willettk/bridle_trails.ipynb

## bridle_trails.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Bridle Trails 50K pairs relay, 2019"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "from matplotlib import pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load data from Ultrasignup for all registered teams as of 1/3/2019. \n",
    "\n",
    "http://ultrasignup.com/relay/teams.aspx?did=62292"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 244,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>team_name</th>\n",
       "      <th>name</th>\n",
       "      <th>gender</th>\n",
       "      <th>rank</th>\n",
       "      <th>age_rank</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Bye Felicia</td>\n",
       "      <td>Mia Brooks</td>\n",
       "      <td>F</td>\n",
       "      <td>71.92</td>\n",
       "      <td>84.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bye Felicia</td>\n",
       "      <td>Katelyn Doran</td>\n",
       "      <td>F</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Et tu, brut IPA?</td>\n",
       "      <td>Kyle Willett</td>\n",
       "      <td>M</td>\n",
       "      <td>76.50</td>\n",
       "      <td>80.78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Et tu, brut IPA?</td>\n",
       "      <td>Kristoffer Jonson</td>\n",
       "      <td>M</td>\n",
       "      <td>71.46</td>\n",
       "      <td>72.85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>GinJen</td>\n",
       "      <td>Virginia Reinert</td>\n",
       "      <td>F</td>\n",
       "      <td>79.49</td>\n",
       "      <td>85.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>GinJen</td>\n",
       "      <td>Jenny Easterberg</td>\n",
       "      <td>F</td>\n",
       "      <td>94.75</td>\n",
       "      <td>97.08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Mathletes</td>\n",
       "      <td>Mike Rowell</td>\n",
       "      <td>M</td>\n",
       "      <td>69.94</td>\n",
       "      <td>74.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Mathletes</td>\n",
       "      <td>Paul Raff</td>\n",
       "      <td>M</td>\n",
       "      <td>63.36</td>\n",
       "      <td>63.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Pony Up</td>\n",
       "      <td>Keelin Patillo</td>\n",
       "      <td>M</td>\n",
       "      <td>82.64</td>\n",
       "      <td>91.88</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Pony Up</td>\n",
       "      <td>Nathan Schaeffer</td>\n",
       "      <td>M</td>\n",
       "      <td>65.28</td>\n",
       "      <td>68.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Shrek and the Donkey</td>\n",
       "      <td>Lisa Holste</td>\n",
       "      <td>F</td>\n",
       "      <td>82.00</td>\n",
       "      <td>99.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Shrek and the Donkey</td>\n",
       "      <td>Ross Gilbert</td>\n",
       "      <td>M</td>\n",
       "      <td>79.85</td>\n",
       "      <td>91.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Tri and Trail</td>\n",
       "      <td>Laura Morrissey</td>\n",
       "      <td>F</td>\n",
       "      <td>77.94</td>\n",
       "      <td>80.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Tri and Trail</td>\n",
       "      <td>Sean Miller</td>\n",
       "      <td>M</td>\n",
       "      <td>56.41</td>\n",
       "      <td>60.73</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               team_name               name gender   rank  age_rank\n",
       "0            Bye Felicia         Mia Brooks      F  71.92     84.15\n",
       "1            Bye Felicia      Katelyn Doran      F   0.00      0.00\n",
       "2       Et tu, brut IPA?       Kyle Willett      M  76.50     80.78\n",
       "3       Et tu, brut IPA?  Kristoffer Jonson      M  71.46     72.85\n",
       "4                 GinJen   Virginia Reinert      F  79.49     85.38\n",
       "5                 GinJen   Jenny Easterberg      F  94.75     97.08\n",
       "6              Mathletes        Mike Rowell      M  69.94     74.77\n",
       "7              Mathletes          Paul Raff      M  63.36     63.36\n",
       "8                Pony Up     Keelin Patillo      M  82.64     91.88\n",
       "9                Pony Up   Nathan Schaeffer      M  65.28     68.72\n",
       "10  Shrek and the Donkey        Lisa Holste      F  82.00     99.35\n",
       "11  Shrek and the Donkey       Ross Gilbert      M  79.85     91.17\n",
       "12         Tri and Trail    Laura Morrissey      F  77.94     80.76\n",
       "13         Tri and Trail        Sean Miller      M  56.41     60.73"
      ]
     },
     "execution_count": 244,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"bridle_trails.txt\")\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot the average Ultrasignup rank for each team. This should supposedly predict the finish order."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 268,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig,ax = plt.subplots(1,1,figsize=(10,6))\n",
    "order = df.groupby(\"team_name\")[\"rank\"].mean().sort_values().index\n",
