giladlotan/optimal_buzzfeed_listicle_length

## optimal_buzzfeed_listicle_length
{
 "metadata": {
  "name": "",
  "signature": "sha256:431c3398715661ec2ce4c2f300849944ee2c04ebf05ac77e071fa65330170e14"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pickle\n",
      "f = open('****','rb')\n",
      "data = pickle.load(f)\n",
      "f.close()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "odds_cnt = 0\n",
      "evens_cnt = 0\n",
      "odds_s = []\n",
      "evens_s = []\n",
      "all_s = []\n",
      "\n",
      "for d,vals in data.items():\n",
      "    for u,s in data[d].items():\n",
      "        if d%2==0:\n",
      "            evens_s.append(s)\n",
      "            evens_cnt += 1\n",
      "        else:\n",
      "            odds_s.append(s)\n",
      "            odds_cnt += 1\n",
      "        all_s.append(s)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np\n",
      "from collections import defaultdict\n",
      "\n",
      "avgs = defaultdict(int)\n",
      "\n",
      "for d,vals in data.items():\n",
      "    scores = np.array(vals.values())\n",
      "    avgs[d]=round(scores.mean(),2)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "avgs_odd = np.array([y for x,y in avgs.items() if x%2==1])\n",
      "avgs_even = np.array([y for x,y in avgs.items() if x%2==0])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "rcParams['figure.figsize'] = 8,5\n",
      "\n",
      "for d,s in avgs.items():\n",
      "            \n",
      "    if d%2==0:\n",
      "        pylab.plot(len(data[d]), s, 'ro', alpha=0.8)\n",
      "    else:\n",
      "        pylab.plot(len(data[d]), s, 'bo', alpha=0.8)\n",
      "\n",
      "    if s>20:\n",
      "        pylab.annotate('{}'.format(d), xy=(len(data[d]), s), xytext=(-5, 5), ha='left', textcoords='offset points')\n",
      "\n",
      "pylab.xlabel('number of published listicles for a given digit')\n",
      "pylab.ylabel('avg score')\n",
      "pylab.title('listicles / score vs. size')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "<matplotlib.text.Text at 0x4481dd0>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAfwAAAFRCAYAAACR0B8jAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQgghhAuQAV8IIYRwAf8PVhqB60StDkoAAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x4474f50>"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "rcParams['figure.figsize'] = 16,6\n",
      "\n",
      "for d,s in avgs.items():\n",
      "    if d<200:\n",
      "        if s==0:\n",
      "            continue\n",
      "        if d%2==0:\n",
      "            pylab.plot(d, s, 'ro', alpha=0.8)\n",
      "        else:\n",
      "            pylab.plot(d, s, 'bo', alpha=0.8)\n",
      "            \n",
      "for i,s in avgs.items():\n",
      "    \n",
      "    if s>20:\n",
      "        #pylab.annotate(i, (i, all_avg_users[i]))\n",
      "        pylab.annotate('{}'.format(i), xy=(i, s), xytext=(-5, 5), ha='left', textcoords='offset points')\n",
      "        \n",
      "pylab.xlabel('listicle length (digit)')\n",
      "pylab.ylabel('avg score')\n",
      "pylab.title('listicles / by score')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "<matplotlib.text.Text at 0x48f4150>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAA7gAAAGJCAYAAACggJ96AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRERERKrwf1trzhxG0kMrAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x44745d0>"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# some basic stats\n",
      "odds_s = np.array(odds_s)\n",
      "evens_s = np.array(evens_s)\n",
      "\n",
      "print 'members:\\nodds: %s\\nevens: %s\\n' % (odds_cnt, evens_cnt)\n",
      "print 'standard deviation:\\nodds: %s\\nevens: %s\\n' % (odds_s.std(), evens_s.std())\n",
      "print 'mean:\\nodds: %s\\nevens: %s\\n' % (odds_s.mean(), evens_s.mean())"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "members:\n",
        "odds: 5037\n",
        "evens: 4886\n",
        "\n",
        "standard deviation:\n",
        "odds: 87.6169551402\n",
        "evens: 39.0589360888\n",
        "\n",
        "mean:\n",
        "odds: 20.9217788366\n",
        "evens: 14.1966844044\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "t-test"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from scipy import stats\n",
      "\n",
      "# t-test on all data\n",
      "print stats.ttest_ind(odds_s, evens_s)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(4.9120672755595303, 9.1560218380972755e-07)\n"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# t-test on data averages (per listicle length)\n",
      "print stats.ttest_ind(avgs_odd, avgs_even)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(2.4086189971429741, 0.017825485089317184)\n"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Finding the Optimal Number"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "<p>Here we try to identify the optimal listicle length across the board. There are some clear candidates from our plot above: 27, 29, 35. These numbers had both a relatively high avg score, as well as a high number of published posts. Numbers such as 71, 81 and 91 displayed high avg scores, with very small number of published posts. The high scores are heavily skewed towards a single post in those bins that performed extraordinarily well. Typical issue with outliers. Lets compare the performance of 27, 29 and 35 with the top performing links (=> scores above 20, approximately 20% of our dataset).</p>"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# performance of 27-length listicles\n",
