{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "When will I win the Great Bear Run?\n", "-----------------------------------------\n", "\n", "This notebook presents an application of Bayesian inference to predicting the outcome of a road race.\n", "\n", "Copyright 2015 Allen Downey\n", "\n", "MIT License: http://opensource.org/licenses/MIT" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false }, "outputs": [], "source": [ "from __future__ import print_function, division\n", "\n", "import thinkbayes2\n", "import thinkplot\n", "\n", "import numpy as np\n", "from scipy import stats\n", "\n", "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Almost every year since 2008 I have participated in the Great Bear Run, a 5K road race in Needham MA. I usually finish in the top 20 or so, and in my age group I have come in 4th, 6th, 4th, 3rd, 2nd, 4th and 4th. In 2015 I didn't run because of a scheduling conflict, but based on the results I estimate that I would have come 4th again.\n", "\n", "Here are the people who beat me:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "data = {\n", " 2008: ['Gardiner', 'McNatt', 'Terry'],\n", " 2009: ['McNatt', 'Ryan', 'Partridge', 'Turner', 'Demers'],\n", " 2010: ['Gardiner', 'Barrett', 'Partridge'],\n", " 2011: ['Barrett', 'Partridge'],\n", " 2012: ['Sagar'],\n", " 2013: ['Hammer', 'Wang', 'Hahn'],\n", " 2014: ['Partridge', 'Hughes', 'Smith'],\n", " 2015: ['Barrett', 'Sagar', 'Fernandez'],\n", "}" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Having come close in 2012, I have to wonder what my chances of winning are.\n", "I'll try out two different models and see how it goes.\n", "\n", "First, a quick function to compute binomial distributions:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [], "source": [ "def MakeBinomialPmf(n, p):\n", " ks = range(n+1)\n", " ps = stats.binom.pmf(ks, n, p)\n", " pmf = thinkbayes2.Pmf(dict(zip(ks, ps)))\n", " pmf.Normalize()\n", " return pmf" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "###The binomial model\n", "\n", "The first model is based on the assumption that there is some population of runners who are faster than me, and who might show up for the Great Bear Run in any given year. The parameters of the model are the number of runners, $n$, and their probability of showing up, $p$.\n", "\n", "The following class uses this model to estimate the parameters from the data. It extends `thinkbayes.Suite`, which provides a simple framework for Bayesian inference.\n", "\n", "The `Likelihood` method computes the likelihood of the data for hypothetical values of $n$ and $p$. For each year, it computes the number of runners who beat me, $k$, and returns the probability of $k$ given $n$ and $p$.\n", "\n", "I explain `Predict` below." ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false }, "outputs": [], "source": [ "class Bear1(thinkbayes2.Suite, thinkbayes2.Joint):\n", " def Likelihood(self, data, hypo):\n", " n, p = hypo\n", " like = 1\n", " for year, sobs in data.items():\n", " k = len(sobs)\n", " if k > n:\n", " return 0\n", " like *= stats.binom.pmf(k, n, p)\n", " return like\n", " \n", " def Predict(self):\n", " metapmf = thinkbayes2.Pmf()\n", " for (n, p), prob in bear.Items():\n", " pmf = MakeBinomialPmf(n, p)\n", " metapmf[pmf] = prob\n", " mix = thinkbayes2.MakeMixture(metapmf)\n", " return mix" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The prior distribution for $n$ is uniform from 15 to 70 (15 is the number of unique runners who have beat me; 70 is an arbitrary upper bound).\n", "\n", "The prior distribution for $p$ is uniform from 0 to 1." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "outputs": [], "source": [ "hypos = [(n, p) for n in range(15, 70) \n", " for p in np.linspace(0, 1, 101)]\n", "bear = Bear1(hypos)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next we update `bear` with the data.\n", "The `Update` function is provided by `thinkbayes.Suite`; it computes the likelihood of the data for each hypothesis, multiplies by the prior probabilities, and renormalizes.\n", "\n", "The return value is the normalizing constant, which is total probability of the data under the prior (but otherwise not particularly meaningful)." