muneebalam/scrapenhl2

View on GitHub
examples/YTD and ROY CF%.ipynb

Summary

Maintainability
Test Coverage
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The purpose of this notebook is to calculate CF% through a certain number of games, and for the rest of the season's games."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from pylab import *\n",
    "%matplotlib inline\n",
    "from pyarrow import ArrowIOError\n",
    "\n",
    "from scrapenhl2.scrape import teams, team_info, schedules\n",
    "from scrapenhl2.manipulate import manipulate as manip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>GameNum</th>\n",
       "      <th>YTD_CF%</th>\n",
       "      <th>ROY_CF%</th>\n",
       "      <th>Season</th>\n",
       "      <th>Team</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.487179</td>\n",
       "      <td>0.522637</td>\n",
       "      <td>2010</td>\n",
       "      <td>NJD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>0.475000</td>\n",
       "      <td>0.523451</td>\n",
       "      <td>2010</td>\n",
       "      <td>NJD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>0.477679</td>\n",
       "      <td>0.523874</td>\n",
       "      <td>2010</td>\n",
       "      <td>NJD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>0.482650</td>\n",
       "      <td>0.524342</td>\n",
       "      <td>2010</td>\n",
       "      <td>NJD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0.501305</td>\n",
       "      <td>0.523578</td>\n",
       "      <td>2010</td>\n",
       "      <td>NJD</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   GameNum   YTD_CF%   ROY_CF%  Season Team\n",
       "0        1  0.487179  0.522637    2010  NJD\n",
       "1        2  0.475000  0.523451    2010  NJD\n",
       "2        3  0.477679  0.523874    2010  NJD\n",
       "3        4  0.482650  0.524342    2010  NJD\n",
       "4        5  0.501305  0.523578    2010  NJD"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "generate = False\n",
    "fname = '/Users/muneebalam/Desktop/team_game_data.csv'\n",
    "\n",
    "if generate:\n",
    "    team_dfs = []\n",
    "    for season in range(2010, 2018):\n",
    "        for team in schedules.get_teams_in_season(season):\n",
    "\n",
    "            # Read in the PBP and get CF and CA counts by game, regular season only\n",
    "            try:\n",
    "                df = teams.get_team_pbp(season, team).query('Game < 30001')\n",
    "            except ArrowIOError:\n",
    "                continue\n",
    "            df = manip.filter_for_five_on_five(manip.filter_for_corsi(df))\n",
    "            df.loc[:, 'CFCA'] = df.Team.apply(lambda x: 'CF' if x == team_info.team_as_id(team) else 'CA')\n",
    "            grouped = df[['Game', 'CFCA']].assign(Count=1).groupby(['Game', 'CFCA'], as_index=False).count()\n",
    "            grouped = grouped.sort_values('Game') \\\n",
    "                .pivot_table(index='Game', columns='CFCA', values='Count')\n",
    "\n",
    "            # Add in game number\n",
    "            grouped.loc[:, 'GameNum'] = 1\n",
    "            grouped.loc[:, 'GameNum'] = grouped.GameNum.cumsum()\n",
    "\n",
    "            # Calculate cumulative sums\n",
    "            grouped.loc[:, 'YTD_CF'] = grouped['CF'].cumsum()\n",
    "            grouped.loc[:, 'YTD_CA'] = grouped['CA'].cumsum()\n",
    "            grouped.loc[:, 'YTD_CF%'] = grouped['YTD_CF'] / (grouped['YTD_CF'] + grouped['YTD_CA'])\n",
    "\n",
    "            # Get EOY numbers and subtract\n",
    "            totals = grouped.max()\n",
    "\n",
    "            grouped.loc[:, 'ROY_CF'] = totals['YTD_CF'] - grouped['YTD_CF']\n",
    "            grouped.loc[:, 'ROY_CA'] = totals['YTD_CA'] - grouped['YTD_CA']\n",
    "            grouped.loc[:, 'ROY_CF%'] = grouped['ROY_CF'] / (grouped['ROY_CF'] + grouped['ROY_CA'])\n",
    "\n",
    "            team_dfs.append(grouped[['GameNum', 'YTD_CF%', 'ROY_CF%']].assign(Season=season, \n",
    "                                                                              Team=team_info.team_as_str(team)))\n",
    "        print('Done with', season)\n",
    "    data = pd.concat(team_dfs)\n",
    "    data.to_csv(fname, index=False)\n",
    "data = pd.read_csv(fname)\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we make some plots and calculate some figures. For example, here's how the correlation (Pearson's r) changes by game number:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x11b6828d0>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11ad270f0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Drop short season and current season, and get correlations\n",
    "data2 = data[(data.Season != 2012) & (data.Season != 2017)].dropna()\n",
    "corrs = data2.drop({'Season', 'Team'}, axis=1).groupby('GameNum').corr().drop('ROY_CF%', axis=1)\n",
    "corrs = corrs[corrs['YTD_CF%'] < 1]\n",
    "corrs = corrs.reset_index().drop('level_1', axis=1).rename(columns={'YTD_CF%': 'r'})\n",
    "plot(corrs.GameNum, corrs.r)\n",
    "xlabel('Game number')\n",
    "ylabel('R')\n",
    "title('Correlation between YTD CF% and ROY CF%')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here's how the slope changes by game:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x122f4da58>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEWCAYAAABv+EDhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrEE5AZiZNajvl5gzLZCuZWQAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1191918d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Now look at the slope\n",
    "from scipy.stats import linregress\n",
    "def get_slope(df):\n",
    "    m, b, r, p, e = linregress(df['YTD_CF%'], df['ROY_CF%'])\n",
    "    return m\n",
    "plot(data2.groupby('GameNum').apply(get_slope), label = 'Slope')\n",
    "xlabel('Game Number')\n",
    "\n",
    "plot(corrs.r, label = 'R')\n",
    "title('Correlation between YTD CF% and ROY CF%')\n",
    "legend(loc=2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You'll note that although the predictivity (as measured by r) is best at 40 games, the slope is still not 1--meaning we expect some regression still.\n",
    "\n",
    "You can see that in the scatterplot below (with the best-fit and 1:1 lines included for reference):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x123526be0>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYwAAAEWCAYAAAB1xKBvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxhhjfGIJwxhjjE/+H6psxg3cSiRhAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x123471908>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tmp = data2[data2.GameNum == 40]\n",
    "x = 'YTD_CF%'\n",
    "y = 'ROY_CF%'\n",
    "\n",
    "scatter(tmp[x], tmp[y], label='_nolegend')\n",
    "xlabel('Season to date CF%')\n",
    "ylabel('Rest of season CF%')\n",
    "title('YTD and ROY CF% at game 40')\n",
    "\n",
    "m, b, r, p, e = linregress(tmp[x], tmp[y])\n",
    "xs = arange(0, 1, 0.01)\n",
    "ys = m * xs + b\n",
    "xlimits = xlim()\n",
    "ylimits = ylim()\n",
    "\n",
    "plot(xs, ys, color='k', ls='--', label='Best slope')\n",
    "plot(xs, xs, color='k', ls=':', label='Slope=1')\n",
    "xlim(*xlimits)\n",
    "ylim(*ylimits)\n",
    "legend(loc=2)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}