      "links_27 = [y for x,y in data[27].items()]\n",
      "links_29 = [y for x,y in data[29].items()]\n",
      "links_35 = [y for x,y in data[35].items()]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print stats.ttest_ind(links_27, all_s)\n",
      "print stats.ttest_ind(links_29, all_s)\n",
      "print stats.ttest_ind(links_35, all_s)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(4.6711298195107691, 3.0338447258973221e-06)\n",
        "(8.0769462172810371, 7.4038388325404207e-16)\n",
        "(3.5244321399517857, 0.0004262834158488855)\n"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Fisher's Exact Test"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# get population mean\n",
      "population_mean = np.array(all_s).mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "odds_score_above_mean = [x for x in odds_s if x>population_mean]\n",
      "odds_score_below_mean = [x for x in odds_s if x<population_mean]\n",
      "\n",
      "evens_score_above_mean = [x for x in evens_s if x>population_mean]\n",
      "evens_score_below_mean = [x for x in evens_s if x<population_mean]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print len(odds_score_above_mean)\n",
      "print len(odds_score_below_mean)\n",
      "print len(evens_score_above_mean)\n",
      "print len(evens_score_below_mean)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1210\n",
        "3827\n",
        "890\n",
        "3996\n"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "oddsratio, pvalue = stats.fisher_exact([[1210,3827],[890,3996]])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print oddsratio\n",
      "print pvalue"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1.41958820093\n",
        "-1.45436468458e-11\n"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Prime Numbers"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def primes(n):\n",
      "    \"\"\" Returns  a list of primes < n \"\"\"\n",
      "    sieve = [True] * n\n",
      "    for i in xrange(3,int(n**0.5)+1,2):\n",
      "        if sieve[i]:\n",
      "            sieve[i*i::2*i]=[False]*((n-i*i-1)/(2*i)+1)\n",
      "    return [2] + [i for i in xrange(3,n,2) if sieve[i]]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 40
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prime_nums = list(set(primes(200)).intersection(set(data.keys())))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "avgs_prime = [y for x,y in avgs.items() if x in prime_nums]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 57
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print stats.ttest_ind(avgs_odd, avgs_even)\n",
      "print stats.ttest_ind(avgs_prime, avgs_odd) # not statistically significant\n",
      "print stats.ttest_ind(avgs_prime, avgs_even)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(2.4086189971429741, 0.017825485089317184)\n",
        "(-0.029120310398447546, 0.97685393494459993)\n",
        "(2.0119545375529109, 0.04772277726894511)\n"
       ]
      }
     ],
     "prompt_number": 59
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "primes_s = []\n",
      "for d in prime_nums:\n",
      "    primes_s+=data[d].values()\n",
      "\n",
      "print stats.ttest_ind(primes_s, evens_s)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(3.8825970347615471, 0.00010421007133924338)\n"
       ]
      }
     ],
     "prompt_number": 65
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Grid Representation of Listicle Length"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "<p>The following plot highlights listicle length performance as a grid. The lower left corner represents the average performance of articles of length = 0 (there was one). The rectangle's color represents average performance (blue = poor, red = high). The bottom row from left to right represents listicle lengths: 0,1,2,3...,9. The row above is: 10,11,12,...19. And so on and so forth.</p>"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# plot as grid\n",
      "rcParams['figure.figsize'] = 10,5\n",
      "\n",
      "data_plot = pylab.random((20,10))\n",
      "for d in sorted(data.keys()):\n",
      "    avg_score = np.mean(data[d].values())\n",
      "    y = d%10\n",
      "    x = d/10\n",
      "    data_plot[x][y]=log(avg_score+1)\n",
      "        \n",
      "pylab.pcolor(data_plot)\n",
      "pylab.colorbar()\n",
      "pylab.show()\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAhgAAAE4CAYAAAAZwIq7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x5a80810>"
       ]
      }
     ],
     "prompt_number": 84
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%pylab inline"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Populating the interactive namespace from numpy and matplotlib\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "WARNING: pylab import has clobbered these variables: ['f']\n",
        "`%matplotlib` prevents importing * from pylab and numpy\n"
       ]
      }
     ],
     "prompt_number": 4
    }
   ],
   "metadata": {}
  }
 ]
}