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "1.007593000426606e-07" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "bear.Update(data)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "From the joint posterior distribution we can extract the marginal distributions of $n$ and $p$.\n", "\n", "The following figure shows the posterior distribution of $n$. The most likely value is 16; that is, we have already seen the entire population of runners. But the mean is almost 35.\n", "\n", "At the upper bound, the posterior probability is non-negligible, which suggests that higher values are possible. If I were attached to this model, I might work on refining the prior for $n$." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "33.853872514737439" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "pmf_n = bear.Marginal(0)\n", "thinkplot.PrePlot(5)\n", "thinkplot.Pdf(pmf_n, label='n')\n", "thinkplot.Config(xlabel='Number of runners (n)', \n", " ylabel='PMF', loc='upper right')\n", "pmf_n.Mean()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The posterior distribution for $p$ is better behaved. The credible interval is between 4% and 21%." ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "(0.040000000000000001, 0.22)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYwAAAEPCAYAAABRHfM8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nycv/BwWap2CcgY8wAAAAAElFTkSuQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "pmf_p = bear.Marginal(1)\n", "thinkplot.Pdf(pmf_p, label='p')\n", "thinkplot.Config(xlabel='Probability of showing up (p)', \n", " ylabel='PMF', loc='upper right')\n", "pmf_p.CredibleInterval(95)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The following figure shows the joint distribution of $n$ and $p$. They are inversely related: the more people there are, the less often they each show up." ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nzMwqOVCYmVklBwozM6v0/wFZ/bDQYdHFGQAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "thinkplot.Contour(bear, pcolor=True, contour=False)\n", "thinkplot.Config(xlabel='Number of runners (n)',\n", " ylabel='Probability of showing up (p)',\n", " ylim=[0, 0.4])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Finally, we can generate a predictive distribution for the number of people who will finish ahead of me, $k$. For each pair of $n$ and $p$, the distribution of $k$ is binomial. So the predictive distribution is a weighted mixture of binomials (see `Bear1.Predict` above).\n", "\n", "The most likely outcomes are 2 or 3 people ahead of me. The probability that I win my age group is about 5%." ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "0.051710821571831947" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "predict = bear.Predict()\n", "thinkplot.Hist(predict, label='k')\n", "thinkplot.Config(xlabel='# Runners who beat me (k)',\n", " ylabel='PMF', xlim=[-0.5, 12])\n", "predict[0]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "###A better model\n", "\n", "The binomial model is simple, but it ignores potentially useful information: from previous results, we can see that the same people appear more than once. We can use this data to improve our estimate of the total population.\n", "\n", "For example, if the same people appear over and over, that's evidence for smaller values of $n$. If the same person seldom appears twice, that's evidence for larger values.\n", "\n", "To quantify that effect, we need a model of the sampling process.\n", "In order to displace me, a runner has to\n", "\n", "1. **S**how up\n", "2. **O**utrun me\n", "3. **B**e in my age group\n", "\n", "For each runner, the probability of displacing me is a product of these factors:\n", "\n", "$p_i = SOB$\n", "\n", "Some runners have a higher SOB factor than others; we can use previous results to estimate it.\n", "\n", "But first we have to think about an appropriate prior. Based on my experience, I conjecture that the prior distribution of $S$ is an increasing function, with many people who run nearly every year, and fewer who run only occasionally:" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZIAAAEPCAYAAABoekJnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ss = thinkbayes2.Beta(2, 1)\n", "thinkplot.Pdf(ss.MakePmf(), label='S')\n", "thinkplot.Config(xlabel='Probability of showing up (S)',\n", " ylabel='PMF', loc='upper left')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The prior distribution of $O$ is biased toward high values. Of the people who have the potential to beat me, many of them will beat me every time. I am only competitive with a few of them.