is in this month\n",
    "    inc!\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc.defaultParallelism"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{u'blocklisted': False,\n",
       "  u'clicktoplay': False,\n",
       "  u'description': u'Shockwave Flash 18.0 r0',\n",
       "  u'disabled': False,\n",
       "  u'mimeTypes': [u'application/x-shockwave-flash',\n",
       "   u'application/futuresplash'],\n",
       "  u'name': u'Shockwave Flash',\n",
       "  u'updateDay': 16660,\n",
       "  u'version': u'18.0.0.232'}]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[x for x in (pings.first()['environment']['addons']['activePlugins']) if x['name']=='Shockwave Flash']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pings = get_pings(sc, app=\"Firefox\", channel=\"release\", submission_date=(\"20150922\", \"20151001\"), fraction=0.001)\n",
    "\n",
    "# 41 release\n",
    "cohortStart = math.floor(time.mktime(time.strptime(\"22 Sep 15\", \"%d %b %y\"))/86400)\n",
    "cohortEnd = math.floor(time.mktime(time.strptime(\"1 Oct 15\", \"%d %b %y\"))/86400)\n",
    "\n",
    "\n",
    "def hasFlash(ping):\n",
    "    try:\n",
    "        maybe = [x for x in (ping['environment']['addons']['activePlugins']) if x['name']=='Shockwave Flash']\n",
    "        if maybe:\n",
    "            return maybe[0]\n",
    "    except KeyError:\n",
    "        return \n",
    "    \n",
    "    return \n",
    "\n",
    "\n",
    "def maybeFlashUpdate(ping):\n",
    "    flash = hasFlash(ping)\n",
    "    if not flash: return None\n",
    "    \n",
    "    ## pretend the clocks are right.\n",
    "    # correct would be creationTime, meta/submission\n",
    "    if not (cohortStart <= flash['updateDay'] <= cohortEnd):\n",
    "        return None\n",
    "    \n",
    "    #return (ping['clientId'], flash['version'])\n",
    "    return (ping['clientId'], flash['updateDay'])\n",
    "\n",
    " \n",
    "print 'numevents', pings.filter(hasFlash).map(maybeFlashUpdate).filter(bool).distinct().collect()   # numerator\n",
    "\n",
    "print 'numclients', pings.map(lambda x: x['clientId']).distinct().count()\n",
    "\n",
    "#print get_one_per_client(pings).count() # denominator\n",
    "\n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "2.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}