beta46_e10s_cohort

beta46_e10s_cohort.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Distribution of e10sCohort in Beta46"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/hadoop/anaconda2/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.\n",
      "  warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')\n",
      "WARNING: "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unable to parse whitelist (/home/hadoop/anaconda2/lib/python2.7/site-packages/moztelemetry/bucket-whitelist.json). Assuming all histograms are acceptable.\n",
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "pylab import has clobbered these variables: ['Annotation', 'Figure']\n",
      "`%matplotlib` prevents importing * from pylab and numpy\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",
    "from plotly.graph_objs import *\n",
    "\n",
    "from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history, get_records\n",
    "\n",
    "%pylab inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "64"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc.defaultParallelism"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pings = get_pings(sc, app=\"Firefox\", channel=\"beta\", version=\"46.0\", fraction=0.01)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "subset = get_pings_properties(pings, [\"clientId\",\n",
    "                                      \"environment/settings/e10sEnabled\",\n",
    "                                      \"environment/settings/e10sCohort\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "subset = get_one_ping_per_client(subset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "cached = subset.cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "How many clients are we looking at?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "365528"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cached.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "defaultdict(int,\n",
       "            {(u'control', False): 33665,\n",
       "             (u'disqualified', False): 88126,\n",
       "             (u'disqualified', True): 1,\n",
       "             (u'optedIn', False): 46,\n",
       "             (u'optedIn', True): 13,\n",
       "             (u'optedOut', False): 1403,\n",
       "             (u'optedOut', True): 1,\n",
       "             (u'test', False): 190,\n",
       "             (u'test', True): 33993,\n",
       "             (u'unknown', False): 152,\n",
       "             (u'unknown', True): 1})"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cohorts_rdd = cached.filter(lambda p: p[\"environment/settings/e10sCohort\"] is not None)\n",
    "cohorts_count = cohorts_rdd.count()\n",
    "cohorts = cohorts_rdd.map(lambda p: ((p[\"environment/settings/e10sCohort\"], p[\"environment/settings/e10sEnabled\"]), 1)).countByKey()\n",
    "cohorts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{(u'control', False): '21.36%',\n",
       " (u'disqualified', False): '55.92%',\n",
       " (u'disqualified', True): '0.00%',\n",
       " (u'optedIn', False): '0.03%',\n",
       " (u'optedIn', True): '0.01%',\n",
       " (u'optedOut', False): '0.89%',\n",
       " (u'optedOut', True): '0.00%',\n",
       " (u'test', False): '0.12%',\n",
       " (u'test', True): '21.57%',\n",
       " (u'unknown', False): '0.10%',\n",
       " (u'unknown', True): '0.00%'}"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "{k:\"{:.2%}\".format(float(v) / float(cohorts_count)) for (k,v) in cohorts.iteritems()}"
   ]
  }
 ],
 "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
}

beta46_e10s_cohort.py

# coding: utf-8

# ### Distribution of e10sCohort in Beta46

# In[1]:

import ujson as json
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import plotly.plotly as py
from plotly.graph_objs import *

from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history, get_records

get_ipython().magic(u'pylab inline')


# In[2]:

sc.defaultParallelism


# In[3]:

pings = get_pings(sc, app="Firefox", channel="beta", version="46.0", fraction=0.01)


# In[4]:

subset = get_pings_properties(pings, ["clientId",
                                      "environment/settings/e10sEnabled",
                                      "environment/settings/e10sCohort"])


# In[6]:

subset = get_one_ping_per_client(subset)


# In[7]:

cached = subset.cache()


# How many clients are we looking at?

# In[8]:

cached.count()


# In[14]:

cohorts_rdd = cached.filter(lambda p: p["environment/settings/e10sCohort"] is not None)
cohorts_count = cohorts_rdd.count()
cohorts = cohorts_rdd.map(lambda p: ((p["environment/settings/e10sCohort"], p["environment/settings/e10sEnabled"]), 1)).countByKey()
cohorts


# In[15]:

{k:"{:.2%}".format(float(v) / float(cohorts_count)) for (k,v) in cohorts.iteritems()}