\n", "\n", "(For example, of the 16 people who have beat me, I have only ever beat 2)." ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZIAAAEPCAYAAABoekJnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiKyKP8TZOjrJG2x3RcAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "os = thinkbayes2.Beta(3, 1)\n", "thinkplot.Pdf(os.MakePmf(), label='O')\n", "thinkplot.Config(xlabel='Probability of outrunning me (O)',\n", " ylabel='PMF', loc='upper left')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The probability that a runner is in my age group depends on the difference between his age and mine. Someone exactly my age will always be in my age group. Someone 4 years older will be in my age group only once every 5 years (the Great Bear run uses 5-year age groups).\n", "\n", "So the distribution of $B$ is uniform." ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZkAAAEPCAYAAACQmrmQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nyJiZWTb/A00kqu/YXQBOAAAAAElFTkSuQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "bs = thinkbayes2.Beta(1, 1)\n", "thinkplot.Pdf(bs.MakePmf(), label='B')\n", "thinkplot.Config(xlabel='Probability of being in my age group (B)',\n", " ylabel='PMF', loc='upper left')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "I used Beta distributions for each of the three factors, so each $p_i$ is the product of three Beta-distributed variates. In general, the result is not a Beta distribution, but maybe we can find a Beta distribution that is a good approximation of the actual distribution.\n", "\n", "I'll draw a sample from the distributions of $S$, $O$, and $B$, and multiply them out. It turns out that the result is a good match for a Beta distribution with parameters 1 and 3." ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEPCAYAAABGP2P1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xl8VOXZ//HPNUNIWCWsIjsKKK2ggCwqGhUrbthiWQVk\nKaCtVq2tVm0ltk9rqbYq+tStiAV/IqhYfUBcaRQoiygQRFllR5EERCAsWe7fHzMJOZkkJCGTWfJ9\nv155cbY5c80hOdfcy7lvc84hIiKSzxfpAEREJLooMYiIiIcSg4iIeCgxiIiIhxKDiIh4KDGIiIhH\nWBODmb1gZnvMbE0px0wxs41mttrMzg9nPCIicnLhLjFMA/qXtNPMrgHOcs51ACYAT4c5HhEROYmw\nJgbn3EJgfymHDAD+FTx2GdDAzJqFMyYRESldpNsYWgA7Cq3vBFpGKBYRESHyiQHAiqxrjA4RkQiq\nEeH33wW0KrTeMrjNw8yULEREKsA5V/TL90lFOjG8BdwGvGJmvYHvnHN7ijtQg/0FpKamkpqaGukw\nooKuxQmxdi2cc6z+fA+vvvklX+85yHcHjpZ6fFbWEbKyssp0H9i2cR5tOlx7SvG1PsNo1zL0flq/\nntGgfrnvsxEzceLECr0urInBzGYClwKNzWwHMAlIAHDOPeuce9vMrjGzTcBhYEw44xGRqrfr6++Z\n/8EmNm/Zz5btB8jOzi32Bl+em39xEmuC3w8Jwbtaq+aGr4TK8uwc8PugaSMjKRHatjR8vhM3/ISE\nBLp3706XLl0qFEu0iMrE4JwbVoZjbgtnDCJSdZxz7M3MYv77m3hz/nrg1G/4AI0bQk5O4IberLHR\nqZ2PWknBnQa1k8AscGOfl1uDP/7x4pi/qUdSpKuSpJxSUlIiHULU0LU4IVLX4tuMw7w0ew2Llm6n\nfr1Evj94DChfMmh4GrRt5aNFM+O0eidu8EWV9Vt8x44dlRROkcVC3b2ZuViIUyRe5eTk8W3GYZ54\nZjnfHzxKUlICX67/ulwlAb8fOrY1GiUbDRsYtZKgZoI3CcRLFU60MLOYbHwWkQhzzrFh8z7Wbcgg\nISFQKb/7m4Ps3H2Q9LXeviDlrRbqca6PDu2MpMQEevTooRt+jFBiEKmG9uw9zK13zyt2X0XbBLr9\nwEfrFoHG3IQapm//MUyJQaQa2fTVPu5J/SBke3mTwQVdfCSfZiSflsAlfVUSiDdKDCJx6Hh2Lq/M\nWUsNv49dX3/P0hW7PDf9khJBvTrQvGmgSjonF2olQqNkI/k0o25t8PlUEqgOlBhE4oRzjhmz0tmb\nmcXiZTtC9heXDBrUh0t6+qlXh7jsxy8Vo8QgEsNycvL48OMtPPvip8XuL6lk0LQR9Onmp35dJQMJ\npcQgEoP2f3eU2+6Zz5Gj2Z7txSWCczsZYNRKMlo2N+rUCiQDJQIpiRKDSAw4fjyX7JxcNm3Zz0OT\nP/LsKy4ZdD3HR6MGgfYCVRFJeSkxiESxb/Yc4ue/eduzraTqoZbNjb49fNSooYfG5NQoMYhEqVVr\nvuEPj3wMlN6d9JrL/DRqoFKBVB4lBpEoNHDU7GKTgRk4FxhJ9JrL/NStrfYCqXxKDCJR5JOVu3n4\nsUUAIUlhxI/9BQPMKRFIOCkxiESBdxds5rF/LCq2uqhZY+PKi33UrFlTyUCqhBKDSITk5uYxdXoa\nL726vsShKC7r46Ndq0TGjNEcVlJ1lBhEqtj8d5fy/IxV7M3MK/GY05sYV1zoIzExUEoQqUpKDCJV\naMTEN9i+45sSSwid2tfg9gm96Nq1axVHJnKCEoNImKWnp7N06QpmzzvKseOh+82My/u25pZxl3J6\n07pVH6BIEUoMImGQnp7OkqUr+Hz9cb7akcf3B0OPMTP+9j830OP85iVOZykSCUoMIpXIOccrc9by\n9NTFpc5t0KNLAmNu6kWXLmdUYXQiZaPEIHKK8vIcQ8a9zsGDh0t8OtnMqF27NrVr1+IX4y7gikvb\nRSBSkbJRYhA5Bdk5uQwZ+zoQ+kAaBBJC48aNuLxvOy6/pC2dOzWJRJgi5aLEIFIBx47l8NRzH/Lm\n/K9KrDK6sHsCwwf1VA8jiTlKDCJlNPfdDTz9wlJq1cxiT0bxzyBcebGPZk1qMnHC2CqOTqTyKDGI\nlMFvJn3A5i37OHjwMN+XUEIYNsBPrSQ9kCaxT4lBpBSTn1jMfxZuKrVR+WcjOjNq+KURiE4kPJQY\nRIpwzpG2eBtPPrccCG1UbtvS+EHHmtw0fBCtWtSPVJgiYaPEIFLI09NW8Oa8tSWWELqc7aNHl0S6\nd++upCBxS4lBBNj/3VHG/fItoPhup73P83FOh5qMHatGZYl/SgxSbeXk5PHJyt088uR/S5w6s10r\no2M7Hy1