{
 "metadata": {
  "name": "",
  "signature": "sha256:700447138dc0e5e87878ad4632a404fc1ad41c47f349d4f640d26999faa70d5a"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "The World Cup Problem: Germany v. Argentina\n",
      "-------------------------------------------\n",
      "\n",
      "Allen Downey\n",
      "\n",
      "This notebook contains a solution to a problem I posed in my Bayesian statistics class:\n",
      "\n",
      "> In the 2014 FIFA World Cup, Germany played Brazil in a semifinal\n",
      "> match.  Germany scored after 11 minutes and again at the 23 minute\n",
      "> mark.  At that point in the match, how many goals would you expect\n",
      "> Germany to score after 90 minutes?  What was the probability that they\n",
      "> would score 5 more goals?\n",
      "\n",
      "Scoring in games like soccer and hockey can be (reasonably) well modeled by a Poisson process, which assumes that each team, against a given opponent, will score goals at some goal-scoring rate, $\\lambda$, and that this rate is stationary; in other words, the probability of scoring a goal is about the same at any point during the game.\n",
      "\n",
      "Based on this modeling decision, we can answer the questions by\n",
      "\n",
      "1. Defining a prior distribution for Germany's goal-scoring rate against Brazil,\n",
      "2. Updating the prior based on the first two goals, and\n",
      "3. Generating a predictive distribution for the number of goals they would score in the remaining minutes.\n",
      "\n",
      "My solution uses the ThinkBayes2 framework, which is described in [Think Bayes](http://thinkbayes.com), and summarized in [this notebook](http://nbviewer.ipython.org/github/AllenDowney/ThinkBayes2/blob/master/code/framework.ipynb).\n",
      "\n",
      "I'll start with Step 2.\n",
      "\n",
      "### Step 2: Updating\n",
      "\n",
      "If goal-scoring is a Poisson process, the distribution of time between goals is exponential with parameter $\\lambda$, the goal scoring rate.  In this case we are given as data the inter-arrival time of the first two goals, 11 minutes and 12 minutes.  We can define a new class that inherits from `thinkbayes2.Suite` and provides an appropriate `Likelihood` function:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import thinkbayes2\n",
      "\n",
      "class Soccer(thinkbayes2.Suite):\n",
      "    \"\"\"Represents hypotheses about goal-scoring rates.\"\"\"\n",
      "\n",
      "    def Likelihood(self, data, hypo):\n",
      "        \"\"\"Computes the likelihood of the data under the hypothesis.\n",
      "\n",
      "        hypo: goal rate in goals per game\n",
      "        data: interarrival time in minutes\n",
      "        \"\"\"\n",
      "        x = data\n",
      "        lam = hypo / 90\n",
      "        like = thinkbayes2.EvalExponentialPdf(x, lam)\n",
      "        return like"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "`Likelihood` computes the likelihood of `data` given `hypo`, where `data` is an observed time between goals in minutes, and `hypo` is a hypothetical goal-scoring rate in goals per game.\n",
      "\n",
      "After converting `hypo` to goals per minute, we can compute the likelihood of the data by evaluating the exponential probability density function (PDF).  The result is a density, and therefore not a true probability.  But the result from `Likelihood` only needs to be proportional to the probability of the data; it doesn't have to be a probability.\n",
      "\n",
      "Now we can get back to Step 1.\n",
      "\n",
      "### Step 1: Constructing the prior\n",
      "\n",
      "Before the game starts, what should we believe about Germany's goal-scoring rate against Brazil?  We could use previous tournament results to construct the prior, but to keep things simple, I'll just use the average goal-scoring rate from all matches in the tournament, which was 2.67 goals per game (total for both teams).\n",
      "\n",
      "To construct the prior, I'll start with an unrealistic uniform distribution and update it with fake data until the mean matches the observed rate for a single team, 1.34 goals per game."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy\n",
      "import thinkplot\n",
      "\n",
      "hypos = numpy.linspace(0, 12, 201)\n",
      "suite = Soccer(hypos)\n",
      "suite.Update(134)                # fake data chosen by trial and error to yield the observed prior mean\n",
      "\n",
      "thinkplot.Pdf(suite)\n",
      "suite.Mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "1.3441732095365195"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEACAYAAABVtcpZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7fa89500bed0>"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Now that we have a prior, we can update with the time of the first goal, 11 minutes."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "suite.Update(11)                # time until first goal is 11 minutes\n",
      "thinkplot.Pdf(suite)\n",