    "g = sns.boxplot(x=\"team_name\",y=\"rank\",data=df,order=order,ax=ax)\n",
    "g.set_ylim(0,100)\n",
    "g.set_xlabel(\"50K pairs relay teams\")\n",
    "g.set_ylabel(\"Ultrasignup gender-specific rank\")\n",
    "plt.xticks(rotation=45);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So according to this, **GinJen** would be expected to win and **Mathletes** last (the second racer for **Bye Felicia** has no Ultrasignup results and thus no rank). However, ranks on Ultrasignup are *gender-specific*. It's not clear that there are separate categories (all-male, all-female, and mixed) for the pairs relay. Either for that reason or out of idle curiosity, let's try to estimate how well each team will do overall in competition. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Extremely simple way; use some past race data to look at the relationship between gender-specific rank (really the percentile) and overall rank among finishers. Eyeball a transformation between the two using the lowest-order polynomial that seems reasonable. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Sample data taken from the Bridle Trails 10M individual race in 2017."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "79 total finishers (45 M, 34 F)\n"
     ]
    }
   ],
   "source": [
    "# http://ultrasignup.com/results_event.aspx?did=42657\n",
    "\n",
    "k = pd.read_table('bt25k.txt')\n",
    "print(\"{} total finishers ({} M, {} F)\".format(len(k),sum(k['gender'] == 'M'),sum(k['gender'] == 'F')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 271,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kf = k[k.gender == 'F']\n",
    "perc_kf = 1 - ((kf['gp'] - 1)/ len(kf))\n",
    "perc_overall = 1 - ((kf.index)/ len(k))\n",
    "\n",
    "# A second-degree polynomial looks like it fits the data OK without too much overfitting\n",
    "p = np.polyfit(perc_kf,perc_overall,2)\n",
    "\n",
    "fig,ax = plt.subplots(1,1,figsize=(6,6))\n",
    "ax.scatter(perc_kf,perc_overall)\n",
    "ax.plot(np.linspace(0,1,10),np.polyval(p,np.linspace(0,1,10)),color='r')\n",
    "ax.plot(np.linspace(0,1,10),np.linspace(0,1,10),color='grey',ls='-.')\n",
    "\n",
    "ax.set_xlim(0,1)\n",
    "ax.set_ylim(0,1)\n",
    "ax.set_xlabel(\"Percentile among female finishers\")\n",
    "ax.set_ylabel(\"Percentile among overall finishers\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add the gender-adjusted rank as a new column in the dataframe and plot the new results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 253,
   "metadata": {},
   "outputs": [],
   "source": [
    "adjusted = df['rank'].copy()\n",
    "f = df['gender'] == \"F\"\n",
    "\n",
    "adjusted.loc[f] = pd.Series(np.polyval(p,df[f]['rank'] / 100.)*100,index=(df[f]).index)\n",
    "df['adjusted_rank'] = adjusted"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 267,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig,ax = plt.subplots(1,1,figsize=(10,6))\n",
    "order = df.groupby(\"team_name\")[\"adjusted_rank\"].mean().sort_values()\n",
    "g = sns.boxenplot(x=\"team_name\",y=\"adjusted_rank\",data=df,order=order.index,ax=ax)\n",
    "g.set_ylim(0,100)\n",
    "g.set_xlabel(\"50K pairs relay teams\")\n",
    "g.set_ylabel(\"Adjusted overall rank\")\n",
    "plt.xticks(rotation=45);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 260,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>adjusted_rank</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>team_name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Bye Felicia</th>\n",
       "      <td>28.378935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tri and Trail</th>\n",
       "      <td>58.500314</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mathletes</th>\n",
       "      <td>66.650000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GinJen</th>\n",
       "      <td>71.696342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Shrek and the Donkey</th>\n",
       "      <td>72.559569</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pony Up</th>\n",
       "      <td>73.960000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Et tu, brut IPA?</th>\n",
       "      <td>73.980000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      adjusted_rank\n",
       "team_name                          \n",
       "Bye Felicia               28.378935\n",
       "Tri and Trail             58.500314\n",
       "Mathletes                 66.650000\n",
       "GinJen                    71.696342\n",
       "Shrek and the Donkey      72.559569\n",
       "Pony Up                   73.960000\n",
       "Et tu, brut IPA?          73.980000"
      ]
     },
     "execution_count": 260,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(order)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After doing an extremely crude adjustment for gender placing, the top four teams are now extremely closely matched. However, **Et tu, brut IPA?** is now projected to (barely) finish first overall."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:anaconda]",
   "language": "python",
   "name": "conda-env-anaconda-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}