OV6OyVB9KDFLtLPlkJ488+V/PtqJJoWdXHz/spHkQpHpSYpBq48jRbG69+22+P3gMoMRS\nwuBr/dStoxKCVF9KDFItfLkhgwf+Z4FnW+Gk0LGdcUGXwMQ4KiVIdafEIHFt1ZpveOqfn7Bv/5GQ\nEsIZTY3L+vjx+QJDXickJKiUIIISg8Sx1Mkfkb52T8F64aRwUXcf7Vv7gEBCUClB5ARfOE9uZv3N\nbJ2ZbTSze4vZ39jM3jGzVWb2uZmNDmc8Un0c+P4o6Wv3kJV1hIyMTPbuzShICiN+7PckBZUSRLys\ntMlETunEZn5gPdAP2AV8Agxzzn1Z6JhUINE5d5+ZNQ4e38w5l1PkXC5ccUr8OXjoGDf//E0AMjIy\ncc7RoplxXmcfDRuYSghSbZgZzrlyTw8YzqqknsAm59xWADN7BbgB+LLQMV8DXYLL9YHMoklBpDzW\nfPEtv3lwfkhvo8sv9AMqIYiURTgTQwtgR6H1nUCvIsc8Dywws91APWBwGOOROJZ1JJs773+XjMys\nkKQw/Aa/Sgki5RDOxFCWup/7gVXOuRQzOxN438y6OudCpk5PTU0tWE5JSSElJaWy4pQY9/Y7S/nL\nlJXFjm005Do/SYl6JkGqh7S0NNLS0k75POFsY+gNpDrn+gfX7wPynHOTCx3zNvAn59zi4PqHwL3O\nuRVFzqU2BgmRk5PH4LGvFbQjFDV2cC2VEqRai8Y2hhVABzNrC+wGhgDDihyzjkDj9GIzawZ0Ar4K\nY0wSJ/67fAePPrUEICQpXHuZn6aN1ZYgUlFhSwzOuRwzuw14F/ADU51zX5rZxOD+Z4E/A9PMbDWB\nrrP3OOf2hSsmiQ/LPt3FH/66IKQtoVYSzH/tFvz+sPbCFol7YatKqkyqSpKDh47x1bbveGjyRwAh\n1UcD+vlp3FDDWYgUFo1VSSKnLDc3j0FjXgNKHvRu5E9qqBuqSCVSYpCotemrfdyT+kHBetGk0KA+\nDOyvBmaRyqbEIFGrcFKAQCNzvTpw8HCgG2qd2uqGKhIOSgwSdfK7oRatOhp0jZ+kxEB16YQJEyIZ\nokhcU2KQqJKdk8uQsa8D3qqjkT858auakJAQkdhEqgslBokax4/nMmD4SyFtCZf1PtH9VI3MIuGn\nxCBRY+jPXg9JCj++0k/DZHVDFalKSgwSFT5avA3wPsU86Bo/9eqqgVmkqikxSEQtXfYZ9zy0LOTZ\nhOuv8PPL2ydGKCqR6k1jB0jEOOeKTQrNGkOTRjUjFJWIKDFIRHzz7SFuvPnVkKRwZhvj2strqfpI\nJIJUlSRV7pmpH/Ly6xtCksL8135G3ToqKYhEmkoMUqUyMrOKTQoD+iUqKYhECZUYpMpkHclmwl1z\nQ5LCmEFJ9OjRI0JRiUhRSgxSJdLT07ntt4tDksLC+T+PUEQiUhJVJUmVKC4pjBmUFKFoRKQ0SgwS\ndgNHzQ5JCqMGqvpIJFqpKknCYvXq1fz7/z7hg8XHQ/b94f5ruKxv26oPSkTKRIlBKt3GzZncft9/\nQ0oJAP0urqmkIBLllBik0uTlOaY8u5yPl2wrNilc3y+R/ldeEIHIRKQ8lBikUuTm5nHtkBnFzsk8\nfFBPJo7ujs9X7jnJRSQC1PgspywjM4tBY14rNimMGZTErWN7KCmIxBCVGOSUHD+ey4S75gLeIbMv\n7O7j7DMTNeaRSAxSYpAK+3T11zzwx/dCSgpDrvNz2y80ZLZIrFJikAo5fjyXP/1tYUhSGPFjPzVr\naswjkVimNgapkKE/ex3wVh8NGxBICqo+EoltKjFIuaSnpzN5yhL27s31bB/5kxpMmDAhQlGJSGVS\niUHKZdHiFWzf5U0KA6/yk5CQEKGIRKSyKTFImTnnmPnWUc+2qy7x0+A0VR+JxBNVJclJpaen8+mn\nn5K21JsUmjRpzO/uGxyhqEQkXJQY5KRWrFjB/314lIx9J7aZGbNf+GnkghKRsFFikFJ9tXU/0171\nlhTMjBGDOlGjhmoiReKREoOUaP4Hm3h++meebU2aNOaC889gwpiLIxSViISbFTcKZrQxMxcLccaT\nee8sYfKUVSFjH019cggdz2oUoahEpDzMDOdcuQcqU12AhNi247tik8LNNyYpKYhUA2GtSjKz/sDj\ngB/4p3NucjHHpACPAQlAhnMuJZwxSenuvP9dtu884EkKZjBmUC11SRWpJsJWlWRmfmA90A/YBXwC\nDHPOfVnomAbAYuAq59xOM2vsnMso5lyqSgqz9PR0bvvt4mIn2Fk4/+cRiEhETlU0ViX1BDY557Y6\n57KBV4AbihwzHHjdObcToLikIFXj0aeWhCSFWkmB+RREpHoJZ1VSC2BHofWdQK8ix3QAEszsP0A9\n4Ann3IwwxiTF2LLtO7bs8A5zkdLbR/vWmk9BpDoKZ2IoS91PAtANuAKoDSwxs6XOuY1hjEuKmPSX\nNM/6reMuYfhPfxiZYEQk4sKZGHYBrQqttyJQaihsB4EG5yPAETP7GOgKhCSG1NTUguWUlBRSUlIq\nOdzqZ9Wq1Tz3r2Vs2ZpTsK1mAkoKIjEqLS2NtLS0Uz5POBufaxBofL4C2A0sJ7Tx+WzgKeAqIBFY\nBgxxzn1R5FxqfK5kzjkuvfaZkHaFYQOS+PmtYyMUlYhUpoo2PoetxOCcyzGz24B3CXRXneqc+9LM\nJgb3P+ucW2dm7wDpQB7wfNGkIJVvzRffMukvaSFJwcy4+KIeEYpKRKKFnnyuRvZmHGbir+adWN97\nohPY/Xf/iMv7tiUxUaOkiMSLqCsxSHR57a0vePm1z8nKOhIyT/OAfn6u7ndWBKMTkWiixFANZOfk\n8vJrnwN4kkLrM4ze5/uoW6dmJMMTkSijxFAN3DThjYLl/KRw0w1+fD4jISFBzyqIiIcSQ5zbt/8I\nOTl5nm0jfxL4b58wYUIkQhKRKKfEEOeGj5/tqT4a2N8f4YhEJNpp2O04dujw8ZCG5jq1Ah0UEhIS\nIhWWiEQ5JYY4NurWf3uSwuBrA6UFtSuISGn0HEMc+njhCn738CchD7Bp+GyR6iUah92WCDienVts\nUhg1UMNni0jZKDHEmaHjXg9JCjdcmUivXhrqQkTKpsReSWb2onNudHD5Zufcv6osKqmQ56d/FrJN\n1UciUl6llRi6Flq+M9yByKmZ+95G5n+wybNt6PXqmioi5afnGOLAC/9vFbPfWO3pmtrtBz4SapS7\nzUlEpNTE0NLMpgAGtCi0DOCcc78Me3RyUmmLtzL33Q0hzyv8oKNPzyqISIWUlhh+Q2B6TgM+LbJP\nfUejwMbNmUx5djlwYgykFqcbl/fx61kFEakwPccQo747cJSxt79VsL53bwbNmxr9LvJrDCQRAcL0\nHIOZjTazz8wsK/izwsxurniYUhkyMrMYOm4WGRmZ7N2bUTDhTr+L1NgsIqeutO6qNwN3AL8CVhKo\nUjofeCT4DX561YQoRU24a25Im0L+iKlqVxCRU1VaieHnwEDn3H+cc9855/Y75xYANwK/qJrwpKit\n278D8CSFm27QGEgiUnlKa3yu55zbUnSjc26rmdULY0xSgs1b9/ObB9/3bBt2vZ9bbpkYoYhEJB6V\nlhiOVnCfhMkvfv2Wpwop+TSooWcVRKSSlZYYzjGzNSXsOzMcwUjJUid/FNKucNUlfrUpiEilKy0x\ndAGaATuLbG8FfB22iCTEocPHSV+7J6SxWW0KIhIOpSWGx4HfOue2Ft5oZvWBx4DrwxiXFDLvvY2e\n9b4X+PSsgoiETWmJoZlzLqQqyTmXbmbtwhiTFPKHyfP44KPtntJC25YaLV1Ewqe0O0yDUvZp1pcq\nsHnr/pCk0P1cjYEkIuFVWmJYYWYh9RVmNp7QsZOkkjnn+M2D74dMutP1nES1K4hIWJVWlXQn8IaZ\n3cSJRNAdSAR+Eu7Aqru573rbFRJrwgdvatIdEQm/EhODc+4bM7sQuAz4IYERVecGn36WMDpyNJtp\nL6/ybBvQT+MgiUjVKHWinuCQpguCP1IFXp2ziCf/ucZThdSnm4+kRD3IJiJVQ91bokzRpABwVhs1\nOItI1VFiiCIvzQ5NCoOv1aQ7IlK1NOdzlMjcl8WcuV96ti2cr8ZmEal6SgxRID09ndt+u9hTWuj2\nQxXmRCQydPeJAitWrAipQjqvc2KEohGR6k6JIQpMe9U7ivnonyapTUFEIiasicHM+pvZOjPbaGb3\nlnLcBWaWY2YDwxlPNFq4ZLtnvUmTxowbN5YuXbpEKCIRqe7ClhjMzA88BfQHOgPDzOycEo6bDLxD\nYF7pauWxp5d61v85RYPWikhkhbPE0BPY5Jzb6pzLBl4BbijmuNuB14C9YYwl6qSnp3PJNU+zd29G\nwbb2rY2GDWpFMCoRkfAmhhbAjkLrO4PbCphZCwLJ4ungJm8LbJzKzskN6YUEkNJbg9aKSOSFMzGU\n5SafPxmQI1CNVC2qkp6Z9mlIUvjxjzRqqohEh3A+x7CLwDSg+VoROk1od+AVMwNoDFxtZtnOubeK\nniw1NbVgOSUlhZSUlEoOt2o45/jPwq2ebTOeHU7b1qVNfyEicnJpaWmkpaWd8nms6DfXymJmNYD1\nwBXAbmA5MMw592UJx08D/s85N6eYfS5ccVa1ERPfIOtIdkHbwiU9ffzpoVsiHJWIxCMzwzlX7pqY\nsJUYnHM5ZnYb8C7gB6Y65740s4nB/c+G672jUXp6Or/6/WKOHfcmuDYt9CiJiESXsA6J4ZybD8wv\nsq3YhOCcGxPOWCJt1pzlIUnhwm4aNVVEoo++rlaB7w4c5eNlxz3bzuvs4+yz1OAsItFHg+iF2Tff\nHuLnv37bs+0X4y9l6MAfRCgiEZHSqcQQRvv2HwlJCoCSgohENZUYwiRzXxY3TXiVrKwszzMLwwdo\n7mYRiW5KDGEy/s65IUlhxI/91KxZM4JRiYicnKqSwmDay6sAik0KamwWkWinEkMlystzPPrUEpau\n8D7gPex6PxMnToxQVCIi5aPEUEmOH89l6M9eD9l+XmcfNWpUiyGgRCROKDFUkqE/e52srCOedoUW\nzYwfdlRSEJHYosRQCXJy8gA8SeHSnj5aB4e70NPNIhJLlBgqweCxrwEnGpuHXu8nIVh9lJCQoAZn\nEYkpSgyn6OtvDoZsS6hhTJgwIQLRiIicOnVXPUUvzlztWb+xvx5gE5HYphLDKcjNzeOjxZsL2hZO\nqwe1a6mxWURim0oMp2DQmNc8Dc49u6qxWURinxJDBeU/xFb46ebTm/jU2CwiMU9VSRXgnOOvU/7r\n2fbTq/1qcBaRuKASQwX8d7l3yIvGyVArSW0LIhIfVGKogD8+ssDTtnDVJeqJJCLxQyWGcnrkySWe\npFC/Lvh8pgZnEYkbSgzlcOxYDks+2eFpcB7Qz68GZxGJK6pKKodh4+d41lN6+zSctojEHZUYyuiJ\nZ5eFbGvVXJdPROKPSgxl8OGC5bz+5meeKqQh16nBWUTik77ylsFDj37qSQod2xk1E9TgLCLxSYnh\nJDZt2edJCgC9zlODs4jEL1UlncQ9kz7wrL/3xnhqJamkICLxSyWGUmzb8V3INiUFEYl3Sgwl2Lg5\nk7seeM+zbdgANTiLSPxTVVIxnHPcfu9czxPOZzQzavg1HpKIxD+VGIox4a55nqQAcGkvn3ohiUi1\noBJDITk5eQwe+xrgnWdh5E9qqBeSiFQbSgxBzrmCpFDY1ZdqngURqV5UlRR0482vhmy7rLePxg3V\nriAi1YtKDED62j0AZGUdKWhbGHiVnzq1lRREpPpRiQFInfwRQLFJQQ3OIlLdhD0xmFl/M1tnZhvN\n7N5i9t9kZqvNLN3MFptZl3DHVFjWkeyCZeccLZubJymowVlEqpuwViWZmR94CugH7AI+MbO3nHNf\nFjrsK+AS59wBM+sPPAf0DmdchY2Y+IZn/bLegYfY1OAs8cxM1aTxpuiYbqci3G0MPYFNzrmtAGb2\nCnADUJAYnHNLCh2/DGgZ5pgKvP3+xqp6K5GoU5k3Eomsyk704U4MLYAdhdZ3Ar1KOX4c8HZYIyLw\nB1FcLyTNsSAiEv7EUOavJGZ2GTAWuKi4/ampqQXLKSkppKSkVDiov/9jKeDthdT6DKNmghKDiMSu\ntLQ00tLSTvk8Fs7ipJn1BlKdc/2D6/cBec65yUWO6wLMAfo75zYVcx5XWXEWLi1kZGTinKNFM+Oy\nPr6C4lhCQgJjxoyplPcTiUZmpqqkOFLS/2dwe7nrmcJdYlgBdDCztsBuYAgwrPABZtaaQFIYUVxS\nqGxvzF1XsOyc46IePtq3OtE5Sz2RRKS6C2ticM7lmNltwLuAH5jqnPvSzCYG9z8LPAgkA08Hv7Fn\nO+d6hiuml15d41nPTwrqhSQSn7Zu3Ur79u3JycnB5yu9h/6LL77I1KlTWbhwYRVFF53C/hyDc26+\nc66Tc+4s59zDwW3PBpMCzrmfOecaOefOD/6ELSk89NePPesXddfzfSLRpm3btiQmJpKZmenZfv75\n5+Pz+di+fXuEIqs+qs2dcWX6N6z+/BvPtvatq83HF4kZZkb79u2ZOXNmwbY1a9Zw5MgRPX9RRarF\nnfF4di5/fDRQWsjKOkJGRiY/OHNfhKMSkZKMGDGC6dOnF6z/61//YtSoUQUNrAcOHGDUqFE0bdqU\ntm3b8qc//algX15eHr/+9a9p0qQJZ555JvPmzfOc+8CBA4wbN44zzjiDli1b8vvf/568vLyq+3Ax\nIO4H0du4OZN7H/qwYD0rK4tGDRytmp/omqrxkES8nnvuuUo7V0Xa73r37s2MGTNYt24dHTp0YNas\nWSxevJjf/e53gRkWb7+dgwcPsmXLFjIyMvjRj35E8+bNGTt2LM899xzz5s1j1apV1K5dm4EDB3pK\nGqNHj+b0009n8+bNHDp0iOuuu45WrVqpnbGQuC8xFE4KEOiJ1P9Sb1JQLySR6DNy5EimT5/O+++/\nT+fOnWnRogUAubm5zJo1i4cffpg6derQpk0b7r77bmbMmAHA7Nmzueuuu2jRogXJycncf//9BaWJ\nPXv2MH/+fB577DFq1apFkyZNuPPOO3nllVci9jmjUVyXGFas2h2ybdj1/oJvD/qGIBKdzIyRI0fS\nt29ftmzZ4qlGysjIIDs7mzZt2hQc37p1a3bt2gXA119/TatWrTz78m3bto3s7GyaN29esC0vL89z\njMR5Yvjz3xd51udMH1ypRWSReBUNX5pat25N+/btmT9/Pi+88ELB9saNG5OQkMDWrVs555xzANi+\nfTstWwaGWWvevLmn51Lh5VatWhX0eDpZ19XqLG6vzPadBzzr7dsmRygSEamoqVOnsmDBAmrVqlWw\nze/3M3jwYB544AEOHTrEtm3beOyxxxgxYgQAgwcPZsqUKezatYv9+/fzl7/8peC1zZs350c/+hG/\n+tWvOHjwIHl5eWzevJmPP/445L2rs7hMDLm5edx5/7sF61lZRzinzQ6VFkRiTPv27enWrVvBuplh\nZjz55JPUqVOH9u3b07dvX2666aaCYWzGjx/PVVddRdeuXenRowc33nijp/F5+vTpHD9+nM6dO9Ow\nYUMGDRrEN9984zl/dRfWsZIqS3nHSnrimWV89N9tBesZGZmM+LF3gDyNhyTVmcZKii+VPVZSXJYY\nCicFgOEDvB9TPZFEREoWd43PU19a6Vn/5cSebFj7XsF6NDSqiYhEs7gqMeTm5jHvPe+sbCkXtY1M\nMCIiMSquEsPz072lhbt/0SdCkYiIxK64qkp67z+bgRMzs61dPZ+1qyMclIhIjImbEsPejMMFy1lZ\nWfQ4N7QhXmMiiYicXNwkhom/OjGConOOju28iUE9kUREyiauqpIK8/k0HpKISEXERYnhm28PedaH\nXu8v4UgRkeg1evRofv/730c6jPhIDHP+b51nPaGGHmkXiWWLFi3iwgsvpEGDBjRq1IiLL76YFStW\nFOzfuXMnN910E40bN6Zu3br06tUrZEIen89H3bp1qVevHk2aNGH48OEcOHCg6FtFlWgZkiMuEsMH\nH31VMDPbkcMZkQ5HRE7B999/z3XXXccdd9zB/v372bVrF5MmTSIxMRGAffv2cfHFF5OUlMQXX3xB\nZmYmd911F8OHD+f111/3nCs9PZ2DBw/y1VdfsX//flJTUyPwiconGoYqifnEcPu97wCBnkjOOfr2\n1MxsIrFsw4YNmBlDhgzBzEhKSuLKK6/k3HPPBeCxxx6jfv36TJ06laZNm5KYmMjQoUN54IEHuPvu\nu4s9Z7169bj++uv54osvSnzfyZMn07JlS+rXr8/ZZ5/NggULAFi+fDl9+vQhOTmZM844g9tvv53s\n7OyC1/l8Pp5++mk6dOhA/fr1efDBB9m8eTN9+vShQYMGDB06tOD4tLQ0WrZsycMPP0yTJk1o164d\nL7/8cokxzZ07l/POO4/k5GQuuugi1qxZU+7rWREx3fj8zbeH2PX198CJLNs4OVAMUy8kkYobOGp2\npZ1rzvTB5Tq+U6dO+P1+Ro8ezdChQ+nVqxfJySeGzX///fe58