The Internation 2014 Prize Pool Prediction

gistfile1.txt

{
 "metadata": {
  "name": "",
  "signature": "sha256:b3cc84a8e3da6c5df0957c9258a407f6a771ff218bad3cc6164a788167eedbc6"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# The International 2014 Prize Pool Prediction\n",
      "\n",
      "Hi. This is just a simple attempt to predict the final prize pool. After all, I gotta know, if I'll get my taunt!\n",
      "\n",
      "__Scroll to the bottom to see the final graph and the date we'll reach 8 mil__"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from __future__ import print_function, division\n",
      "# import some statistics libraries (if you want to it yourself, I recommend using anaconda to install them)\n",
      "import pandas as pd\n",
      "import statsmodels.formula.api as smf\n",
      "import seaborn\n",
      "%pylab inline\n",
      "pylab.rcParams['figure.figsize'] = 12, 9"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Populating the interactive namespace from numpy and matplotlib\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# just copied data from Matt's website http://dota2.cyborgmatt.com/prizetracker/international2014\n",
      "standings = [1.6, 2.862, 3.412, 3.887, 4.459, 4.751, 5.032, 5.294, 5.557, 5.757, 5.920, 6.077]\n",
      "data = pd.DataFrame(standings, index=range(1, len(standings) + 1), columns=['Prize'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data['Prize'].plot()\n",
      "ylabel(\"Prize in Mio USD\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "<matplotlib.text.Text at 0x7faed69288d0>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAssAAAIZCAYAAABQ/nL/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7faf00338110>"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Fit the simple model to the existing data\n",
      "data['Day'] = data.index\n",
      "res = smf.ols(formula='Prize ~ log(Day)', data=data[:len(standings)]).fit()\n",
      "del data['Day']\n",
      "# r^2 (goodness) is quite good!\n",
      "print(res.rsquared)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "0.997271383932\n"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# predict prize pool until the international starts\n",
      "predict_range = pd.date_range('05/09/2014', '07/08/2014', freq='D')\n",
      "predict = pd.DataFrame(res.predict({\"Day\": list(range(len(predict_range)))}), index=range(len(predict_range)), columns=['Predict'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# merge data sets and add time series to it\n",
      "combined = data.merge(predict, left_index=True, right_index=True, how='outer')\n",
      "combined.index = pd.date_range('05/09/2014', periods=len(predict_range), freq='D')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# daily predictions\n",
      "combined[len(standings):]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>Prize</th>\n",
        "      <th>Predict</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>2014-05-21</th>\n",
        "      <td> 6.077</td>\n",
        "      <td> 6.039223</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-22</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.184649</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-23</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.319292</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-24</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.444642</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-25</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.561899</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-26</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.672045</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-27</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.775893</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-28</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.874126</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-29</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 6.967318</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-30</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.055962</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-05-31</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.140482</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-01</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.221245</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-02</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.298569</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-03</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.372737</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-04</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.443995</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-05</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.512564</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-06</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.578638</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-07</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.642394</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-08</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.703988</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-09</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.763562</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-10</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.821245</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-11</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.877152</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-12</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.931391</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-13</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 7.984057</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-14</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.035239</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-15</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.085019</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-16</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.133471</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-17</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.180665</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-18</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.226664</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-19</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.271527</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-20</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.315308</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-21</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.358060</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-22</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.399828</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-23</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.440658</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-24</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.480590</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-25</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.519664</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-26</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.557915</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-27</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.595377</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-28</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.632083</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-29</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.668061</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-06-30</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.703341</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-01</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.737949</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-02</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.771909</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-03</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.805247</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-04</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.837984</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-05</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.870141</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-06</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.901740</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-07</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.932798</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2014-07-08</th>\n",
        "      <td>   NaN</td>\n",
        "      <td> 8.963334</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>49 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "            Prize   Predict\n",
        "2014-05-21  6.077  6.039223\n",
        "2014-05-22    NaN  6.184649\n",
        "2014-05-23    NaN  6.319292\n",
        "2014-05-24    NaN  6.444642\n",
        "2014-05-25    NaN  6.561899\n",
        "2014-05-26    NaN  6.672045\n",
        "2014-05-27    NaN  6.775893\n",
        "2014-05-28    NaN  6.874126\n",
        "2014-05-29    NaN  6.967318\n",
        "2014-05-30    NaN  7.055962\n",
        "2014-05-31    NaN  7.140482\n",
        "2014-06-01    NaN  7.221245\n",
        "2014-06-02    NaN  7.298569\n",
        "2014-06-03    NaN  7.372737\n",
        "2014-06-04    NaN  7.443995\n",
        "2014-06-05    NaN  7.512564\n",
        "2014-06-06    NaN  7.578638\n",
        "2014-06-07    NaN  7.642394\n",
        "2014-06-08    NaN  7.703988\n",
        "2014-06-09    NaN  7.763562\n",
        "2014-06-10    NaN  7.821245\n",
        "2014-06-11    NaN  7.877152\n",
        "2014-06-12    NaN  7.931391\n",
        "2014-06-13    NaN  7.984057\n",
        "2014-06-14    NaN  8.035239\n",
        "2014-06-15    NaN  8.085019\n",
        "2014-06-16    NaN  8.133471\n",
        "2014-06-17    NaN  8.180665\n",
        "2014-06-18    NaN  8.226664\n",
        "2014-06-19    NaN  8.271527\n",
        "2014-06-20    NaN  8.315308\n",
        "2014-06-21    NaN  8.358060\n",
        "2014-06-22    NaN  8.399828\n",
        "2014-06-23    NaN  8.440658\n",
        "2014-06-24    NaN  8.480590\n",
        "2014-06-25    NaN  8.519664\n",
        "2014-06-26    NaN  8.557915\n",
        "2014-06-27    NaN  8.595377\n",
        "2014-06-28    NaN  8.632083\n",
        "2014-06-29    NaN  8.668061\n",
        "2014-06-30    NaN  8.703341\n",
        "2014-07-01    NaN  8.737949\n",
        "2014-07-02    NaN  8.771909\n",
        "2014-07-03    NaN  8.805247\n",
        "2014-07-04    NaN  8.837984\n",
        "2014-07-05    NaN  8.870141\n",
        "2014-07-06    NaN  8.901740\n",
        "2014-07-07    NaN  8.932798\n",
        "2014-07-08    NaN  8.963334\n",
        "\n",
        "[49 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# plot\n",
      "combined.plot(legend=True)\n",
      "title(\"Predicted Prize Pool\")\n",
      "ylabel(\"Prize in Mio USD\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "<matplotlib.text.Text at 0x7faed68bb950>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAsYAAAJACAYAAACOgaBwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxRgAAACQRDEGAAAAJFGMAQAAAEnS/wej+IvgpbaDfAAAAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7faed6908650>"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# when do we reach 8 mil?\n",
      "np.argmax(combined['Predict'] > 8)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "Timestamp('2014-06-14 00:00:00', tz=None)"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Juhu! On the 14th of Juni we should reach 8 mil!!!"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}