      "suite.Mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "1.8620612271278361"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEACAYAAABVtcpZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7fa884095ad0>"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "After the first goal, the posterior mean rate is almost 1.9 goals per game.\n",
      "\n",
      "Now we update with the second goal:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "suite.Update(12)                # time between first and second goals is 12 minutes\n",
      "thinkplot.Pdf(suite)\n",
      "suite.Mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "2.2929790004763997"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEACAYAAABVtcpZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiIiIiIiIiIiIlPj/wN1HwND4YFxPwAAAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7fa86f028910>"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "After the second goal, the posterior mean goal rate is 2.3 goals per game.\n",
      "\n",
      "Now on to Step 3.\n",
      "\n",
      "### Step 3: The predictive distribution\n",
      "\n",
      "If we knew the actual goal scoring rate, $\\lambda$, we could predict how many goals Germany would score in the remaining $t = 90-23$ minutes.  The distribution of goals would be Poisson with parameter $\\lambda t$.\n",
      "\n",
      "We don't actually know $\\lambda$, but we can use the posterior distribution of $\\lambda$ to generate a predictive distribution for the number of additional goals."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def PredRemaining(suite, rem_time):\n",
      "    \"\"\"Plots the predictive distribution for additional number of goals.\n",
      "\n",
      "    suite: posterior distribution of lam in goals per game\n",
      "    rem_time: remaining time in the game in minutes\n",
      "    \"\"\"\n",
      "    metapmf = thinkbayes2.Pmf()\n",
      "    for lam, prob in suite.Items():\n",
      "        lt = lam * rem_time / 90\n",
      "        pred = thinkbayes2.MakePoissonPmf(lt, 15)\n",
      "        metapmf[pred] = prob\n",
      "        thinkplot.Pdf(pred, color='gray', alpha=0.3, linewidth=0.5)\n",
      "\n",
      "    mix = thinkbayes2.MakeMixture(metapmf)\n",
      "    return mix\n",
      "\n",
      "mix = PredRemaining(suite, 90-23)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEACAYAAABMEua6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nipeN/BIAAAAJSURBVPIG5/8H06YfKSlAHdoAAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7fa86efd4490>"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "`PredRemaining` takes the posterior distribution of $\\lambda$ and the remaining game time in minutes (I'm ignoring so-called \"injury time\").\n",
      "\n",
      "It loops through the hypotheses in `suite`, computes the predictive distribution of additional goals for each hypothesis, and assembles a \"meta-Pmf\" which is a Pmf that maps from each predictive distribution to its probability.  The figure shows each of the distributions in the meta-Pmf.\n",
      "\n",
      "Finally, `PredRemaining` uses `MakeMixture` to compute the mixture of the distributions.  Here's what the predictive distribution looks like."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "thinkplot.Hist(mix)\n",
      "thinkplot.Config(xlim=[-0.5, 10.5])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXYAAAEACAYAAACnJV25AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7fa86ec51990>"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "After the first two goals, the most likely outcome is that Germany will score once more, but there is a substantial chance of scoring 0 or 2--4 additional goals.\n",
      "\n",
      "Now we can answer the original questions: what is the chance of scoring 5 or more additional goals:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "mix.ProbGreater(4)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "0.057274188144370755"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "After the first two goals, there was only a 6% chance of scoring 5 more times.  And the expected number of additional goals was only 1.7."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "mix.Mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "1.7069804402488897"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "That's the end of this example.  But for completeness (and if you are curious), here is the code for `MakeMixture`:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def MakeMixture(metapmf, label='mix'):\n",
      "    \"\"\"Make a mixture distribution.\n",
      "\n",
      "    Args:\n",
      "      metapmf: Pmf that maps from Pmfs to probs.\n",
      "      label: string label for the new Pmf.\n",
      "\n",
      "    Returns: Pmf object.\n",
      "    \"\"\"\n",
      "    mix = Pmf(label=label)\n",
      "    for pmf, p1 in metapmf.Items():\n",
      "        for x, p2 in pmf.Items():\n",
      "            mix.Incr(x, p1 * p2)\n",
      "    return mix"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    }
   ],
   "metadata": {}
  }
 ]
}