cYbQ143aNAgfvvb37Jx40Y6dOgA\nnLgv7N+/n3//+99ceOGFxb7n+vXr+d///V9WrFjB6aefzvbt28nJyQGgRo0aPPHEE/To0YMdO3Zw\n9dVX849//IM77rij4PXvvfceK1euZPv27Zx//vksWrSImTNn0rBhQ/r06cPMmTMZNWoUEJhFLjMz\nk927d7P61gxMAAAOoUlEQVRkyRKuueYaLrjggoKY861cuZJx48Yxd+5cevTowYwZMxgwYADr16+n\nZs2a5bqm5RXTJYZnXvjUs97j3MDHmTBhAmPGjKFLly6RCEtETkG9evVYtGgRZsb48eNp2rQpN9xw\nA99++y0AmZmZnhnY8uVvy8g4UZ3crVs3kpOTadKkCTt37iyxl6Lf7+fYsWOsXbuW7OzsgkmC8s/R\ns2dPfD4fbdq0YcKECXz00Uee199zzz3UrVuXzp07c+6553L11VfTtm1b6tevz9VXX83Kld5RGf74\nxz+SkJDAJZdcwrXXXsusWbMK9uW3MTz33HNMnDiRCy64ADNj1KhRJCYmsnTp0vJe0nKL6cSQ/sUe\nz/o5Z8X0xxGRoLPPPptp06axY8cOPv/8c3bv3s2dd94JBGZw2707dNrer7/+umB/vpUrV7J//36O\nHj3KLbfcQt++fTl27FjIa8866ywef/xxUlNTadasGcOGDSs434YNG7juuuto3rw5p512Gg888ACZ\nmZme1zdr1qxguVatWp71pKQkDh060XMyOTnZM/FQmzZtCt6rsG3btvG3v/2N5OTkgp+dO3cWe2xl\ni9mqpBmz0z3rl1+opCBSWcpb/RNOnTp14uabby6YaKtfv37MmTOHSZMmeXrwzJ49m9atW4dUyUCg\nOmjcuHHceeedrF271jP5T75hw4YxbNgwDh48yMSJE7n33nuZPn06t956K927d2fWrFnUqVOHxx9/\nPKSRuzRFexnt37+frKwsateuDQQSQHG1G61bt+aBBx7g/vvvL/N7VZaYvZu+MdfbRfWMppHv4iUi\np279+vX8/e9/Z9euXQDs2LGDmTNn0qdPYFDMu+66iwMHDjBu3Dj27NnD0aNHmTlzJn/+85955JFH\nPOfKb2PIzc1l2rRp1K5du6CKqLANGzawYMECjh07RmJiIklJSfj9gY4shw4dol69etSuXZt169bx\n9NNPn/QzFO5ZVFwvo0mTJpGdnc3ChQuZN28egwYNKjg2//jx48fzzDPPsHz5cpxzHD58mHnz5nlK\nH+ESk4lhTjAp5HdRPavVvqjo+ysip65evXosW7aMXr16UbduXfr06UOXLl3429/+BkDDhg1ZtGgR\nR48epXPnzjRu3JjHH3+cl156qeAGm69r167Uq1ePhg0bMmPGDN544w0aNGgQ8p7Hjh3jvvvuo0mT\nJjRv3pyMjAwefvhhAB599FFefvll6tevz4QJExg6dKjnflPcvafo/sLrp59+ekEPp5EjR/Lss8/S\nsWPHkGO7d+/O888/z2233UbDhg3p0KED06dPr+hlLZeYnNozv8dERkYmzjlG/uREjZim7BQ5OU3t\nGRlpaWmMHDmSHTt2VOp5NbVnIc45OrQ98ZnVRVVE5NTFXOPz9FneRucfdjzRRVVEJNrFQrV3zJUY\n/j3P2+hct070X2QREYCUlBS2b98e6TBOKqYSw31/+NCzfmG3mApfRCQmxExVUkZmFivTdxaMiQTQ\n/+KYCV9EJGbEzFfuCXfN9SSFy3qfCF2D5YmIVJ6Y+spduDtWy+aBxKCeSCIVEwuNoBIZYU0MZtYf\neBzwA/90zk0u5pgpwNVAFjDaObey6DFFDb7Wr15IIqdAzzBIacJWlWRmfuApoD/QGRhmZucUOeYa\n4CznXAdgAnDyZ82BxJrV95tOWlpapEOIGroWJ+hanKBrcerC2cbQE9jknNvqnMsGXgFuKHLMAOBf\nAM65ZUADM2tGKa6/onrP56xf+hN0LU7QtThB1+LUhTMxtAAKP/e9M7jtZMe0LO2kDepX39KCiEhV\nCGdiKGslZtE7fbGv27s3gys0tLaISNiFbRA9M+sNpDrn+gfX7wPyCjdAm9kzQJpz7pXg+jrgUufc\nniLnUkuZiEgFVGQQvXD2SloBdDCztsBuYAgwrMgxbwG3Aa8EE8l3RZMCVOyDiYhIxYQtMTjncszs\nNuBdAt1VpzrnvjSzicH9zzrn3jaza8xsE3AY0HjZIiIRFhPzMYiISNWJqtZcM+tvZuvMbKOZ3VvC\nMVOC+1eb2flVHWNVOdm1MLObgtcg3cwWm1nopLFxoiy/F8HjLjCzHDMbWJXxVZUy/n2kmNlKM/vc\nzNKqOMQqU4a/j8Zm9o6ZrQpei9ERCLNKmNkLZrbHzNaUckz57pv5c4xG+odAddMmoC2QAKwCzily\nzDXA28HlXsDSSMcdwWvRBzgtuNy/Ol+LQsctAOYCN0Y67gj9TjQA1gItg+uNIx13BK9FKvBw/nUA\nMoEakY49TNejL3A+sKaE/eW+b0ZTiSEsD8TFqJNeC+fcEufcgeDqMk7y/EcMK8vvBcDtwGvA3qoM\nrgqV5ToMB153zu0EcM5lVHGMVaUs1+JroH5wuT6Q6ZzLqcIYq4xzbiGwv5RDyn3fjKbEEJYH4mJU\nWa5FYeOAt8MaUeSc9FqYWQsCN4b8IVXiseGsLL8THYCGZvYfM1thZiOrLLqqVZZr8TzwAzPbDawG\n7qii2KJRue+b0TS6aqU+EBfjyvyZzOwyYCxwUfjCiaiyXIvHgd8655wFhgyNx+7NZbkOCUA34Aqg\nNrDEzJY65zaGNbKqV5ZrcT+wyjmXYmZnAu+bWVfn3MEwxxatynXfjKbEsAtoVWi9FYHMVtoxLYPb\n4k1ZrgXBBufngf7OudKKkrGsLNeiO4FnYSBQn3y1mWU7596qmhCrRFmuww4gwzl3BDhiZh8DXYF4\nSwxluRYXAn8CcM5tNrMtQCcCz1dVN+W+b0ZTVVLBA3FmVpPAA3FF/7DfAkZBwZPVxT4QFwdOei3M\nrDUwBxjhnNsUgRirykmvhXOuvXOunXOuHYF2hlvjLClA2f4+3gQuNjO/mdUm0ND4RRXHWRXKci3W\nAf0AgvXpnYCvqjTK6FHu+2bUlBicHogrUJZrATwIJANPB78pZzvnekYq5nAp47WIe2X8+1hnZu8A\n6UAe8LxzLu4SQxl/J/4MTDOz1QS+AN/jnNsXsaDDyMxmApcCjc1sBzCJQLVihe+besBNREQ8oqkq\nSUREooASg4iIeCgxiIiIhxKDiIh4KDGIiIiHEoOIiHgoMUi5mFlucFjnNWY228xqleO1o83syXK+\n36EStj9kZpcHl9PMrFtweZ6Z1Tez08zs1vK810nieCQ4fPPkkxy31cwaBpcXV/C9XjSzGyvwujPM\n7NWKvKdIYUoMUl5ZzrnznXPnAseBWwrvNLPSHpqsyEMzxb7GOTfJObeg6DHOuWudc98TePjv5xV4\nv5KMB851zpU4H0QxsVR0/CpHBa6Vc263c25QBd9TpIASg5yKhcBZZnapmS00szeBz80s0cymBScR\n+szMUgq9plVw9M8NZvZg/kYzeyM4IujnZja+8JuY2d+D2z8ws8bBbcV+qw5+Y28E/AU4M1i6+auZ\n/cvMbih03P8zswHFvP6RYGko3cwGB7e9BdQFPsvfVuj4Rmb2XjC+5yk0WFl+acfMmpvZx4VKWhfl\n7y/usxU5/4Nmtjz4umcLbT8r+JpVZvapmbULDhGxJrh/tJnNMbP5wWs9udBrx5nZejNbZmbPF1eK\nM7PU4DX7OHhNB5rZo8HrMj//C4CZdQ+W2FZYYGKc04ueS2JQpCeZ0E9s/QAHg//WIDA2z0QCj+Mf\nAtoE990N/DO43AnYBiQCo4HdBL7NJwFrgO7B45KD/9YKbs9fzwOGBZd/DzwZXJ4GDAwu/wfoFlze\nAjQE2lBo4hLgEuCN4PJpBMbN8RX5bDcC7xG4uTcNxt2s8Ocu5npMAX4XXL4mGG/DItfqbuD+4LIP\nqFuGz3Zj4esSXJ4OXBdcXgbcEFyuGbxubfM/c/BabwbqBa/9VgLDL58RvEYNgv+HHwNTivlcqcF9\nfqALkAVcFdw3h8Aw5wnAf4FGwe1DCAxPEfHfU/2c2o9KDFJetcxsJfAJgZvNCwRupMudc9uCx1wE\nvATgnFtP4AbbkUD1yHvOuf3OuaMEbjAXB19zh5mtApYQGAmyQ3B7HjAruPxSoeNPxjPMsHPuYwID\nrzUGhgGvOefyirzmIuBlF/At8BFwwUnep2+hz/o2xU+YshwYY2aTCFRH5beblPbZ8quSLjezpWaW\nDlwOdDazesAZzrk3g+973AVGVC3qQ+fcQefcMQKD6bUlMMnNR86571xg4ppXKX6YcgfMd87lAp8T\nSKLvBvetCZ6rI/AD4IPg78QDlD5viMSIqBlET2LGEeecZ85YCwzid7jIcWWZE8EAF6xqugLo7Zw7\namb/IVCiKPb4ckd8wnRgJIFvtqNLiam45dKUepxzbqGZ9QWuA140s78752YUcw7PZzOzJOB/CZSq\ndgUTS1LR40pxrNByLoG/96KvLS3248H488wsu9D2vOC5DFjrnLuwjPFIjFCJQcJhIXATgJl1BFoT\nGAbZgCvNLNkCvZluABYRmHpxfzApnA30LnQuH5DfoDo8eO6yOEigGqWwF4E7AeecW1dC3EPMzGdm\nTQiUBpaf5H0+DsaFmV1NoJrMwwJDpO91zv0TmEpgfl44+WfLT46ZZlY3/9hgiWNnfptJsE2nLL3D\nHIGS3qVm1iDYTnAjFU+264EmFhjKGTNLMLPOFTyXRBElBimv4m4iRXvR/APwBas/XgFudoG5eR2B\nG+3rBKZbfM059xnwDlDDzL4AHiZQnZTvMNAz2KiaAvyhTEE6lwksDjbaTg5u+5ZAlcq0El7zBoEh\nq1cDHwK/Cb6mpM8N8BBwiZl9DvyEQLVZwSmD/14GrDKzzwjc3J8oy2dzzn1HYCKmzwlco2WFdo8E\nfmmBYaUXA/lz+LpC/4bE7JzbTWBI6uUEkvIW4PsSPpsrYTl4KpcN/BSYHKwGXAn0KeFcEkM07LZU\nGxaYvCYdON9FwRSPZnbQOVe0VFMV71vHOXc4WGKYQ6DB+M2qjkOil0oMUi2YWT8CpYUp0ZAUgiL1\nrSw12Fi8BvhKSUGKUolBREQ8VGIQEREPJQYREfFQYhAREQ8lBhER8VBiEBERDyUGERHx+P+T37Qn\nlzmprgAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "n = 1000\n", "sample = ss.Sample(n) * os.Sample(n) * bs.Sample(n)\n", "cdf = thinkbayes2.Cdf(sample)\n", "\n", "thinkplot.PrePlot(1)\n", "\n", "prior = thinkbayes2.Beta(1, 3)\n", "thinkplot.Cdf(prior.MakeCdf(), color='grey', label='Model')\n", "thinkplot.Cdf(cdf, label='SOB sample')\n", "thinkplot.Config(xlabel='Probability of displacing me',\n", " ylabel='CDF', loc='lower right')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now let's look more carefully at the data. There are 16 people who have displaced me during at least one year, several more than once.\n", "\n", "The runner with the biggest SOB factor is Rich Partridge, who has displaced me in 4 of 8 years. In fact, he outruns me almost every year, but is not always in my age group." ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "(15,\n", " Counter({'Partridge': 4, 'Barrett': 3, 'Gardiner': 2, 'McNatt': 2, 'Sagar': 2, 'Demers': 1, 'Hughes': 1, 'Hahn': 1, 'Wang': 1, 'Smith': 1, 'Ryan': 1, 'Terry': 1, 'Turner': 1, 'Hammer': 1, 'Fernandez': 1}))" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from itertools import chain\n", "from collections import Counter\n", "\n", "counter = Counter(chain(*data.values()))\n", "len(counter), counter" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The following function makes a Beta distribution to represent the posterior distribution of $p_i$ for each runner. It starts with the prior, Beta(1, 3), and updates it with the number of times the runner displaces me, and the number of times he doesn't." ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def MakeBeta(count, num_races, precount=3):\n", " beta = thinkbayes2.Beta(1, precount)\n", " beta.Update((count, num_races-count))\n", " return beta" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we can make a posterior distribution for each runner:" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "collapsed": false }, "outputs": [], "source": [ "num_races = len(data)\n", "betas = [MakeBeta(count, num_races) \n", " for count in counter.values()]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's check the posterior means to see if they make sense. For Rich Partridge, who has displaced me 4 times out of 8, the posterior mean is 42%; for someone who has displaced me only once, it is 17%.\n", "\n", "So those don't seem crazy." ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "[0.16666666666666666,\n", " 0.16666666666666666,\n", " 0.16666666666666666,\n", " 0.16666666666666666,\n", " 0.25,\n", " 0.16666666666666666,\n", " 0.16666666666666666,\n", " 0.25,\n", " 0.25,\n", " 0.16666666666666666,\n", " 0.4166666666666667,\n", " 0.16666666666666666,\n", " 0.16666666666666666,\n", " 0.16666666666666666,\n", " 0.3333333333333333]" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "[beta.Mean() for beta in betas]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we're ready to do some inference. The model only has one parameter, the total number of runners who could displace me, $n$. For the 16 SOBS we have actually observed, we use previous results to estimate $p_i$. For additional hypothetical runners, we update the distribution with 0 displacements out of `num_races`.\n", "\n", "To improve performance, my implementation precomputes the distribution of $k$ for each value of $n$, using `ComputePmfs` and `ComputePmf`.\n", "\n", "After that, the `Likelihood` function is simple: it just looks up the probability of $k$ given $n$." ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": true }, "outputs": [], "source": [ "class Bear2(thinkbayes2.Suite, thinkbayes2.Joint):\n", "\n", " def ComputePmfs(self, data):\n", " num_races = len(data)\n", " counter = Counter(chain(*data.values()))\n", " betas = [MakeBeta(count, num_races) \n", " for count in counter.values()]\n", " \n", " self.pmfs = dict()\n", " low = len(betas)\n", " high = max(self.Values())\n", " for n in range(low, high+1):\n", " self.pmfs[n] = self.ComputePmf(betas, n, num_races)\n", " \n", " def ComputePmf(self, betas, n, num_races, label=''):\n", " no_show = MakeBeta(0, num_races)\n", " all_betas = betas + [no_show] * (n - len(betas))\n", " \n", " ks = []\n", " for i in range(2000):\n", " ps = [beta.Random() for beta in all_betas]\n", " xs = np.random.random(len(ps))\n", " k = sum(xs < ps)\n", " ks.append(k)\n", " \n", " return thinkbayes2.Pmf(ks, label=label)\n", " \n", " def Likelihood(self, data, hypo):\n", " n = hypo\n", " k = data\n", " return self.pmfs[n][k]\n", " \n", " def Predict(self):\n", " metapmf = thinkbayes2.Pmf()\n", " for n, prob in self.Items():\n", " pmf = bear2.pmfs[n]\n", " metapmf[pmf] = prob\n", " mix = thinkbayes2.MakeMixture(metapmf)\n", " return mix" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here's what some of the precomputed distributions look like, for several values of $n$.\n", "\n", "If there are fewer runners, my chance of winning is slightly better, but the difference is small, because fewer runners implies a higher mean for $p_i$." ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "bear2 = Bear2()\n", "\n", "thinkplot.PrePlot(3)\n", "pmf = bear2.ComputePmf(betas, 18, num_races, label='n=18')\n", "pmf2 = bear2.ComputePmf(betas, 22, num_races, label='n=22')\n", "pmf3 = bear2.ComputePmf(betas, 26, num_races, label='n=24')\n", "thinkplot.Pdfs([pmf, pmf2, pmf3])\n", "thinkplot.Config(xlabel='# Runners who beat me (k)',\n", " ylabel='PMF', loc='upper right')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For the prior distribution of $n$, I'll use a uniform distribution from 16 to 35 (this upper bound turns out to be sufficient)." ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": false }, "outputs": [], "source": [ "low = 15\n", "high = 35\n", "bear2 = Bear2(range(low, high))\n", "bear2.ComputePmfs(data)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "And here's the update, using the number of runners who displaced me each year:" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false }, "outputs": [], "source": [ "for year, sobs in data.items():\n", " k = len(sobs)\n", " bear2.Update(k)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here's the posterior distribution of $n$. It's noisy because I used random sampling to estimate the conditional distributions of $k$. But that's ok because we don't really care about $n$; we care about the predictive distribution of $k$. And noise in the distribution of $n$ has very little effect on $k$." ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "thinkplot.PrePlot(1)\n", "thinkplot.Pdf(bear2, label='n')\n", "thinkplot.Config(xlabel='Number of SOBs (n)',\n", " ylabel='PMF', loc='upper right')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The predictive distribution for $k$ is a weighted mixture of the conditional distributions we already computed:" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": false }, "outputs": [], "source": [ "predict = bear2.Predict()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "And here's what it looks like:" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "0.017104683992857313" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "thinkplot.Hist(predict, label='k')\n", "thinkplot.Config(xlabel='# Runners who beat me (k)', ylabel='PMF', xlim=[-0.5, 12])\n", "predict[0]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "According to this model, my chance of winning my age groups is less than 2%, which is more pessimistic than the results from the binomial model, about 5%." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] }, { "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": "2.7.11" } }, "nbformat": 4, "nbformat_minor": 0 }